openharmony/third_party_rust_glob
1
0
Fork 0
mirror of https://gitee.com/openharmony/third_party_rust_glob synced 2024-11-27 01:30:24 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Initial commit.

Browse Source
This commit is contained in:
Alex Crichton 2014-08-22 15:22:13 -07:00
commit abb5da2148
8 changed files with 1341 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
/target
/Cargo.lock

5
.travis.yml Normal file
View File

@ -0,0 +1,5 @@
install:
- curl http://www.rust-lang.org/rustup.sh | sudo sh -
script:
- cargo build --verbose
- cargo test --verbose

5
Cargo.toml Normal file
View File

@ -0,0 +1,5 @@
[package]
name = "glob"
version = "0.0.1"
authors = ["The Rust Project Developers"]

201
LICENSE-APACHE Normal file
View File

@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

25
LICENSE-MIT Normal file
View File

@ -0,0 +1,25 @@
Copyright (c) 2014 The Rust Project Developers
Permission is hereby granted, free of charge, to any
person obtaining a copy of this software and associated
documentation files (the "Software"), to deal in the
Software without restriction, including without
limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software
is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice
shall be included in all copies or substantial portions
of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR
IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.

6
README.md Normal file
View File

@ -0,0 +1,6 @@
glob
====
Support for matching file paths against Unix shell style patterns.
[![Build Status](https://travis-ci.org/rust-lang/glob.svg?branch=master)](https://travis-ci.org/rust-lang/glob)

