Compare commits

..
Author SHA1 Message Date
l0ng-ai bc42133a36 fix(debugger): keep the selected tab when a step finishes
Every pause brought Threads & Variables to the front, so stepping from the
Console tab switched away from the output after each Step Over. Only a stop
at a breakpoint, exception or pause request does that now; finishing a step
keeps the tab the user is on.

Refs #2494
2026-11-10 23:22:32 +08:00
1007 changed files with 4156 additions and 68268 deletions

No files matched your search

-2
View File
@@ -1,2 +0,0 @@
custom:
- https://github.com/l0ng-ai/openidea#sponsor
-3
View File
@@ -3,6 +3,3 @@ contact_links:
- name: Download the latest release
url: https://github.com/l0ng-ai/openidea/releases/latest
about: Many problems are already fixed. Please check the latest version before reporting.
- name: Report a security vulnerability
url: https://github.com/l0ng-ai/openidea/security/advisories/new
about: Please report security problems privately, not in a public issue.
Binary file not shown.

Before

Width:  |  Height:  |  Size: 70 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 97 KiB

+1 -22
View File
@@ -251,28 +251,7 @@ jobs:
core.setFailed(`latest.json would miss ${missing.join(", ")}`);
return;
}
// The update's notes: the release body without its Download section. That
// section only matters on the release page, and What's new follows it.
const { data: release } = await github.rest.repos.getRelease({ owner, repo, release_id });
const withoutDownloadSection = (body) => {
const kept = [];
let skip = 0;
for (const line of body.split(/\r?\n/)) {
const heading = /^(#{1,6})\s+(.*)$/.exec(line);
if (heading) {
const level = heading[1].length;
if (!skip && level <= 3 && /^download$/i.test(heading[2].trim())) {
skip = level;
continue;
}
if (skip && level <= skip) skip = 0;
}
if (!skip) kept.push(line);
}
return kept.join("\n").trim();
};
const notes = withoutDownloadSection(String(release.body ?? ""));
const manifest = { version: tag.replace(/^v/, ""), notes, pub_date: new Date().toISOString(), platforms };
const manifest = { version: tag.replace(/^v/, ""), notes: "", pub_date: new Date().toISOString(), platforms };
const old = assets.find((a) => a.name === "latest.json");
if (old) await github.rest.repos.deleteReleaseAsset({ owner, repo, asset_id: old.id });
await github.rest.repos.uploadReleaseAsset({
Generated
+120 -162
View File
@@ -1522,7 +1522,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d045de693cb712d0b22c6a64be5b953f67b3ce00ab5ad3dd5d8b441886ab8e1a"
dependencies = [
"quote",
"syn 3.0.9",
"syn 2.0.119",
]
[[package]]
@@ -1578,6 +1578,16 @@ dependencies = [
"syn 2.0.119",
]
[[package]]
name = "darling"
version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a01d95850c592940db9b8194bc39f4bc0e89dee5c4265e4b1807c34a9aba453c"
dependencies = [
"darling_core 0.13.4",
"darling_macro 0.13.4",
]
[[package]]
name = "darling"
version = "0.23.0"
@@ -1598,6 +1608,20 @@ dependencies = [
"darling_macro 0.24.1",
]
[[package]]
name = "darling_core"
version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "859d65a907b6852c9361e3185c862aae7fafd2887876799fa55f5f99dc40d610"
dependencies = [
"fnv",
"ident_case",
"proc-macro2",
"quote",
"strsim 0.10.0",
"syn 1.0.109",
]
[[package]]
name = "darling_core"
version = "0.23.0"
@@ -1607,7 +1631,7 @@ dependencies = [
"ident_case",
"proc-macro2",
"quote",
"strsim",
"strsim 0.11.1",
"syn 2.0.119",
]
@@ -1620,10 +1644,21 @@ dependencies = [
"ident_case",
"proc-macro2",
"quote",
"strsim",
"strsim 0.11.1",
"syn 3.0.9",
]
[[package]]
name = "darling_macro"
version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c972679f83bdf9c42bd905396b6c3588a843a17f0f16dfcfa3e2c5d57441835"
dependencies = [
"darling_core 0.13.4",
"quote",
"syn 1.0.109",
]
[[package]]
name = "darling_macro"
version = "0.23.0"
@@ -2650,7 +2685,7 @@ checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
dependencies = [
"cfg-if",
"libc",
"wasi 0.11.1+wasi-snapshot-preview1",
"wasi",
]
[[package]]
@@ -4145,7 +4180,7 @@ checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954"
[[package]]
name = "ide-agent"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"encoding_rs",
@@ -4169,7 +4204,7 @@ dependencies = [
[[package]]
name = "ide-analysis"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ast-grep-core",
"ide-core",
@@ -4183,7 +4218,7 @@ dependencies = [
[[package]]
name = "ide-android"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"serde",
@@ -4194,7 +4229,7 @@ dependencies = [
[[package]]
name = "ide-build"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"chardetng",
@@ -4212,7 +4247,7 @@ dependencies = [
[[package]]
name = "ide-cli"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dirs 6.0.0",
"serde",
@@ -4226,7 +4261,7 @@ dependencies = [
[[package]]
name = "ide-clipboard"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"gtk",
"objc2 0.6.5",
@@ -4236,7 +4271,7 @@ dependencies = [
[[package]]
name = "ide-core"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"encoding_rs",
@@ -4253,7 +4288,7 @@ dependencies = [
[[package]]
name = "ide-coverage"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"ide-run",
@@ -4267,20 +4302,15 @@ dependencies = [
[[package]]
name = "ide-dap"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"futures",
"ide-core",
"ide-heap",
"ide-jdwp",
"ide-jsonrpc",
"ide-jvm-attach",
"ide-jvm-inspect",
"ide-language",
"libc",
"memchr",
"parking_lot",
"percent-encoding",
"portable-pty",
"serde",
"serde_json",
@@ -4293,7 +4323,7 @@ dependencies = [
[[package]]
name = "ide-db"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"bb8",
"blake3",
@@ -4303,7 +4333,7 @@ dependencies = [
"ide-core",
"ide-http",
"ide-ssh",
"oracledb",
"oracle",
"parking_lot",
"reqwest",
"rustls",
@@ -4323,7 +4353,7 @@ dependencies = [
[[package]]
name = "ide-docker"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"serde",
@@ -4336,11 +4366,10 @@ dependencies = [
[[package]]
name = "ide-extension"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"base64 0.22.1",
"blake3",
"dunce",
"ed25519-dalek",
"ide-core",
"parking_lot",
@@ -4357,7 +4386,7 @@ dependencies = [
[[package]]
name = "ide-fonts"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"objc2-core-foundation",
"objc2-core-text",
@@ -4369,7 +4398,7 @@ dependencies = [
[[package]]
name = "ide-github"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"ide-vcs",
@@ -4380,27 +4409,9 @@ dependencies = [
"which",
]
[[package]]
name = "ide-heap"
version = "0.1.42"
dependencies = [
"criterion",
"ide-core",
"libc",
"memmap2",
"proptest",
"serde",
"serde_json",
"specta",
"tempfile",
"thiserror 2.0.21",
"tracing",
"uuid",
]
[[package]]
name = "ide-host"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"base64 0.22.1",
"blake3",
@@ -4420,11 +4431,9 @@ dependencies = [
"ide-db",
"ide-docker",
"ide-extension",
"ide-heap",
"ide-http",
"ide-index",
"ide-jsonrpc",
"ide-jvm-attach",
"ide-language",
"ide-lsp",
"ide-mcp",
@@ -4432,7 +4441,6 @@ dependencies = [
"ide-plugin",
"ide-remote",
"ide-run",
"ide-scaffold",
"ide-sdk",
"ide-search",
"ide-spell",
@@ -4469,10 +4477,9 @@ dependencies = [
[[package]]
name = "ide-http"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"ide-vfs",
"parking_lot",
"reqwest",
"rustls",
@@ -4488,7 +4495,7 @@ dependencies = [
[[package]]
name = "ide-index"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"criterion",
@@ -4508,21 +4515,9 @@ dependencies = [
"tracing",
]
[[package]]
name = "ide-jdwp"
version = "0.1.42"
dependencies = [
"ide-jvm-inspect",
"proptest",
"tempfile",
"thiserror 2.0.21",
"tokio",
"tracing",
]
[[package]]
name = "ide-jsonrpc"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"encoding_rs",
"futures",
@@ -4537,29 +4532,9 @@ dependencies = [
"tracing",
]
[[package]]
name = "ide-jvm-attach"
version = "0.1.42"
dependencies = [
"libc",
"tempfile",
"thiserror 2.0.21",
]
[[package]]
name = "ide-jvm-inspect"
version = "0.1.42"
dependencies = [
"futures",
"serde",
"serde_json",
"specta",
"thiserror 2.0.21",
]
[[package]]
name = "ide-language"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"criterion",
@@ -4615,14 +4590,13 @@ dependencies = [
[[package]]
name = "ide-lsp"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"futures",
"globset",
"ide-core",
"ide-jsonrpc",
"ide-jvm-inspect",
"ide-language",
"ide-text",
"ide-vfs",
@@ -4642,7 +4616,7 @@ dependencies = [
[[package]]
name = "ide-mcp"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"bytes",
"dunce",
@@ -4661,7 +4635,7 @@ dependencies = [
[[package]]
name = "ide-notebook"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"futures",
"ide-core",
@@ -4684,7 +4658,7 @@ dependencies = [
[[package]]
name = "ide-plugin"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"dunce",
@@ -4707,7 +4681,7 @@ dependencies = [
[[package]]
name = "ide-profiler"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"ide-run",
@@ -4720,7 +4694,7 @@ dependencies = [
[[package]]
name = "ide-remote"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"globset",
@@ -4739,7 +4713,7 @@ dependencies = [
[[package]]
name = "ide-run"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"encoding_rs",
@@ -4761,25 +4735,9 @@ dependencies = [
"zip",
]
[[package]]
name = "ide-scaffold"
version = "0.1.42"
dependencies = [
"ide-core",
"ide-tools",
"ide-vcs",
"insta",
"serde",
"serde_json",
"specta",
"tempfile",
"toml 0.9.12+spec-1.1.0",
"tracing",
]
[[package]]
name = "ide-sdk"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dunce",
"ide-core",
@@ -4799,10 +4757,9 @@ dependencies = [
[[package]]
name = "ide-search"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"criterion",
"encoding_rs",
"globset",
"grep-matcher",
"grep-regex",
@@ -4820,7 +4777,7 @@ dependencies = [
[[package]]
name = "ide-spell"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"parking_lot",
@@ -4833,7 +4790,7 @@ dependencies = [
[[package]]
name = "ide-ssh"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"dirs 6.0.0",
"flate2",
@@ -4854,7 +4811,7 @@ dependencies = [
[[package]]
name = "ide-syntax"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"ide-language",
@@ -4869,7 +4826,7 @@ dependencies = [
[[package]]
name = "ide-terminal"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"libc",
@@ -4882,7 +4839,7 @@ dependencies = [
[[package]]
name = "ide-text"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"criterion",
"ide-core",
@@ -4895,7 +4852,7 @@ dependencies = [
[[package]]
name = "ide-tools"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"flate2",
"hex",
@@ -4916,7 +4873,7 @@ dependencies = [
[[package]]
name = "ide-vcs"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"dunce",
@@ -4937,7 +4894,7 @@ dependencies = [
[[package]]
name = "ide-vfs"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"chardetng",
"dunce",
@@ -4961,7 +4918,7 @@ dependencies = [
[[package]]
name = "ide-web"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"ide-core",
"open",
@@ -4977,7 +4934,7 @@ dependencies = [
[[package]]
name = "ide-workspace"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"blake3",
"dunce",
@@ -5794,7 +5751,7 @@ checksum = "1788edb87fdc09c7e26304471e2f5be8cdefb1b6930d6e3985fc02ff53bf86ee"
dependencies = [
"libc",
"log",
"wasi 0.11.1+wasi-snapshot-preview1",
"wasi",
"windows-sys 0.61.2",
]
@@ -6530,6 +6487,15 @@ dependencies = [
"memchr",
]
[[package]]
name = "odpic-sys"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "920b5474a5128a9f0232df5a0ffc50aaa5b077b29b8b06ab0131985ac82793ed"
dependencies = [
"cc",
]
[[package]]
name = "once_cell"
version = "1.21.4"
@@ -6555,7 +6521,7 @@ dependencies = [
[[package]]
name = "openidea"
version = "0.1.42"
version = "0.1.40"
dependencies = [
"base64 0.22.1",
"blake3",
@@ -6589,7 +6555,6 @@ dependencies = [
"ide-profiler",
"ide-remote",
"ide-run",
"ide-scaffold",
"ide-sdk",
"ide-search",
"ide-spell",
@@ -6644,24 +6609,29 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d"
[[package]]
name = "oracledb"
version = "26.0.0-beta.5"
name = "oracle"
version = "0.6.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "27b98c7346f2bb5169ec4b2d4f066fb616529ac766b395440c5019fe88d1ef45"
checksum = "3db40fe6e4df881b683691ade5ef1f7b1afd52aefa115581f7b92855524d7ec0"
dependencies = [
"aes",
"base16ct",
"base64ct",
"cbc",
"chrono",
"pbkdf2",
"pkcs8",
"rand 0.10.3",
"rustls",
"sha2 0.11.1",
"uuid",
"webpki-roots",
"whoami",
"cc",
"odpic-sys",
"once_cell",
"oracle_procmacro",
"paste",
"rustversion",
]
[[package]]
name = "oracle_procmacro"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ad247f3421d57de56a0d0408d3249d4b1048a522be2013656d92f022c3d8af27"
dependencies = [
"darling 0.13.4",
"proc-macro2",
"quote",
"syn 1.0.109",
]
[[package]]
@@ -7796,9 +7766,9 @@ dependencies = [
[[package]]
name = "rustix"
version = "1.1.6"
version = "1.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5e76742e5294153d4dde1207dbec5bdd81eef6fabdc0d2118babadabfd858aa"
checksum = "891efababe418670775f199f0d233d84843c227a0949a883ce15b37c78d6629d"
dependencies = [
"bitflags 2.13.2",
"errno",
@@ -8948,6 +8918,12 @@ dependencies = [
"unicode-properties",
]
[[package]]
name = "strsim"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
[[package]]
name = "strsim"
version = "0.11.1"
@@ -8984,6 +8960,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
@@ -9206,7 +9183,7 @@ dependencies = [
"serde",
"serde_json",
"static_vcruntime",
"strsim",
"strsim 0.11.1",
"tauri-utils",
"tauri-winres",
"walkdir",
@@ -10746,15 +10723,6 @@ version = "0.11.1+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
[[package]]
name = "wasi"
version = "0.14.7+wasi-0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "883478de20367e224c0090af9cf5f9fa85bed63a95c1abf3afc5c083ebc06e8c"
dependencies = [
"wasip2",
]
[[package]]
name = "wasip2"
version = "1.0.4+wasi-0.2.12"
@@ -10764,15 +10732,6 @@ dependencies = [
"wit-bindgen",
]
[[package]]
name = "wasite"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "66fe902b4a6b8028a753d5424909b764ccf79b7a209eac9bf97e59cda9f71a42"
dependencies = [
"wasi 0.14.7+wasi-0.2.4",
]
[[package]]
name = "wasm-bindgen"
version = "0.2.129"
@@ -11356,7 +11315,6 @@ dependencies = [
"libc",
"libredox",
"objc2-system-configuration",
"wasite",
"web-sys",
]
+2 -9
View File
@@ -5,7 +5,7 @@ members = ["crates/*", "src-tauri"]
exclude = ["sdk", "plugins"]
[workspace.package]
version = "0.1.42"
version = "0.1.40"
edition = "2024"
rust-version = "1.96"
license = "Apache-2.0"
@@ -43,15 +43,10 @@ ide-ssh = { path = "crates/ide-ssh" }
ide-remote = { path = "crates/ide-remote" }
ide-host = { path = "crates/ide-host" }
ide-mcp = { path = "crates/ide-mcp" }
ide-scaffold = { path = "crates/ide-scaffold" }
ide-notebook = { path = "crates/ide-notebook" }
ide-extension = { path = "crates/ide-extension" }
ide-plugin = { path = "crates/ide-plugin" }
ide-cli = { path = "crates/ide-cli" }
ide-jvm-attach = { path = "crates/ide-jvm-attach" }
ide-jvm-inspect = { path = "crates/ide-jvm-inspect" }
ide-jdwp = { path = "crates/ide-jdwp" }
ide-heap = { path = "crates/ide-heap" }
# serialization & IPC typing
serde = { version = "1", features = ["derive"] }
@@ -87,7 +82,6 @@ trash = "5"
blake3 = "1"
dunce = "1"
dirs = "6"
memmap2 = "0.9"
zip = { version = "9.2.3", default-features = false, features = ["deflate"] }
# search, index, language
@@ -112,8 +106,7 @@ rustls-platform-verifier = "0.7"
# Until SQLx releases its libsqlite3-sys 0.39 update (RUSTSEC-2026-0459).
sqlx = { version = "0.9", git = "https://github.com/transact-rs/sqlx", rev = "10462fa4414c6c7f1ed1d39bb31678e3b726878c", default-features = false, features = ["runtime-tokio", "tls-rustls-ring-webpki", "sqlite", "postgres", "mysql"] }
tiberius = { version = "0.13", default-features = false, features = ["tds73", "rustls", "sql-browser-tokio"] }
# Pure-Rust thin Oracle driver; pinned to the beta until it stabilizes.
oracledb = "=26.0.0-beta.5"
oracle = { version = "0.6", default-features = false }
bb8 = "0.9"
uuid = { version = "1", features = ["v4"] }
# OS credential stores
-13
View File
@@ -19,8 +19,6 @@
<a href="#plugins">Plugins</a>
&nbsp;·&nbsp;
<a href="#community">Community</a>
&nbsp;·&nbsp;
<a href="#sponsor">Sponsor</a>
</p>
https://github.com/user-attachments/assets/234dd54c-1255-4b3a-b35c-533d78d737c0
@@ -70,17 +68,6 @@ the [official plugins](plugins/official). The plugin API is still a preview.
- Contributing: see [CONTRIBUTING.md](CONTRIBUTING.md) and the [contributor docs](https://openidea.sh/en/contribute/setup).
## Sponsor
If OpenIDEA saves you time, you can support its development with Alipay or WeChat Pay.
<table>
<tr>
<td align="center"><img src=".github/assets/sponsor-alipay.png" alt="Alipay QR code" width="200"><br>Alipay</td>
<td align="center"><img src=".github/assets/sponsor-wechat.png" alt="WeChat Pay QR code" width="200"><br>WeChat Pay</td>
</tr>
</table>
## License
[Apache 2.0](LICENSE). Bundled third-party assets are listed in [`THIRD_PARTY_LICENSES.md`](THIRD_PARTY_LICENSES.md).
-26
View File
@@ -1,26 +0,0 @@
# Security policy
## Reporting a vulnerability
Please do not report security problems in public issues, pull requests or discussions.
Report them privately through GitHub:
[Report a vulnerability](https://github.com/l0ng-ai/openidea/security/advisories/new)
(repository **Security** tab → **Report a vulnerability**). Only the maintainers can see
the report.
Include what you can of:
- the affected version, platform, and whether remote development (`openidea-server`)
or plugins are involved;
- steps to reproduce, or a proof of concept;
- the impact you expect, and any fix you suggest.
We will acknowledge the report, keep you updated in the advisory, and agree on a
disclosure date with you. Fixes are released as a new version, and the advisory is
published once users can update.
## Supported versions
Security fixes go into the latest release. Please check that the problem still occurs
there before reporting.
-6
View File
@@ -1,11 +1,5 @@
# Third-party licenses
## Project type icons
`src/ui/brands/*.svg` use the unmodified logo paths from
[Simple Icons](https://github.com/simple-icons/simple-icons), retrieved through
Iconify (`simple-icons:angular`, `simple-icons:astro`, `simple-icons:cplusplus`, `simple-icons:dart`, `simple-icons:django`, `simple-icons:dotnet`, `simple-icons:elixir`, `simple-icons:express`, `simple-icons:fastapi`, `simple-icons:flask`, `simple-icons:flutter`, `simple-icons:go`, `simple-icons:haskell`, `simple-icons:html5`, `simple-icons:kotlin`, `simple-icons:ktor`, `simple-icons:laravel`, `simple-icons:nestjs`, `simple-icons:nextdotjs`, `simple-icons:nodedotjs`, `simple-icons:nuxt`, `simple-icons:openjdk`, `simple-icons:phoenixframework`, `simple-icons:php`, `simple-icons:python`, `simple-icons:quarkus`, `simple-icons:ruby`, `simple-icons:rubyonrails`, `simple-icons:rust`, `simple-icons:scala`, `simple-icons:springboot`, `simple-icons:svelte`, `simple-icons:swift`, `simple-icons:symfony`, `simple-icons:vite`, `simple-icons:zig`) and filled with the brand colors (the standard icon grey for black logos). Licensed under [CC0 1.0 Universal](https://github.com/simple-icons/simple-icons/blob/develop/LICENSE.md).
## Project Lombok
`java/lombok/lombok-1.18.48-openidea.3.jar` contains Project Lombok v1.18.48 with the Equinox
-16
View File
@@ -164,11 +164,6 @@ impl Negotiated {
self.capabilities.pointer(&format!("/promptCapabilities/{name}")).and_then(Value::as_bool) == Some(true)
}
/// `mcpCapabilities.<name>` (`http`, `sse`).
pub fn mcp(&self, name: &str) -> bool {
self.capabilities.pointer(&format!("/mcpCapabilities/{name}")).and_then(Value::as_bool) == Some(true)
}
/// `sessionCapabilities.<name>` (`fork`, `resume`, `close`, `list`, `delete`).
pub fn session(&self, name: &str) -> bool {
self.capabilities.pointer(&format!("/sessionCapabilities/{name}")).is_some_and(|v| !v.is_null())
@@ -178,17 +173,6 @@ impl Negotiated {
pub fn meta(&self, pointer: &str) -> Option<&Value> {
self.capabilities.get("_meta")?.pointer(pointer)
}
/// First authentication method the agent can run over ACP (`type` absent or `"agent"`).
pub fn agent_auth_method(&self) -> Option<&str> {
self.auth_methods.iter().find_map(|m| {
let kind = m.get("type").and_then(Value::as_str).unwrap_or("agent");
(kind == "agent" && m.pointer("/_meta/terminal-auth").is_none())
.then(|| m.get("id").and_then(Value::as_str))
.flatten()
.filter(|id| !id.is_empty())
})
}
}
/// The client side of one agent connection: wraps the task's [`Handler`] and, once
-30
View File
@@ -135,36 +135,6 @@ fn the_shape_decides_the_version_not_the_number() {
assert_eq!((n.generation, n.load_session(), n.session("fork")), (2, false, false));
}
#[test]
fn picks_non_terminal_agent_auth_method() {
let v1 = Negotiated::from_initialize(&json!({
"protocolVersion": 1,
"authMethods": [
{ "id": "cli_login", "_meta": { "terminal-auth": { "command": "copilot", "args": ["login"] } } },
{ "id": "terminal_login", "type": "terminal", "args": ["login"] },
{ "id": "api_key", "type": "env_var" },
{ "id": "github_oauth", "name": "GitHub OAuth" }
]
}));
assert_eq!(v1.agent_auth_method(), Some("github_oauth"));
let v2 = Negotiated::from_initialize(&json!({
"protocolVersion": 2,
"info": { "name": "x", "version": "1" },
"authMethods": [
{ "type": "terminal", "methodId": "cli", "name": "CLI", "args": ["login"] },
{ "type": "agent", "methodId": "oauth", "name": "OAuth" }
]
}));
assert_eq!(v2.agent_auth_method(), Some("oauth"));
let terminal_only = Negotiated::from_initialize(&json!({
"protocolVersion": 1,
"authMethods": [{ "id": "cli", "type": "terminal", "args": ["login"] }]
}));
assert_eq!(terminal_only.agent_auth_method(), None);
}
#[test]
fn meta_and_auth_methods_pass_through() {
// The native shims advertise their extensions in `agentCapabilities._meta`.
-325
View File
@@ -1,325 +0,0 @@
//! Sessions the user started outside OpenIDEA (a terminal, another editor, the CLI):
//! scanned so they can be listed and imported as tasks instead of re-explained (#312).
//!
//! Only the native providers keep transcripts on disk in a readable form: Claude Code
//! (`<config>/projects/*/<id>.jsonl`, see `native::claude::history`) and Codex
//! (`<home>/.codex/sessions/**`, rollout files with a `session_meta` line).
use super::native::claude::history;
use serde::Serialize;
use specta::Type;
use std::io::BufRead;
use std::path::{Path, PathBuf};
/// A session on this machine that no task holds yet.
#[derive(Clone, Debug, Serialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct ExternalSession {
/// The [`crate::AgentProvider`] id that owns it (`claude`, `codex`).
pub provider: String,
/// The id resuming it names (`--resume`, `thread/resume`).
pub session_id: String,
pub title: String,
/// Where it ran, when the transcript names one.
pub cwd: Option<String>,
/// File modification time, ms since the epoch.
pub updated_ms: f64,
}
/// Modification time of `path` in ms, else 0.
fn mtime(path: &Path) -> f64 {
path.metadata()
.and_then(|m| m.modified())
.ok()
.and_then(|t| t.duration_since(std::time::UNIX_EPOCH).ok())
.map(|d| d.as_millis() as f64)
.unwrap_or(0.0)
}
/// Short display text: collapsed whitespace, truncated to `MAX_TITLE` chars.
fn short(text: &str) -> String {
const MAX_TITLE: usize = 80;
let flat: String = text.split_whitespace().collect::<Vec<_>>().join(" ");
if flat.chars().count() <= MAX_TITLE {
flat
} else {
format!("{}…", flat.chars().take(MAX_TITLE - 1).collect::<String>())
}
}
/// The text of a Claude Code transcript entry's message, when it carries prose.
fn message_text(e: &serde_json::Value) -> Option<String> {
match e.pointer("/message/content") {
Some(serde_json::Value::String(s)) => Some(s.clone()),
Some(serde_json::Value::Array(blocks)) => {
let text: Vec<&str> = blocks
.iter()
.filter(|b| b.get("type").and_then(serde_json::Value::as_str) == Some("text"))
.filter_map(|b| b.get("text").and_then(serde_json::Value::as_str))
.collect();
(!text.is_empty()).then(|| text.join("\n"))
}
_ => None,
}
}
/// Whether a session that ran in `cwd` belongs to the project at `root` (in it or below it).
fn in_project(cwd: Option<&str>, root: &Path) -> bool {
cwd.is_some_and(|cwd| Path::new(cwd).starts_with(root))
}
/// Claude Code transcripts of the project at `root`: `<config>/projects/<escaped cwd>/<id>.jsonl`.
/// Only the folders named after `root` or a folder below it are read, so other projects'
/// transcripts (often gigabytes) are never opened.
pub fn claude_sessions(config_dir: &Path, root: &Path) -> Vec<ExternalSession> {
let mut out = Vec::new();
let projects = config_dir.join("projects");
let escaped = history::escape(root);
let dirs: Vec<PathBuf> = std::fs::read_dir(&projects)
.into_iter()
.flatten()
.flatten()
.filter(|d| {
let name = d.file_name().to_string_lossy().into_owned();
name == escaped || name.starts_with(&format!("{escaped}-"))
})
.map(|d| d.path())
.collect();
for dir in dirs {
let files: Vec<PathBuf> = std::fs::read_dir(&dir)
.into_iter()
.flatten()
.flatten()
.map(|d| d.path())
.filter(|p| p.extension().is_some_and(|e| e == "jsonl"))
.collect();
for path in files {
let id = path.file_stem().and_then(|s| s.to_str()).unwrap_or_default().to_owned();
if id.is_empty() {
continue;
}
let entries = history::read(&path).unwrap_or_default();
if entries.is_empty() {
continue;
}
let title = history::title(&entries)
.or_else(|| entries.iter().filter(|e| history::is_turn_start(e)).filter_map(message_text).next())
.map(|t| short(&t))
.unwrap_or_else(|| format!("Claude Code session {}", &id[..id.len().min(8)]));
let cwd = entries
.iter()
.filter_map(|e| e.get("cwd").and_then(serde_json::Value::as_str))
.next()
.map(str::to_owned);
// Escaping is lossy (`a/b-c` and `a/b/c` share a folder): the transcript decides.
if !in_project(cwd.as_deref(), root) {
continue;
}
out.push(ExternalSession {
provider: "claude".to_owned(),
session_id: id,
title,
cwd,
updated_ms: mtime(&path),
});
}
}
out
}
/// The `session_meta` line of a Codex rollout file: `(id, cwd)`, across shapes.
fn codex_meta(line: &serde_json::Value) -> Option<(String, Option<String>)> {
let payload =
line.get("payload").filter(|p| p.get("type").and_then(serde_json::Value::as_str) == Some("session_meta"));
let inner = payload.and_then(|p| p.get("payload")).or_else(|| {
line.get("type").and_then(serde_json::Value::as_str).filter(|t| *t == "session_meta").and(Some(line))
})?;
let id = inner.get("id").and_then(serde_json::Value::as_str)?.to_owned();
let cwd = inner.get("cwd").and_then(serde_json::Value::as_str).map(str::to_owned);
Some((id, cwd))
}
/// A prose line of a Codex rollout file (a user message), across shapes.
fn codex_user_text(line: &serde_json::Value) -> Option<String> {
let payload = line.get("payload")?;
let ty = payload.get("type").and_then(serde_json::Value::as_str)?;
if !(ty == "user_message" || ty == "userMessage" || ty == "event_msg") {
return None;
}
let inner = payload.get("payload").unwrap_or(&serde_json::Value::Null);
for v in [payload, inner] {
if let Some(s) = v.get("message").and_then(serde_json::Value::as_str) {
return Some(s.to_owned());
}
if let Some(s) = v.get("text").and_then(serde_json::Value::as_str) {
return Some(s.to_owned());
}
}
None
}
/// One rollout file's session, or `None` when it names no `session_meta`.
fn codex_file(path: &Path) -> Option<ExternalSession> {
let file = std::fs::File::open(path).ok()?;
let mut id: Option<(String, Option<String>)> = None;
let mut title: Option<String> = None;
// `session_meta` is first, but cap the scan: giant rollouts must not stall listing.
for line in std::io::BufReader::new(file).lines().take(400) {
let Ok(line) = line else { break };
let Ok(v) = serde_json::from_str::<serde_json::Value>(&line) else { continue };
if id.is_none()
&& let Some(meta) = codex_meta(&v)
{
id = Some(meta);
}
if title.is_none()
&& let Some(t) = codex_user_text(&v)
{
title = Some(short(&t));
}
if id.is_some() && title.is_some() {
break;
}
}
let (session_id, cwd) = id?;
Some(ExternalSession {
provider: "codex".to_owned(),
title: title.unwrap_or_else(|| format!("Codex session {}", &session_id[..session_id.len().min(8)])),
session_id,
cwd,
updated_ms: mtime(path),
})
}
/// Collects `*.jsonl` below `dir`, up to 4 levels (`sessions/YYYY/MM/DD/<rollout>`).
fn rollout_files(dir: &Path, depth: usize, out: &mut Vec<PathBuf>) {
if depth == 0 {
return;
}
for entry in std::fs::read_dir(dir).into_iter().flatten().flatten() {
let path = entry.path();
if path.is_dir() {
rollout_files(&path, depth - 1, out);
} else if path.extension().is_some_and(|e| e == "jsonl") {
out.push(path);
}
}
}
/// Codex sessions of the project at `root`: `<home>/.codex/sessions/**`.
pub fn codex_sessions(codex_home: &Path, root: &Path) -> Vec<ExternalSession> {
let mut files = Vec::new();
rollout_files(&codex_home.join("sessions"), 4, &mut files);
files.iter().filter_map(|p| codex_file(p)).filter(|s| in_project(s.cwd.as_deref(), root)).collect()
}
#[cfg(test)]
mod tests {
use super::*;
use serde_json::json;
use std::io::Write;
fn write(path: &Path, lines: &[serde_json::Value]) {
std::fs::create_dir_all(path.parent().unwrap()).unwrap();
let mut f = std::fs::File::create(path).unwrap();
for line in lines {
writeln!(f, "{line}").unwrap();
}
}
fn claude_user(uuid: &str, text: &str) -> serde_json::Value {
json!({"type": "user", "uuid": uuid, "parentUuid": null,
"message": {"role": "user", "content": text}, "cwd": "/work/app"})
}
#[test]
fn lists_claude_transcripts_with_titles() {
let tmp = tempfile::tempdir().unwrap();
write(
&tmp.path().join("projects/-work-app/abc123.jsonl"),
&[
claude_user("u1", "fix the login bug"),
json!({"type": "assistant", "uuid": "a1", "parentUuid": "u1",
"message": {"role": "assistant", "content": []}}),
json!({"type": "ai-title", "aiTitle": "Login fix"}),
],
);
write(&tmp.path().join("projects/-work-app/empty.jsonl"), &[]);
let sessions = claude_sessions(tmp.path(), Path::new("/work/app"));
assert_eq!(sessions.len(), 1);
let s = &sessions[0];
assert_eq!((s.provider.as_str(), s.session_id.as_str()), ("claude", "abc123"));
assert_eq!(s.title, "Login fix");
assert_eq!(s.cwd.as_deref(), Some("/work/app"));
assert!(s.updated_ms > 0.0);
}
#[test]
fn claude_title_falls_back_to_the_first_prompt() {
let tmp = tempfile::tempdir().unwrap();
write(&tmp.path().join("projects/-work-app/def456.jsonl"), &[claude_user("u1", "hello there")]);
let sessions = claude_sessions(tmp.path(), Path::new("/work/app"));
assert_eq!(sessions.len(), 1);
assert_eq!(sessions[0].title, "hello there");
}
#[test]
fn lists_codex_rollouts_with_meta() {
let tmp = tempfile::tempdir().unwrap();
write(
&tmp.path().join("sessions/2026/01/02/rollout-01.jsonl"),
&[
json!({"timestamp": "t", "payload": {"type": "session_meta",
"payload": {"id": "thread-1", "cwd": "/work/app"}}}),
json!({"timestamp": "t", "payload": {"type": "user_message",
"payload": {"message": "add tests"}}}),
],
);
write(&tmp.path().join("sessions/notes.jsonl"), &[json!({"nope": true})]);
let sessions = codex_sessions(tmp.path(), Path::new("/work"));
assert_eq!(sessions.len(), 1);
let s = &sessions[0];
assert_eq!((s.provider.as_str(), s.session_id.as_str()), ("codex", "thread-1"));
assert_eq!(s.title, "add tests");
assert_eq!(s.cwd.as_deref(), Some("/work/app"));
}
#[test]
fn missing_directories_list_nothing() {
let tmp = tempfile::tempdir().unwrap();
assert!(claude_sessions(&tmp.path().join("nope"), Path::new("/work")).is_empty());
assert!(codex_sessions(&tmp.path().join("nope"), Path::new("/work")).is_empty());
}
#[test]
fn only_sessions_of_the_project_are_listed() {
let tmp = tempfile::tempdir().unwrap();
let user = |cwd: &str| {
json!({"type": "user", "uuid": "u1", "parentUuid": null,
"message": {"role": "user", "content": "hi"}, "cwd": cwd})
};
write(&tmp.path().join("projects/-work-app/in-root.jsonl"), &[user("/work/app")]);
write(&tmp.path().join("projects/-work-app-web/below.jsonl"), &[user("/work/app/web")]);
// `/work/app-old` escapes like a folder below `/work/app`; its transcript says otherwise.
write(&tmp.path().join("projects/-work-app-old/sibling.jsonl"), &[user("/work/app-old")]);
write(&tmp.path().join("projects/-other/elsewhere.jsonl"), &[user("/other")]);
let mut ids: Vec<String> =
claude_sessions(tmp.path(), Path::new("/work/app")).into_iter().map(|s| s.session_id).collect();
ids.sort();
assert_eq!(ids, ["below", "in-root"]);
let rollout = |name: &str, cwd: &str| {
write(
&tmp.path().join(format!("codex/sessions/2026/01/02/{name}.jsonl")),
&[json!({"payload": {"type": "session_meta", "payload": {"id": name, "cwd": cwd}}})],
)
};
rollout("mine", "/work/app/api");
rollout("theirs", "/other");
let codex: Vec<String> = codex_sessions(&tmp.path().join("codex"), Path::new("/work/app"))
.into_iter()
.map(|s| s.session_id)
.collect();
assert_eq!(codex, ["mine"]);
}
}
+26 -288
View File
@@ -10,8 +10,6 @@
mod acp;
mod config;
mod conversation;
mod external;
pub mod mcp;
mod model;
mod native;
mod provider;
@@ -20,7 +18,6 @@ mod skills;
mod timeline;
mod worktree;
pub use external::ExternalSession;
pub use model::*;
use conversation::{Conversation, SavedSubagent, Session};
@@ -94,9 +91,6 @@ type Connector = Arc<
+ Sync,
>;
/// Returns the configured MCP servers (User and Workspace) for this project.
pub type McpServersFn = dyn Fn() -> Vec<McpServer> + Send + Sync;
struct Shared {
paths: AgentPaths,
runtime: tokio::runtime::Handle,
@@ -110,7 +104,6 @@ struct Shared {
command_fetches: Mutex<HashMap<String, tokio::sync::watch::Receiver<bool>>>,
/// [`IDLE_RELEASE`], in milliseconds (shorter in tests).
idle_release_ms: AtomicU64,
mcp_servers_hook: RwLock<Option<Arc<McpServersFn>>>,
}
/// What an agent offered in its last session, for the New Task page.
@@ -138,13 +131,6 @@ impl Shared {
}
}
fn mcp_servers_for_session(&self, provider: &str, init: &acp::Negotiated) -> Vec<Value> {
let mut servers = mcp_servers_for(init.mcp_stdio(), &self.paths.project_root);
let configured = self.mcp_servers_hook.read().as_ref().map(|hook| hook()).unwrap_or_default();
servers.extend(mcp::acp_mcp_servers(&configured, provider, init));
servers
}
fn known_config(&self, provider: &str) -> Vec<AgentConfigOption> {
let mut config = self.known.lock().get(provider).map(|k| k.config.clone()).unwrap_or_default();
// Model-specific options are offered separately, never as provider-wide defaults.
@@ -177,25 +163,16 @@ impl Shared {
let shared = self.clone();
// Keep the lookup alive if a composer unmounts while it is waiting.
self.runtime.spawn(async move {
if let Ok(found) =
if let Ok((commands, options)) =
native::claude::discover(spec.clone(), shared.paths.project_root.clone()).await
{
let commands =
config::commands_of(&json!({ "availableCommands": found.commands }), &spec.id);
let options = config::options_of(&json!({ "configOptions": found.options }));
let levels: Vec<_> = found
.efforts
.into_iter()
.map(|(model, o)| {
let options = o.map(|o| config::options_of(&json!({ "configOptions": [o] })));
(model, options.unwrap_or_default())
})
.collect();
let commands = config::commands_of(&json!({ "availableCommands": commands }), &spec.id);
let options = config::options_of(&json!({ "configOptions": options }));
let _ = tokio::task::spawn_blocking(move || {
// Notifies subscribers itself when the discovery
// changed the cached config; unchanged results
// stay silent.
shared.remember_discovered(&spec.id, &options, &commands, &levels);
shared.remember_discovered(&spec.id, &options, &commands);
})
.await;
}
@@ -216,18 +193,6 @@ impl Shared {
self.known.lock().get(provider).is_some_and(|k| !k.config.is_empty())
}
/// Whether the thinking levels of every model the agent offers are known (#1686).
fn knows_all_levels(&self, provider: &str) -> bool {
let cache = self.known.lock();
let Some(known) = cache.get(provider) else { return false };
known
.config
.iter()
.filter(|o| o.category.as_deref() == Some("model"))
.flat_map(|o| &o.values)
.all(|v| known.thought_levels.contains_key(&v.value))
}
fn root_key(&self) -> String {
self.paths.project_root.to_string_lossy().into_owned()
}
@@ -240,19 +205,11 @@ impl Shared {
commands: Option<&[AgentCommand]>,
model: Option<&str>,
) {
self.remember_inner(provider, config, commands, model, &[], false);
self.remember_inner(provider, config, commands, model, false);
}
/// `levels`: each model's thinking-level options, so a new task offers them for any model
/// it picks (#1686). A session's report for a model wins over these.
fn remember_discovered(
&self,
provider: &str,
config: &[AgentConfigOption],
commands: &[AgentCommand],
levels: &[(String, Vec<AgentConfigOption>)],
) {
self.remember_inner(provider, Some(config), Some(commands), model_of(config).as_deref(), levels, true);
fn remember_discovered(&self, provider: &str, config: &[AgentConfigOption], commands: &[AgentCommand]) {
self.remember_inner(provider, Some(config), Some(commands), model_of(config).as_deref(), true);
}
fn remember_inner(
@@ -261,19 +218,12 @@ impl Shared {
config: Option<&[AgentConfigOption]>,
commands: Option<&[AgentCommand]>,
model: Option<&str>,
discovered_levels: &[(String, Vec<AgentConfigOption>)],
discovered: bool,
) {
// Keep the update and its disk write ordered; a session report wins over discovery.
let mut cache = self.known.lock();
let known = cache.entry(provider.to_owned()).or_default();
let mut changed = false;
for (model, levels) in discovered_levels {
if !known.thought_levels.contains_key(model) {
known.thought_levels.insert(model.clone(), levels.clone());
changed = true;
}
}
if let Some(c) = config.filter(|_| !discovered || known.config.is_empty()) {
if let Some(model) = model {
let levels: Vec<_> =
@@ -327,9 +277,6 @@ struct TaskFile {
/// In the project's own checkout: files already changed when the task started.
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
before: BTreeMap<String, worktree::Stamp>,
/// The folder (in the task store) with copies of the `before` files, for rolling back.
#[serde(default, skip_serializing_if = "Option::is_none")]
saved: Option<String>,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
subagents: Vec<SavedSubagent>,
/// Turns to drop from the session once it is loaded (a fork of an earlier point).
@@ -346,7 +293,6 @@ struct TaskState {
conversation: Conversation,
wanted: Vec<AgentConfigChoice>,
before: Arc<BTreeMap<String, worktree::Stamp>>,
saved: Option<String>,
pending_rollback: u32,
/// The user named the task; see `TaskFile::title_renamed`.
title_renamed: bool,
@@ -369,7 +315,7 @@ struct Live {
embedded: bool,
/// `session/load`: the process can be stopped between turns and the session reloaded.
resumable: bool,
init: acp::Negotiated,
mcp_stdio: bool,
}
struct Task {
@@ -439,7 +385,6 @@ impl AgentManager {
probes: Mutex::new(HashMap::new()),
command_fetches: Mutex::new(HashMap::new()),
idle_release_ms: AtomicU64::new(IDLE_RELEASE.as_millis() as u64),
mcp_servers_hook: RwLock::new(None),
});
let mut tasks = HashMap::new();
for file in std::fs::read_dir(&shared.paths.store_dir).into_iter().flatten().flatten() {
@@ -480,11 +425,8 @@ impl AgentManager {
/// The agents (custom ones re-read), whether each is installed, and what they offered last time.
pub fn providers(&self) -> Vec<AgentProvider> {
let specs = provider::load(self.shared.paths.custom_agents_dir.as_deref());
let in_use: std::collections::HashSet<String> =
self.tasks.read().values().map(|t| t.state.lock().task.provider.clone()).collect();
let list = specs
.iter()
.filter(|p| !provider::is_unlisted(p) || in_use.contains(&p.id))
.map(|p| {
let mut info = provider::describe(p);
info.config = self.shared.known_config(&p.id);
@@ -530,11 +472,6 @@ impl AgentManager {
self.shared.emit(AgentEvent::Providers);
}
/// Provides the user and workspace MCP servers configured in settings.
pub fn set_mcp_servers_hook(&self, hook: Box<McpServersFn>) {
*self.shared.mcp_servers_hook.write() = Some(Arc::from(hook));
}
/// The slash commands to complete for `provider`, in `task`'s directory or (without one)
/// in the project: what the agent offered last time there, unadvertised builtins,
/// and, for Claude Code, skills and custom commands on disk it has not listed.
@@ -551,7 +488,7 @@ impl AgentManager {
// merged without duplicating what `availableCommands` or the disk offer.
let mut offered = offered;
if task.is_none()
&& (offered.is_empty() || !self.shared.has_config(&provider) || !self.shared.knows_all_levels(&provider))
&& (offered.is_empty() || !self.shared.has_config(&provider))
&& let Some(spec) = self.shared.spec(&provider).filter(|s| s.driver == provider::Driver::Claude)
{
self.shared.fetch_settings(spec).await;
@@ -587,93 +524,6 @@ impl AgentManager {
Ok(timeline.entries.clone())
}
/// Session ids the tasks already hold (native drivers reuse the CLI's own id).
fn imported_session_ids(&self) -> HashSet<String> {
self.tasks.read().values().filter_map(|t| t.state.lock().session_id.clone()).collect()
}
/// Sessions of this project on this machine that no task holds yet, newest first. Reads
/// transcripts from disk: call it off the UI and command threads.
pub fn external_sessions(&self) -> Vec<ExternalSession> {
let mut out = Vec::new();
let root = self.shared.paths.project_root.clone();
if let Some(spec) = self.shared.spec("claude")
&& let Some(dir) = native::claude::cli::config_dir(&spec.env)
{
out.extend(external::claude_sessions(&dir, &root));
}
let home = self.shared.paths.home_dir.clone().or_else(home_dir);
if let Some(home) = home {
out.extend(external::codex_sessions(&home.join(".codex"), &root));
}
let known = self.imported_session_ids();
out.retain(|s| !known.contains(&s.session_id));
out.sort_by(|a, b| b.updated_ms.total_cmp(&a.updated_ms));
out.truncate(50);
out
}
/// Imports an external session as a task: its first turn loads and replays it (#312).
pub fn import_session(&self, provider: &str, session_id: &str) -> IdeResult<AgentTask> {
if !matches!(provider, "claude" | "codex") {
return Err(IdeError::invalid(format!("cannot import {provider} sessions")));
}
let spec = self.shared.spec(provider).ok_or_else(|| IdeError::invalid(format!("unknown agent {provider}")))?;
if self.imported_session_ids().contains(session_id) {
return Err(IdeError::invalid("that session is already a task"));
}
let found = self
.external_sessions()
.into_iter()
.find(|s| s.provider == provider && s.session_id == session_id)
.ok_or_else(|| IdeError::not_found(format!("unknown {provider} session {session_id}")))?;
let root = self.shared.paths.project_root.clone();
let cwd = found.cwd.map(PathBuf::from).filter(|p| p.is_absolute()).unwrap_or_else(|| root.clone());
let config = self.shared.known_config(&spec.id);
let now = now_ms();
let id = uuid::Uuid::new_v4().simple().to_string();
let task = AgentTask {
project_root: Some(IpcPath(root)),
id,
title: found.title,
provider: spec.id.clone(),
model: model_of(&config),
status: AgentStatus::Ready,
isolation: Isolation::Local,
cwd: IpcPath(cwd),
branch: None,
base: None,
base_commit: None,
error: None,
created_ms: now,
updated_ms: now,
config,
commands: self.shared.known_commands(&spec.id),
usage: None,
queue: Vec::new(),
capabilities: self.shared.probes.lock().get(&spec.id).map(|p| p.capabilities).unwrap_or_default(),
resets_ms: None,
retry: None,
background: Box::default(),
};
let file = TaskFile {
task: task.clone(),
session_id: Some(session_id.to_owned()),
entries: Vec::new(),
wanted: Vec::new(),
before: BTreeMap::new(),
saved: None,
subagents: Vec::new(),
pending_rollback: 0,
title_renamed: true,
};
let handle = Task::restore(file, self.shared.clone());
self.tasks.write().insert(task.id.clone(), handle.clone());
handle.emit_task();
handle.persist();
Ok(task)
}
/// Creates the task (and its worktree) and sends `req.prompt` as its first message.
pub async fn create(&self, req: NewAgentTask) -> IdeResult<AgentTask> {
let spec = self
@@ -726,24 +576,9 @@ impl AgentManager {
}));
}
let now = now_ms();
let id = uuid::Uuid::new_v4().simple().to_string();
// Copies of the files the user had changed already, for rolling back the task's changes to them.
let saved = if before.is_empty() {
None
} else {
let name = format!("{id}.before");
let (dir, at, files) = (self.shared.paths.store_dir.join(&name), cwd.clone(), before.clone());
match blocking(move || worktree::save_before(&at, &files, &dir)).await {
Ok(saved) => saved.then_some(name),
Err(e) => {
tracing::warn!("saving the changed files of agent task {id}: {e}");
None
}
}
};
let task = AgentTask {
project_root,
id,
id: uuid::Uuid::new_v4().simple().to_string(),
title,
provider: spec.id.clone(),
model: model_of(&config),
@@ -771,7 +606,6 @@ impl AgentManager {
entries: Vec::new(),
wanted: req.config,
before,
saved,
subagents: Vec::new(),
pending_rollback: 0,
title_renamed: false,
@@ -939,16 +773,10 @@ impl AgentManager {
return Err(IdeError::invalid("this agent can't copy a conversation from there"));
}
let cwd = source.state.lock().task.cwd.0.clone();
let provider_id = source.state.lock().task.provider.clone();
let mcp_servers = source.shared.mcp_servers_for_session(&provider_id, &live.init);
let cwd_s = dunce::canonicalize(&cwd).unwrap_or(cwd).to_string_lossy().into_owned();
let reply: Value = live
.peer
.request(
"session/fork",
json!({ "sessionId": live.session, "cwd": cwd_s, "mcpServers": mcp_servers }),
None,
)
.request("session/fork", json!({ "sessionId": live.session, "cwd": cwd_s, "mcpServers": mcp_servers_for(live.mcp_stdio, &source.shared.paths.project_root) }), None)
.await
.map_err(|e| IdeError::internal(source.describe(e)))?;
let session = reply
@@ -982,7 +810,6 @@ impl AgentManager {
entries,
wanted: s.wanted.clone(),
before: (*s.before).clone(),
saved: s.saved.clone(),
subagents: s.conversation.saved_subagents(),
pending_rollback: total - keep,
title_renamed: s.title_renamed,
@@ -1234,17 +1061,6 @@ impl AgentManager {
};
// A copy of the task (a fork) may work in the same worktree.
let shared = self.tasks.read().values().any(|t| t.id != id && t.state.lock().task.cwd.0 == cwd);
self.tasks.write().remove(id);
*task.deleted.lock() = true;
let _ = std::fs::remove_file(self.shared.paths.store_dir.join(format!("{id}.json")));
let saved = task.state.lock().saved.clone();
if let Some(saved) = saved
&& !self.tasks.read().values().any(|t| t.state.lock().saved.as_ref() == Some(&saved))
{
let _ = std::fs::remove_dir_all(self.shared.paths.store_dir.join(saved));
}
// The list drops the task now; removing a large worktree's folder can take a while.
self.shared.emit(AgentEvent::Removed { id: id.to_owned() });
if remove_worktree && !shared && isolation == Isolation::Worktree && cwd.exists() {
// On Windows the agent's processes lock the folder (their working directory,
// open files) until they have exited.
@@ -1254,6 +1070,10 @@ impl AgentManager {
let worktrees = self.shared.paths.worktrees_dir.clone();
blocking(move || worktree::remove(&root, &worktrees, &cwd)).await?;
}
self.tasks.write().remove(id);
*task.deleted.lock() = true;
let _ = std::fs::remove_file(self.shared.paths.store_dir.join(format!("{id}.json")));
self.shared.emit(AgentEvent::Removed { id: id.to_owned() });
Ok(())
}
@@ -1271,41 +1091,6 @@ impl AgentManager {
blocking(move || worktree::file_at(&cwd, &path, &base)).await
}
/// Rollback: puts the task's changed files among `rel_paths` (all with `None`) back as they
/// were when it started (files the user had changed then, as the user left them).
pub async fn rollback_changes(&self, id: &str, rel_paths: Option<Vec<String>>) -> IdeResult<()> {
let task = self.task(id)?;
if task.state.lock().busy {
return Err(IdeError::invalid("the agent is working: stop it before rolling back its changes"));
}
let (cwd, base) = task.cwd_and_base();
let (before, saved) = {
let s = task.state.lock();
(s.before.clone(), s.saved.as_ref().map(|name| self.shared.paths.store_dir.join(name)))
};
let restamped = blocking(move || {
let changes = worktree::without_untouched(worktree::changes(&cwd, &base)?, &before);
let mut restamped = Vec::new();
for change in changes.iter().filter(|c| rel_paths.as_ref().is_none_or(|p| p.contains(&c.rel_path))) {
worktree::restore(&cwd, &base, change, &before, saved.as_deref())?;
// Back to the user's own edits: not a change of the task any more.
if before.contains_key(&change.rel_path) {
restamped.push((change.rel_path.clone(), worktree::stamp(&change.path.0)));
}
}
Ok(restamped)
})
.await?;
if !restamped.is_empty() {
let mut s = task.state.lock();
let mut before = (*s.before).clone();
before.extend(restamped);
s.before = Arc::new(before);
}
task.persist();
Ok(())
}
/// Stops every agent (project closed).
pub fn shutdown(&self) {
for task in self.tasks.read().values() {
@@ -1331,7 +1116,6 @@ impl Task {
conversation,
wanted: file.wanted,
before: Arc::new(file.before),
saved: file.saved,
pending_rollback: file.pending_rollback,
title_renamed: file.title_renamed,
busy: false,
@@ -1444,7 +1228,6 @@ impl Task {
entries: s.conversation.main.entries.clone(),
wanted: s.wanted.clone(),
before: (*s.before).clone(),
saved: s.saved.clone(),
subagents: s.conversation.saved_subagents(),
pending_rollback: s.pending_rollback,
title_renamed: s.title_renamed,
@@ -1713,30 +1496,6 @@ impl Task {
})
}
/// Runs `method` and, on an auth error, tries the agent's own ACP `authenticate` once before retrying.
async fn request_with_auth(
&self,
peer: &acp::Conn,
init: &acp::Negotiated,
tried_auth: &mut bool,
method: &str,
params: Value,
) -> Result<Value, RpcError> {
let first = peer.request(method, params.clone(), None).await;
if !*tried_auth
&& let Err(RpcError::Server { code, ref message, .. }) = first
&& acp::auth_required(code, message)
&& let Some(method_id) = init.agent_auth_method()
{
*tried_auth = true;
match peer.request::<_, Value>("authenticate", json!({ "methodId": method_id }), None).await {
Ok(_) => return peer.request(method, params, None).await,
Err(e) => tracing::debug!(task = %self.id, method_id, error = %e, "agent authenticate failed"),
}
}
first
}
async fn ensure_session(self: &Arc<Self>) -> Result<Live, String> {
let _guard = self.connecting.lock().await;
if let Some(live) = self.live.lock().clone()
@@ -1774,17 +1533,16 @@ impl Task {
let init = peer.initialize(&client_info()).await.map_err(|e| self.describe(e))?;
let sign_in_message = spec.sign_in_message(&init.auth_methods);
let can_load = init.load_session();
let mcp_stdio = init.mcp_stdio();
let (capabilities, embedded) = capabilities_of(&init);
let mcp_servers = self.shared.mcp_servers_for_session(&provider_id, &init);
// Agents that compare canonical paths fail in a symlinked directory (macOS `/tmp`).
let cwd_s = dunce::canonicalize(&cwd).unwrap_or(cwd).to_string_lossy().into_owned();
let mut tried_auth = false;
let mut session = None;
if let (Some(id), true) = (saved, can_load) {
self.replaying.store(true, Ordering::Release);
let params = json!({ "sessionId": &id, "cwd": &cwd_s, "mcpServers": &mcp_servers });
let loaded = self.request_with_auth(&peer, &init, &mut tried_auth, "session/load", params).await;
let loaded: Result<Value, RpcError> =
peer.request("session/load", json!({ "sessionId": id, "cwd": cwd_s, "mcpServers": mcp_servers_for(mcp_stdio, &self.shared.paths.project_root) }), None).await;
tokio::time::sleep(REPLAY_GRACE).await;
self.replaying.store(false, Ordering::Release);
match loaded {
@@ -1796,9 +1554,12 @@ impl Task {
let (session_id, result) = match session {
Some(s) => s,
None => {
let params = json!({ "cwd": &cwd_s, "mcpServers": &mcp_servers });
let v = self
.request_with_auth(&peer, &init, &mut tried_auth, "session/new", params)
let v: Value = peer
.request(
"session/new",
json!({ "cwd": cwd_s, "mcpServers": mcp_servers_for(mcp_stdio, &self.shared.paths.project_root) }),
None,
)
.await
.map_err(|e| self.sign_in_error(&e, Some(&sign_in_message)).unwrap_or_else(|| self.describe(e)))?;
let id = v.get("sessionId").and_then(Value::as_str).ok_or("the agent returned no session")?.to_owned();
@@ -1890,7 +1651,7 @@ impl Task {
self.persist();
self.emit_task();
let live =
Live { sign_in_message, peer, session: session_id, capabilities, embedded, resumable: can_load, init };
Live { sign_in_message, peer, session: session_id, capabilities, embedded, resumable: can_load, mcp_stdio };
*self.live.lock() = Some(live.clone());
Ok(live)
}
@@ -1961,7 +1722,7 @@ impl Task {
format!("The agent process exited:\n{}", tail.join("\n"))
}
}
RpcError::Server { message, data, .. } => with_details(message, data.as_ref()),
RpcError::Server { message, .. } => message,
e => e.to_string(),
}
}
@@ -2419,24 +2180,6 @@ fn usage_limit(e: &RpcError) -> Option<Option<f64>> {
.then_some(None)
}
/// An error's message with the detail ACP agents put in `data` (`{"details": …}` or a string):
/// generic codes such as "Internal error" say nothing without it.
fn with_details(message: String, data: Option<&Value>) -> String {
let details = match data {
Some(Value::String(text)) => text.as_str(),
Some(data) => data.get("details").and_then(Value::as_str).unwrap_or_default(),
None => "",
}
.trim();
if details.is_empty() || message.contains(details) {
message
} else if message.trim().is_empty() {
details.to_owned()
} else {
format!("{message}: {details}")
}
}
fn client_info() -> Value {
json!({ "name": "OpenIDEA", "version": env!("CARGO_PKG_VERSION") })
}
@@ -2544,11 +2287,6 @@ fn now_ms() -> f64 {
std::time::SystemTime::now().duration_since(std::time::UNIX_EPOCH).map_or(0.0, |d| d.as_millis() as f64)
}
/// The user's home, for tools that keep state there (Codex sessions).
fn home_dir() -> Option<PathBuf> {
std::env::var_os("HOME").or_else(|| std::env::var_os("USERPROFILE")).map(PathBuf::from)
}
fn write_file(path: &Path, bytes: &[u8]) -> Result<(), String> {
if let Some(dir) = path.parent() {
std::fs::create_dir_all(dir).map_err(|e| e.to_string())?;
-507
View File
@@ -1,507 +0,0 @@
//! Model Context Protocol (MCP) server configurations stored in OpenIDEA's own settings
//! (global `settings.toml` and project `.openidea/settings.toml`), passed to ACP agents in
//! `session/new`, `session/load`, and `session/fork`, plus one-way import from `.mcp.json` /
//! `.vscode/mcp.json`.
use crate::acp::Negotiated;
use crate::{AgentMcpServer, McpKeyValue, McpScope, McpServer, McpServerInput, McpTransport};
use serde_json::{Value, json};
use std::collections::{BTreeMap, HashSet};
use std::path::Path;
/// Stable ID for a server in a given scope (`"user::<name>"` or `"workspace::<name>"`).
pub fn server_id(scope: McpScope, name: &str) -> String {
let prefix = match scope {
McpScope::User => "user",
McpScope::Workspace => "workspace",
};
format!("{prefix}::{name}")
}
/// Parses a server ID (`"user::<name>"` or `"workspace::<name>"`).
pub fn parse_server_id(id: &str) -> Option<(McpScope, &str)> {
let (prefix, name) = id.split_once("::")?;
if name.is_empty() {
return None;
}
match prefix {
"user" => Some((McpScope::User, name)),
"workspace" => Some((McpScope::Workspace, name)),
_ => None,
}
}
/// Converts the User (`settings.toml`) and Workspace (`.openidea/settings.toml`) MCP server maps
/// into the ordered list displayed in Settings › Agents › MCP Servers.
pub fn servers_from_settings(
user: &BTreeMap<String, AgentMcpServer>,
workspace: &BTreeMap<String, AgentMcpServer>,
) -> Vec<McpServer> {
user.iter()
.map(|(name, cfg)| to_mcp_server(McpScope::User, name, cfg))
.chain(workspace.iter().map(|(name, cfg)| to_mcp_server(McpScope::Workspace, name, cfg)))
.collect()
}
fn to_mcp_server(scope: McpScope, name: &str, cfg: &AgentMcpServer) -> McpServer {
McpServer {
id: server_id(scope, name),
name: name.to_owned(),
scope,
transport: cfg.transport,
enabled: cfg.enabled,
command: cfg.command.clone(),
args: cfg.args.clone(),
env: cfg.env.iter().map(|(k, v)| McpKeyValue { name: k.clone(), value: v.clone() }).collect(),
url: cfg.url.clone(),
headers: cfg.headers.iter().map(|(k, v)| McpKeyValue { name: k.clone(), value: v.clone() }).collect(),
agents: cfg.agents.clone(),
}
}
fn normalize_provider(id: &str) -> &str {
id.strip_suffix("-acp").unwrap_or(id)
}
fn matches_agent(agents: &[String], provider: &str) -> bool {
if agents.is_empty() {
return true;
}
let target = normalize_provider(provider);
agents.iter().any(|a| {
let trimmed = a.trim();
trimmed == provider || normalize_provider(trimmed) == target
})
}
/// Builds the ACP `mcpServers` array for `session/new`, `session/load`, and `session/fork`.
/// Workspace entries take precedence over User entries with the same name.
pub(crate) fn acp_mcp_servers(all: &[McpServer], provider: &str, init: &Negotiated) -> Vec<Value> {
let supports_stdio = init.mcp_stdio();
let supports_http = init.mcp("http");
let supports_sse = init.mcp("sse");
let mut seen = HashSet::new();
let mut servers = Vec::new();
let ordered =
all.iter().filter(|s| s.scope == McpScope::Workspace).chain(all.iter().filter(|s| s.scope == McpScope::User));
for srv in ordered {
if !srv.enabled || !matches_agent(&srv.agents, provider) || !seen.insert(srv.name.clone()) {
continue;
}
match srv.transport {
McpTransport::Stdio if supports_stdio => {
let Some(cmd) = srv.command.as_deref().filter(|c| !c.trim().is_empty()) else {
continue;
};
let env: Vec<Value> = srv.env.iter().map(|kv| json!({ "name": kv.name, "value": kv.value })).collect();
servers.push(json!({
"name": srv.name,
"command": cmd,
"args": srv.args,
"env": env,
}));
}
McpTransport::Http if supports_http => {
let Some(url) = srv.url.as_deref().filter(|u| !u.trim().is_empty()) else {
continue;
};
let headers: Vec<Value> =
srv.headers.iter().map(|kv| json!({ "name": kv.name, "value": kv.value })).collect();
servers.push(json!({
"type": "http",
"name": srv.name,
"url": url,
"headers": headers,
}));
}
McpTransport::Sse if supports_sse => {
let Some(url) = srv.url.as_deref().filter(|u| !u.trim().is_empty()) else {
continue;
};
let headers: Vec<Value> =
srv.headers.iter().map(|kv| json!({ "name": kv.name, "value": kv.value })).collect();
servers.push(json!({
"type": "sse",
"name": srv.name,
"url": url,
"headers": headers,
}));
}
_ => {}
}
}
servers
}
/// Applies a create or update operation to the User / Workspace MCP server maps.
pub fn apply_save(
user: &mut BTreeMap<String, AgentMcpServer>,
workspace: &mut BTreeMap<String, AgentMcpServer>,
has_workspace: bool,
input: McpServerInput,
) -> Result<(), String> {
let name = input.name.trim();
if name.is_empty() {
return Err("Server name is required".into());
}
if input.scope == McpScope::Workspace && !has_workspace {
return Err("Open a project to configure workspace MCP servers".into());
}
let cfg = match input.transport {
McpTransport::Stdio => {
let cmd = input.command.as_deref().map(str::trim).unwrap_or_default();
if cmd.is_empty() {
return Err("Command is required for stdio MCP servers".into());
}
let env = input
.env
.into_iter()
.filter_map(|kv| {
let k = kv.name.trim();
(!k.is_empty()).then(|| (k.to_owned(), kv.value))
})
.collect();
AgentMcpServer {
transport: McpTransport::Stdio,
enabled: input.enabled,
command: Some(cmd.to_owned()),
args: input.args,
env,
url: None,
headers: BTreeMap::new(),
agents: normalize_agents_list(input.agents),
}
}
McpTransport::Http | McpTransport::Sse => {
let url = input.url.as_deref().map(str::trim).unwrap_or_default();
if url.is_empty() {
return Err("URL is required for HTTP/SSE MCP servers".into());
}
let headers = input
.headers
.into_iter()
.filter_map(|kv| {
let k = kv.name.trim();
(!k.is_empty()).then(|| (k.to_owned(), kv.value))
})
.collect();
AgentMcpServer {
transport: input.transport,
enabled: input.enabled,
command: None,
args: Vec::new(),
env: BTreeMap::new(),
url: Some(url.to_owned()),
headers,
agents: normalize_agents_list(input.agents),
}
}
};
if let Some(prev_id) = input.id.as_deref()
&& let Some((prev_scope, prev_name)) = parse_server_id(prev_id)
&& (prev_scope != input.scope || prev_name != name)
{
match prev_scope {
McpScope::User => {
user.remove(prev_name);
}
McpScope::Workspace => {
workspace.remove(prev_name);
}
}
}
match input.scope {
McpScope::User => {
user.insert(name.to_owned(), cfg);
}
McpScope::Workspace => {
workspace.insert(name.to_owned(), cfg);
}
}
Ok(())
}
/// Enables or disables a User or Workspace MCP server by ID.
pub fn apply_set_enabled(
user: &mut BTreeMap<String, AgentMcpServer>,
workspace: &mut BTreeMap<String, AgentMcpServer>,
id: &str,
enabled: bool,
) -> Result<McpScope, String> {
let (scope, name) = parse_server_id(id).ok_or_else(|| format!("MCP server `{id}` not found"))?;
let map = match scope {
McpScope::User => user,
McpScope::Workspace => workspace,
};
let srv = map.get_mut(name).ok_or_else(|| format!("MCP server `{name}` not found"))?;
srv.enabled = enabled;
Ok(scope)
}
/// Removes a User or Workspace MCP server by ID.
pub fn apply_remove(
user: &mut BTreeMap<String, AgentMcpServer>,
workspace: &mut BTreeMap<String, AgentMcpServer>,
id: &str,
) -> Result<McpScope, String> {
let (scope, name) = parse_server_id(id).ok_or_else(|| format!("MCP server `{id}` not found"))?;
let map = match scope {
McpScope::User => user,
McpScope::Workspace => workspace,
};
if map.remove(name).is_none() {
return Err(format!("MCP server `{name}` not found"));
}
Ok(scope)
}
/// Imports MCP servers from `<workspace_root>/.mcp.json` and `<workspace_root>/.vscode/mcp.json`
/// into `workspace` without modifying the external files. Returns the number of newly added servers.
pub fn apply_import(workspace: &mut BTreeMap<String, AgentMcpServer>, workspace_root: &Path) -> usize {
let mut added = 0;
for rel in [".mcp.json", ".vscode/mcp.json"] {
let path = workspace_root.join(rel);
for (name, srv) in read_external_file(&path) {
if let std::collections::btree_map::Entry::Vacant(e) = workspace.entry(name) {
e.insert(srv);
added += 1;
}
}
}
added
}
fn normalize_agents_list(agents: Vec<String>) -> Vec<String> {
let mut out = Vec::new();
for a in agents {
let trimmed = a.trim();
if !trimmed.is_empty() && !out.iter().any(|existing: &String| existing == trimmed) {
out.push(trimmed.to_owned());
}
}
out
}
fn read_external_file(path: &Path) -> BTreeMap<String, AgentMcpServer> {
let Ok(bytes) = std::fs::read(path) else {
return BTreeMap::new();
};
let Ok(root) = serde_json::from_slice::<Value>(&bytes) else {
return BTreeMap::new();
};
let Some(servers_obj) = root.get("mcpServers").or_else(|| root.get("servers")).and_then(Value::as_object) else {
return BTreeMap::new();
};
let mut out = BTreeMap::new();
for (name, def) in servers_obj {
let name = name.trim();
let Some(obj) = def.as_object().filter(|_| !name.is_empty()) else {
continue;
};
let disabled = obj.get("disabled").and_then(Value::as_bool).unwrap_or(false)
|| obj.get("enabled").and_then(Value::as_bool) == Some(false);
let type_str = obj.get("type").and_then(Value::as_str).unwrap_or_default().to_ascii_lowercase();
let url = obj
.get("url")
.or_else(|| obj.get("serverUrl"))
.and_then(Value::as_str)
.map(str::trim)
.filter(|s| !s.is_empty())
.map(str::to_owned);
let command =
obj.get("command").and_then(Value::as_str).map(str::trim).filter(|s| !s.is_empty()).map(str::to_owned);
let transport = match type_str.as_str() {
"sse" => McpTransport::Sse,
"http" | "streamable-http" | "streamable_http" => McpTransport::Http,
"stdio" | "local" => McpTransport::Stdio,
_ if url.is_some() && command.is_none() => McpTransport::Http,
_ => McpTransport::Stdio,
};
match transport {
McpTransport::Stdio if command.is_none() => continue,
McpTransport::Http | McpTransport::Sse if url.is_none() => continue,
_ => {}
}
let args = obj
.get("args")
.and_then(Value::as_array)
.map(|arr| arr.iter().filter_map(|v| v.as_str().map(str::to_owned)).collect())
.unwrap_or_default();
out.insert(
name.to_owned(),
AgentMcpServer {
transport,
enabled: !disabled,
command,
args,
env: parse_key_values_map(obj.get("env")),
url,
headers: parse_key_values_map(obj.get("headers")),
agents: Vec::new(),
},
);
}
out
}
fn parse_key_values_map(val: Option<&Value>) -> BTreeMap<String, String> {
match val {
Some(Value::Object(map)) => map
.iter()
.filter_map(|(k, v)| {
let s = match v {
Value::String(s) => s.clone(),
Value::Number(n) => n.to_string(),
Value::Bool(b) => b.to_string(),
_ => return None,
};
Some((k.clone(), s))
})
.collect(),
Some(Value::Array(arr)) => arr
.iter()
.filter_map(|item| {
let obj = item.as_object()?;
let name = obj.get("name")?.as_str()?.to_owned();
let value = obj.get("value")?.as_str()?.to_owned();
Some((name, value))
})
.collect(),
_ => BTreeMap::new(),
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn crud_and_acp_filtering_by_scope_agent_and_transport() {
let mut user = BTreeMap::new();
let mut workspace = BTreeMap::new();
apply_save(
&mut user,
&mut workspace,
true,
McpServerInput {
id: None,
name: "shared".into(),
scope: McpScope::User,
transport: McpTransport::Stdio,
enabled: true,
command: Some("npx".into()),
args: vec!["-y".into(), "user-pkg".into()],
env: vec![McpKeyValue { name: "TOKEN".into(), value: "u1".into() }],
url: None,
headers: Vec::new(),
agents: Vec::new(),
},
)
.unwrap();
apply_save(
&mut user,
&mut workspace,
true,
McpServerInput {
id: None,
name: "shared".into(),
scope: McpScope::Workspace,
transport: McpTransport::Stdio,
enabled: true,
command: Some("npx".into()),
args: vec!["-y".into(), "workspace-pkg".into()],
env: Vec::new(),
url: None,
headers: Vec::new(),
agents: Vec::new(),
},
)
.unwrap();
apply_save(
&mut user,
&mut workspace,
true,
McpServerInput {
id: None,
name: "claude-http".into(),
scope: McpScope::User,
transport: McpTransport::Http,
enabled: true,
command: None,
args: Vec::new(),
env: Vec::new(),
url: Some("https://example.com/mcp".into()),
headers: vec![McpKeyValue { name: "Authorization".into(), value: "Bearer secret".into() }],
agents: vec!["claude".into()],
},
)
.unwrap();
let list = servers_from_settings(&user, &workspace);
assert_eq!(list.len(), 3);
// Negotiated with HTTP support: `claude` gets workspace `shared` + `claude-http`; `codex` only gets `shared`.
let init_http = Negotiated::from_initialize(&json!({
"agentCapabilities": { "mcpCapabilities": { "http": true, "sse": false } }
}));
let claude_servers = acp_mcp_servers(&list, "claude-acp", &init_http);
assert_eq!(claude_servers.len(), 2);
assert_eq!(claude_servers[0]["name"], "shared");
assert_eq!(claude_servers[0]["args"], json!(["-y", "workspace-pkg"]));
assert_eq!(claude_servers[1]["name"], "claude-http");
assert_eq!(claude_servers[1]["type"], "http");
let codex_servers = acp_mcp_servers(&list, "codex", &init_http);
assert_eq!(codex_servers.len(), 1);
assert_eq!(codex_servers[0]["name"], "shared");
// Disable workspace `shared` and remove user `claude-http`.
apply_set_enabled(&mut user, &mut workspace, "workspace::shared", false).unwrap();
apply_remove(&mut user, &mut workspace, "user::claude-http").unwrap();
let list = servers_from_settings(&user, &workspace);
let after = acp_mcp_servers(&list, "claude", &init_http);
assert_eq!(after.len(), 1);
assert_eq!(after[0]["args"], json!(["-y", "user-pkg"]));
}
#[test]
fn imports_from_mcp_json_and_vscode_mcp_json_without_modifying_them() {
let tmp = tempfile::tempdir().unwrap();
let mcp_json = tmp.path().join(".mcp.json");
let vscode_dir = tmp.path().join(".vscode");
std::fs::create_dir_all(&vscode_dir).unwrap();
let vscode_mcp = vscode_dir.join("mcp.json");
let raw_mcp = r#"{"mcpServers":{"sqlite":{"command":"uvx","args":["mcp-server-sqlite"]}}}"#;
let raw_vscode = r#"{"servers":{"remote":{"type":"http","url":"https://mcp.example.com"}}}"#;
std::fs::write(&mcp_json, raw_mcp).unwrap();
std::fs::write(&vscode_mcp, raw_vscode).unwrap();
let mut workspace = BTreeMap::new();
let added = apply_import(&mut workspace, tmp.path());
assert_eq!(added, 2);
assert_eq!(workspace["sqlite"].command.as_deref(), Some("uvx"));
assert_eq!(workspace["remote"].transport, McpTransport::Http);
assert_eq!(workspace["remote"].url.as_deref(), Some("https://mcp.example.com"));
// Re-importing does not duplicate or overwrite existing entries, and leaves files untouched.
workspace.get_mut("sqlite").unwrap().enabled = false;
assert_eq!(apply_import(&mut workspace, tmp.path()), 0);
assert!(!workspace["sqlite"].enabled);
assert_eq!(std::fs::read_to_string(&mcp_json).unwrap(), raw_mcp);
assert_eq!(std::fs::read_to_string(&vscode_mcp).unwrap(), raw_vscode);
}
}
-67
View File
@@ -535,70 +535,3 @@ pub enum AgentEvent {
/// The installed or configured agent providers changed.
