Index: include/llvm/Support/SpecialCaseList.h =================================================================== --- include/llvm/Support/SpecialCaseList.h +++ include/llvm/Support/SpecialCaseList.h @@ -89,6 +89,17 @@ bool inSection(StringRef Section, StringRef Prefix, StringRef Query, StringRef Category = StringRef()) const; + /// Returns the line number corresponding to the special case list entry if + /// the special case list contains a line + /// \code + /// @Prefix:=@Category + /// \endcode + /// where @Query satisfies wildcard expression in a given @Section. + /// Returns zero if there is no blacklist entry corresponding to this + /// expression. + unsigned inSectionBlame(StringRef Section, StringRef Prefix, StringRef Query, + StringRef Category = StringRef()) const; + protected: // Implementations of the create*() functions that can also be used by derived // classes. @@ -106,15 +117,14 @@ /// literal strings than Regex. class Matcher { public: - bool insert(std::string Regexp, std::string &REError); + bool insert(std::string Regexp, unsigned LineNumber, std::string &REError); void compile(); - bool match(StringRef Query) const; + unsigned match(StringRef Query) const; private: - StringSet<> Strings; + StringMap Strings; TrigramIndex Trigrams; - std::unique_ptr RegEx; - std::string UncompiledRegEx; + std::vector, unsigned>> RegExes; }; using SectionEntries = StringMap>; @@ -138,8 +148,8 @@ // Helper method for derived classes to search by Prefix, Query, and Category // once they have already resolved a section entry. - bool inSection(const SectionEntries &Entries, StringRef Prefix, - StringRef Query, StringRef Category) const; + unsigned inSectionBlame(const SectionEntries &Entries, StringRef Prefix, + StringRef Query, StringRef Category) const; }; } // namespace llvm Index: lib/Support/SpecialCaseList.cpp =================================================================== --- lib/Support/SpecialCaseList.cpp +++ lib/Support/SpecialCaseList.cpp @@ -27,6 +27,7 @@ namespace llvm { bool SpecialCaseList::Matcher::insert(std::string Regexp, + unsigned LineNumber, std::string &REError) { if (Regexp.empty()) { REError = "Supplied regexp was blank"; @@ -34,7 +35,7 @@ } if (Regex::isLiteralERE(Regexp)) { - Strings.insert(Regexp); + Strings[Regexp] = LineNumber; return true; } Trigrams.insert(Regexp); @@ -45,30 +46,28 @@ Regexp.replace(pos, strlen("*"), ".*"); } + Regexp = "^(" + Regexp + ")$"; + // Check that the regexp is valid. Regex CheckRE(Regexp); if (!CheckRE.isValid(REError)) return false; - if (!UncompiledRegEx.empty()) - UncompiledRegEx += "|"; - UncompiledRegEx += "^(" + Regexp + ")$"; + RegExes.emplace_back( + std::make_pair(make_unique(std::move(CheckRE)), LineNumber)); return true; } -void SpecialCaseList::Matcher::compile() { - if (!UncompiledRegEx.empty()) { - RegEx.reset(new Regex(UncompiledRegEx)); - UncompiledRegEx.clear(); - } -} - -bool SpecialCaseList::Matcher::match(StringRef Query) const { - if (Strings.count(Query)) - return true; +unsigned SpecialCaseList::Matcher::match(StringRef Query) const { + auto It = Strings.find(Query); + if (It != Strings.end()) + return It->second; if (Trigrams.isDefinitelyOut(Query)) return false; - return RegEx && RegEx->match(Query); + for (auto& RegExKV : RegExes) + if (auto It = RegExKV.first->match(Query)) + return RegExKV.second; + return 0; } SpecialCaseList::SpecialCaseList() : Sections(), IsCompiled(false) {} @@ -114,7 +113,6 @@ return false; } } - compile(); return true; } @@ -123,7 +121,6 @@ StringMap Sections; if (!parse(MB, Sections, Error)) return false; - compile(); return true; } @@ -134,12 +131,14 @@ SmallVector Lines; SplitString(MB->getBuffer(), Lines, "\n\r"); - int LineNo = 1; + unsigned LineNo = 1; StringRef Section = "*"; for (auto I = Lines.begin(), E = Lines.end(); I != E; ++I, ++LineNo) { // Ignore empty lines and lines starting with "#" - if (I->empty() || I->startswith("#")) + if (I->empty() || I->startswith("#")){ + ++LineNo; continue; + } // Save section names if (I->startswith("[")) { @@ -181,11 +180,10 @@ if (SectionsMap.find(Section) == SectionsMap.end()) { std::unique_ptr M = make_unique(); std::string REError; - if (!M->insert(Section, REError)) { + if (!M->insert(Section, LineNo, REError)) { Error = (Twine("malformed section ") + Section + ": '" + REError).str(); return false; } - M->compile(); SectionsMap[Section] = Sections.size(); Sections.emplace_back(std::move(M)); @@ -193,7 +191,7 @@ auto &Entry = Sections[SectionsMap[Section]].Entries[Prefix][Category]; std::string REError; - if (!Entry.insert(std::move(Regexp), REError)) { + if (!Entry.insert(std::move(Regexp), LineNo, REError)) { Error = (Twine("malformed regex in line ") + Twine(LineNo) + ": '" + SplitLine.second + "': " + REError).str(); return false; @@ -202,38 +200,33 @@ return true; } -void SpecialCaseList::compile() { - assert(!IsCompiled && "compile() should only be called once"); - // Iterate through every section compiling regular expressions for every query - // and creating Section entries. - for (auto &Section : Sections) - for (auto &Prefix : Section.Entries) - for (auto &Category : Prefix.getValue()) - Category.getValue().compile(); - - IsCompiled = true; -} - SpecialCaseList::~SpecialCaseList() {} bool SpecialCaseList::inSection(StringRef Section, StringRef Prefix, StringRef Query, StringRef Category) const { - assert(IsCompiled && "SpecialCaseList::compile() was not called!"); + return inSectionBlame(Section, Prefix, Query, Category); +} +unsigned SpecialCaseList::inSectionBlame(StringRef Section, StringRef Prefix, + StringRef Query, + StringRef Category) const { for (auto &SectionIter : Sections) - if (SectionIter.SectionMatcher->match(Section) && - inSection(SectionIter.Entries, Prefix, Query, Category)) - return true; - - return false; + if (SectionIter.SectionMatcher->match(Section)) { + unsigned Blame = + inSectionBlame(SectionIter.Entries, Prefix, Query, Category); + if (Blame) + return Blame; + } + return 0; } -bool SpecialCaseList::inSection(const SectionEntries &Entries, StringRef Prefix, - StringRef Query, StringRef Category) const { +unsigned SpecialCaseList::inSectionBlame(const SectionEntries &Entries, + StringRef Prefix, StringRef Query, + StringRef Category) const { SectionEntries::const_iterator I = Entries.find(Prefix); - if (I == Entries.end()) return false; + if (I == Entries.end()) return 0; StringMap::const_iterator II = I->second.find(Category); - if (II == I->second.end()) return false; + if (II == I->second.end()) return 0; return II->getValue().match(Query); } Index: unittests/Support/SpecialCaseListTest.cpp =================================================================== --- unittests/Support/SpecialCaseListTest.cpp +++ unittests/Support/SpecialCaseListTest.cpp @@ -60,6 +60,33 @@ EXPECT_FALSE(SCL->inSection("", "src", "hello", "category")); } +TEST_F(SpecialCaseListTest, BasicBlame) { + std::unique_ptr SCL = + makeSpecialCaseList("# This is a comment.\n" + "\n" + "src:hello\n" + "src:bye\n" + "src:hi=category\n" + "src:z*=category\n"); + EXPECT_EQ(3u, SCL->inSectionBlame("", "src", "hello")); + EXPECT_EQ(4u, SCL->inSectionBlame("", "src", "bye")); + EXPECT_EQ(5u, SCL->inSectionBlame("", "src", "hi", "category")); + EXPECT_EQ(6u, SCL->inSectionBlame("", "src", "zzzz", "category")); + EXPECT_EQ(0u, SCL->inSectionBlame("", "src", "hi")); + EXPECT_EQ(0u, SCL->inSectionBlame("", "fun", "hello")); + EXPECT_EQ(0u, SCL->inSectionBlame("", "src", "hello", "category")); +} + +TEST_F(SpecialCaseListTest, CorrectErrorLineNumberWithBlankLine) { + std::string Error; + EXPECT_EQ(nullptr, makeSpecialCaseList("# This is a comment.\n" + "\n" + "[not valid\n", + Error)); + EXPECT_TRUE( + ((StringRef)Error).startswith("malformed section header on line 3:")); +} + TEST_F(SpecialCaseListTest, SectionRegexErrorHandling) { std::string Error; EXPECT_EQ(makeSpecialCaseList("[address", Error), nullptr);