885
src/lib.rs Normal file
View File

@ -0,0 +1,885 @@
// Copyright 2014 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
/*!
* Support for matching file paths against Unix shell style patterns.
*
* The `glob` and `glob_with` functions, in concert with the `Paths`
* type, allow querying the filesystem for all files that match a particular
* pattern - just like the libc `glob` function (for an example see the `glob`
* documentation). The methods on the `Pattern` type provide functionality
* for checking if individual paths match a particular pattern - in a similar
* manner to the libc `fnmatch` function
*
* For consistency across platforms, and for Windows support, this module
* is implemented entirely in Rust rather than deferring to the libc
* `glob`/`fnmatch` functions.
*/
#![crate_name = "glob"]
#![experimental]
#![crate_type = "rlib"]
#![crate_type = "dylib"]
#![license = "MIT/ASL2"]
#![doc(html_logo_url = "http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png",
html_favicon_url = "http://www.rust-lang.org/favicon.ico")]
use std::cell::Cell;
use std::{cmp, os, path};
use std::io::fs;
use std::path::is_sep;
use std::string::String;
/**
* An iterator that yields Paths from the filesystem that match a particular
* pattern - see the `glob` function for more details.
*/
pub struct Paths {
dir_patterns: Vec<Pattern>,
require_dir: bool,
options: MatchOptions,
todo: Vec<(Path,uint)>,
}
///
/// Return an iterator that produces all the Paths that match the given pattern,
/// which may be absolute or relative to the current working directory.
///
/// This method uses the default match options and is equivalent to calling
/// `glob_with(pattern, MatchOptions::new())`. Use `glob_with` directly if you
/// want to use non-default match options.
///
/// # Example
///
/// Consider a directory `/media/pictures` containing only the files `kittens.jpg`,
/// `puppies.jpg` and `hamsters.gif`:
///
/// ```rust
/// use glob::glob;
///
/// for path in glob("/media/pictures/*.jpg") {
/// println!("{}", path.display());
/// }
/// ```
///
/// The above code will print:
///
/// ```ignore
/// /media/pictures/kittens.jpg
/// /media/pictures/puppies.jpg
/// ```
///
pub fn glob(pattern: &str) -> Paths {
glob_with(pattern, MatchOptions::new())
}
/**
* Return an iterator that produces all the Paths that match the given pattern,
* which may be absolute or relative to the current working directory.
*
* This function accepts Unix shell style patterns as described by `Pattern::new(..)`.
* The options given are passed through unchanged to `Pattern::matches_with(..)` with
* the exception that `require_literal_separator` is always set to `true` regardless of the
* value passed to this function.
*
* Paths are yielded in alphabetical order, as absolute paths.
*/
pub fn glob_with(pattern: &str, options: MatchOptions) -> Paths {
#[cfg(windows)]
fn check_windows_verbatim(p: &Path) -> bool { path::windows::is_verbatim(p) }
#[cfg(not(windows))]
fn check_windows_verbatim(_: &Path) -> bool { false }
// calculate root this way to handle volume-relative Windows paths correctly
let mut root = os::getcwd();
let pat_root = Path::new(pattern).root_path();
if pat_root.is_some() {
if check_windows_verbatim(pat_root.get_ref()) {
// FIXME: How do we want to handle verbatim paths? I'm inclined to return nothing,
// since we can't very well find all UNC shares with a 1-letter server name.
return Paths {
dir_patterns: Vec::new(),
require_dir: false,
options: options,
todo: Vec::new(),
};
}
root.push(pat_root.get_ref());
}
let root_len = pat_root.map_or(0u, |p| p.as_vec().len());
let dir_patterns = pattern.slice_from(cmp::min(root_len, pattern.len()))
.split_terminator(is_sep)
.map(|s| Pattern::new(s))
.collect::<Vec<Pattern>>();
let require_dir = pattern.chars().next_back().map(is_sep) == Some(true);
let mut todo = Vec::new();
if dir_patterns.len() > 0 {
// Shouldn't happen, but we're using -1 as a special index.
assert!(dir_patterns.len() < -1 as uint);
fill_todo(&mut todo, dir_patterns.as_slice(), 0, &root, options);
}
Paths {