Providers,
}
pub use ide_core::settings::{AgentMcpServer, McpTransport};
/// Where an MCP server configuration is stored (`settings.toml` vs `.openidea/settings.toml`).
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub enum McpScope {
User,
Workspace,
}
/// A named environment variable or HTTP header for an MCP server.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct McpKeyValue {
pub name: String,
pub value: String,
}
/// One configured Model Context Protocol (MCP) server.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct McpServer {
pub id: String,
pub name: String,
pub scope: McpScope,
pub transport: McpTransport,
pub enabled: bool,
pub command: Option<String>,
pub args: Vec<String>,
pub env: Vec<McpKeyValue>,
pub url: Option<String>,
pub headers: Vec<McpKeyValue>,
/// Agent provider ids this server is enabled for; empty means enabled for all agents.
#[serde(default)]
pub agents: Vec<String>,
}
/// Payload for creating or updating a user or workspace MCP server.
#[derive(Clone, Debug, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct McpServerInput {
#[serde(default)]
pub id: Option<String>,
pub name: String,
pub scope: McpScope,
pub transport: McpTransport,
#[serde(default = "default_true")]
pub enabled: bool,
#[serde(default)]
pub command: Option<String>,
#[serde(default)]
pub args: Vec<String>,
#[serde(default)]
pub env: Vec<McpKeyValue>,
#[serde(default)]
pub url: Option<String>,
#[serde(default)]
pub headers: Vec<McpKeyValue>,
/// Agent provider ids this server is enabled for; empty means enabled for all agents.
#[serde(default)]
pub agents: Vec<String>,
}
fn default_true() -> bool {
true
}
+1 -1
View File
@@ -135,7 +135,7 @@ impl Cli for Process {
}
/// Claude Code's configuration directory (`CLAUDE_CONFIG_DIR`, else `~/.claude`).
pub(crate) fn config_dir(env: &[(String, String)]) -> Option<PathBuf> {
pub(super) fn config_dir(env: &[(String, String)]) -> Option<PathBuf> {
let set = env
.iter()
.find(|(k, _)| k == "CLAUDE_CONFIG_DIR")
@@ -31,11 +31,11 @@ pub(super) fn transcript(config_dir: &Path, cwd: &Path, id: &str) -> PathBuf {
}
/// The project directory name Claude Code uses for `cwd`.
pub(crate) fn escape(cwd: &Path) -> String {
pub(super) fn escape(cwd: &Path) -> String {
cwd.to_string_lossy().chars().map(|c| if c.is_ascii_alphanumeric() { c } else { '-' }).collect()
}
pub(crate) fn read(path: &Path) -> std::io::Result<Vec<Value>> {
pub(super) fn read(path: &Path) -> std::io::Result<Vec<Value>> {
let text = std::fs::read_to_string(path)?;
Ok(text.lines().filter_map(|l| serde_json::from_str(l).ok()).collect())
}
@@ -111,7 +111,7 @@ fn block_ids<'a>(e: &'a Value, ty: &'a str, key: &'a str) -> impl Iterator<Item
/// Whether `e` is a message that started a turn: the user's own, not a tool result, a
/// steer, or text Claude Code added.
pub(crate) fn is_turn_start(e: &Value) -> bool {
pub(super) fn is_turn_start(e: &Value) -> bool {
if kind(e) != "user" || e.get("isMeta").and_then(Value::as_bool) == Some(true) {
return false;
}
@@ -149,7 +149,7 @@ pub(super) fn cut(chain: &[&Value], turns: usize) -> Result<Option<String>, Stri
}
/// The newest title Claude Code gave the session.
pub(crate) fn title(entries: &[Value]) -> Option<String> {
pub(super) fn title(entries: &[Value]) -> Option<String> {
entries
.iter()
.rev()
+4 -16
View File
@@ -7,8 +7,8 @@
//! <id>.json`): loading that session, from this connection or a fresh one, starts it that
//! way.
pub(crate) mod cli;
pub(crate) mod history;
mod cli;
mod history;
mod settings;
mod tools;
mod translate;
@@ -69,17 +69,9 @@ pub(crate) fn connect(
Ok(super::serve(shim, client))
}
/// What discovery found: ACP `availableCommands`, `configOptions` for the configured model,
/// and each model's effort option by model value (`None`: none).
pub(crate) struct Discovered {
pub commands: Vec<Value>,
pub options: Value,
pub efforts: Vec<(String, Option<Value>)>,
}
/// Discover the slash commands and the model, mode and effort options without a prompt,
/// ACP session, or pending session file.
pub(crate) async fn discover(spec: ProviderSpec, cwd: PathBuf) -> Result<Discovered, String> {
pub(crate) async fn discover(spec: ProviderSpec, cwd: PathBuf) -> Result<(Vec<Value>, Value), String> {
tokio::time::timeout(Duration::from_secs(5), async move {
let spec = tokio::task::spawn_blocking(move || (spec.resolve_for_launch(&cwd), cwd));
let (spec, cwd) = spec.await.map_err(|e| e.to_string())?;
@@ -108,11 +100,7 @@ pub(crate) async fn discover(spec: ProviderSpec, cwd: PathBuf) -> Result<Discove
.flatten()
.unwrap_or_default();
let settings = Settings::from_cli(&init, &applied);
Ok(Discovered {
commands: settings.commands.clone(),
options: settings.options(),
efforts: settings.efforts_by_model(),
})
Ok((settings.commands.clone(), settings.options()))
})
.await
.map_err(|_| "Claude Code command discovery timed out".to_owned())?
+9 -38
View File
@@ -132,18 +132,19 @@ impl Settings {
}).collect::<Vec<_>>(),
}));
}
if let Some(effort) = self.current_model().and_then(|m| effort_option(m, &self.effort)) {
out.push(effort);
let efforts = self.current_model().map(|m| m.efforts.as_slice()).unwrap_or_default();
if !efforts.is_empty() {
let mut values = vec![json!({ "value": "default", "name": "Default" })];
values.extend(efforts.iter().map(|e| json!({ "value": e, "name": capitalize(e) })));
let current = if efforts.contains(&self.effort) { self.effort.as_str() } else { "default" };
out.push(json!({
"id": EFFORT, "name": "Effort", "category": "thought_level", "type": "select",
"currentValue": current, "options": values,
}));
}
Value::Array(out)
}
/// Each model's effort option by model value (`None`: it has no effort levels): what a new
/// task offers once that model is picked, before any session has run it.
pub fn efforts_by_model(&self) -> Vec<(String, Option<Value>)> {
self.models.iter().map(|m| (m.value.clone(), effort_option(m, &self.effort))).collect()
}
pub fn valid(&self, option: &str, value: &str) -> bool {
self.options()
.as_array()
@@ -155,20 +156,6 @@ impl Settings {
}
}
/// `model`'s effort option, with `effort` selected when the model offers it; `None` without efforts.
fn effort_option(model: &Model, effort: &str) -> Option<Value> {
if model.efforts.is_empty() {
return None;
}
let mut values = vec![json!({ "value": "default", "name": "Default" })];
values.extend(model.efforts.iter().map(|e| json!({ "value": e, "name": capitalize(e) })));
let current = if model.efforts.iter().any(|e| e == effort) { effort } else { "default" };
Some(json!({
"id": EFFORT, "name": "Effort", "category": "thought_level", "type": "select",
"currentValue": current, "options": values,
}))
}
/// Slash commands as ACP `availableCommands`, without those that need Claude Code's terminal.
pub(super) fn commands(list: Option<&Value>, terminal_only: &[String]) -> Vec<Value> {
list.and_then(Value::as_array)
@@ -244,20 +231,4 @@ mod tests {
let cmds = commands(init().get("commands"), &["doctor".into()]);
assert_eq!(cmds, vec![json!({"name": "review", "description": "Review", "input": {"hint": "[pr]"}})]);
}
#[test]
fn every_model_offers_its_own_efforts() {
let s = Settings::from_cli(&init(), &json!({"applied": {"model": "claude-sonnet-5-5", "effort": "high"}}));
let efforts = s.efforts_by_model();
let values = |model: &str| {
let (_, o) = efforts.iter().find(|(m, _)| m == model).unwrap();
let o = o.as_ref().unwrap();
let values: Vec<_> = o["options"].as_array().unwrap().iter().map(|v| v["value"].clone()).collect();
(values, o["currentValue"].clone())
};
assert_eq!(values("default"), (vec![json!("default"), json!("low"), json!("high")], json!("high")));
// The configured effort only where the model offers it.
assert_eq!(values("opus"), (vec![json!("default"), json!("low"), json!("max")], json!("default")));
assert!(efforts.contains(&("claude-haiku-4-5".into(), None)), "no effort option without levels");
}
}
-58
View File
@@ -59,8 +59,6 @@ const BUILTIN: &[(&str, &str, Driver, &[&str], &str)] = &[
("cursor", "Cursor", Driver::Acp, &["cursor-agent", "acp"], "Run `cursor-agent login` in a terminal."),
("opencode", "OpenCode", Driver::Acp, &["opencode", "acp"], "Run `opencode auth login` in a terminal."),
("qwen", "Qwen Code", Driver::Acp, &["qwen", "--experimental-acp"], "Run `qwen` in a terminal and sign in."),
("qoder", "Qoder", Driver::Acp, &["qodercli", "--acp"], "Run `qodercli login` in a terminal."),
("qodercn", "Qoder CN", Driver::Acp, &["qoderclicn", "--acp"], "Run `qoderclicn login` in a terminal."),
("kimi", "Kimi CLI", Driver::Acp, &["kimi", "acp"], "Run `kimi` in a terminal and sign in."),
("goose", "Goose", Driver::Acp, &["goose", "acp"], "Run `goose configure` in a terminal."),
("auggie", "Auggie", Driver::Acp, &["auggie", "--acp"], "Run `auggie login` in a terminal."),
@@ -187,14 +185,6 @@ pub(crate) fn builtin_spec(id: &str) -> Option<ProviderSpec> {
builtins().into_iter().find(|s| s.id == id)
}
/// The ACP adapters of Claude Code and Codex, which the native drivers replace: they still
/// launch, but are listed only once customized through an agent file or used by a task.
const UNLISTED: &[&str] = &["claude-acp", "codex-acp"];
pub(crate) fn is_unlisted(spec: &ProviderSpec) -> bool {
UNLISTED.contains(&spec.id.as_str()) && builtin_spec(&spec.id).as_ref() == Some(spec)
}
/// Public launch metadata, keeping the built-in defaults separate from agent-file overrides.
pub(crate) fn describe(spec: &ProviderSpec) -> AgentProvider {
let builtin = builtin_spec(&spec.id);
@@ -411,45 +401,6 @@ mod tests {
use super::*;
use serde_json::json;
#[test]
fn qoder_global_and_cn_editions_are_both_built_in() {
let info = |id: &str| describe(&load(None).into_iter().find(|s| s.id == id).unwrap());
let (global, cn) = (info("qoder"), info("qodercn"));
assert_eq!((global.name.as_str(), global.command.as_str()), ("Qoder", "qodercli --acp"));
assert_eq!((cn.name.as_str(), cn.command.as_str()), ("Qoder CN", "qoderclicn --acp"));
assert_eq!(global.login_hint.as_deref(), Some("Run `qodercli login` in a terminal."));
}
#[test]
fn qodercn_is_available_without_a_file_and_preserves_existing_customizations() {
let dir = tempfile::tempdir().unwrap();
let qodercn = load(None).into_iter().find(|s| s.id == "qodercn").unwrap();
assert_eq!(qodercn.driver, Driver::Acp);
assert!(!is_unlisted(&qodercn));
let info = describe(&qodercn);
assert_eq!(info.name, "Qoder CN");
assert_eq!(info.command, "qoderclicn --acp");
assert_eq!(info.source, AgentSource::Builtin);
assert!(info.command_editable);
assert_eq!(info.login_hint.as_deref(), Some("Run `qoderclicn login` in a terminal."));
std::fs::write(
dir.path().join("qodercn.toml"),
"command = \"/custom/qoderclicn\"\nargs = [\"--acp\"]\n[env]\nK = \"v\"\n",
)
.unwrap();
let specs = load(Some(dir.path()));
assert_eq!(specs.iter().filter(|s| s.id == "qodercn").count(), 1);
let custom = specs.iter().find(|s| s.id == "qodercn").unwrap();
assert_eq!(custom.command, "/custom/qoderclicn");
assert_eq!(custom.env, [("K".into(), "v".into())]);
set_builtin_command(dir.path(), "qodercn", None).unwrap();
let reset = load(Some(dir.path())).into_iter().find(|s| s.id == "qodercn").unwrap();
assert_eq!(reset.command, "qoderclicn");
assert_eq!(reset.args, ["--acp"]);
assert_eq!(reset.env, custom.env);
}
#[test]
fn login_hints_cover_all_builtin_commands_and_preserve_separate_login_tools() {
for spec in builtins() {
@@ -640,15 +591,6 @@ mod tests {
set_builtin_env(dir.path(), "not-a-builtin", env).unwrap_err();
}
#[test]
fn acp_adapters_of_native_agents_are_unlisted_until_customized() {
let dir = tempfile::tempdir().unwrap();
let unlisted = |dir: &Path| load(Some(dir)).into_iter().filter(is_unlisted).map(|s| s.id).collect::<Vec<_>>();
assert_eq!(unlisted(dir.path()), ["claude-acp", "codex-acp"]);
set_builtin_env(dir.path(), "codex-acp", BTreeMap::from([("A".to_owned(), "1".to_owned())])).unwrap();
assert_eq!(unlisted(dir.path()), ["claude-acp"]);
}
#[test]
fn set_builtin_command_overrides_and_clears_a_builtin() {
let dir = tempfile::tempdir().unwrap();
+5 -207
View File
@@ -35,9 +35,6 @@ struct FakeAgent {
/// Without `loadSession` (a session lives only as long as its process).
no_load: bool,
auth_on_new: bool,
auth_on_load: bool,
authenticate_method: Option<String>,
authenticated: AtomicBool,
request_error: Option<(i64, String)>,
auth_methods: Vec<Value>,
/// Hold the late mode reply until the prompt's permission request is already waiting.
@@ -130,9 +127,9 @@ impl Handler for FakeAgent {
fn on_request(&self, method: &str, params: Value) -> Result<Value, (i64, String)> {
self.calls.lock().push(method.to_owned());
let needs_auth = !self.authenticated.load(Ordering::Acquire)
&& ((method == "session/new" && self.auth_on_new) || (method == "session/load" && self.auth_on_load));
if needs_auth || (method == "session/prompt" && params.pointer("/prompt/0/text") == Some(&json!("auth"))) {
if (method == "session/new" && self.auth_on_new)
|| (method == "session/prompt" && params.pointer("/prompt/0/text") == Some(&json!("auth")))
{
return Err(self
.request_error
.clone()
@@ -179,16 +176,6 @@ impl Handler for FakeAgent {
self.say(&session, "replayed history");
Ok(json!({}))
}
"authenticate" if self.authenticate_method.is_some() => {
let id = params.get("methodId").and_then(Value::as_str).unwrap_or_default();
self.calls.lock().push(format!("authenticate {id}"));
if Some(id) == self.authenticate_method.as_deref() {
self.authenticated.store(true, Ordering::Release);
Ok(json!({}))
} else {
Err((codes::INVALID_PARAMS, format!("unexpected methodId {id}")))
}
}
"session/set_config_option" | "session/set_mode" => {
self.calls.lock().push(format!("{method} {}", params.get("value").or(params.get("modeId")).unwrap()));
if params["configId"] == "model" && !self.model_options.lock().is_empty() {
@@ -709,91 +696,6 @@ async fn registry_sign_in_errors_use_the_advertised_terminal_login() {
}
}
#[tokio::test(flavor = "multi_thread")]
async fn authenticates_and_retries_session_setup_once_on_auth_error() {
let tmp = tempfile::tempdir().unwrap();
let methods = vec![
json!({"id": "cli_login", "_meta": {"terminal-auth": {"command": "copilot", "args": ["login"]}}}),
json!({"id": "github_oauth", "name": "GitHub OAuth"}),
];
let agent = Arc::new(FakeAgent {
auth_on_new: true,
authenticate_method: Some("github_oauth".into()),
request_error: Some((-32000, "Authentication required".into())),
auth_methods: methods.clone(),
..Default::default()
});
let mgr = manager(tmp.path(), agent.clone());
let task = mgr
.create(NewAgentTask {
project_root: None,
prompt: text("again"),
provider: "copilot".into(),
config: vec![],
isolation: Isolation::Local,
base: None,
})
.await
.unwrap();
wait_for(&mgr, &task.id, AgentStatus::Ready).await;
assert_eq!(
agent
.calls
.lock()
.iter()
.filter(|c| c.starts_with("session/") || c.starts_with("authenticate"))
.collect::<Vec<_>>(),
["session/new", "authenticate", "authenticate github_oauth", "session/new", "session/prompt"],
);
// Resuming after an IDE restart also authenticates once and retries `session/load`.
mgr.shutdown();
let agent2 = Arc::new(FakeAgent {
auth_on_load: true,
auth_on_new: true,
authenticate_method: Some("github_oauth".into()),
request_error: Some((-32000, "Authentication required".into())),
auth_methods: methods.clone(),
..Default::default()
});
let mgr2 = manager(tmp.path(), agent2.clone());
mgr2.prompt(&task.id, text("again"), false).await.unwrap();
tokio::time::sleep(Duration::from_millis(50)).await;
wait_for(&mgr2, &task.id, AgentStatus::Ready).await;
assert_eq!(
agent2
.calls
.lock()
.iter()
.filter(|c| c.starts_with("session/") || c.starts_with("authenticate"))
.collect::<Vec<_>>(),
["session/load", "authenticate", "authenticate github_oauth", "session/load", "session/prompt"],
);
// If `authenticate` fails during `session/load`, fallback to `session/new` does not try it again.
mgr2.shutdown();
let agent3 = Arc::new(FakeAgent {
auth_on_load: true,
auth_on_new: true,
request_error: Some((-32000, "Authentication required".into())),
auth_methods: methods,
..Default::default()
});
let mgr3 = manager(tmp.path(), agent3.clone());
mgr3.prompt(&task.id, text("again"), false).await.unwrap();
wait_for(&mgr3, &task.id, AgentStatus::Failed).await;
assert_eq!(
agent3
.calls
.lock()
.iter()
.filter(|c| c.starts_with("session/") || c.starts_with("authenticate"))
.collect::<Vec<_>>(),
["session/load", "authenticate", "session/new"],
);
mgr3.shutdown();
}
#[tokio::test(flavor = "multi_thread")]
async fn commands_are_remembered_per_project_and_merged_with_skills_on_disk() {
let tmp = tempfile::tempdir().unwrap();
@@ -2619,10 +2521,10 @@ async fn session_settings_win_over_discovery_in_memory_and_on_disk() {
let saved = options("saved", "low");
let discovered = options("discovered", "high");
if discovery_first {
mgr.shared.remember_discovered("claude", &discovered, &[], &[]);
mgr.shared.remember_discovered("claude", &discovered, &[]);
}
mgr.shared.remember("claude", Some(&saved), None, Some("saved"));
mgr.shared.remember_discovered("claude", &discovered, &[], &[]);
mgr.shared.remember_discovered("claude", &discovered, &[]);
let restored = manager(tmp.path(), Arc::new(FakeAgent::default()));
for mgr in [&mgr, &restored] {
assert_eq!(model_of(&mgr.shared.known_config("claude")).as_deref(), Some("saved"));
@@ -2631,31 +2533,6 @@ async fn session_settings_win_over_discovery_in_memory_and_on_disk() {
}
}
#[tokio::test(flavor = "multi_thread")]
async fn discovered_effort_levels_fill_models_no_session_has_reported() {
let tmp = tempfile::tempdir().unwrap();
let mgr = manager(tmp.path(), Arc::new(FakeAgent::default()));
let effort = |values: &[&str], current: &str| {
config::options_of(&json!({ "configOptions": [
{ "id": "effort", "category": "thought_level", "type": "select", "currentValue": current,
"options": values.iter().map(|v| json!({ "value": v })).collect::<Vec<_>>() }
] }))
};
let model = config::options_of(&json!({ "configOptions": [
{ "id": "model", "category": "model", "type": "select", "currentValue": "sonnet",
"options": [{ "value": "sonnet" }, { "value": "opus" }] }
] }));
// A session already reported sonnet's levels; discovery adds opus's.
let reported = [model.clone(), effort(&["low", "high"], "high")].concat();
mgr.shared.remember("claude", Some(&reported), None, Some("sonnet"));
let levels =
[("sonnet".to_owned(), effort(&["low"], "low")), ("opus".to_owned(), effort(&["low", "max"], "default"))];
mgr.shared.remember_discovered("claude", &model, &[], &levels);
let known = mgr.shared.known.lock();
assert_eq!(known["claude"].thought_levels["sonnet"], effort(&["low", "high"], "high"), "the session's report wins");
assert_eq!(known["claude"].thought_levels["opus"], effort(&["low", "max"], "default"));
}
#[test]
fn streamed_text_is_sent_as_appends() {
let mut streamed = HashMap::new();
@@ -2691,82 +2568,3 @@ fn streamed_text_is_sent_as_appends() {
let rewritten = entry_event("t", &mut streamed, None, 5, &agent(&format!("{}x!??", "é".repeat(4999))));
assert!(matches!(rewritten, AgentEvent::Entry { .. }), "a rewritten end is sent whole");
}
#[test]
fn error_messages_keep_the_agents_details() {
let details = json!({ "details": "spawn claude ENOENT" });
assert_eq!(with_details("Internal error".into(), Some(&details)), "Internal error: spawn claude ENOENT");
assert_eq!(
with_details("Internal error".into(), Some(&json!("model not found"))),
"Internal error: model not found"
);
assert_eq!(with_details(String::new(), Some(&details)), "spawn claude ENOENT");
assert_eq!(with_details("spawn claude ENOENT".into(), Some(&details)), "spawn claude ENOENT");
assert_eq!(with_details("Internal error".into(), Some(&json!({ "other": 1 }))), "Internal error");
assert_eq!(with_details("Internal error".into(), None), "Internal error");
}
#[tokio::test(flavor = "multi_thread")]
async fn rolling_back_restores_the_start_of_the_task_and_keeps_the_users_own_edits() {
let tmp = tempfile::tempdir().unwrap();
let dir = dunce::canonicalize(tmp.path()).unwrap();
let git = |args: &[&str]| {
let ok = std::process::Command::new("git")
.args(["-c", "user.name=t", "-c", "user.email=t@t", "-c", "commit.gpgsign=false"])
.args(args)
.current_dir(&dir)
.status()
.unwrap()
.success();
assert!(ok, "{args:?}");
};
let write = |rel: &str, text: &str| std::fs::write(dir.join(rel), text).unwrap();
let read = |rel: &str| std::fs::read_to_string(dir.join(rel)).unwrap();
git(&["init", "-q", "-b", "main"]);
write(".gitignore", "store/\nworktrees/\nagents/\nmodels.json\n");
write("mine.txt", "base\n");
write("other.txt", "base\n");
git(&["add", "."]);
git(&["commit", "-q", "-m", "init"]);
// The user's own uncommitted edit, before the task starts.
write("mine.txt", "my edit\n");
let mgr = manager(&dir, Arc::new(FakeAgent::default()));
let task = mgr
.create(NewAgentTask {
project_root: None,
prompt: text("Hello"),
provider: "claude".into(),
config: Vec::new(),
isolation: Isolation::Local,
base: None,
})
.await
.unwrap();
wait_for(&mgr, &task.id, AgentStatus::NeedsInput).await;
mgr.cancel(&task.id, None).unwrap();
wait_for(&mgr, &task.id, AgentStatus::Ready).await;
// What the agent did.
write("mine.txt", "my edit\nand the agent's\n");
write("other.txt", "agent\n");
write("new.txt", "agent\n");
async fn changed(mgr: &AgentManager, id: &str) -> Vec<String> {
mgr.changes(id).await.unwrap().into_iter().map(|c| c.rel_path).collect()
}
assert_eq!(changed(&mgr, &task.id).await, ["mine.txt", "new.txt", "other.txt"]);
mgr.rollback_changes(&task.id, Some(vec!["other.txt".into()])).await.unwrap();
assert_eq!(read("other.txt"), "base\n");
assert_eq!(changed(&mgr, &task.id).await, ["mine.txt", "new.txt"]);
// After a restart, from the saved copy.
mgr.shutdown();
let mgr = manager(&dir, Arc::new(FakeAgent::default()));
mgr.rollback_changes(&task.id, None).await.unwrap();
assert_eq!(read("mine.txt"), "my edit\n", "the user's edit stays");
assert!(!dir.join("new.txt").exists());
assert!(changed(&mgr, &task.id).await.is_empty());
mgr.delete(&task.id, false).await.unwrap();
assert!(!dir.join("store").join(format!("{}.before", task.id)).exists());
}
+5 -81
View File
@@ -93,9 +93,8 @@ fn retrying(attempts: u32, pause: Duration, mut op: impl FnMut() -> std::io::Res
pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
let Some(repo) = Repo::discover(cwd)? else { return Ok(Vec::new()) };
let root = repo.root().to_path_buf();
let stats: std::collections::HashMap<String, (u32, u32)> =
repo.numstat_with_worktree(base)?.into_iter().map(|(p, a, r)| (p, (a, r))).collect();
let stat = |rel: &str| stats.get(rel).copied().unwrap_or((0, 0));
let stats = repo.numstat_with_worktree(base)?;
let stat = |rel: &str| stats.iter().find(|(p, ..)| p == rel).map_or((0, 0), |&(_, a, r)| (a, r));
let mut out: Vec<AgentChange> = repo
.diff_with_worktree(base)?
.into_iter()
@@ -104,9 +103,8 @@ pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
AgentChange { path: IpcPath(root.join(&f.path)), rel_path: f.path, kind: f.kind, added, removed }
})
.collect();
let tracked: std::collections::HashSet<String> = out.iter().map(|c| c.rel_path.clone()).collect();
for s in repo.status()? {
if s.unstaged == Some(ChangeKind::Untracked) && !tracked.contains(&s.rel_path) {
if s.unstaged == Some(ChangeKind::Untracked) && !out.iter().any(|c| c.rel_path == s.rel_path) {
let added = std::fs::read_to_string(&*s.path).map_or(0, |t| t.lines().count() as u32);
out.push(AgentChange { path: s.path, rel_path: s.rel_path, kind: ChangeKind::Added, added, removed: 0 });
}
@@ -118,7 +116,7 @@ pub(crate) fn changes(cwd: &Path, base: &str) -> IdeResult<Vec<AgentChange>> {
/// Size and modification time of a file, `None` once it is gone.
pub(crate) type Stamp = Option<(u64, u128)>;
pub(crate) fn stamp(path: &Path) -> Stamp {
fn stamp(path: &Path) -> Stamp {
let meta = std::fs::metadata(path).ok()?;
let modified = meta.modified().ok()?.duration_since(UNIX_EPOCH).ok()?.as_nanos();
Some((meta.len(), modified))
@@ -126,10 +124,7 @@ pub(crate) fn stamp(path: &Path) -> Stamp {
/// The files already changed in `cwd` against `HEAD`, stamped so later edits to them show.
pub(crate) fn snapshot(cwd: &Path) -> IdeResult<BTreeMap<String, Stamp>> {
// Paths and stamps only: no diff and no line counts, which read every untracked file
// and held up starting a task in a checkout with many of them.
let Some(repo) = Repo::discover(cwd)? else { return Ok(BTreeMap::new()) };
Ok(repo.status()?.into_iter().map(|s| (s.rel_path, stamp(&s.path))).collect())
Ok(changes(cwd, "HEAD")?.into_iter().map(|c| (c.rel_path, stamp(&c.path))).collect())
}
/// Drops the changes that were there before the task and haven't been touched since.
@@ -137,77 +132,6 @@ pub(crate) fn without_untouched(changes: Vec<AgentChange>, before: &BTreeMap<Str
changes.into_iter().filter(|c| before.get(&c.rel_path).is_none_or(|s| *s != stamp(&c.path))).collect()
}
/// Files larger than this that were changed before the task keep no copy: they can't be rolled back.
const SAVED_MAX: u64 = 8 * 1024 * 1024;
fn saved_name(rel: &str) -> String {
use std::hash::{DefaultHasher, Hash, Hasher};
let mut hash = DefaultHasher::new();
rel.hash(&mut hash);
format!("{:016x}", hash.finish())
}
/// Copies the files in `before` (already changed in the checkout at `cwd` when the task started)
/// into `dir`, so rolling back the task's changes to them restores the user's own edits.
/// Whether anything was saved.
pub(crate) fn save_before(cwd: &Path, before: &BTreeMap<String, Stamp>, dir: &Path) -> IdeResult<bool> {
let Some(repo) = Repo::discover(cwd)? else { return Ok(false) };
let mut saved = false;
for (rel, stamp) in before {
let path = repo.root().join(rel);
if stamp.is_none() || !std::fs::metadata(&path).is_ok_and(|m| m.is_file() && m.len() <= SAVED_MAX) {
continue;
}
std::fs::create_dir_all(dir)?;
std::fs::copy(&path, dir.join(saved_name(rel)))?;
saved = true;
}
Ok(saved)
}
/// Rolls `change` back: to the copy saved when the task started when the file had changes
/// then (`before`, `saved` holding the copies), otherwise to `base` (removed when `base`
/// lacks it).
pub(crate) fn restore(
cwd: &Path,
base: &str,
change: &AgentChange,
before: &BTreeMap<String, Stamp>,
saved: Option<&Path>,
) -> IdeResult<()> {
let path = &change.path.0;
let content = match before.get(&change.rel_path) {
Some(None) => None,
Some(Some(_)) => {
let copy =
saved.map(|d| d.join(saved_name(&change.rel_path))).filter(|p| p.is_file()).ok_or_else(|| {
IdeError::invalid(format!(
"{} had changes of yours when the task started that weren't saved; roll it back in Git instead",
change.rel_path
))
})?;
Some(std::fs::read(copy)?)
}
None => {
let repo = Repo::discover(cwd)?.ok_or_else(|| IdeError::invalid("not in a git repository"))?;
repo.file_bytes_at(path, Some(base))?
}
};
match content {
Some(bytes) => {
if let Some(parent) = path.parent() {
std::fs::create_dir_all(parent)?;
}
std::fs::write(path, bytes)?;
}
None => match std::fs::remove_file(path) {
Err(e) if e.kind() != std::io::ErrorKind::NotFound => return Err(e.into()),
_ => {}
},
}
Ok(())
}
pub(crate) fn file_at(cwd: &Path, path: &Path, rev: &str) -> IdeResult<Option<String>> {
let Some(repo) = Repo::discover(cwd)? else { return Ok(None) };
let encoding = match ide_vfs::load_text(path) {
+22 -110
View File
@@ -79,26 +79,23 @@ fn scan(
Ok(())
}
/// One planned step as fingerprinted: resolved program, args, cwd and env.
type StepFingerprint = (PathBuf, Vec<String>, PathBuf, BTreeMap<String, String>);
/// Environment, planned steps and input paths shared by every Maven build
/// fingerprint: the filtered process environment plus the wrapper, settings
/// and JDK files the planned invocation reads.
struct Collected {
inputs: Vec<PathBuf>,
environment: BTreeMap<String, String>,
steps: Vec<StepFingerprint>,
inherited_hash: u64,
}
fn collect(
/// `None` means an input cannot be resolved safely: build normally without reuse.
/// All filesystem work belongs on the caller's blocking thread.
pub fn launch_fingerprint(
root: &Path,
projects: &[&maven::MavenProject],
plan: &BuildPlan,
model: &BuildModel,
module: &Path,
test: bool,
local_repo: Option<PathBuf>,
) -> IdeResult<Option<Collected>> {
let Some(mut inputs) = maven::launch_inputs(root, projects, local_repo) else { return Ok(None) };
cancel: &CancellationToken,
) -> IdeResult<Option<LaunchFingerprint>> {
let Some(m) = &model.maven else { return Ok(None) };
let projects = maven_launch_projects(root, m, module, test);
if projects.is_empty() {
return Ok(None);
}
let Some(mut inputs) = maven::launch_inputs(root, &projects, local_repo) else { return Ok(None) };
let plan = launch_plan(root, model, module, test, BuildKind::Build)?;
let mut environment: BTreeMap<String, String> = std::env::vars()
.map(|(key, value)| (key.to_ascii_uppercase(), value))
.filter(|(key, _)| {
@@ -168,111 +165,26 @@ fn collect(
Path::new(home).join(if cfg!(windows) { "bin/java.exe" } else { "bin/java" }),
]);
}
let steps = plan
.steps
.iter()
.map(|s| (process::program_path(&s.program, &s.env), s.args.clone(), s.cwd.clone(), s.env.clone()))
.collect();
let steps: Vec<_> =
plan.steps.iter().map(|s| (process::program_path(&s.program, &s.env), &s.args, &s.cwd, &s.env)).collect();
// Profiles and plugins can read arbitrary environment variables. Keep a signature
// of the inherited environment without persisting unrelated credentials.
let inherited: BTreeMap<_, _> = std::env::vars_os().collect();
let mut inherited_hash = std::hash::DefaultHasher::new();
inherited.hash(&mut inherited_hash);
Ok(Some(Collected { inputs, environment, steps, inherited_hash: inherited_hash.finish() }))
}
/// Scans every input, storing project inputs relative to the project.
fn scan_all(
root: &Path,
inputs: Vec<PathBuf>,
cancel: &CancellationToken,
) -> IdeResult<BTreeMap<PathBuf, Option<Stamp>>> {
let parameters =
serde_json::to_string(&(root, module, test, steps, environment, inherited_hash.finish(), projects))
.map_err(|e| IdeError::internal(e.to_string()))?;
let mut files = BTreeMap::new();
for path in inputs {
scan(root, &path, &mut files, &mut HashSet::new(), cancel)?;
}
// Store project inputs relative to the project, including each file's relative path.
Ok(files.into_iter().map(|(p, stamp)| (p.strip_prefix(root).unwrap_or(&p).to_path_buf(), stamp)).collect())
}
/// `None` means an input cannot be resolved safely: build normally without reuse.
/// All filesystem work belongs on the caller's blocking thread.
pub fn launch_fingerprint(
root: &Path,
model: &BuildModel,
module: &Path,
test: bool,
local_repo: Option<PathBuf>,
cancel: &CancellationToken,
) -> IdeResult<Option<LaunchFingerprint>> {
let Some(m) = &model.maven else { return Ok(None) };
let projects = maven_launch_projects(root, m, module, test);
if projects.is_empty() {
return Ok(None);
}
let plan = launch_plan(root, model, module, test, BuildKind::Build)?;
let Some(collected) = collect(root, &projects, &plan, local_repo)? else { return Ok(None) };
let Collected { inputs, environment, steps, inherited_hash } = collected;
let parameters = serde_json::to_string(&(root, module, test, steps, environment, inherited_hash, projects))
.map_err(|e| IdeError::internal(e.to_string()))?;
Ok(Some(LaunchFingerprint { version: 2, parameters, files: scan_all(root, inputs, cancel)? }))
}
/// Inputs fingerprint of a menu build (`Build Project` / `Build Module`): the
/// built modules' sources, resources and POM chain plus the exact planned
/// steps, so an unchanged project skips Maven entirely (#2476). Only `Build`
/// callers reuse it, never `Rebuild` or `Artifacts`; `None` disables reuse.
/// All filesystem work belongs on the caller's blocking thread.
pub fn menu_fingerprint(
root: &Path,
model: &BuildModel,
file: Option<&Path>,
cancel: &CancellationToken,
) -> IdeResult<Option<LaunchFingerprint>> {
let plan = plan(root, model, BuildKind::Build, file, None)?;
if plan.system != BuildSystem::Maven {
return Ok(None);
}
let Some(m) = &model.maven else { return Ok(None) };
let projects: Vec<&maven::MavenProject> = match file {
Some(file) => {
// The innermost linked project owning the file, as in single-file compilation.
let rel = rel_str(root, file);
let module = m
.projects
.iter()
.filter(|p| rel == p.dir || rel.starts_with(&format!("{}/", p.dir)) || p.dir.is_empty())
.max_by_key(|p| p.dir.len());
match module {
Some(project) if project.packaging != "pom" => {
maven_launch_projects(root, m, &subdir(root, &project.dir), true)
}
_ => return Ok(None),
}
}
// A project build walks every linked project.
None => m.projects.iter().collect(),
};
if projects.is_empty() {
return Ok(None);
}
let Some(collected) = collect(root, &projects, &plan, None)? else { return Ok(None) };
let Collected { inputs, environment, steps, inherited_hash } = collected;
let scope = file.map(|f| rel_str(root, f));
let parameters = serde_json::to_string(&("menu-build", scope, steps, environment, inherited_hash))
.map_err(|e| IdeError::internal(e.to_string()))?;
Ok(Some(LaunchFingerprint { version: 2, parameters, files: scan_all(root, inputs, cancel)? }))
let files = files.into_iter().map(|(p, stamp)| (p.strip_prefix(root).unwrap_or(&p).to_path_buf(), stamp)).collect();
Ok(Some(LaunchFingerprint { version: 2, parameters, files }))
}
impl LaunchFingerprint {
/// Folders (relative to the project) of the Maven projects whose POM is an input.
pub(super) fn project_dirs(&self) -> impl Iterator<Item = &Path> {
self.files
.keys()
.filter(|p| p.is_relative() && p.file_name().is_some_and(|n| n == "pom.xml"))
.map(|pom| pom.parent().unwrap_or(Path::new("")))
}
/// Relative paths whose content changed while `(length, mtime)` stayed the same
/// compared to `previous` (timestamp-preserving external edits, coarse-granularity
/// filesystems). Timestamp-incremental builders (Maven, the Kotlin plugin) would
@@ -1,253 +0,0 @@
//! Resources a Gradle build changes while copying them (filters, `expand`, renames, extra
//! sources). The Java language server copies them as they are into Buildship's
//! `bin/<source set>` folders, which launches run from; IntelliJ IDEA runs Gradle's copy.
//! Before a launch, Gradle processes them and its output replaces those plain copies, so
//! each resource is on the classpath once, as the build produces it.
use super::{BuildPlan, BuildStep, BuildSystem, Format, run, subdir};
use crate::BuildModel;
use crate::gradle::{self, GradleModel, ReportedProject};
use ide_core::{CancellationToken, IdeError, IdeResult, Severity};
use std::fs;
use std::path::{Path, PathBuf};
/// A source set whose resources Gradle processes, with the folder the launch reads them from.
#[derive(Debug, PartialEq)]
struct Target {
/// Task path from the root build (`:app:processResources`).
task: String,
/// Where the task writes the resources.
output: PathBuf,
/// The Java language server's output folder of the source set, on the launch classpath.
jdtls: PathBuf,
}
fn targets(reported: &[ReportedProject], class_paths: &[String]) -> Vec<Target> {
// buildSrc is built before the build, never addressable as `:buildSrc:<task>`.
let addressable = |p: &&ReportedProject| !p.build.as_deref().is_some_and(|b| b.ends_with(":buildSrc"));
let sets: Vec<_> = reported
.iter()
.filter(addressable)
.flat_map(|p| p.source_sets.iter().filter_map(move |s| Some((p, s, s.processed.as_ref()?))))
.collect();
if sets.is_empty() {
return Vec::new();
}
// Canonical, as Gradle reports its folders: jdtls may spell them differently.
let entries: Vec<PathBuf> = class_paths.iter().filter_map(|p| dunce::canonicalize(p).ok()).collect();
sets.into_iter()
.filter_map(|(p, set, resources)| {
// Buildship's output folder of the source set.
let jdtls = dunce::canonicalize(Path::new(&p.dir).join("bin").join(&set.name)).ok()?;
let project = if p.path == ":" { "" } else { p.path.as_str() };
entries.contains(&jdtls).then(|| Target {
task: format!("{project}:{}", resources.task),
output: PathBuf::from(&resources.dir),
jdtls,
})
})
.collect()
}
/// Before a JVM launch from the Java language server's output folders on `class_paths`:
/// runs the Gradle tasks that process resources of those folders' source sets (see the
/// module docs) and copies their output over the plain copies. `cache_dir` holds the
/// linked builds' last syncs. Returns the tasks run, none for builds that copy their
/// resources as they are.
pub fn process_launch_resources(
root: &Path,
model: &BuildModel,
cache_dir: &Path,
class_paths: &[String],
cancel: &CancellationToken,
) -> IdeResult<Vec<String>> {
// A composite also reports the builds it includes: the deepest build owning a folder runs its task.
let mut builds: Vec<&GradleModel> = model.gradle.iter().collect();
builds.sort_by_key(|g| std::cmp::Reverse(subdir(root, &g.dir).components().count()));
let mut done: Vec<PathBuf> = Vec::new();
let mut tasks = Vec::new();
for g in builds {
let reported = crate::sync::reported_gradle_projects(&gradle::cache_dir(cache_dir, &g.dir));
let targets: Vec<Target> =
targets(&reported, class_paths).into_iter().filter(|t| !done.contains(&t.jdtls)).collect();
if targets.is_empty() {
continue;
}
let mut step = BuildStep::new(&g.command, &["--console=plain"], &subdir(root, &g.dir), Format::Gradle);
step.args.extend(targets.iter().map(|t| t.task.clone()));
step.env = g.env.clone();
let plan = BuildPlan { system: BuildSystem::Gradle, title: "Process resources".into(), steps: vec![step] };
let result = run(root, &plan, cancel, &|_| {})?;
if !result.success {
let errors: Vec<&str> = result
.messages
.iter()
.filter(|m| m.severity == Severity::Error)
.take(5)
.map(|m| m.text.as_str())
.collect();
return Err(IdeError::internal(errors.join("\n")));
}
for t in targets {
if cancel.is_cancelled() {
return Err(IdeError::cancelled());
}
overlay(&t.output, &t.output, &t.jdtls)?;
done.push(t.jdtls);
tasks.push(t.task);
}
}
Ok(tasks)
}
/// Copies the files under `dir` to the same place under `to` (relative to `base`) where
/// they differ, so unchanged resources are not rewritten on every launch.
fn overlay(base: &Path, dir: &Path, to: &Path) -> IdeResult<()> {
let entries = match fs::read_dir(dir) {
// No resources: the task had nothing to copy.
Err(e) if e.kind() == std::io::ErrorKind::NotFound => return Ok(()),
entries => entries?,
};
for entry in entries {
let entry = entry?;
let path = entry.path();
let kind = entry.file_type()?;
if kind.is_dir() {
overlay(base, &path, to)?;
} else if kind.is_file() {
let dest = to.join(path.strip_prefix(base).map_err(|e| IdeError::internal(e.to_string()))?);
if !same_content(&path, &dest) {
if let Some(parent) = dest.parent() {
fs::create_dir_all(parent)?;
}
fs::copy(&path, &dest)?;
}
}
}
Ok(())
}
fn same_content(a: &Path, b: &Path) -> bool {
match (fs::metadata(a), fs::metadata(b)) {
(Ok(m), Ok(n)) if m.len() == n.len() => matches!((fs::read(a), fs::read(b)), (Ok(x), Ok(y)) if x == y),
_ => false,
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::gradle::{ProcessedResources, ReportedSourceSet};
fn write(path: &Path, text: &str) {
fs::create_dir_all(path.parent().unwrap()).unwrap();
fs::write(path, text).unwrap();
}
fn set(name: &str, processed: Option<&Path>) -> ReportedSourceSet {
ReportedSourceSet {
name: name.into(),
test: name == "test",
processed: processed.map(|dir| ProcessedResources {
task: if name == "main" { "processResources".into() } else { "processTestResources".into() },
dir: dir.to_string_lossy().into_owned(),
}),
..Default::default()
}
}
fn project(path: &str, dir: &Path, sets: Vec<ReportedSourceSet>) -> ReportedProject {
ReportedProject {
path: path.into(),
dir: dir.to_string_lossy().into_owned(),
source_sets: sets,
..Default::default()
}
}
/// Only processed source sets whose jdtls output is on the classpath: the launched
/// module, upstream modules of the build, tests only for a test classpath; never buildSrc.
#[test]
fn targets_are_processed_sets_on_the_classpath() {
let tmp = tempfile::tempdir().unwrap();
let root = dunce::canonicalize(tmp.path()).unwrap();
let (app, lib, plain, src) = (root.join("app"), root.join("lib"), root.join("plain"), root.join("buildSrc"));
for dir in [&root, &app, &lib, &plain, &src] {
for set in ["main", "test"] {
fs::create_dir_all(dir.join("bin").join(set)).unwrap();
}
}
let out = |dir: &Path, set: &str| dir.join("build/resources").join(set);
let mut build_src = project(":buildSrc", &src, vec![set("main", Some(&out(&src, "main")))]);
build_src.build = Some(":buildSrc".into());
let reported = [
project(":", &root, vec![set("main", Some(&out(&root, "main")))]),
project(":app", &app, vec![set("main", Some(&out(&app, "main"))), set("test", Some(&out(&app, "test")))]),
project(":lib", &lib, vec![set("main", Some(&out(&lib, "main")))]),
project(":plain", &plain, vec![set("main", None)]),
build_src,
];
let entry = |dir: &Path, set: &str| dir.join("bin").join(set).to_string_lossy().into_owned();
let runtime = [
entry(&app, "main"),
// Spelled differently from Gradle's canonical folders.
format!("{}/", entry(&lib, "main")),
entry(&plain, "main"),
entry(&src, "main"),
"/m2/spring-core.jar".into(),
];
let tasks = |cp: &[String]| targets(&reported, cp).into_iter().map(|t| t.task).collect::<Vec<_>>();
assert_eq!(tasks(&runtime), [":app:processResources", ":lib:processResources"]);
let mut test = runtime.to_vec();
test.insert(0, entry(&app, "test"));
assert_eq!(tasks(&test), [":app:processResources", ":app:processTestResources", ":lib:processResources"]);
assert_eq!(tasks(&[entry(&root, "main")]), [":processResources"], "the root project");
let app_targets = targets(&reported, &runtime);
let t = &app_targets[0];
assert_eq!(
(t.output.as_path(), t.jdtls.as_path()),
(out(&app, "main").as_path(), app.join("bin/main").as_path())
);
let unprocessed = [project(":app", &app, vec![set("main", None)])];
assert!(targets(&unprocessed, &runtime).is_empty());
}
/// The processed copy replaces jdtls's plain one (the reported `@version@` case), new
/// files are added, identical ones are left alone and files Gradle doesn't produce stay.
#[test]
fn overlay_replaces_plain_copies_with_gradle_output() {
let tmp = tempfile::tempdir().unwrap();
let (output, jdtls) = (tmp.path().join("build/resources/main"), tmp.path().join("bin/main"));
write(&output.join("application.yaml"), "spring:\n application:\n version: 0.0.1\n");
write(&output.join("static/extra.txt"), "from an extra source");
write(&output.join("migrations/V1__init.sql"), "create table t (id int);");
write(&jdtls.join("application.yaml"), "spring:\n application:\n version: @version@\n");
write(&jdtls.join("migrations/V1__init.sql"), "create table t (id int);");
write(&jdtls.join("com/example/App.class"), "bytecode");
let unchanged = fs::metadata(jdtls.join("migrations/V1__init.sql")).unwrap().modified().unwrap();
std::thread::sleep(std::time::Duration::from_millis(20));
overlay(&output, &output, &jdtls).unwrap();
let read = |rel: &str| fs::read_to_string(jdtls.join(rel)).unwrap();
assert_eq!(read("application.yaml"), "spring:\n application:\n version: 0.0.1\n");
assert_eq!(read("static/extra.txt"), "from an extra source");
assert_eq!(read("com/example/App.class"), "bytecode");
let modified = fs::metadata(jdtls.join("migrations/V1__init.sql")).unwrap().modified().unwrap();
assert_eq!(modified, unchanged, "identical files are not rewritten");
overlay(&tmp.path().join("missing"), &tmp.path().join("missing"), &jdtls).unwrap();
}
#[test]
fn builds_without_processed_resources_run_nothing() {
let tmp = tempfile::tempdir().unwrap();
// Running this command would fail the call.
let missing = tmp.path().join("missing-gradle").to_string_lossy().into_owned();
let model =
BuildModel { gradle: vec![GradleModel { command: missing, ..Default::default() }], ..Default::default() };
let class_paths = [tmp.path().join("bin/main").to_string_lossy().into_owned()];
let tasks =
process_launch_resources(tmp.path(), &model, tmp.path(), &class_paths, &CancellationToken::new()).unwrap();
assert!(tasks.is_empty());
}
}
+6 -55
View File
@@ -4,17 +4,9 @@
//! for the Build tool window, the Problems view and the editor.
mod fingerprint;
mod launch_resources;
mod parse;
mod single;
mod up_to_date;
pub use fingerprint::{LaunchFingerprint, launch_fingerprint, menu_fingerprint};
pub use launch_resources::process_launch_resources;
pub use single::{
SingleFileTarget, compile_file_plan, find_javac, javac_step, single_file_classpath, single_file_target,
};
pub use up_to_date::{menu_up_to_date, record_menu_build};
pub use fingerprint::{LaunchFingerprint, launch_fingerprint};
use crate::process::{self, Stream};
use crate::{BuildModel, maven};
@@ -271,12 +263,7 @@ pub(super) fn maven_steps(
return Err(IdeError::not_found("no Maven project found"));
}
let step = |p: &maven::MavenProject, extra: &[String]| {
let mut s = BuildStep::new(
&p.command,
&["-B", "-Dstyle.color=never", maven::LOCAL_REPO_TRACKING_ARG],
&subdir(root, &p.dir),
Format::Maven,
);
let mut s = BuildStep::new(&p.command, &["-B", "-Dstyle.color=never"], &subdir(root, &p.dir), Format::Maven);
s.args.extend(p.options.iter().cloned());
s.args.extend(extra.iter().cloned());
s.args.extend(goals.iter().map(|g| (*g).to_owned()));
@@ -1057,21 +1044,9 @@ mod tests {
assert_eq!(p.system, BuildSystem::Maven);
assert_eq!(p.title, "demo");
assert_eq!(p.steps.len(), 1);
assert_eq!(p.steps[0].args, ["-B", "-Dstyle.color=never", maven::LOCAL_REPO_TRACKING_ARG, "test-compile"]);
assert_eq!(p.steps[0].args, ["-B", "-Dstyle.color=never", "test-compile"]);
let p = plan(&root, &model, BuildKind::Rebuild, Some(&root.join("core/src/main/java/A.java")), None).unwrap();
assert_eq!(
p.steps[0].args,
[
"-B",
"-Dstyle.color=never",
maven::LOCAL_REPO_TRACKING_ARG,
"-pl",
"core",
"-am",
"clean",
"test-compile"
]
);
assert_eq!(p.steps[0].args, ["-B", "-Dstyle.color=never", "-pl", "core", "-am", "clean", "test-compile"]);
assert_eq!(p.steps[0].cwd, root);
assert_eq!(p.title, "demo: build module 'core'");
@@ -1345,36 +1320,12 @@ mod tests {
assert_eq!(step.cwd, root);
assert_eq!(step.program, "mvnw");
assert_eq!(step.env["JAVA_HOME"], "/jdk");
assert_eq!(
step.args,
[
"-B",
"-Dstyle.color=never",
maven::LOCAL_REPO_TRACKING_ARG,
"-s",
"settings.xml",
"-pl",
"app",
"-am",
goal
]
);
assert_eq!(step.args, ["-B", "-Dstyle.color=never", "-s", "settings.xml", "-pl", "app", "-am", goal]);
// Rebuild cleans first, as IDEA's Rebuild does.
let plan = launch_plan(root, &model, &root.join("app"), test, BuildKind::Rebuild).unwrap();
assert_eq!(
plan.steps[0].args,
[
"-B",
"-Dstyle.color=never",
maven::LOCAL_REPO_TRACKING_ARG,
"-s",
"settings.xml",
"-pl",
"app",
"-am",
"clean",
goal
]
["-B", "-Dstyle.color=never", "-s", "settings.xml", "-pl", "app", "-am", "clean", goal]
);
}
}
+26 -1
View File
@@ -7,7 +7,6 @@
//! [`super::resolve`] turns them into IDE coordinates.
use ide_core::Severity;
pub(crate) use ide_core::output_encoding::strip_ansi;
use serde_json::Value;
/// Output dialect of a build step.
@@ -99,6 +98,32 @@ pub(crate) struct OutputParser {
pending: Option<Pending>,
}
/// Removes ANSI escape sequences (colour, cursor movement).
pub(crate) fn strip_ansi(s: &str) -> String {
if !s.contains('\u{1b}') {
return s.to_owned();
}
let mut out = String::with_capacity(s.len());
let mut chars = s.chars().peekable();
while let Some(c) = chars.next() {
if c != '\u{1b}' {
out.push(c);
continue;
}
if chars.peek() == Some(&'[') {
chars.next();
for c in chars.by_ref() {
if c.is_ascii_alphabetic() || c == '~' {
break;
}
}
} else {
chars.next();
}
}
out
}
fn num(s: &str) -> Option<u32> {
s.trim().parse().ok().filter(|n| *n > 0)
}
-331
View File
@@ -1,331 +0,0 @@
//! Single-file Java compilation with `javac` for the Compile File action (#2476).
//!
//! A module build (`-pl … -am`) still walks every upstream module, and packaging
//! walks the whole reactor; compiling one file only needs that file's module
//! outputs plus its dependency classpath, which is much faster to assemble.
use super::*;
use std::fs;
use std::process::Command as ProcCommand;
/// Output file of the `dependency:build-classpath` probe, relative to each module.
const CP_FILE: &str = "target/ide-compile-cp.txt";
/// A `.java` source and the module build that compiles it.
pub struct SingleFileTarget {
/// Absolute module directory.
pub module: PathBuf,
/// The source is under `src/test`: compile to test classes with the test classpath.
pub test: bool,
/// Absolute `target/classes` (or `target/test-classes`).
pub out_dir: PathBuf,
/// Reactor root building the module (owns the Maven command and options).
pub top: maven::MavenProject,
/// `-pl` value of the module relative to the reactor root; empty when the
/// module is the root itself.
pub pl: String,
/// `maven.compiler.release` (or equivalent) of the module's project.
pub java_version: Option<u32>,
}
/// Locates the linked Maven module owning a `.java` source file.
pub fn single_file_target(root: &Path, model: &BuildModel, file: &Path) -> IdeResult<SingleFileTarget> {
if file.extension().is_none_or(|ext| ext != "java") {
return Err(IdeError::invalid("only Java sources can be compiled as a single file"));
}
if !file.is_file() {
return Err(IdeError::not_found("no Java source found for single-file compilation"));
}
let Some(m) = &model.maven else {
return Err(IdeError::not_found("no linked Maven project found for module"));
};
// The innermost project whose directory contains the file owns it; the
// aggregator root (`""`) is a prefix of everything, so take the longest match.
let rel = rel_str(root, file);
let project = m
.projects
.iter()
.filter(|p| rel == p.dir || rel.starts_with(&format!("{}/", p.dir)) || p.dir.is_empty())
.max_by_key(|p| p.dir.len())
.ok_or_else(|| IdeError::not_found("no linked Maven project found for module"))?;
if project.packaging == "pom" {
// An aggregator owns no sources itself: a file that only matches it
// belongs to no linked module.
return Err(IdeError::not_found("no linked Maven project found for module"));
}
let module = subdir(root, &project.dir);
let top = maven_reactor(m, &project.dir)
.ok_or_else(|| IdeError::not_found("no linked Maven project found for module"))?;
let top_dir = subdir(root, &top.dir);
let pl = module.strip_prefix(&top_dir).map(|r| r.to_string_lossy().replace('\\', "/")).unwrap_or_default();
// Test sources see the test classpath and compile into test classes.
let parts: Vec<&str> = rel.split('/').collect();
let test = parts.windows(2).any(|w| w == ["src", "test"]);
let out_dir = module.join("target").join(if test { "test-classes" } else { "classes" });
Ok(SingleFileTarget { module, test, out_dir, top: top.clone(), pl, java_version: project.java_version })
}
/// `javac` for the module: its `JAVA_HOME`, else `PATH`.
pub fn find_javac(env: &BTreeMap<String, String>) -> String {
let home = env.get("JAVA_HOME").map(Path::new);
let exe = if cfg!(windows) { "javac.exe" } else { "javac" };
if let Some(javac) = home.map(|h| h.join("bin").join(exe)).filter(|p| p.is_file()) {
return javac.to_string_lossy().into_owned();
}
exe.to_owned()
}
/// Dependency classpath of the module: existing reactor class directories plus
/// `mvn dependency:build-classpath` (which resolves without compiling anything,
/// so `-am` stays cheap). Entries are platform-separated (`;` on Windows).
pub fn single_file_classpath(root: &Path, model: &BuildModel, target: &SingleFileTarget) -> IdeResult<String> {
let mut entries: Vec<String> = Vec::new();
// The module's own classes first: the file almost always uses classes next to it.
let own: &[&str] = if target.test { &["target/test-classes", "target/classes"] } else { &["target/classes"] };
for out in own {
let path = target.module.join(out);
if path.is_dir() {
entries.push(path.to_string_lossy().into_owned());
}
}
if let Some(m) = &model.maven {
// Upstream reactor modules first: their freshly built classes shadow
// installed snapshots of the same artifacts.
for project in maven_launch_projects(root, m, &target.module, target.test) {
let dir = subdir(root, &project.dir);
if dir == target.module {
continue;
}
for classes in ["target/classes", "target/test-classes"] {
let path = dir.join(classes);
if path.is_dir() {
entries.push(path.to_string_lossy().into_owned());
}
}
}
}
let probe = CP_FILE;
let mut args = vec!["-B", "-Dstyle.color=never", maven::LOCAL_REPO_TRACKING_ARG];
args.extend(target.top.options.iter().map(String::as_str));
if !target.pl.is_empty() {
args.extend(["-pl", target.pl.as_str(), "-am"]);
}
let output_arg = format!("-Dmdep.outputFile={probe}");
args.extend(["dependency:build-classpath", output_arg.as_str(), "-Dmdep.includeScope=test", "-q"]);
let top_dir = subdir(root, &target.top.dir);
let status = ProcCommand::new(&target.top.command)
.args(&args)
.envs(&target.top.env)
.current_dir(&top_dir)
.output()
.map_err(|e| IdeError::internal(format!("cannot resolve the compile classpath: {e}")))?;
if !status.status.success() {
let stderr = String::from_utf8_lossy(&status.stderr);
let tail: Vec<&str> = stderr.lines().filter(|l| !l.trim().is_empty()).collect();
let tail = tail.iter().rev().take(5).rev().cloned().collect::<Vec<_>>().join("\n");
return Err(IdeError::internal(format!("cannot resolve the compile classpath:\n{tail}")));
}
// With `-am` every visited module writes its own file; only this module's counts.
let cp_file = target.module.join(probe);
let content = fs::read_to_string(&cp_file).map_err(|e| {
IdeError::internal(format!("cannot resolve the compile classpath: {} ({e})", cp_file.display()))
})?;
let separator = if cfg!(windows) { ';' } else { ':' };
entries.extend(content.split([separator, '\n', '\r']).map(str::trim).filter(|e| !e.is_empty()).map(str::to_owned));
entries.dedup();
Ok(entries.join(&separator.to_string()))
}
/// The `javac` step compiling `file` into `target`'s output directory.
pub fn javac_step(target: &SingleFileTarget, file: &Path, classpath: &str, javac: &str) -> IdeResult<BuildStep> {
fs::create_dir_all(&target.out_dir)
.map_err(|e| IdeError::internal(format!("cannot create {} ({e})", target.out_dir.display())))?;
let mut step = BuildStep::new(javac, &[], &target.module, Format::Gradle);
// Raw `javac` prints `path:line: error: …`, the same form Gradle forwards.
step.args.push("-encoding".into());
step.args.push("UTF-8".into());
step.args.push("-d".into());
step.args.push(target.out_dir.to_string_lossy().into_owned());
step.args.push("-cp".into());
step.args.push(classpath.to_owned());
// Classes of the module that were never built (or are older than their source) are read
// from its sources; only `file` is written, so a test compile never puts main classes
// into test-classes.
let sources = source_roots(target);
if !sources.is_empty() {
let separator = if cfg!(windows) { ";" } else { ":" };
step.args.push("-sourcepath".into());
step.args.push(sources.iter().map(|p| p.to_string_lossy()).collect::<Vec<_>>().join(separator));
step.args.push("-implicit:none".into());
}
if let Some(version) = target.java_version {
step.args.push("--release".into());
step.args.push(version.to_string());
}
step.args.push(file.to_string_lossy().into_owned());
step.env = target.top.env.clone();
Ok(step)
}
/// The module's Java source folders that exist, generated ones included; test sources see
/// the main ones too.
fn source_roots(target: &SingleFileTarget) -> Vec<PathBuf> {
let scopes: &[(&str, &str)] = if target.test {
&[("src/test/java", "target/generated-test-sources"), ("src/main/java", "target/generated-sources")]
} else {
&[("src/main/java", "target/generated-sources")]
};
let mut roots = Vec::new();
for (src, generated) in scopes {
roots.push(target.module.join(src));
let generated = target.module.join(generated);
let mut dirs: Vec<PathBuf> =
fs::read_dir(&generated).into_iter().flatten().flatten().map(|d| d.path()).filter(|p| p.is_dir()).collect();
dirs.sort();
roots.extend(dirs);
}
roots.retain(|p| p.is_dir());
roots
}
/// Resolves the classpath and plans the `javac` invocation for one Java source.
pub fn compile_file_plan(root: &Path, model: &BuildModel, file: &Path) -> IdeResult<BuildPlan> {
let target = single_file_target(root, model, file)?;
let classpath = single_file_classpath(root, model, &target)?;
let javac = find_javac(&target.top.env);
let name = file.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default();
Ok(BuildPlan {
system: BuildSystem::Maven,
title: format!("Compile {name}"),
steps: vec![javac_step(&target, file, &classpath, &javac)?],
})
}
#[cfg(test)]
mod tests {
use super::*;
fn write(root: &Path, rel: &str, value: &str) {
let path = root.join(rel);
fs::create_dir_all(path.parent().unwrap()).unwrap();
fs::write(path, value).unwrap();
}
fn fixture(root: &Path) -> BuildModel {
write(
root,
"pom.xml",
r#"<project><groupId>demo</groupId><artifactId>parent</artifactId><version>1</version>
<packaging>pom</packaging><modules><module>lib</module><module>app</module></modules></project>"#,
);
write(
root,
"lib/pom.xml",
r#"<project><parent><groupId>demo</groupId><artifactId>parent</artifactId><version>1</version></parent>
<artifactId>lib</artifactId></project>"#,
);
write(
root,
"app/pom.xml",
r#"<project><parent><groupId>demo</groupId><artifactId>parent</artifactId><version>1</version></parent>
<artifactId>app</artifactId><dependencies><dependency><groupId>demo</groupId><artifactId>lib</artifactId><version>1</version></dependency></dependencies></project>"#,
);
write(root, "app/src/main/java/demo/Main.java", "class Main {}");
write(root, "app/src/test/java/demo/MainTest.java", "class MainTest {}");
write(root, "lib/target/classes/Lib.class", "built");
crate::load(root, &root.join("cache"), None)
}
#[test]
fn target_finds_the_owning_module_and_the_test_scope() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let main = single_file_target(root, &model, &root.join("app/src/main/java/demo/Main.java")).unwrap();
assert_eq!(main.module, root.join("app"));
assert!(!main.test);
assert_eq!(main.out_dir, root.join("app/target/classes"));
let test = single_file_target(root, &model, &root.join("app/src/test/java/demo/MainTest.java")).unwrap();
assert!(test.test);
assert_eq!(test.out_dir, root.join("app/target/test-classes"));
}
#[test]
fn target_rejects_non_java_missing_and_unlinked_files() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
write(root, "app/pom.xml", "<project/>");
assert!(single_file_target(root, &model, &root.join("app/pom.xml")).is_err());
assert!(single_file_target(root, &model, &root.join("app/src/main/java/demo/Missing.java")).is_err());
write(root, "other/Main.java", "class Main {}");
assert!(single_file_target(root, &model, &root.join("other/Main.java")).is_err());
}
#[test]
fn javac_prefers_the_module_jdk_and_scopes_test_sources() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let file = root.join("app/src/test/java/demo/MainTest.java");
let target = single_file_target(root, &model, &file).unwrap();
let jdk = root.join("jdk");
fs::create_dir_all(jdk.join("bin")).unwrap();
let exe = if cfg!(windows) { "javac.exe" } else { "javac" };
fs::write(jdk.join("bin").join(exe), "fake").unwrap();
let mut target = target;
target.top.env.insert("JAVA_HOME".into(), jdk.to_string_lossy().into_owned());
let step = javac_step(&target, &file, "/repo/a.jar", &find_javac(&target.top.env)).unwrap();
assert!(step.program.ends_with(exe));
assert!(target.out_dir.is_dir());
let args = step.args.join(" ");
assert!(args.contains("-encoding UTF-8"), "{args}");
assert!(args.contains("-d ") && args.contains("test-classes"), "{args}");
assert!(args.contains("-cp /repo/a.jar"), "{args}");
assert!(args.contains("MainTest.java"), "{args}");
// Test sources resolve their own and the main sources, without writing them.
let sourcepath = step.args.iter().position(|a| a == "-sourcepath").map(|i| step.args[i + 1].clone());
let roots = sourcepath.expect("a -sourcepath");
assert!(roots.contains("src/test/java") && roots.contains("src/main/java"), "{roots}");
assert!(step.args.iter().any(|a| a == "-implicit:none"), "{args}");
// No `JAVA_HOME`: plain `javac` from `PATH`.
assert_eq!(find_javac(&BTreeMap::new()), exe);
}
/// The classpath probe runs the project's Maven command with `-pl … -am`
/// `dependency:build-classpath`; the fake `mvnw` below only records its
/// arguments and writes a canned classpath file for the `-pl` module.
#[cfg(unix)]
#[test]
fn classpath_probe_writes_one_file_per_module_and_reads_the_compiled_one() {
use std::os::unix::fs::PermissionsExt;
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
fixture(root);
let script = root.join("mvnw");
fs::write(
&script,
"#!/bin/sh\npl='.'\nwhile [ $# -gt 0 ]; do\nif [ \"$1\" = \"-pl\" ]; then pl=\"$2\"; shift 2; else shift; fi\ndone\nmkdir -p \"$pl/target\"\nprintf '/repo/a.jar:/repo/b.jar' > \"$pl/target/ide-compile-cp.txt\"\n",
)
.unwrap();
fs::set_permissions(&script, fs::Permissions::from_mode(0o755)).unwrap();
let model = crate::load(root, &root.join("cache"), None);
let file = root.join("app/src/main/java/demo/Main.java");
let target = single_file_target(root, &model, &file).unwrap();
assert!(target.top.command.ends_with("mvnw"));
assert_eq!(target.pl, "app");
let cp = single_file_classpath(root, &model, &target).unwrap();
let separator = ':';
// Reactor class directories first, so fresh outputs shadow installed snapshots.
let lib = root.join("lib/target/classes").to_string_lossy().into_owned();
assert!(cp.starts_with(&lib), "{cp}");
// The module's own classes come first once they exist.
fs::create_dir_all(root.join("app/target/classes")).unwrap();
let cp = single_file_classpath(root, &model, &target).unwrap();
let own = root.join("app/target/classes").to_string_lossy().into_owned();
assert!(cp.starts_with(&format!("{own}:{lib}")), "{cp}");
assert!(cp.contains("/repo/a.jar"), "{cp}");
assert!(cp.contains("/repo/b.jar"), "{cp}");
assert!(cp.split(separator).count() >= 3, "{cp}");
}
}
-253
View File
@@ -1,253 +0,0 @@
//! Up-to-date checks for menu builds (`Build Project` / `Build Module`, #2476).
//!
//! Menu builds have no fingerprint record on the launch path, so a second
//! click always pays a full offline Maven run. This module stores one JSON
//! record per scope (project, or one module file's build) after a successful
//! build and compares it before the next build; on a match the build is
//! skipped entirely. Like launch reuse, timestamp-preserving external edits
//! are re-stamped first so Maven actually recompiles them on the next run.
use super::*;
use std::fs;
/// Record of the last successful menu build of one scope.
#[derive(serde::Serialize, serde::Deserialize)]
struct Record {
fingerprint: LaunchFingerprint,
/// Output folders of the built projects that existed after the build, relative to the
/// project. Deleting one outside the IDE (`mvn clean` in a terminal) leaves every input
/// unchanged, so a build is skipped only while they are all still there.
#[serde(default)]
outputs: Vec<PathBuf>,
}
/// The build's output folders that exist now, relative to `root`.
fn existing_outputs(root: &Path, fingerprint: &LaunchFingerprint) -> Vec<PathBuf> {
fingerprint
.project_dirs()
.flat_map(|dir| ["target/classes", "target/test-classes"].map(|out| dir.join(out)))
.filter(|rel| root.join(rel).is_dir())
.collect()
}
fn record_path(cache: &Path, root: &Path, file: Option<&Path>) -> PathBuf {
let base = cache.join("menu-build").join("records");
match file {
Some(f) => base.join(f.strip_prefix(root).unwrap_or(f)).with_extension("json"),
None => base.join("project.json"),
}
}
/// Re-stamps files whose content changed without advancing mtime (git
/// checkout, external sync): timestamp-incremental Maven would otherwise skip
/// them as "unchanged" and the rebuild would compile nothing.
fn restamp(root: &Path, edits: &[PathBuf]) {
let now = std::time::SystemTime::now();
for rel in edits {
let path = root.join(rel);
let _ = fs::File::options().write(true).open(&path).and_then(|f| f.set_modified(now)).or_else(|_| {
fs::OpenOptions::new()
.create(true)
.truncate(false)
.write(true)
.open(&path)
.and_then(|f| f.set_modified(now))
});
}
}
/// Whether the last successful menu build of this scope is still fresh: its
/// record exists and the fingerprint matches. On a mismatch caused by
/// timestamp-preserving external edits the files are re-stamped first, so the
/// rebuild Maven runs actually recompiles them.
pub fn menu_up_to_date(
cache: &Path,
root: &Path,
model: &BuildModel,
file: Option<&Path>,
cancel: &CancellationToken,
) -> bool {
let current = match menu_fingerprint(root, model, file, cancel) {
Ok(Some(current)) => current,
_ => return false,
};
let bytes = match fs::read(record_path(cache, root, file)) {
Ok(bytes) => bytes,
_ => return false,
};
let record: Record = match serde_json::from_slice(&bytes) {
Ok(record) => record,
_ => return false,
};
if record.fingerprint != current {
restamp(root, &record.fingerprint.mtime_preserved_edits(&current));
return false;
}
record.outputs.iter().all(|out| root.join(out).is_dir())
}
/// Records a successful menu build as the baseline for future up-to-date
/// checks. Failures are swallowed: a missing record only costs one Maven run.
pub fn record_menu_build(
cache: &Path,
root: &Path,
model: &BuildModel,
file: Option<&Path>,
cancel: &CancellationToken,
) {
let current = match menu_fingerprint(root, model, file, cancel) {
Ok(Some(current)) => current,
_ => return,
};
// A torn write fails to parse later and is treated as "no record", so a
// plain write is enough.
let path = record_path(cache, root, file);
if path.parent().is_some_and(|p| fs::create_dir_all(p).is_err()) {
return;
}
let outputs = existing_outputs(root, &current);
let bytes = match serde_json::to_vec(&Record { fingerprint: current, outputs }) {
Ok(bytes) => bytes,
_ => return,
};
let _ = fs::write(&path, bytes);
}
#[cfg(test)]
mod tests {
use super::*;
fn write(root: &Path, rel: &str, value: &str) {
let path = root.join(rel);
fs::create_dir_all(path.parent().unwrap()).unwrap();
fs::write(path, value).unwrap();
}
fn fixture(root: &Path) -> BuildModel {
maven_two_module(root, "int x;");
BuildModel { maven: Some(maven::load(root)), ..Default::default() }
}
fn maven_two_module(root: &Path, extra_app: &str) {
write(
root,
"pom.xml",
r#"<project><modelVersion>4.0.0</modelVersion><groupId>t</groupId><artifactId>root</artifactId><version>1</version><packaging>pom</packaging><modules><module>app</module><module>lib</module></modules></project>"#,
);
write(
root,
"app/pom.xml",
r#"<project><modelVersion>4.0.0</modelVersion><parent><groupId>t</groupId><artifactId>root</artifactId><version>1</version></parent><artifactId>app</artifactId><dependencies><dependency><groupId>t</groupId><artifactId>lib</artifactId><version>1</version></dependency></dependencies></project>"#,
);
write(
root,
"lib/pom.xml",
r#"<project><modelVersion>4.0.0</modelVersion><parent><groupId>t</groupId><artifactId>root</artifactId><version>1</version></parent><artifactId>lib</artifactId></project>"#,
);
write(root, "app/src/main/java/t/A.java", &format!("package t; public class A {{ {extra_app} }}"));
write(root, "lib/src/main/java/t/L.java", "package t; public class L {}");
}
#[test]
fn record_then_skip_without_changes() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let cache = root.join("cache");
let file = root.join("app/src/main/java/t/A.java");
let cancel = CancellationToken::new();
assert!(!menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
record_menu_build(&cache, root, &model, Some(&file), &cancel);
assert!(menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
// The project scope is independent of the module scope.
assert!(!menu_up_to_date(&cache, root, &model, None, &cancel));
record_menu_build(&cache, root, &model, None, &cancel);
assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
}
#[test]
fn deleted_outputs_invalidate_the_record() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let cache = root.join("cache");
let cancel = CancellationToken::new();
for out in ["app/target/classes/t", "lib/target/classes/t", "app/target/test-classes"] {
fs::create_dir_all(root.join(out)).unwrap();
}
record_menu_build(&cache, root, &model, None, &cancel);
assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
// `mvn clean` outside the IDE: no input changed, but the classes are gone.
fs::remove_dir_all(root.join("lib/target")).unwrap();
assert!(!menu_up_to_date(&cache, root, &model, None, &cancel));
fs::create_dir_all(root.join("lib/target/classes")).unwrap();
assert!(menu_up_to_date(&cache, root, &model, None, &cancel));
}
#[test]
fn edit_invalidates_and_rerecord_restores_skip() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let cache = root.join("cache");
let file = root.join("app/src/main/java/t/A.java");
let cancel = CancellationToken::new();
record_menu_build(&cache, root, &model, Some(&file), &cancel);
assert!(menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
write(root, "app/src/main/java/t/A.java", "package t; public class A { int y; }");
assert!(!menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
record_menu_build(&cache, root, &model, Some(&file), &cancel);
assert!(menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
}
#[test]
fn mtime_preserved_edit_forces_rebuild_and_restamps() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let cache = root.join("cache");
let rel = "app/src/main/java/t/A.java";
let file = root.join(rel);
let cancel = CancellationToken::new();
record_menu_build(&cache, root, &model, Some(&file), &cancel);
let before = fs::metadata(&file).unwrap().modified().unwrap();
// Same length, same mtime, different content: an external edit that
// preserved the timestamp.
write(root, rel, "package t; public class A { int z; }");
fs::File::options().write(true).open(&file).and_then(|f| f.set_modified(before)).unwrap();
assert!(!menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
assert!(fs::metadata(&file).unwrap().modified().unwrap() > before);
}
#[test]
fn corrupt_record_never_skips() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
let cache = root.join("cache");
let file = root.join("app/src/main/java/t/A.java");
let cancel = CancellationToken::new();
fs::create_dir_all(cache.join("menu-build").join("records").join("app/src/main/java/t")).unwrap();
fs::write(cache.join("menu-build").join("records").join("app/src/main/java/t/A.json"), b"{not json").unwrap();
assert!(!menu_up_to_date(&cache, root, &model, Some(&file), &cancel));
}
#[test]
fn unsupported_builds_never_skip() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
let model = fixture(root);
write(root, "other/Main.java", "public class Main {}");
let cache = root.join("cache");
let cancel = CancellationToken::new();
// A file outside any non-aggregator module has no fingerprint.
let stray = root.join("other/Main.java");
record_menu_build(&cache, root, &model, Some(&stray), &cancel);
assert!(!menu_up_to_date(&cache, root, &model, Some(&stray), &cancel));
}
}
+1 -22
View File
@@ -8,24 +8,6 @@ def canon = { File f -> f.canonicalPath }
// the identity path (`:lib:core`, `:buildSrc`) tells them apart and addresses their tasks
// from the root build. Internal API, hence the fallback.
def identity = { Project p -> try { p.identityPath.toString() } catch (ignored) { p.path } }
// The task copying a source set's resources and its output folder, when it changes them on the
// way (filters, `expand`, renames, includes / excludes, extra sources): jdtls copies resources as
// they are, so launches take them from Gradle. Internal API, hence the fallback.
def processedResources = { Project p, s ->
try {
def task = p.tasks.findByName(s.processResourcesTaskName)
if (task == null) return null
def specs = 0
def changes = task.mainSpec.sourcePaths.size() > 1
task.rootSpec.buildRootResolver().walk { r ->
specs++
changes |= !r.allCopyActions.isEmpty() || !r.allIncludes.isEmpty() || !r.allExcludes.isEmpty() ||
!r.allIncludeSpecs.isEmpty() || !r.allExcludeSpecs.isEmpty() || r.destPath.segments.length > 0
}
// The root and main specs exist for every task; more come from `from(…) { … }`.
