Author: sammccall Date: Thu Apr 25 10:47:07 2019 New Revision: 359214 URL: http://llvm.org/viewvc/llvm-project?rev=359214&view=rev Log: [clangd] Optimize "don't include me" check.
Summary: llvm::Regex is really slow, and regex evaluation during preamble indexing was showing up as 25% on a profile of clangd in a codebase with large preambles. Reviewers: ilya-biryukov Subscribers: MaskRay, jkorous, arphaman, kadircet, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D61120 Modified: clang-tools-extra/trunk/clangd/index/SymbolCollector.cpp clang-tools-extra/trunk/clangd/index/SymbolCollector.h Modified: clang-tools-extra/trunk/clangd/index/SymbolCollector.cpp URL: http://llvm.org/viewvc/llvm-project/clang-tools-extra/trunk/clangd/index/SymbolCollector.cpp?rev=359214&r1=359213&r2=359214&view=diff ============================================================================== --- clang-tools-extra/trunk/clangd/index/SymbolCollector.cpp (original) +++ clang-tools-extra/trunk/clangd/index/SymbolCollector.cpp Thu Apr 25 10:47:07 2019 @@ -639,7 +639,7 @@ bool SymbolCollector::isSelfContainedHea return false; // This pattern indicates that a header can't be used without // particular preprocessor state, usually set up by another header. - if (DontIncludeMePattern.match(SM.getBufferData(FID))) + if (isDontIncludeMeHeader(SM.getBufferData(FID))) return false; return true; }; @@ -650,5 +650,36 @@ bool SymbolCollector::isSelfContainedHea return R.first->second; } +// Is Line an #if or #ifdef directive? +static bool isIf(llvm::StringRef Line) { + Line = Line.ltrim(); + if (!Line.consume_front("#")) + return false; + Line = Line.ltrim(); + return Line.startswith("if"); +} +// Is Line an #error directive mentioning includes? +static bool isErrorAboutInclude(llvm::StringRef Line) { + Line = Line.ltrim(); + if (!Line.consume_front("#")) + return false; + Line = Line.ltrim(); + if (! Line.startswith("error")) + return false; + return Line.contains_lower("includ"); // Matches "include" or "including". +} + +bool SymbolCollector::isDontIncludeMeHeader(llvm::StringRef Content) { + llvm::StringRef Line; + // Only sniff up to 100 lines or 10KB. + Content = Content.take_front(100*100); + for (unsigned I = 0; I < 100 && !Content.empty(); ++I) { + std::tie(Line, Content) = Content.split('\n'); + if (isIf(Line) && isErrorAboutInclude(Content.split('\n').first)) + return true; + } + return false; +} + } // namespace clangd } // namespace clang Modified: clang-tools-extra/trunk/clangd/index/SymbolCollector.h URL: http://llvm.org/viewvc/llvm-project/clang-tools-extra/trunk/clangd/index/SymbolCollector.h?rev=359214&r1=359213&r2=359214&view=diff ============================================================================== --- clang-tools-extra/trunk/clangd/index/SymbolCollector.h (original) +++ clang-tools-extra/trunk/clangd/index/SymbolCollector.h Thu Apr 25 10:47:07 2019 @@ -120,12 +120,8 @@ private: llvm::Optional<std::string> getIncludeHeader(llvm::StringRef QName, FileID); bool isSelfContainedHeader(FileID); - // Heuristic to detect headers that aren't self-contained, usually because - // they need to be included via an umbrella header. e.g. GTK matches this. - llvm::Regex DontIncludeMePattern = { - "^[ \t]*#[ \t]*if.*\n" // An #if, #ifndef etc directive, then - "[ \t]*#[ \t]*error.*include", // an #error directive mentioning "include" - llvm::Regex::Newline}; + // Heuristically headers that only want to be included via an umbrella. + static bool isDontIncludeMeHeader(llvm::StringRef); // All Symbols collected from the AST. SymbolSlab::Builder Symbols; _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