dir_patterns: dir_patterns,
require_dir: require_dir,
options: options,
todo: todo,
}
}
impl Iterator<Path> for Paths {
fn next(&mut self) -> Option<Path> {
loop {
if self.dir_patterns.is_empty() || self.todo.is_empty() {
return None;
}
let (path,idx) = self.todo.pop().unwrap();
// idx -1: was already checked by fill_todo, maybe path was '.' or
// '..' that we can't match here because of normalization.
if idx == -1 as uint {
if self.require_dir && !path.is_dir() { continue; }
return Some(path);
}
let ref pattern = self.dir_patterns[idx];
if pattern.matches_with(match path.filename_str() {
// this ugly match needs to go here to avoid a borrowck error
None => {
// FIXME (#9639): How do we handle non-utf8 filenames? Ignore them for now
// Ideally we'd still match them against a *
continue;
}
Some(x) => x
}, self.options) {
if idx == self.dir_patterns.len() - 1 {
// it is not possible for a pattern to match a directory *AND* its children
// so we don't need to check the children
if !self.require_dir || path.is_dir() {
return Some(path);
}
} else {
fill_todo(&mut self.todo, self.dir_patterns.as_slice(),
idx + 1, &path, self.options);
}
}
}
}
}
fn list_dir_sorted(path: &Path) -> Option<Vec<Path>> {
match fs::readdir(path) {
Ok(mut children) => {
children.sort_by(|p1, p2| p2.filename().cmp(&p1.filename()));
Some(children.move_iter().collect())
}
Err(..) => None
}
}
/**
* A compiled Unix shell style pattern.
*/
#[deriving(Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub struct Pattern {
tokens: Vec<PatternToken>,
}
#[deriving(Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
enum PatternToken {
Char(char),
AnyChar,
AnySequence,
AnyWithin(Vec<CharSpecifier> ),
AnyExcept(Vec<CharSpecifier> )
}
#[deriving(Clone, PartialEq, Eq, PartialOrd, Ord, Hash)]
enum CharSpecifier {
SingleChar(char),
CharRange(char, char)
}
#[deriving(PartialEq)]
enum MatchResult {
Match,
SubPatternDoesntMatch,
EntirePatternDoesntMatch
}
impl Pattern {
/**
* This function compiles Unix shell style patterns: `?` matches any single
* character, `*` matches any (possibly empty) sequence of characters and
* `[...]` matches any character inside the brackets, unless the first
* character is `!` in which case it matches any character except those
* between the `!` and the `]`. Character sequences can also specify ranges
* of characters, as ordered by Unicode, so e.g. `[0-9]` specifies any
* character between 0 and 9 inclusive.
*
* The metacharacters `?`, `*`, `[`, `]` can be matched by using brackets
* (e.g. `[?]`). When a `]` occurs immediately following `[` or `[!` then
* it is interpreted as being part of, rather then ending, the character
* set, so `]` and NOT `]` can be matched by `[]]` and `[!]]` respectively.
* The `-` character can be specified inside a character sequence pattern by
* placing it at the start or the end, e.g. `[abc-]`.
*
* When a `[` does not have a closing `]` before the end of the string then
* the `[` will be treated literally.
*/
pub fn new(pattern: &str) -> Pattern {
let chars = pattern.chars().collect::<Vec<_>>();
let mut tokens = Vec::new();
let mut i = 0;
while i < chars.len() {
match chars[i] {
'?' => {
tokens.push(AnyChar);
i += 1;
}
'*' => {
// *, **, ***, ****, ... are all equivalent
while i < chars.len() && chars[i] == '*' {
i += 1;
}
tokens.push(AnySequence);
}
'[' => {
if i <= chars.len() - 4 && chars[i + 1] == '!' {
match chars.slice_from(i + 3).position_elem(&']') {
None => (),
Some(j) => {
let chars = chars.slice(i + 2, i + 3 + j);
let cs = parse_char_specifiers(chars);
tokens.push(AnyExcept(cs));
i += j + 4;
continue;
}
}
}
else if i <= chars.len() - 3 && chars[i + 1] != '!' {
match chars.slice_from(i + 2).position_elem(&']') {
None => (),
Some(j) => {
let cs = parse_char_specifiers(chars.slice(i + 1, i + 2 + j));
tokens.push(AnyWithin(cs));
i += j + 3;
continue;
}
}
}
// if we get here then this is not a valid range pattern
tokens.push(Char('['));
i += 1;
}
c => {
tokens.push(Char(c));
i += 1;
}
}
}
Pattern { tokens: tokens }
}
/**
* Escape metacharacters within the given string by surrounding them in