(changes || specs > 2) ? [task: task.name, dir: canon(task.destinationDir)] : null
} catch (ignored) { null }
}
def describe = { Project p ->
def m = [path: identity(p), dir: canon(p.projectDir), buildDir: canon(p.layout.buildDirectory.get().asFile)]
@@ -44,10 +26,7 @@ def describe = { Project p ->
def test = s.name == 'test' || s.name == 'testFixtures' || suites.contains(s.name) ||
s.name.endsWith('Test') || s.name.endsWith('Tests') ||
(!src.isEmpty() && src.every { ideaTests.contains(it) })
def set = [name: s.name, test: test, src: src, res: res]
def processed = processedResources(p, s)
if (processed != null) set.processed = processed
set
[name: s.name, test: test, src: src, res: res]
}
}
try {
-13
View File
@@ -335,19 +335,6 @@ pub struct ReportedSourceSet {
/// Absolute resource folders.
#[serde(default)]
pub res: Vec<String>,
/// Set when Gradle changes the resources while copying them (filters, `expand`, renames,
/// includes / excludes, extra sources), which the Java language server's copy does not.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub processed: Option<ProcessedResources>,
}
/// The task that copies a source set's resources, and where it writes them.
#[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
pub struct ProcessedResources {
/// Task name in its project (`processResources`).
pub task: String,
/// Absolute output folder.
pub dir: String,
}
const MODEL_LINE: &str = "@openidea-model\t";
+1 -11
View File
@@ -528,17 +528,7 @@ mod tests {
for (step, name) in plan.steps.iter().zip(["java", "kotlin"]) {
assert_eq!(step.cwd, root.join(name));
assert_eq!(step.program, format!("{name}-mvnw"));
assert_eq!(
step.args,
[
"-B",
"-Dstyle.color=never",
crate::maven::LOCAL_REPO_TRACKING_ARG,
"-o",
"-Peditor",
"test-compile"
]
);
assert_eq!(step.args, ["-B", "-Dstyle.color=never", "-o", "-Peditor", "test-compile"]);
assert_eq!(step.env.get("JAVA_HOME").map(String::as_str), Some("/jdk"));
}
}
-8
View File
@@ -18,14 +18,6 @@ use std::sync::{Mutex, OnceLock};
pub mod sources;
/// Lets the IDE's own Maven runs (Reload, Build) use what the local repository already
/// has. Maven 3.9 re-resolves an artifact whose recorded origin repository (`_remote.repositories`)
/// isn't declared in the build, such as a vendor jar downloaded through another project or
/// installed by hand, and fails when no declared repository has it. Tracking under another
/// file name makes such artifacts count as locally installed. Maven goals the user runs keep
/// plain Maven's behaviour.
pub const LOCAL_REPO_TRACKING_ARG: &str = "-Daether.enhancedLocalRepository.trackingFilename=openidea.repositories";
/// Phases shown under "Lifecycle" (IDEA's default list).
pub const LIFECYCLE: &[&str] =
&["clean", "validate", "compile", "test", "package", "verify", "install", "site", "deploy"];
+4 -32
View File
@@ -73,9 +73,6 @@ struct GradleCache {
/// The projects as Gradle evaluated them; empty in caches from before they were read.
#[serde(default)]
projects: Vec<ReportedProject>,
/// The projects report how their resources are processed; older caches are stale.
#[serde(default)]
resources: bool,
}
/// Init script printing every project, its source sets and Java version once configured.
@@ -247,12 +244,11 @@ pub fn apply_gradle_cache(root: &Path, cache_dir: &Path, model: &mut GradleModel
}
}
}
// A successful sync from before projects were cached has not seen computed includes,
// nor, before resources were read, which launches need Gradle to process them.
let outdated = cache.error.is_none() && (cache.projects.is_empty() || !cache.resources);
// A successful sync from before projects were cached has not seen computed includes.
let without_projects = cache.error.is_none() && cache.projects.is_empty();
model.synced_at = Some(cache.at_ms);
model.sync_error = cache.error;
model.stale = outdated || cache.hash != hash_gradle_files(&gradle::build_files(root, model));
model.stale = without_projects || cache.hash != hash_gradle_files(&gradle::build_files(root, model));
}
// ---------------------------------------------------------------- processes
@@ -345,13 +341,7 @@ pub fn sync_maven(
// `-T1` keeps mvnd serial: its default parallel build interleaves the
// `dependency:tree` output of concurrent modules, which the sync parses
// as one stream. mvn is serial anyway, so this only pins the daemon.
let mut args: Vec<String> = vec![
"-B".into(),
"-fae".into(),
"-Dstyle.color=never".into(),
"-T1".into(),
maven::LOCAL_REPO_TRACKING_ARG.into(),
];
let mut args: Vec<String> = vec!["-B".into(), "-fae".into(), "-Dstyle.color=never".into(), "-T1".into()];
args.extend(sync_maven_options(&options.maven_options));
if options.offline {
args.push("-o".into());
@@ -466,7 +456,6 @@ pub fn sync_gradle_model(
error: (!out.success).then(|| error_summary(&out.text)),
tasks: if out.success { gradle::parse_tasks(&out.text) } else { Vec::new() },
projects,
resources: true,
};
write_cache(&cache_dir, GRADLE_CACHE, &cache)
}
@@ -718,7 +707,6 @@ mod tests {
test,
src: src.iter().map(|p| core_src(p)).collect(),
res: res.iter().map(|p| core_src(p)).collect(),
processed: None,
};
// A settings script's own println comes first; task listing lines follow.
let out = format!(
@@ -743,15 +731,6 @@ mod tests {
);
let projects = parse_reported_projects(&out);
assert_eq!(projects.len(), 3, "the malformed line is skipped");
// As the init script prints a set whose resources Gradle filters or renames.
let processed = parse_reported_projects(&format!(
"@openidea-model\t{}",
r#"{"path":":","dir":"/p","sourceSets":[{"name":"main","test":false,"src":[],"res":[],"processed":{"task":"processResources","dir":"/p/build/resources/main"}}]}"#
));
assert_eq!(
processed[0].source_sets[0].processed,
Some(gradle::ProcessedResources { task: "processResources".into(), dir: "/p/build/resources/main".into() })
);
let src = |p: &str| PathBuf::from(core_src(p));
assert_eq!(
gradle::reported_source_roots(&projects),
@@ -817,18 +796,12 @@ mod tests {
..Default::default()
})
.collect(),
resources: true,
};
write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();
apply_gradle_cache(&root, &cache_dir, &mut model);
assert_eq!(model.projects[1].tasks.len(), 1);
assert!(model.projects[0].tasks.iter().any(|t| t.name == "wrapper"), "root keeps its defaults");
assert!(!model.stale);
write_cache(&cache_dir, GRADLE_CACHE, &GradleCache { resources: false, ..cache.clone() }).unwrap();
let mut m = gradle::load(&root).unwrap();
apply_gradle_cache(&root, &cache_dir, &mut m);
assert!(m.stale, "synced before resource processing was read");
write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();
let stale_after = |script: &str| {
std::fs::write(root.join("app/build.gradle"), script).unwrap();
@@ -862,7 +835,6 @@ mod tests {
dir: root.to_string_lossy().into_owned(),
..Default::default()
}],
resources: true,
..Default::default()
};
write_cache(&cache_dir, GRADLE_CACHE, &cache).unwrap();
-23
View File
@@ -73,8 +73,6 @@ pub struct EditorAppearanceSettings {
pub whitespace_inner: bool,
pub whitespace_trailing: bool,
pub indent_guides: bool,
/// Colour indent guides by depth (`--syn-rainbow-*`), while `indent_guides` is on.
pub rainbow_indent_guides: bool,
/// Right margin and visual guides from Code Style.
pub hard_wrap_guides: bool,
pub intention_bulb: bool,
@@ -97,7 +95,6 @@ impl Default for EditorAppearanceSettings {
whitespace_inner: true,
whitespace_trailing: true,
indent_guides: true,
rainbow_indent_guides: false,
hard_wrap_guides: true,
intention_bulb: true,
distraction_free_width: 80,
@@ -333,23 +330,6 @@ pub struct InlayHintsSettings {
pub code_vision_usages: bool,
/// Code vision: last author of a declaration (VCS blame) beside its usages.
pub code_vision_author: bool,
/// Code vision: "no usages" on declarations nothing uses (IDEA shows it; clicking searches everywhere).
pub code_vision_no_usages: bool,
/// Code vision: where the usages go, above the declaration or at the end of its line.
pub code_vision_usages_position: CodeVisionPosition,
/// Code vision: where the author goes, above the declaration or at the end of its line.
pub code_vision_author_position: CodeVisionPosition,
}
/// Editor › Inlay Hints › Code Vision position (IDEA's "Default position for metrics").
#[derive(Clone, Copy, Debug, Default, PartialEq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub enum CodeVisionPosition {
/// A row of its own above the declaration.
#[default]
Top,
/// After the end of the declaration's first line.
Right,
}
impl Default for InlayHintsSettings {
@@ -361,9 +341,6 @@ impl Default for InlayHintsSettings {
disabled_languages: Vec::new(),
code_vision_usages: true,
code_vision_author: true,
code_vision_no_usages: true,
code_vision_usages_position: CodeVisionPosition::Top,
code_vision_author_position: CodeVisionPosition::Top,
}
}
}
-37
View File
@@ -273,27 +273,6 @@ pub enum DebugEvent {
change_type: String,
message: String,
},
/// The session's capabilities changed after it started: fetch them again.
Capabilities,
JvmBackend {
state: JvmBackendState,
},
}
/// The backend that reads a debugged JVM's objects (instances, fields, referrers).
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmBackendState {
Ready,
/// Turned off for the rest of the session: the debug adapter lacks what it needs.
Unsupported {
detail: String,
},
/// The Kotlin JDWP link only forwards now; inspecting stops.
Degraded {
detail: String,
},
Closed,
}
/// Where backend crates publish [`IdeEvent`]s. Cheap to clone via `Arc`.
@@ -315,19 +294,3 @@ pub struct NullSink;
impl EventSink for NullSink {
fn emit(&self, _: IdeEvent) {}
}
#[cfg(test)]
mod tests {
use super::*;
use serde_json::json;
#[test]
fn jvm_backend_events_json_shape() {
let degraded = DebugEvent::JvmBackend { state: JvmBackendState::Degraded { detail: "x".into() } };
assert_eq!(
serde_json::to_value(&degraded).unwrap(),
json!({"kind": "jvmBackend", "state": {"kind": "degraded", "detail": "x"}})
);
assert_eq!(serde_json::to_value(DebugEvent::Capabilities).unwrap(), json!({"kind": "capabilities"}));
}
}
-26
View File
@@ -21,32 +21,6 @@
use std::collections::BTreeMap;
/// Removes ANSI escape sequences (colour, cursor movement).
pub fn strip_ansi(s: &str) -> String {
if !s.contains('\u{1b}') {
return s.to_owned();
}
let mut out = String::with_capacity(s.len());
let mut chars = s.chars().peekable();
while let Some(c) = chars.next() {
if c != '\u{1b}' {
out.push(c);
continue;
}
if chars.peek() == Some(&'[') {
chars.next();
for c in chars.by_ref() {
if c.is_ascii_alphabetic() || c == '~' {
break;
}
}
} else {
chars.next();
}
}
out
}
/// Decodes complete lines or collected output from IDE-managed tools, preferring UTF-8.
/// Windows launcher/native diagnostics fall back to the system ANSI code page.
/// Callers must buffer incomplete lines so multibyte characters are never split.
-112
View File
@@ -72,75 +72,6 @@ pub fn kill_tree_of(pid: u32) {
let _ = pid;
}
/// Whether a process with this id exists. PID reuse makes this conservative: a reused id keeps
/// whatever was tied to the old process alive, a live process is never reported dead.
pub fn process_alive(pid: u32) -> bool {
// `kill(0, 0)` would signal the caller's own process group.
if pid == 0 {
return false;
}
#[cfg(unix)]
{
// Above `i32::MAX` the id would wrap to a negative value, which `kill` reads as a group.
let Ok(pid) = libc::pid_t::try_from(pid) else { return false };
// SAFETY: signal 0 delivers nothing; it only checks that the process exists and is reachable.
unsafe { libc::kill(pid, 0) == 0 || std::io::Error::last_os_error().raw_os_error() == Some(libc::EPERM) }
}
#[cfg(windows)]
{
use std::os::windows::io::{AsRawHandle, FromRawHandle, OwnedHandle};
use windows_sys::Win32::Foundation::{ERROR_ACCESS_DENIED, GetLastError, STILL_ACTIVE};
use windows_sys::Win32::System::Threading::{
GetExitCodeProcess, OpenProcess, PROCESS_QUERY_LIMITED_INFORMATION,
};
// SAFETY: plain call; a non-null result is a process handle owned by this function.
let handle = unsafe { OpenProcess(PROCESS_QUERY_LIMITED_INFORMATION, 0, pid) };
if handle.is_null() {
// A process we may not open still exists.
// SAFETY: reads the thread's last error, set by the call above.
return unsafe { GetLastError() } == ERROR_ACCESS_DENIED;
}
// SAFETY: `handle` is valid and nobody else owns it.
let handle = unsafe { OwnedHandle::from_raw_handle(handle) };
let mut code = 0u32;
// SAFETY: a live process handle opened with query access; one out-parameter.
let ok = unsafe { GetExitCodeProcess(handle.as_raw_handle(), &mut code) };
// A handle that cannot be queried is not evidence that the process is gone.
ok == 0 || code == STILL_ACTIVE as u32
}
#[cfg(not(any(unix, windows)))]
{
true
}
}
/// The program and everything it started: an adapter may report the launcher shell, whose
/// child is the debugged program, so stopping only the reported pid leaves the program alive.
#[cfg(unix)]
pub fn process_tree(pid: i32) -> Vec<i32> {
use std::collections::HashMap;
let Ok(out) = std::process::Command::new("ps").args(["-A", "-o", "pid=,ppid="]).output() else {
return vec![pid];
};
let mut children: HashMap<i32, Vec<i32>> = HashMap::new();
for line in String::from_utf8_lossy(&out.stdout).lines() {
let mut it = line.split_whitespace();
let (Some(p), Some(parent)) = (it.next(), it.next()) else { continue };
let (Ok(p), Ok(parent)) = (p.parse::<i32>(), parent.parse::<i32>()) else { continue };
children.entry(parent).or_default().push(p);
}
let mut tree = vec![pid];
let mut at = 0;
while at < tree.len() {
if let Some(kids) = children.get(&tree[at]) {
tree.extend(kids.iter().copied());
}
at += 1;
}
tree
}
/// [`kill_tree`] that first asks the group to exit: `SIGTERM`, then `grace`, then `SIGKILL`.
/// Git removes its `index.lock` on `SIGTERM`, where `SIGKILL` leaves it behind and the next
/// git command fails. Windows has no such signal to send from outside the child's console,
@@ -799,30 +730,6 @@ fn append_path_entries(path: &OsStr, extra: &OsStr) -> OsString {
mod tests {
use super::*;
#[test]
fn process_alive_tells_live_from_dead_pids() {
assert!(process_alive(std::process::id()));
assert!(!process_alive(0));
let mut cmd = if cfg!(windows) {
let mut cmd = Command::new("cmd");
cmd.args(["/C", "exit 0"]);
cmd
} else {
Command::new("true")
};
let mut child = cmd.spawn().unwrap();
let pid = child.id();
child.wait().unwrap();
drop(child);
assert!(!process_alive(pid));
}
#[cfg(unix)]
#[test]
fn process_alive_rejects_ids_that_are_not_a_single_process() {
assert!(!process_alive(u32::MAX));
}
#[cfg(unix)]
#[test]
fn kill_tree_of_reaches_what_the_child_started() {
@@ -1143,25 +1050,6 @@ mod tests {
}
assert_eq!(find_executable("nope", &search), None);
}
#[cfg(unix)]
#[test]
fn process_tree_lists_the_child_of_a_shell() {
let mut cmd = Command::new("sh");
own_group(&mut cmd).args(["-c", "sleep 5 & wait"]);
let mut child = cmd.spawn().unwrap();
let sh_pid = child.id() as i32;
// The shell forks `sleep` after it starts, so the tree grows a moment later.
let deadline = std::time::Instant::now() + Duration::from_secs(2);
let mut tree = process_tree(sh_pid);
while tree.len() < 2 && std::time::Instant::now() < deadline {
std::thread::sleep(Duration::from_millis(20));
tree = process_tree(sh_pid);
}
kill_tree(&mut child);
assert_eq!(tree[0], sh_pid, "the pid itself comes first");
assert!(tree.len() >= 2 && tree[1..].iter().all(|p| *p != sh_pid), "the shell's child follows: {tree:?}");
}
}
#[cfg(all(test, unix))]
+1 -93
View File
@@ -104,11 +104,6 @@ pub struct AgentSettings {
#[serde(deserialize_with = "agent_defaults")]
#[specta(type = BTreeMap<String, BTreeMap<String, String>>)]
pub defaults: BTreeMap<String, BTreeMap<String, String>>,
/// MCP servers passed to coding agents in `session/new`, `session/load` and `session/fork`,
/// keyed by server name (`[agents.mcpServers.<name>]`).
#[serde(deserialize_with = "or_default")]
#[specta(type = BTreeMap<String, AgentMcpServer>)]
pub mcp_servers: BTreeMap<String, AgentMcpServer>,
}
impl Default for AgentSettings {
@@ -126,58 +121,6 @@ impl Default for AgentSettings {
send_with: SendKey::Enter,
while_running: WhileRunning::Queue,
defaults: BTreeMap::new(),
mcp_servers: BTreeMap::new(),
}
}
}
/// Transport of an MCP server configured in Settings › Agents › MCP Servers.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub enum McpTransport {
#[default]
Stdio,
Http,
Sse,
}
/// An MCP server passed to coding agents in `session/new`, `session/load` and `session/fork`.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(default, rename_all = "camelCase")]
pub struct AgentMcpServer {
#[serde(deserialize_with = "or_default")]
#[specta(type = McpTransport)]
pub transport: McpTransport,
pub enabled: bool,
#[serde(skip_serializing_if = "Option::is_none")]
#[specta(optional)]
pub command: Option<String>,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub args: Vec<String>,
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub env: BTreeMap<String, String>,
#[serde(skip_serializing_if = "Option::is_none")]
#[specta(optional)]
pub url: Option<String>,
#[serde(default, skip_serializing_if = "BTreeMap::is_empty")]
pub headers: BTreeMap<String, String>,
/// Agent provider ids this server is enabled for (e.g. `["claude", "codex"]`);
/// empty means enabled for all agents.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub agents: Vec<String>,
}
impl Default for AgentMcpServer {
fn default() -> Self {
Self {
transport: McpTransport::Stdio,
enabled: true,
command: None,
args: Vec::new(),
env: BTreeMap::new(),
url: None,
headers: BTreeMap::new(),
agents: Vec::new(),
}
}
}
@@ -261,9 +204,6 @@ pub enum WhileRunning {
pub struct McpServerSettings {
/// Serve the tools on 127.0.0.1 while the IDE runs.
pub enabled: bool,
/// Run the tools that change the project or start processes without asking first
/// (IDEA's brave mode). Read from the IDE's own settings only, never a project's.
pub run_without_confirmation: bool,
}
/// Absent profiles retain automatic discovery for existing projects.
@@ -456,10 +396,6 @@ pub struct GeneralSettings {
/// Where updates come from: `auto` (the CNB mirror for the Chinese UI, else GitHub) | `github` | `cnb`.
pub update_source: String,
pub auto_check_updates: bool,
/// System Settings › Updates: open the What's New page after the app starts a new version.
pub show_whats_new_after_update: bool,
/// The version the app last started with, so the first start after an update is recognisable.
pub last_run_version: String,
}
impl Default for GeneralSettings {
@@ -478,8 +414,6 @@ impl Default for GeneralSettings {
project_name: String::new(),
update_source: "auto".into(),
auto_check_updates: true,
show_whats_new_after_update: true,
last_run_version: String::new(),
}
}
}
@@ -583,7 +517,7 @@ pub struct AppearanceSettings {
pub project_colors_in_toolbar: bool,
pub dnd_with_alt_only: bool,
pub menu_icons: bool,
/// `hamburger` | `merged` | `toolbar` (a separate row): main menu presentation in the frameless title bar.
/// `hamburger` | `merged`: main menu presentation in the frameless title bar.
pub main_menu_style: String,
/// A lone Alt press focuses or opens the main menu (IDEA `ide.windows.main.menu.focus.on.alt`).
pub main_menu_alt: bool,
@@ -1339,11 +1273,6 @@ pub struct ProjectStructureSettings {
pub unmarked: Vec<String>,
/// Content roots besides the project folder (absolute paths), shown and searched with it.
pub content_roots: Vec<String>,
/// Other projects (absolute paths) this project depends on; indexed and navigable like content roots.
pub dependencies: Vec<String>,
/// Per-workspace-member dependencies: member root (IPC path) → the roots it depends on.
/// A member not listed here (or with an empty list) navigates only into itself.
pub member_dependencies: BTreeMap<String, Vec<String>>,
/// "Exclude files": `;`-separated name patterns (`*.log;tmp*`) excluded at any depth.
pub exclude_files: String,
/// Project compiler output directory (relative to project root or absolute; empty = default).
@@ -1517,27 +1446,6 @@ mod tests {
}
}
#[test]
fn double_click_opens_diff_is_unset_by_default_and_round_trips() {
let old: Settings = serde_json::from_str(r#"{"vcs":{"commit":{"nonModal":true}}}"#).unwrap();
assert_eq!(old.vcs.commit.double_click_opens_diff, None);
// The unset value shows up as `null` in the defaults: `SettingsStore::set` only
// accepts a key path it finds there.
let json = serde_json::to_value(Settings::default()).unwrap();
assert_eq!(json["vcs"]["commit"]["doubleClickOpensDiff"], serde_json::Value::Null);
for on in [true, false] {
let mut settings = Settings::default();
settings.vcs.commit.double_click_opens_diff = Some(on);
let json = serde_json::to_value(&settings).unwrap();
assert_eq!(json["vcs"]["commit"]["doubleClickOpensDiff"], on);
let restored: Settings = serde_json::from_value(json).unwrap();
assert_eq!(restored.vcs.commit.double_click_opens_diff, Some(on));
}
// Explicit `null` reads back as unset.
let cleared: Settings = serde_json::from_str(r#"{"vcs":{"commit":{"doubleClickOpensDiff":null}}}"#).unwrap();
assert_eq!(cleared.vcs.commit.double_click_opens_diff, None);
}
#[test]
fn agent_meters_default_and_round_trip() {
let old: Settings = serde_json::from_str(r#"{"agents":{"showCost":true}}"#).unwrap();
-12
View File
@@ -43,7 +43,6 @@ impl Default for VcsSettings {
pub struct GitSettings {
/// Show blame after the current editor line.
pub inline_blame: bool,
pub show_branch_in_project_view: bool,
/// Path to the git executable; empty = auto-detect.
pub executable: String,
/// Default of Update Project: `merge` | `rebase`.
@@ -75,7 +74,6 @@ impl Default for GitSettings {
fn default() -> Self {
Self {
inline_blame: false,
show_branch_in_project_view: false,
executable: String::new(),
update_method: "merge".into(),
auto_update_on_push_rejected: false,
@@ -117,13 +115,6 @@ pub struct CommitSettings {
pub wrap_at_margin: bool,
/// Plugin before-commit checks turned off (`<plugin id>/<check id>`); the rest run.
pub disabled_plugin_checks: Vec<String>,
/// Double-click / Enter in the changes view: `None` follows the interface (the
/// Commit tool window opens the diff, Local Changes the source file).
///
/// No `skip_serializing_if`: an unset value must still appear in
/// `Settings::default()`, or `SettingsStore::set` rejects the key as unknown.
#[specta(optional)]
pub double_click_opens_diff: Option<bool>,
}
impl Default for CommitSettings {
@@ -144,7 +135,6 @@ impl Default for CommitSettings {
show_right_margin: true,
wrap_at_margin: false,
disabled_plugin_checks: Vec::new(),
double_click_opens_diff: None,
}
}
}
@@ -322,7 +312,6 @@ pub struct TerminalSettings {
pub override_ide_shortcuts: bool,
pub shell_integration: bool,
pub highlight_hyperlinks: bool,
pub highlight_selection: bool,
pub option_as_meta: bool,
/// Escape moves focus to the editor instead of reaching the shell.
pub escape_to_editor: bool,
@@ -355,7 +344,6 @@ impl Default for TerminalSettings {
override_ide_shortcuts: true,
shell_integration: true,
highlight_hyperlinks: true,
highlight_selection: true,
option_as_meta: false,
escape_to_editor: false,
cursor_shape: "block".into(),
-5
View File
@@ -11,17 +11,12 @@ tempfile.workspace = true
ide-core.workspace = true
ide-language.workspace = true
ide-jsonrpc.workspace = true
ide-jvm-attach.workspace = true
ide-jvm-inspect.workspace = true
ide-jdwp.workspace = true
ide-heap.workspace = true
serde.workspace = true
serde_json.workspace = true
specta.workspace = true
tokio = { workspace = true, features = ["net"] }
parking_lot.workspace = true
memchr = "2"
percent-encoding = "2"
portable-pty.workspace = true
tracing.workspace = true
+7 -48
View File
@@ -246,7 +246,13 @@ impl Connection {
fn dispatch(inner: &Inner, incoming: &mpsc::UnboundedSender<Incoming>, body: &[u8]) {
tracing::trace!(target: "ide_dap::wire", "<-- {}", String::from_utf8_lossy(body));
let Some(msg) = parse_message(body) else { return };
let msg: Value = match serde_json::from_slice(body) {
Ok(v) => v,
Err(e) => {
tracing::warn!("dap: unparsable message: {e}");
return;
}
};
match msg.get("type").and_then(Value::as_str) {
Some("response") => {
let Some(request_seq) = msg.get("request_seq").and_then(Value::as_i64) else {
@@ -279,25 +285,6 @@ fn dispatch(inner: &Inner, incoming: &mpsc::UnboundedSender<Incoming>, body: &[u
}
}
/// A message body as JSON. Some adapters pass the debuggee's output through as it was
/// written: netcoredbg on Windows embeds console output in the ANSI code page (GBK on a
/// Chinese system), which isn't valid UTF-8 and made the whole `output` event unparsable,
/// so every line with non-ASCII text went missing. Such a body is decoded like other tool
/// output (UTF-8, else the system code page) before parsing.
fn parse_message(body: &[u8]) -> Option<Value> {
let error = match serde_json::from_slice(body) {
Ok(v) => return Some(v),
Err(e) => e,
};
if std::str::from_utf8(body).is_err()
&& let Ok(v) = serde_json::from_str(&ide_core::output_encoding::decode_tool_output(body))
{
return Some(v);
}
tracing::warn!("dap: unparsable message: {error}");
None
}
/// `message`, or the formatted `body.error` (`{format, variables}`) when present.
fn error_message(msg: &Value) -> String {
if let Some(err) = msg.pointer("/body/error")
@@ -319,22 +306,6 @@ fn error_message(msg: &Value) -> String {
mod tests {
use super::*;
#[test]
fn parses_output_events_with_non_utf8_text() {
// "中文" in GBK inside an output event, as netcoredbg sends it on a Chinese Windows.
let mut body = br#"{"seq":5,"type":"event","event":"output","body":{"category":"stdout","output":""#.to_vec();
body.extend_from_slice(&[0xd6, 0xd0, 0xce, 0xc4]);
body.extend_from_slice(br#"\n"}}"#);
let msg = parse_message(&body).expect("parsed");
assert_eq!(msg["event"], "output");
let output = msg["body"]["output"].as_str().unwrap();
assert!(output.ends_with('\n'));
// Off Windows (UTF-8 code page) the bytes decode lossily; the line still arrives.
#[cfg(not(windows))]
assert!(output.starts_with(char::REPLACEMENT_CHARACTER));
assert!(parse_message(b"{not json").is_none());
}
#[test]
fn formats_structured_errors() {
let msg =
@@ -342,16 +313,4 @@ mod tests {
assert_eq!(error_message(&msg), "cannot find a.py");
assert_eq!(error_message(&json!({"message": "nope"})), "nope");
}
#[test]
fn a_failed_launch_response_keeps_delves_too_old_error_verbatim() {
// The UI's repair offer keys off this exact wording (`missingAdapter`), so the
// conversion to the IPC error must not fold it into a generic message.
let message = "Failed to launch /p/api: Version of Delve is too old for Go version go1.27.0 \
(maximum supported version 1.26, suppress this error with --check-go-version=false)";
let e = ide_core::IdeError::from(DapError::Failed { command: "launch".into(), message: message.into() });
assert_eq!(e.kind, ide_core::error::ErrorKind::InvalidInput);
assert_eq!(e.message, format!("launch failed: {message}"));
assert!(e.message.contains("Version of Delve is too old for Go version go1.27.0"));
}
}
+12 -99
View File
@@ -12,35 +12,6 @@ use tokio::net::{TcpListener, TcpStream};
/// How long the relay waits for java-debug to attach once the JVM is connected.
const ATTACH_TIMEOUT: Duration = Duration::from_secs(60);
/// Loopback ports relaying a connected JVM, while their relay runs.
static RELAY_PORTS: std::sync::Mutex<Vec<u16>> = std::sync::Mutex::new(Vec::new());
fn relay_ports() -> std::sync::MutexGuard<'static, Vec<u16>> {
RELAY_PORTS.lock().unwrap_or_else(std::sync::PoisonError::into_inner)
}
/// Whether `port` is a relay of [`listen_for_jvm`]: a session attaching to it debugs a JVM that
/// connected to the IDE, so the JVM has no JDWP listener the memory view could find it by.
pub(crate) fn is_listen_relay(port: u16) -> bool {
relay_ports().contains(&port)
}
/// Registers a relay port for as long as it lives.
struct RelayPort(u16);
impl RelayPort {
fn new(port: u16) -> Self {
relay_ports().push(port);
Self(port)
}
}
impl Drop for RelayPort {
fn drop(&mut self) {
relay_ports().retain(|&p| p != self.0);
}
}
/// The address to listen on for `host`: the interface it names, or every interface when
/// it is not one of this machine's (a DNS name or a NAT address the JVM connects to).
async fn bind(host: &str, port: u16) -> IdeResult<TcpListener> {
@@ -69,11 +40,11 @@ pub async fn listen_for_jvm(host: &str, port: u16, cancel: CancellationToken) ->
let _ = jvm.set_nodelay(true);
let relay = TcpListener::bind(("127.0.0.1", 0)).await?;
let local = relay.local_addr()?.port();
tokio::spawn(relay_one(relay, jvm, RelayPort::new(local)));
tokio::spawn(relay_one(relay, jvm));
Ok(local)
}
async fn relay_one(relay: TcpListener, mut jvm: TcpStream, _registered: RelayPort) {
async fn relay_one(relay: TcpListener, mut jvm: TcpStream) {
let debugger = match tokio::time::timeout(ATTACH_TIMEOUT, relay.accept()).await {
Ok(Ok((s, _))) => s,
_ => return,
@@ -87,64 +58,22 @@ async fn relay_one(relay: TcpListener, mut jvm: TcpStream, _registered: RelayPor
}
#[cfg(test)]
pub(crate) mod tests {
mod tests {
use super::*;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
/// A remote JVM (`server=n`) connected to [`listen_for_jvm`], and the relay port. A port
/// picked by binding to 0 can be taken by a parallel test before `listen_for_jvm` binds it,
/// so a failed listen is retried on a fresh one.
pub(crate) async fn connected_jvm() -> (TcpStream, u16) {
for _ in 0..20 {
let port = TcpListener::bind(("127.0.0.1", 0)).await.unwrap().local_addr().unwrap().port();
if let Some(connected) = jvm_on(port).await {
return connected;
}
}
panic!("listen_for_jvm never accepted a JVM");
}
/// One attempt of [`connected_jvm`]; `None` when the port turned out to be taken.
async fn jvm_on(port: u16) -> Option<(TcpStream, u16)> {
let mut waiting = tokio::spawn(listen_for_jvm("127.0.0.1", port, CancellationToken::new()));
let mut jvm = None;
for _ in 0..100 {
// A listen that failed to bind leaves nothing to connect to.
if waiting.is_finished() {
break;
}
// macOS does not refuse a connect to a port a socket holds without listening: the
// SYN goes unanswered until the connect times out.
let connect = TcpStream::connect(("127.0.0.1", port));
if let Ok(Ok(s)) = tokio::time::timeout(Duration::from_secs(1), connect).await {
jvm = Some(s);
break;
}
tokio::time::sleep(Duration::from_millis(20)).await;
}
// A connection to another test's listener never reaches `listen_for_jvm`.
let relay = tokio::time::timeout(Duration::from_secs(2), &mut waiting).await;
if let (Some(jvm), Ok(Ok(Ok(relay)))) = (jvm, relay) {
return Some((jvm, relay));
}
waiting.abort();
None
}
#[tokio::test]
async fn a_port_another_socket_holds_is_given_up() {
// Bound but not listening, as a parallel test's outgoing connection holds its local port.
let held = tokio::net::TcpSocket::new_v4().unwrap();
held.bind(([127, 0, 0, 1], 0).into()).unwrap();
let port = held.local_addr().unwrap().port();
let attempt = tokio::time::timeout(Duration::from_secs(5), jvm_on(port)).await;
assert!(matches!(attempt, Ok(None)), "an attempt on a taken port gives up instead of waiting forever");
}
#[tokio::test]
async fn relays_the_jdwp_handshake_both_ways() {
let port = TcpListener::bind(("127.0.0.1", 0)).await.unwrap().local_addr().unwrap().port();
let waiting = tokio::spawn(listen_for_jvm("127.0.0.1", port, CancellationToken::new()));
// The remote JVM (`server=n`) connects to the IDE.
let (mut jvm, local) = connected_jvm().await;
let mut jvm = loop {
if let Ok(s) = TcpStream::connect(("127.0.0.1", port)).await {
break s;
}
tokio::time::sleep(Duration::from_millis(20)).await;
};
let local = waiting.await.unwrap().unwrap();
// java-debug attaches to the relay and starts the handshake.
let mut debugger = TcpStream::connect(("127.0.0.1", local)).await.unwrap();
debugger.write_all(b"JDWP-Handshake").await.unwrap();
@@ -156,22 +85,6 @@ pub(crate) mod tests {
assert_eq!(&buf, b"JDWP-Handshake");
}
#[tokio::test]
async fn relay_port_is_known_while_the_relay_runs() {
let (jvm, local) = connected_jvm().await;
assert!(is_listen_relay(local));
let debugger = TcpStream::connect(("127.0.0.1", local)).await.unwrap();
drop((jvm, debugger));
for _ in 0..200 {
if !is_listen_relay(local) {
return;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
panic!("relay port {local} still registered after the relay ended");
}
#[tokio::test]
async fn waiting_is_cancellable() {
let cancel = CancellationToken::new();
-92
View File
@@ -1,92 +0,0 @@
//! The class table counted by the debugger (JDWP `InstanceCounts`) where no histogram can be
//! taken: JDK 8-16 while suspended, Windows, a remote JVM. Only while suspended, and slow on a
//! large heap (seconds on JDK 17+).
use super::inspect::Call;
use super::snapshot::diff_rows;
use super::{ClassCounts, JvmMemoryResult, JvmMemorySnapshot, JvmMemorySource, JvmMemoryState, JvmMemoryUnavailable};
use crate::session::Session;
use ide_core::IdeResult;
use ide_jvm_attach::HistogramRow;
use ide_jvm_inspect::ClassCount;
/// Reasons the debugger may be able to work around; the others (the program exited, the JVM
/// did not answer) would fail for it too.
pub(super) fn falls_back(reason: &JvmMemoryUnavailable) -> bool {
use JvmMemoryUnavailable as U;
matches!(
reason,
U::UnsafeWhileSuspended { .. }
| U::UnsupportedPlatform
| U::AttachedJvmNotFound
| U::ListenerNotRunning
| U::ListenModeNotSupported
| U::NoJvmProcess
)
}
/// `histogram` unless it is unavailable for a reason `session`'s inspector can work around.
pub(super) async fn or_debugger_counts(
state: &mut JvmMemoryState,
histogram: Result<JvmMemorySnapshot, JvmMemoryUnavailable>,
session: Option<&Session>,
) -> IdeResult<JvmMemoryResult> {
let reason = match histogram {
Ok(snapshot) => return Ok(JvmMemoryResult::Ready { snapshot }),
Err(reason) => reason,
};
let unavailable = |can_count_when_paused| Ok(JvmMemoryResult::Unavailable { reason, can_count_when_paused });
let Some(session) = session.filter(|_| falls_back(&reason)) else {
return unavailable(false);
};
let call = match Call::begin(session, None).await {
Ok(call) => call,
Err(super::JvmInspectUnavailable::NotSuspended) => return unavailable(true),
Err(_) => return unavailable(false),
};
let started = std::time::Instant::now();
let result = call.run(call.inspector.class_counts(&call.target)).await;
match call.finish(result) {
Ok(counts) => {
let elapsed_ms = u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX);
let previous = state.baseline(JvmMemorySource::Debugger);
let (snapshot, counts) = debugger_snapshot(counts, previous.as_deref(), elapsed_ms);
state.remember(JvmMemorySource::Debugger, counts);
Ok(JvmMemoryResult::Ready { snapshot })
}
Err(e) => {
tracing::debug!("debugger class counts: {e}");
let running = !session.suspended.get();
unavailable(running && session.jvm_inspector.lock().is_some())
}
}
}
/// Classes without instances are left out; most instances first.
pub(super) fn debugger_snapshot(
counts: Vec<ClassCount>,
previous: Option<&ClassCounts>,
elapsed_ms: u32,
) -> (JvmMemorySnapshot, ClassCounts) {
let rows = counts
.into_iter()
.filter(|c| c.instances > 0)
.map(|c| HistogramRow { name: c.name, module: None, instances: c.instances, bytes: 0 })
.collect();
let (mut rows, counts) = diff_rows(rows, previous);
for row in &mut rows {
row.delta_bytes = None;
}
rows.sort_by(|a, b| b.instances.cmp(&a.instances).then_with(|| a.name.cmp(&b.name)));
let snapshot = JvmMemorySnapshot {
total_instances: rows.iter().map(|r| r.instances).sum(),
total_bytes: 0,
rows,
java_version: String::new(),
taken_while_suspended: true,
has_baseline: previous.is_some(),
elapsed_ms,
source: JvmMemorySource::Debugger,
};
(snapshot, counts)
}
-293
View File
@@ -1,293 +0,0 @@
//! A heap dump of a debugged JVM, written over its attach listener into a snapshot directory.
use super::snapshot::{AttachProbe, JdkProbe, attach_failure, gone, pick_jvm_pid};
use super::{
JvmMemoryState, JvmMemoryUnavailable, JvmTarget, histogram_pid, keep_found, lookup, resolve_jvm,
safe_while_suspended, session_target,
};
use crate::session::Session;
use ide_core::{CancellationToken, IdeError, IdeResult};
use ide_jvm_attach::{AttachError, HeapDumpReply};
use serde::{Deserialize, Serialize};
use specta::Type;
use std::future::Future;
use std::path::{Path, PathBuf};
use std::sync::Arc;
const DUMP_FILE: &str = "dump.hprof";
/// For a refusal whose reply holds no reason: empty, or only the line announcing the dump.
const NO_REASON: &str = "the JVM wrote no heap dump and gave no reason";
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmHeapUnavailable {
/// The reason a class table could not be read applies to the dump too.
Memory {
reason: JvmMemoryUnavailable,
},
/// Bytes.
NotEnoughDiskSpace {
needed: u64,
available: u64,
},
DumpFailed {
message: String,
},
DumpTimedOut {
seconds: u32,
},
}
#[derive(Clone, Debug, PartialEq)]
pub struct JvmHeapDump {
pub path: PathBuf,
/// The class histogram taken just before the dump.
pub histogram: Vec<ide_heap::HistogramEntry>,
/// Raw `VM.flags`; empty when the JVM did not answer.
pub vm_flags: String,
/// 0 when unknown.
pub java_major: u32,
/// Empty when unknown.
pub java_version: String,
pub pid: u32,
pub taken_while_suspended: bool,
pub dump_ms: u32,
}
#[derive(Clone, Debug, PartialEq)]
pub enum JvmHeapOutcome {
Ready(JvmHeapDump),
/// The snapshot directory has been deleted.
Unavailable(JvmHeapUnavailable),
/// The snapshot directory has been deleted.
Cancelled,
}
pub(crate) async fn session_heap_dump(
session: Arc<Session>,
dir: PathBuf,
cancel: CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
let launched = histogram_pid(&session);
let capture = {
let (dir, cancel) = (dir.clone(), cancel.clone());
async move {
let target = session_target(&session, launched);
let probe = |suspended| -> Arc<dyn AttachProbe> { Arc::new(JdkProbe { suspended }) };
let stopped = session.clone();
let suspended = move || capture_suspended(&stopped);
heap_dump_with(&session.jvm_memory, suspended, probe, target, dir, cancel).await
}
};
detached(capture, dir, cancel).await
}
/// The JVM can be suspended before the adapter reports the stop, so a session with a JDWP link
/// also counts the link's view.
pub(super) fn capture_suspended(session: &Session) -> bool {
session.suspended.get()
|| session
.jdwp_link
.lock()
.as_ref()
.is_some_and(|link| matches!(link.state(), ide_jdwp::LinkState::Suspended { .. }))
}
/// Runs `capture` in a task of its own, so a caller that stops waiting cannot release the
/// session's lock while the JVM is still writing the dump and let a class-table request run
/// next to it. On `cancel` returns at once and deletes `dir`.
pub(super) async fn detached(
capture: impl Future<Output = IdeResult<JvmHeapOutcome>> + Send + 'static,
dir: PathBuf,
cancel: CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
let task = tokio::spawn(capture);
tokio::select! {
joined = task => joined.map_err(|e| IdeError::internal(format!("JVM heap dump failed: {e}")))?,
() = cancel.cancelled() => {
discard_later(dir).await;
Ok(JvmHeapOutcome::Cancelled)
}
}
}
/// Holds `state`'s lock throughout, as a class-table request does; `suspended` and then `probe`
/// are read once it is held, and `suspended` again by [`take_heap_dump`]. Anything but `Ready`
/// deletes `dir`.
pub(super) async fn heap_dump_with(
state: &tokio::sync::Mutex<JvmMemoryState>,
suspended: impl Fn() -> bool + Send + Sync + 'static,
probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
target: JvmTarget<'_>,
dir: PathBuf,
cancel: CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
// The capture's histogram never becomes the Memory view's baseline, so the state is unused.
let _turn = state.lock().await;
let outcome = capture(suspended, probe, target, dir.clone(), cancel).await;
if !matches!(outcome, Ok(JvmHeapOutcome::Ready(_))) {
discard_later(dir).await;
}
outcome
}
async fn capture(
suspended_now: impl Fn() -> bool + Send + Sync + 'static,
probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
target: JvmTarget<'_>,
dir: PathBuf,
cancel: CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
if cancel.is_cancelled() {
return Ok(JvmHeapOutcome::Cancelled);
}
let suspended = suspended_now();
let lookup = match lookup(target) {
Ok(lookup) => lookup,
Err(reason) => return Ok(memory(reason)),
};
let probe = probe(suspended);
let (found, outcome) = tokio::task::spawn_blocking(move || match resolve_jvm(lookup, &*probe, suspended) {
Ok((tree, found)) => (found, take_heap_dump(&*probe, &tree, suspended, &suspended_now, &dir, &cancel)),
Err(reason) => (None, Ok(memory(reason))),
})
.await
.map_err(|e| IdeError::internal(format!("JVM heap dump failed: {e}")))?;
keep_found(target, found);
outcome
}
/// `tree` starts with the session's reported pid, followed by its descendants. `suspended` is
/// the stop read when the capture began; `suspended_now` reads it again. Anything but `Ready`
/// deletes `dir`.
pub(crate) fn take_heap_dump(
probe: &dyn AttachProbe,
tree: &[i32],
suspended: bool,
suspended_now: &dyn Fn() -> bool,
dir: &Path,
cancel: &CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
let outcome = dump(probe, tree, suspended, suspended_now, dir, cancel);
if !matches!(outcome, Ok(JvmHeapOutcome::Ready(_))) {
discard(dir);
}
outcome
}
fn dump(
probe: &dyn AttachProbe,
tree: &[i32],
suspended: bool,
suspended_now: &dyn Fn() -> bool,
dir: &Path,
cancel: &CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
use JvmHeapUnavailable as H;
use JvmMemoryUnavailable as U;
let Some(root) = tree.first().and_then(|&p| u32::try_from(p).ok()) else {
return Ok(memory(U::NoJvmProcess));
};
let Some(jvm) = pick_jvm_pid(tree, |p| probe.has_listener(p)) else {
return Ok(memory(gone(probe, root)));
};
let version = probe.version(jvm);
let java_major = version.as_ref().map_or(0, |v| v.major);
let safe = safe_while_suspended(version.as_ref());
let unsafe_stop = || Ok(memory(U::UnsafeWhileSuspended { java_major }));
if suspended && !safe {
return unsafe_stop();
}
// The program may stop during the histogram, and a stopped JDK below 17 hangs on the next
// request until it resumes.
let stopped_since = || !safe && suspended_now();
let text = match probe.histogram(jvm) {
Ok(text) => text,
Err(e) => return attach_failure(probe, jvm, e, "class histogram").map(memory),
};
let histogram: Vec<ide_heap::HistogramEntry> = ide_jvm_attach::parse_class_histogram(&text)
.rows
.into_iter()
.map(|r| ide_heap::HistogramEntry { name: r.name, instances: r.instances, bytes: r.bytes })
.collect();
let (instances, bytes) =
histogram.iter().fold((0u64, 0u64), |(i, b), e| (i.saturating_add(e.instances), b.saturating_add(e.bytes)));
let needed = ide_heap::capture_need(bytes, instances);
if let Some(available) = probe.free_bytes(dir)
&& available < needed
{
return Ok(JvmHeapOutcome::Unavailable(H::NotEnoughDiskSpace { needed, available }));
}
if stopped_since() {
return unsafe_stop();
}
// Without flags the index assumes the default object layout.
let vm_flags = probe.vm_flags(jvm).unwrap_or_else(|e| {
tracing::debug!("VM.flags of JVM {jvm}: {e}");
String::new()
});
if cancel.is_cancelled() {
return Ok(JvmHeapOutcome::Cancelled);
}
if stopped_since() {
return unsafe_stop();
}
let path = dir.join(DUMP_FILE);
let timeout = ide_jvm_attach::dump_timeout(bytes);
let started = std::time::Instant::now();
let reply = probe.heap_dump(jvm, &path, timeout);
let dump_ms = u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX);
if cancel.is_cancelled() {
return Ok(JvmHeapOutcome::Cancelled);
}
let failed = |message: String| Ok(JvmHeapOutcome::Unavailable(H::DumpFailed { message }));
match reply {
Ok(HeapDumpReply::Created { .. }) => {
if !std::fs::metadata(&path).is_ok_and(|m| m.is_file() && m.len() > 0) {
return failed(format!("the JVM reported a heap dump, but {} is missing or empty", path.display()));
}
Ok(JvmHeapOutcome::Ready(JvmHeapDump {
path,
histogram,
vm_flags,
java_major,
java_version: version.map(|v| v.text).unwrap_or_default(),
pid: jvm,
taken_while_suspended: suspended,
dump_ms,
}))
}
Ok(HeapDumpReply::Refused { message }) if message.is_empty() || message.starts_with("Dumping heap to") => {
failed(NO_REASON.into())
}
Ok(HeapDumpReply::Refused { message }) => failed(message),
Err(AttachError::Timeout) => {
let seconds = u32::try_from(timeout.as_secs()).unwrap_or(u32::MAX);
Ok(JvmHeapOutcome::Unavailable(H::DumpTimedOut { seconds }))
}
// A running JDK rejects an argument with a non-zero result code.
Err(AttachError::Command { message, .. }) => failed(message),
Err(e) => attach_failure(probe, jvm, e, "heap dump").map(memory),
}
}
fn memory(reason: JvmMemoryUnavailable) -> JvmHeapOutcome {
JvmHeapOutcome::Unavailable(JvmHeapUnavailable::Memory { reason })
}
fn discard(dir: &Path) {
if let Err(e) = std::fs::remove_dir_all(dir)
&& e.kind() != std::io::ErrorKind::NotFound
{
tracing::warn!("could not delete heap snapshot directory {}: {e}", dir.display());
}
}
/// A dump may be large, so it is deleted off the async threads.
async fn discard_later(dir: PathBuf) {
let _ = tokio::task::spawn_blocking(move || discard(&dir)).await;
}
-251
View File
@@ -1,251 +0,0 @@
//! A suspended JVM's instances, fields and referrers, read through the session's
//! [`JvmInspector`]. An object is only valid within the stop it was read in.
use super::launch_pid;
use crate::session::Session;
use ide_core::event::{DebugEvent, JvmBackendState};
use ide_core::{IdeError, IdeResult};
use ide_jvm_inspect::{
DEFAULT_REFERRERS, InspectError, InspectFuture, JvmField, JvmInspector, JvmReferrer, JvmValue, MAX_INSTANCES,
MAX_REFERRERS, ObjectId, VmTarget,
};
use serde::{Deserialize, Serialize};
use specta::Type;
use std::sync::Arc;
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct JvmObjectRef {
/// The `generation` of the [`JvmInstancesResult`] the object came from.
pub generation: u64,
pub id: ObjectId,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmInspectUnavailable {
/// The session has no inspector: not a JVM session, not ready yet, or turned off.
NoBackend,
/// The debug adapter lacks what the inspector needs; turned off for the session.
Unsupported {
detail: String,
},
NotSuspended,
/// The object is from an earlier stop, or the program stopped or resumed meanwhile.
Stale,
Collected,
ClassNotLoaded,
VmNotFound,
/// Transient: ask again.
TimedOut,
BackendClosed,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(tag = "status", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmInstancesResult {
Ready {
/// Goes into the [`JvmObjectRef`] of each instance.
generation: u64,
instances: Vec<JvmValue>,
/// The limit was reached; there may be more.
truncated: bool,
},
Unavailable {
reason: JvmInspectUnavailable,
},
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(tag = "status", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmFieldsResult {
Ready { fields: Vec<JvmField> },
Unavailable { reason: JvmInspectUnavailable },
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(tag = "status", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmReferrersResult {
Ready { referrers: Vec<JvmReferrer>, truncated: bool },
Unavailable { reason: JvmInspectUnavailable },
}
/// The session's JVM for the inspector: java-debug's VM is found by the launched program's pid
/// or by the port of an attach (the thread lists of two JVMs can be identical).
pub(crate) fn vm_target(s: &Session) -> VmTarget {
let (pid, attach) = if s.request == "launch" {
(u32::try_from(launch_pid(s)).ok().filter(|&p| p > 0), None)
} else {
(None, s.attach_target.get())
};
VmTarget {
pid,
attach_host: attach.map(|(host, _)| host.clone()).filter(|h| !h.is_empty()),
attach_port: attach.map(|&(_, port)| port),
generation: s.suspended.ticket(),
}
}
pub(crate) fn set_inspector(s: &Session, inspector: Arc<dyn JvmInspector>) {
*s.jvm_inspector.lock() = Some(inspector);
s.emit(DebugEvent::Capabilities);
}
pub(crate) async fn instances(s: &Session, class_name: &str, limit: u32) -> IdeResult<JvmInstancesResult> {
let limit = limit.clamp(1, MAX_INSTANCES);
let call = match Call::begin(s, None).await {
Ok(call) => call,
Err(reason) => return Ok(JvmInstancesResult::Unavailable { reason }),
};
let generation = call.target.generation;
let result = call.run(call.inspector.instances(&call.target, class_name, limit)).await;
Ok(match settle(call.finish(result))? {
Ok(instances) => {
JvmInstancesResult::Ready { generation, truncated: instances.len() >= limit as usize, instances }
}
Err(reason) => JvmInstancesResult::Unavailable { reason },
})
}
pub(crate) async fn fields(s: &Session, object: JvmObjectRef) -> IdeResult<JvmFieldsResult> {
let call = match Call::begin(s, Some(object.generation)).await {
Ok(call) => call,
Err(reason) => return Ok(JvmFieldsResult::Unavailable { reason }),
};
let result = call.run(call.inspector.fields(&call.target, object.id)).await;
Ok(match settle(call.finish(result))? {
Ok(fields) => JvmFieldsResult::Ready { fields },
Err(reason) => JvmFieldsResult::Unavailable { reason },
})
}
pub(crate) async fn referrers(s: &Session, object: JvmObjectRef, limit: u32) -> IdeResult<JvmReferrersResult> {
let limit = if limit == 0 { DEFAULT_REFERRERS } else { limit.min(MAX_REFERRERS) };
let call = match Call::begin(s, Some(object.generation)).await {
Ok(call) => call,
Err(reason) => return Ok(JvmReferrersResult::Unavailable { reason }),
};
let result = call.run(call.inspector.referrers(&call.target, object.id, limit)).await;
Ok(match settle(call.finish(result))? {
Ok(referrers) => JvmReferrersResult::Ready { truncated: referrers.len() >= limit as usize, referrers },
Err(reason) => JvmReferrersResult::Unavailable { reason },
})
}
/// One inspector request. Holds the session's inspect lock and a clone of its inspector, which
/// [`Call::run`] lets go of when the session ends.
pub(super) struct Call<'s> {
session: &'s Session,
pub(super) inspector: Arc<dyn JvmInspector>,
pub(super) target: VmTarget,
_turn: tokio::sync::MutexGuard<'s, ()>,
}
impl<'s> Call<'s> {
/// `object_generation`: the stop the request's object was read in.
pub(super) async fn begin(
s: &'s Session,
object_generation: Option<u64>,
) -> Result<Call<'s>, JvmInspectUnavailable> {
// Checked under the lock: a request queued behind another must see the state it runs in.
let turn = s.inspect_lock.lock().await;
let Some(inspector) = s.jvm_inspector.lock().clone() else {
return Err(JvmInspectUnavailable::NoBackend);
};
if !s.suspended.get() {
return Err(JvmInspectUnavailable::NotSuspended);
}
let target = vm_target(s);
if object_generation.is_some_and(|g| g != target.generation) {
return Err(JvmInspectUnavailable::Stale);
}
Ok(Call { session: s, inspector, target, _turn: turn })
}
pub(super) async fn run<T>(&self, request: InspectFuture<'_, T>) -> Result<T, InspectError> {
tokio::select! {
result = request => result,
() = self.session.ended.cancelled() => Err(InspectError::Closed),
}
}
/// The result unless the program stopped or resumed while it was read: a request of several
/// commands can straddle a stop. `Unsupported` turns the backend off.
pub(super) fn finish<T>(self, result: Result<T, InspectError>) -> Result<T, InspectError> {
let s = self.session;
match result {
Err(InspectError::Unsupported(detail)) => {
turn_off(s, &self.inspector, &detail);
Err(InspectError::Unsupported(detail))
}
_ if !s.suspended.get() || s.suspended.ticket() != self.target.generation => Err(InspectError::Stale),
result => result,
}
}
}
/// An adapter that lacks what the inspector needs will not gain it during the session.
fn turn_off(s: &Session, inspector: &Arc<dyn JvmInspector>, detail: &str) {
let removed = {
let mut slot = s.jvm_inspector.lock();
// Not one installed since this request began.
let current = slot.as_ref().is_some_and(|i| std::ptr::addr_eq(Arc::as_ptr(i), Arc::as_ptr(inspector)));
current && slot.take().is_some()
};
if removed {
s.emit(DebugEvent::JvmBackend { state: JvmBackendState::Unsupported { detail: detail.to_owned() } });
s.emit(DebugEvent::Capabilities);
}
}
/// A failure the inspector could not classify is an error, not a reason shown to the user.
fn settle<T>(result: Result<T, InspectError>) -> IdeResult<Result<T, JvmInspectUnavailable>> {
use JvmInspectUnavailable as U;
let error = match result {
Ok(value) => return Ok(Ok(value)),
Err(error) => error,
};
Ok(Err(match error {
InspectError::NotSuspended => U::NotSuspended,
InspectError::Stale => U::Stale,
InspectError::Collected => U::Collected,
InspectError::ClassNotLoaded => U::ClassNotLoaded,
InspectError::VmNotFound => U::VmNotFound,
InspectError::Unsupported(detail) => U::Unsupported { detail },
// Also the Kotlin link's `Busy`: the backend stays.
InspectError::TimedOut => U::TimedOut,
InspectError::Closed => U::BackendClosed,
InspectError::Failed(message) => return Err(IdeError::internal(format!("JVM inspector: {message}"))),
}))
}
/// Reports a Kotlin link that stops inspecting or closes. Holds neither the link nor the
/// session: it ends once the session drops the link, and never drops it itself (after
/// `VirtualMachine.Dispose` the link is closed but still forwarding the reply).
pub(crate) fn watch_link(s: &Arc<Session>, link: &ide_jdwp::JdwpLink) {
let mut states = link.subscribe();
let session = Arc::downgrade(s);
tokio::spawn(async move {
let mut reported = None;
loop {
let state = match &*states.borrow_and_update() {
ide_jdwp::LinkState::Degraded(detail) => Some(JvmBackendState::Degraded { detail: detail.clone() }),
ide_jdwp::LinkState::Closed => Some(JvmBackendState::Closed),
_ => None,
};
if let Some(state) = state
&& reported.as_ref() != Some(&state)
{
let Some(s) = session.upgrade() else { return };
if s.ended.is_cancelled() || s.terminated.load(std::sync::atomic::Ordering::Acquire) {
return;
}
s.emit(DebugEvent::JvmBackend { state: state.clone() });
reported = Some(state);
}
if states.changed().await.is_err() {
return;
}
}
});
}
-338
View File
@@ -1,338 +0,0 @@
//! Class-table snapshots of a debugged JVM, read over the HotSpot attach listener or, where
//! that is unavailable, counted by the debugger; and the JVM's objects through the debugger.
mod fallback;
mod heap;
mod inspect;
mod scan;
mod snapshot;
#[cfg(test)]
pub(crate) mod test_support;
#[cfg(test)]
mod tests;
use crate::session::Session;
use crate::session::Suspension;
use ide_core::IdeResult;
use serde::{Deserialize, Serialize};
use specta::Type;
use std::collections::HashMap;
use std::sync::Arc;
use std::sync::atomic::{AtomicI64, Ordering};
use std::time::Duration;
pub use heap::*;
pub use inspect::{JvmFieldsResult, JvmInspectUnavailable, JvmInstancesResult, JvmObjectRef, JvmReferrersResult};
pub(crate) use inspect::{fields, instances, referrers, set_inspector, watch_link};
#[cfg(all(test, unix))]
pub(crate) use scan::watch_for_attached_jvm;
pub(crate) use scan::{JvmFinder, attach_target, find_attached_jvm, find_local_jvm, local_jdwp_port};
use snapshot::{AttachProbe, JdkProbe, take_snapshot};
pub const JVM_MEMORY_ADAPTERS: &[&str] = &["java-debug", crate::kotlin::ADAPTER];
pub const HISTOGRAM_TIMEOUT: Duration = Duration::from_secs(10);
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct JvmClassRow {
pub name: String,
pub module: Option<String>,
pub instances: u64,
pub bytes: u64,
/// Change since the previous snapshot; `None` on the first one and for ambiguous rows.
pub delta_instances: Option<i64>,
pub delta_bytes: Option<i64>,
/// Several classes share this name (different class loaders), so it has no delta.
pub ambiguous: bool,
}
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct JvmMemorySnapshot {
/// Largest `bytes` first.
pub rows: Vec<JvmClassRow>,
pub total_instances: u64,
pub total_bytes: u64,
/// Empty when unknown.
pub java_version: String,
pub taken_while_suspended: bool,
/// A previous snapshot from the same source exists; deltas are against it.
pub has_baseline: bool,
/// Wall time of the histogram or count request.
pub elapsed_ms: u32,
pub source: JvmMemorySource,
}
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub enum JvmMemorySource {
/// `GC.class_histogram -all`: sizes, and objects not yet collected.
Histogram,
/// JDWP `InstanceCounts`: reachable objects only, no sizes (`bytes` is 0).
Debugger,
}
#[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize, Type)]
#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmMemoryUnavailable {
/// An attach session whose JVM is remote, or local but not found by its JDWP port.
AttachedJvmNotFound,
/// An attach through the IDE's listen-mode relay: the JVM connected to the IDE, so it has
/// no JDWP listener to be found by.
ListenModeNotSupported,
UnsupportedPlatform,
NoJvmProcess,
ListenerNotRunning,
/// `java_major` is 0 when the version is unknown.
UnsafeWhileSuspended {
java_major: u32,
},
ProgramExited,
TimedOut,
}
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, Type)]
#[serde(tag = "status", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum JvmMemoryResult {
Ready {
snapshot: JvmMemorySnapshot,
},
Unavailable {
reason: JvmMemoryUnavailable,
/// The debugger could count the classes if the program were paused.
can_count_when_paused: bool,
},
}
/// Instances and bytes per class name, for the next snapshot's deltas; `None` for a name
/// several classes shared, so it gets no delta next time either.
type ClassCounts = HashMap<String, Option<(u64, u64)>>;
/// Per-session baseline; its mutex also keeps one class-table request per session at a time.
#[derive(Default)]
pub struct JvmMemoryState {
/// Shared with the blocking task, so a task that panics leaves it in place.
previous: Option<(JvmMemorySource, Arc<ClassCounts>)>,
}
impl JvmMemoryState {
/// The previous snapshot's counts if it came from `source`: counts from the other source
/// are not comparable (only reachable objects versus all of them).
pub(crate) fn baseline(&self, source: JvmMemorySource) -> Option<Arc<ClassCounts>> {
self.previous.as_ref().filter(|(s, _)| *s == source).map(|(_, counts)| counts.clone())
}
pub(crate) fn remember(&mut self, source: JvmMemorySource, counts: ClassCounts) {
self.previous = Some((source, Arc::new(counts)));
}
}
pub(crate) async fn session_classes(session: Arc<Session>) -> IdeResult<JvmMemoryResult> {
until_located(&session).await;
let launched = histogram_pid(&session);
// Detached, so a caller that gives up cannot release the lock while the JVM is still
// answering and let a second histogram request run next to it.
tokio::spawn(async move {
let target = session_target(&session, launched);
let probe = |suspended| -> Arc<dyn AttachProbe> { Arc::new(JdkProbe { suspended }) };
snapshot(&session.jvm_memory, &session.suspended, probe, target, Some(&session)).await
})
.await
.map_err(|e| ide_core::IdeError::internal(format!("JVM memory snapshot failed: {e}")))?
}
/// Bounds the wait of [`until_located`]; `configure` has its own timeouts, this only guards them.
const LOCATE_WAIT: Duration = Duration::from_secs(30);
/// Until `configure` has recorded where `session`'s JVM is. The Memory view asks as soon as the
/// session appears; looked up earlier, an attached JVM is reported as missing.
async fn until_located(session: &Session) {
let mut located = session.jvm_located.subscribe();
tokio::select! {
_ = located.wait_for(|v| *v) => {}
() = session.ended.cancelled() => {}
() = tokio::time::sleep(LOCATE_WAIT) => {}
}
}
/// `launched`: [`histogram_pid`] of `session`.
fn session_target(session: &Session, launched: Result<Option<i32>, JvmMemoryUnavailable>) -> JvmTarget<'_> {
match launched {
Ok(Some(pid)) => JvmTarget::Launched(pid),
Ok(None) => JvmTarget::Attached { pid: &session.jvm_pid, jdwp_port: session.jdwp_port.get().copied() },
Err(reason) => JvmTarget::Unavailable(reason),
}
}
/// The pid of a launch session's program (`None` for an attach session), or why no histogram
/// can be taken.
fn histogram_pid(session: &Session) -> Result<Option<i32>, JvmMemoryUnavailable> {
if !JVM_MEMORY_ADAPTERS.contains(&session.adapter.as_str()) {
return Err(JvmMemoryUnavailable::NoJvmProcess);
}
if !cfg!(unix) {
return Err(JvmMemoryUnavailable::UnsupportedPlatform);
}
if session.request == "launch" {
return match i32::try_from(launch_pid(session)).ok().filter(|&p| p > 0) {
Some(pid) => Ok(Some(pid)),
None => Err(JvmMemoryUnavailable::NoJvmProcess),
};
}
if session.jvm_pid.load(Ordering::Acquire) <= 0 {
if session.terminated.load(Ordering::Acquire) {
return Err(JvmMemoryUnavailable::ProgramExited);
}
if session.listen_relay.load(Ordering::Acquire) {
return Err(JvmMemoryUnavailable::ListenModeNotSupported);
}
}
Ok(None)
}
/// The JVM a launch session started: the one the IDE started for an app-launched (Kotlin)
/// session, else the program the adapter reported; 0 when neither is known.
pub(crate) fn launch_pid(session: &Session) -> i64 {
match session.jvm_pid.load(Ordering::Acquire) {
p if p > 0 => p,
_ => session.debuggee_pid.load(Ordering::Acquire),
}
}
#[derive(Clone, Copy)]
pub(crate) enum JvmTarget<'a> {
/// The program a launch session started: its pid and everything it started.
Launched(i32),
/// The JVM of an attach session. While `pid` is 0 it is looked up by `jdwp_port`, which is
/// `None` for a remote JVM.
Attached { pid: &'a AtomicI64, jdwp_port: Option<u16> },
/// Known without asking any JVM: no histogram can be taken, for this reason.
Unavailable(JvmMemoryUnavailable),
}
enum Lookup {
Tree(i32),
Known(i32),
Scan(u16),
}
/// `probe` is built from the suspension read once the lock is held: a request queued behind
/// another must not decide on a state from before the program hit a breakpoint. Where no
/// histogram can be taken, `debugger` (the session) may count the classes instead.
pub(crate) async fn snapshot(
state: &tokio::sync::Mutex<JvmMemoryState>,
suspended: &Suspension,
probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
target: JvmTarget<'_>,
debugger: Option<&Session>,
) -> IdeResult<JvmMemoryResult> {
let mut state = state.lock().await;
let outcome = histogram(&mut state, suspended, probe, target).await?;
fallback::or_debugger_counts(&mut state, outcome, debugger).await
}
async fn histogram(
state: &mut JvmMemoryState,
suspended: &Suspension,
probe: impl FnOnce(bool) -> Arc<dyn AttachProbe>,
target: JvmTarget<'_>,
) -> IdeResult<Result<JvmMemorySnapshot, JvmMemoryUnavailable>> {
let suspended = suspended.get();
let lookup = match lookup(target) {
Ok(lookup) => lookup,
Err(reason) => return Ok(Err(reason)),
};
let probe = probe(suspended);
let previous = state.baseline(JvmMemorySource::Histogram);
let (found, outcome) = tokio::task::spawn_blocking(move || match resolve_jvm(lookup, &*probe, suspended) {
Ok((tree, found)) => (found, take_snapshot(&*probe, &tree, suspended, previous.as_deref())),
Err(reason) => (None, Ok(Err(reason))),
})
.await
.map_err(|e| ide_core::IdeError::internal(format!("JVM memory snapshot failed: {e}")))?;
keep_found(target, found);
Ok(outcome?.map(|(snapshot, counts)| {
state.remember(JvmMemorySource::Histogram, counts);
snapshot
}))
}
/// Where to look for `target`'s JVM, or why there is none to ask.
fn lookup(target: JvmTarget<'_>) -> Result<Lookup, JvmMemoryUnavailable> {
match target {
JvmTarget::Launched(pid) => Ok(Lookup::Tree(pid)),
JvmTarget::Attached { pid, jdwp_port } => match i32::try_from(pid.load(Ordering::Acquire)) {
Ok(p) if p > 0 => Ok(Lookup::Known(p)),
_ => jdwp_port.map(Lookup::Scan).ok_or(JvmMemoryUnavailable::AttachedJvmNotFound),
},
JvmTarget::Unavailable(reason) => Err(reason),
}
}
/// Blocking. The pids to pick the JVM from, and the pid a scan found (for [`keep_found`]).
fn resolve_jvm(
lookup: Lookup,
probe: &dyn AttachProbe,
suspended: bool,
) -> Result<(Vec<i32>, Option<i32>), JvmMemoryUnavailable> {
match lookup {
Lookup::Tree(pid) => Ok((pid_tree(pid), None)),
Lookup::Known(pid) => Ok((vec![pid], None)),
Lookup::Scan(port) => scan_for_jvm(probe, port, suspended).map(|pid| (vec![pid], Some(pid))),
}
}
fn keep_found(target: JvmTarget<'_>, found: Option<i32>) {
if let (Some(found), JvmTarget::Attached { pid, .. }) = (found, target) {
// The attach-time scan may have found it meanwhile; either answer is the same JVM.
let _ = pid.compare_exchange(0, i64::from(found), Ordering::AcqRel, Ordering::Acquire);
}
}
/// A suspended JDK below 17 hangs on an attach request, so while suspended only a JVM known to
/// be 17 or later is asked anything. Pass a version read without attaching (the `release` file).
fn safe_while_suspended(version: Option<&ide_jvm_attach::JavaVersion>) -> bool {
version.is_some_and(|v| ide_jvm_attach::histogram_safe_while_suspended(v.major))
}
/// The JVM listening on JDWP `port`. While suspended the scan reaches the session's own JVM
/// too, so JVMs unsafe to ask are skipped, and when one of them may be the session's the
/// answer is a refusal rather than "not found".
fn scan_for_jvm(probe: &dyn AttachProbe, port: u16, suspended: bool) -> Result<i32, JvmMemoryUnavailable> {
// Majors of the JVMs left out; 0 for an unknown version.
let skipped = std::cell::RefCell::new(std::collections::BTreeSet::new());
let may_query = |pid: u32| {
if !suspended {
return true;
}
let version = probe.version(pid);
let safe = safe_while_suspended(version.as_ref());
if !safe {
skipped.borrow_mut().insert(version.map_or(0, |v| v.major));
}
safe
};
match probe.find_by_jdwp_port(port, &may_query).and_then(|p| i32::try_from(p).ok()) {
Some(pid) if pid > 0 => Ok(pid),
_ => {
let skipped = skipped.into_inner();
Err(match skipped.first() {
None => JvmMemoryUnavailable::AttachedJvmNotFound,
Some(&major) => JvmMemoryUnavailable::UnsafeWhileSuspended {
java_major: if skipped.len() == 1 { major } else { 0 },
},
})
}
}
}
fn pid_tree(pid: i32) -> Vec<i32> {
#[cfg(unix)]
{
ide_core::process::process_tree(pid)
}
#[cfg(not(unix))]
{
vec![pid]
}
}
-146
View File
@@ -1,146 +0,0 @@
//! Finding the JVM behind an attach session by its JDWP port.
use super::safe_while_suspended;
use crate::session::Session;
use serde_json::Value;
use std::net::IpAddr;
use std::sync::Arc;
use std::sync::atomic::Ordering;
use std::time::Duration;
/// One try of the scan at attach time, and the limit per socket within it: a silent socket's
/// query thread lives that long, so a longer per-socket limit piles threads up across tries.
const ATTACH_SCAN_TRY: Duration = Duration::from_millis(500);
const ATTACH_SCAN_INTERVAL: Duration = Duration::from_millis(150);
/// The JVM's attach socket can appear a little after the JDWP "Listening" banner, which is
/// when the IDE attaches.
const ATTACH_SCAN_WINDOW: Duration = Duration::from_secs(3);
/// The single scan a refresh makes while the attach-time one found nothing.
pub(super) const RESCAN_PER_SOCKET: Duration = Duration::from_secs(1);
pub(super) const RESCAN_BUDGET: Duration = Duration::from_secs(2);
/// JDWP port of an attach to this machine (`hostName` loopback or absent): only such a JVM has
/// an attach socket the IDE can find.
pub(crate) fn local_jdwp_port(arguments: &Value) -> Option<u16> {
let local = match arguments.get("hostName") {
None | Some(Value::Null) => true,
Some(Value::String(host)) => {
let host = host.trim();
let ip = host.strip_prefix('[').and_then(|h| h.strip_suffix(']')).unwrap_or(host);
host.eq_ignore_ascii_case("localhost") || ip.parse::<IpAddr>().is_ok_and(|ip| ip.is_loopback())
}
Some(_) => false,
};
jdwp_port(arguments).filter(|_| local)
}
/// `port` of an attach request: a number or a numeric string, never 0.
fn jdwp_port(arguments: &Value) -> Option<u16> {
let port = match arguments.get("port")? {
Value::Number(n) => n.as_u64().and_then(|p| u16::try_from(p).ok()),
Value::String(s) => s.trim().parse().ok(),
_ => None,
};
port.filter(|&p| p != 0)
}
/// `hostName` (empty when absent) and `port` of an attach request, local or not.
pub(crate) fn attach_target(arguments: &Value) -> Option<(String, u16)> {
let host = arguments.get("hostName").and_then(Value::as_str).unwrap_or_default();
Some((host.to_owned(), jdwp_port(arguments)?))
