[llvm] 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
Added:
llvm/trunk/include/llvm/Support/GlobPattern.h
llvm/trunk/lib/Support/GlobPattern.cpp
llvm/trunk/unittests/Support/GlobPatternTest.cpp
Modified:
llvm/trunk/lib/Support/CMakeLists.txt
llvm/trunk/unittests/Support/CMakeLists.txt
Added: llvm/trunk/include/llvm/Support/GlobPattern.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Support/GlobPattern.h?rev=290212&view=auto
==============================================================================
--- llvm/trunk/include/llvm/Support/GlobPattern.h (added)
+++ llvm/trunk/include/llvm/Support/GlobPattern.h Tue Dec 20 17:09:09 2016
@@ -0,0 +1,48 @@
+//===-- GlobPattern.h - glob pattern matcher implementation -*- C++ -*-----===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements a glob pattern matcher. The glob pattern is the
+// rule used by the shell.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_GLOB_PATTERN_H
+#define LLVM_SUPPORT_GLOB_PATTERN_H
+
+#include "llvm/ADT/BitVector.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/Error.h"
+#include <vector>
+
+// This class represents a glob pattern. Supported metacharacters
+// are "*", "?", "[<chars>]" and "[^<chars>]".
+namespace llvm {
+class BitVector;
+template <typename T> class ArrayRef;
+
+class GlobPattern {
+public:
+ static Expected<GlobPattern> create(StringRef Pat);
+ bool match(StringRef S) const;
+
+private:
+ bool matchOne(ArrayRef<BitVector> Pat, StringRef S) const;
+
+ // Parsed glob pattern.
+ std::vector<BitVector> Tokens;
+
+ // The following members are for optimization.
+ Optional<StringRef> Exact;
+ Optional<StringRef> Prefix;
+ Optional<StringRef> Suffix;
+};
+}
+
+#endif // LLVM_SUPPORT_GLOB_PATTERN_H
Modified: llvm/trunk/lib/Support/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/CMakeLists.txt?rev=290212&r1=290211&r2=290212&view=diff
==============================================================================
--- llvm/trunk/lib/Support/CMakeLists.txt (original)
+++ llvm/trunk/lib/Support/CMakeLists.txt Tue Dec 20 17:09:09 2016
@@ -56,6 +56,7 @@ add_llvm_library(LLVMSupport
FoldingSet.cpp
FormattedStream.cpp
FormatVariadic.cpp
+ GlobPattern.cpp
GraphWriter.cpp
Hashing.cpp
IntEqClasses.cpp
Added: llvm/trunk/lib/Support/GlobPattern.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/GlobPattern.cpp?rev=290212&view=auto
==============================================================================
--- llvm/trunk/lib/Support/GlobPattern.cpp (added)
+++ llvm/trunk/lib/Support/GlobPattern.cpp Tue Dec 20 17:09:09 2016
@@ -0,0 +1,167 @@
+//===-- GlobPattern.cpp - Glob pattern matcher implementation -------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements a glob pattern matcher.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/GlobPattern.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/Support/Errc.h"
+
+using namespace llvm;
+
+static bool hasWildcard(StringRef S) {
+ return S.find_first_of("?*[") != StringRef::npos;
+}
+
+// Expands character ranges and returns a bitmap.
+// For example, "a-cf-hz" is expanded to "abcfghz".
+static Expected<BitVector> expand(StringRef S, StringRef Original) {
+ 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])
+ return make_error<StringError>("invalid glob pattern: " + Original,
+ errc::invalid_argument);
+
+ 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;
+}
+
+// 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.
+static Expected<BitVector> scan(StringRef &S, StringRef Original) {
+ 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)
+ 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("^")) {
+ Expected<BitVector> BV = expand(Chars.substr(1), Original);
+ if (!BV)
+ return BV.takeError();
+ return BV->flip();
+ }
+ return expand(Chars, Original);
+ }
+ default:
+ BitVector BV(256, false);
+ BV[S[0]] = true;
+ S = S.substr(1);
+ return BV;
+ }
+}
+
+Expected<GlobPattern> GlobPattern::create(StringRef S) {
+ GlobPattern Pat;
+
+ // S doesn't contain any metacharacter,
+ // so the regular string comparison should work.
+ if (!hasWildcard(S)) {
+ Pat.Exact = S;
+ return Pat;
+ }
+
+ // S is something like "foo*". We can use startswith().
+ if (S.endswith("*") && !hasWildcard(S.drop_back())) {
+ Pat.Prefix = S.drop_back();
+ return Pat;
+ }
+
+ // S is something like "*foo". We can use endswith().
+ if (S.startswith("*") && !hasWildcard(S.drop_front())) {
+ Pat.Suffix = S.drop_front();
+ return Pat;
+ }
+
+ // Otherwise, we need to do real glob pattern matching.
+ // Parse the pattern now.
