[lld] r290212 - Move GlobPattern class from LLD to llvm/Support.
Rui Ueyama via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 20 15:09:09 PST 2016
Author: ruiu
Date: Tue Dec 20 17:09:09 2016
New Revision: 290212
URL: http://llvm.org/viewvc/llvm-project?rev=290212&view=rev
Log:
Move GlobPattern class from LLD to llvm/Support.
GlobPattern is a class to handle glob pattern matching. Currently
only LLD is using that, but technically that feature is not specific
to linkers, so in this patch I move that file to LLVM.
Differential Revision: https://reviews.llvm.org/D27969
Modified:
lld/trunk/ELF/Strings.cpp
lld/trunk/ELF/Strings.h
Modified: lld/trunk/ELF/Strings.cpp
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/Strings.cpp?rev=290212&r1=290211&r2=290212&view=diff
==============================================================================
--- lld/trunk/ELF/Strings.cpp (original)
+++ lld/trunk/ELF/Strings.cpp Tue Dec 20 17:09:09 2016
@@ -21,134 +21,14 @@ using namespace llvm;
using namespace lld;
using namespace lld::elf;
-// 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.
-// This function returns the first token in S.
-BitVector GlobPattern::scan(StringRef &S) {
- switch (S[0]) {
- case '*':
- S = S.substr(1);
- // '*' is represented by an empty bitvector.
- // All other bitvectors are 256-bit long.
- return BitVector();
- case '?':
- S = S.substr(1);
- return BitVector(256, true);
- case '[': {
- size_t End = S.find(']', 1);
- if (End == StringRef::npos) {
- error("invalid glob pattern: " + Original);
- S = "";
- return BitVector(256, false);
- }
- StringRef Chars = S.substr(1, End - 1);
- S = S.substr(End + 1);
- if (Chars.startswith("^"))
- return expand(Chars.substr(1)).flip();
- return expand(Chars);
- }
- default:
- BitVector BV(256, false);
- BV[S[0]] = true;
- S = S.substr(1);
- return BV;
- }
-}
-
-// Expands character ranges and returns a bitmap.
-// For example, "a-cf-hz" is expanded to "abcfghz".
-BitVector GlobPattern::expand(StringRef S) {
- BitVector BV(256, false);
-
- // Expand "x-y".
- for (;;) {
- if (S.size() < 3)
- break;
-
- // If it doesn't start with something like "x-y",
- // consume the first character and proceed.
- if (S[1] != '-') {
- BV[S[0]] = true;
- S = S.substr(1);
- continue;
- }
-
- // It must be in the form of "x-y".
- // Validate it and then interpret the range.
- if (S[0] > S[2]) {
- error("invalid glob pattern: " + Original);
- return BV;
- }
- for (int C = S[0]; C <= S[2]; ++C)
- BV[C] = true;
- S = S.substr(3);
- }
-
- for (char C : S)
- BV[C] = true;
- return BV;
-}
-
-GlobPattern::GlobPattern(StringRef S) : Original(S) {
- if (!hasWildcard(S)) {
- // S doesn't contain any metacharacter,
- // so the regular string comparison should work.
- Exact = S;
- } else if (S.endswith("*") && !hasWildcard(S.drop_back())) {
- // S is something like "foo*". We can use startswith().
- Prefix = S.drop_back();
- } else if (S.startswith("*") && !hasWildcard(S.drop_front())) {
- // S is something like "*foo". We can use endswith().
- Suffix = S.drop_front();
- } else {
- // Otherwise, we need to do real glob pattern matching.
- // Parse the pattern now.
- while (!S.empty())
- Tokens.push_back(scan(S));
- }
-}
-
-bool GlobPattern::match(StringRef S) const {
- if (Exact)
- return S == *Exact;
- if (Prefix)
- return S.startswith(*Prefix);
- if (Suffix)
- return S.endswith(*Suffix);
- return matchOne(Tokens, S);
-}
-
-// Runs glob pattern Pats against string S.
-bool GlobPattern::matchOne(ArrayRef<BitVector> Pats, StringRef S) const {
- for (;;) {
- if (Pats.empty())
- return S.empty();
-
- // If Pats[0] is '*', try to match Pats[1..] against all possible
- // substrings of S to see at least one pattern succeeds.
- if (Pats[0].size() == 0) {
- Pats = Pats.slice(1);
- if (Pats.empty())
- // Fast path. If a pattern is '*', it matches anything.
- return true;
- for (size_t I = 0, E = S.size(); I < E; ++I)
- if (matchOne(Pats, S.substr(I)))
- return true;
- return false;
- }
-
- // If Pats[0] is not '*', it must consume one character.
- if (S.empty() || !Pats[0][S[0]])
- return false;
- Pats = Pats.slice(1);
- S = S.substr(1);
- }
-}
-
StringMatcher::StringMatcher(const std::vector<StringRef> &Pat) {
- for (StringRef S : Pat)
- Patterns.push_back(GlobPattern(S));
+ for (StringRef S : Pat) {
+ Expected<GlobPattern> Pat = GlobPattern::create(S);
+ if (!Pat)
+ error(toString(Pat.takeError()));
+ else
+ Patterns.push_back(*Pat);
+ }
}
bool StringMatcher::match(StringRef S) const {
Modified: lld/trunk/ELF/Strings.h
URL: http://llvm.org/viewvc/llvm-project/lld/trunk/ELF/Strings.h?rev=290212&r1=290211&r2=290212&view=diff
==============================================================================
--- lld/trunk/ELF/Strings.h (original)
+++ lld/trunk/ELF/Strings.h Tue Dec 20 17:09:09 2016
@@ -15,6 +15,7 @@
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/GlobPattern.h"
#include <vector>
namespace lld {
@@ -56,30 +57,6 @@ private:
mutable size_t Size;
};
-// This class represents a glob pattern. Supported metacharacters
-// are "*", "?", "[<chars>]" and "[^<chars>]".
-class GlobPattern {
-public:
- explicit GlobPattern(StringRef Pat);
- bool match(StringRef S) const;
-
-private:
- bool matchOne(ArrayRef<llvm::BitVector> Pat, StringRef S) const;
- llvm::BitVector scan(StringRef &S);
- llvm::BitVector expand(StringRef S);
-
- // Parsed glob pattern.
- std::vector<llvm::BitVector> Tokens;
-
- // A glob pattern given to this class. This is for error reporting.
- StringRef Original;
-
- // The following members are for optimization.
- llvm::Optional<StringRef> Exact;
- llvm::Optional<StringRef> Prefix;
- llvm::Optional<StringRef> Suffix;
-};
-
// This class represents multiple glob patterns.
class StringMatcher {
public:
@@ -89,7 +66,7 @@ public:
bool match(StringRef S) const;
private:
- std::vector<GlobPattern> Patterns;
+ std::vector<llvm::GlobPattern> Patterns;
};
// Returns a demangled C++ symbol name. If Name is not a mangled
More information about the llvm-commits
mailing list