}
/// Pid of the local JVM listening on a JDWP port (first argument), given whether the session is
/// suspended (second). Replaceable so tests never send attach requests to real JVMs.
pub(crate) type JvmFinder = Arc<dyn Fn(u16, bool) -> Option<u32> + Send + Sync>;
/// The [`JvmFinder`] of the attach-time scan.
pub(crate) fn find_local_jvm(port: u16, suspended: bool) -> Option<u32> {
let may_query = |pid| !suspended || safe_while_suspended(ide_jvm_attach::java_version_of(pid).as_ref());
ide_jvm_attach::find_jvm_by_jdwp_port(port, ATTACH_SCAN_TRY, ATTACH_SCAN_TRY, may_query)
}
/// Looks for the JVM behind a local attach: one try now, the rest in the background, so a JVM
/// that never opens an attach socket holds the attach up by one try at most. Call it before the
/// debugger connects: the JVM clears its JDWP listener address then, and a scan can no longer
/// tell it by its port.
pub(crate) async fn find_attached_jvm(session: &Arc<Session>, port: u16, finder: JvmFinder) {
let _ = session.jdwp_port.set(port);
let find = move |suspended: bool| finder(port, suspended);
let first = find.clone();
if let Ok(Some(pid)) = tokio::task::spawn_blocking(move || first(false)).await {
let _ = session.jvm_pid.compare_exchange(0, i64::from(pid), Ordering::AcqRel, Ordering::Acquire);
return;
}
drop(watch_for_attached_jvm(session, port, find, ATTACH_SCAN_INTERVAL, ATTACH_SCAN_WINDOW));
}
/// Retries `find` for the session's `jvm_pid`, holding the session weakly so an ended session
/// is not kept alive. `find` is told whether the session is suspended.
pub(crate) fn watch_for_attached_jvm<F>(
session: &Arc<Session>,
port: u16,
find: F,
interval: Duration,
window: Duration,
) -> tokio::task::JoinHandle<()>
where
F: Fn(bool) -> Option<u32> + Clone + Send + 'static,
{
let weak = Arc::downgrade(session);
tokio::spawn(async move {
let gate = || match weak.upgrade() {
Some(s) if !s.terminated.load(Ordering::Acquire) && !s.conn.is_closed() => {
if s.jvm_pid.load(Ordering::Acquire) > 0 {
ScanGate::Ended
} else {
ScanGate::Scan { suspended: s.suspended.get() }
}
}
_ => ScanGate::Ended,
};
let Some(pid) = retry_find(find, gate, interval, window).await else {
tracing::debug!("no local JVM found for JDWP port {port} yet");
return;
};
if let Some(s) = weak.upgrade() {
let _ = s.jvm_pid.compare_exchange(0, i64::from(pid), Ordering::AcqRel, Ordering::Acquire);
}
})
}
#[derive(Clone, Copy, Debug, PartialEq)]
pub(crate) enum ScanGate {
Scan { suspended: bool },
Ended,
}
/// Calls `find` on a blocking thread, on each try `gate` allows, until it returns a pid, `gate`
/// reports the end or `window` has passed.
pub(crate) async fn retry_find<F>(
find: F,
gate: impl Fn() -> ScanGate,
interval: Duration,
window: Duration,
) -> Option<u32>
where
F: Fn(bool) -> Option<u32> + Clone + Send + 'static,
{
let deadline = tokio::time::Instant::now() + window;
loop {
match gate() {
ScanGate::Ended => break,
ScanGate::Scan { suspended } => {
let find = find.clone();
if let Ok(Some(pid)) = tokio::task::spawn_blocking(move || find(suspended)).await {
return Some(pid);
}
}
}
if tokio::time::Instant::now() + interval >= deadline {
break;
}
tokio::time::sleep(interval).await;
}
None
}
-214
View File
@@ -1,214 +0,0 @@
//! One class histogram of a JVM and its deltas against the previous one.
use super::scan::{RESCAN_BUDGET, RESCAN_PER_SOCKET};
use super::{
ClassCounts, HISTOGRAM_TIMEOUT, JvmClassRow, JvmMemorySnapshot, JvmMemorySource, JvmMemoryUnavailable,
safe_while_suspended,
};
use ide_core::IdeResult;
use ide_jvm_attach::{AttachError, HeapDumpReply, HistogramRow, JavaVersion};
use std::collections::HashMap;
use std::path::Path;
use std::time::Duration;
/// Version probe for a JVM whose `release` file could not be read.
const VERSION_TIMEOUT: Duration = Duration::from_secs(2);
const FLAGS_TIMEOUT: Duration = Duration::from_secs(2);
/// The attach calls a snapshot or a heap dump makes, so tests can stand in for a JVM.
pub(crate) trait AttachProbe: Send + Sync {
fn has_listener(&self, pid: u32) -> bool;
/// Asks only the JVMs whose pid `may_query` accepts.
fn find_by_jdwp_port(&self, port: u16, may_query: &dyn Fn(u32) -> bool) -> Option<u32>;
fn version(&self, pid: u32) -> Option<JavaVersion>;
fn histogram(&self, pid: u32) -> Result<String, AttachError>;
fn alive(&self, pid: u32) -> bool;
fn vm_flags(&self, pid: u32) -> Result<String, AttachError>;
fn heap_dump(&self, pid: u32, path: &Path, timeout: Duration) -> Result<HeapDumpReply, AttachError>;
/// `None` where the free space is not known.
fn free_bytes(&self, dir: &Path) -> Option<u64>;
}
pub(super) struct JdkProbe {
pub(super) suspended: bool,
}
impl AttachProbe for JdkProbe {
fn has_listener(&self, pid: u32) -> bool {
ide_jvm_attach::has_listener(pid)
}
fn find_by_jdwp_port(&self, port: u16, may_query: &dyn Fn(u32) -> bool) -> Option<u32> {
ide_jvm_attach::find_jvm_by_jdwp_port(port, RESCAN_PER_SOCKET, RESCAN_BUDGET, may_query)
}
fn version(&self, pid: u32) -> Option<JavaVersion> {
ide_jvm_attach::java_version_of(pid).or_else(|| {
// The version decides whether attaching to a suspended VM hangs it, so never
// attach to learn it while suspended.
if self.suspended {
return None;
}
let out = ide_jvm_attach::jcmd(pid, "VM.version", VERSION_TIMEOUT).ok()?;
ide_jvm_attach::parse_vm_version(&out)
})
}
fn histogram(&self, pid: u32) -> Result<String, AttachError> {
ide_jvm_attach::jcmd(pid, "GC.class_histogram -all", HISTOGRAM_TIMEOUT)
}
fn alive(&self, pid: u32) -> bool {
alive(pid)
}
fn vm_flags(&self, pid: u32) -> Result<String, AttachError> {
ide_jvm_attach::vm_flags(pid, FLAGS_TIMEOUT)
}
fn heap_dump(&self, pid: u32, path: &Path, timeout: Duration) -> Result<HeapDumpReply, AttachError> {
ide_jvm_attach::heap_dump(pid, path, timeout)
}
fn free_bytes(&self, dir: &Path) -> Option<u64> {
ide_heap::free_bytes(dir)
}
}
fn alive(pid: u32) -> bool {
#[cfg(unix)]
{
// 0 and negative pids address process groups.
let Ok(pid) = i32::try_from(pid) else { return false };
// SAFETY: signal 0 only checks that the process exists and may be signalled.
pid > 0
&& (unsafe { libc::kill(pid, 0) } == 0
|| std::io::Error::last_os_error().raw_os_error() == Some(libc::EPERM))
}
#[cfg(not(unix))]
{
let _ = pid;
false
}
}
/// Why `pid`'s attach listener cannot answer: it stopped listening or the program ended.
pub(super) fn gone(probe: &dyn AttachProbe, pid: u32) -> JvmMemoryUnavailable {
if probe.alive(pid) { JvmMemoryUnavailable::ListenerNotRunning } else { JvmMemoryUnavailable::ProgramExited }
}
/// The reason for an attach request (`what`) to `jvm` that failed, or an error where no reason
/// fits.
pub(super) fn attach_failure(
probe: &dyn AttachProbe,
jvm: u32,
error: AttachError,
what: &str,
) -> IdeResult<JvmMemoryUnavailable> {
use JvmMemoryUnavailable as U;
match error {
AttachError::Timeout => Ok(U::TimedOut),
AttachError::Refused | AttachError::NoListener => Ok(gone(probe, jvm)),
AttachError::ForeignListener => {
tracing::warn!("attach socket of JVM {jvm} is no longer private to this user; not using it");
Ok(U::ListenerNotRunning)
}
AttachError::Unsupported => Ok(U::UnsupportedPlatform),
e => Err(ide_core::IdeError::internal(format!("{what} of JVM {jvm}: {e}"))),
}
}
pub(crate) fn pick_jvm_pid(tree: &[i32], has_listener: impl Fn(u32) -> bool) -> Option<u32> {
tree.iter().filter_map(|&p| u32::try_from(p).ok()).filter(|&p| p > 0).find(|&p| has_listener(p))
}
pub(crate) fn diff_rows(rows: Vec<HistogramRow>, previous: Option<&ClassCounts>) -> (Vec<JvmClassRow>, ClassCounts) {
let mut seen: HashMap<&str, u32> = HashMap::with_capacity(rows.len());
for r in &rows {
*seen.entry(r.name.as_str()).or_default() += 1;
}
let ambiguous: Vec<bool> = rows.iter().map(|r| seen[r.name.as_str()] > 1).collect();
drop(seen);
let mut counts = ClassCounts::with_capacity(rows.len());
let mut out: Vec<JvmClassRow> = rows
.into_iter()
.zip(ambiguous)
.map(|(r, ambiguous)| {
counts.insert(r.name.clone(), (!ambiguous).then_some((r.instances, r.bytes)));
let delta = match previous {
_ if ambiguous => None,
None => None,
Some(p) => match p.get(&r.name) {
Some(None) => None,
// Absent: new since the previous snapshot, so it grew from nothing.
before => {
let (instances, bytes) = before.copied().flatten().unwrap_or_default();
Some((delta(r.instances, instances), delta(r.bytes, bytes)))
}
},
};
JvmClassRow {
name: r.name,
module: r.module,
instances: r.instances,
bytes: r.bytes,
delta_instances: delta.map(|d| d.0),
delta_bytes: delta.map(|d| d.1),
ambiguous,
}
})
.collect();
out.sort_by(|a, b| b.bytes.cmp(&a.bytes).then_with(|| a.name.cmp(&b.name)));
(out, counts)
}
/// Exact while the difference fits in an i64 (two's complement).
fn delta(now: u64, before: u64) -> i64 {
now.wrapping_sub(before) as i64
}
/// `pid_tree` starts with the session's reported pid, followed by its descendants.
pub(crate) fn take_snapshot(
probe: &dyn AttachProbe,
pid_tree: &[i32],
suspended: bool,
previous: Option<&ClassCounts>,
) -> IdeResult<Result<(JvmMemorySnapshot, ClassCounts), JvmMemoryUnavailable>> {
use JvmMemoryUnavailable as U;
let Some(root) = pid_tree.first().and_then(|&p| u32::try_from(p).ok()) else {
return Ok(Err(U::NoJvmProcess));
};
let Some(jvm) = pick_jvm_pid(pid_tree, |p| probe.has_listener(p)) else {
return Ok(Err(gone(probe, root)));
};
let version = probe.version(jvm);
if suspended && !safe_while_suspended(version.as_ref()) {
return Ok(Err(U::UnsafeWhileSuspended { java_major: version.map_or(0, |v| v.major) }));
}
let started = std::time::Instant::now();
let text = match probe.histogram(jvm) {
Ok(text) => text,
Err(e) => return attach_failure(probe, jvm, e, "class histogram").map(Err),
};
let elapsed_ms = u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX);
let histogram = ide_jvm_attach::parse_class_histogram(&text);
if histogram.skipped_lines > 0 {
tracing::debug!("class histogram of JVM {jvm}: {} unreadable lines", histogram.skipped_lines);
}
let (rows, counts) = diff_rows(histogram.rows, previous);
let snapshot = JvmMemorySnapshot {
total_instances: rows.iter().map(|r| r.instances).sum(),
total_bytes: rows.iter().map(|r| r.bytes).sum(),
rows,
java_version: version.map(|v| v.text).unwrap_or_default(),
taken_while_suspended: suspended,
has_baseline: previous.is_some(),
elapsed_ms,
source: JvmMemorySource::Histogram,
};
Ok(Ok((snapshot, counts)))
}
@@ -1,119 +0,0 @@
//! A scripted [`JvmInspector`] and a session without an adapter behind it.
use crate::SessionOwner;
use crate::adapter::{AdapterSpec, Transport};
use crate::connection::Connection;
use crate::session::Session;
use ide_core::{DebugSessionId, IdeEvent, SharedSink};
use ide_jvm_inspect::{
ClassCount, InspectError, InspectFuture, JvmField, JvmInspector, JvmReferrer, JvmValue, ObjectId, VmTarget,
};
use parking_lot::Mutex;
use std::sync::Arc;
use std::sync::atomic::{AtomicUsize, Ordering};
use tokio::sync::Notify;
#[derive(Default)]
pub(crate) struct FakeInspector {
pub targets: Mutex<Vec<VmTarget>>,
/// The `limit` of each `instances` / `referrers` call.
pub limits: Mutex<Vec<u32>>,
pub calls: AtomicUsize,
/// Returned by every call when set.
pub error: Mutex<Option<InspectError>>,
pub counts: Mutex<Vec<ClassCount>>,
pub instances: Mutex<Vec<JvmValue>>,
/// Every call signals `entered`, then waits for `release`.
pub hold: bool,
pub entered: Notify,
pub release: Notify,
}
impl FakeInspector {
pub fn failing(error: InspectError) -> Self {
Self { error: Mutex::new(Some(error)), ..Self::default() }
}
pub fn calls(&self) -> usize {
self.calls.load(Ordering::SeqCst)
}
async fn answer<T: Send>(&self, target: &VmTarget, limit: Option<u32>, ok: T) -> Result<T, InspectError> {
self.calls.fetch_add(1, Ordering::SeqCst);
self.targets.lock().push(target.clone());
self.limits.lock().extend(limit);
if self.hold {
self.entered.notify_one();
self.release.notified().await;
}
match self.error.lock().clone() {
Some(e) => Err(e),
None => Ok(ok),
}
}
}
impl JvmInspector for FakeInspector {
fn class_counts<'a>(&'a self, target: &'a VmTarget) -> InspectFuture<'a, Vec<ClassCount>> {
Box::pin(self.answer(target, None, self.counts.lock().clone()))
}
fn instances<'a>(&'a self, target: &'a VmTarget, _: &'a str, limit: u32) -> InspectFuture<'a, Vec<JvmValue>> {
Box::pin(self.answer(target, Some(limit), self.instances.lock().clone()))
}
fn fields<'a>(&'a self, target: &'a VmTarget, _: ObjectId) -> InspectFuture<'a, Vec<JvmField>> {
Box::pin(self.answer(target, None, Vec::new()))
}
fn referrers<'a>(&'a self, target: &'a VmTarget, _: ObjectId, limit: u32) -> InspectFuture<'a, Vec<JvmReferrer>> {
Box::pin(self.answer(target, Some(limit), Vec::new()))
}
}
pub(crate) struct BareSession {
pub session: Arc<Session>,
pub events: Arc<Mutex<Vec<IdeEvent>>>,
/// The adapter's end of the connection, kept open.
_adapter: tokio::io::DuplexStream,
}
/// A java-debug session that no adapter answers; must be called inside a Tokio runtime.
pub(crate) fn bare_session(request: &str) -> BareSession {
bare_session_of("java-debug", request)
}
/// A session of adapter `name` that no adapter answers; must be called inside a Tokio runtime.
pub(crate) fn bare_session_of(name: &str, request: &str) -> BareSession {
let events: Arc<Mutex<Vec<IdeEvent>>> = Arc::default();
let sink_events = events.clone();
let sink: SharedSink = Arc::new(move |e: IdeEvent| sink_events.lock().push(e));
let (client, adapter) = tokio::io::duplex(1 << 10);
let (reader, writer) = tokio::io::split(client);
let (conn, _) = Connection::start(reader, writer);
let spec = AdapterSpec {
adapter: name.into(),
command: String::new(),
args: Vec::new(),
transport: Transport::Stdio,
install_hint: None,
cwd: std::env::temp_dir(),
env: Vec::new(),
server_host: None,
connect: None,
pinned: None,
};
let session = Session::new(
DebugSessionId(1),
SessionOwner::new("test", sink),
"test".into(),
name.into(),
None,
request.into(),
conn,
spec,
None,
None,
);
BareSession { session: Arc::new(session), events, _adapter: adapter }
}
File diff suppressed because it is too large. Load diff
-7
View File
@@ -9,13 +9,6 @@ use std::{
pub const ADAPTER: &str = "kotlin-debug-adapter";
/// The adapter attaches to a JVM the IDE starts, through the JDWP link. It resumes the VM while
/// constructing its debuggee, before its breakpoint hooks exist, so the link holds resumes back
/// until the attach is done.
pub(crate) fn link_options() -> ide_jdwp::LinkOptions {
ide_jdwp::LinkOptions { hold_resumes: true }
}
pub struct SourceMirror {
dir: tempfile::TempDir,
paths: HashMap<PathBuf, PathBuf>,
+166
View File
@@ -0,0 +1,166 @@
//! Keep a suspended JVM stopped until Kotlin's adapter has installed its listeners.
//! The official 0.4.4 adapter resumes VMStart while constructing its debuggee, before
//! installing breakpoint hooks. DAP attach completes only after those hooks exist.
use ide_core::IdeResult;
use std::{io, time::Duration};
use tokio::{
io::{AsyncRead, AsyncReadExt, AsyncWrite, AsyncWriteExt},
net::{TcpListener, TcpStream},
sync::oneshot,
task::JoinHandle,
};
pub(crate) struct StartupRelay {
release: Option<oneshot::Sender<()>>,
task: JoinHandle<()>,
}
impl StartupRelay {
pub async fn start(host: String, port: u16) -> IdeResult<(Self, u16)> {
let listener = TcpListener::bind(("127.0.0.1", 0)).await?;
let local = listener.local_addr()?.port();
let (release, ready) = oneshot::channel();
let task = tokio::spawn(async move {
let connect = async {
let (adapter, _) = listener.accept().await?;
let jvm = TcpStream::connect((host.as_str(), port)).await?;
adapter.set_nodelay(true)?;
jvm.set_nodelay(true)?;
Ok::<_, io::Error>((adapter, jvm))
};
if let Ok(Ok((adapter, jvm))) = tokio::time::timeout(Duration::from_secs(60), connect).await {
let (mut ar, mut aw) = adapter.into_split();
let (mut jr, mut jw) = jvm.into_split();
let upstream = forward(&mut ar, &mut jw, ready);
let downstream = tokio::io::copy(&mut jr, &mut aw);
// Close both sockets as soon as either side disconnects.
tokio::select! {
r = upstream => if let Err(e) = r { tracing::debug!("Kotlin JDWP relay: {e}"); },
_ = downstream => {},
}
}
});
Ok((Self { release: Some(release), task }, local))
}
pub fn release(&mut self) {
if let Some(ready) = self.release.take() {
let _ = ready.send(());
}
}
}
impl Drop for StartupRelay {
fn drop(&mut self) {
self.task.abort();
}
}
async fn packet(reader: &mut (impl AsyncRead + Unpin)) -> io::Result<Vec<u8>> {
let mut header = [0; 11];
reader.read_exact(&mut header).await?;
let len = u32::from_be_bytes(header[..4].try_into().unwrap()) as usize;
if !(11..=16 * 1024 * 1024).contains(&len) {
return Err(io::Error::new(io::ErrorKind::InvalidData, "Invalid JDWP packet length"));
}
let mut packet = vec![0; len];
packet[..11].copy_from_slice(&header);
reader.read_exact(&mut packet[11..]).await?;
Ok(packet)
}
async fn forward(
reader: &mut (impl AsyncRead + Unpin),
writer: &mut (impl AsyncWrite + Unpin),
mut ready: oneshot::Receiver<()>,
) -> io::Result<()> {
let mut handshake = [0; 14];
reader.read_exact(&mut handshake).await?;
if &handshake != b"JDWP-Handshake" {
return Err(io::Error::new(io::ErrorKind::InvalidData, "Invalid JDWP handshake"));
}
writer.write_all(&handshake).await?;
let mut released = false;
let mut held: Vec<Vec<u8>> = Vec::new();
loop {
// Retain the in-flight read when attach completes, including partial packets.
let read = packet(reader);
tokio::pin!(read);
let packet = tokio::select! {
result = &mut read => result?,
result = &mut ready, if !released => {
result.map_err(|_| io::Error::new(io::ErrorKind::ConnectionAborted, "Kotlin attach cancelled"))?;
released = true;
for packet in held.drain(..) {
writer.write_all(&packet).await?;
}
read.await?
}
};
// JDWP VirtualMachine.Resume (1/9), ThreadReference.Resume (11/3).
// Other commands must proceed: attach itself queries threads and installs requests.
if !released && packet[8] == 0 && matches!((packet[9], packet[10]), (1, 9) | (11, 3)) {
if held.len() >= 1024 {
return Err(io::Error::new(io::ErrorKind::InvalidData, "Too many pending JDWP resumes"));
}
held.push(packet);
} else {
writer.write_all(&packet).await?;
}
}
}
#[cfg(test)]
mod tests {
use super::*;
fn command(id: u8, set: u8, cmd: u8) -> Vec<u8> {
vec![0, 0, 0, 11, 0, 0, 0, id, 0, set, cmd]
}
#[tokio::test]
async fn holds_resumes_but_allows_setup_and_preserves_partial_reads() {
let (mut adapter, mut reader) = tokio::io::duplex(4096);
let (mut writer, mut jvm) = tokio::io::duplex(4096);
let (release, ready) = oneshot::channel();
let task = tokio::spawn(async move { forward(&mut reader, &mut writer, ready).await });
adapter.write_all(b"JDWP-Handshake").await.unwrap();
let mut handshake = [0; 14];
jvm.read_exact(&mut handshake).await.unwrap();
assert_eq!(&handshake, b"JDWP-Handshake");
let resume = command(1, 1, 9);
let thread_resume = command(2, 11, 3);
let setup = command(3, 1, 4);
adapter.write_all(&resume).await.unwrap();
adapter.write_all(&thread_resume).await.unwrap();
adapter.write_all(&setup).await.unwrap();
assert_eq!(packet(&mut jvm).await.unwrap(), setup);
let next = command(4, 1, 9);
adapter.write_all(&next[..6]).await.unwrap();
release.send(()).unwrap();
assert_eq!(packet(&mut jvm).await.unwrap(), resume);
assert_eq!(packet(&mut jvm).await.unwrap(), thread_resume);
adapter.write_all(&next[6..]).await.unwrap();
assert_eq!(packet(&mut jvm).await.unwrap(), next);
drop(adapter);
assert!(task.await.unwrap().is_err());
}
#[tokio::test]
async fn dropping_session_closes_relay() {
let (relay, port) = StartupRelay::start("127.0.0.1".into(), 1).await.unwrap();
let mut adapter = TcpStream::connect(("127.0.0.1", port)).await.unwrap();
drop(relay);
let result = tokio::time::timeout(Duration::from_secs(1), adapter.read_u8()).await.unwrap();
assert!(result.is_err());
}
#[tokio::test]
async fn rejects_invalid_packet_lengths() {
for len in [0_u32, 10, 16 * 1024 * 1024 + 1] {
let mut bytes = command(1, 1, 9);
bytes[..4].copy_from_slice(&len.to_be_bytes());
assert_eq!(packet(&mut bytes.as_slice()).await.unwrap_err().kind(), io::ErrorKind::InvalidData);
}
}
}
+12 -129
View File
@@ -13,8 +13,8 @@ pub mod attach;
mod cargo;
pub mod connection;
pub mod jdwp;
mod jvm_memory;
pub mod kotlin;
mod kotlin_jdwp;
mod session;
use adapter::{AdapterLauncher, AdapterSpec, ProcessLauncher};
@@ -22,7 +22,6 @@ use connection::{Connection, DapError};
use futures::future::join_all;
use ide_core::{DebugSessionId, IdeError, IdeResult, SharedSink};
use ide_language::LanguageRegistry;
pub use jvm_memory::*;
use parking_lot::Mutex;
use serde::{Deserialize, Serialize};
use serde_json::{Value, json};
@@ -127,14 +126,6 @@ pub struct DebugCapabilities {
pub log_points: bool,
/// HotSwap ("Reload Changed Classes"): java-debug's `redefineClasses` request.
pub hot_code_replace: bool,
/// The session debugs a JVM, so it has a Memory view; [`DebugManager::jvm_memory_classes`]
/// says why when it has no data (platform, remote JVM, ...).
pub jvm_memory: bool,
/// The session has a JVM inspector: instances, fields and referrers while suspended. Can
/// change during the session ([`ide_core::event::DebugEvent::Capabilities`]).
pub jvm_instances: bool,
/// The session can be asked for a heap dump ([`DebugManager::jvm_heap_dump`]).
pub jvm_heap: bool,
}
/// Result of [`DebugManager::redefine_classes`].
@@ -311,7 +302,6 @@ pub struct DebugManager {
data_breakpoints: Mutex<Vec<DataBreakpoint>>,
/// In-flight stops, by session: a second Stop sets `stop_force`, the waiting one kills.
stopping: Mutex<HashMap<DebugSessionId, Arc<Session>>>,
jvm_finder: Mutex<jvm_memory::JvmFinder>,
}
/// rdbg (Ruby's debug gem) starts the debuggee itself and ignores `launch`'s program,
@@ -576,21 +566,9 @@ pub(crate) fn capabilities_from(caps: &Value) -> DebugCapabilities {
hit_conditional_breakpoints: has("supportsHitConditionalBreakpoints"),
log_points: has("supportsLogPoints"),
hot_code_replace: false,
jvm_memory: false,
jvm_instances: false,
jvm_heap: false,
}
}
pub(crate) fn session_capabilities(session: &Session) -> DebugCapabilities {
let mut caps = capabilities_from(&session.caps.lock());
caps.hot_code_replace = HOT_CODE_REPLACE_ADAPTERS.contains(&session.adapter.as_str());
caps.jvm_memory = JVM_MEMORY_ADAPTERS.contains(&session.adapter.as_str());
caps.jvm_instances = session.jvm_inspector.lock().is_some();
caps.jvm_heap = JVM_MEMORY_ADAPTERS.contains(&session.adapter.as_str());
caps
}
/// States of a file's line breakpoints that no session has been sent.
fn unsent(breakpoints: &[Breakpoint]) -> Vec<BreakpointState> {
breakpoints
@@ -679,15 +657,9 @@ impl DebugManager {
function_breakpoints: Mutex::default(),
data_breakpoints: Mutex::default(),
stopping: Mutex::default(),
jvm_finder: Mutex::new(Arc::new(jvm_memory::find_local_jvm)),
})
}
#[cfg(test)]
pub(crate) fn set_jvm_finder(&self, finder: jvm_memory::JvmFinder) {
*self.jvm_finder.lock() = finder;
}
fn session(&self, s: DebugSessionId) -> IdeResult<Arc<Session>> {
self.sessions.lock().get(&s).cloned().ok_or_else(|| no_session(s))
}
@@ -1007,31 +979,13 @@ impl DebugManager {
.await?;
*s.caps.lock() = if caps.is_object() { caps } else { json!({}) };
// The Kotlin adapters ignore the resolved classpath and project runtime on launch.
// The Kotlin adapter ignores the resolved classpath and project runtime on launch.
let request = if s.adapter == kotlin::ADAPTER && s.request == "launch" {
session::start_kotlin_debuggee(s, &mut arguments).await?;
"attach"
} else {
&s.request
};
// Both blocks below run before the Kotlin link replaces the JVM's address with its own.
if request == "attach"
&& let Some(target) = jvm_memory::attach_target(&arguments)
{
let _ = s.attach_target.set(target);
}
if cfg!(unix)
&& s.request == "attach"
&& JVM_MEMORY_ADAPTERS.contains(&s.adapter.as_str())
&& let Some(port) = jvm_memory::local_jdwp_port(&arguments)
{
if jdwp::is_listen_relay(port) {
s.listen_relay.store(true, Ordering::Release);
} else {
let finder = self.jvm_finder.lock().clone();
jvm_memory::find_attached_jvm(s, port, finder).await;
}
}
if s.adapter == kotlin::ADAPTER {
let host = arguments
.get("hostName")
@@ -1044,14 +998,11 @@ impl DebugManager {
.and_then(|p| u16::try_from(p).ok())
.filter(|p| *p != 0)
.ok_or_else(|| IdeError::invalid("Invalid Kotlin JDWP port"))?;
let (link, port) = ide_jdwp::JdwpLink::start(host, port, kotlin::link_options()).await?;
*s.jvm_inspector.lock() = Some(Arc::new(ide_jdwp::LinkInspector::new(link.clone())));
jvm_memory::watch_link(s, &link);
*s.jdwp_link.lock() = Some(link);
let (relay, port) = kotlin_jdwp::StartupRelay::start(host, port).await?;
*s.kotlin_relay.lock() = Some(relay);
arguments["hostName"] = json!("127.0.0.1");
arguments["port"] = json!(port);
}
s.jvm_located.send_replace(true);
// Launch/attach may wait for a slow runtime or a remote target. Let the adapter report
// failure; Stop cancels configuration and a closed connection fails the pending reply.
// Many adapters answer only after `configurationDone`, so don't wait for the reply yet.
@@ -1146,8 +1097,8 @@ impl DebugManager {
reply.await.unwrap_or(Err(DapError::Closed))?;
}
}
if let Some(link) = s.jdwp_link.lock().as_ref() {
link.release();
if let Some(relay) = s.kotlin_relay.lock().as_mut() {
relay.release();
}
Ok(())
}
@@ -1380,9 +1331,8 @@ impl DebugManager {
}
pub async fn threads(&self, s: DebugSessionId) -> IdeResult<Vec<ThreadInfo>> {
let session = self.session(s)?;
let body = session.conn.request_timeout("threads", Value::Null, REQUEST_TIMEOUT).await?;
let threads: Vec<ThreadInfo> = body
let body = self.session(s)?.conn.request_timeout("threads", Value::Null, REQUEST_TIMEOUT).await?;
Ok(body
.get("threads")
.and_then(Value::as_array)
.map(|t| {
@@ -1393,8 +1343,7 @@ impl DebugManager {
})
.collect()
})
.unwrap_or_default();
Ok(threads)
.unwrap_or_default())
}
pub async fn stack_trace(&self, s: DebugSessionId, thread_id: i64) -> IdeResult<Vec<StackFrame>> {
@@ -1523,11 +1472,8 @@ impl DebugManager {
pub async fn resume(&self, s: DebugSessionId, thread_id: i64) -> IdeResult<()> {
let session = self.session(s)?;
let ticket = session.suspended.ticket();
let body = session.conn.request_timeout("continue", json!({ "threadId": thread_id }), REQUEST_TIMEOUT).await?;
// DAP: a response without the flag continued every thread.
let all = body.get("allThreadsContinued").and_then(Value::as_bool).unwrap_or(true);
session.suspended.resumed(ticket, thread_id, all);
session.emit(ide_core::event::DebugEvent::Continued { thread_id, all_threads_continued: all });
Ok(())
}
@@ -1567,10 +1513,7 @@ impl DebugManager {
StepKind::Out => "stepOut",
};
let session = self.session(s)?;
let ticket = session.suspended.ticket();
session.conn.request_timeout(command, json!({ "threadId": thread_id }), REQUEST_TIMEOUT).await?;
// A step runs its thread; other threads stopped by their own events stay stopped.
session.suspended.resumed(ticket, thread_id, false);
session.emit(ide_core::event::DebugEvent::Continued { thread_id, all_threads_continued: true });
Ok(())
}
@@ -1668,12 +1611,10 @@ impl DebugManager {
/// Step into a specific call of the current line (Smart Step Into).
pub async fn step_in_target(&self, s: DebugSessionId, thread_id: i64, target_id: i64) -> IdeResult<()> {
let session = self.session(s)?;
let ticket = session.suspended.ticket();
session
.conn
.request_timeout("stepIn", json!({ "threadId": thread_id, "targetId": target_id }), REQUEST_TIMEOUT)
.await?;
session.suspended.resumed(ticket, thread_id, false);
session.emit(ide_core::event::DebugEvent::Continued { thread_id, all_threads_continued: true });
Ok(())
}
@@ -1707,68 +1648,10 @@ impl DebugManager {
}
pub fn capabilities(&self, s: DebugSessionId) -> IdeResult<DebugCapabilities> {
Ok(session_capabilities(&*self.session(s)?))
}
/// Class table of the session's JVM (`GC.class_histogram -all`, or counted by the debugger
/// while suspended where no histogram can be taken), with deltas against the session's
/// previous snapshot from the same source.
pub async fn jvm_memory_classes(&self, s: DebugSessionId) -> IdeResult<JvmMemoryResult> {
let session = self.session(s)?;
jvm_memory::session_classes(session).await
}
/// Writes a heap dump of the session's JVM to `dir/dump.hprof`, one class-table or dump
/// request per session at a time. Anything but `Ready` deletes `dir`, unless `s` is not a
/// session. On `cancel` the result is `Cancelled` at once, while a dump the JVM is writing
/// still holds the session's turn until the JVM answers.
pub async fn jvm_heap_dump(
&self,
s: DebugSessionId,
dir: PathBuf,
cancel: ide_core::CancellationToken,
) -> IdeResult<JvmHeapOutcome> {
let session = self.session(s)?;
jvm_memory::session_heap_dump(session, dir, cancel).await
}
/// Gives the session the backend for [`Self::jvm_memory_instances`] and the debugger's class
/// counts; the UI is told to reload the session's capabilities.
pub fn set_jvm_inspector(
&self,
s: DebugSessionId,
inspector: Arc<dyn ide_jvm_inspect::JvmInspector>,
) -> IdeResult<()> {
let session = self.session(s)?;
if session.ended.is_cancelled() {
return Err(no_session(s));
}
jvm_memory::set_inspector(&session, inspector);
Ok(())
}
/// Up to `limit` (clamped to `1..=MAX_INSTANCES`) instances of `class_name` while suspended.
pub async fn jvm_memory_instances(
&self,
s: DebugSessionId,
class_name: String,
limit: u32,
) -> IdeResult<JvmInstancesResult> {
jvm_memory::instances(&*self.session(s)?, &class_name, limit).await
}
pub async fn jvm_memory_fields(&self, s: DebugSessionId, object: JvmObjectRef) -> IdeResult<JvmFieldsResult> {
jvm_memory::fields(&*self.session(s)?, object).await
}
/// Objects that point at `object`; `limit` 0 means `DEFAULT_REFERRERS`, at most `MAX_REFERRERS`.
pub async fn jvm_memory_referrers(
&self,
s: DebugSessionId,
object: JvmObjectRef,
limit: u32,
) -> IdeResult<JvmReferrersResult> {
jvm_memory::referrers(&*self.session(s)?, object, limit).await
let mut caps = capabilities_from(&session.caps.lock());
caps.hot_code_replace = HOT_CODE_REPLACE_ADAPTERS.contains(&session.adapter.as_str());
Ok(caps)
}
/// HotSwap: reloads the classes compiled since the session started (or since the
+42 -315
View File
@@ -5,8 +5,6 @@ use crate::adapter::AdapterSpec;
use crate::connection::{Connection, DapError, Incoming};
use crate::{Breakpoint, BreakpointState, DataBreakpoint, DebugManager, FunctionBreakpoint, SessionOwner};
use ide_core::event::DebugEvent;
#[cfg(unix)]
use ide_core::process::process_tree;
use ide_core::{DebugSessionId, IdeEvent, TaskId};
use parking_lot::Mutex;
use serde_json::{Value, json};
@@ -64,15 +62,6 @@ pub(crate) struct Session {
pub stop_force: AtomicBool,
/// `systemProcessId` from the adapter's `process` event: the program being debugged.
pub debuggee_pid: AtomicI64,
/// The JVM an app-launched (Kotlin) session started, or the local JVM an attach session
/// found by its JDWP port. Separate from `debuggee_pid`, which decides how Stop signals the
/// program and is 0 for Kotlin.
pub jvm_pid: AtomicI64,
/// JDWP port of an attach to a local JVM, to look the JVM up again; unset for a remote one.
pub jdwp_port: std::sync::OnceLock<u16>,
/// The attach goes through the listen-mode relay of [`crate::jdwp::listen_for_jvm`].
pub listen_relay: AtomicBool,
pub suspended: Suspension,
/// Pids signalled for the current stop: the reported pid and everything it started (an
/// adapter may report the launcher shell, whose child is the program).
#[cfg_attr(not(unix), allow(dead_code))]
@@ -86,105 +75,8 @@ pub(crate) struct Session {
/// Resolved path → the path as the IDE knows it, for adapters given resolved paths.
resolved_paths: Mutex<HashMap<PathBuf, PathBuf>>,
progress: Mutex<HashMap<String, TaskId>>,
/// Relay between a Kotlin adapter and its JVM. Dropping it closes both sockets.
pub jdwp_link: parking_lot::Mutex<Option<ide_jdwp::JdwpLink>>,
pub jvm_inspector: parking_lot::Mutex<Option<Arc<dyn ide_jvm_inspect::JvmInspector>>>,
/// One inspector request per session at a time.
pub inspect_lock: tokio::sync::Mutex<()>,
/// Cancelled when the session ends, so a request still waiting on the inspector lets go of
/// it (and of the JDWP link it holds).
pub ended: ide_core::CancellationToken,
/// `hostName` (empty when absent) and `port` of the session's `attach` request, as the IDE
/// was given them: Kotlin then replaces them with the link's. Unlike `jdwp_port`, also set
/// for a remote JVM.
pub attach_target: std::sync::OnceLock<(String, u16)>,
/// Set once `configure` has recorded where the program's JVM is (the fields above, the
/// Kotlin link), just before the `launch`/`attach` request goes out.
pub jvm_located: watch::Sender<bool>,
pub kotlin_relay: Mutex<Option<crate::kotlin_jdwp::StartupRelay>>,
pub kotlin_mirror: Mutex<Option<crate::kotlin::SourceMirror>>,
pub jvm_memory: tokio::sync::Mutex<crate::JvmMemoryState>,
}
/// Which threads of the program are suspended: each from its `stopped` event until a
/// `continued` event or a successful resume/step request for it. Never cleared elsewhere, since
/// a stale "suspended" only makes a later check refuse. fwcd and java-debug stop a breakpoint's
/// thread alone, so a thread can run while another stays stopped.
///
/// A resume reply ends only the stops taken before the request was sent: a thread's next
/// `stopped` event can overtake the reply. The check and the removal happen under one lock, so
/// no stop can land between them and be lost.
#[derive(Default)]
pub(crate) struct Suspension(Mutex<Stops>);
#[derive(Default)]
struct Stops {
/// Counts stops, and moves back to an earlier stopped thread: an object read under one
/// ticket is stale under another.
ticket: u64,
/// Threads stopped alone by their event, oldest first, with the ticket of that stop.
threads: Vec<(i64, u64)>,
/// The ticket of a stop of every thread (`allThreadsStopped`, or no thread id): any resume
/// ends it.
all: Option<u64>,
}
impl Stops {
fn latest(&self) -> Option<u64> {
self.threads.last().map(|&(_, ticket)| ticket).max(self.all)
}
/// Ends the stops taken by ticket `upto` of `thread`, or of every thread.
fn release(&mut self, thread: Option<i64>, every: bool, upto: u64) {
let latest = self.latest();
if every || thread.is_none() || self.all.is_some_and(|t| t <= upto) {
self.all = self.all.filter(|&t| t > upto);
self.threads.retain(|&(_, t)| t > upto);
} else {
self.threads.retain(|&(id, t)| Some(id) != thread || t > upto);
}
// Back on an earlier thread's stop, as the JDWP link moves to it with a new generation.
let now = self.latest();
if now.is_some() && now != latest {
self.ticket += 1;
}
}
}
impl Suspension {
/// Whether some thread is stopped.
pub fn get(&self) -> bool {
let stops = self.0.lock();
stops.all.is_some() || !stops.threads.is_empty()
}
/// A `stopped` event; `all`: its `allThreadsStopped`.
pub fn stopped(&self, thread: Option<i64>, all: bool) {
let mut stops = self.0.lock();
stops.ticket += 1;
let ticket = stops.ticket;
match thread.filter(|_| !all) {
Some(thread) => {
stops.threads.retain(|&(id, _)| id != thread);
stops.threads.push((thread, ticket));
}
None => stops.all = Some(ticket),
}
}
/// A `continued` event; `all`: its `allThreadsContinued`.
pub fn continued(&self, thread: Option<i64>, all: bool) {
self.0.lock().release(thread, all, u64::MAX);
}
/// Take before sending a resume-like request and pass to [`Self::resumed`].
pub fn ticket(&self) -> u64 {
self.0.lock().ticket
}
/// After a successful resume-like request for `thread`; `all`: every thread ran.
pub fn resumed(&self, ticket: u64, thread: i64, all: bool) {
self.0.lock().release(Some(thread), all, ticket);
}
}
/// Adapters that only match files by their resolved path: Godot maps a script to
@@ -233,10 +125,6 @@ impl Session {
terminated: AtomicBool::new(false),
stop_force: AtomicBool::new(false),
debuggee_pid: AtomicI64::new(0),
jvm_pid: AtomicI64::new(0),
jdwp_port: std::sync::OnceLock::new(),
listen_relay: AtomicBool::new(false),
suspended: Suspension::default(),
stop_pids: parking_lot::Mutex::new(Vec::new()),
#[cfg(windows)]
stop_tree: Mutex::new(None),
@@ -244,14 +132,8 @@ impl Session {
breakpoint_ids: Mutex::new(HashMap::new()),
resolved_paths: Mutex::new(HashMap::new()),
progress: Mutex::new(HashMap::new()),
jdwp_link: parking_lot::Mutex::new(None),
jvm_inspector: parking_lot::Mutex::new(None),
inspect_lock: tokio::sync::Mutex::default(),
ended: ide_core::CancellationToken::new(),
attach_target: std::sync::OnceLock::new(),
jvm_located: watch::channel(false).0,
kotlin_relay: Mutex::new(None),
kotlin_mirror: Mutex::new(None),
jvm_memory: tokio::sync::Mutex::default(),
}
}
@@ -412,10 +294,7 @@ impl Session {
/// Kills the adapter and every debuggee we started.
pub fn kill_processes(&self) {
self.ended.cancel();
// The inspector holds a clone of the link, so both go.
self.jvm_inspector.lock().take();
self.jdwp_link.lock().take();
self.kotlin_relay.lock().take();
#[cfg(unix)]
if self.request == "launch" {
for group in launch_groups(self) {
@@ -472,6 +351,32 @@ pub(crate) async fn remember_debuggee(s: &Arc<Session>) {
let _ = s;
}
/// The program and everything it started: an adapter may report the launcher shell, whose
/// child is the debugged program, so stopping only the reported pid leaves the program alive.
#[cfg(unix)]
fn process_tree(pid: i32) -> Vec<i32> {
use std::collections::HashMap;
let Ok(out) = std::process::Command::new("ps").args(["-A", "-o", "pid=,ppid="]).output() else {
return vec![pid];
};
let mut children: HashMap<i32, Vec<i32>> = HashMap::new();
for line in String::from_utf8_lossy(&out.stdout).lines() {
let mut it = line.split_whitespace();
let (Some(p), Some(parent)) = (it.next(), it.next()) else { continue };
let (Ok(p), Ok(parent)) = (p.parse::<i32>(), parent.parse::<i32>()) else { continue };
children.entry(parent).or_default().push(p);
}
let mut tree = vec![pid];
let mut at = 0;
while at < tree.len() {
if let Some(kids) = children.get(&tree[at]) {
tree.extend(kids.iter().copied());
}
at += 1;
}
tree
}
/// Asks the program itself to exit (`force` = SIGKILL) without ending the adapter session:
/// its output keeps flowing over DAP while it shuts down. The first call remembers the pid
/// tree, because the reported pid may die before its program does.
@@ -695,27 +600,18 @@ async fn on_event(mgr: &Arc<DebugManager>, s: &Arc<Session>, event: &str, mut bo
s.emit(DebugEvent::Initialized);
}
"stopped" => {
let all = body.get("allThreadsStopped").and_then(Value::as_bool).unwrap_or(false);
s.suspended.stopped(int("threadId"), all);
let reason = str_("reason").unwrap_or_else(|| "pause".into());
mgr.restore_breakpoints(s).await;
s.emit(DebugEvent::Stopped {
thread_id: int("threadId").unwrap_or(0),
reason,
reason: str_("reason").unwrap_or_else(|| "pause".into()),
description: str_("description").or_else(|| str_("text")),
all_threads_stopped: all,
});
}
"continued" => {
let all = body.get("allThreadsContinued").and_then(Value::as_bool);
// DAP: an event without the flag continues its thread alone. The UI keeps treating
// it as all threads; the suspension, which holds only threads that stopped, need not.
s.suspended.continued(int("threadId"), all.unwrap_or(false));
s.emit(DebugEvent::Continued {
thread_id: int("threadId").unwrap_or(0),
all_threads_continued: all.unwrap_or(true),
all_threads_stopped: body.get("allThreadsStopped").and_then(Value::as_bool).unwrap_or(false),
});
}
"continued" => s.emit(DebugEvent::Continued {
thread_id: int("threadId").unwrap_or(0),
all_threads_continued: body.get("allThreadsContinued").and_then(Value::as_bool).unwrap_or(true),
}),
"output" => {
let category = str_("category").unwrap_or_else(|| "console".into());
if category == "telemetry" {
@@ -1021,19 +917,6 @@ fn forward_output<R: AsyncRead + Unpin + Send + 'static>(s: &Session, mut stream
});
}
/// The attach listener must be on the command line before the user's arguments, which may
/// override it; the memory view needs it because the JVM is started by the IDE, not attached to.
/// Not on Windows (`windows`), which the memory view does not support.
fn kotlin_jvm_args(user: Vec<String>, windows: bool) -> Vec<String> {
if windows || !ide_jvm_attach::wants_listener_flag(&user.join(" ")) {
return user;
}
let mut args = Vec::with_capacity(user.len() + 1);
args.push(ide_jvm_attach::START_LISTENER_FLAG.to_owned());
args.extend(user);
args
}
/// Launch with the IDE's resolved runtime and classpath; the adapter only attaches.
pub(crate) async fn start_kotlin_debuggee(s: &Arc<Session>, args: &mut Value) -> ide_core::IdeResult<()> {
use tokio::io::{AsyncBufReadExt, BufReader};
@@ -1048,7 +931,7 @@ pub(crate) async fn start_kotlin_debuggee(s: &Arc<Session>, args: &mut Value) ->
std::env::join_paths(strings("classPaths")).map_err(|e| ide_core::IdeError::invalid(e.to_string()))?;
let mut cmd = tokio::process::Command::new(java);
ide_core::process::prepare(cmd.as_std_mut());
cmd.args(kotlin_jvm_args(strings("vmArguments"), cfg!(windows)))
cmd.args(strings("vmArguments"))
// Let the JVM pick its own port (`:0`) and report it below: pre-picking a free
// port here races with other processes that may take it before the JVM binds.
.arg("-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=127.0.0.1:0")
@@ -1082,12 +965,11 @@ pub(crate) async fn start_kotlin_debuggee(s: &Arc<Session>, args: &mut Value) ->
// forced stop), the session's job on Windows, so a stop reaches what it forks.
ide_core::process::own_group(cmd.as_std_mut());
let mut child = cmd.spawn()?;
if let Some(pid) = child.id() {
s.jvm_pid.store(i64::from(pid), Ordering::Release);
#[cfg(windows)]
if let Some(job) = s.job.lock().as_ref() {
job.assign_pid(pid);
}
#[cfg(windows)]
if let Some(pid) = child.id()
&& let Some(job) = s.job.lock().as_ref()
{
job.assign_pid(pid);
}
if let Some(err) = child.stderr.take() {
forward_output(s, err, "stderr");
@@ -1128,162 +1010,7 @@ fn parse_jdwp_port(line: &str) -> Option<u16> {
#[cfg(test)]
mod tests {
use super::{Suspension, kotlin_jvm_args, parse_jdwp_port};
#[test]
fn a_resume_reply_clears_the_stop_it_was_sent_for() {
let s = Suspension::default();
assert!(!s.get());
s.stopped(Some(1), true);
let ticket = s.ticket();
s.resumed(ticket, 1, true);
assert!(!s.get());
}
#[test]
fn a_stop_after_the_resume_request_keeps_the_session_suspended() {
let s = Suspension::default();
s.stopped(Some(1), true);
let ticket = s.ticket();
// The next breakpoint's `stopped` event overtakes the reply to `continue`.
s.continued(Some(1), true);
s.stopped(Some(1), true);
s.resumed(ticket, 1, true);
assert!(s.get());
// A reply for the new stop still clears it.
s.resumed(s.ticket(), 1, true);
assert!(!s.get());
}
#[test]
fn a_reply_after_a_continued_event_changes_nothing() {
let s = Suspension::default();
s.stopped(Some(1), true);
let ticket = s.ticket();
s.continued(Some(1), true);
s.resumed(ticket, 1, true);
assert!(!s.get());
s.stopped(Some(1), true);
assert!(s.get());
}
#[test]
fn concurrent_stops_are_never_lost() {
let s = std::sync::Arc::new(Suspension::default());
s.stopped(Some(1), true);
let ticket = s.ticket();
let stopping = {
let s = s.clone();
std::thread::spawn(move || (0..10_000).for_each(|_| s.stopped(Some(1), true)))
};
for _ in 0..10_000 {
s.resumed(ticket, 1, true);
}
stopping.join().unwrap();
// However they interleave, a resume for the old ticket never clears a later stop.
assert!(s.get());
assert_eq!(s.ticket(), ticket + 10_000);
}
/// fwcd and java-debug stop a breakpoint's thread alone (`SUSPEND_EVENT_THREAD`): 7, then 8.
fn two_threads_stopped() -> Suspension {
let s = Suspension::default();
s.stopped(Some(7), false);
s.stopped(Some(8), false);
s
}
#[test]
fn continuing_the_latest_stopped_thread_keeps_the_other_as_a_new_stop() {
let s = two_threads_stopped();
let ticket = s.ticket();
s.continued(Some(8), false);
assert!(s.get());
// Objects read on thread 8's stop are stale.
assert_eq!(s.ticket(), ticket + 1);
s.continued(Some(7), false);
assert!(!s.get());
}
#[test]
fn continuing_an_earlier_stopped_thread_keeps_the_latest_stop() {
let s = two_threads_stopped();
let ticket = s.ticket();
s.continued(Some(7), false);
assert!(s.get());
assert_eq!(s.ticket(), ticket);
}
#[test]
fn continuing_all_threads_ends_every_stop() {
let s = two_threads_stopped();
s.continued(Some(7), true);
assert!(!s.get());
let s = two_threads_stopped();
s.continued(None, false);
assert!(!s.get());
}
#[test]
fn continuing_a_thread_that_did_not_stop_changes_nothing() {
let s = two_threads_stopped();
let ticket = s.ticket();
s.continued(Some(5), false);
assert!(s.get());
assert_eq!(s.ticket(), ticket);
}
#[test]
fn a_step_reply_resumes_its_thread_alone() {
let s = two_threads_stopped();
let ticket = s.ticket();
s.resumed(ticket, 8, false);
assert!(s.get());
assert_eq!(s.ticket(), ticket + 1);
s.resumed(s.ticket(), 7, true);
assert!(!s.get());
}
#[test]
fn a_thread_stopping_again_before_its_resume_reply_stays_stopped() {
let s = two_threads_stopped();
let ticket = s.ticket();
// Thread 7's step ends, and its `stopped` event overtakes the reply to `next`.
s.stopped(Some(7), false);
s.resumed(ticket, 7, false);
s.continued(Some(8), false);
assert!(s.get());
}
#[test]
fn a_stop_of_every_thread_ends_with_any_resume() {
let s = Suspension::default();
s.stopped(Some(7), false);
s.stopped(Some(8), true);
s.continued(Some(8), false);
assert!(!s.get());
// A stop without a thread.
s.stopped(None, false);
s.resumed(s.ticket(), 5, false);
assert!(!s.get());
}
#[test]
fn kotlin_launch_starts_attach_listener_first() {
assert_eq!(
kotlin_jvm_args(vec!["-Xmx1g".into()], false),
vec!["-XX:+StartAttachListener".to_string(), "-Xmx1g".into()]
);
assert_eq!(
kotlin_jvm_args(vec!["-XX:+DisableAttachMechanism".into()], false),
vec!["-XX:+DisableAttachMechanism".to_string()]
);
}
#[test]
fn kotlin_launch_on_windows_gets_no_attach_listener() {
assert_eq!(kotlin_jvm_args(vec!["-Xmx1g".into()], true), vec!["-Xmx1g".to_string()]);
}
use super::parse_jdwp_port;
#[test]
fn reads_the_port_the_jvm_chose() {
+17 -471
View File
@@ -1,7 +1,5 @@
//! Protocol flow against an in-memory fake adapter.
mod jvm_inspect;
use super::*;
use crate::adapter::{AdapterIo, LaunchFuture};
use ide_core::IdeEvent;
@@ -122,14 +120,6 @@ struct Script {
supports_terminate: bool,
/// Answer `setBreakpoints` only once this many are waiting (a client that waits for each never gets one).
hold_set_breakpoints: usize,
/// Send a `continued` event right after the first `stopped` one.
continued_after_stop: bool,
/// Close the connection when a `pause` request arrives (the adapter dies).
hang_up_on_pause: bool,
/// Answer `continue` with this body and keep the program running, instead of letting it exit.
continue_reply: Option<Value>,
/// Answer `initialize` only after this long (a slow adapter keeps the session connecting).
delay_initialize: Option<Duration>,
initialized_delay: Duration,
launch_delay: Duration,
/// Leave startup pending before `initialized` (false) or after configuration (true).
@@ -154,10 +144,6 @@ impl Default for Script {
output_after_terminate: false,
supports_terminate: true,
hold_set_breakpoints: 0,
continued_after_stop: false,
hang_up_on_pause: false,
continue_reply: None,
delay_initialize: None,
initialized_delay: Duration::ZERO,
launch_delay: Duration::ZERO,
pending_startup: None,
@@ -224,9 +210,6 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
}
match msg["command"].as_str().unwrap_or_default() {
"initialize" => {
if let Some(delay) = script.delay_initialize {
tokio::time::sleep(delay).await;
}
ok!(
msg,
json!({
@@ -358,9 +341,6 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
send!(
json!({"type": "event", "event": "stopped", "body": {"reason": "breakpoint", "threadId": 1, "allThreadsStopped": true}})
);
if script.continued_after_stop {
send!(json!({"type": "event", "event": "continued", "body": {"threadId": 1}}));
}
send!(
json!({"type": "event", "event": "breakpoint", "body": {"reason": "changed", "breakpoint": {"id": 1, "verified": false, "message": "moved", "line": 9, "source": {"path": script.source_path}}}})
);
@@ -392,13 +372,11 @@ async fn fake_adapter<S: AsyncRead + AsyncWrite + Unpin + Send + 'static>(stream
{"label": ""},
]})
),
"continue" if script.continue_reply.is_some() => ok!(msg, script.continue_reply.clone().unwrap()),
"continue" => {
ok!(msg, json!({"allThreadsContinued": true}));
send!(json!({"type": "event", "event": "exited", "body": {"exitCode": 3}}));
send!(json!({"type": "event", "event": "terminated"}));
}
"pause" if script.hang_up_on_pause => break,
"stepIn" | "stepOut" | "pause" => ok!(msg, Value::Null),
"redefineClasses" => {
send!(
@@ -452,8 +430,6 @@ fn harness(script: Script) -> Harness {
Arc::new(LanguageRegistry::from_configs(Vec::new())),
Arc::new(FakeLauncher { log: log.clone(), script }),
);
// A local attach must not send requests to the developer's own JVMs.
manager.set_jvm_finder(Arc::new(|_, _| None));
Harness { manager, log, events, owner }
}
@@ -1376,36 +1352,6 @@ async fn hot_swap_only_for_java_debug() {
assert_eq!(failed.error_message.as_deref(), Some("boom"));
}
/// A loopback port nothing listens on until `listen` is called on the socket, and that no parallel
/// test can bind meanwhile. A port picked by binding to 0 and closing the listener can be taken
/// by another test before the code under test connects to it.
fn reserved_port() -> (tokio::net::TcpSocket, u16) {
// Without SO_REUSEADDR, which every `TcpListener::bind` sets: no other socket may bind it.
let socket = tokio::net::TcpSocket::new_v4().unwrap();
socket.bind(([127, 0, 0, 1], 0).into()).unwrap();
let port = socket.local_addr().unwrap().port();
(socket, port)
}
/// An editor that starts listening on the reserved port after `delay` and serves one session.
#[cfg(unix)]
fn fake_editor(socket: tokio::net::TcpSocket, delay: Duration, log: Log) {
tokio::spawn(async move {
tokio::time::sleep(delay).await;
let listener = socket.listen(1).unwrap();
let (stream, _) = listener.accept().await.unwrap();
// Closed once its session is accepted, so a later start finds no editor open.
drop(listener);
fake_adapter(stream, log, Script::default()).await;
});
}
#[tokio::test]
async fn a_reserved_port_cannot_be_taken_by_a_parallel_test() {
let (_socket, port) = reserved_port();
assert!(tokio::net::TcpListener::bind(("127.0.0.1", port)).await.is_err(), "port {port} is still free to bind");
}
fn godot_registry(port: u16, command: &str, args: &[&str]) -> Arc<LanguageRegistry> {
let lang = ide_language::LanguageConfig {
id: ide_core::LanguageId::new("gdscript"),
@@ -1473,7 +1419,7 @@ async fn godot_connects_to_the_editor_adapter() {
#[tokio::test]
async fn godot_without_editor_or_executable_says_what_to_do() {
let (_no_editor, port) = reserved_port();
let port = std::net::TcpListener::bind(("127.0.0.1", 0)).unwrap().local_addr().unwrap().port();
let (owner, _events) = recording_owner("main");
let manager = DebugManager::new(godot_registry(port, "openidea-no-such-godot", &[]));
let err = manager.start(godot_launch(&std::env::temp_dir()), owner).await.unwrap_err();
@@ -1486,9 +1432,15 @@ async fn godot_without_editor_or_executable_says_what_to_do() {
#[cfg(unix)]
#[tokio::test]
async fn godot_starts_a_headless_editor_when_none_is_open() {
let (editor, port) = reserved_port();
let port = std::net::TcpListener::bind(("127.0.0.1", 0)).unwrap().local_addr().unwrap().port();
let log: Log = Arc::default();
fake_editor(editor, Duration::from_millis(300), log.clone());
let server_log = log.clone();
tokio::spawn(async move {
tokio::time::sleep(std::time::Duration::from_millis(300)).await;
let listener = tokio::net::TcpListener::bind(("127.0.0.1", port)).await.unwrap();
let (stream, _) = listener.accept().await.unwrap();
fake_adapter(stream, server_log, Script::default()).await;
});
let (owner, _events) = recording_owner("main");
// `sleep` stands in for `godot --headless --editor --path ${root} …`.
let manager = DebugManager::new(godot_registry(port, "sleep", &["30"]));
@@ -1691,7 +1643,7 @@ async fn a_plugin_language_runs_its_debug_adapter_from_the_approved_program() {
std::fs::write(&program, "#!/bin/sh\nexec sleep 30\n").unwrap();
std::fs::set_permissions(&program, std::fs::Permissions::from_mode(0o755)).unwrap();
let (editor, port) = reserved_port();
let port = std::net::TcpListener::bind(("127.0.0.1", 0)).unwrap().local_addr().unwrap().port();
let mut gdscript = parse_definition(include_str!("../../../languages/gdscript.toml")).unwrap();
let debugger = gdscript.debugger.as_mut().unwrap();
debugger.args.clear();
@@ -1708,7 +1660,13 @@ async fn a_plugin_language_runs_its_debug_adapter_from_the_approved_program() {
let _language = store.add("acme.godot".into(), gdscript);
let log: Log = Arc::default();
fake_editor(editor, Duration::from_millis(300), log.clone());
let server_log = log.clone();
tokio::spawn(async move {
tokio::time::sleep(std::time::Duration::from_millis(300)).await;
let listener = tokio::net::TcpListener::bind(("127.0.0.1", port)).await.unwrap();
let (stream, _) = listener.accept().await.unwrap();
fake_adapter(stream, server_log, Script::default()).await;
});
let (owner, _events) = recording_owner("main");
let manager = DebugManager::new(registry.clone());
let id = manager.start(godot_launch(&dir), owner).await.unwrap();
@@ -2060,418 +2018,6 @@ fn delve_leftovers_are_removed_without_touching_other_files() {
std::fs::remove_dir_all(&dir).unwrap();
}
fn is_suspended(h: &Harness, id: DebugSessionId) -> bool {
h.manager.session(id).unwrap().suspended.get()
}
#[tokio::test]
async fn stopped_event_marks_session_suspended() {
let h = harness(Script::default());
let id = h.start(config()).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
assert!(is_suspended(&h, id));
}
#[tokio::test]
async fn resume_clears_suspended_without_continued_event() {
let h = harness(Script::default());
let id = h.start(config()).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
// The fake adapter ends the session after `continue`, so keep the session alive here.
let session = h.manager.session(id).unwrap();
assert!(session.suspended.get());
h.manager.resume(id, 1).await.unwrap();
assert!(!session.suspended.get());
}
/// After the fake adapter's stop of every thread ends, threads 7 then 8 stop alone, as a
/// breakpoint does on fwcd and java-debug (`SUSPEND_EVENT_THREAD`).
async fn threads_stopped(script: Script) -> (Harness, Arc<Session>, DebugSessionId) {
let h = harness(script);
let id = h.start(config()).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
let session = h.manager.session(id).unwrap();
session.suspended.continued(Some(1), true);
session.suspended.stopped(Some(7), false);
session.suspended.stopped(Some(8), false);
(h, session, id)
}
#[tokio::test]
async fn resume_of_one_thread_keeps_the_others_suspended() {
let only_it = Script { continue_reply: Some(json!({"allThreadsContinued": false})), ..Script::default() };
let (h, session, id) = threads_stopped(only_it).await;
h.manager.resume(id, 7).await.unwrap();
assert!(session.suspended.get());
h.manager.resume(id, 8).await.unwrap();
assert!(!session.suspended.get());
}
#[tokio::test]
async fn resume_reply_without_the_flag_continues_every_thread() {
let (h, session, id) = threads_stopped(Script { continue_reply: Some(json!({})), ..Script::default() }).await;
h.manager.resume(id, 7).await.unwrap();
assert!(!session.suspended.get());
}
#[tokio::test]
async fn step_of_one_thread_keeps_the_others_suspended() {
let (h, session, id) = threads_stopped(Script::default()).await;
let ticket = session.suspended.ticket();
h.manager.step(id, 8, StepKind::Into).await.unwrap();
assert!(session.suspended.get());
// Thread 8 was the latest stop: what was read on it is stale.
assert_eq!(session.suspended.ticket(), ticket + 1);
h.manager.step_in_target(id, 7, 1).await.unwrap();
assert!(!session.suspended.get());
}
#[tokio::test]
async fn continued_event_clears_suspended() {
let h = harness(Script { continued_after_stop: true, ..Script::default() });
let id = h.start(config()).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Continued { .. })).await;
assert!(!is_suspended(&h, id));
}
fn java_config(request: &str) -> LaunchConfig {
LaunchConfig { adapter: "java-debug".into(), request: request.into(), extra_json: None, ..config() }
}
fn remote_attach(adapter: &str, project: &std::path::Path) -> LaunchConfig {
LaunchConfig {
adapter: adapter.into(),
cwd: Some(project.to_owned().into()),
extra_json: Some(json!({"projectRoot": project, "hostName": "10.0.0.5", "port": 5005}).to_string()),
..java_config("attach")
}
}
#[tokio::test]
async fn attach_session_reports_capability() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
for adapter in ["java-debug", kotlin::ADAPTER] {
let id = h.start(remote_attach(adapter, project.path())).await.unwrap();
let caps = h.manager.capabilities(id).unwrap();
assert!(caps.jvm_memory, "{adapter}");
assert_eq!(caps.jvm_heap, caps.jvm_memory, "{adapter}");
}
let id = h.start(config()).await.unwrap();
let caps = h.manager.capabilities(id).unwrap();
assert!(!caps.jvm_memory);
assert_eq!(caps.jvm_heap, caps.jvm_memory);
assert_eq!(
h.manager.jvm_memory_classes(id).await.unwrap(),
JvmMemoryResult::Unavailable { reason: JvmMemoryUnavailable::NoJvmProcess, can_count_when_paused: false }
);
}
#[cfg(unix)]
#[tokio::test]
async fn ended_attach_session_without_pid_reports_program_exited() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let id = h.start(remote_attach("java-debug", project.path())).await.unwrap();
h.manager.session(id).unwrap().terminated.store(true, Ordering::Release);
assert_eq!(
h.manager.jvm_memory_classes(id).await.unwrap(),
JvmMemoryResult::Unavailable { reason: JvmMemoryUnavailable::ProgramExited, can_count_when_paused: false }
);
}
#[cfg(unix)]
#[tokio::test]
async fn listen_mode_attach_is_not_scanned() {
let h = harness(Script::default());
let scans = Arc::new(Mutex::new(Vec::new()));
let counted = scans.clone();
h.manager.set_jvm_finder(Arc::new(move |port, _| {
counted.lock().push(port);
None
}));
let (_jvm, relay) = jdwp::tests::connected_jvm().await;
let mut cfg = java_config("attach");
cfg.extra_json = Some(json!({"hostName": "127.0.0.1", "port": relay}).to_string());
let id = h.start(cfg).await.unwrap();
assert_eq!(
h.manager.jvm_memory_classes(id).await.unwrap(),
JvmMemoryResult::Unavailable {
reason: JvmMemoryUnavailable::ListenModeNotSupported,
can_count_when_paused: false
}
);
tokio::time::sleep(Duration::from_millis(50)).await;
assert!(scans.lock().is_empty());
}
#[cfg(unix)]
#[tokio::test]
async fn remote_host_is_not_scanned() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let id = h.start(remote_attach("java-debug", project.path())).await.unwrap();
let session = h.manager.session(id).unwrap();
assert_eq!(session.jdwp_port.get(), None);
assert_eq!(
h.manager.jvm_memory_classes(id).await.unwrap(),
JvmMemoryResult::Unavailable {
reason: JvmMemoryUnavailable::AttachedJvmNotFound,
can_count_when_paused: false
}
);
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 0);
}
/// The Memory view asks as soon as the session appears, while its JVM is still being looked up:
/// answering then would claim there is no JVM to ask.
#[cfg(unix)]
#[tokio::test]
async fn memory_asked_while_an_attach_connects_waits_for_its_jvm() {
let h = harness(Script { delay_initialize: Some(Duration::from_millis(300)), ..Script::default() });
let project = tempfile::tempdir().unwrap();
let (manager, owner) = (h.manager.clone(), h.owner.clone());
let config = remote_attach("java-debug", project.path());
let start = tokio::spawn(async move { manager.start(config, owner).await });
h.wait_event(|e| matches!(e, DebugEvent::Started { .. })).await;
let id = DebugSessionId(*event_sessions(&h.events).first().unwrap());
let session = h.manager.session(id).unwrap();
assert!(session.attach_target.get().is_none(), "asked too late to cover the connecting session");
h.manager.jvm_memory_classes(id).await.unwrap();
assert!(session.attach_target.get().is_some(), "answered before the attach was looked at");
start.await.unwrap().unwrap();
}
/// A JVM clears its JDWP listener address once a debugger connects, so only a scan made before
/// the `attach` request can tell it by its port.
#[cfg(unix)]
#[tokio::test]
async fn local_attach_finds_its_jvm_before_the_debugger_connects() {
let h = harness(Script::default());
let log = h.log.clone();
h.manager.set_jvm_finder(Arc::new(move |port, _| {
std::thread::sleep(Duration::from_millis(50));
let attached = log.lock().iter().any(|m| m["command"] == "attach");
(port == 5005 && !attached).then_some(4242)
}));
let mut cfg = java_config("attach");
cfg.extra_json = Some(json!({"hostName": "127.0.0.1", "port": 5005}).to_string());
let id = h.start(cfg).await.unwrap();
let session = h.manager.session(id).unwrap();
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 4242);
}
#[cfg(unix)]
#[tokio::test]
async fn local_attach_remembers_its_jdwp_port() {
let h = harness(Script::default());
let ports = Arc::new(Mutex::new(Vec::new()));
let asked = ports.clone();
h.manager.set_jvm_finder(Arc::new(move |port, _| {
asked.lock().push(port);
Some(4242)
}));
let mut cfg = java_config("attach");
cfg.extra_json = Some(json!({"hostName": "localhost", "port": "5005"}).to_string());
let id = h.start(cfg).await.unwrap();
let session = h.manager.session(id).unwrap();
assert_eq!(session.jdwp_port.get(), Some(&5005));
assert_eq!(h.request("attach")["arguments"]["port"], "5005");
for _ in 0..200 {
if session.jvm_pid.load(Ordering::Acquire) != 0 {
break;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 4242);
assert_eq!(ports.lock().first(), Some(&5005));
}
/// A fake `find_jvm_by_jdwp_port` for the JVM 4242, recording whether each scan ran while
/// suspended. A JVM not `safe_while_suspended` (JDK below 17) is skipped by a suspended scan.