* brackets. The resulting string will, when compiled into a `Pattern`,
* match the input string and nothing else.
*/
pub fn escape(s: &str) -> String {
let mut escaped = String::new();
for c in s.chars() {
match c {
// note that ! does not need escaping because it is only special inside brackets
'?' | '*' | '[' | ']' => {
escaped.push_char('[');
escaped.push_char(c);
escaped.push_char(']');
}
c => {
escaped.push_char(c);
}
}
}
escaped
}
/**
* Return if the given `str` matches this `Pattern` using the default
* match options (i.e. `MatchOptions::new()`).
*
* # Example
*
* ```rust
* use glob::Pattern;
*
* assert!(Pattern::new("c?t").matches("cat"));
* assert!(Pattern::new("k[!e]tteh").matches("kitteh"));
* assert!(Pattern::new("d*g").matches("doog"));
* ```
*/
pub fn matches(&self, str: &str) -> bool {
self.matches_with(str, MatchOptions::new())
}
/**
* Return if the given `Path`, when converted to a `str`, matches this `Pattern`
* using the default match options (i.e. `MatchOptions::new()`).
*/
pub fn matches_path(&self, path: &Path) -> bool {
// FIXME (#9639): This needs to handle non-utf8 paths
path.as_str().map_or(false, |s| {
self.matches(s)
})
}
/**
* Return if the given `str` matches this `Pattern` using the specified match options.
*/
pub fn matches_with(&self, str: &str, options: MatchOptions) -> bool {
self.matches_from(None, str, 0, options) == Match
}
/**
* Return if the given `Path`, when converted to a `str`, matches this `Pattern`
* using the specified match options.
*/
pub fn matches_path_with(&self, path: &Path, options: MatchOptions) -> bool {
// FIXME (#9639): This needs to handle non-utf8 paths
path.as_str().map_or(false, |s| {
self.matches_with(s, options)
})
}
fn matches_from(&self,
prev_char: Option<char>,
mut file: &str,
i: uint,
options: MatchOptions) -> MatchResult {
let prev_char = Cell::new(prev_char);
let require_literal = |c| {
(options.require_literal_separator && is_sep(c)) ||
(options.require_literal_leading_dot && c == '.'
&& is_sep(prev_char.get().unwrap_or('/')))
};
for (ti, token) in self.tokens.slice_from(i).iter().enumerate() {
match *token {
AnySequence => {
loop {
match self.matches_from(prev_char.get(), file, i + ti + 1, options) {
SubPatternDoesntMatch => (), // keep trying
m => return m,
}
if file.is_empty() {
return EntirePatternDoesntMatch;
}
let (some_c, next) = file.slice_shift_char();
if require_literal(some_c.unwrap()) {
return SubPatternDoesntMatch;
}
prev_char.set(some_c);
file = next;
}
}
_ => {
if file.is_empty() {
return EntirePatternDoesntMatch;
}
let (some_c, next) = file.slice_shift_char();
let c = some_c.unwrap();
let matches = match *token {
AnyChar => {
!require_literal(c)
}
AnyWithin(ref specifiers) => {
!require_literal(c) &&
in_char_specifiers(specifiers.as_slice(),
c,
options)
}
AnyExcept(ref specifiers) => {
!require_literal(c) &&
!in_char_specifiers(specifiers.as_slice(),
c,
options)
}
Char(c2) => {
chars_eq(c, c2, options.case_sensitive)
}
AnySequence => {
unreachable!()
}
};
if !matches {
return SubPatternDoesntMatch;
}
prev_char.set(some_c);
file = next;
}
}
}
if file.is_empty() {
Match
} else {
SubPatternDoesntMatch
}
}
}
// Fills `todo` with paths under `path` to be matched by `patterns[idx]`,
// special-casing patterns to match `.` and `..`, and avoiding `readdir()`
// calls when there are no metacharacters in the pattern.
fn fill_todo(todo: &mut Vec<(Path, uint)>, patterns: &[Pattern], idx: uint, path: &Path,
options: MatchOptions) {
// convert a pattern that's just many Char(_) to a string
fn pattern_as_str(pattern: &Pattern) -> Option<String> {
let mut s = String::new();
for token in pattern.tokens.iter() {
match *token {
Char(c) => s.push_char(c),
_ => return None
}
}
return Some(s);
}
let add = |todo: &mut Vec<_>, next_path: Path| {
if idx + 1 == patterns.len() {
// We know it's good, so don't make the iterator match this path
// against the pattern again. In particular, it can't match
// . or .. globs since these never show up as path components.
todo.push((next_path, -1 as uint));
} else {
