Reapply r375051: [support] GlobPattern: add support for \ and [!...], and allow ] in more places

Reland r375051 (reverted in r375052) after fixing lld tests on Windows in r375126 and r375131.

Original description: Update GlobPattern in libSupport to handle a few more cases. It does not fully match the `fnmatch` used by GNU objcopy since named character classes (e.g. `[[:digit:]]`) are not supported, but this should support most existing use cases (mostly just `*` is what's used anyway).

This will be used to implement the `--wildcard` flag in llvm-objcopy to be more compatible with GNU objcopy.

This is split off of D66613 to land the libSupport changes separately. The llvm-objcopy part will land soon.

Reviewers: jhenderson, MaskRay, evgeny777, espindola, alexshap

Reviewed By: MaskRay

Subscribers: nickdesaulniers, emaste, arichardson, hiraditya, jakehehrlich, abrachet, seiya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D66613

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@375149 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jordan Rupprecht
2019-10-17 18:09:05 +00:00
parent 929d131f83
commit 1f0245cf5c
3 changed files with 110 additions and 43 deletions
+16 -7
View File
@@ -19,7 +19,7 @@
using namespace llvm;
static bool hasWildcard(StringRef S) {
return S.find_first_of("?*[") != StringRef::npos;
return S.find_first_of("?*[\\") != StringRef::npos;
}
// Expands character ranges and returns a bitmap.
@@ -60,8 +60,9 @@ static Expected<BitVector> expand(StringRef S, StringRef Original) {
}
// This is a scanner for the glob pattern.
// A glob pattern token is one of "*", "?", "[<chars>]", "[^<chars>]"
// (which is a negative form of "[<chars>]"), or a non-meta character.
// A glob pattern token is one of "*", "?", "\", "[<chars>]", "[^<chars>]"
// (which is a negative form of "[<chars>]"), "[!<chars>]" (which is
// equivalent to "[^<chars>]"), or a non-meta character.
// This function returns the first token in S.
static Expected<BitVector> scan(StringRef &S, StringRef Original) {
switch (S[0]) {
@@ -74,14 +75,16 @@ static Expected<BitVector> scan(StringRef &S, StringRef Original) {
S = S.substr(1);
return BitVector(256, true);
case '[': {
size_t End = S.find(']', 1);
// ']' is allowed as the first character of a character class. '[]' is
// invalid. So, just skip the first character.
size_t End = S.find(']', 2);
if (End == StringRef::npos)
return make_error<StringError>("invalid glob pattern: " + Original,
errc::invalid_argument);
StringRef Chars = S.substr(1, End - 1);
S = S.substr(End + 1);
if (Chars.startswith("^")) {
if (Chars.startswith("^") || Chars.startswith("!")) {
Expected<BitVector> BV = expand(Chars.substr(1), Original);
if (!BV)
return BV.takeError();
@@ -89,6 +92,11 @@ static Expected<BitVector> scan(StringRef &S, StringRef Original) {
}
return expand(Chars, Original);
}
case '\\':
// Eat this character and fall through below to treat it like a non-meta
// character.
S = S.substr(1);
LLVM_FALLTHROUGH;
default:
BitVector BV(256, false);
BV[(uint8_t)S[0]] = true;
@@ -107,8 +115,9 @@ Expected<GlobPattern> GlobPattern::create(StringRef S) {
return Pat;
}
// S is something like "foo*". We can use startswith().
if (S.endswith("*") && !hasWildcard(S.drop_back())) {
// S is something like "foo*", and the "* is not escaped. We can use
// startswith().
if (S.endswith("*") && !S.endswith("\\*") && !hasWildcard(S.drop_back())) {
Pat.Prefix = S.drop_back();
return Pat;
}