#[cfg(unix)]
fn counting_find(
safe_while_suspended: bool,
) -> (Arc<Mutex<Vec<bool>>>, impl Fn(bool) -> Option<u32> + Clone + Send + 'static) {
let scans = Arc::new(Mutex::new(Vec::new()));
let counted = scans.clone();
(scans, move |suspended| {
counted.lock().push(suspended);
(!suspended || safe_while_suspended).then_some(4242)
})
}
#[cfg(unix)]
async fn suspended_remote_attach(h: &Harness) -> Arc<Session> {
let project = tempfile::tempdir().unwrap();
let id = h.start(remote_attach("java-debug", project.path())).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
let session = h.manager.session(id).unwrap();
assert!(session.suspended.get());
session
}
#[cfg(unix)]
#[tokio::test]
async fn background_scan_skips_an_old_jdk_while_suspended() {
let h = harness(Script::default());
let session = suspended_remote_attach(&h).await;
let (scans, find) = counting_find(false);
let task =
jvm_memory::watch_for_attached_jvm(&session, 5005, find, Duration::from_millis(5), Duration::from_secs(5));
tokio::time::sleep(Duration::from_millis(100)).await;
assert!(!scans.lock().is_empty() && scans.lock().iter().all(|&suspended| suspended));
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 0);
session.suspended.continued(None, true);
tokio::time::timeout(Duration::from_secs(2), task).await.unwrap().unwrap();
assert_eq!(scans.lock().last(), Some(&false));
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 4242);
}
#[cfg(unix)]
#[tokio::test]
async fn background_scan_finds_a_jdk_17_or_later_while_suspended() {
let h = harness(Script::default());
let session = suspended_remote_attach(&h).await;
let (scans, find) = counting_find(true);
let task =
jvm_memory::watch_for_attached_jvm(&session, 5005, find, Duration::from_millis(5), Duration::from_secs(5));
tokio::time::timeout(Duration::from_secs(2), task).await.unwrap().unwrap();
assert_eq!(*scans.lock(), [true]);
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 4242);
}
#[cfg(unix)]
#[tokio::test]
async fn background_scan_keeps_a_known_pid_and_stops_with_the_session() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let id = h.start(remote_attach("java-debug", project.path())).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
let session = h.manager.session(id).unwrap();
session.suspended.continued(None, true);
session.jvm_pid.store(7, Ordering::Release);
let watch = |find| {
jvm_memory::watch_for_attached_jvm(&session, 5005, find, Duration::from_millis(5), Duration::from_secs(5))
};
let (scans, find) = counting_find(true);
tokio::time::timeout(Duration::from_secs(2), watch(find)).await.unwrap().unwrap();
assert!(scans.lock().is_empty(), "a known pid needs no scan");
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 7);
// A refresh stores the pid while this scan is still running.
session.jvm_pid.store(0, Ordering::Release);
let racing = session.clone();
let find = move |_| {
racing.jvm_pid.store(7, Ordering::Release);
Some(4242)
};
let task =
jvm_memory::watch_for_attached_jvm(&session, 5005, find, Duration::from_millis(5), Duration::from_secs(5));
tokio::time::timeout(Duration::from_secs(2), task).await.unwrap().unwrap();
assert_eq!(session.jvm_pid.load(Ordering::Acquire), 7, "a pid stored first is kept");
h.manager.stop(id).await.unwrap();
let (scans, find) = counting_find(true);
tokio::time::timeout(Duration::from_secs(2), watch(find)).await.unwrap().unwrap();
assert!(scans.lock().is_empty());
}
#[cfg(unix)]
#[tokio::test]
async fn unknown_pid_reports_no_jvm_process() {
let h = harness(Script::default());
let id = h.start(java_config("launch")).await.unwrap();
assert!(h.manager.capabilities(id).unwrap().jvm_memory);
assert_eq!(
h.manager.jvm_memory_classes(id).await.unwrap(),
JvmMemoryResult::Unavailable { reason: JvmMemoryUnavailable::NoJvmProcess, can_count_when_paused: false }
);
}
fn kotlin_attach(project: &std::path::Path, host: &str, port: u16) -> LaunchConfig {
LaunchConfig {
adapter: kotlin::ADAPTER.into(),
cwd: Some(project.to_owned().into()),
extra_json: Some(json!({"projectRoot": project, "hostName": host, "port": port}).to_string()),
..java_config("attach")
}
}
#[tokio::test]
async fn kotlin_session_installs_link_inspector() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let id = h.start(kotlin_attach(project.path(), "127.0.0.1", 5005)).await.unwrap();
let session = h.manager.session(id).unwrap();
assert!(session.jdwp_link.lock().is_some());
assert!(session.jvm_inspector.lock().is_some());
}
#[tokio::test]
async fn attach_target_recorded_before_kotlin_rewrite() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let id = h.start(kotlin_attach(project.path(), "10.0.0.5", 5005)).await.unwrap();
let session = h.manager.session(id).unwrap();
assert_eq!(session.attach_target.get(), Some(&("10.0.0.5".to_owned(), 5005)));
let sent = &h.request("attach")["arguments"];
assert_eq!(sent["hostName"], "127.0.0.1");
let link_port = sent["port"].as_u64().unwrap();
assert!(link_port != 0 && link_port != 5005);
}
#[tokio::test]
async fn java_attach_records_target() {
let h = harness(Script::default());
let mut cfg = java_config("attach");
cfg.extra_json = Some(json!({"hostName": "localhost", "port": 5005}).to_string());
let id = h.start(cfg).await.unwrap();
let session = h.manager.session(id).unwrap();
assert_eq!(session.attach_target.get(), Some(&("localhost".to_owned(), 5005)));
assert!(session.jdwp_link.lock().is_none());
assert!(session.jvm_inspector.lock().is_none());
}
#[tokio::test]
async fn attach_target_recorded_for_any_adapter() {
let h = harness(Script::default());
let mut cfg = java_config("attach");
// "x" is not a registered adapter; debugpy has no JVM link or memory support.
cfg.adapter = "debugpy".into();
cfg.extra_json = Some(json!({"hostName": "h", "port": 7}).to_string());
let id = h.start(cfg).await.unwrap();
assert_eq!(h.manager.session(id).unwrap().attach_target.get(), Some(&("h".to_owned(), 7)));
}
#[tokio::test]
async fn launch_sessions_have_no_attach_target() {
let h = harness(Script::default());
let id = h.start(java_config("launch")).await.unwrap();
assert_eq!(h.manager.session(id).unwrap().attach_target.get(), None);
}
#[tokio::test]
async fn closing_the_session_drops_the_link() {
let h = harness(Script { hang_up_on_pause: true, ..Script::default() });
let project = tempfile::tempdir().unwrap();
let id = h.start(kotlin_attach(project.path(), "127.0.0.1", 5005)).await.unwrap();
let session = h.manager.session(id).unwrap();
assert!(session.jdwp_link.lock().is_some() && session.jvm_inspector.lock().is_some());
let _ = session.conn.request_timeout("pause", json!({"threadId": 1}), Duration::from_secs(2)).await;
for _ in 0..200 {
if h.manager.session(id).is_err() {
break;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
assert!(session.jdwp_link.lock().is_none());
assert!(session.jvm_inspector.lock().is_none());
}
#[cfg(unix)]
#[tokio::test]
async fn rdbg_drains_test_output_after_dap_closes_before_killing_the_process() {
-401
View File
@@ -1,401 +0,0 @@
//! Instances, fields and referrers through a session's JVM inspector.
use super::*;
use crate::jvm_memory::test_support::FakeInspector;
use ide_core::event::JvmBackendState;
use ide_jvm_inspect::{InspectError, JvmValue, VmTarget};
use tokio::io::AsyncReadExt;
fn debug_events(h: &Harness) -> Vec<DebugEvent> {
h.events
.lock()
.iter()
.filter_map(|e| match e {
IdeEvent::Debug { event, .. } => Some(event.clone()),
_ => None,
})
.collect()
}
fn backend_events(h: &Harness) -> Vec<JvmBackendState> {
debug_events(h)
.into_iter()
.filter_map(|e| match e {
DebugEvent::JvmBackend { state } => Some(state),
_ => None,
})
.collect()
}
/// A java-debug session stopped at its breakpoint, inspected by `fake`.
async fn stopped_with(h: &Harness, config: LaunchConfig, fake: &Arc<FakeInspector>) -> DebugSessionId {
let id = h.start(config).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
h.manager.set_jvm_inspector(id, fake.clone()).unwrap();
id
}
fn object(id: u64) -> JvmValue {
JvmValue::Object { id, type_name: "A".into() }
}
const NOT_SUSPENDED: JvmInstancesResult =
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::NotSuspended };
#[tokio::test]
async fn instances_need_a_suspended_session() {
let h = harness(Script { continued_after_stop: true, ..Script::default() });
let id = h.start(java_config("launch")).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Continued { .. })).await;
let fake = Arc::new(FakeInspector::default());
h.manager.set_jvm_inspector(id, fake.clone()).unwrap();
assert_eq!(h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap(), NOT_SUSPENDED);
assert_eq!(fake.calls(), 0);
}
#[tokio::test]
async fn instances_without_an_inspector_have_no_backend() {
let h = harness(Script::default());
let id = h.start(java_config("launch")).await.unwrap();
h.wait_event(|e| matches!(e, DebugEvent::Stopped { .. })).await;
assert_eq!(
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::NoBackend }
);
}
#[tokio::test]
async fn object_from_previous_stop_is_stale() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::default());
fake.instances.lock().push(object(7));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let JvmInstancesResult::Ready { generation, instances, truncated } =
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap()
else {
panic!("instances unavailable");
};
assert_eq!((generation, instances, truncated), (1, vec![object(7)], false));
h.manager.session(id).unwrap().suspended.stopped(None, true);
let stale = JvmObjectRef { generation, id: 7 };
assert_eq!(
h.manager.jvm_memory_fields(id, stale).await.unwrap(),
JvmFieldsResult::Unavailable { reason: JvmInspectUnavailable::Stale }
);
assert_eq!(
h.manager.jvm_memory_referrers(id, stale, 10).await.unwrap(),
JvmReferrersResult::Unavailable { reason: JvmInspectUnavailable::Stale }
);
assert_eq!(fake.calls(), 1, "a stale object never reaches the inspector");
let current = JvmObjectRef { generation: 2, id: 7 };
assert_eq!(h.manager.jvm_memory_fields(id, current).await.unwrap(), JvmFieldsResult::Ready { fields: Vec::new() });
}
#[tokio::test]
async fn instances_stay_readable_while_another_thread_is_stopped() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::default());
fake.instances.lock().push(object(7));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let session = h.manager.session(id).unwrap();
// Threads 20, 21, then 22 stop alone (SUSPEND_EVENT_THREAD).
session.suspended.continued(Some(1), true);
for thread in [20, 21, 22] {
session.suspended.stopped(Some(thread), false);
}
let instances = || h.manager.jvm_memory_instances(id, "A".into(), 10);
let result = instances().await.unwrap();
let JvmInstancesResult::Ready { generation, .. } = result else { panic!("{result:?}") };
let read_on_22 = JvmObjectRef { generation, id: 7 };
// An earlier thread resumes: the stop on 22 goes on, and so does what was read on it.
session.suspended.continued(Some(20), false);
assert_eq!(
h.manager.jvm_memory_fields(id, read_on_22).await.unwrap(),
JvmFieldsResult::Ready { fields: Vec::new() }
);
// The latest one resumes: 21 is still stopped, but what was read on 22 is stale.
session.suspended.continued(Some(22), false);
assert_eq!(
h.manager.jvm_memory_fields(id, read_on_22).await.unwrap(),
JvmFieldsResult::Unavailable { reason: JvmInspectUnavailable::Stale }
);
let result = instances().await.unwrap();
assert!(matches!(result, JvmInstancesResult::Ready { .. }), "{result:?}");
}
/// Starts `instances` on a held fake inspector; returns once the inspector was entered.
async fn held_request(
h: &Harness,
id: DebugSessionId,
fake: &Arc<FakeInspector>,
) -> tokio::task::JoinHandle<IdeResult<JvmInstancesResult>> {
let manager = h.manager.clone();
let request = tokio::spawn(async move { manager.jvm_memory_instances(id, "A".into(), 10).await });
tokio::time::timeout(Duration::from_secs(2), fake.entered.notified()).await.unwrap();
request
}
#[tokio::test]
async fn stop_during_request_is_stale() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector { hold: true, ..FakeInspector::default() });
fake.instances.lock().push(object(7));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let request = held_request(&h, id, &fake).await;
h.manager.session(id).unwrap().suspended.stopped(None, true);
fake.release.notify_one();
assert_eq!(
request.await.unwrap().unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::Stale }
);
}
#[tokio::test]
async fn resume_during_request_is_stale() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector { hold: true, ..FakeInspector::default() });
let id = stopped_with(&h, java_config("launch"), &fake).await;
let request = held_request(&h, id, &fake).await;
h.manager.session(id).unwrap().suspended.continued(None, true);
fake.release.notify_one();
assert_eq!(
request.await.unwrap().unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::Stale }
);
}
#[tokio::test]
async fn one_request_at_a_time_per_session() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector { hold: true, ..FakeInspector::default() });
let id = stopped_with(&h, java_config("launch"), &fake).await;
let first = held_request(&h, id, &fake).await;
let manager = h.manager.clone();
let second = tokio::spawn(async move { manager.jvm_memory_instances(id, "B".into(), 10).await });
tokio::time::sleep(Duration::from_millis(50)).await;
assert_eq!(fake.calls(), 1, "the second request waits for the first");
fake.release.notify_one();
first.await.unwrap().unwrap();
tokio::time::timeout(Duration::from_secs(2), fake.entered.notified()).await.unwrap();
fake.release.notify_one();
second.await.unwrap().unwrap();
assert_eq!(fake.calls(), 2);
}
#[tokio::test]
async fn session_end_lets_go_of_a_waiting_inspector() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector { hold: true, ..FakeInspector::default() });
let id = stopped_with(&h, java_config("launch"), &fake).await;
let request = held_request(&h, id, &fake).await;
h.manager.session(id).unwrap().kill_processes();
assert_eq!(
tokio::time::timeout(Duration::from_secs(2), request).await.unwrap().unwrap().unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::BackendClosed }
);
assert_eq!(Arc::strong_count(&fake), 1, "no clone of the inspector outlives the session");
}
#[tokio::test]
async fn target_carries_pid_for_launch() {
let h = harness(Script { debuggee_pid: Some(4242), java_process_id: true, ..Script::default() });
let fake = Arc::new(FakeInspector::default());
let id = stopped_with(&h, java_config("launch"), &fake).await;
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap();
assert_eq!(
*fake.targets.lock(),
[VmTarget { pid: Some(4242), attach_host: None, attach_port: None, generation: 1 }]
);
}
#[tokio::test]
async fn target_carries_attach_port_and_host() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let fake = Arc::new(FakeInspector::default());
let id = stopped_with(&h, remote_attach("java-debug", project.path()), &fake).await;
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap();
assert_eq!(
*fake.targets.lock(),
[VmTarget { pid: None, attach_host: Some("10.0.0.5".into()), attach_port: Some(5005), generation: 1 }]
);
}
#[tokio::test]
async fn unsupported_backend_turns_instances_off() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::failing(InspectError::Unsupported("x".into())));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let before = debug_events(&h).len();
assert_eq!(
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::Unsupported { detail: "x".into() } }
);
let after: Vec<_> = debug_events(&h).split_off(before);
assert!(
matches!(
after.as_slice(),
[DebugEvent::JvmBackend { state: JvmBackendState::Unsupported { detail } }, DebugEvent::Capabilities]
if detail == "x"
),
"{after:?}"
);
assert!(!h.manager.capabilities(id).unwrap().jvm_instances);
assert_eq!(
h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap(),
JvmInstancesResult::Unavailable { reason: JvmInspectUnavailable::NoBackend }
);
assert_eq!(fake.calls(), 1);
}
/// `error` is reported but leaves the backend on.
async fn keeps_the_backend(error: InspectError, reason: JvmInspectUnavailable) {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::failing(error));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let object = JvmObjectRef { generation: 1, id: 7 };
assert_eq!(h.manager.jvm_memory_fields(id, object).await.unwrap(), JvmFieldsResult::Unavailable { reason });
assert!(h.manager.capabilities(id).unwrap().jvm_instances);
assert!(backend_events(&h).is_empty());
assert!(h.manager.session(id).unwrap().jvm_inspector.lock().is_some());
}
#[tokio::test]
async fn collected_keeps_the_backend() {
keeps_the_backend(InspectError::Collected, JvmInspectUnavailable::Collected).await;
}
#[tokio::test]
async fn timed_out_keeps_the_backend() {
keeps_the_backend(InspectError::TimedOut, JvmInspectUnavailable::TimedOut).await;
}
#[tokio::test]
async fn failed_inspection_is_an_error() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::failing(InspectError::Failed("boom".into())));
let id = stopped_with(&h, java_config("launch"), &fake).await;
let err = h.manager.jvm_memory_instances(id, "A".into(), 10).await.unwrap_err();
assert!(err.to_string().contains("boom"), "{err}");
assert!(h.manager.capabilities(id).unwrap().jvm_instances);
}
#[tokio::test]
async fn limits_are_clamped() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::default());
let id = stopped_with(&h, java_config("launch"), &fake).await;
for limit in [5000, 0] {
h.manager.jvm_memory_instances(id, "A".into(), limit).await.unwrap();
}
let object = JvmObjectRef { generation: 1, id: 7 };
for limit in [0, 900, 20] {
h.manager.jvm_memory_referrers(id, object, limit).await.unwrap();
}
assert_eq!(*fake.limits.lock(), [1000, 1, 50, 200, 20]);
}
#[tokio::test]
async fn a_full_page_is_truncated() {
let h = harness(Script::default());
let fake = Arc::new(FakeInspector::default());
fake.instances.lock().extend([object(1), object(2)]);
let id = stopped_with(&h, java_config("launch"), &fake).await;
let truncated = |r: JvmInstancesResult| match r {
JvmInstancesResult::Ready { truncated, .. } => truncated,
other => panic!("{other:?}"),
};
assert!(truncated(h.manager.jvm_memory_instances(id, "A".into(), 2).await.unwrap()));
assert!(!truncated(h.manager.jvm_memory_instances(id, "A".into(), 3).await.unwrap()));
}
#[tokio::test]
async fn capability_follows_the_inspector() {
let h = harness(Script::default());
let id = h.start(java_config("launch")).await.unwrap();
assert!(!h.manager.capabilities(id).unwrap().jvm_instances);
let before = debug_events(&h).len();
h.manager.set_jvm_inspector(id, Arc::new(FakeInspector::default())).unwrap();
assert!(h.manager.capabilities(id).unwrap().jvm_instances);
assert!(matches!(debug_events(&h).split_off(before).as_slice(), [DebugEvent::Capabilities]));
}
#[tokio::test]
async fn remote_attach_counts_classes_through_the_debugger() {
let h = harness(Script::default());
let project = tempfile::tempdir().unwrap();
let fake = Arc::new(FakeInspector::default());
fake.counts.lock().push(ide_jvm_inspect::ClassCount { name: "A".into(), instances: 3 });
let id = stopped_with(&h, remote_attach("java-debug", project.path()), &fake).await;
let result = h.manager.jvm_memory_classes(id).await.unwrap();
assert!(
matches!(&result, JvmMemoryResult::Ready { snapshot }
if snapshot.source == JvmMemorySource::Debugger && snapshot.rows.len() == 1),
"{result:?}"
);
assert_eq!(fake.targets.lock()[0].attach_port, Some(5005));
}
const HANDSHAKE: &[u8; 14] = b"JDWP-Handshake";
/// A Kotlin attach whose link reaches a fake JVM: (adapter end, JVM end) after both handshakes.
async fn linked_kotlin(h: &Harness) -> (DebugSessionId, tokio::net::TcpStream, tokio::net::TcpStream) {
let jvm = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
let project = tempfile::tempdir().unwrap();
let id = h.start(kotlin_attach(project.path(), "127.0.0.1", jvm.local_addr().unwrap().port())).await.unwrap();
let link_port = h.request("attach")["arguments"]["port"].as_u64().unwrap() as u16;
let mut adapter = tokio::net::TcpStream::connect(("127.0.0.1", link_port)).await.unwrap();
adapter.write_all(HANDSHAKE).await.unwrap();
let (mut jvm, _) = tokio::time::timeout(Duration::from_secs(2), jvm.accept()).await.unwrap().unwrap();
let mut buf = [0; 14];
jvm.read_exact(&mut buf).await.unwrap();
jvm.write_all(HANDSHAKE).await.unwrap();
adapter.read_exact(&mut buf).await.unwrap();
(id, adapter, jvm)
}
/// A command the adapter sends with an id from the link's own range: the link then only forwards.
async fn degrade(adapter: &mut tokio::net::TcpStream) {
let mut packet = 11u32.to_be_bytes().to_vec();
packet.extend(ide_jdwp::OWN_IDS.start.to_be_bytes());
packet.extend([0, 1, 1]);
adapter.write_all(&packet).await.unwrap();
}
async fn wait_backend(h: &Harness, want: impl Fn(&JvmBackendState) -> bool) {
h.wait_event(|e| matches!(e, DebugEvent::JvmBackend { state } if want(state))).await;
}
#[tokio::test]
async fn kotlin_link_reports_degraded_then_closed() {
let h = harness(Script::default());
let (id, mut adapter, jvm) = linked_kotlin(&h).await;
degrade(&mut adapter).await;
wait_backend(&h, |s| matches!(s, JvmBackendState::Degraded { .. })).await;
drop(jvm);
wait_backend(&h, |s| *s == JvmBackendState::Closed).await;
assert_eq!(backend_events(&h).len(), 2, "{:?}", backend_events(&h));
let session = h.manager.session(id).unwrap();
assert!(session.jdwp_link.lock().is_some(), "a closed link is kept until the session ends");
}
#[tokio::test]
async fn kotlin_link_is_quiet_once_the_program_ended() {
let h = harness(Script::default());
let (id, _adapter, jvm) = linked_kotlin(&h).await;
let session = h.manager.session(id).unwrap();
// The adapter reported the end; the session keeps its link until it shuts down.
session.terminated.store(true, Ordering::Release);
drop(jvm);
for _ in 0..100 {
if session.jdwp_link.lock().as_ref().is_some_and(|l| l.state() == ide_jdwp::LinkState::Closed) {
break;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
tokio::time::sleep(Duration::from_millis(50)).await;
assert!(backend_events(&h).is_empty(), "{:?}", backend_events(&h));
}
+1 -1
View File
@@ -20,7 +20,7 @@ parking_lot.workspace = true
futures.workspace = true
sqlx.workspace = true
tiberius.workspace = true
oracledb.workspace = true
oracle.workspace = true
bb8.workspace = true
tokio-util = { workspace = true, features = ["compat"] }
dirs.workspace = true
+3 -3
View File
@@ -417,7 +417,7 @@ fn binary_type(name: &str, text: bool) -> bool {
}
/// Bytes as text: UTF-8, else hex (grids) or with invalid sequences replaced (catalog names).
pub(crate) fn bytes_text(bytes: Vec<u8>, mode: Cells) -> String {
fn bytes_text(bytes: Vec<u8>, mode: Cells) -> String {
match (String::from_utf8(bytes), mode) {
(Ok(s), _) => s,
(Err(e), Cells::Display) => hex(e.as_bytes()),
@@ -1042,7 +1042,7 @@ pub enum Held {
Mysql(Box<bb8::PooledConnection<'static, MysqlManager>>),
SqlServer(Box<bb8::PooledConnection<'static, MssqlConnectionManager>>),
Clickhouse(crate::clickhouse::ClickhousePool),
Oracle(Box<crate::oracle::OracleConnection>),
Oracle(crate::oracle::OracleConnection),
}
impl Held {
@@ -1058,7 +1058,7 @@ impl Held {
}
Held::Clickhouse(p.clone())
}
Pool::Oracle(p) => Held::Oracle(Box::new(p.get().await?)),
Pool::Oracle(p) => Held::Oracle(p.get().await?),
})
}
+3 -41
View File
@@ -57,7 +57,6 @@ impl DbTableKind {
pub enum DbObjectKind {
Function,
Procedure,
Package,
Trigger,
Sequence,
}
@@ -93,21 +92,12 @@ pub struct SequenceInfo {
pub data_type: String,
}
/// An Oracle package (its procedures and functions are not listed separately).
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
#[serde(rename = "DbPackageInfo")]
pub struct PackageInfo {
pub name: String,
}
/// A schema's routines (procedures and functions), packages and sequences.
/// A schema's routines (procedures and functions) and sequences.
#[derive(Debug, Clone, PartialEq, Eq, Default, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
#[serde(rename = "DbSchemaObjects")]
pub struct SchemaObjects {
pub routines: Vec<RoutineInfo>,
pub packages: Vec<PackageInfo>,
pub sequences: Vec<SequenceInfo>,
}
@@ -306,7 +296,7 @@ fn through_tunnel(e: IdeError, source: &DataSource, via: Option<&str>) -> IdeErr
/// Options › Run keep-alive query: pings the pool until it is closed or dropped
/// (a dropped SSH tunnel or an idle-killing proxy stays alive meanwhile).
pub(crate) fn keep_alive(pool: &Arc<Pool>, every: Duration) {
fn keep_alive(pool: &Arc<Pool>, every: Duration) {
let pool = Arc::downgrade(pool);
tokio::spawn(async move {
let mut tick = tokio::time::interval(every);
@@ -863,14 +853,6 @@ impl DbManager {
})
.collect();
}
if let Some(q) = sql::packages(driver, schema) {
out.packages = pool
.rows(&q, MAX_META_ROWS)
.await?
.into_iter()
.filter_map(|r| Some(PackageInfo { name: r.into_iter().next().flatten()? }))
.collect();
}
if let Some(q) = sql::sequences(driver, schema) {
out.sequences = pool
.rows(&q, MAX_META_ROWS)
@@ -888,29 +870,9 @@ impl DbManager {
Ok(out)
}
/// The definition of a routine (every overload), package (spec and body), trigger or sequence.
/// The definition of a routine (every overload), trigger or sequence.
pub async fn object_ddl(&self, id: &str, schema: &str, kind: DbObjectKind, name: &str) -> IdeResult<String> {
let pool = self.pool(id).await?;
if kind == DbObjectKind::Package {
let mut defs: Vec<String> = Vec::new();
for body in [false, true] {
let Some(q) = sql::package_ddl(pool.driver(), schema, name, body) else { continue };
match pool.rows(&q, MAX_META_ROWS).await {
Ok(rows) => defs.extend(rows.into_iter().filter_map(|r| r.into_iter().next().flatten())),
// A spec-only package has no body: the spec alone still opens.
Err(e) if body => tracing::warn!("package body {schema}.{name}: {}", e.message),
Err(e) => return Err(e),
}
}
if defs.is_empty() {
return Err(IdeError::not_found(format!("{schema}.{name}")));
}
return Ok(defs
.iter()
.map(|d| format!("{};\n", d.trim_end().trim_end_matches(';')))
.collect::<Vec<_>>()
.join("\n"));
}
let (q, column) = sql::object_ddl(pool.driver(), schema, kind, name)
.ok_or_else(|| IdeError::invalid(format!("no {kind:?} objects in this database")))?;
let defs: Vec<String> = pool
File diff suppressed because it is too large. Load diff
+3 -1
View File
@@ -20,7 +20,7 @@ pub enum DbDriver {
/// Microsoft SQL Server.
SqlServer,
Clickhouse,
/// Oracle Database (pure-Rust thin driver, no client library).
/// Oracle Database (via Oracle Instant Client).
Oracle,
}
@@ -88,6 +88,8 @@ pub struct DbOptions {
pub auto_disconnect_secs: Option<u32>,
/// PostgreSQL: show only the configured database, its schemas right under the data source.
pub single_database: bool,
/// Oracle: directory of the Oracle Instant Client (empty: `ORACLE_HOME` / system search path).
pub instant_client: String,
}
/// Schemas tab: the databases / schemas the tree shows. Names may use `*` and `?`.
-39
View File
@@ -664,32 +664,6 @@ pub fn routines(driver: DbDriver, schema: &str) -> Option<String> {
}
}
/// Rows: `name` of a schema's packages (Oracle only; their procedures and functions are not
/// listed separately, as in IDEA).
pub fn packages(driver: DbDriver, schema: &str) -> Option<String> {
match driver {
DbDriver::Oracle => Some(format!(
"SELECT object_name FROM all_objects WHERE owner = {} AND object_type = 'PACKAGE' \
AND object_name NOT LIKE 'BIN$%' ORDER BY 1",
quote_literal(driver, schema)
)),
_ => None,
}
}
/// The statement reading a package's specification (`body` false) or body as DDL.
pub fn package_ddl(driver: DbDriver, schema: &str, name: &str, body: bool) -> Option<String> {
match driver {
DbDriver::Oracle => Some(format!(
"SELECT DBMS_METADATA.GET_DDL('{}', {}, {}) FROM DUAL",
if body { "PACKAGE_BODY" } else { "PACKAGE" },
quote_literal(driver, name),
quote_literal(driver, schema)
)),
_ => None,
}
}
/// Rows: `name, data type` of a schema's sequences (PostgreSQL, Oracle).
pub fn sequences(driver: DbDriver, schema: &str) -> Option<String> {
match driver {
@@ -989,7 +963,6 @@ mod tests {
assert!(completion_columns(DbDriver::Oracle).contains("all_tab_columns"));
assert!(triggers(DbDriver::Oracle, "hr", "t").contains("all_triggers"));
assert!(routines(DbDriver::Oracle, "hr").unwrap().contains("all_objects"));
assert!(packages(DbDriver::Oracle, "hr").unwrap().contains("object_type = 'PACKAGE'"));
assert!(sequences(DbDriver::Oracle, "hr").unwrap().contains("all_sequences"));
}
@@ -1011,17 +984,6 @@ mod tests {
let (q, col) = object_ddl(DbDriver::Oracle, "hr", K::Procedure, "p").unwrap();
assert!(q.contains("DBMS_METADATA.GET_DDL('PROCEDURE'") && col == 0);
assert!(object_ddl(DbDriver::Oracle, "hr", K::Sequence, "q").unwrap().0.contains("all_sequences"));
assert!(
package_ddl(DbDriver::Oracle, "hr", "pkg", false)
.unwrap()
.contains("DBMS_METADATA.GET_DDL('PACKAGE', 'pkg', 'hr')")
);
assert!(
package_ddl(DbDriver::Oracle, "hr", "pkg", true)
.unwrap()
.contains("DBMS_METADATA.GET_DDL('PACKAGE_BODY', 'pkg', 'hr')")
);
assert!(package_ddl(DbDriver::Postgres, "public", "pkg", false).is_none());
}
#[test]
@@ -1039,7 +1001,6 @@ mod tests {
fn schema_objects_per_dialect() {
use crate::DbObjectKind as K;
assert!(routines(DbDriver::Sqlite, "main").is_none());
assert!(packages(DbDriver::Sqlite, "main").is_none());
assert!(sequences(DbDriver::Mysql, "db").is_none());
assert!(routines(DbDriver::Postgres, "public").unwrap().contains("n.nspname = 'public'"));
assert_eq!(
+17 -44
View File
@@ -136,19 +136,24 @@ pub struct DockerRegistry {
pub username: String,
}
#[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize, Type)]
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub struct DockerSettings {
#[serde(default)]
#[serde(default = "default_connections")]
pub connections: Vec<DockerConnection>,
#[serde(default)]
pub registries: Vec<DockerRegistry>,
}
/// Whether `c` is the connection older versions injected when nothing was configured:
/// Services lists only connections the user added, so this one is dropped on load.
fn is_injected_default(c: &DockerConnection) -> bool {
c.id == "default" && c.name == "Docker" && c.endpoint == DockerEndpoint::Default
impl Default for DockerSettings {
fn default() -> Self {
Self { connections: default_connections(), registries: Vec::new() }
}
}
/// Before anything is configured the CLI's own daemon is shown, as before connections existed.
fn default_connections() -> Vec<DockerConnection> {
vec![DockerConnection { id: "default".into(), name: "Docker".into(), endpoint: DockerEndpoint::Default }]
}
const SETTINGS_FILE: &str = "docker.json";
@@ -156,17 +161,10 @@ const PASSWORDS_FILE: &str = "docker-passwords.json";
pub fn load_settings(data_dir: &Path) -> DockerSettings {
match std::fs::read(data_dir.join(SETTINGS_FILE)) {
// A file written before the opt-in Services rework carries the injected default
// (saved along with a registry or another connection); drop it unless edited.
Ok(bytes) => serde_json::from_slice(&bytes)
.map(|mut s: DockerSettings| {
s.connections.retain(|c| !is_injected_default(c));
s
})
.unwrap_or_else(|e| {
tracing::warn!("{SETTINGS_FILE}: {e}");
DockerSettings::default()
}),
Ok(bytes) => serde_json::from_slice(&bytes).unwrap_or_else(|e| {
tracing::warn!("{SETTINGS_FILE}: {e}");
DockerSettings::default()
}),
Err(_) => DockerSettings::default(),
}
}
@@ -375,8 +373,7 @@ mod tests {
fn settings_round_trip_and_passwords() {
let tmp = tempfile::tempdir().unwrap();
let dir = tmp.path();
// Nothing configured: no connection is invented.
assert!(load_settings(dir).connections.is_empty());
assert_eq!(load_settings(dir).connections[0].endpoint, DockerEndpoint::Default);
let settings = DockerSettings {
connections: vec![DockerConnection {
id: "c1".into(),
@@ -398,32 +395,8 @@ mod tests {
assert!(auth_for(dir, "postgres").is_none());
save_settings(dir, &DockerSettings { registries: Vec::new(), ..settings }).unwrap();
assert_eq!(registry_password(dir, "r1"), None);
// An empty list stays empty.
// An empty list stays empty (the default connection is only for a missing file).
save_settings(dir, &DockerSettings { connections: Vec::new(), registries: Vec::new() }).unwrap();
assert!(load_settings(dir).connections.is_empty());
}
#[test]
fn load_drops_the_injected_default_connection() {
let tmp = tempfile::tempdir().unwrap();
let dir = tmp.path();
let injected =
|| DockerConnection { id: "default".into(), name: "Docker".into(), endpoint: DockerEndpoint::Default };
let registry =
DockerRegistry { id: "r1".into(), name: "GHCR".into(), address: "ghcr.io".into(), username: "me".into() };
// Saved untouched by an older version (e.g. along with a registry): dropped on load.
save_settings(dir, &DockerSettings { connections: vec![injected()], registries: vec![registry.clone()] })
.unwrap();
let loaded = load_settings(dir);
assert!(loaded.connections.is_empty());
assert_eq!(loaded.registries, vec![registry]);
// A connection the user renamed or re-pointed stays theirs.
let renamed = DockerConnection { name: "Local engine".into(), ..injected() };
save_settings(dir, &DockerSettings { connections: vec![renamed.clone()], registries: Vec::new() }).unwrap();
assert_eq!(load_settings(dir).connections, vec![renamed]);
let repointed =
DockerConnection { endpoint: DockerEndpoint::Socket { path: "/var/run/docker.sock".into() }, ..injected() };
save_settings(dir, &DockerSettings { connections: vec![repointed.clone()], registries: Vec::new() }).unwrap();
assert_eq!(load_settings(dir).connections, vec![repointed]);
}
}
-1
View File
@@ -18,7 +18,6 @@ semver = "1"
blake3.workspace = true
zip.workspace = true
base64.workspace = true
dunce.workspace = true
ed25519-dalek = "3"
[dev-dependencies]
+3 -25
View File
@@ -420,13 +420,7 @@ pub fn resolve_program(name: &str, path_var: Option<&OsStr>) -> Result<PathBuf,
return if candidate.is_file() { Ok(candidate.to_path_buf()) } else { Err(format!("{name}: no such program")) };
}
let exts: Vec<String> = if cfg!(windows) {
let pathext = std::env::var("PATHEXT").unwrap_or_else(|_| ".EXE;.CMD;.BAT".into());
let pathext: Vec<String> = pathext.split(';').filter(|e| !e.is_empty()).map(str::to_owned).collect();
// A name given with its extension (`cargo.exe`) is looked up as written.
let has_ext = candidate.extension().is_some_and(|e| {
pathext.iter().any(|x| x.trim_start_matches('.').eq_ignore_ascii_case(&e.to_string_lossy()))
});
if has_ext { vec![String::new()] } else { pathext }
std::env::var("PATHEXT").unwrap_or_else(|_| ".EXE;.CMD;.BAT".into()).split(';').map(str::to_owned).collect()
} else {
vec![String::new()]
};
@@ -447,13 +441,11 @@ pub fn resolve_program(name: &str, path_var: Option<&OsStr>) -> Result<PathBuf,
/// `p` with its parent canonicalized but the file name as found: PATH
/// entries like `/var` → `/private/var` (macOS) or `~` links collapse to
/// their real directory, while a linked program (`cargo` → rustup) keeps
/// its link name so the shim still dispatches on argv[0]. `dunce` keeps the
/// path in its usual form on Windows: a `\\?\`-prefixed pin would never
/// match the path the program was actually started with.
/// its link name so the shim still dispatches on argv[0].
fn canonical_dir(p: &Path) -> PathBuf {
let Some(dir) = p.parent() else { return p.to_path_buf() };
let Some(name) = p.file_name() else { return p.to_path_buf() };
dunce::canonicalize(dir).map(|d| d.join(name)).unwrap_or_else(|_| p.to_path_buf())
std::fs::canonicalize(dir).map(|d| d.join(name)).unwrap_or_else(|_| p.to_path_buf())
}
fn is_executable(p: &Path) -> bool {
@@ -506,20 +498,6 @@ mod tests {
list.iter().map(|s| s.parse().unwrap()).collect()
}
#[test]
#[cfg(windows)]
fn pinned_program_path_has_no_verbatim_prefix() {
// std::fs::canonicalize returns \\?\-prefixed paths on Windows; a pin
// stored in that form would never match the plain path the program is
// started with. dunce keeps the usual form.
let dir = tempfile::tempdir().unwrap();
std::fs::write(dir.path().join("cargo.exe"), b"").unwrap();
let pinned = resolve_program("cargo.exe", Some(dir.path().as_os_str())).unwrap();
let shown = pinned.to_string_lossy();
assert!(!shown.starts_with(r"\\?\"), "verbatim prefix leaked into the pin: {shown}");
assert!(pinned.is_absolute());
}
fn req<'a>(version: &'a str, hash: &'a str, required: &[&str], optional: &[&str]) -> Request<'a> {
Request {
subject: Subject::Installed("p".into()),
+1 -8
View File
@@ -19,10 +19,8 @@ mod index;
pub mod ledger;
mod manifest;
pub mod package;
mod plugin_point;
mod point;
mod registry;
mod resolve;
mod ui;
mod when;
@@ -32,12 +30,7 @@ pub use manifest::{
ActivationEvent, CATEGORIES, Capabilities, ENGINE_VERSION, EVENT_KINDS, LEGACY_API, MANIFEST_FILE, MAX_CATEGORIES,
Manifest, check_relative, engine_compatible, validate_item_id, validate_plugin_id, validate_point_id,
};
pub use plugin_point::{FieldType, PointDecl};
pub use point::{Commit, Disposable, ExtensionPoint, MAX_PACKAGE_FILE, Package, Placement, Prepared, decode};
pub use registry::{
ChangeListener, Contribution, ContributionInfo, DeclaredPoint, ExtensionRegistry, LOCALES_DIR, LOCALES_POINT,
PreparedSet,
};
pub use resolve::{Blocked, Dependency, DependencyState, Node, Plan, dependency_state, dependents, plan};
pub use registry::{ContributionInfo, ExtensionRegistry, LOCALES_DIR, LOCALES_POINT, PreparedSet};
pub use ui::{UiContribution, UiDecl, UiPoint, UiStore, to_json};
pub use when::validate_when;
+2 -136
View File
@@ -26,8 +26,6 @@
//! activated at start-up, as before.
use crate::capability::Capability;
use crate::plugin_point::PointDecl;
use crate::resolve::Dependency;
use serde::Deserialize;
use std::collections::BTreeSet;
use std::path::{Component, Path, PathBuf};
@@ -68,10 +66,6 @@ pub struct Manifest {
pub wasm: Option<PathBuf>,
pub activation: Vec<ActivationEvent>,
pub capabilities: Capabilities,
/// `[[depends]]`: plugins this one needs (API 1.5).
pub depends: Vec<Dependency>,
/// `[[extension-points]]`: what other plugins may contribute to this one (API 1.5).
pub extension_points: Vec<PointDecl>,
/// `contributes.<point>` → its declarations, validated by the extension points.
pub contributes: toml::Table,
}
@@ -157,7 +151,6 @@ pub const EVENT_KINDS: &[&str] = &[
"file-closed",
"settings-changed",
"input-mode-changed",
"extensions-changed",
"file-opened",
"file-saved",
"files-changed",
@@ -217,10 +210,6 @@ struct Raw {
#[serde(default)]
permissions: Option<Vec<String>>,
#[serde(default)]
depends: Vec<Dependency>,
#[serde(default)]
extension_points: Vec<PointDecl>,
#[serde(default)]
contributes: toml::Table,
}
@@ -292,8 +281,6 @@ impl Manifest {
wasm: raw.wasm,
activation,
capabilities,
depends: raw.depends,
extension_points: raw.extension_points,
contributes: raw.contributes,
};
m.validate()?;
@@ -370,9 +357,6 @@ impl Manifest {
{
self.needs_api(&format!("`{event}`"), 4)?;
}
if matches!(event, ActivationEvent::Event(kind) if kind == "extensions-changed") {
self.needs_api("`on-event:extensions-changed`", 5)?;
}
if matches!(event, ActivationEvent::Event(kind) if kind == "files-changed") {
self.needs_api("`on-event:files-changed`", 3)?;
}
@@ -383,7 +367,6 @@ impl Manifest {
for c in &self.declared_categories {
validate_item_id(c, "category")?;
}
self.validate_relations()?;
for (point, decls) in &self.contributes {
validate_point_id(point)?;
if !matches!(decls, toml::Value::Array(_) | toml::Value::Table(_)) {
@@ -393,42 +376,6 @@ impl Manifest {
Ok(())
}
/// `[[depends]]` and `[[extension-points]]`.
fn validate_relations(&self) -> Result<(), String> {
if !self.depends.is_empty() {
self.needs_api("`[[depends]]`", 5)?;
}
if !self.extension_points.is_empty() {
self.needs_api("`[[extension-points]]`", 5)?;
}
let mut required = BTreeSet::new();
for dep in &self.depends {
validate_plugin_id(&dep.id)?;
if dep.id == self.id {
return Err(format!("`depends`: {} cannot depend on itself", self.id));
}
if let Some(req) = &dep.version
&& semver::VersionReq::parse(req).is_err()
{
return Err(format!(
"`depends`: {:?} is not a version requirement like \"^1.2\" (plugin {})",
req, dep.id
));
}
if !required.insert(&dep.id) {
return Err(format!("`depends`: {} is listed twice", dep.id));
}
}
let mut declared = BTreeSet::new();
for point in &self.extension_points {
point.validate(&self.id)?;
if !declared.insert(&point.id) {
return Err(format!("extension point {} is declared twice", point.id));
}
}
Ok(())
}
/// The declarations of one extension point: `[[contributes.x]]` gives
/// several, `[contributes.x]` one.
pub fn declarations(&self, point: &str) -> Vec<toml::Value> {
@@ -525,12 +472,11 @@ pub fn validate_item_id(id: &str, what: &str) -> Result<(), String> {
}
/// Extension point ids: `camelCase` or `kebab-case` words, dots allowed (`iconThemes`, `menus`).
/// Points declared by plugins are `<plugin id>.<name>`, which may be longer and contain `_`.
pub fn validate_point_id(id: &str) -> Result<(), String> {
let ok = !id.is_empty()
&& id.len() <= 128
&& id.len() <= 64
&& id.starts_with(|c: char| c.is_ascii_lowercase())
&& id.chars().all(|c| c.is_ascii_alphanumeric() || matches!(c, '-' | '.' | '_'));
&& id.chars().all(|c| c.is_ascii_alphanumeric() || matches!(c, '-' | '.'));
if ok { Ok(()) } else { Err(format!("invalid contribution point {id:?}")) }
}
@@ -765,86 +711,6 @@ mod api14_tests {
}
}
#[cfg(test)]
mod relations_tests {
use super::*;
const HEAD: &str = "id = \"acme.app\"\nname = \"App\"\nversion = \"1.0.0\"\nengines.openidea = \"^1.5\"\n";
fn parse(rest: &str) -> Result<Manifest, String> {
Manifest::parse(&format!("{HEAD}{rest}"))
}
#[test]
fn parses_depends_and_extension_points() {
let m = parse(
r#"
[[depends]]
id = "acme.base"
version = "^0.2"
[[depends]]
id = "acme.extra"
optional = true
[[extension-points]]
id = "acme.app.hooks"
required = ["name"]
fields = { name = "string" }
[[contributes."acme.base.things"]]
name = "x"
"#,
)
.unwrap();
assert_eq!(m.depends.len(), 2);
assert_eq!(m.depends[0].version.as_deref(), Some("^0.2"));
assert!(m.depends[1].optional);
assert_eq!(m.extension_points[0].id, "acme.app.hooks");
assert_eq!(m.declarations("acme.base.things").len(), 1);
}
#[test]
fn the_new_keys_need_api_1_5() {
let older =
"id = \"acme.app\"\nname = \"App\"\nversion = \"1.0.0\"\nwasm = \"p.wasm\"\nengines.openidea = \"^1.4\"\n";
let err = Manifest::parse(&format!("{older}[[depends]]\nid = \"acme.base\"\n")).unwrap_err();
assert!(err.contains("new in plugin API 1.5"), "{err}");
let err = Manifest::parse(&format!("{older}[[extension-points]]\nid = \"acme.app.x\"\n")).unwrap_err();
assert!(err.contains("new in plugin API 1.5"), "{err}");
let err = Manifest::parse(&format!("{older}activation = [\"on-event:extensions-changed\"]\n")).unwrap_err();
assert!(err.contains("new in plugin API 1.5"), "{err}");
let current = older.replace("^1.4", "^1.5");
assert!(Manifest::parse(&format!("{current}activation = [\"on-event:extensions-changed\"]\n")).is_ok());
}
#[test]
fn refuses_bad_dependencies() {
assert!(parse("[[depends]]\nid = \"acme.app\"\n").unwrap_err().contains("itself"));
assert!(parse("[[depends]]\nid = \"Bad Id\"\n").unwrap_err().contains("invalid plugin id"));
assert!(
parse("[[depends]]\nid = \"acme.base\"\nversion = \"one\"\n").unwrap_err().contains("version requirement")
);
let twice = "[[depends]]\nid = \"acme.base\"\n[[depends]]\nid = \"acme.base\"\n";
assert!(parse(twice).unwrap_err().contains("listed twice"));
assert!(parse("[[depends]]\nid = \"acme.base\"\nunknown = 1\n").is_err());
}
#[test]
fn refuses_points_outside_the_plugins_namespace() {
let err = parse("[[extension-points]]\nid = \"other.thing\"\n").unwrap_err();
assert!(err.contains("acme.app.<name>"), "{err}");
let twice = "[[extension-points]]\nid = \"acme.app.x\"\n[[extension-points]]\nid = \"acme.app.x\"\n";
assert!(parse(twice).unwrap_err().contains("declared twice"));
}
#[test]
fn plugin_ids_with_underscores_work_as_contribution_keys() {
assert!(validate_point_id("my_tools.base.things").is_ok());
assert!(validate_point_id("Bad").is_err());
}
}
#[cfg(test)]
mod commands_api_tests {
use super::*;
-40
View File
@@ -352,22 +352,6 @@ pub struct IndexEntry {
/// the IDE before showing it.
#[serde(default)]
pub icon: Option<PluginIcon>,
/// Where to read more: the manifest's homepage, else the registry's source repository.
#[serde(default)]
pub homepage: Option<String>,
/// This version's release notes (the manifest's `change-notes`).
#[serde(default)]
pub notes: Option<String>,
/// Downloads of the plugin's packages, as counted by whoever serves them.
#[serde(default)]
pub downloads: Option<u64>,
/// Picked by the marketplace's maintainers.
#[serde(default)]
pub featured: bool,
/// Project-relative paths whose presence makes the plugin worth suggesting
/// (`pom.xml`, `config/routes.rb`).
#[serde(default)]
pub suggest: Vec<String>,
}
impl IndexEntry {
@@ -701,33 +685,9 @@ mod tests {
engine: "^1.0".into(),
categories: Vec::new(),
icon: None,
homepage: None,
notes: None,
downloads: None,
featured: false,
suggest: Vec::new(),
}
}
#[test]
fn listing_details_are_optional() {
let mut json = serde_json::to_value(entry("acme.a", "acme")).unwrap();
for key in ["homepage", "notes", "downloads", "featured", "suggest"] {
json.as_object_mut().unwrap().remove(key);
}
assert_eq!(serde_json::from_value::<IndexEntry>(json).unwrap(), entry("acme.a", "acme"));
let full = IndexEntry {
homepage: Some("https://example.com".into()),
notes: Some("Fixes".into()),
downloads: Some(42),
featured: true,
suggest: vec!["pom.xml".into()],
..entry("acme.a", "acme")
};
let back: IndexEntry = serde_json::from_str(&serde_json::to_string(&full).unwrap()).unwrap();
assert_eq!(back, full);
}
fn version(id: &str, version: &str, engine: &str) -> IndexEntry {
IndexEntry { version: version.into(), engine: engine.into(), ..entry(id, "acme") }
}
-192
View File
@@ -1,192 +0,0 @@
//! Extension points a plugin declares for other plugins to contribute to
//! (`[[extension-points]]`), and the check of a contribution against them.
use serde::{Deserialize, Serialize};
use specta::Type;
use std::collections::BTreeMap;
const MAX_FIELDS: usize = 32;
const MAX_ID: usize = 128;
/// Longest string a contribution may carry in one field.
const MAX_TEXT: usize = 64 * 1024;
const MAX_LIST: usize = 1000;
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "kebab-case")]
pub enum FieldType {
String,
Boolean,
Integer,
Number,
StringList,
}
/// `[[extension-points]]`: a kind of contribution the declaring plugin's code reads.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(deny_unknown_fields)]
pub struct PointDecl {
/// `<plugin id>.<name>`.
pub id: String,
#[serde(default)]
pub description: String,
/// Fields a contribution must have.
#[serde(default)]
pub required: Vec<String>,
/// Every field a contribution may have; a contribution with another key is refused.
#[serde(default)]
pub fields: BTreeMap<String, FieldType>,
}
impl PointDecl {
pub fn validate(&self, plugin_id: &str) -> Result<(), String> {
let prefix = format!("{plugin_id}.");
let name = self.id.strip_prefix(&prefix).unwrap_or("");
let name_ok = name.chars().next().is_some_and(|c| c.is_ascii_lowercase() || c.is_ascii_digit())
&& name.chars().all(|c| c.is_ascii_lowercase() || c.is_ascii_digit() || matches!(c, '-' | '_' | '.'));
if !name_ok || self.id.len() > MAX_ID {
return Err(format!(
"invalid extension point {:?}: use \"{plugin_id}.<name>\" with a-z, 0-9, '.', '-', '_' in the name",
self.id
));
}
if self.description.len() > 500 {
return Err(format!("extension point {}: `description` is longer than 500 characters", self.id));
}
if self.fields.len() > MAX_FIELDS {
return Err(format!("extension point {}: at most {MAX_FIELDS} fields", self.id));
}
for field in self.fields.keys() {
let ok = field.chars().next().is_some_and(|c| c.is_ascii_lowercase())
&& field.chars().all(|c| c.is_ascii_alphanumeric() || matches!(c, '-' | '_'))
&& field.len() <= 64;
if !ok {
return Err(format!("extension point {}: invalid field name {field:?}", self.id));
}
}
for field in &self.required {
if !self.fields.contains_key(field) {
return Err(format!("extension point {}: required field {field:?} is not in `fields`", self.id));
}
}
Ok(())
}
/// Checks one contribution and returns it as JSON for the declaring plugin's code.
pub fn check(&self, value: &toml::Value) -> Result<serde_json::Value, String> {
let toml::Value::Table(table) = value else {
return Err("a contribution is a table".into());
};
for key in table.keys() {
if !self.fields.contains_key(key) {
let known: Vec<&str> = self.fields.keys().map(String::as_str).collect();
return Err(format!("unknown field {key:?} (this extension point has: {})", known.join(", ")));
}
}
for key in &self.required {
if !table.contains_key(key) {
return Err(format!("missing required field {key:?}"));
}
}
let mut out = serde_json::Map::new();
for (key, value) in table {
out.insert(key.clone(), convert(key, self.fields[key], value)?);
}
Ok(serde_json::Value::Object(out))
}
}
fn convert(key: &str, ty: FieldType, value: &toml::Value) -> Result<serde_json::Value, String> {
use serde_json::Value as J;
let wrong = |expected: &str| format!("field {key:?} must be {expected}");
match (ty, value) {
(FieldType::String, toml::Value::String(s)) => text(key, s).map(J::from),
(FieldType::Boolean, toml::Value::Boolean(b)) => Ok(J::from(*b)),
(FieldType::Integer, toml::Value::Integer(i)) => Ok(J::from(*i)),
(FieldType::Number, toml::Value::Integer(i)) => Ok(J::from(*i)),
(FieldType::Number, toml::Value::Float(f)) if f.is_finite() => Ok(J::from(*f)),
(FieldType::StringList, toml::Value::Array(items)) => {
if items.len() > MAX_LIST {
return Err(format!("field {key:?} has more than {MAX_LIST} items"));
}
items
.iter()
.map(|item| match item {
toml::Value::String(s) => text(key, s).map(J::from),
_ => Err(wrong("a list of strings")),
})
.collect::<Result<Vec<_>, _>>()
.map(J::Array)
}
(FieldType::String, _) => Err(wrong("a string")),
(FieldType::Boolean, _) => Err(wrong("true or false")),
(FieldType::Integer, _) => Err(wrong("an integer")),
(FieldType::Number, _) => Err(wrong("a number")),
(FieldType::StringList, _) => Err(wrong("a list of strings")),
}
}
fn text(key: &str, s: &str) -> Result<String, String> {
if s.len() > MAX_TEXT {
return Err(format!("field {key:?} is longer than {} KiB", MAX_TEXT >> 10));
}
Ok(s.to_owned())
}
#[cfg(test)]
mod tests {
use super::*;
fn decl(src: &str) -> PointDecl {
toml::from_str(src).unwrap()
}
const COMPLETIONS: &str = r#"
id = "acme.base.completions"
description = "Extra completions"
required = ["label"]
fields = { label = "string", detail = "string", weight = "integer", scopes = "string-list" }
"#;
#[test]
fn the_id_is_namespaced_by_the_declaring_plugin() {
assert!(decl(COMPLETIONS).validate("acme.base").is_ok());
let err = decl(COMPLETIONS).validate("acme.other").unwrap_err();
assert!(err.contains("acme.other.<name>"), "{err}");
assert!(decl("id = \"acme.base.\"").validate("acme.base").is_err());
assert!(decl("id = \"acme.base.Bad Name\"").validate("acme.base").is_err());
}
#[test]
fn required_fields_must_be_declared() {
let err = decl("id = \"p.x\"\nrequired = [\"a\"]").validate("p").unwrap_err();
assert!(err.contains("required field \"a\""), "{err}");
}
#[test]
fn checks_a_contribution_and_converts_it_to_json() {
let point = decl(COMPLETIONS);
let contribution: toml::Value =
toml::from_str("label = \"ew.x\"\nweight = 3\nscopes = [\"xml\", \"java\"]").unwrap();
let json = point.check(&contribution).unwrap();
assert_eq!(json, serde_json::json!({"label": "ew.x", "weight": 3, "scopes": ["xml", "java"]}));
}
#[test]
fn refuses_what_the_point_does_not_declare() {
let point = decl(COMPLETIONS);
let check = |src: &str| point.check(&toml::from_str::<toml::Value>(src).unwrap()).unwrap_err();
assert!(check("detail = \"x\"").contains("missing required field \"label\""));
let err = check("label = \"a\"\nextra = 1");
assert!(err.contains("unknown field \"extra\"") && err.contains("label"), "{err}");
assert!(check("label = 1").contains("must be a string"));
assert!(check("label = \"a\"\nweight = \"3\"").contains("must be an integer"));
assert!(check("label = \"a\"\nscopes = [1]").contains("list of strings"));
}
#[test]
fn numbers_take_integers_and_floats() {
let point = decl("id = \"p.x\"\nfields = { ratio = \"number\" }");
assert!(point.check(&toml::from_str::<toml::Value>("ratio = 2").unwrap()).is_ok());
assert!(point.check(&toml::from_str::<toml::Value>("ratio = 0.5").unwrap()).is_ok());
}
}
+6 -281
View File
@@ -1,7 +1,6 @@
//! Extension points plus the contributions committed to them, accounted per plugin.
use crate::capability::Capability;
use crate::plugin_point::PointDecl;
use crate::point::{Disposable, ExtensionPoint, Package, Placement, Prepared};
use parking_lot::{Mutex, RwLock};
use serde::{Deserialize, Serialize};
@@ -24,7 +23,7 @@ pub struct ContributionInfo {
}
struct Entry {
point: String,
point: &'static str,
key: Option<String>,
label: String,
disposable: Disposable,
@@ -39,7 +38,7 @@ pub struct PreparedSet {
pub files: Vec<PathBuf>,
/// Declarations for extension points this host does not know (skipped).
pub warnings: Vec<String>,
items: Vec<(String, Prepared)>,
items: Vec<(&'static str, Prepared)>,
}
impl PreparedSet {
@@ -62,41 +61,11 @@ impl std::fmt::Debug for PreparedSet {
}
}
/// What one plugin contributed to an extension point another plugin declared.
#[derive(Clone, Debug, PartialEq)]
pub struct Contribution {
/// The contributing plugin.
pub plugin: String,
/// The declaration as JSON, checked against the point's fields.
pub data: serde_json::Value,
}
/// An extension point a plugin declared, with who contributes to it.
#[derive(Clone, Debug, PartialEq)]
pub struct DeclaredPoint {
pub owner: String,
pub decl: PointDecl,
/// Plugin ids, in commit order, once each.
pub contributors: Vec<String>,
}
#[derive(Default)]
struct Dynamic {
points: BTreeMap<String, (String, PointDecl)>,
contributions: BTreeMap<String, Vec<Contribution>>,
}
/// Called with (point id, owner plugin) after contributions to a declared point changed.
pub type ChangeListener = Arc<dyn Fn(&str, &str) + Send + Sync>;
#[derive(Default)]
pub struct ExtensionRegistry {
points: RwLock<BTreeMap<&'static str, Arc<dyn ExtensionPoint>>>,
/// plugin id → its contributions in commit order.
entries: Mutex<BTreeMap<String, Vec<Entry>>>,
/// Points declared by plugins and what was contributed to them.
dynamic: Arc<Mutex<Dynamic>>,
listener: Arc<RwLock<Option<ChangeListener>>>,
}
impl ExtensionRegistry {
@@ -128,111 +97,6 @@ impl ExtensionRegistry {
self.points.read().get(id).cloned()
}
/// Registers the function told when contributions to a plugin-declared point change.
pub fn set_change_listener(&self, listener: ChangeListener) {
*self.listener.write() = Some(listener);
}
/// The plugin that declared `point`, while it is committed.
pub fn point_owner(&self, point: &str) -> Option<String> {
self.dynamic.lock().points.get(point).map(|(owner, _)| owner.clone())
}
/// What plugins contributed to `point`, in commit order. Empty unless a plugin declares it.
pub fn contributions_to(&self, point: &str) -> Vec<Contribution> {
let dynamic = self.dynamic.lock();
if !dynamic.points.contains_key(point) {
return Vec::new();
}
dynamic.contributions.get(point).cloned().unwrap_or_default()
}
/// The points `owner` declared, with their contributors.
pub fn declared_points(&self, owner: &str) -> Vec<DeclaredPoint> {
let dynamic = self.dynamic.lock();
dynamic
.points
.iter()
.filter(|(_, (o, _))| o == owner)
.map(|(id, (owner, decl))| {
let mut contributors: Vec<String> = Vec::new();
for c in dynamic.contributions.get(id).into_iter().flatten() {
if !contributors.contains(&c.plugin) {
contributors.push(c.plugin.clone());
}
}
DeclaredPoint { owner: owner.clone(), decl: decl.clone(), contributors }
})
.collect()
}
/// Makes `pkg`'s `[[extension-points]]` known: they take effect with the set's commit.
fn prepare_declarations(&self, pkg: &Package) -> Vec<(String, Prepared)> {
pkg.manifest
.extension_points
.iter()
.map(|decl| {
let (dynamic, owner, decl) = (self.dynamic.clone(), pkg.id().to_owned(), decl.clone());
let id = decl.id.clone();
let prepared = Prepared::new(format!("Extension point {id}"), move || {
let id = decl.id.clone();
dynamic.lock().points.insert(id.clone(), (owner.clone(), decl));
Ok(Disposable::new(move || {
dynamic.lock().points.remove(&id);
}))
})
.key(format!("extension-point:{id}"));
(id, prepared)
})
.collect()
}
/// Validates `pkg`'s contributions to a point some plugin declares, or `None`
/// when no plugin declares `point` (the caller then skips it as unknown).
fn prepare_contributions(&self, pkg: &Package, point: &str) -> Option<Result<Vec<Prepared>, String>> {
let declared = self.dynamic.lock().points.get(point).cloned();
let own =
pkg.manifest.extension_points.iter().find(|d| d.id == point).map(|d| (pkg.id().to_owned(), d.clone()));
let (owner, decl) = declared.or(own)?;
if owner != pkg.id() && !pkg.manifest.depends.iter().any(|d| d.id == owner) {
return Some(Err(format!("{point} is declared by {owner}: add it to [[depends]]")));
}
let listener = self.listener.clone();
let result = pkg
.manifest
.declarations(point)
.into_iter()
.enumerate()
.map(|(i, value)| {
let data = decl.check(&value).map_err(|e| format!("contributions[{i}]: {e}"))?;
let label = decl
.required
.first()
.and_then(|field| data.get(field))
.and_then(|v| v.as_str())
.map_or_else(|| point.to_owned(), str::to_owned);
let contribution = Contribution { plugin: pkg.id().to_owned(), data };
let (dynamic, listener, point) = (self.dynamic.clone(), listener.clone(), point.to_owned());
Ok(Prepared::new(label, move || {
dynamic.lock().contributions.entry(point.clone()).or_default().push(contribution.clone());
notify(&dynamic, &listener, &point);
Ok(Disposable::new(move || {
{
let mut guard = dynamic.lock();
if let Some(list) = guard.contributions.get_mut(&point)
&& let Some(pos) = list.iter().position(|c| *c == contribution)
{
list.remove(pos);
}
}
notify(&dynamic, &listener, &point);
}))
}))
})
.collect();
Some(result)
}
/// Validates every `contributes.<point>` declaration of `pkg`. Fails as a
/// whole on the first invalid declaration; unknown points are skipped with
/// a warning (forward compatibility).
@@ -244,24 +108,9 @@ impl ExtensionRegistry {
warnings: Vec::new(),
items: Vec::new(),
};
// Declared points first: contributions to them (the plugin's own too) commit after.
set.items.extend(self.prepare_declarations(pkg));
for point_id in pkg.manifest.contributes.keys() {
let Some(point) = self.point(point_id) else {
if let Some(result) = self.prepare_contributions(pkg, point_id) {
let prepared = result.map_err(|e| format!("contributes.{point_id}: {e}"))?;
set.items.extend(prepared.into_iter().map(|p| (point_id.clone(), p)));
continue;
}
// Point ids are `<owner id>.<name>`, so the dependency that owns it can be named.
let owner =
pkg.manifest.depends.iter().find(|d| point_id.strip_prefix(&format!("{}.", d.id)).is_some());
let msg = match owner {
Some(owner) => {
format!("contributes.{point_id}: {} is not running, so this is skipped until it is", owner.id)
}
None => format!("contributes.{point_id}: not supported by this version of the IDE; skipped"),
};
let msg = format!("contributes.{point_id}: not supported by this version of the IDE; skipped");
tracing::warn!(plugin = %pkg.id(), "{msg}");
set.warnings.push(msg);
continue;
@@ -280,7 +129,7 @@ impl ExtensionRegistry {
set.files.push(f.clone());
}
}
set.items.push((point.id().to_owned(), prepared));
set.items.push((point.id(), prepared));
}
}
if let Some(point) = self.point(LOCALES_POINT)
@@ -295,7 +144,7 @@ impl ExtensionRegistry {
set.files.push(f.clone());
}
}
set.items.push((point.id().to_owned(), prepared));
set.items.push((point.id(), prepared));
}
Ok(set)
}
@@ -352,7 +201,7 @@ impl ExtensionRegistry {
.lock()
.get(plugin)
.map(|list| {
list.iter().map(|e| ContributionInfo { point: e.point.clone(), label: e.label.clone() }).collect()
list.iter().map(|e| ContributionInfo { point: e.point.into(), label: e.label.clone() }).collect()
})
.unwrap_or_default()
}
@@ -368,14 +217,6 @@ impl ExtensionRegistry {
}
}
fn notify(dynamic: &Mutex<Dynamic>, listener: &RwLock<Option<ChangeListener>>, point: &str) {
let owner = dynamic.lock().points.get(point).map(|(owner, _)| owner.clone());
let callback = listener.read().clone();
if let (Some(owner), Some(callback)) = (owner, callback) {
callback(point, &owner);
}
}
fn strip_prefix<'a>(e: &'a str, point: &str) -> &'a str {
e.strip_prefix(&format!("contributes.{point}: ")).unwrap_or(e)
}
@@ -469,122 +310,6 @@ mod tests {
assert!(reg.contributions("p").is_empty());
}
fn pkg_of(id: &str, body: &str) -> Package {
let src = format!("id = \"{id}\"\nname = \"N\"\nversion = \"1.0.0\"\nengines.openidea = \"^1.5\"\n{body}");
Package::new(Manifest::parse(&src).unwrap(), PathBuf::from("/nonexistent"))
}
const BASE: &str = r#"
[[extension-points]]
id = "acme.base.things"
required = ["name"]
fields = { name = "string", weight = "integer" }
"#;
const PLUGIN: &str =
"[[depends]]\nid = \"acme.base\"\n\n[[contributes.\"acme.base.things\"]]\nname = \"a\"\nweight = 2\n";
fn commit(reg: &ExtensionRegistry, pkg: &Package) {
reg.commit(reg.prepare(pkg).unwrap()).unwrap();
}
#[test]
fn a_plugin_declares_a_point_and_a_dependent_contributes_to_it() {
let reg = ExtensionRegistry::new();
commit(&reg, &pkg_of("acme.base", BASE));
assert_eq!(reg.point_owner("acme.base.things").as_deref(), Some("acme.base"));
assert!(reg.contributions_to("acme.base.things").is_empty());
commit(&reg, &pkg_of("acme.more", PLUGIN));
let got = reg.contributions_to("acme.base.things");
assert_eq!(got.len(), 1);
assert_eq!(got[0].plugin, "acme.more");
assert_eq!(got[0].data, serde_json::json!({"name": "a", "weight": 2}));
assert_eq!(
reg.contributions("acme.more")[0],
ContributionInfo { point: "acme.base.things".into(), label: "a".into() }
);
let declared = reg.declared_points("acme.base");
assert_eq!(declared.len(), 1);
assert_eq!(declared[0].contributors, ["acme.more"]);
assert!(reg.dispose_plugin("acme.more"));
assert!(reg.contributions_to("acme.base.things").is_empty());
assert!(reg.dispose_plugin("acme.base"));
assert_eq!(reg.point_owner("acme.base.things"), None);
}
#[test]
fn contributions_disappear_from_view_while_the_owner_is_gone() {
let reg = ExtensionRegistry::new();
commit(&reg, &pkg_of("acme.base", BASE));
commit(&reg, &pkg_of("acme.more", PLUGIN));
reg.dispose_plugin("acme.base");
assert!(reg.contributions_to("acme.base.things").is_empty(), "nobody may read a point that is not declared");
commit(&reg, &pkg_of("acme.base", BASE));
assert_eq!(reg.contributions_to("acme.base.things").len(), 1, "back with the owner");
}
#[test]
fn contributing_needs_a_dependency_on_the_owner() {
let reg = ExtensionRegistry::new();
commit(&reg, &pkg_of("acme.base", BASE));
let err =
reg.prepare(&pkg_of("acme.rogue", "[[contributes.\"acme.base.things\"]]\nname = \"x\"\n")).unwrap_err();
assert!(err.contains("acme.base") && err.contains("[[depends]]"), "{err}");
}
#[test]
fn a_contribution_is_checked_against_the_declared_fields() {
let reg = ExtensionRegistry::new();
commit(&reg, &pkg_of("acme.base", BASE));
let bad = "[[depends]]\nid = \"acme.base\"\n[[contributes.\"acme.base.things\"]]\nweight = 1\n";
let err = reg.prepare(&pkg_of("acme.more", bad)).unwrap_err();
assert_eq!(err, "contributes.acme.base.things: contributions[0]: missing required field \"name\"");
}
#[test]
fn a_point_nobody_declares_is_skipped_with_a_warning() {
let reg = ExtensionRegistry::new();
let set = reg.prepare(&pkg_of("acme.more", PLUGIN)).unwrap();
assert!(set.is_empty());
assert!(set.warnings[0].contains("acme.base.things"), "{:?}", set.warnings);
}
#[test]
fn a_missing_owner_is_named_instead_of_blaming_the_ide_version() {
let reg = ExtensionRegistry::new();
let set = reg.prepare(&pkg_of("acme.more", PLUGIN)).unwrap();
let warning = &set.warnings[0];
assert!(warning.contains("acme.base") && warning.contains("not running"), "{warning}");
assert!(!warning.contains("this version of the IDE"), "{warning}");
let unrelated = "[[contributes.\"acme.nobody.things\"]]\nname = \"x\"\n";
let set = reg.prepare(&pkg_of("acme.more", unrelated)).unwrap();
assert!(set.warnings[0].contains("this version of the IDE"), "{:?}", set.warnings);
}
#[test]
fn a_plugin_may_contribute_to_its_own_point() {
let reg = ExtensionRegistry::new();
let own = format!("{BASE}\n[[contributes.\"acme.base.things\"]]\nname = \"builtin\"\n");
commit(&reg, &pkg_of("acme.base", &own));
assert_eq!(reg.contributions_to("acme.base.things")[0].data["name"], "builtin");
}
#[test]
fn the_owner_hears_about_changes_to_its_point() {
let reg = ExtensionRegistry::new();
let heard: Arc<Mutex<Vec<(String, String)>>> = Arc::default();
let sink = heard.clone();
reg.set_change_listener(Arc::new(move |point, owner| sink.lock().push((point.into(), owner.into()))));
commit(&reg, &pkg_of("acme.base", BASE));
assert!(heard.lock().is_empty(), "declaring is not a contribution");
commit(&reg, &pkg_of("acme.more", PLUGIN));
reg.dispose_plugin("acme.more");
let expected = ("acme.base.things".to_owned(), "acme.base".to_owned());
assert_eq!(*heard.lock(), [expected.clone(), expected]);
}
#[test]
fn invalid_declarations_fail_prepare_and_unknown_points_warn() {
let (reg, _) = setup();
-433
View File
@@ -1,433 +0,0 @@
//! Which plugins can run, and in which order, given what they depend on.
use semver::{Version, VersionReq};
use serde::{Deserialize, Serialize};
use specta::Type;
use std::collections::{BTreeMap, BTreeSet};
use std::fmt;
/// `[[depends]]` of a manifest.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(deny_unknown_fields)]
pub struct Dependency {
pub id: String,
/// Semver requirement on the dependency's version; none accepts any.
#[serde(default)]
pub version: Option<String>,
/// The plugin runs without it; when present it starts first.
#[serde(default)]
pub optional: bool,
}
impl Dependency {
/// `acme.base ^1.0`.
pub fn describe(&self) -> String {
match &self.version {
Some(v) => format!("{} {v}", self.id),
None => self.id.clone(),
}
}
}
/// A plugin as the resolver sees it.
#[derive(Clone, Copy, Debug)]
pub struct Node<'a> {
pub id: &'a str,
pub version: &'a str,
pub depends: &'a [Dependency],
/// Not switched off by the user.
pub enabled: bool,
}
/// Why an enabled plugin cannot run.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase", tag = "kind")]
pub enum Blocked {
/// A required plugin is not installed.
Missing { requirement: String },
/// A required plugin is switched off.
Disabled { id: String },
/// A required plugin is installed in a version that does not satisfy the requirement.
Version { requirement: String, found: String },
/// A required plugin cannot run itself.
Dependency { id: String },
/// The plugin is part of a dependency cycle (`a → b → a`).
Cycle { ring: Vec<String> },
}
impl fmt::Display for Blocked {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
Self::Missing { requirement } => write!(f, "Requires {requirement}, which is not installed"),
Self::Disabled { id } => write!(f, "Requires {id}, which is disabled"),
Self::Version { requirement, found } => {
write!(f, "Requires {requirement}, but version {found} is installed")
}
Self::Dependency { id } => write!(f, "Requires {id}, which cannot run"),
Self::Cycle { ring } => write!(f, "Part of a dependency cycle: {}", ring.join(" → ")),
}
}
}
#[derive(Clone, Debug, Default, PartialEq, Eq)]
pub struct Plan {
/// Plugins that can run, every plugin after the plugins it depends on.
pub order: Vec<String>,
/// Enabled plugins that cannot run. Disabled plugins are in neither list.
pub blocked: BTreeMap<String, Blocked>,
}
/// Decides, for every enabled plugin, whether its required plugins allow it to
/// run and the order to start them in (the counterpart of IntelliJ's
/// `PluginSetBuilder`: dependency graph, topological order, cycle report).
pub fn plan(nodes: &[Node<'_>]) -> Plan {
let by_id: BTreeMap<&str, &Node<'_>> = nodes.iter().map(|n| (n.id, n)).collect();
let enabled: Vec<&Node<'_>> = by_id.values().copied().filter(|n| n.enabled).collect();
let mut blocked: BTreeMap<String, Blocked> = BTreeMap::new();
for node in &enabled {
for dep in node.depends.iter().filter(|d| !d.optional) {
if let Some(reason) = direct_reason(dep, by_id.get(dep.id.as_str()).copied()) {
blocked.entry(node.id.to_owned()).or_insert(reason);
}
}
}
// Cycles among plugins whose requirements are otherwise present.
let candidates: BTreeSet<&str> = enabled.iter().map(|n| n.id).filter(|id| !blocked.contains_key(*id)).collect();
let graph: Graph<'_> = candidates
.iter()
.map(|id| {
let deps = by_id[id].depends.iter().filter(|d| !d.optional).map(|d| d.id.as_str());
(*id, deps.filter(|d| candidates.contains(d)).collect())
})
.collect();
for component in components(&graph) {
let cyclic = component.len() > 1 || graph[component[0]].contains(&component[0]);
if cyclic {
let ring = ring_of(&component, &graph);
for id in component {
blocked.insert(id.to_owned(), Blocked::Cycle { ring: ring.clone() });
}
}
}
// A plugin that needs a blocked plugin is blocked too.
loop {
let mut changed = false;
for node in &enabled {
if blocked.contains_key(node.id) {
continue;
}
if let Some(dep) = node.depends.iter().find(|d| !d.optional && blocked.contains_key(&d.id)) {
blocked.insert(node.id.to_owned(), Blocked::Dependency { id: dep.id.clone() });
changed = true;
}
}
if !changed {
break;
}
}
let runnable: BTreeSet<&str> = enabled.iter().map(|n| n.id).filter(|id| !blocked.contains_key(*id)).collect();
Plan { order: topological(&runnable, &by_id), blocked }
}
/// Plugins that need `id`, directly or through other plugins, whether or not
/// they are enabled. Optional dependencies do not count.
pub fn dependents(nodes: &[Node<'_>], id: &str) -> Vec<String> {
let mut found: BTreeSet<String> = BTreeSet::new();
let mut frontier = vec![id.to_owned()];
while let Some(current) = frontier.pop() {
for node in nodes {
if node.depends.iter().any(|d| !d.optional && d.id == current) && found.insert(node.id.to_owned()) {
frontier.push(node.id.to_owned());
}
}
}
found.remove(id);
found.into_iter().collect()
}
/// How one dependency stands right now, for the plugin details page.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, Type)]
#[serde(rename_all = "camelCase")]
pub enum DependencyState {
Satisfied,
Missing,
Disabled,
/// Installed, wrong version.