fill_todo(todo, patterns, idx + 1, &next_path, options);
}
};
let pattern = &patterns[idx];
match pattern_as_str(pattern) {
Some(s) => {
// This pattern component doesn't have any metacharacters, so we
// don't need to read the current directory to know where to
// continue. So instead of passing control back to the iterator,
// we can just check for that one entry and potentially recurse
// right away.
let special = "." == s.as_slice() || ".." == s.as_slice();
let next_path = path.join(s.as_slice());
if (special && path.is_dir()) || (!special && next_path.exists()) {
add(todo, next_path);
}
},
None => {
match list_dir_sorted(path) {
Some(entries) => {
todo.extend(entries.move_iter().map(|x|(x, idx)));
// Matching the special directory entries . and .. that refer to
// the current and parent directory respectively requires that
// the pattern has a leading dot, even if the `MatchOptions` field
// `require_literal_leading_dot` is not set.
if pattern.tokens.len() > 0 && pattern.tokens[0] == Char('.') {
for &special in [".", ".."].iter() {
if pattern.matches_with(special, options) {
add(todo, path.join(special));
}
}
}
}
None => {}
}
}
}
}
fn parse_char_specifiers(s: &[char]) -> Vec<CharSpecifier> {
let mut cs = Vec::new();
let mut i = 0;
while i < s.len() {
if i + 3 <= s.len() && s[i + 1] == '-' {
cs.push(CharRange(s[i], s[i + 2]));
i += 3;
} else {
cs.push(SingleChar(s[i]));
i += 1;
}
}
cs
}
fn in_char_specifiers(specifiers: &[CharSpecifier], c: char, options: MatchOptions) -> bool {
for &specifier in specifiers.iter() {
match specifier {
SingleChar(sc) => {
if chars_eq(c, sc, options.case_sensitive) {
return true;
}
}
CharRange(start, end) => {
// FIXME: work with non-ascii chars properly (issue #1347)
if !options.case_sensitive && c.is_ascii() && start.is_ascii() && end.is_ascii() {
let start = start.to_ascii().to_lowercase();
let end = end.to_ascii().to_lowercase();
let start_up = start.to_uppercase();
let end_up = end.to_uppercase();
// only allow case insensitive matching when
// both start and end are within a-z or A-Z
if start != start_up && end != end_up {
let start = start.to_char();
let end = end.to_char();
let c = c.to_ascii().to_lowercase().to_char();
if c >= start && c <= end {
return true;
}
}
}
if c >= start && c <= end {
return true;
}
}
}
}
false
}
/// A helper function to determine if two chars are (possibly case-insensitively) equal.
fn chars_eq(a: char, b: char, case_sensitive: bool) -> bool {
if cfg!(windows) && path::windows::is_sep(a) && path::windows::is_sep(b) {
true
} else if !case_sensitive && a.is_ascii() && b.is_ascii() {
// FIXME: work with non-ascii chars properly (issue #1347)
a.to_ascii().eq_ignore_case(b.to_ascii())
} else {
a == b
}
}
/**
* Configuration options to modify the behaviour of `Pattern::matches_with(..)`
*/
#[deriving(Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub struct MatchOptions {
/**
* Whether or not patterns should be matched in a case-sensitive manner. This
* currently only considers upper/lower case relationships between ASCII characters,
* but in future this might be extended to work with Unicode.
*/
pub case_sensitive: bool,
/**
* If this is true then path-component separator characters (e.g. `/` on Posix)
* must be matched by a literal `/`, rather than by `*` or `?` or `[...]`
*/
pub require_literal_separator: bool,
/**
* If this is true then paths that contain components that start with a `.` will
* not match unless the `.` appears literally in the pattern: `*`, `?` or `[...]`
* will not match. This is useful because such files are conventionally considered
* hidden on Unix systems and it might be desirable to skip them when listing files.
*/
pub require_literal_leading_dot: bool
}
impl MatchOptions {
/**
* Constructs a new `MatchOptions` with default field values. This is used
* when calling functions that do not take an explicit `MatchOptions` parameter.
*
* This function always returns this value:
*
* ```rust,ignore
* MatchOptions {
* case_sensitive: true,
* require_literal_separator: false.
* require_literal_leading_dot: false