+ StringRef Original = S;
+ while (!S.empty()) {
+ Expected<BitVector> BV = scan(S, Original);
+ if (!BV)
+ return BV.takeError();
+ Pat.Tokens.push_back(*BV);
+ }
+ return Pat;
+}
+
+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
+ // tail strings 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);
+ }
+}
Modified: llvm/trunk/unittests/Support/CMakeLists.txt
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/unittests/Support/CMakeLists.txt?rev=290212&r1=290211&r2=290212&view=diff
==============================================================================
--- llvm/trunk/unittests/Support/CMakeLists.txt (original)
+++ llvm/trunk/unittests/Support/CMakeLists.txt Tue Dec 20 17:09:09 2016
@@ -17,10 +17,11 @@ add_llvm_unittest(SupportTests
DwarfTest.cpp
EndianStreamTest.cpp
EndianTest.cpp
- ErrorTest.cpp
ErrorOrTest.cpp
+ ErrorTest.cpp
FileOutputBufferTest.cpp
FormatVariadicTest.cpp
+ GlobPatternTest.cpp
Host.cpp
LEB128Test.cpp
LineIteratorTest.cpp
Added: llvm/trunk/unittests/Support/GlobPatternTest.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/unittests/Support/GlobPatternTest.cpp?rev=290212&view=auto
==============================================================================
--- llvm/trunk/unittests/Support/GlobPatternTest.cpp (added)
+++ llvm/trunk/unittests/Support/GlobPatternTest.cpp Tue Dec 20 17:09:09 2016
@@ -0,0 +1,70 @@
+//===- llvm/unittest/Support/GlobPatternTest.cpp --------------------------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/GlobPattern.h"
+#include "gtest/gtest.h"
+
+using namespace llvm;
+namespace {
+
+class GlobPatternTest : public ::testing::Test {};
+
+TEST_F(GlobPatternTest, Basics) {
+ Expected<GlobPattern> Pat1 = GlobPattern::create("");
+ EXPECT_TRUE((bool)Pat1);
+ EXPECT_TRUE(Pat1->match(""));
+ EXPECT_FALSE(Pat1->match("a"));
+
+ Expected<GlobPattern> Pat2 = GlobPattern::create("ab*c*def");
+ EXPECT_TRUE((bool)Pat2);
+ EXPECT_TRUE(Pat2->match("abcdef"));
+ EXPECT_TRUE(Pat2->match("abxcxdef"));
+ EXPECT_FALSE(Pat2->match(""));
+ EXPECT_FALSE(Pat2->match("xabcdef"));
+ EXPECT_FALSE(Pat2->match("abcdefx"));
+
+ Expected<GlobPattern> Pat3 = GlobPattern::create("a??c");
+ EXPECT_TRUE((bool)Pat3);
+ EXPECT_TRUE(Pat3->match("axxc"));
+ EXPECT_FALSE(Pat3->match("axxx"));
+ EXPECT_FALSE(Pat3->match(""));
+
+ Expected<GlobPattern> Pat4 = GlobPattern::create("[abc-fy-z]");
+ EXPECT_TRUE((bool)Pat4);
+ EXPECT_TRUE(Pat4->match("a"));
+ EXPECT_TRUE(Pat4->match("b"));
+ EXPECT_TRUE(Pat4->match("c"));
+ EXPECT_TRUE(Pat4->match("d"));
+ EXPECT_TRUE(Pat4->match("e"));
+ EXPECT_TRUE(Pat4->match("f"));
+ EXPECT_TRUE(Pat4->match("y"));
+ EXPECT_TRUE(Pat4->match("z"));
+ EXPECT_FALSE(Pat4->match("g"));
+ EXPECT_FALSE(Pat4->match(""));
+
+ Expected<GlobPattern> Pat5 = GlobPattern::create("[^abc-fy-z]");
+ EXPECT_TRUE((bool)Pat5);
+ EXPECT_TRUE(Pat5->match("g"));
+ EXPECT_FALSE(Pat5->match("a"));
+ EXPECT_FALSE(Pat5->match("b"));
+ EXPECT_FALSE(Pat5->match("c"));
+ EXPECT_FALSE(Pat5->match("d"));
+ EXPECT_FALSE(Pat5->match("e"));
+ EXPECT_FALSE(Pat5->match("f"));
+ EXPECT_FALSE(Pat5->match("y"));
+ EXPECT_FALSE(Pat5->match("z"));
+ EXPECT_FALSE(Pat5->match(""));
+}
+
+TEST_F(GlobPatternTest, Invalid) {
+ Expected<GlobPattern> Pat1 = GlobPattern::create("[");
+ EXPECT_FALSE((bool)Pat1);
+ handleAllErrors(Pat1.takeError(), [&](ErrorInfoBase &EIB) {});
+}
+}
More information about the llvm-commits
mailing list