Version,
/// Installed and enabled, but cannot run itself.
Blocked,
}
pub fn dependency_state(dep: &Dependency, found: Option<&Node<'_>>, found_blocked: bool) -> DependencyState {
match direct_reason(dep, found) {
Some(Blocked::Missing { .. }) => DependencyState::Missing,
Some(Blocked::Disabled { .. }) => DependencyState::Disabled,
Some(Blocked::Version { .. }) => DependencyState::Version,
_ if found_blocked => DependencyState::Blocked,
_ => DependencyState::Satisfied,
}
}
fn direct_reason(dep: &Dependency, found: Option<&Node<'_>>) -> Option<Blocked> {
let Some(target) = found else {
return Some(Blocked::Missing { requirement: dep.describe() });
};
if !target.enabled {
return Some(Blocked::Disabled { id: dep.id.clone() });
}
let want = dep.version.as_deref()?;
let satisfied = VersionReq::parse(want)
.ok()
.zip(Version::parse(target.version).ok())
.is_some_and(|(req, have)| req.matches(&have));
(!satisfied).then(|| Blocked::Version { requirement: dep.describe(), found: target.version.to_owned() })
}
/// Plugin id → the plugin ids it requires.
type Graph<'a> = BTreeMap<&'a str, Vec<&'a str>>;
/// Strongly connected components (Tarjan) of `graph`.
fn components<'a>(graph: &Graph<'a>) -> Vec<Vec<&'a str>> {
struct State<'a, 'g> {
index: usize,
stack: Vec<&'a str>,
info: BTreeMap<&'a str, (usize, usize, bool)>,
out: Vec<Vec<&'a str>>,
graph: &'g Graph<'a>,
}
fn visit<'a>(s: &mut State<'a, '_>, v: &'a str) {
s.info.insert(v, (s.index, s.index, true));
s.index += 1;
s.stack.push(v);
for &w in &s.graph[v] {
match s.info.get(w).copied() {
None => {
visit(s, w);
let low = s.info[w].1;
let entry = s.info.get_mut(v).expect("visited");
entry.1 = entry.1.min(low);
}
Some((index, _, true)) => {
let entry = s.info.get_mut(v).expect("visited");
entry.1 = entry.1.min(index);
}
Some(_) => {}
}
}
let (index, low, _) = s.info[v];
if index == low {
let mut component = Vec::new();
while let Some(w) = s.stack.pop() {
s.info.get_mut(w).expect("visited").2 = false;
component.push(w);
if w == v {
break;
}
}
component.sort_unstable();
s.out.push(component);
}
}
let mut state = State { index: 0, stack: Vec::new(), info: BTreeMap::new(), out: Vec::new(), graph };
for &id in graph.keys() {
if !state.info.contains_key(id) {
visit(&mut state, id);
}
}
state.out
}
/// One cycle through `component`, from its smallest id back to it.
fn ring_of(component: &[&str], graph: &Graph<'_>) -> Vec<String> {
let start = component[0];
let mut ring = vec![start.to_owned()];
let mut current = start;
let mut seen: BTreeSet<&str> = BTreeSet::from([start]);
loop {
let mut next: Vec<&str> = graph[current].iter().copied().filter(|d| component.contains(d)).collect();
next.sort_unstable();
// Prefer closing the ring; otherwise take the smallest unseen member.
let step =
if next.contains(&start) { start } else { *next.iter().find(|d| !seen.contains(**d)).unwrap_or(&start) };
ring.push(step.to_owned());
if step == start {
return ring;
}
seen.insert(step);
current = step;
}
}
/// Kahn's algorithm over the runnable plugins; ties break by id. Optional
/// dependencies order too, but never block: leftovers (an optional edge
/// closing a loop) are appended by id.
fn topological(runnable: &BTreeSet<&str>, by_id: &BTreeMap<&str, &Node<'_>>) -> Vec<String> {
let mut waiting: BTreeMap<&str, BTreeSet<&str>> = runnable
.iter()
.map(|id| {
let deps = by_id[id].depends.iter().map(|d| d.id.as_str()).filter(|d| runnable.contains(d) && d != id);
(*id, deps.collect())
})
.collect();
let mut order: Vec<String> = Vec::with_capacity(runnable.len());
while let Some(next) = waiting.iter().find(|(_, deps)| deps.is_empty()).map(|(id, _)| *id) {
waiting.remove(next);
for deps in waiting.values_mut() {
deps.remove(next);
}
order.push(next.to_owned());
}
order.extend(waiting.keys().map(|id| (*id).to_owned()));
order
}
#[cfg(test)]
mod tests {
use super::*;
fn dep(id: &str) -> Dependency {
Dependency { id: id.into(), version: None, optional: false }
}
fn dep_v(id: &str, version: &str) -> Dependency {
Dependency { id: id.into(), version: Some(version.into()), optional: false }
}
fn optional(id: &str) -> Dependency {
Dependency { id: id.into(), version: None, optional: true }
}
fn node<'a>(id: &'a str, depends: &'a [Dependency]) -> Node<'a> {
Node { id, version: "1.0.0", depends, enabled: true }
}
#[test]
fn dependencies_start_first_whatever_the_ids_sort_like() {
let (a, z) = ([dep("z.base")], []);
let plan = plan(&[node("a.app", &a), node("z.base", &z)]);
assert_eq!(plan.order, ["z.base", "a.app"]);
assert!(plan.blocked.is_empty());
}
#[test]
fn independent_plugins_keep_id_order() {
let plan = plan(&[node("b", &[]), node("a", &[]), node("c", &[])]);
assert_eq!(plan.order, ["a", "b", "c"]);
}
#[test]
fn a_missing_requirement_blocks_with_the_requirement_text() {
let needs = [dep_v("acme.base", "^1.0")];
let plan = plan(&[node("acme.app", &needs)]);
assert!(plan.order.is_empty());
assert_eq!(plan.blocked["acme.app"], Blocked::Missing { requirement: "acme.base ^1.0".into() });
assert_eq!(plan.blocked["acme.app"].to_string(), "Requires acme.base ^1.0, which is not installed");
}
#[test]
fn a_disabled_requirement_blocks_but_the_disabled_plugin_itself_is_not_blocked() {
let needs = [dep("acme.base")];
let mut base = node("acme.base", &[]);
base.enabled = false;
let plan = plan(&[base, node("acme.app", &needs)]);
assert_eq!(plan.blocked["acme.app"], Blocked::Disabled { id: "acme.base".into() });
assert!(!plan.blocked.contains_key("acme.base"));
assert!(plan.order.is_empty());
}
#[test]
fn the_installed_version_must_satisfy_the_requirement() {
let needs = [dep_v("acme.base", "^0.2")];
let mut base = node("acme.base", &[]);
base.version = "0.3.0";
let plan_bad = plan(&[base, node("acme.app", &needs)]);
assert_eq!(
plan_bad.blocked["acme.app"],
Blocked::Version { requirement: "acme.base ^0.2".into(), found: "0.3.0".into() }
);
assert_eq!(plan_bad.blocked["acme.app"].to_string(), "Requires acme.base ^0.2, but version 0.3.0 is installed");
base.version = "0.2.7";
let plan_ok = plan(&[base, node("acme.app", &needs)]);
assert!(plan_ok.blocked.is_empty());
assert_eq!(plan_ok.order, ["acme.base", "acme.app"]);
}
#[test]
fn blocking_propagates_to_everything_downstream() {
let (b, c) = ([dep("a")], [dep("b")]);
let plan = plan(&[node("b", &b), node("c", &c)]);
assert_eq!(plan.blocked["b"], Blocked::Missing { requirement: "a".into() });
assert_eq!(plan.blocked["c"], Blocked::Dependency { id: "b".into() });
assert!(plan.order.is_empty());
}
#[test]
fn an_optional_requirement_never_blocks_but_orders_when_present() {
let app = [optional("acme.extra")];
let alone = plan(&[node("acme.app", &app)]);
assert_eq!(alone.order, ["acme.app"]);
assert!(alone.blocked.is_empty());
let with = plan(&[node("acme.app", &app), node("acme.extra", &[])]);
assert_eq!(with.order, ["acme.extra", "acme.app"]);
let mut off = node("acme.extra", &[]);
off.enabled = false;
let disabled = plan(&[node("acme.app", &app), off]);
assert_eq!(disabled.order, ["acme.app"]);
assert!(disabled.blocked.is_empty());
}
#[test]
fn a_cycle_blocks_its_members_and_names_the_ring() {
let (a, b, d) = ([dep("b")], [dep("a")], [dep("a")]);
let plan = plan(&[node("a", &a), node("b", &b), node("d", &d)]);
let ring = Blocked::Cycle { ring: vec!["a".into(), "b".into(), "a".into()] };
assert_eq!(plan.blocked["a"], ring);
assert_eq!(plan.blocked["b"], ring);
assert_eq!(ring.to_string(), "Part of a dependency cycle: a → b → a");
assert_eq!(plan.blocked["d"], Blocked::Dependency { id: "a".into() });
assert!(plan.order.is_empty());
}
#[test]
fn a_plugin_requiring_itself_is_a_cycle() {
let a = [dep("a")];
let plan = plan(&[node("a", &a)]);
assert_eq!(plan.blocked["a"], Blocked::Cycle { ring: vec!["a".into(), "a".into()] });
}
#[test]
fn an_optional_loop_does_not_block_and_still_yields_every_plugin() {
let (a, b) = ([optional("b")], [optional("a")]);
let plan = plan(&[node("a", &a), node("b", &b)]);
assert!(plan.blocked.is_empty());
assert_eq!(plan.order.len(), 2);
}
#[test]
fn dependents_are_transitive_and_ignore_optional_edges() {
let (b, c, d) = ([dep("a")], [dep("b")], [optional("a")]);
let nodes = [node("a", &[]), node("b", &b), node("c", &c), node("d", &d)];
assert_eq!(dependents(&nodes, "a"), ["b", "c"]);
assert_eq!(dependents(&nodes, "c"), Vec::<String>::new());
}
#[test]
fn dependency_state_tells_the_details_page_what_to_say() {
let want = dep_v("base", "^1.0");
assert_eq!(dependency_state(&want, None, false), DependencyState::Missing);
let mut base = node("base", &[]);
assert_eq!(dependency_state(&want, Some(&base), false), DependencyState::Satisfied);
assert_eq!(dependency_state(&want, Some(&base), true), DependencyState::Blocked);
base.version = "2.0.0";
assert_eq!(dependency_state(&want, Some(&base), false), DependencyState::Version);
base.enabled = false;
assert_eq!(dependency_state(&want, Some(&base), false), DependencyState::Disabled);
}
}
-28
View File
@@ -1,28 +0,0 @@
[package]
name = "ide-heap"
description = "HotSpot .hprof parser and heap-snapshot analysis for the debugger's JVM Memory view"
version.workspace = true
edition.workspace = true
license.workspace = true
[dependencies]
ide-core.workspace = true
memmap2.workspace = true
serde.workspace = true
serde_json.workspace = true
specta.workspace = true
thiserror.workspace = true
tracing.workspace = true
uuid.workspace = true
[target.'cfg(unix)'.dependencies]
libc = "0.2"
[dev-dependencies]
criterion = { version = "0.5", default-features = false }
proptest.workspace = true
tempfile.workspace = true
[[bench]]
name = "heap"
harness = false
-100
View File
@@ -1,100 +0,0 @@
//! `cargo bench -p ide-heap`: whole-dump analysis and the dominator tree at a million objects.
use criterion::{Criterion, black_box, criterion_group, criterion_main};
use ide_core::CancellationToken;
use ide_heap::testing::{MiniHeap, XorShift};
use ide_heap::{AnalyzeOptions, BasicType, HeapError, HeapPhase, HeapRootKind, Store, analyze, dominators};
const CHAINS: u64 = 100_000;
const CHAIN_LEN: u64 = 5;
const NODES: u64 = CHAINS * CHAIN_LEN;
/// Every object takes one slot: node `k` at slot `2k`, its payload at `2k + 1`.
const BASE: u64 = 0x1_0000_0000;
const SLOT: u64 = 0x20;
fn node_addr(k: u64) -> u64 {
BASE + 2 * k * SLOT
}
fn payload_addr(k: u64) -> u64 {
node_addr(k) + SLOT
}
/// 100k rooted chains of five `Node { next, payload }`, each node with its own `byte[16]`. Every
/// seventh node points at the payload of the same position in the next chain instead, so that
/// payload has two owners and its own one is garbage: 1M objects in all.
fn million_objects() -> MiniHeap {
let mut heap = MiniHeap::new();
heap.class("Node", Some("java.lang.Object"), &[("next", BasicType::Object), ("payload", BasicType::Object)]);
for k in 0..NODES {
let next = if (k + 1) % CHAIN_LEN == 0 { 0 } else { node_addr(k + 1) };
let payload = if k % 7 == 0 { payload_addr((k + CHAIN_LEN) % NODES) } else { payload_addr(k) };
heap.object(node_addr(k), "Node", &[("next", next), ("payload", payload)]);
heap.prim(payload_addr(k), BasicType::Byte, 16);
if k % CHAIN_LEN == 0 {
heap.root(HeapRootKind::JniGlobal, node_addr(k));
}
}
heap
}
/// CSR of a random tree on `nodes` nodes rooted at 0 plus `extra` random edges, targets of each
/// node in scrambled order.
fn random_graph(nodes: u32, extra: u32, seed: u64) -> (Vec<u32>, Vec<u32>) {
let mut rng = XorShift::new(seed);
let mut edges: Vec<(u32, u32)> = (1..nodes).map(|v| (rng.below(v), v)).collect();
edges.extend((0..extra).map(|_| (rng.below(nodes), rng.below(nodes))));
for i in (1..edges.len()).rev() {
edges.swap(i, rng.below(i as u32 + 1) as usize);
}
let mut start = vec![0u32; nodes as usize + 1];
for &(from, _) in &edges {
start[from as usize + 1] += 1;
}
for v in 0..nodes as usize {
start[v + 1] += start[v];
}
let mut cursor = start.clone();
let mut out = vec![0u32; edges.len()];
for &(from, to) in &edges {
out[cursor[from as usize] as usize] = to;
cursor[from as usize] += 1;
}
(start, out)
}
fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
Ok(())
}
fn bench(c: &mut Criterion) {
let dir = tempfile::tempdir().expect("temp dir");
let hprof = dir.path().join("dump.hprof");
million_objects().write_to(&hprof);
let (start, out) = random_graph(1_000_000, 500_000, 0x5EED_D0D0);
let cancel = CancellationToken::new();
let opts = AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() };
let summary = analyze(&hprof, dir.path(), opts, &no_progress, &cancel).expect("analyze").summary;
assert_eq!(summary.objects, 2 * NODES, "{summary:?}");
assert_eq!(summary.unreachable_objects, NODES.div_ceil(7), "{summary:?}");
let mut g = c.benchmark_group("heap");
g.sample_size(10);
g.bench_function("index_1m_objects", |b| {
b.iter(|| {
let opts = AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() };
let index = analyze(&hprof, dir.path(), opts, &no_progress, &cancel).expect("analyze");
black_box(index.summary.objects)
})
});
g.bench_function("dominators_1m_random", |b| {
b.iter(|| {
let d = dominators(&start, &out, 0, &Store::Ram, &no_progress, &cancel).expect("dominators");
black_box(d.reachable)
})
});
g.finish();
}
criterion_group!(benches, bench);
criterion_main!(benches);
-202
View File
@@ -1,202 +0,0 @@
//! Ties the passes together: graph, dominators, shallow and retained sizes, the class table and
//! paths to GC roots, into a [`HeapIndex`].
mod classes;
mod paths;
mod retained;
use std::collections::HashMap;
use std::fs::File;
use std::path::Path;
use std::time::Instant;
use ide_core::CancellationToken;
use memmap2::Mmap;
use crate::column::Store;
use crate::dominators::{Dominators, dominators};
use crate::error::HeapError;
use crate::files::INDEX_FILES;
use crate::graph::{HeapGraph, build_graph};
use crate::index::{HeapIndex, HeapSummary, write_summary};
use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
use crate::shallow::{HistogramEntry, ShallowModel, VmLayout};
#[derive(Clone, Debug, Default)]
pub struct AnalyzeOptions {
/// The JVM's class histogram from the same stop as the dump.
pub histogram: Option<Vec<HistogramEntry>>,
/// `VM.flags` output of the JVM that wrote the dump.
pub vm_flags: Option<String>,
pub java_major: Option<u32>,
/// Keep every array in RAM and write nothing to `index_dir`.
pub in_memory: bool,
}
/// Analyzes the dump at `hprof`, writing the index columns and `summary.json` into `index_dir`
/// (which must exist and may hold the dump itself). `progress` gets every [`HeapPhase`] in order;
/// an `Err` from it, a cancel or any other error removes every index file from `index_dir` and
/// leaves the rest of the directory alone.
pub fn analyze(
hprof: &Path,
index_dir: &Path,
opts: AnalyzeOptions,
progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
cancel: &CancellationToken,
) -> Result<HeapIndex, HeapError> {
let store = if opts.in_memory { Store::Ram } else { Store::Dir(index_dir.to_path_buf()) };
let result = run(hprof, &store, opts, progress, cancel);
// `run` has dropped every column by now: Windows cannot delete a mapped file.
if result.is_err() && !matches!(store, Store::Ram) {
remove_index_files(index_dir);
}
result
}
fn run(
hprof: &Path,
store: &Store,
opts: AnalyzeOptions,
report: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
cancel: &CancellationToken,
) -> Result<HeapIndex, HeapError> {
let started = Instant::now();
let progress = Progress::new(report, cancel);
let file = File::open(hprof)?;
// SAFETY: nothing writes the dump while it is analyzed or viewed: a capture finishes writing
// it before analysis and deletes it only with the snapshot that holds this index.
let dump = unsafe { Mmap::map(&file)? };
let graph = build_graph(&dump, store, report, cancel)?;
let Dominators { idom, preorder, .. } =
dominators(&graph.out_start, &graph.out, graph.root, store, report, cancel)?;
let nodes = u64::from(graph.root) + 1;
// Seven walks over the nodes, roughly: sizes, retained, child counts, child sorting, class
// counts and the tree walk, which visits every node twice.
let mut meter = Meter::start(&progress, HeapPhase::Retained, 7 * nodes)?;
let layout = VmLayout::from_vm_flags(opts.vm_flags.as_deref().unwrap_or(""), opts.java_major);
let model = ShallowModel::new(&graph, layout, opts.histogram.as_deref(), cancel)?;
let (shallow8, retained) = retained::sizes(&graph, &model, &idom, &preorder, store, &mut meter)?;
drop(preorder);
let (kids_start, kids) = retained::children(&idom, &retained, graph.root, store, &mut meter)?;
let tree = retained::Tree { idom, shallow8, retained, kids_start, kids };
let (classes, totals) = classes::table(&graph, &tree, store, &mut meter)?;
meter.finish()?;
let mut meter = Meter::start(&progress, HeapPhase::Paths, nodes + graph.out.len() as u64)?;
let gc_parent = paths::gc_parents(&graph, store, &mut meter)?;
meter.finish()?;
progress.report(HeapPhase::Saving, 0, 1)?;
let HeapGraph {
ids,
types,
offsets,
roots,
classes: class_info,
class_slot,
thread_objects,
weak_edges_skipped,
id_size,
..
} = graph;
let summary = HeapSummary {
objects: totals.reachable_objects + totals.unreachable_objects,
reachable_objects: totals.reachable_objects,
reachable_bytes: totals.reachable_bytes,
unreachable_objects: totals.unreachable_objects,
unreachable_bytes: totals.unreachable_bytes,
classes: class_info.iter().filter(|c| c.id != 0).count() as u32,
weak_edges_skipped,
size_source: model.source,
analysis_ms: u32::try_from(started.elapsed().as_millis()).unwrap_or(u32::MAX),
};
if let Store::Dir(dir) = store {
write_summary(dir, &summary)?;
}
let mut root_kinds = HashMap::with_capacity(roots.len());
for (object, kind, serial) in roots {
root_kinds.entry(object).or_insert((kind, serial));
}
progress.report(HeapPhase::Saving, 1, 1)?;
let retained::Tree { idom, shallow8, retained, kids_start, kids } = tree;
Ok(HeapIndex {
hprof: dump,
ids,
types,
offsets,
shallow8,
retained,
idom,
kids_start,
kids,
gc_parent,
classes,
class_info,
class_slot,
roots: root_kinds,
thread_objects,
id_size,
summary,
})
}
/// Removes what an analysis may have written; a file that is not there is fine.
fn remove_index_files(dir: &Path) {
for name in INDEX_FILES {
let path = dir.join(name);
if let Err(err) = std::fs::remove_file(&path)
&& err.kind() != std::io::ErrorKind::NotFound
{
tracing::warn!("could not remove {}: {err}", path.display());
}
}
}
/// Steps of one phase: reports progress every [`CHECK_EVERY`] steps, and each loop looks at the
/// token before its first step.
pub(super) struct Meter<'a> {
progress: &'a Progress<'a>,
phase: HeapPhase,
/// An estimate; `done` is clamped to it.
total: u64,
done: u64,
next_report: u64,
}
impl<'a> Meter<'a> {
fn start(progress: &'a Progress<'a>, phase: HeapPhase, total: u64) -> Result<Self, HeapError> {
progress.report(phase, 0, total)?;
Ok(Self { progress, phase, total, done: 0, next_report: CHECK_EVERY })
}
pub(super) fn begin_loop(&self) -> Result<(), HeapError> {
self.progress.check()
}
pub(super) fn token(&self) -> &'a CancellationToken {
self.progress.token()
}
#[inline]
pub(super) fn tick(&mut self) -> Result<(), HeapError> {
self.advance(1)
}
pub(super) fn advance(&mut self, steps: u64) -> Result<(), HeapError> {
self.done += steps;
if self.done < self.next_report {
return Ok(());
}
self.next_report = self.done + CHECK_EVERY;
self.progress.report(self.phase, self.done.min(self.total), self.total)
}
fn finish(self) -> Result<(), HeapError> {
self.progress.report(self.phase, self.total, self.total)
}
}
#[cfg(test)]
mod tests;
-117
View File
@@ -1,117 +0,0 @@
//! The class table: counts and shallow sizes per type slot, retained sizes per type from a walk of
//! the dominator tree, and the reachable / unreachable totals of the summary.
use super::Meter;
use super::retained::Tree;
use crate::column::{NONE, Store};
use crate::error::HeapError;
use crate::graph::{HeapGraph, PRIM_SLOTS};
use crate::hprof::BasicType;
use crate::index::ClassStat;
use crate::names::display_name;
/// Instances and arrays only: class objects are left out.
#[derive(Default)]
pub(super) struct Totals {
pub(super) reachable_objects: u64,
pub(super) reachable_bytes: u64,
pub(super) unreachable_objects: u64,
pub(super) unreachable_bytes: u64,
}
pub(super) fn table(
graph: &HeapGraph,
tree: &Tree,
store: &Store,
meter: &mut Meter,
) -> Result<(Vec<ClassStat>, Totals), HeapError> {
let slots = graph.classes.len() + PRIM_SLOTS as usize;
let mut classes: Vec<ClassStat> = (0..slots as u32)
.map(|slot| ClassStat { name: slot_name(graph, slot), count: 0, shallow: 0, retained: 0, unreachable_count: 0 })
.collect();
let mut totals = Totals::default();
meter.begin_loop()?;
for v in 0..graph.root as usize {
meter.tick()?;
let slot = graph.types[v];
let bytes = u64::from(tree.shallow8[v]) * 8;
let stat = &mut classes[slot as usize];
let instance = slot != graph.class_slot;
if tree.idom[v] == NONE {
stat.unreachable_count += 1;
if instance {
totals.unreachable_objects += 1;
totals.unreachable_bytes += bytes;
}
} else {
stat.count += 1;
stat.shallow += bytes;
if instance {
totals.reachable_objects += 1;
totals.reachable_bytes += bytes;
}
}
}
retained_by_type(graph, tree, &mut classes, store, meter)?;
Ok((classes, totals))
}
/// Adds to each type the retained size of its instances that have no instance of the same type
/// above them in the dominator tree. The walk keeps no stack: it goes up through `idom` and
/// resumes a node's children from `cursor`, while `active[t]` counts the instances of type `t` on
/// the path from the root.
fn retained_by_type(
graph: &HeapGraph,
tree: &Tree,
classes: &mut [ClassStat],
store: &Store,
meter: &mut Meter,
) -> Result<(), HeapError> {
let root = graph.root;
let mut cursor = store.scratch::<u32>(root as usize + 1, 0)?;
let mut active = vec![0u32; classes.len()];
cursor[root as usize] = tree.kids_start[root as usize];
let mut v = root;
meter.begin_loop()?;
loop {
meter.tick()?;
let next = cursor[v as usize];
if next < tree.kids_start[v as usize + 1] {
cursor[v as usize] = next + 1;
let child = tree.kids[next as usize];
let slot = graph.types[child as usize] as usize;
if active[slot] == 0 {
classes[slot].retained += tree.retained[child as usize];
}
active[slot] += 1;
cursor[child as usize] = tree.kids_start[child as usize];
v = child;
} else if v == root {
return Ok(());
} else {
active[graph.types[v as usize] as usize] -= 1;
v = tree.idom[v as usize];
}
}
}
fn slot_name(graph: &HeapGraph, slot: u32) -> String {
match graph.classes.get(slot as usize) {
Some(class) => display_name(&class.name),
None => graph.prim_type(slot).map_or_else(String::new, |ty| prim_array_name(ty).to_owned()),
}
}
fn prim_array_name(ty: BasicType) -> &'static str {
match ty {
BasicType::Object => "java.lang.Object[]",
BasicType::Boolean => "boolean[]",
BasicType::Char => "char[]",
BasicType::Float => "float[]",
BasicType::Double => "double[]",
BasicType::Byte => "byte[]",
BasicType::Short => "short[]",
BasicType::Int => "int[]",
BasicType::Long => "long[]",
}
}
-32
View File
@@ -1,32 +0,0 @@
//! Parents on shortest paths from the GC roots, by breadth-first search over strong edges.
use super::Meter;
use crate::column::{Column, NONE, Store};
use crate::error::HeapError;
use crate::files::GC_PARENT_FILE;
use crate::graph::HeapGraph;
pub(super) fn gc_parents(graph: &HeapGraph, store: &Store, meter: &mut Meter) -> Result<Column<u32>, HeapError> {
let root = graph.root;
let nodes = root as usize + 1;
let mut parent = store.column::<u32>(GC_PARENT_FILE, nodes, NONE)?;
let mut queue = store.scratch::<u32>(nodes, 0)?;
parent[root as usize] = root;
queue[0] = root;
let (mut head, mut tail) = (0, 1);
meter.begin_loop()?;
while head < tail {
meter.tick()?;
let v = queue[head];
head += 1;
for &w in graph.out_edges(v) {
meter.tick()?;
if parent[w as usize] == NONE {
parent[w as usize] = v;
queue[tail] = w;
tail += 1;
}
}
}
Ok(parent)
}
-209
View File
@@ -1,209 +0,0 @@
//! Shallow and retained sizes, and the dominator tree as child lists sorted by retained size.
use std::cmp::Reverse;
use super::Meter;
use crate::column::{Column, NONE, Store};
use crate::error::HeapError;
use crate::files::{KIDS_FILE, KIDS_START_FILE, RETAINED_FILE, SHALLOW8_FILE};
use crate::graph::{HeapGraph, accumulate};
use crate::progress::CHECK_EVERY;
use crate::shallow::ShallowModel;
/// The dominator tree with sizes; see [`crate::HeapIndex`] for each column.
pub(super) struct Tree {
pub(super) idom: Column<u32>,
pub(super) shallow8: Column<u32>,
pub(super) retained: Column<u64>,
pub(super) kids_start: Column<u32>,
pub(super) kids: Column<u32>,
}
/// `(shallow8, retained)` of every node, the root included. `preorder` is the DFS preorder of the
/// reachable nodes, from the root.
pub(super) fn sizes(
graph: &HeapGraph,
model: &ShallowModel,
idom: &[u32],
preorder: &[u32],
store: &Store,
meter: &mut Meter,
) -> Result<(Column<u32>, Column<u64>), HeapError> {
let nodes = idom.len();
let mut shallow8 = store.column::<u32>(SHALLOW8_FILE, nodes, 0)?;
let mut retained = store.column::<u64>(RETAINED_FILE, nodes, 0)?;
meter.begin_loop()?;
for v in 0..graph.root {
meter.tick()?;
let units = u32::try_from(model.size_of(graph, v).div_ceil(8)).unwrap_or(u32::MAX);
shallow8[v as usize] = units;
if idom[v as usize] != NONE {
retained[v as usize] = u64::from(units) * 8;
}
}
// A dominator is a DFS ancestor, so in reverse preorder every node is complete before it is
// added to its dominator.
meter.begin_loop()?;
for &v in preorder.iter().skip(1).rev() {
meter.tick()?;
let own = retained[v as usize];
retained[idom[v as usize] as usize] += own;
}
Ok((shallow8, retained))
}
/// `(kids_start, kids)`: the children of every reachable node in the dominator tree, as CSR.
pub(super) fn children(
idom: &[u32],
retained: &[u64],
root: u32,
store: &Store,
meter: &mut Meter,
) -> Result<(Column<u32>, Column<u32>), HeapError> {
let nodes = idom.len();
// Counted into `starts[d + 1]`; filled through `starts[d]` as a cursor, which leaves it at d's
// end until the column is shifted one slot.
let mut starts = store.column::<u32>(KIDS_START_FILE, nodes + 1, 0)?;
let mut longest = 0;
meter.begin_loop()?;
for (v, &d) in idom.iter().enumerate() {
meter.tick()?;
if d != NONE && v != root as usize {
let count = &mut starts[d as usize + 1];
*count += 1;
longest = longest.max(*count);
}
}
let total = accumulate(&mut starts, meter.token())?;
let mut kids = store.column::<u32>(KIDS_FILE, total as usize, 0)?;
meter.begin_loop()?;
for (v, &d) in idom.iter().enumerate() {
meter.tick()?;
if d != NONE && v != root as usize {
let cursor = &mut starts[d as usize];
kids[*cursor as usize] = v as u32;
*cursor += 1;
}
}
starts.copy_within(0..nodes, 1);
starts[0] = 0;
sort_children(&mut kids, &starts, retained, longest as usize, CHECK_EVERY as usize, store, meter)?;
Ok((starts, kids))
}
/// Sorts each child list by retained size descending, then by node. A list longer than `run` is
/// sorted in runs of `run` that are then merged, so no single step takes longer than one run.
fn sort_children(
kids: &mut [u32],
starts: &[u32],
retained: &[u64],
longest: usize,
run: usize,
store: &Store,
meter: &mut Meter,
) -> Result<(), HeapError> {
let key = |&k: &u32| (Reverse(retained[k as usize]), k);
let mut buffer = if longest > run { store.scratch::<u32>(longest, 0)? } else { Column::ram(0, 0) };
meter.begin_loop()?;
for v in 0..starts.len() - 1 {
meter.tick()?;
let list = &mut kids[starts[v] as usize..starts[v + 1] as usize];
if list.len() <= run {
list.sort_unstable_by_key(key);
meter.advance(list.len() as u64)?;
continue;
}
for chunk in list.chunks_mut(run) {
meter.begin_loop()?;
chunk.sort_unstable_by_key(key);
meter.advance(chunk.len() as u64)?;
}
let len = list.len();
let (mut from, mut to) = (list, &mut buffer[..len]);
let mut in_buffer = false;
let mut width = run;
while width < len {
meter.begin_loop()?;
for start in (0..len).step_by(2 * width) {
let mid = (start + width).min(len);
let end = (start + 2 * width).min(len);
merge(&from[start..mid], &from[mid..end], &mut to[start..end], &key, meter)?;
}
std::mem::swap(&mut from, &mut to);
in_buffer = !in_buffer;
width *= 2;
}
if in_buffer {
to.copy_from_slice(from);
}
}
Ok(())
}
fn merge<K: Ord>(
left: &[u32],
right: &[u32],
out: &mut [u32],
key: &impl Fn(&u32) -> K,
meter: &mut Meter,
) -> Result<(), HeapError> {
let (mut i, mut j) = (0, 0);
for slot in out.iter_mut() {
meter.tick()?;
let take_left = j == right.len() || (i < left.len() && key(&left[i]) <= key(&right[j]));
if take_left {
*slot = left[i];
i += 1;
} else {
*slot = right[j];
j += 1;
}
}
Ok(())
}
#[cfg(test)]
mod tests {
use ide_core::CancellationToken;
use super::*;
use crate::error::HeapError;
use crate::progress::{HeapPhase, Progress};
use crate::testing::XorShift;
fn sorted_with_run(lists: &[Vec<u32>], retained: &[u64], run: usize) -> Vec<u32> {
let report = |_, _, _| Ok::<(), HeapError>(());
let cancel = CancellationToken::new();
let progress = Progress::new(&report, &cancel);
let mut meter = Meter::start(&progress, HeapPhase::Retained, 1).unwrap();
let mut starts = vec![0u32];
for list in lists {
starts.push(starts.last().unwrap() + list.len() as u32);
}
let mut kids: Vec<u32> = lists.concat();
let longest = lists.iter().map(Vec::len).max().unwrap_or(0);
sort_children(&mut kids, &starts, retained, longest, run, &Store::Ram, &mut meter).unwrap();
kids
}
#[test]
fn long_child_lists_are_merged_from_sorted_runs() {
let mut rng = XorShift::new(7);
let retained: Vec<u64> = (0..500).map(|_| u64::from(rng.below(40))).collect();
let mut nodes: Vec<u32> = (0..500).collect();
for i in (1..nodes.len()).rev() {
nodes.swap(i, rng.below(i as u32 + 1) as usize);
}
// Lists below, at and above the run length, and one that ends on a partial run.
let lists = vec![nodes[..3].to_vec(), nodes[3..7].to_vec(), nodes[7..400].to_vec(), nodes[400..].to_vec()];
for run in [1, 4, 7, 64, 1000] {
let mut expected = Vec::new();
for list in &lists {
let mut list = list.clone();
list.sort_by_key(|&k| (Reverse(retained[k as usize]), k));
expected.extend(list);
}
assert_eq!(sorted_with_run(&lists, &retained, run), expected, "run {run}");
}
}
}
-265
View File
@@ -1,265 +0,0 @@
use std::cell::Cell;
use std::collections::BTreeSet;
use std::path::PathBuf;
use super::*;
use crate::column::{Column, NONE};
use crate::files::INDEX_FILES;
use crate::hprof::{BasicType, HeapRootKind};
use crate::index::{ClassStat, HeapSummary};
use crate::shallow::SizeSource;
use crate::testing::{MiniHeap, sample};
const DUMP: &str = "dump.hprof";
const ROOT: Option<&str> = Some("java.lang.Object");
const NODE_FIELDS: [(&str, BasicType); 2] = [("next", BasicType::Object), ("v", BasicType::Long)];
fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
Ok(())
}
fn in_memory() -> AnalyzeOptions {
AnalyzeOptions { in_memory: true, ..AnalyzeOptions::default() }
}
/// A temp dir holding `heap` as `dump.hprof`, the way a capture lays out its snapshot dir.
fn dump_dir(heap: &MiniHeap) -> (tempfile::TempDir, PathBuf) {
let dir = tempfile::tempdir().unwrap();
let dump = dir.path().join(DUMP);
heap.write_to(&dump);
(dir, dump)
}
fn analyze_with(heap: &MiniHeap, opts: AnalyzeOptions) -> HeapIndex {
let (dir, dump) = dump_dir(heap);
analyze(&dump, dir.path(), opts, &no_progress, &CancellationToken::new()).unwrap()
}
fn file_names(dir: &Path) -> BTreeSet<String> {
std::fs::read_dir(dir).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect()
}
fn node(index: &HeapIndex, addr: u64) -> u32 {
index.ids.rank(addr).unwrap_or_else(|| panic!("{addr:#x} is not in the dump"))
}
fn shallow(index: &HeapIndex, addr: u64) -> u64 {
u64::from(index.shallow8[node(index, addr) as usize]) * 8
}
fn retained(index: &HeapIndex, addr: u64) -> u64 {
index.retained[node(index, addr) as usize]
}
fn idom(index: &HeapIndex, addr: u64) -> u32 {
index.idom[node(index, addr) as usize]
}
fn class<'a>(index: &'a HeapIndex, name: &str) -> &'a ClassStat {
let mut rows = index.classes.iter().filter(|c| c.name == name);
let row = rows.next().unwrap_or_else(|| panic!("no class {name}"));
assert!(rows.next().is_none(), "two classes named {name}");
row
}
fn stat(c: &ClassStat) -> (u64, u64, u64, u64) {
(c.count, c.shallow, c.retained, c.unreachable_count)
}
fn kids_of(index: &HeapIndex, v: u32) -> &[u32] {
&index.kids[index.kids_start[v as usize] as usize..index.kids_start[v as usize + 1] as usize]
}
const H: u64 = 0x1000;
const N1: u64 = 0x1100;
const N2: u64 = 0x1200;
const N3: u64 = 0x1300;
const L: u64 = 0x1400;
const R: u64 = 0x1500;
const W: u64 = 0x1600;
const N4: u64 = 0x1700;
#[test]
fn sample_retained_sizes() {
let index = analyze_with(&sample(), in_memory());
let shallows: Vec<u64> = [H, N1, L, W, R].iter().map(|&a| shallow(&index, a)).collect();
assert_eq!(shallows, [24, 24, 32, 24, 32]);
let retained_sizes: Vec<u64> = [L, N3, N1, N2, H, W].iter().map(|&a| retained(&index, a)).collect();
assert_eq!(retained_sizes, [32, 56, 24, 24, 72, 24]);
let root = index.root();
assert_eq!(
[idom(&index, N1), idom(&index, N2), idom(&index, N3), idom(&index, L)],
[node(&index, H), node(&index, H), root, node(&index, N3)]
);
assert_eq!((idom(&index, R), idom(&index, N4)), (NONE, NONE));
assert_eq!((retained(&index, R), retained(&index, N4)), (0, 0));
// Children by retained size descending, ties by node.
assert_eq!(kids_of(&index, node(&index, H)), [node(&index, N1), node(&index, N2)]);
let top = kids_of(&index, root);
assert_eq!(top[..2], [node(&index, H), node(&index, N3)]);
assert!(top.windows(2).all(|p| (index.retained[p[0] as usize], p[1]) > (index.retained[p[1] as usize], p[0])));
assert_eq!(index.retained[root as usize], top.iter().map(|&k| index.retained[k as usize]).sum::<u64>());
}
#[test]
fn sample_class_table() {
let index = analyze_with(&sample(), in_memory());
assert_eq!(stat(class(&index, "Node")), (3, 72, 104, 1));
assert_eq!(stat(class(&index, "Holder")), (1, 24, 72, 0));
assert_eq!(stat(class(&index, "long[]")), (1, 32, 32, 0));
assert_eq!(stat(class(&index, "java.lang.ref.WeakReference")), (1, 24, 24, 0));
let objects = class(&index, "java.lang.Object[]");
assert_eq!((objects.count, objects.unreachable_count), (0, 1));
// Indexed by type slot, primitive array slots included.
assert_eq!(index.classes.len(), index.class_info.len() + crate::graph::PRIM_SLOTS as usize);
let slot = index.types[node(&index, H) as usize] as usize;
assert_eq!(index.classes[slot].name, "Holder");
assert_eq!(index.class_info[slot].name, "Holder");
}
#[test]
fn sample_summary() {
let index = analyze_with(&sample(), in_memory());
let s = &index.summary;
assert_eq!(
(s.reachable_objects, s.reachable_bytes, s.unreachable_objects, s.unreachable_bytes, s.weak_edges_skipped),
(6, 152, 2, 56, 1)
);
assert_eq!(s.objects, 8);
assert_eq!(s.classes, 7);
assert_eq!(s.size_source, SizeSource::Layout);
}
#[test]
fn sample_gc_parents() {
let index = analyze_with(&sample(), in_memory());
let parent = |addr| index.gc_parent[node(&index, addr) as usize];
let root = index.root();
assert_eq!(index.gc_parent[root as usize], root);
assert_eq!([parent(H), parent(N3), parent(W)], [root; 3]);
assert_eq!([parent(N1), parent(L)], [node(&index, H), node(&index, N3)]);
assert_eq!((parent(R), parent(N4)), (NONE, NONE));
assert_eq!(index.roots[&node(&index, N3)], (HeapRootKind::JavaFrame, Some(1)));
}
#[test]
fn cycle_is_retained_once() {
let mut heap = MiniHeap::new();
heap.class("Node", ROOT, &NODE_FIELDS)
.object(0xA000, "Node", &[("next", 0xB000)])
.object(0xB000, "Node", &[("next", 0xA000)])
.root(HeapRootKind::JniGlobal, 0xA000);
let index = analyze_with(&heap, in_memory());
assert_eq!((retained(&index, 0xA000), retained(&index, 0xB000)), (48, 24));
assert_eq!(class(&index, "Node").retained, 48);
}
#[test]
fn deep_chain_retained_by_class() {
// A small stack proves no pass recurses along the chain.
std::thread::Builder::new()
.stack_size(256 << 10)
.spawn(|| {
const NODES: u64 = 1_000_000;
let addr = |i: u64| 0x10_0000 + i * 0x100;
let mut heap = MiniHeap::new();
heap.class("Node", ROOT, &NODE_FIELDS);
for i in 0..NODES {
let next = if i + 1 < NODES { addr(i + 1) } else { 0 };
heap.object(addr(i), "Node", &[("next", next)]);
}
heap.root(HeapRootKind::JniGlobal, addr(0));
let index = analyze_with(&heap, in_memory());
assert_eq!(retained(&index, addr(0)), 24_000_000);
assert_eq!(retained(&index, addr(NODES - 1)), 24);
assert_eq!(class(&index, "Node").retained, 24_000_000);
assert_eq!(index.summary.reachable_objects, NODES);
})
.unwrap()
.join()
.unwrap();
}
#[test]
fn histogram_sizes_flow_into_retained() {
let histogram = vec![HistogramEntry { name: "Node".to_owned(), instances: 3, bytes: 96 }];
let index = analyze_with(&sample(), AnalyzeOptions { histogram: Some(histogram), ..in_memory() });
assert_eq!(shallow(&index, N3), 32);
assert_eq!(retained(&index, N3), 64);
assert_eq!(index.summary.size_source, SizeSource::Jvm);
}
#[test]
fn vm_flags_of_an_unknown_jdk_set_the_layout() {
// Without compressed oops a Node is 12 + 8 + 8 = 28 → 32.
let opts = AnalyzeOptions { vm_flags: Some("-XX:MaxHeapSize=42949672960".to_owned()), ..in_memory() };
let index = analyze_with(&sample(), opts);
assert_eq!(shallow(&index, N4), 32);
}
#[test]
fn cancel_stops_analysis() {
let (dir, dump) = dump_dir(&sample());
let cancel = CancellationToken::new();
let phases = Cell::new(Vec::new());
let progress = |phase, _, _| {
let mut seen = phases.take();
seen.push(phase);
phases.set(seen);
if phase == HeapPhase::Dominators {
cancel.cancel();
}
Ok(())
};
let result = analyze(&dump, dir.path(), AnalyzeOptions::default(), &progress, &cancel);
assert!(matches!(result, Err(HeapError::Cancelled)), "{:?}", result.err());
assert_eq!(phases.take().last(), Some(&HeapPhase::Dominators), "stops at the first check");
// The dump the capture analyzes in place stays; every file the analysis wrote is gone.
assert_eq!(file_names(dir.path()), BTreeSet::from([DUMP.to_owned()]));
}
#[test]
fn progress_error_stops_analysis_and_removes_its_files() {
let (dir, dump) = dump_dir(&sample());
// The last report, once every index file is written.
let progress = |phase, done, _| match (phase, done) {
(HeapPhase::Saving, 1) => Err(HeapError::NotEnoughDiskSpace { needed: 2, available: 1 }),
_ => Ok(()),
};
let result = analyze(&dump, dir.path(), AnalyzeOptions::default(), &progress, &CancellationToken::new());
assert!(matches!(result, Err(HeapError::NotEnoughDiskSpace { .. })), "{:?}", result.err());
assert_eq!(file_names(dir.path()), BTreeSet::from([DUMP.to_owned()]));
}
#[test]
fn writes_index_files() {
let (dir, dump) = dump_dir(&sample());
let index = analyze(&dump, dir.path(), AnalyzeOptions::default(), &no_progress, &CancellationToken::new()).unwrap();
let names = file_names(dir.path());
for name in [
"types.u32",
"shallow8.u32",
"retained.u64",
"idom.u32",
"kids_start.u32",
"kids.u32",
"gc_parent.u32",
"offsets.u64",
"summary.json",
] {
assert!(names.contains(name), "{name} missing from {names:?}");
}
assert!(names.iter().any(|n| n.starts_with("ids.")), "{names:?}");
// Nothing but the index files and the dump: scratch arrays are gone.
let unexpected: Vec<_> = names.iter().filter(|n| *n != DUMP && !INDEX_FILES.contains(&n.as_str())).collect();
assert!(unexpected.is_empty(), "{unexpected:?}");
let summary: HeapSummary =
serde_json::from_slice(&std::fs::read(dir.path().join("summary.json")).unwrap()).unwrap();
assert_eq!(summary, index.summary);
drop(index);
let retained = Column::<u64>::open(&dir.path().join("retained.u64")).unwrap();
let in_ram = analyze_with(&sample(), in_memory());
assert_eq!(&*retained, &*in_ram.retained);
}
-306
View File
@@ -1,306 +0,0 @@
//! Fixed-width arrays that live in RAM or in memory-mapped files, so the analysis arrays of a
//! large heap do not count against the process's anonymous memory.
use std::fs::{File, OpenOptions};
use std::io;
use std::marker::PhantomData;
use std::mem::size_of;
use std::ops::{Deref, DerefMut};
use std::path::{Path, PathBuf};
use memmap2::{Mmap, MmapMut};
/// Index value meaning "no object" in every `u32` column.
pub const NONE: u32 = u32::MAX;
/// # Safety
/// Every bit pattern of `Self` is a valid value and `Self` has no padding, so a mapped file's
/// bytes can be viewed as `[Self]` and a file can be written from one.
pub unsafe trait Pod: Copy + 'static {}
unsafe impl Pod for u8 {}
unsafe impl Pod for u32 {}
unsafe impl Pod for u64 {}
enum Backing<T> {
Ram(Vec<T>),
Map(MmapMut),
ReadOnly(Mmap),
}
/// A fixed-length array of `T`. File contents use the machine's byte order: the arrays are a
/// cache for this machine and are never moved to another one.
pub struct Column<T: Pod> {
backing: Backing<T>,
/// Scratch file to delete on drop where it could not be unlinked while mapped.
delete_on_drop: Option<PathBuf>,
_marker: PhantomData<T>,
}
fn byte_len<T: Pod>(len: usize) -> io::Result<usize> {
len.checked_mul(size_of::<T>())
.filter(|&bytes| bytes <= isize::MAX as usize)
.ok_or_else(|| io::Error::new(io::ErrorKind::InvalidInput, "column is too long"))
}
fn is_zero<T: Pod>(value: &T) -> bool {
// SAFETY: `Pod` types have no padding, so all `size_of::<T>()` bytes are initialized.
let bytes = unsafe { std::slice::from_raw_parts((value as *const T).cast::<u8>(), size_of::<T>()) };
bytes.iter().all(|&b| b == 0)
}
impl<T: Pod> Column<T> {
fn new(backing: Backing<T>, delete_on_drop: Option<PathBuf>) -> Self {
Self { backing, delete_on_drop, _marker: PhantomData }
}
pub fn ram(len: usize, fill: T) -> Self {
Self::new(Backing::Ram(vec![fill; len]), None)
}
/// Creates (or truncates) `path` and maps it; the file stays after the column is dropped.
pub fn file(path: &Path, len: usize, fill: T) -> io::Result<Self> {
let bytes = byte_len::<T>(len)?;
let file = OpenOptions::new().read(true).write(true).create(true).truncate(true).open(path)?;
match Self::map_new(&file, len, bytes, fill) {
Ok(column) => Ok(column),
Err(err) => {
drop(file);
let _ = std::fs::remove_file(path);
Err(err)
}
}
}
/// A temporary column in `dir` that never outlives the process. On unix the file is unlinked
/// right after mapping, so even a crash leaves nothing behind; elsewhere (Windows cannot delete
/// a mapped file) it is deleted on drop.
pub fn scratch(dir: &Path, len: usize, fill: T) -> io::Result<Self> {
let bytes = byte_len::<T>(len)?;
if bytes == 0 {
return Ok(Self::ram(0, fill));
}
let path = dir.join(format!("scratch-{}.tmp", uuid::Uuid::new_v4().simple()));
let file = OpenOptions::new().read(true).write(true).create_new(true).open(&path)?;
let mut column = match Self::map_new(&file, len, bytes, fill) {
Ok(column) => column,
Err(err) => {
drop(file);
let _ = std::fs::remove_file(&path);
return Err(err);
}
};
// If the unlink fails the drop-time delete is the fallback, so the file is never left behind.
if !cfg!(unix) || std::fs::remove_file(&path).is_err() {
column.delete_on_drop = Some(path);
}
Ok(column)
}
/// Maps an existing file read-only; writing through the column panics.
pub fn open(path: &Path) -> io::Result<Self> {
let file = File::open(path)?;
let bytes = file.metadata()?.len();
if bytes % size_of::<T>() as u64 != 0 {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!("{} is {bytes} bytes, not a multiple of {}", path.display(), size_of::<T>()),
));
}
if bytes == 0 {
return Ok(Self::ram(0, zero_value()));
}
// SAFETY: the file is private to the snapshot directory; nothing truncates it while mapped.
let map = unsafe { Mmap::map(&file)? };
Ok(Self::new(Backing::ReadOnly(map), None))
}
fn map_new(file: &File, len: usize, bytes: usize, fill: T) -> io::Result<Self> {
if bytes == 0 {
return Ok(Self::ram(0, fill));
}
file.set_len(bytes as u64)?;
// SAFETY: as in `open`; the file was just created by this process.
let map = unsafe { MmapMut::map_mut(file)? };
let mut column = Self::new(Backing::Map(map), None);
// A fresh file reads as zeros, and writing a zero fill would fault in every page.
if !is_zero(&fill) {
debug_assert_eq!(column.len(), len);
column.fill(fill);
}
Ok(column)
}
}
fn zero_value<T: Pod>() -> T {
// SAFETY: every bit pattern of a `Pod` type is a valid value.
unsafe { std::mem::zeroed() }
}
impl<T: Pod> Deref for Column<T> {
type Target = [T];
fn deref(&self) -> &[T] {
match &self.backing {
Backing::Ram(v) => v,
// SAFETY: maps are page-aligned, `T` is `Pod` and the length is a multiple of its width.
Backing::Map(m) => unsafe { std::slice::from_raw_parts(m.as_ptr().cast(), m.len() / size_of::<T>()) },
Backing::ReadOnly(m) => unsafe { std::slice::from_raw_parts(m.as_ptr().cast(), m.len() / size_of::<T>()) },
}
}
}
impl<T: Pod> DerefMut for Column<T> {
fn deref_mut(&mut self) -> &mut [T] {
match &mut self.backing {
Backing::Ram(v) => v,
// SAFETY: as in `deref`; `&mut self` makes the access exclusive.
Backing::Map(m) => unsafe {
std::slice::from_raw_parts_mut(m.as_mut_ptr().cast(), m.len() / size_of::<T>())
},
Backing::ReadOnly(_) => panic!("column opened from a file is read-only"),
}
}
}
impl<T: Pod> Drop for Column<T> {
fn drop(&mut self) {
if let Some(path) = self.delete_on_drop.take() {
// Unmap before deleting: Windows refuses to delete a mapped file.
self.backing = Backing::Ram(Vec::new());
let _ = std::fs::remove_file(path);
}
}
}
/// Where a computation puts its arrays: result columns are named files in `Dir`, temporary arrays
/// are scratch columns in the same directory.
pub enum Store {
Ram,
Dir(PathBuf),
}
impl Store {
/// `name` is the whole file name (`types.u32`); it is used as given.
pub fn column<T: Pod>(&self, name: &str, len: usize, fill: T) -> io::Result<Column<T>> {
match self {
Store::Ram => Ok(Column::ram(len, fill)),
Store::Dir(dir) => Column::file(&dir.join(name), len, fill),
}
}
pub fn scratch<T: Pod>(&self, len: usize, fill: T) -> io::Result<Column<T>> {
match self {
Store::Ram => Ok(Column::ram(len, fill)),
Store::Dir(dir) => Column::scratch(dir, len, fill),
}
}
}
#[cfg(test)]
mod tests {
use super::*;
fn dir_is_empty(dir: &Path) -> bool {
std::fs::read_dir(dir).unwrap().next().is_none()
}
#[test]
fn file_column_round_trips() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("x.u32");
{
let mut col = Column::<u32>::file(&path, 4, 7).unwrap();
assert_eq!(&*col, &[7, 7, 7, 7]);
col.copy_from_slice(&[1, 2, 3, 4]);
}
let col = Column::<u32>::open(&path).unwrap();
assert_eq!(&*col, &[1, 2, 3, 4]);
}
#[test]
fn scratch_column_leaves_no_file() {
let dir = tempfile::tempdir().unwrap();
{
let mut col = Column::<u64>::scratch(dir.path(), 1024, 9).unwrap();
col[1023] = 5;
assert_eq!((col[0], col[1023]), (9, 5));
// Windows cannot delete a mapped file, so only unix unlinks while the map is alive.
#[cfg(unix)]
assert!(dir_is_empty(dir.path()));
}
assert!(dir_is_empty(dir.path()));
}
#[test]
fn zero_fill_and_non_zero_fill() {
let dir = tempfile::tempdir().unwrap();
let zeros = Column::<u64>::file(&dir.path().join("z.u64"), 3000, 0).unwrap();
assert!(zeros.iter().all(|&v| v == 0));
let ones = Column::<u8>::file(&dir.path().join("o.u8"), 10_000, 0xAB).unwrap();
assert!(ones.iter().all(|&v| v == 0xAB));
let ram = Column::<u32>::ram(5, NONE);
assert_eq!(&*ram, &[NONE; 5]);
}
#[test]
fn empty_columns_work_everywhere() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("e.u32");
assert_eq!(Column::<u32>::ram(0, 1).len(), 0);
assert_eq!(Column::<u32>::file(&path, 0, 1).unwrap().len(), 0);
assert_eq!(Column::<u32>::open(&path).unwrap().len(), 0);
assert_eq!(Column::<u32>::scratch(dir.path(), 0, 1).unwrap().len(), 0);
}
#[test]
fn open_rejects_a_length_that_is_not_a_multiple_of_the_width() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("odd.u32");
std::fs::write(&path, [0u8; 6]).unwrap();
let err = Column::<u32>::open(&path).err().unwrap();
assert_eq!(err.kind(), io::ErrorKind::InvalidData);
}
#[test]
fn file_rejects_a_byte_length_that_overflows() {
let dir = tempfile::tempdir().unwrap();
let err = Column::<u64>::file(&dir.path().join("big.u64"), usize::MAX, 0).err().unwrap();
assert_eq!(err.kind(), io::ErrorKind::InvalidInput);
assert!(dir_is_empty(dir.path()));
}
#[test]
#[should_panic(expected = "read-only")]
fn opened_columns_are_read_only() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("r.u32");
drop(Column::<u32>::file(&path, 2, 0).unwrap());
let mut col = Column::<u32>::open(&path).unwrap();
col[0] = 1;
}
#[test]
fn store_names_files_exactly_as_given() {
let dir = tempfile::tempdir().unwrap();
let store = Store::Dir(dir.path().to_path_buf());
let mut col = store.column::<u32>("types.u32", 3, 0).unwrap();
col[2] = 8;
drop(col);
let names: Vec<_> =
std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
assert_eq!(names, ["types.u32"]);
assert_eq!(&*Column::<u32>::open(&dir.path().join("types.u32")).unwrap(), &[0, 0, 8]);
}
#[test]
fn store_scratch_is_anonymous_and_ram_store_touches_no_disk() {
let dir = tempfile::tempdir().unwrap();
let store = Store::Dir(dir.path().to_path_buf());
drop(store.scratch::<u32>(16, 1).unwrap());
assert!(dir_is_empty(dir.path()));
let ram = Store::Ram.column::<u8>("ignored.u8", 4, 2).unwrap();
assert_eq!(&*ram, &[2; 4]);
assert_eq!(&*Store::Ram.scratch::<u8>(2, 3).unwrap(), &[3, 3]);
}
}
-59
View File
@@ -1,59 +0,0 @@
//! Class-by-class differences between two snapshots.
use std::collections::HashMap;
use serde::{Deserialize, Serialize};
use crate::index::HeapIndex;
/// One class name in two snapshots; a side without the name has zeros.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapClassDiff {
pub name: String,
pub base_count: u64,
pub count: u64,
pub base_shallow: u64,
pub shallow: u64,
pub base_retained: u64,
pub retained: u64,
/// Several classes have this name on one side or both, so the sides cannot be matched: each
/// side shows the sum over its classes, and there is no difference to show.
pub ambiguous: bool,
}
/// Joined by class name, the only key two dumps share. By the change in retained size
/// descending (none for an ambiguous name), then by name.
pub fn compare(base: &HeapIndex, current: &HeapIndex) -> Vec<HeapClassDiff> {
let mut by_name: HashMap<String, HeapClassDiff> = HashMap::new();
for (index, is_base) in [(base, true), (current, false)] {
for row in index.class_rows() {
let diff = by_name.entry(row.name).or_insert_with_key(|name| HeapClassDiff {
name: name.clone(),
base_count: 0,
count: 0,
base_shallow: 0,
shallow: 0,
base_retained: 0,
retained: 0,
ambiguous: false,
});
let (count, shallow, retained) = if is_base {
(&mut diff.base_count, &mut diff.base_shallow, &mut diff.base_retained)
} else {
(&mut diff.count, &mut diff.shallow, &mut diff.retained)
};
*count = count.saturating_add(row.count);
*shallow = shallow.saturating_add(row.shallow);
*retained = retained.saturating_add(row.retained);
diff.ambiguous |= row.ambiguous;
}
}
let change = |d: &HeapClassDiff| if d.ambiguous { 0 } else { d.retained.abs_diff(d.base_retained) };
let mut diffs: Vec<HeapClassDiff> = by_name.into_values().collect();
diffs.sort_by(|a, b| change(b).cmp(&change(a)).then_with(|| a.name.cmp(&b.name)));
diffs
}
#[cfg(test)]
mod tests;
-78
View File
@@ -1,78 +0,0 @@
use super::*;
use crate::hprof::HeapRootKind;
use crate::test_index::analyzed;
use crate::testing::{MiniHeap, sample, sample_with_two_more_nodes};
fn diff<'a>(diffs: &'a [HeapClassDiff], name: &str) -> &'a HeapClassDiff {
let mut rows = diffs.iter().filter(|d| d.name == name);
let row = rows.next().unwrap_or_else(|| panic!("no diff for {name}"));
assert!(rows.next().is_none(), "two diffs for {name}");
row
}
fn sort_key(d: &HeapClassDiff) -> u64 {
if d.ambiguous { 0 } else { d.retained.abs_diff(d.base_retained) }
}
fn assert_sorted(diffs: &[HeapClassDiff]) {
assert!(diffs.windows(2).all(|p| (sort_key(&p[1]), &p[0].name) < (sort_key(&p[0]), &p[1].name)), "{diffs:#?}");
}
#[test]
fn compare_counts_by_class() {
let base = analyzed(&sample());
let mut current = sample_with_two_more_nodes();
current
.class("Extra", Some("java.lang.Object"), &[])
.object(0x4000, "Extra", &[])
.root(HeapRootKind::JniGlobal, 0x4000);
let diffs = compare(&base, &analyzed(&current));
let node = diff(&diffs, "Node");
assert_eq!((node.base_count, node.count), (3, 5));
assert_eq!(node.shallow - node.base_shallow, 48);
assert_eq!((node.base_retained, node.retained), (104, 152));
assert!(!node.ambiguous);
let extra = diff(&diffs, "Extra");
assert_eq!((extra.base_count, extra.base_shallow, extra.base_retained, extra.count), (0, 0, 0, 1));
assert_eq!(diffs[0].name, "Node");
let holder = diff(&diffs, "Holder");
assert_eq!((holder.base_count, holder.count, holder.base_retained, holder.retained), (1, 1, 72, 72));
assert_sorted(&diffs);
// A class only in the base snapshot.
let gone = compare(&analyzed(&current), &base);
let extra = diff(&gone, "Extra");
assert_eq!((extra.base_count, extra.count, extra.shallow, extra.retained), (1, 0, 0, 0));
assert_sorted(&gone);
}
fn two_foos(extra: bool) -> MiniHeap {
let mut heap = sample();
heap.class("Foo", Some("java.lang.Object"), &[])
.object(0x3000, "Foo", &[])
.class("Foo", Some("java.lang.Object"), &[])
.object(0x3100, "Foo", &[]);
if extra {
heap.object(0x3200, "Foo", &[]);
}
for addr in [0x3000, 0x3100, 0x3200] {
heap.root(HeapRootKind::JniGlobal, addr);
}
heap
}
#[test]
fn compare_gives_no_diff_for_a_name_of_several_classes() {
let diffs = compare(&analyzed(&two_foos(false)), &analyzed(&two_foos(true)));
let foo = diff(&diffs, "Foo");
assert!(foo.ambiguous);
assert_eq!((foo.base_count, foo.count), (2, 3));
assert!(diffs.iter().filter(|d| d.name != "Foo").all(|d| !d.ambiguous));
assert_sorted(&diffs);
// Ambiguous on one side only is still ambiguous.
let diffs = compare(&analyzed(&sample()), &analyzed(&two_foos(false)));
let foo = diff(&diffs, "Foo");
assert!(foo.ambiguous);
assert_eq!((foo.base_count, foo.count), (0, 2));
}
-137
View File
@@ -1,137 +0,0 @@
//! Disk-space estimates and the per-snapshot directories under the app's cache.
//!
//! A snapshot directory holds the index columns and, for a capture, the dump itself. Its `owner`
//! file names the host process that created it, so a host that starts later can remove the
//! directories of hosts that died without cleaning up.
use std::fs;
use std::io::{self, Read};
use std::path::{Path, PathBuf};
use std::time::{Duration, SystemTime};
/// Space to leave free on top of an estimate.
pub const DISK_MARGIN: u64 = 1 << 30;
/// hprof ≈ `bytes + 16 × instances`; index columns and scratch arrays ≈ `90 × instances`.
const CAPTURE_BYTES_PER_INSTANCE: u64 = 106;
const INDEX_BYTES_PER_OBJECT: u64 = 90;
const OWNER_FILE: &str = "owner";
const TMP_SUFFIX: &str = ".tmp";
/// A directory still being created by a live host has no `owner` for a moment; one that stays
/// unfinished for longer than this was abandoned.
const TMP_GRACE: Duration = Duration::from_secs(60 * 60);
/// Bytes of free space that a dump of `heap_bytes` bytes holding `instances` instances needs,
/// including its index.
pub fn capture_need(heap_bytes: u64, instances: u64) -> u64 {
heap_bytes.saturating_add(CAPTURE_BYTES_PER_INSTANCE.saturating_mul(instances)).saturating_add(DISK_MARGIN)
}
/// Bytes of free space that indexing a dump of `objects` objects needs.
pub fn index_need(objects: u64) -> u64 {
INDEX_BYTES_PER_OBJECT.saturating_mul(objects).saturating_add(DISK_MARGIN)
}
/// Bytes available to this process on the volume holding `dir`; `None` where it is not checked
/// (not unix) or cannot be read, so callers go ahead rather than refuse.
pub fn free_bytes(dir: &Path) -> Option<u64> {
#[cfg(unix)]
{
use std::os::unix::ffi::OsStrExt;
let path = std::ffi::CString::new(dir.as_os_str().as_bytes()).ok()?;
// SAFETY: `path` is NUL-terminated and `stat` is only read after `statvfs` filled it in.
let stat = unsafe {
let mut stat = std::mem::MaybeUninit::<libc::statvfs>::zeroed();
if libc::statvfs(path.as_ptr(), stat.as_mut_ptr()) != 0 {
return None;
}
stat.assume_init()
};
// The field widths differ between unix targets.
#[allow(clippy::unnecessary_cast)]
Some((stat.f_bavail as u64).saturating_mul(stat.f_frsize as u64))
}
#[cfg(not(unix))]
{
let _ = dir;
None
}
}
/// `<local_data_dir>/cache/heap-snapshots`.
pub fn snapshots_root(local_data_dir: &Path) -> PathBuf {
local_data_dir.join("cache").join("heap-snapshots")
}
/// Creates `<root>/<uuid>/` holding an `owner` file with this process's pid. The directory is
/// built as `<uuid>.tmp` and renamed, so another host scanning `root` never sees it without its
/// owner and removes it as abandoned.
pub fn create_snapshot_dir(root: &Path) -> io::Result<PathBuf> {
fs::create_dir_all(root)?;
let name = uuid::Uuid::new_v4().to_string();
let building = root.join(format!("{name}{TMP_SUFFIX}"));
let dir = root.join(&name);
create_private_dir(&building)?;
let published =
fs::write(building.join(OWNER_FILE), std::process::id().to_string()).and_then(|()| fs::rename(&building, &dir));
if let Err(err) = published {
let _ = fs::remove_dir_all(&building);
return Err(err);
}
Ok(dir)
}
/// A dump holds whatever was in the JVM's memory, passwords and tokens included, so on unix only
/// the owner may enter the directory. Windows keeps the ACL inherited from the user's data dir.
fn create_private_dir(path: &Path) -> io::Result<()> {
#[cfg(unix)]
{
use std::os::unix::fs::DirBuilderExt;
fs::DirBuilder::new().mode(0o700).create(path)
}
#[cfg(not(unix))]
{
fs::DirBuilder::new().create(path)
}
}
/// Removes the directories under `root` whose owner file is missing, unreadable or names a pid
/// for which `alive` is false, and unfinished `*.tmp` ones older than an hour. Only directories
/// directly under `root` are touched; a symlink there is left alone.
pub fn remove_stale(root: &Path, alive: impl Fn(u32) -> bool) {
remove_stale_at(root, alive, SystemTime::now());
}
fn remove_stale_at(root: &Path, alive: impl Fn(u32) -> bool, now: SystemTime) {
let Ok(entries) = fs::read_dir(root) else { return };
for entry in entries.flatten() {
let path = entry.path();
// `symlink_metadata` does not follow: a link out of `root` is not a directory here.
let Ok(meta) = fs::symlink_metadata(&path) else { continue };
if !meta.file_type().is_dir() {
continue;
}
let stale = if path.extension().is_some_and(|ext| ext == "tmp") {
meta.modified()
.ok()
.and_then(|modified| now.duration_since(modified).ok())
.is_some_and(|age| age >= TMP_GRACE)
} else {
read_owner(&path).is_none_or(|pid| !alive(pid))
};
if stale && let Err(err) = fs::remove_dir_all(&path) {
tracing::warn!(dir = %path.display(), %err, "could not remove a stale heap snapshot directory");
}
}
}
fn read_owner(dir: &Path) -> Option<u32> {
let mut text = String::new();
fs::File::open(dir.join(OWNER_FILE)).ok()?.take(32).read_to_string(&mut text).ok()?;
text.trim().parse().ok()
}
#[cfg(test)]
mod tests;
-137
View File
@@ -1,137 +0,0 @@
use std::time::{Duration, SystemTime};
use super::*;
fn names(dir: &Path) -> Vec<String> {
let mut names: Vec<_> =
std::fs::read_dir(dir).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
names.sort();
names
}
fn dir_with_owner(root: &Path, name: &str, owner: Option<&str>) {
let dir = root.join(name);
std::fs::create_dir(&dir).unwrap();
std::fs::write(dir.join("dump.hprof"), b"x").unwrap();
if let Some(owner) = owner {
std::fs::write(dir.join(OWNER_FILE), owner).unwrap();
}
}
#[test]
fn estimates() {
assert_eq!(capture_need(664_018_520, 20_087_506), 664_018_520 + 106 * 20_087_506 + (1 << 30));
assert_eq!(index_need(10), 900 + (1 << 30));
}
#[test]
fn estimates_saturate_instead_of_wrapping() {
assert_eq!(capture_need(u64::MAX, u64::MAX), u64::MAX);
assert_eq!(index_need(u64::MAX), u64::MAX);
}
#[cfg(unix)]
#[test]
fn not_enough_space_for_estimate() {
let dir = tempfile::tempdir().unwrap();
let free = free_bytes(dir.path()).expect("statvfs works on a temp dir");
assert!(free > 0);
assert!(capture_need(u64::MAX / 4, 0) > free);
}
#[cfg(unix)]
#[test]
fn free_bytes_of_a_missing_dir_is_unknown() {
let dir = tempfile::tempdir().unwrap();
assert_eq!(free_bytes(&dir.path().join("missing")), None);
}
#[cfg(not(unix))]
#[test]
fn free_space_is_not_checked_off_unix() {
assert_eq!(free_bytes(Path::new(".")), None);
}
#[test]
fn snapshots_root_is_under_the_cache() {
let local = Path::new("local");
assert_eq!(snapshots_root(local), local.join("cache").join("heap-snapshots"));
}
#[test]
fn snapshot_dir_records_its_owner_and_leaves_no_tmp() {
let root = tempfile::tempdir().unwrap();
let missing_parent = root.path().join("cache").join("heap-snapshots");
let dir = create_snapshot_dir(&missing_parent).unwrap();
assert_eq!(dir.parent(), Some(missing_parent.as_path()));
assert!(uuid::Uuid::parse_str(dir.file_name().unwrap().to_str().unwrap()).is_ok());
assert_eq!(std::fs::read_to_string(dir.join(OWNER_FILE)).unwrap(), std::process::id().to_string());
assert_eq!(names(&missing_parent), [dir.file_name().unwrap().to_str().unwrap()]);
assert_ne!(create_snapshot_dir(&missing_parent).unwrap(), dir);
}
#[cfg(unix)]
#[test]
fn snapshot_dir_is_private_to_the_owner() {
use std::os::unix::fs::PermissionsExt;
let root = tempfile::tempdir().unwrap();
let dir = create_snapshot_dir(root.path()).unwrap();
assert_eq!(std::fs::metadata(&dir).unwrap().permissions().mode() & 0o777, 0o700);
}
#[test]
fn stale_dirs_removed_on_start() {
let root = tempfile::tempdir().unwrap();
dir_with_owner(root.path(), "a", Some("999999"));
dir_with_owner(root.path(), "b", Some(&std::process::id().to_string()));
dir_with_owner(root.path(), "c", None);
remove_stale(root.path(), |pid| pid == std::process::id());
assert_eq!(names(root.path()), ["b"]);
}
#[test]
fn owner_that_is_not_a_pid_is_stale() {
let root = tempfile::tempdir().unwrap();
dir_with_owner(root.path(), "empty", Some(""));
dir_with_owner(root.path(), "word", Some("not-a-pid"));
dir_with_owner(root.path(), "negative", Some("-1"));
dir_with_owner(root.path(), "padded", Some(&format!(" {}\n", std::process::id())));
remove_stale(root.path(), |pid| pid == std::process::id());
assert_eq!(names(root.path()), ["padded"]);
}
#[test]
fn stale_scan_tolerates_a_missing_root_and_leaves_loose_files_alone() {
let root = tempfile::tempdir().unwrap();
remove_stale(&root.path().join("missing"), |_| false);
std::fs::write(root.path().join("notes.txt"), b"keep").unwrap();
remove_stale(root.path(), |_| false);
assert_eq!(names(root.path()), ["notes.txt"]);
}
#[test]
fn unfinished_dir_is_left_alone_for_an_hour() {
let root = tempfile::tempdir().unwrap();
// Another host may be between `create_dir` and the rename of its own snapshot dir.
dir_with_owner(root.path(), "young.tmp", None);
let now = SystemTime::now();
remove_stale_at(root.path(), |_| false, now);
assert_eq!(names(root.path()), ["young.tmp"]);
remove_stale_at(root.path(), |_| false, now + TMP_GRACE - Duration::from_secs(60));
assert_eq!(names(root.path()), ["young.tmp"]);
remove_stale_at(root.path(), |_| false, now + TMP_GRACE + Duration::from_secs(60));
assert!(names(root.path()).is_empty());
}
#[cfg(unix)]
#[test]
fn stale_scan_never_follows_a_symlink_out_of_the_root() {
let outside = tempfile::tempdir().unwrap();
std::fs::write(outside.path().join("precious"), b"x").unwrap();
let root = tempfile::tempdir().unwrap();
std::os::unix::fs::symlink(outside.path(), root.path().join("link")).unwrap();
remove_stale(root.path(), |_| false);
remove_stale_at(root.path(), |_| false, SystemTime::now() + 2 * TMP_GRACE);
assert_eq!(names(outside.path()), ["precious"]);
}
-247
View File
@@ -1,247 +0,0 @@
//! Dominator tree of the object graph, by Lengauer–Tarjan with path compression and no recursion:
//! the DFS "stack" is the chain of DFS parents, and `eval` reverses the links of the path it
//! compresses instead of keeping a stack.
//!