* }
* ```
*/
pub fn new() -> MatchOptions {
MatchOptions {
case_sensitive: true,
require_literal_separator: false,
require_literal_leading_dot: false
}
}
}
#[cfg(test)]
mod test {
use std::os;
use super::{glob, Pattern, MatchOptions};
#[test]
fn test_absolute_pattern() {
// assume that the filesystem is not empty!
assert!(glob("/*").next().is_some());
assert!(glob("//").next().is_some());
// check windows absolute paths with host/device components
let root_with_device = os::getcwd().root_path().unwrap().join("*");
// FIXME (#9639): This needs to handle non-utf8 paths
assert!(glob(root_with_device.as_str().unwrap()).next().is_some());
}
#[test]
fn test_wildcard_optimizations() {
assert!(Pattern::new("a*b").matches("a___b"));
assert!(Pattern::new("a**b").matches("a___b"));
assert!(Pattern::new("a***b").matches("a___b"));
assert!(Pattern::new("a*b*c").matches("abc"));
assert!(!Pattern::new("a*b*c").matches("abcd"));
assert!(Pattern::new("a*b*c").matches("a_b_c"));
assert!(Pattern::new("a*b*c").matches("a___b___c"));
assert!(Pattern::new("abc*abc*abc").matches("abcabcabcabcabcabcabc"));
assert!(!Pattern::new("abc*abc*abc").matches("abcabcabcabcabcabcabca"));
assert!(Pattern::new("a*a*a*a*a*a*a*a*a").matches("aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"));
assert!(Pattern::new("a*b[xyz]c*d").matches("abxcdbxcddd"));
}
#[test]
fn test_lots_of_files() {
// this is a good test because it touches lots of differently named files
glob("/*/*/*/*").skip(10000).next();
}
#[test]
fn test_range_pattern() {
let pat = Pattern::new("a[0-9]b");
for i in range(0u, 10) {
assert!(pat.matches(format!("a{}b", i).as_slice()));
}
assert!(!pat.matches("a_b"));
let pat = Pattern::new("a[!0-9]b");
for i in range(0u, 10) {
assert!(!pat.matches(format!("a{}b", i).as_slice()));
}
assert!(pat.matches("a_b"));
let pats = ["[a-z123]", "[1a-z23]", "[123a-z]"];
for &p in pats.iter() {
let pat = Pattern::new(p);
for c in "abcdefghijklmnopqrstuvwxyz".chars() {
assert!(pat.matches(c.to_string().as_slice()));
}
for c in "ABCDEFGHIJKLMNOPQRSTUVWXYZ".chars() {
let options = MatchOptions {case_sensitive: false, .. MatchOptions::new()};
assert!(pat.matches_with(c.to_string().as_slice(), options));
}
assert!(pat.matches("1"));
assert!(pat.matches("2"));
assert!(pat.matches("3"));
}
let pats = ["[abc-]", "[-abc]", "[a-c-]"];
for &p in pats.iter() {
let pat = Pattern::new(p);
assert!(pat.matches("a"));
assert!(pat.matches("b"));
assert!(pat.matches("c"));
assert!(pat.matches("-"));
assert!(!pat.matches("d"));
}
let pat = Pattern::new("[2-1]");
assert!(!pat.matches("1"));
assert!(!pat.matches("2"));
assert!(Pattern::new("[-]").matches("-"));
assert!(!Pattern::new("[!-]").matches("-"));
}
#[test]
fn test_unclosed_bracket() {
// unclosed `[` should be treated literally
assert!(Pattern::new("abc[def").matches("abc[def"));
assert!(Pattern::new("abc[!def").matches("abc[!def"));
assert!(Pattern::new("abc[").matches("abc["));
assert!(Pattern::new("abc[!").matches("abc[!"));
assert!(Pattern::new("abc[d").matches("abc[d"));
assert!(Pattern::new("abc[!d").matches("abc[!d"));
assert!(Pattern::new("abc[]").matches("abc[]"));
assert!(Pattern::new("abc[!]").matches("abc[!]"));
}
#[test]
fn test_pattern_matches() {
let txt_pat = Pattern::new("*hello.txt");
assert!(txt_pat.matches("hello.txt"));
assert!(txt_pat.matches("gareth_says_hello.txt"));
assert!(txt_pat.matches("some/path/to/hello.txt"));
assert!(txt_pat.matches("some\\path\\to\\hello.txt"));
assert!(txt_pat.matches("/an/absolute/path/to/hello.txt"));
assert!(!txt_pat.matches("hello.txt-and-then-some"));
assert!(!txt_pat.matches("goodbye.txt"));
let dir_pat = Pattern::new("*some/path/to/hello.txt");
assert!(dir_pat.matches("some/path/to/hello.txt"));
assert!(dir_pat.matches("a/bigger/some/path/to/hello.txt"));
assert!(!dir_pat.matches("some/path/to/hello.txt-and-then-some"));
assert!(!dir_pat.matches("some/other/path/to/hello.txt"));
}
#[test]
fn test_pattern_escape() {
let s = "_[_]_?_*_!_";
assert_eq!(Pattern::escape(s), "_[[]_[]]_[?]_[*]_!_".to_string());