//! Between the DFS and the final translation every array is indexed by DFS number, so the root is
//! 0 and a vertex's DFS ancestors all have smaller numbers.
use ide_core::CancellationToken;
use crate::column::{Column, NONE, Store};
use crate::error::HeapError;
use crate::files::IDOM_FILE;
use crate::graph::accumulate;
use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
const PHASE: HeapPhase = HeapPhase::Dominators;
pub struct Dominators {
/// Immediate dominator of each node, saved as `idom.u32` in the store; [`NONE`] for
/// unreachable nodes, `root` for `root`.
pub idom: Column<u32>,
/// Nodes in DFS preorder from `root`, `reachable` entries.
pub preorder: Column<u32>,
pub reachable: u32,
}
/// The dominators of the graph whose node `v` has targets `out[out_start[v]..out_start[v + 1]]`,
/// from `root` (which must be a node). `progress` gets `Dominators` from `(0, total)` to
/// `(total, total)`; an `Err` from it stops the computation with that error.
pub fn dominators(
out_start: &[u32],
out: &[u32],
root: u32,
store: &Store,
progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
cancel: &CancellationToken,
) -> Result<Dominators, HeapError> {
compute(out_start, out, root, store, progress, cancel).map(|(dominators, _)| dominators)
}
/// [`dominators`], plus the number of steps of work it took.
fn compute(
out_start: &[u32],
out: &[u32],
root: u32,
store: &Store,
progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
cancel: &CancellationToken,
) -> Result<(Dominators, u64), HeapError> {
let nodes = out_start.len().saturating_sub(1);
if nodes >= NONE as usize {
return Err(HeapError::TooLarge);
}
assert!((root as usize) < nodes, "root {root} is not one of the {nodes} nodes");
// Three walks of at most `nodes` vertices each: DFS, semidominators, immediate dominators.
let span = nodes as u64;
let mut work = Work::new(Progress::new(progress, cancel), 3 * span);
work.report(0)?;
// DFS: `pre` maps nodes to DFS numbers and `vertex` back; `cursor[d]` is the next edge of
// DFS vertex d to follow.
let mut pre = store.scratch::<u32>(nodes, NONE)?;
let mut vertex = store.scratch::<u32>(nodes, 0)?;
let mut parent = store.scratch::<u32>(nodes, 0)?;
let mut cursor = store.scratch::<u32>(nodes, 0)?;
pre[root as usize] = 0;
vertex[0] = root;
cursor[0] = out_start[root as usize];
let (mut reachable, mut d) = (1u32, 0u32);
loop {
work.tick()?;
let edge = cursor[d as usize];
if edge < out_start[vertex[d as usize] as usize + 1] {
cursor[d as usize] = edge + 1;
let w = out[edge as usize] as usize;
if pre[w] == NONE {
let next = reachable as usize;
pre[w] = reachable;
vertex[next] = w as u32;
parent[next] = d;
cursor[next] = out_start[w];
d = reachable;
reachable += 1;
work.done = u64::from(reachable);
}
} else if d == 0 {
break;
} else {
d = parent[d as usize];
}
}
let r = reachable as usize;
work.report(span)?;
// Predecessors by DFS number, as CSR: counted into `starts[w + 1]`, then filled through
// `starts[w]` as a cursor, which leaves it at w's end until the column is shifted one slot.
let mut semi = cursor;
let mut label = store.scratch::<u32>(r, 0)?;
let mut starts = store.scratch::<u32>(r + 1, 0)?;
for d in 0..r {
work.tick()?;
semi[d] = d as u32;
label[d] = d as u32;
for &w in targets(out_start, out, vertex[d]) {
work.tick()?;
starts[pre[w as usize] as usize + 1] += 1;
}
}
let edges = accumulate(&mut starts, cancel)?;
let mut preds = store.scratch::<u32>(edges as usize, 0)?;
for d in 0..r {
work.tick()?;
for &w in targets(out_start, out, vertex[d]) {
work.tick()?;
let slot = &mut starts[pre[w as usize] as usize];
preds[*slot as usize] = d as u32;
*slot += 1;
}
}
starts.copy_within(0..r, 1);
starts[0] = 0;
drop(pre);
work.report(span)?;
// Semidominators in reverse preorder, linking each finished vertex to its parent. Vertex w
// waits in its semidominator's bucket until a child of that semidominator is linked; then
// `eval` gives w's idom, or a vertex whose idom is also w's, fixed up in preorder below.
// `idom[v]` is the next vertex in v's bucket until v leaves the bucket.
let mut ancestor = store.scratch::<u32>(r, NONE)?;
let mut bucket = store.scratch::<u32>(r, NONE)?;
let mut idom = store.scratch::<u32>(r, NONE)?;
for w in (1..r).rev() {
work.done = span + (r - w) as u64;
work.tick()?;
let mut s = semi[w];
for &v in &preds[starts[w] as usize..starts[w + 1] as usize] {
work.tick()?;
let u = eval(v, &mut ancestor, &mut label, &semi, &mut work)?;
s = s.min(semi[u as usize]);
}
semi[w] = s;
idom[w] = bucket[s as usize];
bucket[s as usize] = w as u32;
let p = parent[w];
ancestor[w] = p;
let mut v = std::mem::replace(&mut bucket[p as usize], NONE);
while v != NONE {
work.tick()?;
let next = idom[v as usize];
let u = eval(v, &mut ancestor, &mut label, &semi, &mut work)?;
idom[v as usize] = if semi[u as usize] < semi[v as usize] { u } else { p };
v = next;
}
}
drop((label, starts, preds, ancestor, bucket, parent));
work.report(2 * span)?;
// Immediate dominators, translated back to nodes; in preorder, so a deferred vertex's
// stand-in already has its final idom.
let mut node_idom = store.column::<u32>(IDOM_FILE, nodes, NONE)?;
let mut preorder = store.scratch::<u32>(r, 0)?;
idom[0] = 0;
node_idom[root as usize] = root;
preorder[0] = root;
for w in 1..r {
work.done = 2 * span + w as u64;
work.tick()?;
if idom[w] != semi[w] {
idom[w] = idom[idom[w] as usize];
}
node_idom[vertex[w] as usize] = vertex[idom[w] as usize];
preorder[w] = vertex[w];
}
work.report(3 * span)?;
Ok((Dominators { idom: node_idom, preorder, reachable }, work.steps))
}
fn targets<'a>(out_start: &[u32], out: &'a [u32], v: u32) -> &'a [u32] {
let v = v as usize;
&out[out_start[v] as usize..out_start[v + 1] as usize]
}
/// Counts steps of work and reports progress, which also looks at the cancellation token, at
/// every phase boundary and after every [`CHECK_EVERY`] steps, whichever loop they are in.
struct Work<'a> {
progress: Progress<'a>,
total: u64,
/// Progress to report at the next check; the loops keep it current.
done: u64,
steps: u64,
next_report: u64,
}
impl<'a> Work<'a> {
fn new(progress: Progress<'a>, total: u64) -> Self {
Self { progress, total, done: 0, steps: 0, next_report: CHECK_EVERY }
}
fn report(&mut self, done: u64) -> Result<(), HeapError> {
self.done = done;
self.next_report = self.steps + CHECK_EVERY;
self.progress.report(PHASE, done, self.total)
}
#[inline]
fn tick(&mut self) -> Result<(), HeapError> {
self.steps += 1;
if self.steps < self.next_report { Ok(()) } else { self.report(self.done) }
}
}
/// The vertex of smallest semidominator on the forest path from `v` up to, not including, its
/// tree's root (`v` itself when it is a root), compressing that path so the root becomes the
/// ancestor of every vertex on it. The walk up reverses the `ancestor` links so the walk down can
/// fold labels nearest-root first, as the recursive compress does, without a stack.
fn eval(v: u32, ancestor: &mut [u32], label: &mut [u32], semi: &[u32], work: &mut Work) -> Result<u32, HeapError> {
let at = |x: u32| x as usize;
if ancestor[at(v)] == NONE {
return Ok(v);
}
let (mut x, mut below) = (v, NONE);
while ancestor[at(ancestor[at(x)])] != NONE {
work.tick()?;
let up = ancestor[at(x)];
ancestor[at(x)] = below;
below = x;
x = up;
}
// `x` is the root's child, already compressed; `below` is the vertex under it.
let root = ancestor[at(x)];
let mut best = label[at(x)];
while below != NONE {
work.tick()?;
let y = at(below);
if semi[at(best)] < semi[at(label[y])] {
label[y] = best;
} else {
best = label[y];
}
below = ancestor[y];
ancestor[y] = root;
}
Ok(label[at(v)])
}
#[cfg(test)]
mod tests;
-348
View File
@@ -1,348 +0,0 @@
use std::cell::RefCell;
use std::time::Instant;
use proptest::collection::vec;
use proptest::prelude::*;
use super::*;
use crate::NONE;
use crate::graph::build_graph;
use crate::testing::{XorShift, sample};
fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
Ok(())
}
/// CSR of `edges` over `n` nodes, targets in edge order.
fn csr(n: usize, edges: &[(u32, u32)]) -> (Vec<u32>, Vec<u32>) {
let mut start = vec![0u32; n + 1];
for &(from, _) in edges {
start[from as usize + 1] += 1;
}
for v in 0..n {
start[v + 1] += start[v];
}
let mut cursor = start.clone();
let mut out = vec![0u32; edges.len()];
for &(from, to) in edges {
out[cursor[from as usize] as usize] = to;
cursor[from as usize] += 1;
}
(start, out)
}
fn run(n: usize, edges: &[(u32, u32)], root: u32) -> Dominators {
let (start, out) = csr(n, edges);
dominators(&start, &out, root, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap()
}
fn preds(n: usize, edges: &[(u32, u32)]) -> Vec<Vec<u32>> {
let mut preds = vec![Vec::new(); n];
for &(from, to) in edges {
preds[to as usize].push(from);
}
preds
}
/// Immediate dominators from iterated `Dom` sets (one `u64` bitset per node, `n <= 64`).
fn dataflow_idom(n: usize, edges: &[(u32, u32)], root: u32) -> Vec<u32> {
let (start, out) = csr(n, edges);
let mut reachable = vec![false; n];
let mut todo = vec![root];
reachable[root as usize] = true;
while let Some(v) = todo.pop() {
for &w in &out[start[v as usize] as usize..start[v as usize + 1] as usize] {
if !std::mem::replace(&mut reachable[w as usize], true) {
todo.push(w);
}
}
}
let preds = preds(n, edges);
let mut dom = vec![u64::MAX; n];
dom[root as usize] = 1 << root;
let mut changed = true;
while changed {
changed = false;
for v in (0..n).filter(|&v| reachable[v] && v != root as usize) {
let meet =
preds[v].iter().filter(|&&p| reachable[p as usize]).fold(u64::MAX, |acc, &p| acc & dom[p as usize]);
let next = meet | 1 << v;
if next != dom[v] {
dom[v] = next;
changed = true;
}
}
}
(0..n)
.map(|v| {
if !reachable[v] {
NONE
} else if v == root as usize {
root
} else {
// The strict dominator dominated by all the others has the most dominators itself.
let strict = dom[v] & !(1 << v);
(0..n as u32).filter(|&d| strict & 1 << d != 0).max_by_key(|&d| dom[d as usize].count_ones()).unwrap()
}
})
.collect()
}
/// Cooper–Harvey–Kennedy iteration over reverse postorder from an explicit-stack DFS.
fn chk_idom(n: usize, edges: &[(u32, u32)], root: u32) -> Vec<u32> {
let (start, out) = csr(n, edges);
let mut post_number = vec![NONE; n];
let mut postorder = Vec::new();
let mut seen = vec![false; n];
let mut stack = vec![(root, start[root as usize])];
seen[root as usize] = true;
while let Some(&mut (v, ref mut next)) = stack.last_mut() {
if *next < start[v as usize + 1] {
let w = out[*next as usize];
*next += 1;
if !std::mem::replace(&mut seen[w as usize], true) {
stack.push((w, start[w as usize]));
}
} else {
post_number[v as usize] = postorder.len() as u32;
postorder.push(v);
stack.pop();
}
}
let preds = preds(n, edges);
let mut idom = vec![NONE; n];
idom[root as usize] = root;
let intersect = |idom: &[u32], mut a: u32, mut b: u32| {
while a != b {
while post_number[a as usize] < post_number[b as usize] {
a = idom[a as usize];
}
while post_number[b as usize] < post_number[a as usize] {
b = idom[b as usize];
}
}
a
};
let mut changed = true;
while changed {
changed = false;
for &v in postorder.iter().rev().filter(|&&v| v != root) {
let mut new = NONE;
for &p in &preds[v as usize] {
if idom[p as usize] != NONE {
new = if new == NONE { p } else { intersect(&idom, p, new) };
}
}
if new != idom[v as usize] {
idom[v as usize] = new;
changed = true;
}
}
}
idom
}
#[test]
fn diamond() {
let d = run(5, &[(0, 1), (0, 2), (1, 3), (2, 3), (3, 4)], 0);
assert_eq!(&*d.idom, &[0, 0, 0, 0, 3]);
assert_eq!(d.reachable, 5);
assert_eq!(&*d.preorder, &[0, 1, 3, 4, 2]);
}
#[test]
fn unreachable_is_none() {
let d = run(6, &[(0, 1), (0, 2), (1, 3), (2, 3), (3, 4), (5, 3)], 0);
assert_eq!(&*d.idom, &[0, 0, 0, 0, 3, NONE]);
assert_eq!(d.reachable, 5);
assert_eq!(d.preorder.len(), 5);
}
#[test]
fn cycle_back_to_root() {
let d = run(3, &[(0, 1), (1, 2), (2, 1), (2, 0)], 0);
assert_eq!(&*d.idom, &[0, 0, 1]);
}
#[test]
fn root_need_not_be_node_zero() {
let d = run(4, &[(3, 1), (1, 0), (3, 2), (2, 0), (0, 3)], 3);
assert_eq!(&*d.idom, &[3, 3, 3, 3]);
assert_eq!(d.preorder[0], 3);
}
#[test]
fn sample_heap_dominators() {
let bytes = sample().bytes();
let g = build_graph(&bytes, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
let d = dominators(&g.out_start, &g.out, g.root, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
let node = |id: u64| g.ids.rank(id).unwrap();
let idom_of = |id: u64| d.idom[node(id) as usize];
assert_eq!(idom_of(0x1100), node(0x1000), "N1 → H");
assert_eq!(idom_of(0x1200), node(0x1000), "N2 → H");
assert_eq!(idom_of(0x1300), g.root, "N3 → root");
assert_eq!(idom_of(0x1400), node(0x1300), "L → N3");
assert_eq!(idom_of(0x1500), NONE, "R is unreachable");
assert_eq!(idom_of(0x1700), NONE, "N4 only through the weak referent");
assert_eq!(d.idom[g.root as usize], g.root);
}
#[test]
fn idom_is_written_to_the_store() {
let dir = tempfile::tempdir().unwrap();
let (start, out) = csr(3, &[(0, 1), (1, 2)]);
let store = Store::Dir(dir.path().to_path_buf());
let d = dominators(&start, &out, 0, &store, &no_progress, &CancellationToken::new()).unwrap();
drop(d);
assert_eq!(&*Column::<u32>::open(&dir.path().join("idom.u32")).unwrap(), &[0, 0, 1]);
let names: Vec<_> = std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name()).collect();
assert_eq!(names, ["idom.u32"], "scratch columns leave no files");
}
#[test]
fn reports_dominators_progress_and_stops_on_cancel() {
let (start, out) = csr(3, &[(0, 1), (1, 2)]);
let calls = RefCell::new(Vec::new());
let record = |phase, done, total| {
calls.borrow_mut().push((phase, done, total));
Ok(())
};
dominators(&start, &out, 0, &Store::Ram, &record, &CancellationToken::new()).unwrap();
let calls = calls.into_inner();
let total = calls[0].2;
assert_eq!(calls.first(), Some(&(HeapPhase::Dominators, 0, total)));
assert_eq!(calls.last(), Some(&(HeapPhase::Dominators, total, total)));
assert!(calls.windows(2).all(|w| w[0].1 <= w[1].1), "progress never goes back: {calls:?}");
let cancel = CancellationToken::new();
let cancel_on_first = |_, _, _| {
cancel.cancel();
Ok(())
};
let result = dominators(&start, &out, 0, &Store::Ram, &cancel_on_first, &cancel);
assert!(matches!(result, Err(HeapError::Cancelled)));
let refuse = |_, _, _| Err(HeapError::TooLarge);
let result = dominators(&start, &out, 0, &Store::Ram, &refuse, &CancellationToken::new());
assert!(matches!(result, Err(HeapError::TooLarge)));
}
#[test]
fn cancel_during_idom_phase() {
// Long enough that the last phase alone passes a check interval.
const NODES: u32 = (CHECK_EVERY + CHECK_EVERY / 2) as u32;
let edges: Vec<_> = (1..NODES).map(|v| (v - 1, v)).collect();
let (start, out) = csr(NODES as usize, &edges);
let span = u64::from(NODES);
let cancel = CancellationToken::new();
let calls = RefCell::new(Vec::new());
let cancel_past_semidominators = |_, done, _| {
calls.borrow_mut().push(done);
if done > 2 * span {
cancel.cancel();
}
Ok(())
};
let result = dominators(&start, &out, 0, &Store::Ram, &cancel_past_semidominators, &cancel);
assert!(matches!(result, Err(HeapError::Cancelled)));
let calls = calls.into_inner();
assert!(calls.contains(&(2 * span)), "the semidominator phase finished: {calls:?}");
let last = *calls.last().unwrap();
assert!(last > 2 * span && last < 3 * span, "stopped inside the idom phase: {calls:?}");
}
proptest! {
#[test]
fn matches_dataflow_on_random_graphs(n in 2usize..64, edges in vec((0u32..64, 0u32..64), 0..192)) {
let edges: Vec<_> = edges.into_iter().map(|(a, b)| (a % n as u32, b % n as u32)).collect();
let d = run(n, &edges, 0);
prop_assert_eq!(d.idom.to_vec(), dataflow_idom(n, &edges, 0));
prop_assert_eq!(d.preorder.len(), d.reachable as usize);
}
}
#[test]
fn matches_chk_on_a_large_random_graph() {
const NODES: u32 = 200_000;
const EXTRA_EDGES: u32 = 100_000;
let mut rng = XorShift::new(0x5EED_D0D0);
let mut edges: Vec<_> = (1..NODES).map(|v| (rng.below(v), v)).collect();
edges.extend((0..EXTRA_EDGES).map(|_| (rng.below(NODES), rng.below(NODES))));
// Visit edges in a scrambled order so the DFS tree differs from the generating tree.
for i in (1..edges.len()).rev() {
edges.swap(i, rng.below(i as u32 + 1) as usize);
}
let started = Instant::now();
let d = run(NODES as usize, &edges, 0);
let elapsed = started.elapsed();
let expected = chk_idom(NODES as usize, &edges, 0);
let mismatches = d.idom.iter().zip(&expected).filter(|(a, b)| a != b).count();
assert_eq!(mismatches, 0);
assert_eq!(d.reachable, NODES);
eprintln!("dominators of {NODES} random nodes: {elapsed:?}");
}
/// A doubly linked list whose items an array list also holds: super-root 0 → list 1 → node 0,
/// 0 → array list 2 → element array 3 → every item; node j → item j, next, prev.
fn shared_list_and_array(k: u32) -> (usize, Vec<(u32, u32)>) {
let node = |j: u32| 4 + 2 * j;
let item = |j: u32| 5 + 2 * j;
let mut edges = vec![(0, 1), (0, 2), (2, 3), (1, node(0))];
for j in 0..k {
edges.push((node(j), item(j)));
if j + 1 < k {
edges.push((node(j), node(j + 1)));
}
if j > 0 {
edges.push((node(j), node(j - 1)));
}
edges.push((3, item(j)));
}
((4 + 2 * k) as usize, edges)
}
#[test]
fn shared_list_and_array_is_near_linear() {
let (n, edges) = shared_list_and_array(29);
assert_eq!(run(n, &edges, 0).idom.to_vec(), dataflow_idom(n, &edges, 0));
let (n, edges) = shared_list_and_array(3_000);
assert_eq!(run(n, &edges, 0).idom.to_vec(), chk_idom(n, &edges, 0));
const K: u32 = 200_000;
let (n, edges) = shared_list_and_array(K);
let (start, out) = csr(n, &edges);
let started = Instant::now();
let (d, steps) = compute(&start, &out, 0, &Store::Ram, &no_progress, &CancellationToken::new()).unwrap();
let elapsed = started.elapsed();
let item = |j: u32| (5 + 2 * j) as usize;
assert!((0..K).all(|j| d.idom[item(j)] == 0), "every item is held by both collections");
let m = edges.len() as u64;
let bound = (n as u64 + m) * u64::from(n.ilog2());
eprintln!("shared list k={K}: {steps} steps (n={n}, m={m}, bound {bound}), {elapsed:?}");
assert!(steps <= bound, "{steps} steps for n={n}, m={m}");
}
#[test]
fn deep_chain_has_linear_dominators() {
// A small stack proves the algorithm does not recurse along the chain.
std::thread::Builder::new()
.stack_size(256 << 10)
.spawn(|| {
const NODES: u32 = 1_000_000;
let mut edges: Vec<_> = (1..NODES).map(|v| (v - 1, v)).collect();
edges.push((0, NODES - 1));
// Makes `eval` compress the whole chain at once.
edges.push((NODES - 1, 1));
let started = Instant::now();
let d = run(NODES as usize, &edges, 0);
eprintln!("dominators of a {NODES}-node chain: {:?}", started.elapsed());
assert_eq!(d.reachable, NODES);
assert_eq!(d.idom[0], 0);
assert_eq!(d.idom[NODES as usize - 1], 0);
let wrong = (1..NODES - 1).filter(|&v| d.idom[v as usize] != v - 1).count();
assert_eq!(wrong, 0);
})
.unwrap()
.join()
.unwrap();
}
-26
View File
@@ -1,26 +0,0 @@
/// Offsets (`at`) are byte positions in the `.hprof` file.
#[derive(Debug, thiserror::Error)]
pub enum HeapError {
#[error("the dump ends early at byte {at}")]
Truncated { at: u64 },
#[error("not a heap dump (no JAVA PROFILE header)")]
NotHprof,
#[error("unsupported identifier size {0}")]
UnsupportedIdSize(u32),
#[error("unknown heap sub-record tag {tag:#04x} at byte {at}")]
UnknownSubRecord { tag: u8, at: u64 },
#[error("unknown value type {ty} at byte {at}")]
UnknownType { ty: u8, at: u64 },
#[error("class {id:#x} used at byte {at} is not in the dump")]
MissingClass { id: u64, at: u64 },
#[error("the heap has too many objects to analyze")]
TooLarge,
#[error("the dump's class and field names are too long; it is not a dump a JVM wrote")]
NamesTooLarge,
#[error("not enough disk space: {needed} bytes needed, {available} free")]
NotEnoughDiskSpace { needed: u64, available: u64 },
#[error("cancelled")]
Cancelled,
#[error("{0}")]
Io(#[from] std::io::Error),
}
-34
View File
@@ -1,34 +0,0 @@
//! Names of the files an analysis writes into its index directory. They live in one list so a
//! failed analysis removes exactly these and never the dump or anything else sharing the directory.
pub(crate) const IDS_BITS_FILE: &str = "ids.bits.u64";
pub(crate) const IDS_WRANK_FILE: &str = "ids.wrank.u32";
pub(crate) const IDS_TABLE_FILE: &str = "ids.table.u32";
pub(crate) const IDS_CHUNKS_FILE: &str = "ids.chunks.u32";
pub(crate) const IDS_SORTED_FILE: &str = "ids.sorted.u64";
pub(crate) const TYPES_FILE: &str = "types.u32";
pub(crate) const OFFSETS_FILE: &str = "offsets.u64";
pub(crate) const IDOM_FILE: &str = "idom.u32";
pub(crate) const SHALLOW8_FILE: &str = "shallow8.u32";
pub(crate) const RETAINED_FILE: &str = "retained.u64";
pub(crate) const KIDS_START_FILE: &str = "kids_start.u32";
pub(crate) const KIDS_FILE: &str = "kids.u32";
pub(crate) const GC_PARENT_FILE: &str = "gc_parent.u32";
pub(crate) const SUMMARY_FILE: &str = "summary.json";
pub(crate) const INDEX_FILES: &[&str] = &[
IDS_BITS_FILE,
IDS_WRANK_FILE,
IDS_TABLE_FILE,
IDS_CHUNKS_FILE,
IDS_SORTED_FILE,
TYPES_FILE,
OFFSETS_FILE,
IDOM_FILE,
SHALLOW8_FILE,
RETAINED_FILE,
KIDS_START_FILE,
KIDS_FILE,
GC_PARENT_FILE,
SUMMARY_FILE,
];
-274
View File
@@ -1,274 +0,0 @@
//! The object graph of a heap dump in CSR form: one node per object, plus a super-root.
mod classes;
mod link;
use std::collections::hash_map::Entry;
use std::collections::{HashMap, HashSet};
use ide_core::CancellationToken;
use self::classes::{ClassTable, IdHash};
use self::link::Linker;
use crate::column::{Column, Store};
use crate::error::HeapError;
use crate::files::{OFFSETS_FILE, TYPES_FILE};
use crate::hprof::{BasicType, HeapRecord, HeapRootKind, Record, parse_header, scan, scan_segment};
use crate::ids::{IdMap, IdMapBuilder};
use crate::progress::{CHECK_EVERY, HeapPhase, Progress};
/// Number of primitive array type slots, one per non-object [`BasicType`].
pub const PRIM_SLOTS: u32 = 8;
pub struct ClassInfo {
pub id: u64,
/// The hprof name with `/` turned into `.` (`java.lang.String`, `[Ljava.lang.Object;`).
pub name: String,
/// Index in [`HeapGraph::classes`]. Chains always end: a super cycle in the dump is cut where it closes.
pub super_index: Option<u32>,
/// This class's own instance fields, in dump order.
pub fields: Vec<(String, BasicType)>,
/// `(name, object id)` of reference statics; a null static has object id 0.
pub statics: Vec<(String, u64)>,
pub static_bytes: u64,
/// Index in `fields` of `java.lang.ref.Reference.referent`, on that class only.
pub weak_field: Option<usize>,
}
pub struct HeapGraph {
pub ids: IdMap,
/// Type slot of each object: class index for instances and object arrays,
/// [`Self::class_slot`] for class objects, [`Self::prim_slot`] for primitive arrays.
pub types: Column<u32>,
/// Array length, 0 for instances and classes.
pub lens: Column<u32>,
/// File offset of each object's record, for [`crate::record_at`].
pub offsets: Column<u64>,
/// `n + 2` entries: node `v`'s targets are `out[out_start[v]..out_start[v + 1]]`.
pub out_start: Column<u32>,
pub out: Column<u32>,
/// The super-root, node `n`, with an edge to every rooted object.
pub root: u32,
/// `(object, kind, thread serial)` of every root record whose object is in the dump.
pub roots: Vec<(u32, HeapRootKind, Option<u32>)>,
/// Class dumps in dump order, then a synthetic `java.lang.Class` when the dump has none.
pub classes: Vec<ClassInfo>,
/// Type slot of class objects (`java.lang.Class`).
pub class_slot: u32,
/// Thread serial → thread object, from `ROOT THREAD OBJECT` records.
pub thread_objects: HashMap<u32, u32>,
/// `Reference.referent` edges left out of the graph.
pub weak_edges_skipped: u64,
pub id_size: u8,
pub timestamp_ms: u64,
}
impl HeapGraph {
pub fn prim_slot(&self, ty: BasicType) -> u32 {
self.classes.len() as u32 + (ty as u32 - BasicType::Boolean as u32)
}
/// The element type of primitive array slot `slot`, or `None` for a class slot.
pub fn prim_type(&self, slot: u32) -> Option<BasicType> {
let offset = slot.checked_sub(self.classes.len() as u32).filter(|&o| o < PRIM_SLOTS)?;
BasicType::from_u8(offset as u8 + BasicType::Boolean as u8)
}
pub fn out_edges(&self, v: u32) -> &[u32] {
let v = v as usize;
&self.out[self.out_start[v] as usize..self.out_start[v + 1] as usize]
}
}
/// Builds the graph of the dump in `buf`. Strong edges only: `Reference.referent` is counted in
/// [`HeapGraph::weak_edges_skipped`] instead. `progress` gets `Reading` by bytes, then
/// `Linking` by objects, starting with `(Linking, 0, objects)` once the object count is known;
/// an `Err` from it stops the build with that error.
pub fn build_graph(
buf: &[u8],
store: &Store,
progress: &dyn Fn(HeapPhase, u64, u64) -> Result<(), HeapError>,
cancel: &CancellationToken,
) -> Result<HeapGraph, HeapError> {
let progress = Progress::new(progress, cancel);
let header = parse_header(buf)?;
let id_size = header.id_size;
let len = buf.len() as u64;
// Pass 1: names, classes, roots and every object id.
progress.report(HeapPhase::Reading, 0, len)?;
let mut names: IdHash<&[u8]> = IdHash::default();
let mut class_names: IdHash<u64> = IdHash::default();
let mut dumps = Vec::new();
let mut class_by_id: IdHash<u32> = IdHash::default();
let mut raw_roots = Vec::new();
let mut segments = Vec::new();
let mut builder = IdMapBuilder::new();
let (mut step, mut pos) = (0, header.body_start as u64);
scan(buf, &header, &mut |record| {
progress.step(step, HeapPhase::Reading, pos, len)?;
step += 1;
match record {
Record::Utf8 { id, text } => {
names.insert(id, text);
}
Record::LoadClass { class_id, name_id } => {
class_names.insert(class_id, name_id);
}
Record::Segment(range) => {
pos = range.start as u64;
segments.push(range);
}
Record::Heap { at, record } => {
pos = at as u64;
match record {
HeapRecord::Root { kind, id, thread_serial } => raw_roots.push((id, kind, thread_serial)),
HeapRecord::Class(dump) => {
builder.insert(dump.id);
if let Entry::Vacant(slot) = class_by_id.entry(dump.id) {
slot.insert(dumps.len() as u32);
dumps.push(dump);
}
}
HeapRecord::Instance { id, .. }
| HeapRecord::ObjectArray { id, .. }
| HeapRecord::PrimitiveArray { id, .. } => builder.insert(id),
}
}
}
Ok(())
})?;
progress.report(HeapPhase::Reading, len, len)?;
let ids = builder.build(store, cancel)?;
let table = classes::resolve(dumps, class_by_id, &names, &class_names, id_size, buf.len())?;
drop((names, class_names));
let n = ids.len();
let objects = u64::from(n);
progress.report(HeapPhase::Linking, 0, objects)?;
let mut roots = Vec::new();
let mut root_targets = Vec::new();
let mut thread_objects = HashMap::new();
let (mut seen_records, mut seen_targets) = (HashSet::new(), HashSet::new());
for (i, &(id, kind, serial)) in raw_roots.iter().enumerate() {
progress.step(i as u64, HeapPhase::Linking, 0, objects)?;
let Some(object) = ids.rank(id).filter(|_| id != 0) else { continue };
if seen_records.insert((object, kind as u8, serial)) {
roots.push((object, kind, serial));
}
if seen_targets.insert(object) {
root_targets.push(object);
}
if let (HeapRootKind::ThreadObject, Some(serial)) = (kind, serial) {
thread_objects.entry(serial).or_insert(object);
}
}
drop((raw_roots, seen_records, seen_targets));
let linker = Linker::new(&ids, &table, id_size);
let nodes = n as usize;
let mut types = store.column::<u32>(TYPES_FILE, nodes, 0)?;
let mut lens = store.scratch::<u32>(nodes, 0)?;
let mut offsets = store.column::<u64>(OFFSETS_FILE, nodes, 0)?;
let mut out_start = store.scratch::<u32>(nodes + 2, 0)?;
// Both passes visit every object record once; report them as one walk over the objects.
let mut visited = 0u64;
let tick = |visited: &mut u64| {
let result = progress.step(*visited, HeapPhase::Linking, (*visited / 2).min(objects), objects);
*visited += 1;
result
};
// Pass 2: node columns and out-degrees, counted into `out_start[v + 1]`.
let mut weak_edges_skipped = 0;
for segment in &segments {
scan_segment(buf, segment.clone(), id_size, &mut |at, record| {
let Some(node) = linker.node(at, &record)? else { return Ok(()) };
tick(&mut visited)?;
let v = node.index as usize;
types[v] = node.ty;
lens[v] = node.len;
offsets[v] = at as u64;
let mut degree = 0u64;
linker.edges(&record, &mut |_, weak| {
if weak {
weak_edges_skipped += 1;
} else {
degree += 1;
}
});
let count = &mut out_start[v + 1];
*count = u32::try_from(u64::from(*count) + degree).map_err(|_| HeapError::TooLarge)?;
Ok(())
})?;
}
out_start[nodes + 1] = u32::try_from(root_targets.len()).map_err(|_| HeapError::TooLarge)?;
let edges = accumulate(&mut out_start, cancel)?;
// Pass 3: `out_start[v]` is node v's write cursor; once filled it holds v's end, so the
// column is shifted one slot right to become the starts again.
let mut out = store.scratch::<u32>(edges as usize, 0)?;
for segment in &segments {
scan_segment(buf, segment.clone(), id_size, &mut |at, record| {
let Some(node) = linker.node(at, &record)? else { return Ok(()) };
tick(&mut visited)?;
let v = node.index as usize;
let mut cursor = out_start[v] as usize;
linker.edges(&record, &mut |target, weak| {
if !weak && let Some(slot) = out.get_mut(cursor) {
*slot = target;
cursor += 1;
}
});
out_start[v] = cursor as u32;
Ok(())
})?;
}
let first_root_edge = out_start[nodes] as usize;
for (slot, &target) in out[first_root_edge..].iter_mut().zip(&root_targets) {
*slot = target;
}
out_start[nodes] = edges;
out_start.copy_within(0..nodes + 1, 1);
out_start[0] = 0;
progress.report(HeapPhase::Linking, objects, objects)?;
drop(linker);
let ClassTable { classes, class_slot, .. } = table;
Ok(HeapGraph {
ids,
types,
lens,
offsets,
out_start,
out,
root: n,
roots,
classes,
class_slot,
thread_objects,
weak_edges_skipped,
id_size,
timestamp_ms: header.timestamp_ms,
})
}
/// Turns per-node counts into running totals in place (`counts[k]` becomes the sum of
/// `counts[..=k]`) and returns the last one; past `u32::MAX` the graph is `TooLarge`.
pub(crate) fn accumulate(counts: &mut [u32], cancel: &CancellationToken) -> Result<u32, HeapError> {
let mut sum = 0u32;
for chunk in counts.chunks_mut(CHECK_EVERY as usize) {
if cancel.is_cancelled() {
return Err(HeapError::Cancelled);
}
for count in chunk {
sum = sum.checked_add(*count).ok_or(HeapError::TooLarge)?;
*count = sum;
}
}
Ok(sum)
}
#[cfg(test)]
mod tests;
-188
View File
@@ -1,188 +0,0 @@
//! Class dumps resolved into [`ClassInfo`]s, plus where the references sit in instance data.
use std::collections::HashMap;
use std::hash::BuildHasherDefault;
use super::{ClassInfo, PRIM_SLOTS};
use crate::column::NONE;
use crate::error::HeapError;
use crate::hprof::{BasicType, ClassDump};
use crate::ids::ChunkHasher;
/// Keyed by hprof id (an address).
pub(super) type IdHash<V> = HashMap<u64, V, BuildHasherDefault<ChunkHasher>>;
const REFERENCE: &str = "java.lang.ref.Reference";
const JAVA_LANG_CLASS: &str = "java.lang.Class";
/// Not computed yet, in [`ClassTable::fielded`].
const UNSET: u32 = NONE - 1;
pub(super) struct ClassTable {
pub(super) classes: Vec<ClassInfo>,
/// Class id → class index.
pub(super) by_id: IdHash<u32>,
pub(super) class_slot: u32,
/// Per class: `(offset, is the referent)` of each reference field in the class's own part of
/// the instance data.
pub(super) refs: Vec<Vec<(usize, bool)>>,
/// Per class: bytes of its own part of the instance data.
pub(super) own_bytes: Vec<usize>,
/// Per class: the nearest class up its chain (itself included) whose own part is not empty, or
/// `NONE`. Walking these instead of every super keeps a walk bounded by the data it reads.
pub(super) fielded: Vec<u32>,
}
/// The longest name a JVM gives a class or field (a constant pool UTF8 has a `u2` length).
const MAX_NAME_BYTES: usize = 65_535;
/// Name bytes a dump may decode beyond 4 per byte of the file.
const NAME_BUDGET_FLOOR: usize = 64 << 20;
/// Names decoded from the UTF8 records within a budget: every field of every class may name the
/// same record, so a small crafted file could otherwise ask for terabytes and abort the IDE.
struct Names<'m, 'b> {
records: &'m IdHash<&'b [u8]>,
left: usize,
}
impl Names<'_, '_> {
/// Empty for an id with no record.
fn text(&mut self, id: u64) -> Result<String, HeapError> {
let Some(bytes) = self.records.get(&id) else { return Ok(String::new()) };
if bytes.len() > MAX_NAME_BYTES || bytes.len() > self.left {
return Err(HeapError::NamesTooLarge);
}
self.left -= bytes.len();
Ok(String::from_utf8_lossy(bytes).into_owned())
}
}
/// `dumps` holds one dump per class id, and `by_id` its position; `names` are the UTF8 records
/// and `class_names` the LOAD CLASS class id → name id pairs. `file_len` bounds the name bytes.
pub(super) fn resolve(
dumps: Vec<ClassDump>,
by_id: IdHash<u32>,
names: &IdHash<&[u8]>,
class_names: &IdHash<u64>,
id_size: u8,
file_len: usize,
) -> Result<ClassTable, HeapError> {
// Room for the synthetic java.lang.Class and the primitive slots in a `u32` type id.
if dumps.len() > (u32::MAX - PRIM_SLOTS - 1) as usize {
return Err(HeapError::TooLarge);
}
let mut names = Names { records: names, left: file_len.saturating_mul(4).saturating_add(NAME_BUDGET_FLOOR) };
let mut supers: Vec<Option<u32>> =
dumps.iter().map(|d| if d.super_id == 0 { None } else { by_id.get(&d.super_id).copied() }).collect();
cut_super_cycles(&mut supers);
let mut classes = Vec::with_capacity(dumps.len() + 1);
let mut refs = Vec::with_capacity(dumps.len() + 1);
let mut own_bytes = Vec::with_capacity(dumps.len() + 1);
for (dump, super_index) in dumps.into_iter().zip(supers) {
let name = match class_names.get(&dump.id) {
Some(&name_id) if names.records.contains_key(&name_id) => names.text(name_id)?.replace('/', "."),
_ => format!("{:#x}", dump.id),
};
let fields =
dump.fields.iter().map(|&(n, ty)| Ok((names.text(n)?, ty))).collect::<Result<Vec<_>, HeapError>>()?;
let weak_field = if name == REFERENCE {
fields.iter().position(|(n, ty)| n == "referent" && *ty == BasicType::Object)
} else {
None
};
let mut offset = 0;
let mut class_refs = Vec::new();
for (k, &(_, ty)) in fields.iter().enumerate() {
if ty == BasicType::Object {
class_refs.push((offset, weak_field == Some(k)));
}
offset += ty.hprof_size(id_size);
}
refs.push(class_refs);
own_bytes.push(offset);
classes.push(ClassInfo {
id: dump.id,
name,
super_index,
fields,
statics: dump
.statics
.iter()
.map(|&(n, object)| Ok((names.text(n)?, object)))
.collect::<Result<_, HeapError>>()?,
static_bytes: dump.static_bytes,
weak_field,
});
}
let class_slot = match classes.iter().position(|c| c.name == JAVA_LANG_CLASS) {
Some(slot) => slot as u32,
None => {
classes.push(ClassInfo {
id: 0,
name: JAVA_LANG_CLASS.to_owned(),
super_index: None,
fields: Vec::new(),
statics: Vec::new(),
static_bytes: 0,
weak_field: None,
});
refs.push(Vec::new());
own_bytes.push(0);
classes.len() as u32 - 1
}
};
let fielded = nearest_fielded(&classes, &own_bytes);
Ok(ClassTable { classes, by_id, class_slot, refs, own_bytes, fielded })
}
/// A dump may claim `A extends B extends A`; the edge that closes a cycle is dropped so every
/// walk up the chain ends. Iterative, so a long chain cannot overflow the stack.
fn cut_super_cycles(supers: &mut [Option<u32>]) {
const NEW: u8 = 0;
const ON_PATH: u8 = 1;
const DONE: u8 = 2;
let mut state = vec![NEW; supers.len()];
let mut path = Vec::new();
for start in 0..supers.len() {
let mut c = start;
while state[c] == NEW {
state[c] = ON_PATH;
path.push(c);
match supers[c] {
Some(s) if state[s as usize] == ON_PATH => {
supers[c] = None;
break;
}
Some(s) => c = s as usize,
None => break,
}
}
for p in path.drain(..) {
state[p] = DONE;
}
}
}
fn nearest_fielded(classes: &[ClassInfo], own_bytes: &[usize]) -> Vec<u32> {
let mut fielded: Vec<u32> =
own_bytes.iter().enumerate().map(|(c, &b)| if b > 0 { c as u32 } else { UNSET }).collect();
let mut path = Vec::new();
for start in 0..classes.len() {
let mut c = start;
let found = loop {
if fielded[c] != UNSET {
break fielded[c];
}
path.push(c);
match classes[c].super_index {
Some(s) => c = s as usize,
None => break NONE,
}
};
for p in path.drain(..) {
fielded[p] = found;
}
}
fielded
}
-107
View File
@@ -1,107 +0,0 @@
//! Turns one heap sub-record into its node (index, type, length) and its outgoing edges. Both
//! linking passes go through here, so the degrees counted in the first match the edges written
//! in the second.
use super::classes::ClassTable;
use crate::column::NONE;
use crate::error::HeapError;
use crate::hprof::{BasicType, HeapRecord};
use crate::ids::IdMap;
pub(super) struct Node {
pub(super) index: u32,
pub(super) ty: u32,
pub(super) len: u32,
}
pub(super) struct Linker<'a> {
ids: &'a IdMap,
table: &'a ClassTable,
/// Per class: the node of its class object, `NONE` for the synthetic `java.lang.Class`.
class_objects: Vec<u32>,
id_size: u8,
}
impl<'a> Linker<'a> {
pub(super) fn new(ids: &'a IdMap, table: &'a ClassTable, id_size: u8) -> Self {
let class_objects =
table.classes.iter().map(|c| if c.id == 0 { NONE } else { ids.rank(c.id).unwrap_or(NONE) }).collect();
Self { ids, table, class_objects, id_size }
}
/// `None` for root records. `at` is the record's offset, for the error of an instance or array
/// whose class is not in the dump.
pub(super) fn node(&self, at: usize, record: &HeapRecord<'_>) -> Result<Option<Node>, HeapError> {
let class_index = |class_id: u64| {
self.table.by_id.get(&class_id).copied().ok_or(HeapError::MissingClass { id: class_id, at: at as u64 })
};
let (id, ty, len) = match record {
HeapRecord::Root { .. } => return Ok(None),
HeapRecord::Class(c) => (c.id, self.table.class_slot, 0),
HeapRecord::Instance { id, class_id, .. } => (*id, class_index(*class_id)?, 0),
HeapRecord::ObjectArray { id, class_id, len, .. } => (*id, class_index(*class_id)?, *len),
HeapRecord::PrimitiveArray { id, ty, len, .. } => {
let prim_base = self.table.classes.len() as u32;
(*id, prim_base + (*ty as u32 - BasicType::Boolean as u32), *len)
}
};
Ok(self.ids.rank(id).map(|index| Node { index, ty, len }))
}
/// Calls `edge(target, is_referent)` for every reference to an object in the dump, in field
/// order; `is_referent` marks `Reference.referent`, which callers leave out of the graph.
pub(super) fn edges(&self, record: &HeapRecord<'_>, edge: &mut impl FnMut(u32, bool)) {
let mut to = |id: u64, weak: bool| {
if let Some(target) = self.target(id) {
edge(target, weak);
}
};
match record {
HeapRecord::Root { .. } | HeapRecord::PrimitiveArray { .. } => {}
HeapRecord::Class(c) => {
to(c.super_id, false);
to(c.loader_id, false);
for &(_, object) in &c.statics {
to(object, false);
}
}
HeapRecord::ObjectArray { data, .. } => {
for item in data.chunks_exact(usize::from(self.id_size)) {
to(read_id(item, 0, self.id_size).unwrap_or(0), false);
}
}
HeapRecord::Instance { class_id, data, .. } => {
let Some(&class) = self.table.by_id.get(class_id) else { return };
let mut base = 0;
let mut next = self.table.fielded[class as usize];
'chain: while next != NONE && base < data.len() {
let c = next as usize;
for &(offset, weak) in &self.table.refs[c] {
let Some(id) = read_id(data, base + offset, self.id_size) else { break 'chain };
to(id, weak);
}
base += self.table.own_bytes[c];
next = self.table.classes[c].super_index.map_or(NONE, |s| self.table.fielded[s as usize]);
}
let object = self.class_objects[class as usize];
if object != NONE {
edge(object, false);
}
}
}
}
/// Id 0 is null; ids not in the dump have no node.
fn target(&self, id: u64) -> Option<u32> {
if id == 0 { None } else { self.ids.rank(id) }
}
}
/// The big-endian id at `at`, or `None` when `data` ends first.
fn read_id(data: &[u8], at: usize, id_size: u8) -> Option<u64> {
let bytes = data.get(at..at.checked_add(usize::from(id_size))?)?;
Some(match *bytes {
[a, b, c, d] => u64::from(u32::from_be_bytes([a, b, c, d])),
_ => u64::from_be_bytes(bytes.try_into().ok()?),
})
}
-479
View File
@@ -1,479 +0,0 @@
use std::cell::RefCell;
use proptest::prelude::*;
use super::*;
use crate::hprof::{HeapRecord, record_at};
use crate::testing::{HprofWriter, MiniHeap, sample};
const H: u64 = 0x1000;
const N1: u64 = 0x1100;
const N2: u64 = 0x1200;
const N3: u64 = 0x1300;
const L: u64 = 0x1400;
const R: u64 = 0x1500;
const W: u64 = 0x1600;
const N4: u64 = 0x1700;
fn no_progress(_: HeapPhase, _: u64, _: u64) -> Result<(), HeapError> {
Ok(())
}
fn build(bytes: &[u8]) -> Result<HeapGraph, HeapError> {
build_graph(bytes, &Store::Ram, &no_progress, &CancellationToken::new())
}
fn index(g: &HeapGraph, id: u64) -> u32 {
g.ids.rank(id).unwrap_or_else(|| panic!("{id:#x} is not in the graph"))
}
fn class(g: &HeapGraph, name: &str) -> (u32, u64) {
let slot = g.classes.iter().position(|c| c.name == name).unwrap_or_else(|| panic!("no class {name}"));
(slot as u32, g.classes[slot].id)
}
/// Targets of `id`'s edges, as ids, in edge order.
fn out_of(g: &HeapGraph, id: u64) -> Vec<u64> {
g.out_edges(index(g, id)).iter().map(|&t| g.ids.id_at(t)).collect()
}
fn root_targets(g: &HeapGraph) -> Vec<u64> {
g.out_edges(g.root).iter().map(|&t| g.ids.id_at(t)).collect()
}
fn assert_csr(g: &HeapGraph) {
let n = g.ids.len();
assert_eq!(g.root, n);
assert_eq!(g.out_start.len(), n as usize + 2);
assert_eq!(g.out_start[0], 0);
assert!(g.out_start.windows(2).all(|w| w[0] <= w[1]), "out_start is not monotone");
assert_eq!(g.out_start[n as usize + 1] as usize, g.out.len());
assert!(g.out.iter().all(|&t| t < n), "edge to a node outside the objects");
assert_eq!((g.types.len(), g.lens.len(), g.offsets.len()), (n as usize, n as usize, n as usize));
let slots = g.classes.len() as u32 + PRIM_SLOTS;
assert!(g.types.iter().all(|&t| t < slots), "type outside the slots");
for c in &g.classes {
let mut steps = 0;
let mut cursor = c.super_index;
while let Some(s) = cursor {
steps += 1;
assert!(steps <= g.classes.len(), "super chain of {} does not end", c.name);
cursor = g.classes[s as usize].super_index;
}
}
}
#[test]
fn edges_follow_fields_and_skip_weak_referents() {
let g = build(&sample().bytes()).unwrap();
assert_csr(&g);
let (_, holder) = class(&g, "Holder");
let (_, node) = class(&g, "Node");
let (_, weak) = class(&g, "java.lang.ref.WeakReference");
assert_eq!(out_of(&g, H), [N1, N2, holder]);
assert_eq!(out_of(&g, N1), [N3, node]);
assert_eq!(out_of(&g, N3), [L, node]);
assert_eq!(out_of(&g, W), [weak]);
assert_eq!(out_of(&g, N4), [node]);
assert_eq!(out_of(&g, L), Vec::<u64>::new());
assert_eq!(g.weak_edges_skipped, 1);
let (reference, _) = class(&g, "java.lang.ref.Reference");
assert_eq!(g.classes[reference as usize].weak_field, Some(0));
assert!(g.classes.iter().filter(|c| c.name != "java.lang.ref.Reference").all(|c| c.weak_field.is_none()));
}
#[test]
fn object_arrays_skip_null_and_unknown() {
let mut heap = sample();
heap.array_of(0x1800, "[Ljava.lang.Object;", &[N2, 0, 0x9990, N1, 0xDEAD_BEEF]);
let g = build(&heap.bytes()).unwrap();
assert_csr(&g);
assert_eq!(out_of(&g, R), [N1]);
assert_eq!(out_of(&g, 0x1800), [N2, N1]);
}
#[test]
fn super_root_points_at_each_root_once() {
let mut heap = sample();
heap.root(HeapRootKind::JniGlobal, H).root(HeapRootKind::MonitorUsed, H).root(HeapRootKind::JniLocal, 0x9990);
let g = build(&heap.bytes()).unwrap();
assert_csr(&g);
let targets = root_targets(&g);
assert_eq!(targets.iter().filter(|&&t| t == H).count(), 1);
assert!(targets.contains(&N3) && targets.contains(&W));
assert!(!targets.contains(&N1) && !targets.contains(&R) && !targets.contains(&N4));
let classes = g.classes.iter().filter(|c| c.id != 0).count();
assert_eq!(targets.len(), 3 + classes, "H, N3, W and every sticky class");
let mut sorted = targets.clone();
sorted.sort_unstable();
sorted.dedup();
assert_eq!(sorted.len(), targets.len());
let h = index(&g, H);
let of_h: Vec<_> = g.roots.iter().filter(|r| r.0 == h).map(|r| (r.1, r.2)).collect();
assert_eq!(of_h, [(HeapRootKind::JniGlobal, None), (HeapRootKind::MonitorUsed, None)]);
assert!(g.roots.contains(&(index(&g, N3), HeapRootKind::JavaFrame, Some(1))));
assert!(g.roots.iter().all(|r| r.0 < g.root));
}
#[test]
fn class_dump_edges_cover_statics() {
let mut w = HprofWriter::new();
w.string(1, "java/lang/Object")
.load_class(0x100, 1)
.class(0x100, 0, &[], &[])
.string(2, "Config")
.string(3, "INSTANCE")
.string(4, "EMPTY")
.string(5, "LOST")
.load_class(0x200, 2)
.class_with_loader(0x200, 0x100, 0x1200, &[], &[(3, N1), (4, 0), (5, 0x9990)])
.instance(N1, 0x100, &[])
.instance(0x1200, 0x100, &[]);
let g = build(&w.finish()).unwrap();
assert_csr(&g);
assert_eq!(out_of(&g, 0x200), [0x100, 0x1200, N1]);
assert_eq!(out_of(&g, 0x100), Vec::<u64>::new());
let (config, _) = class(&g, "Config");
let info = &g.classes[config as usize];
let statics: Vec<_> = info.statics.iter().map(|(n, id)| (n.as_str(), *id)).collect();
assert_eq!(statics, [("INSTANCE", N1), ("EMPTY", 0), ("LOST", 0x9990)]);
assert_eq!(info.super_index, Some(class(&g, "java.lang.Object").0));
}
#[test]
fn missing_class_is_an_error() {
let mut w = HprofWriter::new();
w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]).instance(N1, 0x999, &[]);
let bytes = w.finish();
let at = instance_offset(&bytes, N1);
let err = build(&bytes).err().unwrap();
assert!(matches!(err, HeapError::MissingClass { id: 0x999, at: a } if a == at as u64), "{err:?}");
let mut w = HprofWriter::new();
w.obj_array(0x10, 0x999, &[]);
assert!(matches!(build(&w.finish()), Err(HeapError::MissingClass { id: 0x999, .. })));
}
fn instance_offset(bytes: &[u8], id: u64) -> usize {
let header = crate::hprof::parse_header(bytes).unwrap();
let mut found = None;
crate::hprof::scan(bytes, &header, &mut |r| {
if let crate::hprof::Record::Heap { at, record: HeapRecord::Instance { id: i, .. } } = r
&& i == id
{
found = Some(at);
}
Ok(())
})
.unwrap();
found.unwrap()
}
#[test]
fn cancel_during_linking_returns_cancelled() {
let bytes = sample().bytes();
let cancelled = CancellationToken::new();
cancelled.cancel();
let result = build_graph(&bytes, &Store::Ram, &no_progress, &cancelled);
assert!(matches!(result, Err(HeapError::Cancelled)));
let cancel = CancellationToken::new();
let phases = RefCell::new(Vec::new());
let result = build_graph(
&bytes,
&Store::Ram,
&|phase, done, total| {
phases.borrow_mut().push((phase, done, total));
if phase == HeapPhase::Linking {
cancel.cancel();
}
Ok(())
},
&cancel,
);
assert!(matches!(result, Err(HeapError::Cancelled)));
let phases = phases.into_inner();
assert_eq!(phases.first(), Some(&(HeapPhase::Reading, 0, bytes.len() as u64)));
assert_eq!(phases.last(), Some(&(HeapPhase::Linking, 0, 15)), "stops at the first Linking report");
}
#[test]
fn progress_error_stops_the_build() {
let bytes = sample().bytes();
let fail = |phase, _, total| {
if phase == HeapPhase::Linking {
Err(HeapError::NotEnoughDiskSpace { needed: total * 90, available: 0 })
} else {
Ok(())
}
};
let result = build_graph(&bytes, &Store::Ram, &fail, &CancellationToken::new());
assert!(matches!(result, Err(HeapError::NotEnoughDiskSpace { needed: 1350, available: 0 })));
}
#[test]
fn progress_reads_bytes_then_links_objects() {
let bytes = sample().bytes();
let phases = RefCell::new(Vec::new());
let g = build_graph(
&bytes,
&Store::Ram,
&|phase, done, total| {
phases.borrow_mut().push((phase, done, total));
Ok(())
},
&CancellationToken::new(),
)
.unwrap();
let phases = phases.into_inner();
let len = bytes.len() as u64;
let objects = u64::from(g.root);
assert_eq!(objects, 15, "7 classes and 8 objects");
assert_eq!(phases.first(), Some(&(HeapPhase::Reading, 0, len)));
assert!(phases.contains(&(HeapPhase::Reading, len, len)));
let linking: Vec<_> = phases.iter().filter(|p| p.0 == HeapPhase::Linking).collect();
assert_eq!(linking.first(), Some(&&(HeapPhase::Linking, 0, objects)));
assert_eq!(linking.iter().filter(|p| ***p == (HeapPhase::Linking, 0, objects)).count(), 1, "{linking:?}");
assert_eq!(linking.last(), Some(&&(HeapPhase::Linking, objects, objects)));
assert!(phases.iter().all(|&(_, done, total)| done <= total));
}
#[test]
fn types_lengths_and_offsets() {
let bytes = sample().bytes();
let g = build(&bytes).unwrap();
let (holder, holder_id) = class(&g, "Holder");
let (node, _) = class(&g, "Node");
let (array, _) = class(&g, "[Ljava.lang.Object;");
let (java_lang_class, _) = class(&g, "java.lang.Class");
assert_eq!(g.class_slot, java_lang_class);
let ty = |id| g.types[index(&g, id) as usize];
let len = |id| g.lens[index(&g, id) as usize];
assert_eq!([ty(H), ty(N1), ty(R), ty(holder_id)], [holder, node, array, java_lang_class]);
assert_eq!(ty(L), g.prim_slot(BasicType::Long));
assert_eq!(g.prim_type(ty(L)), Some(BasicType::Long));
assert_eq!(g.prim_type(holder), None);
assert_eq!(g.prim_type(g.classes.len() as u32 + PRIM_SLOTS), None);
assert_eq!(g.prim_slot(BasicType::Boolean), g.classes.len() as u32);
assert_eq!(g.prim_slot(BasicType::Long), g.classes.len() as u32 + PRIM_SLOTS - 1);
assert_eq!([len(H), len(L), len(R), len(holder_id)], [0, 2, 3, 0]);
for i in 0..g.root {
let id = match record_at(&bytes, g.offsets[i as usize] as usize, g.id_size).unwrap() {
HeapRecord::Class(c) => c.id,
HeapRecord::Instance { id, .. } | HeapRecord::ObjectArray { id, .. } => id,
HeapRecord::PrimitiveArray { id, .. } => id,
other => panic!("offset of object {i} points at {other:?}"),
};
assert_eq!(id, g.ids.id_at(i));
}
assert_eq!((g.id_size, g.timestamp_ms), (8, 1_700_000_000_000));
let holder_info = &g.classes[holder as usize];
let fields: Vec<_> = holder_info.fields.iter().map(|(n, t)| (n.as_str(), *t)).collect();
assert_eq!(fields, [("a", BasicType::Object), ("b", BasicType::Object)]);
assert_eq!(holder_info.super_index, Some(class(&g, "java.lang.Object").0));
assert_eq!(g.classes[class(&g, "java.lang.Object").0 as usize].super_index, None);
}
#[test]
fn dump_without_java_lang_class_gets_a_synthetic_slot() {
let mut w = HprofWriter::new();
w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]).instance(N1, 0x100, &[]);
let g = build(&w.finish()).unwrap();
assert_csr(&g);
assert_eq!(g.classes.len(), 2);
let synthetic = &g.classes[g.class_slot as usize];
assert_eq!((synthetic.id, synthetic.name.as_str(), synthetic.super_index), (0, "java.lang.Class", None));
assert_eq!(g.types[index(&g, 0x100) as usize], g.class_slot);
assert_eq!(g.types[index(&g, N1) as usize], 0);
}
#[test]
fn classes_without_a_name_record_get_their_address() {
let mut w = HprofWriter::new();
w.class(0x100, 0, &[(9, BasicType::Object)], &[])
.instance(N1, 0x100, &N2.to_be_bytes())
.instance(N2, 0x100, &[0; 8]);
let g = build(&w.finish()).unwrap();
assert_eq!(g.classes[0].name, "0x100");
assert_eq!(g.classes[0].fields, [(String::new(), BasicType::Object)]);
assert_eq!(out_of(&g, N1), [N2, 0x100]);
}
#[test]
fn thread_objects_map_serials_to_threads() {
let mut heap = sample();
heap.class("java.lang.Thread", Some("java.lang.Object"), &[])
.object(0x2000, "java.lang.Thread", &[])
.object(0x2100, "java.lang.Thread", &[])
.root_in_thread(HeapRootKind::ThreadObject, 0x2000, 1)
.root_in_thread(HeapRootKind::ThreadObject, 0x2100, 7)
.root_in_thread(HeapRootKind::ThreadObject, 0x9990, 9);
let g = build(&heap.bytes()).unwrap();
let expected: HashMap<u32, u32> = [(1, index(&g, 0x2000)), (7, index(&g, 0x2100))].into();
assert_eq!(g.thread_objects, expected);
assert!(g.roots.contains(&(index(&g, 0x2100), HeapRootKind::ThreadObject, Some(7))));
}
#[test]
fn inherited_fields_follow_the_class_first_layout() {
let mut heap = MiniHeap::new();
heap.class("A", Some("java.lang.Object"), &[("a", BasicType::Object), ("n", BasicType::Int)])
.class("Empty", Some("A"), &[])
.class("B", Some("Empty"), &[("flag", BasicType::Byte), ("b", BasicType::Object)])
.object(0x10, "B", &[("a", 0x20), ("b", 0x30), ("flag", 1)])
.object(0x20, "A", &[])
.object(0x30, "A", &[]);
let g = build(&heap.bytes()).unwrap();
assert_csr(&g);
assert_eq!(out_of(&g, 0x10), [0x30, 0x20, class(&g, "B").1]);
}
#[test]
fn super_class_cycles_are_cut() {
let mut w = HprofWriter::new();
w.string(1, "A")
.string(2, "B")
.string(3, "S")
.string(4, "f")
.load_class(0x100, 1)
.load_class(0x200, 2)
.load_class(0x300, 3)
.class(0x100, 0x200, &[(4, BasicType::Object)], &[])
.class(0x200, 0x100, &[(4, BasicType::Object)], &[])
.class(0x300, 0x300, &[], &[])
.instance(0x10, 0x100, &[[0; 7].as_slice(), &[0x20], &[0; 7], &[0x30]].concat())
.instance(0x20, 0x300, &[])
.instance(0x30, 0x300, &[0; 64]);
let g = build(&w.finish()).unwrap();
assert_csr(&g);
assert_eq!(out_of(&g, 0x10), [0x20, 0x30, 0x100]);
assert_eq!(out_of(&g, 0x30), [0x300]);
}
#[test]
fn short_instance_data_stops_at_the_last_whole_field() {
let mut w = HprofWriter::new();
w.string(1, "P")
.string(2, "x")
.load_class(0x100, 1)
.class(0x100, 0, &[(2, BasicType::Object), (2, BasicType::Object)], &[])
.instance(0x10, 0x100, &[[0; 7].as_slice(), &[0x20], &[0; 5]].concat())
.instance(0x20, 0x100, &[]);
let g = build(&w.finish()).unwrap();
assert_csr(&g);
assert_eq!(out_of(&g, 0x10), [0x20, 0x100]);
}
#[test]
fn id_size_4_dump_links() {
let mut w = HprofWriter::with_id_size(4);
w.string(1, "Node")
.string(2, "next")
.load_class(0x100, 1)
.class(0x100, 0, &[(2, BasicType::Object)], &[(2, 0x20)])
.instance(0x10, 0x100, &0x20u32.to_be_bytes())
.instance(0x20, 0x100, &[0; 4])
.obj_array(0x30, 0x100, &[0x10, 0, 0x20])
.root(HeapRootKind::JniGlobal, 0x30);
let g = build(&w.finish()).unwrap();
assert_csr(&g);
assert_eq!(g.id_size, 4);
assert_eq!(out_of(&g, 0x10), [0x20, 0x100]);
assert_eq!(out_of(&g, 0x30), [0x10, 0x20]);
assert_eq!(out_of(&g, 0x100), [0x20]);
assert_eq!(root_targets(&g), [0x30]);
}
#[test]
fn dir_store_keeps_types_and_offsets_only() {
let dir = tempfile::tempdir().unwrap();
// The id map's own files (`ids.*`) depend on its layout; MiniHeap's class ids are unaligned.
let names = || {
let mut names: Vec<_> = std::fs::read_dir(dir.path())
.unwrap()
.map(|e| e.unwrap().file_name().into_string().unwrap())
.filter(|name| !name.starts_with("ids."))
.collect();
names.sort();
names
};
let g =
build_graph(&sample().bytes(), &Store::Dir(dir.path().to_path_buf()), &no_progress, &CancellationToken::new())
.unwrap();
assert_eq!(out_of(&g, H).len(), 3);
let kept = ["offsets.u64", "types.u32"];
assert!(dir.path().join("ids.sorted.u64").exists());
#[cfg(unix)]
assert_eq!(names(), kept);
drop(g);
assert_eq!(names(), kept);
}
#[test]
fn empty_dump_has_only_the_super_root() {
let g = build(&HprofWriter::new().finish()).unwrap();
assert_csr(&g);
assert_eq!((g.root, g.out.len(), g.classes.len()), (0, 0, 1));
assert_eq!(g.class_slot, 0);
}
#[test]
fn edge_count_past_u32_is_too_large() {
let cancel = CancellationToken::new();
let mut counts = [0, 2, 0, 3, 1];
assert_eq!(accumulate(&mut counts, &cancel).unwrap(), 6);
assert_eq!(counts, [0, 2, 2, 5, 6]);
let mut full = [0, u32::MAX - 1, 1];
assert_eq!(accumulate(&mut full, &cancel).unwrap(), u32::MAX);
let mut over = [0, u32::MAX, 1];
assert!(matches!(accumulate(&mut over, &cancel), Err(HeapError::TooLarge)));
cancel.cancel();
assert!(matches!(accumulate(&mut [0, 1], &cancel), Err(HeapError::Cancelled)));
}
/// A class with `fields` instance fields, every one named by the same `name_len`-byte UTF8 record.
fn shared_long_field_names(name_len: usize, fields: usize) -> Vec<u8> {
let mut w = HprofWriter::new();
let long = "f".repeat(name_len);
w.string(1, "java/lang/Object").load_class(0x100, 1).class(0x100, 0, &[], &[]);
w.string(2, "Wide").string(3, &long).load_class(0x200, 2);
w.class(0x200, 0x100, &vec![(3, BasicType::Int); fields], &[]);
w.finish()
}
#[test]
fn names_that_would_decode_far_larger_than_the_file_are_refused() {
// 128 MiB of names from a file of about 70 KB.
let bytes = shared_long_field_names(32 << 10, 4000);
assert!(bytes.len() < 100 << 10, "{}", bytes.len());
let err = build(&bytes).err().expect("refused");
assert!(matches!(err, HeapError::NamesTooLarge), "{err:?}");
}
#[test]
fn a_name_longer_than_the_jvm_allows_is_refused() {
let mut w = HprofWriter::new();
w.string(1, &"C".repeat(70_000)).load_class(0x100, 1).class(0x100, 0, &[], &[]);
assert!(matches!(build(&w.finish()), Err(HeapError::NamesTooLarge)));
}
#[test]
fn real_sized_names_shared_by_many_fields_are_fine() {
let g = build(&shared_long_field_names(40, 4000)).unwrap();
assert_eq!(g.classes[class(&g, "Wide").0 as usize].fields.len(), 4000);
}
proptest! {
#[test]
fn build_graph_never_panics_on_mutated_dumps(flips in proptest::collection::vec((0usize..4096, any::<u8>()), 1..12)) {
let mut bytes = sample().bytes();
for (pos, value) in flips {
let at = pos % bytes.len();
bytes[at] = value;
}
if let Ok(g) = build(&bytes) {
assert_csr(&g);
}
}
}
-945
View File
@@ -1,945 +0,0 @@
//! Reader for HotSpot `.hprof` heap dumps (format 1.0.1 / 1.0.2, 4- or 8-byte ids).
use std::ops::Range;
use serde::{Deserialize, Serialize};
use crate::error::HeapError;
use crate::reader::Reader;
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum BasicType {
Object = 2,
Boolean = 4,
Char = 5,
Float = 6,
Double = 7,
Byte = 8,
Short = 9,
Int = 10,
Long = 11,
}
impl BasicType {
pub fn from_u8(v: u8) -> Option<Self> {
Some(match v {
2 => Self::Object,
4 => Self::Boolean,
5 => Self::Char,
6 => Self::Float,
7 => Self::Double,
8 => Self::Byte,
9 => Self::Short,
10 => Self::Int,
11 => Self::Long,
_ => return None,
})
}
/// Bytes one value takes in the dump; `id_size` is the dump's identifier size.
pub fn hprof_size(self, id_size: u8) -> usize {
match self {
Self::Object => usize::from(id_size),
Self::Boolean | Self::Byte => 1,
Self::Char | Self::Short => 2,
Self::Float | Self::Int => 4,
Self::Double | Self::Long => 8,
}
}
/// Bytes one value takes in the JVM heap; `ref_size` is 4 with compressed oops, else 8.
pub fn heap_size(self, ref_size: u8) -> u64 {
match self {
Self::Object => u64::from(ref_size),
other => other.hprof_size(ref_size) as u64,
}
}
/// JVM class name of an array of this type (`[I`); `Object` arrays have no single name, so
/// they report the most general one.
pub fn array_name(self) -> &'static str {
match self {
Self::Object => "[Ljava.lang.Object;",
Self::Boolean => "[Z",
Self::Char => "[C",
Self::Float => "[F",
Self::Double => "[D",
Self::Byte => "[B",
Self::Short => "[S",
Self::Int => "[I",
Self::Long => "[J",
}
}
}
#[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub enum HeapRootKind {
Unknown,
JniGlobal,
JniLocal,
JavaFrame,
NativeStack,
StickyClass,
ThreadBlock,
MonitorUsed,
ThreadObject,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct HprofHeader {
pub version: String,
pub id_size: u8,
pub timestamp_ms: u64,
/// Offset of the first record.
pub body_start: usize,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct ClassDump {
pub id: u64,
pub super_id: u64,
pub loader_id: u64,
/// `(name id, object id)` of reference statics; a null static has object id 0.
pub statics: Vec<(u64, u64)>,
/// Heap bytes taken by the primitive statics.
pub static_bytes: u64,
/// Instance fields in dump order, `(name id, type)`.
pub fields: Vec<(u64, BasicType)>,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub enum HeapRecord<'a> {
/// `thread_serial` is present for the kinds that carry one.
Root {
kind: HeapRootKind,
id: u64,
thread_serial: Option<u32>,
},
Class(ClassDump),
/// `data` is the field values, class first, then each superclass.
Instance {
id: u64,
class_id: u64,
data: &'a [u8],
},
/// `data` is `len` ids.
ObjectArray {
id: u64,
class_id: u64,
len: u32,
data: &'a [u8],
},
/// `data` is `len` big-endian elements.
PrimitiveArray {
id: u64,
ty: BasicType,
len: u32,
data: &'a [u8],
},
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub enum Record<'a> {
Utf8 {
id: u64,
text: &'a [u8],
},
LoadClass {
class_id: u64,
name_id: u64,
},
/// Byte range of a heap-dump segment's sub-records; its contents follow as `Heap` records.
Segment(Range<usize>),
/// `at` is the offset of the sub-record's tag, for [`record_at`].
Heap {
at: usize,
record: HeapRecord<'a>,
},
}
const MAGIC_1_0_2: &[u8] = b"JAVA PROFILE 1.0.2\0";
const MAGIC_1_0_1: &[u8] = b"JAVA PROFILE 1.0.1\0";
const TAG_UTF8: u8 = 0x01;
const TAG_LOAD_CLASS: u8 = 0x02;
const TAG_HEAP_DUMP: u8 = 0x0C;
const TAG_HEAP_DUMP_SEGMENT: u8 = 0x1C;
const TAG_HEAP_DUMP_END: u8 = 0x2C;
/// Tag (u1), timestamp (u4) and body length (u4).
const RECORD_HEADER_LEN: usize = 9;
fn check_id_size(id_size: u8) -> Result<(), HeapError> {
match id_size {
4 | 8 => Ok(()),
other => Err(HeapError::UnsupportedIdSize(u32::from(other))),
}
}
fn truncated(buf: &[u8]) -> HeapError {
HeapError::Truncated { at: buf.len() as u64 }
}
pub fn parse_header(buf: &[u8]) -> Result<HprofHeader, HeapError> {
let magic =
[MAGIC_1_0_2, MAGIC_1_0_1].into_iter().find(|magic| buf.starts_with(magic)).ok_or(HeapError::NotHprof)?;
let mut r = Reader::new(buf, magic.len(), 8);
let id_size = r.u4()?;
let id_size = u8::try_from(id_size).map_err(|_| HeapError::UnsupportedIdSize(id_size))?;
check_id_size(id_size)?;
let timestamp_ms = r.u8()?;
let version = String::from_utf8_lossy(&magic[..magic.len() - 1]).into_owned();
Ok(HprofHeader { version, id_size, timestamp_ms, body_start: r.pos() })
}
/// Walks every top-level record and, for heap-dump segments, the sub-records inside them.
/// A record whose length runs past the end of `buf` is `Truncated`, and so are segments that no
/// HEAP DUMP END follows: HotSpot writes whole segments, so a dump it did not finish ends after one.
pub fn scan<'a>(
buf: &'a [u8],
header: &HprofHeader,
visit: &mut dyn FnMut(Record<'a>) -> Result<(), HeapError>,
) -> Result<(), HeapError> {
let id_size = header.id_size;
check_id_size(id_size)?;
if header.body_start > buf.len() {
return Err(truncated(buf));
}
let mut pos = header.body_start;
let mut unended_segments = false;
while pos < buf.len() {
let mut head = Reader::new(buf, pos, id_size);
let tag = head.u1()?;
head.skip(4)?; // timestamp
let len = head.u4()? as usize;
let start = pos + RECORD_HEADER_LEN;
let end = start.checked_add(len).filter(|&end| end <= buf.len()).ok_or_else(|| truncated(buf))?;
let body = &buf[..end];
let mut r = Reader::new(body, start, id_size);
match tag {
TAG_UTF8 => {
let id = r.id()?;
let text = r.bytes(end - r.pos())?;
visit(Record::Utf8 { id, text })?;
}
TAG_LOAD_CLASS => {
r.skip(4)?; // class serial
let class_id = r.id()?;
r.skip(4)?; // stack trace serial
let name_id = r.id()?;
visit(Record::LoadClass { class_id, name_id })?;
}
TAG_HEAP_DUMP | TAG_HEAP_DUMP_SEGMENT => {
// A single HEAP DUMP (JDK 8, under 2 GB) has no end record.
unended_segments |= tag == TAG_HEAP_DUMP_SEGMENT;
visit(Record::Segment(start..end))?;
walk_segment(buf, start..end, id_size, &mut |at, record| visit(Record::Heap { at, record }))?;
}
TAG_HEAP_DUMP_END => unended_segments = false,
_ => {}
}
pos = end;
}
if unended_segments {
return Err(truncated(buf));
}
Ok(())
}
/// Visits the sub-records of one segment (the range from [`Record::Segment`]) with their offsets.
/// The last sub-record must end exactly at the segment's end.
pub fn scan_segment<'a>(
buf: &'a [u8],
segment: Range<usize>,
id_size: u8,
visit: &mut dyn FnMut(usize, HeapRecord<'a>) -> Result<(), HeapError>,
) -> Result<(), HeapError> {
check_id_size(id_size)?;
walk_segment(buf, segment, id_size, visit)
}
fn walk_segment<'a>(
buf: &'a [u8],
segment: Range<usize>,
id_size: u8,
visit: &mut dyn FnMut(usize, HeapRecord<'a>) -> Result<(), HeapError>,
) -> Result<(), HeapError> {
if segment.start > segment.end || segment.end > buf.len() {
return Err(truncated(buf));
}
let mut r = Reader::new(&buf[..segment.end], segment.start, id_size);
while r.pos() < segment.end {
let at = r.pos();
let record = read_sub_record(&mut r)?;
visit(at, record)?;
}
Ok(())
}
/// Reads the sub-record whose tag is at `at`, as given by [`Record::Heap`].
pub fn record_at(buf: &[u8], at: usize, id_size: u8) -> Result<HeapRecord<'_>, HeapError> {
check_id_size(id_size)?;
read_sub_record(&mut Reader::new(buf, at, id_size))
}
fn read_sub_record<'a>(r: &mut Reader<'a>) -> Result<HeapRecord<'a>, HeapError> {
let at = r.pos();
let tag = r.u1()?;
// (kind, carries a thread serial, bytes after it)
let root = match tag {
0xFF => Some((HeapRootKind::Unknown, false, 0)),
0x01 => Some((HeapRootKind::JniGlobal, false, usize::from(r.id_size()))),
0x02 => Some((HeapRootKind::JniLocal, true, 4)),
0x03 => Some((HeapRootKind::JavaFrame, true, 4)),
0x04 => Some((HeapRootKind::NativeStack, true, 0)),
0x05 => Some((HeapRootKind::StickyClass, false, 0)),
0x06 => Some((HeapRootKind::ThreadBlock, true, 0)),
0x07 => Some((HeapRootKind::MonitorUsed, false, 0)),
0x08 => Some((HeapRootKind::ThreadObject, true, 4)),
_ => None,
};
if let Some((kind, has_serial, trailing)) = root {
let id = r.id()?;
let thread_serial = if has_serial { Some(r.u4()?) } else { None };
r.skip(trailing)?;
return Ok(HeapRecord::Root { kind, id, thread_serial });
}
match tag {
0x20 => read_class_dump(r).map(HeapRecord::Class),
0x21 => {
let id = r.id()?;
r.skip(4)?; // stack trace serial
let class_id = r.id()?;
let len = r.u4()? as usize;
Ok(HeapRecord::Instance { id, class_id, data: r.bytes(len)? })
}
0x22 => {
let id = r.id()?;
r.skip(4)?;
let len = r.u4()?;
let class_id = r.id()?;
let size = (len as usize).checked_mul(usize::from(r.id_size())).ok_or_else(|| truncated(r.buf()))?;
Ok(HeapRecord::ObjectArray { id, class_id, len, data: r.bytes(size)? })
}
0x23 => {
let id = r.id()?;
r.skip(4)?;
let len = r.u4()?;
let ty = read_type(r)?;
if ty == BasicType::Object {
return Err(HeapError::UnknownType { ty: ty as u8, at: (r.pos() - 1) as u64 });
}
let size = (len as usize).checked_mul(ty.hprof_size(r.id_size())).ok_or_else(|| truncated(r.buf()))?;
Ok(HeapRecord::PrimitiveArray { id, ty, len, data: r.bytes(size)? })
}
tag => Err(HeapError::UnknownSubRecord { tag, at: at as u64 }),
}
}
fn read_type(r: &mut Reader<'_>) -> Result<BasicType, HeapError> {
let at = r.pos();
let ty = r.u1()?;
BasicType::from_u8(ty).ok_or(HeapError::UnknownType { ty, at: at as u64 })
}
fn read_class_dump(r: &mut Reader<'_>) -> Result<ClassDump, HeapError> {
let id_size = r.id_size();
let id = r.id()?;
r.skip(4)?; // stack trace serial
let super_id = r.id()?;
let loader_id = r.id()?;
r.skip(4 * usize::from(id_size))?; // signers, protection domain, 2 reserved
r.skip(4)?; // instance size
for _ in 0..r.u2()? {
r.skip(2)?; // constant pool index
let ty = read_type(r)?;
r.skip(ty.hprof_size(id_size))?;
}
let mut statics = Vec::new();
let mut static_bytes = 0;
for _ in 0..r.u2()? {
let name = r.id()?;
let ty = read_type(r)?;
if ty == BasicType::Object {
statics.push((name, r.id()?));
} else {
r.skip(ty.hprof_size(id_size))?;
static_bytes += ty.heap_size(id_size);
}
}
let mut fields = Vec::new();
for _ in 0..r.u2()? {
let name = r.id()?;
fields.push((name, read_type(r)?));
}
Ok(ClassDump { id, super_id, loader_id, statics, static_bytes, fields })
}
#[cfg(test)]
mod tests {
use super::*;
use crate::testing::{HprofWriter, MiniHeap};
use proptest::prelude::*;
fn collect(bytes: &[u8]) -> Result<Vec<Record<'_>>, HeapError> {
let header = parse_header(bytes)?;
let mut out = Vec::new();
scan(bytes, &header, &mut |r| {
out.push(r);
Ok(())
})?;
Ok(out)
}
fn segment_of(bytes: &[u8]) -> Range<usize> {
collect(bytes)
.unwrap()
.into_iter()
.find_map(|r| if let Record::Segment(s) = r { Some(s) } else { None })
.expect("a segment")
}
fn all_kinds(w: &mut HprofWriter) {
w.string(1, "Node")
.string(2, "next")
.load_class(0x100, 1)
.class(0x100, 0, &[(2, BasicType::Object), (3, BasicType::Long)], &[(2, 0x10)])
.instance(0x10, 0x100, &[0u8; 16])
.obj_array(0x20, 0x100, &[0x10, 0])
.prim_array(0x30, BasicType::Int, 3)
.root(HeapRootKind::JavaFrame, 0x10)
.root(HeapRootKind::StickyClass, 0x100);
}
#[test]
fn parses_header() {
let header = parse_header(&MiniHeap::new().bytes()).unwrap();
assert_eq!((header.version.as_str(), header.id_size, header.body_start), ("JAVA PROFILE 1.0.2", 8, 31));
let mut old = b"JAVA PROFILE 1.0.1\0".to_vec();
old.extend_from_slice(&[0, 0, 0, 4, 0, 0, 0, 1, 0, 0, 0, 2]);
let header = parse_header(&old).unwrap();
assert_eq!(
(header.version.as_str(), header.id_size, header.timestamp_ms),
("JAVA PROFILE 1.0.1", 4, (1 << 32) + 2)
);
let bad_size = b"JAVA PROFILE 1.0.2\0\0\0\0\x03\0\0\0\0\0\0\0\0";
assert!(matches!(parse_header(bad_size), Err(HeapError::UnsupportedIdSize(3))));
assert!(matches!(parse_header(b"GIF89a"), Err(HeapError::NotHprof)));
assert!(matches!(parse_header(b""), Err(HeapError::NotHprof)));
assert!(matches!(parse_header(b"JAVA PROFILE 1.0.3\0\0\0\0\x08"), Err(HeapError::NotHprof)));
assert!(matches!(parse_header(b"JAVA PROFILE 1.0.2\0\0\0"), Err(HeapError::Truncated { at: 21 })));
}
#[test]
fn scans_every_record_kind() {
let mut w = HprofWriter::new();
all_kinds(&mut w);
let bytes = w.finish();
let records = collect(&bytes).unwrap();
let (mut utf8, mut loads, mut segments) = (0, 0, 0);
let (mut classes, mut instances, mut obj_arrays, mut prim_arrays, mut roots) = (0, 0, 0, 0, 0);
for record in &records {
match record {
Record::Utf8 { .. } => utf8 += 1,
Record::LoadClass { class_id, name_id } => {
loads += 1;
assert_eq!((*class_id, *name_id), (0x100, 1));
}
Record::Segment(_) => segments += 1,
Record::Heap { record, .. } => match record {
HeapRecord::Class(c) => {
classes += 1;
assert_eq!((c.id, c.super_id, c.loader_id), (0x100, 0, 0));
assert_eq!(c.statics, [(2, 0x10)]);
assert_eq!(c.fields, [(2, BasicType::Object), (3, BasicType::Long)]);
}
HeapRecord::Instance { id, class_id, data } => {
instances += 1;
assert_eq!((*id, *class_id, data.len()), (0x10, 0x100, 16));
}
HeapRecord::ObjectArray { id, class_id, len, data } => {
obj_arrays += 1;
assert_eq!((*id, *class_id, *len, data.len()), (0x20, 0x100, 2, 16));
}
HeapRecord::PrimitiveArray { id, ty, len, data } => {
prim_arrays += 1;
assert_eq!((*id, *ty, *len, data.len()), (0x30, BasicType::Int, 3, 12));
}
HeapRecord::Root { kind, id, thread_serial } => {
roots += 1;
match kind {
HeapRootKind::JavaFrame => assert_eq!((*id, *thread_serial), (0x10, Some(1))),
HeapRootKind::StickyClass => assert_eq!((*id, *thread_serial), (0x100, None)),
other => panic!("unexpected root {other:?}"),
}
}
},
}
}
assert_eq!((utf8, loads, segments), (2, 1, 1));
assert_eq!((classes, instances, obj_arrays, prim_arrays, roots), (1, 1, 1, 1, 2));
assert!(matches!(&records[3], Record::Segment(s) if s.end <= bytes.len()), "segment precedes its contents");
}
#[test]
fn root_kinds_carry_the_thread_serial_they_have() {
let kinds = [
(HeapRootKind::Unknown, false),
(HeapRootKind::JniGlobal, false),
(HeapRootKind::JniLocal, true),
(HeapRootKind::JavaFrame, true),
(HeapRootKind::NativeStack, true),
(HeapRootKind::StickyClass, false),
(HeapRootKind::ThreadBlock, true),
(HeapRootKind::MonitorUsed, false),
(HeapRootKind::ThreadObject, true),
];
let mut w = HprofWriter::new();
for (i, (kind, _)) in kinds.iter().enumerate() {
w.root_in_thread(*kind, 0x40 + i as u64, 7);
w.root(*kind, 0x80 + i as u64);
}
let bytes = w.finish();
let mut seen = Vec::new();
for r in collect(&bytes).unwrap() {
if let Record::Heap { record: HeapRecord::Root { kind, id, thread_serial }, .. } = r {
seen.push((kind, id, thread_serial));
}
}
assert_eq!(seen.len(), kinds.len() * 2);
for (i, (kind, carries)) in kinds.iter().enumerate() {
let explicit = seen[2 * i];
let default = seen[2 * i + 1];
assert_eq!(explicit, (*kind, 0x40 + i as u64, carries.then_some(7)));
assert_eq!(default, (*kind, 0x80 + i as u64, carries.then_some(1)));
}
}
#[test]
fn primitive_arrays_expose_their_contents() {
let mut w = HprofWriter::new();
w.prim_bytes(0x1, BasicType::Char, &[0, b'h', 0, 0xE9]).prim_bytes(0x2, BasicType::Byte, b"v42");
let bytes = w.finish();
let arrays: Vec<_> = collect(&bytes)
.unwrap()
.into_iter()
.filter_map(|r| match r {
Record::Heap { record: HeapRecord::PrimitiveArray { ty, len, data, .. }, .. } => {
Some((ty, len, data.to_vec()))
}
_ => None,
})
.collect();
assert_eq!(arrays, [(BasicType::Char, 2, vec![0, b'h', 0, 0xE9]), (BasicType::Byte, 3, b"v42".to_vec())]);
}
#[test]
fn mini_heap_builds_strings_and_defines_object_and_class() {
let mut heap = MiniHeap::new();
heap.string(0x10, "v42", true).string(0x20, "hé", false);
let bytes = heap.bytes();
let records = collect(&bytes).unwrap();
let names: Vec<_> = records
.iter()
.filter_map(|r| {
if let Record::Utf8 { text, .. } = r { Some(String::from_utf8_lossy(text).into_owned()) } else { None }
})
.collect();
assert!(names.iter().any(|n| n == "java/lang/Object") && names.iter().any(|n| n == "java/lang/Class"));
let arrays: Vec<_> = records
.iter()
.filter_map(|r| match r {
Record::Heap { record: HeapRecord::PrimitiveArray { data, .. }, .. } => Some(data.to_vec()),
_ => None,
})
.collect();
assert_eq!(arrays, [b"v42".to_vec(), vec![b'h', 0, 0xE9, 0]]);
let coders: Vec<_> = records
.iter()
.filter_map(|r| match r {
Record::Heap { record: HeapRecord::Instance { id, data, .. }, .. } => Some((*id, data[8])),
_ => None,
})
.collect();
assert_eq!(coders, [(0x10, 0), (0x20, 1)]);
}
#[test]
fn mini_heap_lays_out_fields_class_first_then_super() {
let mut heap = MiniHeap::new();
heap.class("A", Some("java.lang.Object"), &[("a", BasicType::Int)])
.class("B", Some("A"), &[("b", BasicType::Object), ("c", BasicType::Byte)])
.object(0x10, "B", &[("a", 7), ("b", 0x99), ("c", 0x1FF)]);
let bytes = heap.bytes();
let data = collect(&bytes)
.unwrap()
.into_iter()
.find_map(|r| match r {
Record::Heap { record: HeapRecord::Instance { data, .. }, .. } => Some(data.to_vec()),
_ => None,
})
.unwrap();
assert_eq!(data, [0, 0, 0, 0, 0, 0, 0, 0x99, 0xFF, 0, 0, 0, 7]);
}
#[test]
fn record_at_reads_back_an_instance() {
let mut w = HprofWriter::new();
all_kinds(&mut w);
let bytes = w.finish();
let at = collect(&bytes)
.unwrap()
.into_iter()
.find_map(|r| match r {
Record::Heap { at, record: HeapRecord::Instance { .. } } => Some(at),
_ => None,
})
.unwrap();
match record_at(&bytes, at, 8).unwrap() {
HeapRecord::Instance { id, class_id, data } => assert_eq!((id, class_id, data.len()), (0x10, 0x100, 16)),
other => panic!("expected an instance, got {other:?}"),
}
assert!(matches!(record_at(&bytes, bytes.len(), 8), Err(HeapError::Truncated { .. })));
assert!(matches!(record_at(&bytes, at, 3), Err(HeapError::UnsupportedIdSize(3))));
}
#[test]
fn scan_segment_visits_the_same_records_scan_does() {
let mut w = HprofWriter::new();
all_kinds(&mut w);
let bytes = w.finish();
let from_scan: Vec<_> = collect(&bytes)
.unwrap()
.into_iter()
.filter_map(|r| if let Record::Heap { at, record } = r { Some((at, record)) } else { None })
.collect();
let mut from_segment = Vec::new();
scan_segment(&bytes, segment_of(&bytes), 8, &mut |at, record| {
from_segment.push((at, record));
Ok(())
})
.unwrap();
assert_eq!(from_scan.len(), 6);
assert_eq!(from_scan, from_segment);
}
#[test]
fn visitor_errors_stop_the_scan() {
let bytes = MiniHeap::new().bytes();
let header = parse_header(&bytes).unwrap();
let mut calls = 0;
let result = scan(&bytes, &header, &mut |_| {
calls += 1;
Err(HeapError::Cancelled)
});
assert!(matches!(result, Err(HeapError::Cancelled)));
assert_eq!(calls, 1);
}
#[test]
fn both_heap_dump_tags_are_segments() {
let bytes = MiniHeap::new().bytes();
let segment = segment_of(&bytes);
let mut old_style = bytes.clone();
old_style[segment.start - 9] = 0x0C;
assert_eq!(segment_of(&old_style), segment);
}
#[test]
fn id_size_4_dump_parses() {
let mut w = HprofWriter::with_id_size(4);
w.string(1, "Node")
.load_class(0x100, 1)
.class(0x100, 0, &[(2, BasicType::Object), (3, BasicType::Long)], &[(2, 0x10)])
.instance(0x10, 0x100, &[0u8; 12])
.obj_array(0x20, 0x100, &[0x10, 0, 0xFFFF_FFFF])
.prim_array(0x30, BasicType::Short, 5)
.root(HeapRootKind::ThreadObject, 0x10);
let bytes = w.finish();
let header = parse_header(&bytes).unwrap();
assert_eq!((header.id_size, header.body_start), (4, 31));
let records: Vec<_> = collect(&bytes)
.unwrap()
.into_iter()
.filter_map(|r| if let Record::Heap { record, .. } = r { Some(record) } else { None })
.collect();
assert_eq!(records.len(), 5);
match &records[0] {
HeapRecord::Class(c) => {
assert_eq!((c.id, c.statics.as_slice(), c.fields.len()), (0x100, &[(2, 0x10)][..], 2));
}
other => panic!("expected the class, got {other:?}"),
}
assert!(matches!(&records[1], HeapRecord::Instance { id: 0x10, class_id: 0x100, data } if data.len() == 12));
assert!(
matches!(&records[2], HeapRecord::ObjectArray { len: 3, data, .. } if data.len() == 12 && data[8..] == [0xFF; 4])
);
assert!(
matches!(&records[3], HeapRecord::PrimitiveArray { ty: BasicType::Short, len: 5, data, .. } if data.len() == 10)
);
assert!(matches!(
&records[4],
HeapRecord::Root { kind: HeapRootKind::ThreadObject, id: 0x10, thread_serial: Some(1) }
));
}
fn push_id(out: &mut Vec<u8>, v: u64) {
out.extend_from_slice(&v.to_be_bytes());
}
/// A class dump written by hand: loader, a constant-pool entry, and statics of each shape.
fn class_dump_bytes(last_field_type: u8) -> Vec<u8> {
let mut b = vec![0x20];
push_id(&mut b, 0x500);
b.extend_from_slice(&0u32.to_be_bytes());
for id in [0x400, 0x77, 0, 0, 0, 0] {
push_id(&mut b, id); // super, loader, signers, domain, 2 reserved
}
b.extend_from_slice(&24u32.to_be_bytes());
b.extend_from_slice(&[0, 1, 0, 7, 10, 0, 0, 0, 99]); // constant pool: one int
b.extend_from_slice(&[0, 3]);
push_id(&mut b, 0xA);
b.push(2);
push_id(&mut b, 0xBEEF); // object static
push_id(&mut b, 0xB);
b.push(10);
b.extend_from_slice(&5u32.to_be_bytes()); // int static
push_id(&mut b, 0xC);
b.push(11);
b.extend_from_slice(&6u64.to_be_bytes()); // long static
b.extend_from_slice(&[0, 2]);
push_id(&mut b, 0xD);
b.push(2);
push_id(&mut b, 0xE);
b.push(last_field_type);
b
}
#[test]
fn class_dump_reads_loader_statics_and_skips_the_constant_pool() {
let bytes = class_dump_bytes(11);
let HeapRecord::Class(c) = record_at(&bytes, 0, 8).unwrap() else { panic!("expected a class") };
assert_eq!((c.id, c.super_id, c.loader_id), (0x500, 0x400, 0x77));
assert_eq!(c.statics, [(0xA, 0xBEEF)]);
assert_eq!(c.static_bytes, 12);
assert_eq!(c.fields, [(0xD, BasicType::Object), (0xE, BasicType::Long)]);
}
#[test]
fn unknown_value_type_reports_its_offset() {
let bytes = class_dump_bytes(0x63);
let err = record_at(&bytes, 0, 8).unwrap_err();
assert!(matches!(err, HeapError::UnknownType { ty: 0x63, at } if at == bytes.len() as u64 - 1), "{err:?}");
}
#[test]
fn truncated_dump_reports_offset() {
let mut bytes = MiniHeap::new().bytes();
let body_start = parse_header(&bytes).unwrap().body_start as u64;
bytes.truncate(bytes.len() - 5);
let err = collect(&bytes).unwrap_err();
assert!(matches!(err, HeapError::Truncated { at } if at > body_start && at == bytes.len() as u64), "{err:?}");
assert!(err.to_string().contains(&bytes.len().to_string()));
}
/// HotSpot flushes whole segments, so a JVM killed while dumping leaves a file that ends
/// right after one, without HEAP DUMP END.
#[test]
fn a_dump_the_jvm_did_not_finish_ends_early() {
let mut bytes = MiniHeap::new().bytes();
bytes.truncate(bytes.len() - RECORD_HEADER_LEN);
let err = collect(&bytes).unwrap_err();
assert!(matches!(err, HeapError::Truncated { at } if at == bytes.len() as u64), "{err:?}");
assert!(err.to_string().starts_with("the dump ends early"), "{err}");
}
#[test]
fn every_prefix_is_ok_or_truncated_at_its_length() {
let mut heap = MiniHeap::new();
heap.class("N", Some("java.lang.Object"), &[("next", BasicType::Object)])
.object(0x10, "N", &[("next", 0x20)])
.string(0x20, "x", true)
.root(HeapRootKind::ThreadObject, 0x10);
let bytes = heap.bytes();
let header = parse_header(&bytes).unwrap();
let segment = segment_of(&bytes);
for cut in header.body_start..bytes.len() {
let prefix = &bytes[..cut];
match scan(prefix, &header, &mut |_| Ok(())) {
// Only a prefix without heap data is a complete (empty) dump.
Ok(()) => assert!(cut < segment.start, "cut at {cut} has heap data but no end"),
Err(HeapError::Truncated { at }) => assert_eq!(at, cut as u64, "cut at {cut}"),
Err(other) => panic!("cut at {cut}: {other:?}"),
}
}
let past_end = HprofHeader { body_start: bytes.len() + 1, ..header };
assert!(matches!(scan(&bytes, &past_end, &mut |_| Ok(())), Err(HeapError::Truncated { .. })));
}
#[test]
fn sub_record_overrunning_its_segment_is_truncated() {
let mut bytes = MiniHeap::new().bytes();
let segment = segment_of(&bytes);
let len_at = segment.start - 4;
let shrunk = (segment.len() as u32 - 3).to_be_bytes();
bytes[len_at..segment.start].copy_from_slice(&shrunk);
let err = collect(&bytes).unwrap_err();
assert!(matches!(err, HeapError::Truncated { at } if at == segment.end as u64 - 3), "{err:?}");
}
#[test]
fn unknown_sub_record_is_an_error() {
let mut bytes = MiniHeap::new().bytes();
let segment = segment_of(&bytes);
bytes[segment.start] = 0x99;
let err = collect(&bytes).unwrap_err();
assert!(matches!(err, HeapError::UnknownSubRecord { tag: 0x99, at } if at == segment.start as u64), "{err:?}");
assert!(err.to_string().contains("0x99"));
}
#[test]
fn array_lengths_larger_than_the_dump_do_not_allocate_or_panic() {
let mut b = vec![0x23];
push_id(&mut b, 1);
b.extend_from_slice(&0u32.to_be_bytes());
b.extend_from_slice(&u32::MAX.to_be_bytes());
b.push(11);
assert!(matches!(record_at(&b, 0, 8), Err(HeapError::Truncated { .. })));
b[0] = 0x22;
assert!(matches!(record_at(&b, 0, 8), Err(HeapError::Truncated { .. })));
}
#[test]
fn primitive_array_of_objects_is_an_unknown_type() {
let mut b = vec![0x23];
push_id(&mut b, 1);
b.extend_from_slice(&[0, 0, 0, 0, 0, 0, 0, 0]);
b.push(2);
assert!(matches!(record_at(&b, 0, 8), Err(HeapError::UnknownType { ty: 2, .. })));
}
#[test]
fn basic_type_sizes_and_names() {
assert_eq!(BasicType::from_u8(10), Some(BasicType::Int));
assert_eq!([0, 1, 3, 12, 255].map(BasicType::from_u8), [None; 5]);
assert_eq!((BasicType::Object.hprof_size(4), BasicType::Object.hprof_size(8)), (4, 8));
assert_eq!((BasicType::Object.heap_size(4), BasicType::Long.heap_size(4)), (4, 8));
assert_eq!((BasicType::Char.hprof_size(8), BasicType::Boolean.heap_size(8)), (2, 1));
assert_eq!(
(BasicType::Int.array_name(), BasicType::Boolean.array_name(), BasicType::Long.array_name()),
("[I", "[Z", "[J")
);
}
fn sample() -> Vec<u8> {
let mut heap = MiniHeap::new();
heap.class("Node", Some("java.lang.Object"), &[("next", BasicType::Object), ("v", BasicType::Long)])
.class("[LNode;", Some("java.lang.Object"), &[])
.object(0x10, "Node", &[("next", 0x20), ("v", 5)])
.object(0x20, "Node", &[])
.array_of(0x30, "[LNode;", &[0x10, 0x20, 0])
.prim(0x40, BasicType::Int, 3)
.string(0x50, "hello", true)
.root(HeapRootKind::ThreadObject, 0x10)
.root(HeapRootKind::JniGlobal, 0x30);
heap.bytes()
}
fn with_header(id_size: u8, body: &[u8]) -> Vec<u8> {
let mut bytes = MAGIC_1_0_2.to_vec();
bytes.extend_from_slice(&u32::from(id_size).to_be_bytes());
bytes.extend_from_slice(&1_700_000_000_000u64.to_be_bytes());
bytes.extend_from_slice(body);
bytes
}
proptest! {
#[test]
fn parser_never_panics(bytes in proptest::collection::vec(any::<u8>(), 0..4096)) {
let _ = parse_header(&bytes).and_then(|h| scan(&bytes, &h, &mut |_| Ok(())));
}
/// Random bytes alone fail the magic check, so this puts a valid header in front to make
/// `scan` and `scan_segment` run on arbitrary record streams.
#[test]
fn random_bytes_after_a_valid_header_never_panic(
id_size in prop_oneof![Just(4u8), Just(8u8)],
body in proptest::collection::vec(any::<u8>(), 0..4096),
) {
let bytes = with_header(id_size, &body);
let header = parse_header(&bytes).unwrap();
prop_assert_eq!(header.id_size, id_size);
let _ = scan(&bytes, &header, &mut |_| Ok(()));
let _ = scan_segment(&bytes, header.body_start..bytes.len(), id_size, &mut |_, _| Ok(()));
for at in header.body_start..bytes.len() {
let _ = record_at(&bytes, at, id_size);
}
}
/// Same, but every record has a correct length so the random bytes reach the heap-dump
/// segments and the sub-record parsers instead of stopping at the first bad length.
#[test]
fn random_records_after_a_valid_header_never_panic(
id_size in prop_oneof![Just(4u8), Just(8u8)],
records in proptest::collection::vec(
(
prop_oneof![Just(0x01u8), Just(0x02), Just(0x0C), Just(0x1C), Just(0x2C), any::<u8>()],
prop_oneof![
Just(0x20u8), Just(0x21), Just(0x22), Just(0x23), Just(0x01), Just(0x02), Just(0x03),
Just(0x04), Just(0x05), Just(0x06), Just(0x07), Just(0x08), Just(0xFF), any::<u8>()
],
proptest::collection::vec(any::<u8>(), 0..96),
),
0..12,
),
) {
let mut body = Vec::new();
for (tag, first, rest) in records {
let mut record_body = vec![first];
record_body.extend_from_slice(&rest);
body.push(tag);
body.extend_from_slice(&0u32.to_be_bytes());
body.extend_from_slice(&(record_body.len() as u32).to_be_bytes());
body.extend_from_slice(&record_body);
}
let bytes = with_header(id_size, &body);
let header = parse_header(&bytes).unwrap();
let mut segments = Vec::new();
let _ = scan(&bytes, &header, &mut |r| {
if let Record::Segment(s) = r {
segments.push(s);
}
Ok(())
});
for s in segments {
let _ = scan_segment(&bytes, s, id_size, &mut |_, _| Ok(()));
}
}
#[test]
fn mutated_dump_never_panics(flips in proptest::collection::vec((0usize..2048, any::<u8>()), 1..16)) {
let pristine = sample();
let header = parse_header(&pristine).unwrap();
let segment = segment_of(&pristine);
let mut bytes = pristine.clone();
for (pos, value) in flips {
let at = pos % bytes.len();
bytes[at] = value;
}
let _ = scan(&bytes, &header, &mut |_| Ok(()));
for id_size in [4, 8] {
let _ = scan_segment(&bytes, segment.clone(), id_size, &mut |_, _| Ok(()));
}
for at in 0..bytes.len() {
let _ = record_at(&bytes, at, 8);
}
}
}
}
-327
View File
@@ -1,327 +0,0 @@
//! Maps hprof object ids (addresses) to dense `u32` indices in ascending address order.
//!
//! Object ids are addresses and objects are at least 8 bytes apart, so one bit per 8-byte slot
//! ranks ids at about a byte per object. Addresses are grouped in 1 MiB chunks of
//! [`WORDS_PER_CHUNK`] words; only chunks holding an id get words, and a dense table maps a chunk
//! to its first word. The rank of an id is the number of set bits before its word plus the set
//! bits below it in the word. Ids that are not multiples of 8, or that span too wide an address
//! range for the table, use a sorted array and binary search instead.
mod builder;
pub(crate) use builder::ChunkHasher;
pub use builder::IdMapBuilder;
use crate::column::{Column, NONE};
const SLOT_SHIFT: u32 = 3;
const CHUNK_SLOT_BITS: u32 = 17;
const WORD_BITS: u64 = 64;
const WORDS_PER_CHUNK: usize = (1 << CHUNK_SLOT_BITS) / WORD_BITS as usize;
// The bit table is matched in hot paths; boxing the big variant would only add
// an indirection to save stack space `IdMap` never holds by value in bulk.
#[allow(clippy::large_enum_variant)]
enum Repr {
Bits {
/// Chunk number of the first table entry.
min_chunk: u64,
words: Column<u64>,
/// Set bits before each word.
wrank: Column<u32>,
/// Per chunk from `min_chunk` up: index of its first word, or `NONE` when it has no id.
table: Column<u32>,
/// Per chunk that has words, in word order: its offset from `min_chunk`.
chunk_offsets: Column<u32>,
len: u32,
},
Sorted(Column<u64>),
}
/// Ids ranked in ascending address order: the index of an object is its position in the order.
pub struct IdMap {
repr: Repr,
}
impl IdMap {
pub fn len(&self) -> u32 {
match &self.repr {
Repr::Bits { len, .. } => *len,
Repr::Sorted(ids) => ids.len() as u32,
}
}
pub fn is_empty(&self) -> bool {
self.len() == 0
}
/// The index of `id`, or `None` when it is not in the map.
pub fn rank(&self, id: u64) -> Option<u32> {
match &self.repr {
Repr::Sorted(ids) => ids.binary_search(&id).ok().map(|r| r as u32),
Repr::Bits { min_chunk, words, wrank, table, .. } => {
if id & 7 != 0 {
return None;
}
let slot = id >> SLOT_SHIFT;
let offset = (slot >> CHUNK_SLOT_BITS).checked_sub(*min_chunk)?;
let first = *table.get(usize::try_from(offset).ok()?)?;
if first == NONE {
return None;
}
let w = first as usize + (slot >> 6) as usize % WORDS_PER_CHUNK;
let bit = slot & 63;
let word = words[w];
if word >> bit & 1 == 0 {
return None;
}
Some(wrank[w] + (word & ((1u64 << bit) - 1)).count_ones())
}
}
}
/// The id with index `rank`. Panics when `rank >= len()`.
pub fn id_at(&self, rank: u32) -> u64 {
match &self.repr {
Repr::Sorted(ids) => ids[rank as usize],
Repr::Bits { words, wrank, len, .. } => {
assert!(rank < *len, "rank {rank} out of range for {len} ids");
let w = wrank.partition_point(|&before| before <= rank) - 1;
let mut word = words[w];
for _ in 0..rank - wrank[w] {
word &= word - 1;
}
(self.word_first_slot(w) + u64::from(word.trailing_zeros())) << SLOT_SHIFT
}
}
}
/// All ids in ascending order.
pub fn ids(&self) -> impl Iterator<Item = u64> + '_ {
Ids { map: self, next: 0, slot_base: 0, rest: 0 }
}
/// Bytes of all the columns, in RAM or on disk.
pub fn column_bytes(&self) -> u64 {
match &self.repr {
Repr::Sorted(ids) => std::mem::size_of_val(&**ids) as u64,
Repr::Bits { words, wrank, table, chunk_offsets, .. } => {
(std::mem::size_of_val(&**words)
+ std::mem::size_of_val(&**wrank)
+ std::mem::size_of_val(&**table)
+ std::mem::size_of_val(&**chunk_offsets)) as u64
}
}
}
/// Slot number of bit 0 of word `w` (bitmap layout only).
fn word_first_slot(&self, w: usize) -> u64 {
let Repr::Bits { min_chunk, chunk_offsets, .. } = &self.repr else {
unreachable!("sorted layout has no words")
};
let chunk = min_chunk + u64::from(chunk_offsets[w / WORDS_PER_CHUNK]);
(chunk << CHUNK_SLOT_BITS) + (w % WORDS_PER_CHUNK) as u64 * WORD_BITS
}
}
struct Ids<'a> {
map: &'a IdMap,
/// Next word (bitmap layout) or next id (sorted layout).
next: usize,
slot_base: u64,
/// Bits of the current word not yielded yet.
rest: u64,
}
impl Iterator for Ids<'_> {
type Item = u64;
fn next(&mut self) -> Option<u64> {
match &self.map.repr {
Repr::Sorted(ids) => {
let id = *ids.get(self.next)?;
self.next += 1;
Some(id)
}
Repr::Bits { words, .. } => loop {
if self.rest != 0 {
let bit = u64::from(self.rest.trailing_zeros());
self.rest &= self.rest - 1;
return Some((self.slot_base + bit) << SLOT_SHIFT);
}
self.rest = *words.get(self.next)?;
self.slot_base = self.map.word_first_slot(self.next);
self.next += 1;
},
}
}
}
#[cfg(test)]
mod tests {
use ide_core::CancellationToken;
use super::*;
use crate::column::Store;
/// Deterministic generator so failures replay; the crate has no `rand`.
struct XorShift(u64);
impl XorShift {
fn next(&mut self) -> u64 {
self.0 ^= self.0 << 13;
self.0 ^= self.0 >> 7;
self.0 ^= self.0 << 17;
self.0
}
}
fn build(ids: &[u64], store: &Store) -> IdMap {
let mut builder = IdMapBuilder::new();
for &id in ids {
builder.insert(id);
}
builder.build(store, &CancellationToken::new()).unwrap()
}
fn assert_matches_model(map: &IdMap, model: &[u64]) {
assert_eq!(map.len() as usize, model.len());
assert_eq!(map.ids().collect::<Vec<_>>(), model);
for (rank, &id) in model.iter().enumerate() {
assert_eq!(map.rank(id), Some(rank as u32), "rank of {id:#x}");
assert_eq!(map.id_at(rank as u32), id, "id at {rank}");
for near in [id.wrapping_sub(8), id.wrapping_add(8), id.wrapping_add(1), id.wrapping_add(4)] {
if model.binary_search(&near).is_err() {
assert_eq!(map.rank(near), None, "{near:#x} was never inserted");
}
}
}
}
#[test]
fn rank_follows_address_order() {
let map = build(&[0x2000, 0x1000, 0x1010, 0x7_0000_0000], &Store::Ram);
assert_eq!(map.len(), 4);
assert_eq!(
[0x1000, 0x1010, 0x2000, 0x7_0000_0000].map(|id| map.rank(id)),
[Some(0), Some(1), Some(2), Some(3)]
);
assert_eq!(map.rank(0x1008), None);
assert_eq!(map.rank(0), None);
assert_eq!(map.id_at(2), 0x2000);
assert_eq!(map.ids().collect::<Vec<_>>(), [0x1000, 0x1010, 0x2000, 0x7_0000_0000]);
}
#[test]
fn unaligned_ids_use_sorted_fallback() {
let map = build(&[0x2000, 0x1004, 0x1000, 0x1010, 0x7_0000_0000], &Store::Ram);
assert_eq!(
[0x1000, 0x1004, 0x1010, 0x2000, 0x7_0000_0000].map(|id| map.rank(id)),
[Some(0), Some(1), Some(2), Some(3), Some(4)]
);
assert_eq!(map.rank(0x1008), None);
assert_eq!(map.id_at(1), 0x1004);
}
#[test]
fn sparse_wide_span_uses_fallback() {
let map = build(&[0x1000 + (1 << 50), 0x1000], &Store::Ram);
assert_eq!(map.rank(0x1000), Some(0));
assert_eq!(map.rank(0x1000 + (1 << 50)), Some(1));
assert_eq!(map.rank(0x1008), None);
assert!(map.column_bytes() < 64, "a two-id map must not allocate a chunk table");
}
#[test]
fn ten_million_ids_cost_about_a_byte_each() {
let mut builder = IdMapBuilder::new();
for i in 0..10_000_000u64 {
builder.insert(0x7_0000_0000 + i * 32);
}
let map = builder.build(&Store::Ram, &CancellationToken::new()).unwrap();
assert_eq!(map.len(), 10_000_000);
assert!(map.column_bytes() < 16_000_000, "{} bytes", map.column_bytes());
assert_eq!(map.rank(0x7_0000_0000 + 9_999_999 * 32), Some(9_999_999));
assert_eq!(map.id_at(5_000_000), 0x7_0000_0000 + 5_000_000 * 32);
}
#[test]
fn empty_map_and_duplicates() {
let map = build(&[], &Store::Ram);
assert!(map.is_empty());
assert_eq!(map.rank(0x1000), None);
assert_eq!(map.ids().count(), 0);
let map = build(&[0x1000, 0x1000, 0x1008, 0x1000], &Store::Ram);
assert_eq!(map.len(), 2);
assert_eq!(map.rank(0x1008), Some(1));
}
#[test]
fn chunk_boundaries_and_gaps_between_chunks() {
let ids = [0, 0xF_FFF8, 0x10_0000, 0x10_0008, 0x50_0000, 0x1_0000_0000];
let mut model = ids.to_vec();
model.sort_unstable();
let map = build(&ids, &Store::Ram);
assert_matches_model(&map, &model);
}
#[test]
fn ids_outside_the_populated_chunks_are_absent() {
let ids = [0x30_0000, 0x30_0008, 0x70_0000];
let map = build(&ids, &Store::Ram);
assert_matches_model(&map, &ids);
// Chunk 5 lies between the lowest and highest chunk but holds nothing.
assert_eq!(map.rank(0x50_0000), None);
// Chunk 1 is below the lowest populated chunk.
assert_eq!(map.rank(0x10_0000), None);
// Chunk 9 is past the last table entry.
assert_eq!(map.rank(0x900_0000), None);
assert_eq!(map.rank(u64::MAX - 7), None);
}
#[test]
fn highest_address_round_trips() {
let map = build(&[0xFFFF_FFFF_FFFF_FFF8], &Store::Ram);
assert_eq!(map.rank(0xFFFF_FFFF_FFFF_FFF8), Some(0));
assert_eq!(map.id_at(0), 0xFFFF_FFFF_FFFF_FFF8);
let map = build(&[0, 0xFFFF_FFFF_FFFF_FFF8], &Store::Ram);
assert_matches_model(&map, &[0, 0xFFFF_FFFF_FFFF_FFF8]);
}
#[test]
fn random_ids_match_a_sorted_model_in_ram_and_on_disk() {
for seed in 1..=8u64 {
let mut rng = XorShift(seed.wrapping_mul(0x9E37_79B9_7F4A_7C15) | 1);
let aligned = seed % 4 != 0;
let wide = seed % 3 == 0;
let ids: Vec<u64> = (0..3000)
.map(|_| {
let r = rng.next();
let base = if wide { (r >> 20) << 12 } else { 0x6_0000_0000 + (r % (6 << 20)) };
if aligned { base & !7 } else { base }
})
.collect();
let mut model = ids.clone();
model.sort_unstable();
model.dedup();
let dir = tempfile::tempdir().unwrap();
for store in [Store::Ram, Store::Dir(dir.path().to_path_buf())] {
assert_matches_model(&build(&ids, &store), &model);
}
}
}
#[test]
fn dir_store_keeps_the_index_columns_under_stable_names() {
let dir = tempfile::tempdir().unwrap();
let map = build(&[0x1000, 0x2000], &Store::Dir(dir.path().to_path_buf()));
let mut names: Vec<_> =
std::fs::read_dir(dir.path()).unwrap().map(|e| e.unwrap().file_name().into_string().unwrap()).collect();
names.sort();
assert_eq!(names, ["ids.bits.u64", "ids.chunks.u32", "ids.table.u32", "ids.wrank.u32"]);
assert_eq!(map.rank(0x2000), Some(1));
let dir = tempfile::tempdir().unwrap();
build(&[0x1004], &Store::Dir(dir.path().to_path_buf()));
assert!(dir.path().join("ids.sorted.u64").exists());
}
}
-409
View File
@@ -1,409 +0,0 @@
//! Collects object ids in any order and lays them out as an [`IdMap`].
use std::cmp::Reverse;
use std::collections::{BinaryHeap, HashMap};
use std::hash::{BuildHasherDefault, Hasher};
use ide_core::CancellationToken;
use super::{CHUNK_SLOT_BITS, IdMap, Repr, SLOT_SHIFT, WORD_BITS, WORDS_PER_CHUNK};
use crate::column::{NONE, Store};
use crate::error::HeapError;
use crate::files::{IDS_BITS_FILE, IDS_CHUNKS_FILE, IDS_SORTED_FILE, IDS_TABLE_FILE, IDS_WRANK_FILE};
/// Widest chunk range the dense table covers (256 MiB of table at most).
const MAX_CHUNK_SPAN: u64 = 1 << 26;
/// Chunks whose first word index still fits in the table's `u32`.
const MAX_CHUNKS: usize = (NONE as usize - 1) / WORDS_PER_CHUNK;
/// Largest object count: `NONE` and the one after it stay free as sentinels for the columns above.
const MAX_IDS: u64 = NONE as u64 - 2;
const CHUNK_BYTES: u64 = (WORDS_PER_CHUNK * size_of::<u64>()) as u64;
/// The bitmaps may take this much before any id is inserted, then this many bytes per distinct id.
/// A heap that fits in 4 GiB of address space never reaches the base allowance whatever the
/// insertion order; sparse input (one id per chunk) is moved to plain `u64` ids, 8 bytes each,
/// after at most `BITMAP_BASE_BYTES + BITMAP_BYTES_PER_ID * ids` of bitmaps, so builder memory is
/// bounded by the number of ids rather than by the address range they spread over.
const BITMAP_BASE_BYTES: u64 = 64 << 20;
const BITMAP_BYTES_PER_ID: u64 = 32;
/// Longest stretch of work between two looks at the cancellation token.
const CHECK_EVERY: usize = 1 << 20;
/// Chunk numbers are already well spread by a multiplicative hash; SipHash would dominate the
/// per-insert cost on a 100M-object heap. The product keeps the low zero bits of its input, so
/// the high half is folded down for the bucket index. The graph builder keys class and string
/// ids (addresses) with it for the same reason.
#[derive(Default)]
pub(crate) struct ChunkHasher(u64);
impl Hasher for ChunkHasher {
fn finish(&self) -> u64 {
self.0 ^ (self.0 >> 32)
}
fn write(&mut self, bytes: &[u8]) {
for &b in bytes {
self.write_u64(self.0.rotate_left(8) ^ u64::from(b));
}
}
fn write_u64(&mut self, n: u64) {
self.0 = n.wrapping_mul(0x9E37_79B9_7F4A_7C15);
}
}
struct BitChunks {
/// Chunk number → position in `words`.
index: HashMap<u64, usize, BuildHasherDefault<ChunkHasher>>,
words: Vec<Box<[u64]>>,
min: u64,
max: u64,
/// The chunk of the previous insert; ids usually arrive in runs.
last: Option<(u64, usize)>,
distinct: u64,
}
impl BitChunks {
fn new() -> Self {
Self { index: HashMap::default(), words: Vec::new(), min: u64::MAX, max: 0, last: None, distinct: 0 }
}
/// `false` when the id's chunk does not fit the dense table or the bitmap budget; the id is
/// then not recorded and the caller moves to plain ids.
fn insert(&mut self, id: u64) -> bool {
let slot = id >> SLOT_SHIFT;
let chunk = slot >> CHUNK_SLOT_BITS;
let at = match self.last {
Some((c, at)) if c == chunk => at,
_ => match self.index.get(&chunk) {
Some(&at) => at,
None => {
let (min, max) = (self.min.min(chunk), self.max.max(chunk));
let bitmap_bytes = (self.words.len() as u64 + 1) * CHUNK_BYTES;
if self.words.len() >= MAX_CHUNKS
|| max - min >= MAX_CHUNK_SPAN
|| bitmap_bytes > BITMAP_BASE_BYTES + BITMAP_BYTES_PER_ID * self.distinct
{
return false;
}
(self.min, self.max) = (min, max);
self.words.push(vec![0u64; WORDS_PER_CHUNK].into_boxed_slice());
self.index.insert(chunk, self.words.len() - 1);
self.words.len() - 1
}
},
};
self.last = Some((chunk, at));
let word = &mut self.words[at][(slot >> 6) as usize % WORDS_PER_CHUNK];
let bit = 1u64 << (slot & 63);
if *word & bit == 0 {
*word |= bit;
self.distinct += 1;
}
true
}
/// `(chunk number, position in words)` in ascending address order.
fn sorted_chunks(&self) -> Vec<(u64, usize)> {
let mut chunks: Vec<_> = self.index.iter().map(|(&chunk, &at)| (chunk, at)).collect();
chunks.sort_unstable();
chunks
}
/// The recorded ids, ascending.
fn ids(&self) -> BitIds<'_> {
BitIds { chunks: self.sorted_chunks(), words: &self.words, chunk: 0, word: 0, base: 0, rest: 0 }
}
}
struct BitIds<'a> {
chunks: Vec<(u64, usize)>,
words: &'a [Box<[u64]>],
chunk: usize,
word: usize,
/// Slot number of bit 0 of the word `rest` came from.
base: u64,
rest: u64,
}
impl Iterator for BitIds<'_> {
type Item = u64;
fn next(&mut self) -> Option<u64> {
loop {
if self.rest != 0 {
let bit = u64::from(self.rest.trailing_zeros());
self.rest &= self.rest - 1;
return Some((self.base + bit) << SLOT_SHIFT);
}
let &(chunk, at) = self.chunks.get(self.chunk)?;
self.rest = self.words[at][self.word];
self.base = (chunk << CHUNK_SLOT_BITS) + self.word as u64 * WORD_BITS;
self.word += 1;
if self.word == WORDS_PER_CHUNK {
self.word = 0;
self.chunk += 1;
}
}
}
}
pub struct IdMapBuilder {
bits: BitChunks,
/// Set once an id cannot go into `bits`; every later id goes here, and `bits` keeps what it
/// had. Unsorted, with duplicates.
plain: Option<Vec<u64>>,
max_ids: u64,
}
impl Default for IdMapBuilder {
fn default() -> Self {
Self::new()
}
}
impl IdMapBuilder {
pub fn new() -> Self {
Self::with_limit(MAX_IDS)
}
/// `max_ids` is a parameter so tests can reach the too-large path without billions of inserts.
fn with_limit(max_ids: u64) -> Self {
Self { bits: BitChunks::new(), plain: None, max_ids }
}
/// Inserting an id twice is the same as once.
pub fn insert(&mut self, id: u64) {
match &mut self.plain {
Some(plain) => plain.push(id),
None => {
if id & 7 != 0 || !self.bits.insert(id) {
self.plain = Some(vec![id]);
}
}
}
}
/// Fails with [`HeapError::TooLarge`] when there are more than `u32::MAX - 2` distinct ids,
/// and with [`HeapError::Cancelled`] when `cancel` fires (checked at least every `1 << 20`
/// steps).
pub fn build(self, store: &Store, cancel: &CancellationToken) -> Result<IdMap, HeapError> {
match self.plain {
None if self.bits.words.is_empty() => sorted_map(store, &[]),
None => bit_map(&self.bits, store, self.max_ids, cancel),
Some(plain) => merged_map(&self.bits, plain, store, self.max_ids, cancel),
}
}
#[cfg(test)]
fn allocated_bytes(&self) -> u64 {
self.bits.words.len() as u64 * CHUNK_BYTES
+ self.plain.as_ref().map_or(0, |p| (p.capacity() * size_of::<u64>()) as u64)
}
}
fn check(cancel: &CancellationToken) -> Result<(), HeapError> {
if cancel.is_cancelled() { Err(HeapError::Cancelled) } else { Ok(()) }
}
fn sorted_map(store: &Store, ids: &[u64]) -> Result<IdMap, HeapError> {
let mut column = store.column(IDS_SORTED_FILE, ids.len(), 0u64)?;
column.copy_from_slice(ids);
Ok(IdMap { repr: Repr::Sorted(column) })
}
fn bit_map(bits: &BitChunks, store: &Store, max_ids: u64, cancel: &CancellationToken) -> Result<IdMap, HeapError> {
if bits.distinct > max_ids {
return Err(HeapError::TooLarge);
}
let chunks = bits.sorted_chunks();
let span = (bits.max - bits.min + 1) as usize;
let mut words = store.column(IDS_BITS_FILE, chunks.len() * WORDS_PER_CHUNK, 0u64)?;
let mut wrank = store.column(IDS_WRANK_FILE, chunks.len() * WORDS_PER_CHUNK, 0u32)?;
let mut table = store.column(IDS_TABLE_FILE, span, NONE)?;
let mut chunk_offsets = store.column(IDS_CHUNKS_FILE, chunks.len(), 0u32)?;
let mut before = 0u32;
for (ordinal, &(chunk, at)) in chunks.iter().enumerate() {
check(cancel)?;
let first = ordinal * WORDS_PER_CHUNK;
let offset = (chunk - bits.min) as usize;
table[offset] = first as u32;
chunk_offsets[ordinal] = offset as u32;
for (w, &word) in bits.words[at].iter().enumerate() {
words[first + w] = word;
wrank[first + w] = before;
before += word.count_ones();
}
}
Ok(IdMap { repr: Repr::Bits { min_chunk: bits.min, words, wrank, table, chunk_offsets, len: before } })
}
enum Source<'a> {
Bits(BitIds<'a>),
Run(std::iter::Copied<std::slice::Iter<'a, u64>>),
}
impl Iterator for Source<'_> {
type Item = u64;
fn next(&mut self) -> Option<u64> {
match self {
Source::Bits(it) => it.next(),
Source::Run(it) => it.next(),
}
}
}
/// Sorts `plain` in runs and merges the runs with the ids already in `bits` (itself a sorted
/// source), dropping duplicates. A single `sort_unstable` of a very large vector could not be
/// interrupted.
fn merged_map(
bits: &BitChunks,
mut plain: Vec<u64>,
store: &Store,
max_ids: u64,
cancel: &CancellationToken,
) -> Result<IdMap, HeapError> {
for run in plain.chunks_mut(CHECK_EVERY) {
check(cancel)?;
run.sort_unstable();
}
let mut sources = vec![Source::Bits(bits.ids())];
sources.extend(plain.chunks(CHECK_EVERY).map(|run| Source::Run(run.iter().copied())));
let mut heap = BinaryHeap::with_capacity(sources.len());
for (i, source) in sources.iter_mut().enumerate() {
if let Some(id) = source.next() {
heap.push(Reverse((id, i)));
}
}
let upper_bound = bits.distinct as usize + plain.len();
let mut merged = store.scratch::<u64>(upper_bound, 0)?;
let mut count = 0usize;
let mut steps = 0usize;
while let Some(Reverse((id, i))) = heap.pop() {
steps += 1;
if steps.is_multiple_of(CHECK_EVERY) {
check(cancel)?;
}
if let Some(next) = sources[i].next() {
heap.push(Reverse((next, i)));
}
if count > 0 && merged[count - 1] == id {
continue;
}
if count as u64 >= max_ids {
return Err(HeapError::TooLarge);
}
merged[count] = id;
count += 1;
}
let mut column = store.column(IDS_SORTED_FILE, count, 0u64)?;
for (to, from) in column.chunks_mut(CHECK_EVERY).zip(merged[..count].chunks(CHECK_EVERY)) {
check(cancel)?;
to.copy_from_slice(from);
}
Ok(IdMap { repr: Repr::Sorted(column) })
}
#[cfg(test)]
mod tests {
use super::*;
fn insert_all(builder: &mut IdMapBuilder, ids: &[u64]) {
for &id in ids {
builder.insert(id);
}
}
#[test]
fn too_many_ids_is_too_large() {
// Dense layout, then the merged layout (one unaligned id); the duplicate does not count.
for unaligned in [false, true] {
let filled = |limit| {
let mut builder = IdMapBuilder::with_limit(limit);
insert_all(&mut builder, &[0x1000, 0x1008, 0x1010, 0x1010]);
if unaligned {
builder.insert(0x1_0004);
}
builder
};
let distinct = if unaligned { 4 } else { 3 };
let map = filled(distinct).build(&Store::Ram, &CancellationToken::new()).unwrap();
assert_eq!(u64::from(map.len()), distinct);
let err = filled(distinct - 1).build(&Store::Ram, &CancellationToken::new()).err().unwrap();
assert!(matches!(err, HeapError::TooLarge), "{err}");
}
}
#[test]
fn cancelled_build_returns_cancelled() {
let cancelled = CancellationToken::new();
cancelled.cancel();
let mut dense = IdMapBuilder::new();
insert_all(&mut dense, &[0x1000, 0x1008, 0x20_0000]);
assert!(matches!(dense.build(&Store::Ram, &cancelled), Err(HeapError::Cancelled)));
let mut merged = IdMapBuilder::new();
insert_all(&mut merged, &[0x1000, 0x1004, 0x20_0000]);
assert!(matches!(merged.build(&Store::Ram, &cancelled), Err(HeapError::Cancelled)));
let mut ok = IdMapBuilder::new();
insert_all(&mut ok, &[0x1000, 0x1004]);
assert_eq!(ok.build(&Store::Ram, &CancellationToken::new()).unwrap().len(), 2);
}
#[test]
fn sparse_ids_do_not_amplify_builder_memory() {
const IDS: u64 = 2_000_000;
let mut builder = IdMapBuilder::new();
let mut peak = 0;
for i in 0..IDS {
builder.insert(0x1_0000_0000 + (i << 20));
if i % 1024 == 0 {
peak = peak.max(builder.allocated_bytes());
}
}
peak = peak.max(builder.allocated_bytes());
// Bitmaps up to the budget, plus the plain ids' vector, which may have doubled its capacity.
let budget = BITMAP_BASE_BYTES + (BITMAP_BYTES_PER_ID + 2 * size_of::<u64>() as u64) * IDS;
assert!(peak <= budget, "peak {peak} bytes, budget {budget}");
// One bitmap per id would have taken 16 KiB each.
assert!(peak < IDS * CHUNK_BYTES / 100, "peak {peak} bytes");
assert!(builder.plain.is_some(), "sparse input must have left the bitmaps");
let map = builder.build(&Store::Ram, &CancellationToken::new()).unwrap();
assert_eq!(map.len() as u64, IDS);
assert_eq!(map.rank(0x1_0000_0000 + (1_234_567 << 20)), Some(1_234_567));
assert_eq!(map.rank(0x1_0000_0000 + (1_234_567 << 20) + 8), None);
}
#[test]
fn dense_input_in_any_order_stays_in_bitmaps() {
// 4 GiB of address space is the base allowance; random order must not trip the budget.
let mut state = 0x2545_F491_4F6C_DD1Du64;
let mut builder = IdMapBuilder::new();
for _ in 0..300_000 {
state ^= state << 13;
state ^= state >> 7;
state ^= state << 17;
builder.insert((0x7_0000_0000 + (state % (4 << 30))) & !7);
}
assert!(builder.plain.is_none());
assert!(builder.allocated_bytes() <= BITMAP_BASE_BYTES);
}
#[test]
fn chunk_hasher_spreads_chunks_that_share_low_zero_bits() {
let buckets: std::collections::HashSet<u64> = (0..1024u64)
.map(|i| {
let mut hasher = ChunkHasher::default();
hasher.write_u64(i << 12);
hasher.finish() & 1023
})
.collect();
assert!(buckets.len() > 500, "{} buckets for 1024 keys", buckets.len());
}
}
-109
View File
@@ -1,109 +0,0 @@
//! The result of analyzing a heap dump: per-object columns, the class table and the summary.
mod fields;
mod path;
mod queries;
mod rows;
use std::collections::HashMap;
use std::path::Path;
use memmap2::Mmap;
use serde::{Deserialize, Serialize};
use crate::column::Column;
use crate::error::HeapError;
use crate::files::SUMMARY_FILE;
use crate::graph::ClassInfo;
use crate::hprof::HeapRootKind;
use crate::ids::IdMap;
use crate::shallow::SizeSource;
pub(crate) use self::fields::{id_value, instance_fields};
pub use self::rows::{
HeapClassRow, HeapEdge, HeapObjectPage, HeapObjectRef, HeapObjectRow, HeapPathStep, HeapRootPath, MAX_PAGE,
};
/// Counts over instances and arrays; class objects (class dumps) are left out.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapSummary {
/// `reachable_objects + unreachable_objects`.
pub objects: u64,
pub reachable_objects: u64,
pub reachable_bytes: u64,
pub unreachable_objects: u64,
pub unreachable_bytes: u64,
/// Class dumps in the dump.
pub classes: u32,
pub weak_edges_skipped: u64,
pub size_source: SizeSource,
pub analysis_ms: u32,
}
/// One row of the class table, for one type slot.
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct ClassStat {
/// [`crate::display_name`] of the class (`long[]` for a primitive array slot).
pub name: String,
/// Reachable instances.
pub count: u64,
/// Shallow bytes of the reachable instances.
pub shallow: u64,
/// Bytes the reachable instances retain together: the sum of the retained sizes of those
/// with no instance of the same type above them in the dominator tree.
pub retained: u64,
pub unreachable_count: u64,
}
/// Columns are indexed by node: objects `0..root`, then the super-root `root`. Columns of the
/// objects only (`types`, `offsets`) have no entry for the root.
pub struct HeapIndex {
/// The dump, for [`crate::record_at`] at `offsets[v]`.
pub hprof: Mmap,
pub ids: IdMap,
/// Type slot of each object, as in [`crate::HeapGraph::types`].
pub types: Column<u32>,
pub offsets: Column<u64>,
/// Shallow size in units of 8 bytes, rounded up.
pub shallow8: Column<u32>,
/// Retained bytes; 0 for unreachable objects, every reachable byte for the root.
pub retained: Column<u64>,
/// Immediate dominator; [`crate::NONE`] for unreachable objects, `root` for the root.
pub idom: Column<u32>,
/// Children of node `v` in the dominator tree are `kids[kids_start[v]..kids_start[v + 1]]`,
/// by retained size descending, then by node.
pub kids_start: Column<u32>,
pub kids: Column<u32>,
/// Parent on a shortest path from the root (BFS over strong edges); [`crate::NONE`] for
/// unreachable objects, `root` for the root.
pub gc_parent: Column<u32>,
/// By type slot: class slots, then the primitive array slots.
pub classes: Vec<ClassStat>,
/// By class slot, as in [`crate::HeapGraph::classes`].
pub class_info: Vec<ClassInfo>,
/// Type slot of class objects.
pub class_slot: u32,
/// Object → kind and thread serial of its first root record.
pub roots: HashMap<u32, (HeapRootKind, Option<u32>)>,
/// Thread serial → thread object.
pub thread_objects: HashMap<u32, u32>,
pub id_size: u8,
pub summary: HeapSummary,
}
impl HeapIndex {
/// The super-root, whose children in both trees are the rooted objects.
pub fn root(&self) -> u32 {
self.ids.len()
}
}
pub(crate) fn write_summary(dir: &Path, summary: &HeapSummary) -> Result<(), HeapError> {
let json = serde_json::to_vec_pretty(summary).map_err(std::io::Error::from)?;
std::fs::write(dir.join(SUMMARY_FILE), json)?;
Ok(())
}
#[cfg(test)]
mod tests;
-41
View File
@@ -1,41 +0,0 @@
//! Named field values of an instance record.
use super::HeapIndex;
use crate::hprof::BasicType;
pub(crate) struct FieldValue<'a> {
pub(crate) name: &'a str,
pub(crate) ty: BasicType,
/// Big-endian, as in the dump.
pub(crate) bytes: &'a [u8],
/// `java.lang.ref.Reference.referent`, which the graph leaves out.
pub(crate) weak: bool,
}
/// The fields of an instance of class slot `class` whose record holds `data`: the class's own,
/// then each superclass's, as HotSpot lays them out. Stops where `data` ends.
pub(crate) fn instance_fields<'a>(index: &'a HeapIndex, class: u32, data: &'a [u8]) -> Vec<FieldValue<'a>> {
let mut out = Vec::new();
let mut base = 0usize;
let mut cursor = Some(class);
// Super chains end (their cycles are cut), so this is only a bound on corrupt input.
for _ in 0..index.class_info.len() {
let Some(info) = cursor.and_then(|c| index.class_info.get(c as usize)) else { break };
for (k, (name, ty)) in info.fields.iter().enumerate() {
let size = ty.hprof_size(index.id_size);
let Some(bytes) = base.checked_add(size).and_then(|end| data.get(base..end)) else { return out };
out.push(FieldValue { name, ty: *ty, bytes, weak: info.weak_field == Some(k) });
base += size;
}
cursor = info.super_index;
}
out
}
/// A 4- or 8-byte big-endian id.
pub(crate) fn id_value(bytes: &[u8]) -> Option<u64> {
match *bytes {
[a, b, c, d] => Some(u64::from(u32::from_be_bytes([a, b, c, d]))),
_ => Some(u64::from_be_bytes(bytes.try_into().ok()?)),
}
}
-105
View File
@@ -1,105 +0,0 @@
//! Paths to GC roots, along the BFS tree of `gc_parent`.
use super::{HeapEdge, HeapIndex, HeapObjectRef, HeapPathStep, HeapRootPath, id_value, instance_fields};
use crate::column::NONE;
use crate::hprof::{BasicType, HeapRecord, HeapRootKind};
use crate::strings::{char_array_text, string_preview};
const THREAD_NAME_CHARS: usize = 100;
/// Steps a long path keeps at each end: one deep in a long linked list would otherwise send
/// every node over IPC.
const PATH_END_STEPS: u32 = 500;
impl HeapIndex {
/// From `object` up to its GC root, each step with how the next one holds it; past 1000
/// steps, only the 500 at each end. `None` for an unreachable object or a ref that names no
/// object.
pub fn path_to_root(&self, object: HeapObjectRef) -> Option<HeapRootPath> {
let root = self.root();
let mut v = object.0;
if v >= root || self.gc_parent[v as usize] == NONE {
return None;
}
let len = self.path_len(v)?;
let end = PATH_END_STEPS;
let cut = len > 2 * end;
let mut steps = Vec::with_capacity(len.min(2 * end) as usize);
for i in 0..len {
let parent = self.gc_parent[v as usize];
if !cut || i < end || i >= len - end {
let via = if parent == root { self.root_edge(v) } else { self.edge(parent, v) };
steps.push(HeapPathStep { object: self.object_row(HeapObjectRef(v))?, via });
}
v = parent;
}
let omitted = if cut { len - 2 * end } else { 0 };
Some(HeapRootPath { steps, omitted, omitted_after: if cut { end } else { 0 } })
}
/// Steps from `v` to the root; `None` when `gc_parent` leads nowhere.
fn path_len(&self, mut v: u32) -> Option<u32> {
let root = self.root();
// A BFS tree has no cycles; the bound only stops a corrupt column from looping.
for len in 1..=root {
let parent = self.gc_parent[v as usize];
if parent == root {
return Some(len);
}
if parent > root {
return None;
}
v = parent;
}
None
}
fn root_edge(&self, v: u32) -> HeapEdge {
let (kind, serial) = self.roots.get(&v).copied().unwrap_or((HeapRootKind::Unknown, None));
let thread = serial.and_then(|s| self.thread_objects.get(&s)).and_then(|&t| self.thread_name(t));
HeapEdge::Root { root: kind, thread }
}
/// `Thread.name`: a String, or a `char[]` before JDK 9.
fn thread_name(&self, thread: u32) -> Option<String> {
let Some(HeapRecord::Instance { data, .. }) = self.record(thread) else { return None };
let fields = instance_fields(self, *self.types.get(thread as usize)?, data);
let name = fields.iter().find(|f| f.name == "name" && f.ty == BasicType::Object)?;
let target = self.ids.rank(id_value(name.bytes)?)?;
string_preview(self, target, THREAD_NAME_CHARS).or_else(|| char_array_text(self, target, THREAD_NAME_CHARS))
}
/// How `parent` refers to `child`, checked in the order the graph's edges were made. A strong
/// edge from `parent` always exists; the empty field name only covers a dump that changed.
fn edge(&self, parent: u32, child: u32) -> HeapEdge {
self.find_edge(parent, self.ids.id_at(child)).unwrap_or(HeapEdge::Field { name: String::new() })
}
fn find_edge(&self, parent: u32, child_id: u64) -> Option<HeapEdge> {
match self.record(parent)? {
HeapRecord::Instance { data, .. } => {
let class = self.types[parent as usize];
let field = instance_fields(self, class, data)
.into_iter()
.find(|f| !f.weak && f.ty == BasicType::Object && id_value(f.bytes) == Some(child_id));
match field {
Some(f) => Some(HeapEdge::Field { name: f.name.to_owned() }),
None => (self.class_info.get(class as usize)?.id == child_id).then_some(HeapEdge::ClassOf),
}
}
HeapRecord::ObjectArray { data, .. } => {
let index =
data.chunks_exact(usize::from(self.id_size)).position(|item| id_value(item) == Some(child_id))?;
Some(HeapEdge::Element { index: u32::try_from(index).ok()? })
}
HeapRecord::Class(dump) if dump.super_id == child_id => Some(HeapEdge::SuperClass),
HeapRecord::Class(dump) if dump.loader_id == child_id => Some(HeapEdge::ClassLoader),
HeapRecord::Class(_) => {
let info = self.class_info.get(self.class_of_object(parent)?)?;
let (name, _) = info.statics.iter().find(|(_, object)| *object == child_id)?;
Some(HeapEdge::Static { name: name.clone() })
}
HeapRecord::Root { .. } | HeapRecord::PrimitiveArray { .. } => None,
}
}
}
-164
View File
@@ -1,164 +0,0 @@
//! Class table rows, pages of the dominator tree and single object rows.
use std::cmp::Reverse;
use std::collections::{BinaryHeap, HashMap};
use super::{HeapClassRow, HeapIndex, HeapObjectPage, HeapObjectRef, HeapObjectRow, HeapSummary, MAX_PAGE};
use crate::column::NONE;
use crate::hprof::HeapRecord;
use crate::strings::string_preview;
const PREVIEW_CHARS: usize = 100;
impl HeapIndex {
pub fn summary(&self) -> &HeapSummary {
&self.summary
}
/// Types that have objects, by retained size descending, then by name.
pub fn class_rows(&self) -> Vec<HeapClassRow> {
let class_slots = &self.classes[..self.class_info.len().min(self.classes.len())];
let mut names: HashMap<&str, u32> = HashMap::with_capacity(class_slots.len());
for class in class_slots {
*names.entry(class.name.as_str()).or_default() += 1;
}
let mut rows: Vec<HeapClassRow> = self
.classes
.iter()
.enumerate()
.filter(|(_, c)| c.count > 0 || c.unreachable_count > 0)
.map(|(slot, c)| HeapClassRow {
class_index: slot as u32,
name: c.name.clone(),
count: c.count,
shallow: c.shallow,
retained: c.retained,
unreachable_count: c.unreachable_count,
// Primitive array slots have no class dump and so no second loader.
ambiguous: slot < class_slots.len() && names[c.name.as_str()] > 1,
})
.collect();
rows.sort_by(|a, b| b.retained.cmp(&a.retained).then_with(|| a.name.cmp(&b.name)));
rows
}
/// A page of objects by retained size descending, then by index:
///
/// - no `parent`, no `class_index`: the children of the super-root, class objects left out;
/// - `parent`: its children in the dominator tree, of type `class_index` if given;
/// - `class_index` only: every reachable object of that type.
///
/// `limit` is clamped to [`MAX_PAGE`]. A `parent` or `class_index` that names nothing gives an
/// empty page.
pub fn dominated(
&self,
parent: Option<HeapObjectRef>,
class_index: Option<u32>,
offset: u32,
limit: u32,
) -> HeapObjectPage {
let limit = limit.min(MAX_PAGE);
let root = self.root();
if class_index.is_some_and(|c| c as usize >= self.classes.len()) {
return HeapObjectPage { rows: Vec::new(), total: 0 };
}
match (parent, class_index) {
(Some(HeapObjectRef(p)), _) if p >= root => HeapObjectPage { rows: Vec::new(), total: 0 },
(Some(HeapObjectRef(p)), class) => self.page(
self.children(p).filter(|&v| class.is_none_or(|c| self.types[v as usize] == c)),
offset,
limit,
),
(None, None) => {
self.page(self.children(root).filter(|&v| self.types[v as usize] != self.class_slot), offset, limit)
}
(None, Some(class)) => self.largest_of(class, offset, limit),
}
}
/// `None` for a ref that names no object, the super-root included.
pub fn object_row(&self, object: HeapObjectRef) -> Option<HeapObjectRow> {
let v = object.0;
if v >= self.root() {
return None;
}
let i = v as usize;
let slot = self.types[i];
let preview = if slot == self.class_slot {
self.class_of_object(v).and_then(|c| self.classes.get(c)).map(|c| c.name.clone())
} else {
string_preview(self, v, PREVIEW_CHARS)
};
Some(HeapObjectRow {
object,
class_name: self.classes.get(slot as usize).map(|c| c.name.clone()).unwrap_or_default(),
address: format!("{:#x}", self.ids.id_at(v)),
shallow: u64::from(self.shallow8[i]) * 8,
retained: self.retained[i],
has_children: self.kids_start[i + 1] > self.kids_start[i],
preview,
})
}
/// The record of object `v`, or `None` when it cannot be read.
pub(crate) fn record(&self, v: u32) -> Option<HeapRecord<'_>> {
let at = usize::try_from(*self.offsets.get(v as usize)?).ok()?;
crate::hprof::record_at(&self.hprof, at, self.id_size).ok()
}
/// The class slot a class object stands for.
pub(crate) fn class_of_object(&self, v: u32) -> Option<usize> {
if v >= self.root() {
return None;
}
let id = self.ids.id_at(v);
self.class_info.iter().position(|c| c.id == id && c.id != 0)
}
/// Children of node `v` in the dominator tree, already in page order.
fn children(&self, v: u32) -> impl Iterator<Item = u32> + '_ {
let v = v as usize;
self.kids[self.kids_start[v] as usize..self.kids_start[v + 1] as usize].iter().copied()
}
fn page(&self, objects: impl Iterator<Item = u32>, offset: u32, limit: u32) -> HeapObjectPage {
let mut rows = Vec::new();
let mut total = 0u32;
for v in objects {
if total >= offset && total - offset < limit {
rows.extend(self.object_row(HeapObjectRef(v)));
}
total = total.saturating_add(1);
}
HeapObjectPage { rows, total }
}
/// Scans every object: the top `offset + limit` stay in a heap whose top is the smallest.
fn largest_of(&self, class: u32, offset: u32, limit: u32) -> HeapObjectPage {
let count = self.classes[class as usize].count;
let total = u32::try_from(count).unwrap_or(u32::MAX);
let keep = match offset.checked_add(limit) {
Some(keep) if offset < total && limit > 0 => keep.min(total) as usize,
_ => return HeapObjectPage { rows: Vec::new(), total },
};
let mut top: BinaryHeap<Reverse<(u64, Reverse<u32>)>> = BinaryHeap::with_capacity(keep + 1);
for v in 0..self.root() {
let i = v as usize;
if self.types[i] != class || self.idom[i] == NONE {
continue;
}
top.push(Reverse((self.retained[i], Reverse(v))));
if top.len() > keep {
top.pop();
}
}
// Ascending `Reverse` order is descending retained, then ascending index.
let rows = top
.into_sorted_vec()
.into_iter()
.skip(offset as usize)
.filter_map(|Reverse((_, Reverse(v)))| self.object_row(HeapObjectRef(v)))
.collect();
HeapObjectPage { rows, total }
}
}
-95
View File
@@ -1,95 +0,0 @@
//! What the index queries return over IPC.
use serde::{Deserialize, Serialize};
use crate::hprof::HeapRootKind;
/// Most rows one page of [`crate::HeapIndex::dominated`] returns.
pub const MAX_PAGE: u32 = 500;
/// An object of one snapshot: its index in the [`crate::HeapIndex`] columns. Any value may
/// arrive over IPC; queries answer an index that names no object with nothing.
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize, specta::Type)]
#[serde(transparent)]
pub struct HeapObjectRef(pub u32);
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapClassRow {
/// Type slot, as `classIndex` in [`crate::HeapIndex::dominated`].
pub class_index: u32,
pub name: String,
pub count: u64,
pub shallow: u64,
pub retained: u64,
pub unreachable_count: u64,
/// Another class has the same name (several class loaders): nothing joined by name, such as a
/// second snapshot, can tell them apart.
pub ambiguous: bool,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapObjectRow {
pub object: HeapObjectRef,
pub class_name: String,
/// The object's hprof id in hex, `0x1300`.
pub address: String,
pub shallow: u64,
pub retained: u64,
/// Has children in the dominator tree.
pub has_children: bool,
/// The text of a `java.lang.String`, or the name of the class a class object stands for.
pub preview: Option<String>,
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapObjectPage {
pub rows: Vec<HeapObjectRow>,
/// Rows of every page together.
pub total: u32,
}
/// How an object is held by the next step of a path to a GC root.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(tag = "kind", rename_all = "camelCase", rename_all_fields = "camelCase")]
pub enum HeapEdge {
/// An instance field; the name is empty when the dump does not show which one.
Field {
name: String,
},
Element {
index: u32,
},
Static {
name: String,
},
/// From an instance to its class.
ClassOf,
SuperClass,
ClassLoader,
/// `thread` is the name of the thread whose root it is, when the dump has it.
Root {
root: HeapRootKind,
thread: Option<String>,
},
}
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapPathStep {
pub object: HeapObjectRow,
/// How the next step holds this object; on the last step, the root.
pub via: HeapEdge,
}
/// A path from an object up to its GC root. A long one keeps only the steps nearest each end.
#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize, specta::Type)]
#[serde(rename_all = "camelCase")]
pub struct HeapRootPath {
pub steps: Vec<HeapPathStep>,
/// Steps left out between `steps[omitted_after - 1]` and `steps[omitted_after]`; 0 for none.
pub omitted: u32,
pub omitted_after: u32,
}
Loaded 100 of 1007 files, more files were not shown because too many files have changed in this diff. Show more