assert!(Pattern::new(Pattern::escape(s).as_slice()).matches(s));
}
#[test]
fn test_pattern_matches_case_insensitive() {
let pat = Pattern::new("aBcDeFg");
let options = MatchOptions {
case_sensitive: false,
require_literal_separator: false,
require_literal_leading_dot: false
};
assert!(pat.matches_with("aBcDeFg", options));
assert!(pat.matches_with("abcdefg", options));
assert!(pat.matches_with("ABCDEFG", options));
assert!(pat.matches_with("AbCdEfG", options));
}
#[test]
fn test_pattern_matches_case_insensitive_range() {
let pat_within = Pattern::new("[a]");
let pat_except = Pattern::new("[!a]");
let options_case_insensitive = MatchOptions {
case_sensitive: false,
require_literal_separator: false,
require_literal_leading_dot: false
};
let options_case_sensitive = MatchOptions {
case_sensitive: true,
require_literal_separator: false,
require_literal_leading_dot: false
};
assert!(pat_within.matches_with("a", options_case_insensitive));
assert!(pat_within.matches_with("A", options_case_insensitive));
assert!(!pat_within.matches_with("A", options_case_sensitive));
assert!(!pat_except.matches_with("a", options_case_insensitive));
assert!(!pat_except.matches_with("A", options_case_insensitive));
assert!(pat_except.matches_with("A", options_case_sensitive));
}
#[test]
fn test_pattern_matches_require_literal_separator() {
let options_require_literal = MatchOptions {
case_sensitive: true,
require_literal_separator: true,
require_literal_leading_dot: false
};
let options_not_require_literal = MatchOptions {
case_sensitive: true,
require_literal_separator: false,
require_literal_leading_dot: false
};
assert!(Pattern::new("abc/def").matches_with("abc/def", options_require_literal));
assert!(!Pattern::new("abc?def").matches_with("abc/def", options_require_literal));
assert!(!Pattern::new("abc*def").matches_with("abc/def", options_require_literal));
assert!(!Pattern::new("abc[/]def").matches_with("abc/def", options_require_literal));
assert!(Pattern::new("abc/def").matches_with("abc/def", options_not_require_literal));
assert!(Pattern::new("abc?def").matches_with("abc/def", options_not_require_literal));
assert!(Pattern::new("abc*def").matches_with("abc/def", options_not_require_literal));
assert!(Pattern::new("abc[/]def").matches_with("abc/def", options_not_require_literal));
}
#[test]
fn test_pattern_matches_require_literal_leading_dot() {
let options_require_literal_leading_dot = MatchOptions {
case_sensitive: true,
require_literal_separator: false,
require_literal_leading_dot: true
};
let options_not_require_literal_leading_dot = MatchOptions {
case_sensitive: true,
require_literal_separator: false,
require_literal_leading_dot: false
};
let f = |options| Pattern::new("*.txt").matches_with(".hello.txt", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(!f(options_require_literal_leading_dot));
let f = |options| Pattern::new(".*.*").matches_with(".hello.txt", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(f(options_require_literal_leading_dot));
let f = |options| Pattern::new("aaa/bbb/*").matches_with("aaa/bbb/.ccc", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(!f(options_require_literal_leading_dot));
let f = |options| Pattern::new("aaa/bbb/*").matches_with("aaa/bbb/c.c.c.", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(f(options_require_literal_leading_dot));
let f = |options| Pattern::new("aaa/bbb/.*").matches_with("aaa/bbb/.ccc", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(f(options_require_literal_leading_dot));
let f = |options| Pattern::new("aaa/?bbb").matches_with("aaa/.bbb", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(!f(options_require_literal_leading_dot));
let f = |options| Pattern::new("aaa/[.]bbb").matches_with("aaa/.bbb", options);
assert!(f(options_not_require_literal_leading_dot));
assert!(!f(options_require_literal_leading_dot));
}
#[test]
fn test_matches_path() {
// on windows, (Path::new("a/b").as_str().unwrap() == "a\\b"), so this
// tests that / and \ are considered equivalent on windows
assert!(Pattern::new("a/b").matches_path(&Path::new("a/b")));
}
}

212
tests/glob-std.rs Normal file
View File

@ -0,0 +1,212 @@
// Copyright 2013-2014 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
// ignore-windows TempDir may cause IoError on windows: #10462
#![feature(macro_rules)]
extern crate glob;
use glob::glob;
use std::os;
use std::io;
use std::io::TempDir;
macro_rules! assert_eq ( ($e1:expr, $e2:expr) => (
if $e1 != $e2 {
fail!("{} != {}", stringify!($e1), stringify!($e2))
}
) )
#[test]
fn main() {
fn mk_file(path: &str, directory: bool) {
if directory {
io::fs::mkdir(&Path::new(path), io::UserRWX).unwrap();
} else {
io::File::create(&Path::new(path)).unwrap();
}
}
fn abs_path(path: &str) -> Path {
os::getcwd().join(&Path::new(path))
}
fn glob_vec(pattern: &str) -> Vec<Path> {
glob(pattern).collect()
}
let root = TempDir::new("glob-tests");
let root = root.expect("Should have created a temp directory");
assert!(os::change_dir(root.path()));
mk_file("aaa", true);
mk_file("aaa/apple", true);
mk_file("aaa/orange", true);
mk_file("aaa/tomato", true);
mk_file("aaa/tomato/tomato.txt", false);
mk_file("aaa/tomato/tomoto.txt", false);
mk_file("bbb", true);
mk_file("bbb/specials", true);
mk_file("bbb/specials/!", false);
// windows does not allow `*` or `?` characters to exist in filenames
if os::consts::FAMILY != "windows" {
mk_file("bbb/specials/*", false);
mk_file("bbb/specials/?", false);
}
mk_file("bbb/specials/[", false);
mk_file("bbb/specials/]", false);
mk_file("ccc", true);
mk_file("xyz", true);
mk_file("xyz/x", false);
mk_file("xyz/y", false);
mk_file("xyz/z", false);
assert_eq!(glob_vec(""), Vec::new());
assert_eq!(glob_vec("."), vec!(os::getcwd()));
assert_eq!(glob_vec(".."), vec!(os::getcwd().join("..")));
assert_eq!(glob_vec("aaa"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aaa/"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("a"), Vec::new());
assert_eq!(glob_vec("aa"), Vec::new());
assert_eq!(glob_vec("aaaa"), Vec::new());
assert_eq!(glob_vec("aaa/apple"), vec!(abs_path("aaa/apple")));
assert_eq!(glob_vec("aaa/apple/nope"), Vec::new());
// windows should support both / and \ as directory separators
if os::consts::FAMILY == "windows" {
assert_eq!(glob_vec("aaa\\apple"), vec!(abs_path("aaa/apple")));
}
assert_eq!(glob_vec("???/"), vec!(
abs_path("aaa"),
abs_path("bbb"),
abs_path("ccc"),
abs_path("xyz")));
assert_eq!(glob_vec("aaa/tomato/tom?to.txt"), vec!(
abs_path("aaa/tomato/tomato.txt"),
abs_path("aaa/tomato/tomoto.txt")));
assert_eq!(glob_vec("xyz/?"), vec!(
abs_path("xyz/x"),
abs_path("xyz/y"),
abs_path("xyz/z")));
assert_eq!(glob_vec("a*"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("*a*"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("a*a"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aaa*"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("*aaa"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("*aaa*"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("*a*a*a*"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aaa*/"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aaa/*"), vec!(
abs_path("aaa/apple"),
abs_path("aaa/orange"),
abs_path("aaa/tomato")));
assert_eq!(glob_vec("aaa/*a*"), vec!(
abs_path("aaa/apple"),
abs_path("aaa/orange"),
abs_path("aaa/tomato")));
assert_eq!(glob_vec("*/*/*.txt"), vec!(
abs_path("aaa/tomato/tomato.txt"),
abs_path("aaa/tomato/tomoto.txt")));
assert_eq!(glob_vec("*/*/t[aob]m?to[.]t[!y]t"), vec!(
abs_path("aaa/tomato/tomato.txt"),
abs_path("aaa/tomato/tomoto.txt")));
assert_eq!(glob_vec("./aaa"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("./*"), glob_vec("*"));
assert_eq!(glob_vec("*/..").pop().unwrap(), abs_path("."));
assert_eq!(glob_vec("aaa/../bbb"), vec!(abs_path("bbb")));
assert_eq!(glob_vec("nonexistent/../bbb"), Vec::new());
assert_eq!(glob_vec("aaa/tomato/tomato.txt/.."), Vec::new());
assert_eq!(glob_vec("aaa/tomato/tomato.txt/"), Vec::new());
assert_eq!(glob_vec("aa[a]"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aa[abc]"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("a[bca]a"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aa[b]"), Vec::new());
assert_eq!(glob_vec("aa[xyz]"), Vec::new());
assert_eq!(glob_vec("aa[]]"), Vec::new());
assert_eq!(glob_vec("aa[!b]"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aa[!bcd]"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("a[!bcd]a"), vec!(abs_path("aaa")));
assert_eq!(glob_vec("aa[!a]"), Vec::new());
assert_eq!(glob_vec("aa[!abc]"), Vec::new());
assert_eq!(glob_vec("bbb/specials/[[]"), vec!(abs_path("bbb/specials/[")));
assert_eq!(glob_vec("bbb/specials/!"), vec!(abs_path("bbb/specials/!")));
assert_eq!(glob_vec("bbb/specials/[]]"), vec!(abs_path("bbb/specials/]")));
if os::consts::FAMILY != "windows" {
assert_eq!(glob_vec("bbb/specials/[*]"), vec!(abs_path("bbb/specials/*")));
assert_eq!(glob_vec("bbb/specials/[?]"), vec!(abs_path("bbb/specials/?")));
}
if os::consts::FAMILY == "windows" {
assert_eq!(glob_vec("bbb/specials/[![]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/]")));
assert_eq!(glob_vec("bbb/specials/[!]]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/[")));
assert_eq!(glob_vec("bbb/specials/[!!]"), vec!(
abs_path("bbb/specials/["),
abs_path("bbb/specials/]")));
} else {
assert_eq!(glob_vec("bbb/specials/[![]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/*"),
abs_path("bbb/specials/?"),
abs_path("bbb/specials/]")));
assert_eq!(glob_vec("bbb/specials/[!]]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/*"),
abs_path("bbb/specials/?"),
abs_path("bbb/specials/[")));
assert_eq!(glob_vec("bbb/specials/[!!]"), vec!(
abs_path("bbb/specials/*"),
abs_path("bbb/specials/?"),
abs_path("bbb/specials/["),
abs_path("bbb/specials/]")));
assert_eq!(glob_vec("bbb/specials/[!*]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/?"),
abs_path("bbb/specials/["),
abs_path("bbb/specials/]")));
assert_eq!(glob_vec("bbb/specials/[!?]"), vec!(
abs_path("bbb/specials/!"),
abs_path("bbb/specials/*"),
abs_path("bbb/specials/["),
abs_path("bbb/specials/]")));
}
}