hokein created this revision. hokein added reviewers: kadircet, sammccall. Herald added a subscriber: arphaman. Herald added a project: All. hokein requested review of this revision. Herald added subscribers: MaskRay, ilya-biryukov. Herald added projects: clang, clang-tools-extra.
We plan to reuse it in the include-cleaner library, this patch moves this functionality from clangd to libtooling, so that this piece of code can be shared among all clang tools. Repository: rG LLVM Github Monorepo https://reviews.llvm.org/D137697 Files: clang-tools-extra/clangd/Headers.cpp clang-tools-extra/clangd/SourceCode.cpp clang-tools-extra/clangd/SourceCode.h clang-tools-extra/clangd/index/SymbolCollector.cpp clang/include/clang/Tooling/Inclusions/Header.h clang/lib/Tooling/Inclusions/CMakeLists.txt clang/lib/Tooling/Inclusions/Header.cpp clang/unittests/Tooling/CMakeLists.txt clang/unittests/Tooling/HeaderTest.cpp
Index: clang/unittests/Tooling/HeaderTest.cpp =================================================================== --- /dev/null +++ clang/unittests/Tooling/HeaderTest.cpp @@ -0,0 +1,64 @@ +//===- unittest/Tooling/HeaderTest.cpp ------------------------------------===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#include "clang/Tooling/Inclusions/Header.h" +#include "clang/Lex/Preprocessor.h" +#include "clang/Testing/TestAST.h" +#include "gtest/gtest.h" + +namespace clang { +namespace tooling { +namespace { + +TEST(HeaderTest, IsSelfContained) { + TestInputs Inputs; + Inputs.Code = R"cpp( + #include "headerguard.h" + #include "pragmaonce.h" + + #include "bad.h" + #include "unguarded.h" + )cpp"; + + Inputs.ExtraFiles["headerguard.h"] = R"cpp( + #ifndef HEADER_H + #define HEADER_H + + #endif HEADER_H + )cpp"; + Inputs.ExtraFiles["pragmaonce.h"] = R"cpp( + #pragma once + )cpp"; + Inputs.ExtraFiles["unguarded.h"] = ""; + Inputs.ExtraFiles["bad.h"] = R"cpp( + #pragma once + + #if defined(INSIDE_H) + #error "Only ... can be included directly" + #endif + )cpp"; + + TestAST AST(Inputs); + const auto &SM = AST.sourceManager(); + auto &FM = SM.getFileManager(); + auto &HI = AST.preprocessor().getHeaderSearchInfo(); + + EXPECT_TRUE(tooling::isSelfContainedHeader(FM.getFile("headerguard.h").get(), + SM, HI)); + EXPECT_TRUE( + tooling::isSelfContainedHeader(FM.getFile("pragmaonce.h").get(), SM, HI)); + + EXPECT_FALSE( + tooling::isSelfContainedHeader(FM.getFile("unguarded.h").get(), SM, HI)); + EXPECT_FALSE( + tooling::isSelfContainedHeader(FM.getFile("bad.h").get(), SM, HI)); +} + +} // namespace +} // namespace tooling +} // namespace clang Index: clang/unittests/Tooling/CMakeLists.txt =================================================================== --- clang/unittests/Tooling/CMakeLists.txt +++ clang/unittests/Tooling/CMakeLists.txt @@ -16,6 +16,7 @@ DiagnosticsYamlTest.cpp ExecutionTest.cpp FixItTest.cpp + HeaderTest.cpp HeaderIncludesTest.cpp StandardLibraryTest.cpp LexicallyOrderedRecursiveASTVisitorTest.cpp Index: clang/lib/Tooling/Inclusions/Header.cpp =================================================================== --- /dev/null +++ clang/lib/Tooling/Inclusions/Header.cpp @@ -0,0 +1,66 @@ +//===--- Header.cpp ---------------------------------------------*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#include "clang/Tooling/Inclusions/Header.h" +#include "clang/Basic/SourceLocation.h" +#include "clang/Lex/HeaderSearch.h" + +namespace clang::tooling { +namespace { + +// Is Line an #if or #ifdef directive? +// FIXME: This makes headers with #ifdef LINUX/WINDOWS/MACOS marked as non +// self-contained and is probably not what we want. +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? +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_insensitive( + "includ"); // Matches "include" or "including". +} + +// Heuristically headers that only want to be included via an umbrella. +bool 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 + +bool isSelfContainedHeader(const FileEntry *FE, const SourceManager &SM, + HeaderSearch &HeaderInfo) { + // FIXME: Should files that have been #import'd be considered + // self-contained? That's really a property of the includer, + // not of the file. + if (!HeaderInfo.isFileMultipleIncludeGuarded(FE) && + !HeaderInfo.hasFileBeenImported(FE)) + return false; + // This pattern indicates that a header can't be used without + // particular preprocessor state, usually set up by another header. + return !isDontIncludeMeHeader(SM.getBufferData(SM.translateFile(FE))); +} +} // namespace clang::tooling Index: clang/lib/Tooling/Inclusions/CMakeLists.txt =================================================================== --- clang/lib/Tooling/Inclusions/CMakeLists.txt +++ clang/lib/Tooling/Inclusions/CMakeLists.txt @@ -1,6 +1,7 @@ set(LLVM_LINK_COMPONENTS support) add_clang_library(clangToolingInclusions + Header.cpp HeaderIncludes.cpp IncludeStyle.cpp Index: clang/include/clang/Tooling/Inclusions/Header.h =================================================================== --- /dev/null +++ clang/include/clang/Tooling/Inclusions/Header.h @@ -0,0 +1,32 @@ +//===--- Header.h ------------------------------------------------*- C++-*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_CLANG_TOOLING_INCLUSIONS_HEADER_H +#define LLVM_CLANG_TOOLING_INCLUSIONS_HEADER_H + +namespace clang { +class FileEntry; +class SourceManager; +class HeaderSearch; + +namespace tooling { + +/// Returns true the the given physical file is a self-contained header. +/// +/// A header is considered self-contained if either it has a proper header guard +/// or it doesn't has dont-include-me-similar pattern. +/// +/// This function can be expensive as it may scan the source code to find out +/// dont-include-me pattern heuristically. +bool isSelfContainedHeader(const FileEntry *FE, const SourceManager &SM, + HeaderSearch &HeaderInfo); + +} // namespace tooling +} // namespace clang + +#endif // LLVM_CLANG_TOOLING_INCLUSIONS_HEADER_H Index: clang-tools-extra/clangd/index/SymbolCollector.cpp =================================================================== --- clang-tools-extra/clangd/index/SymbolCollector.cpp +++ clang-tools-extra/clangd/index/SymbolCollector.cpp @@ -28,6 +28,7 @@ #include "clang/Index/IndexSymbol.h" #include "clang/Lex/Preprocessor.h" #include "clang/Lex/Token.h" +#include "clang/Tooling/Inclusions/Header.h" #include "llvm/ADT/ArrayRef.h" #include "llvm/Support/Casting.h" #include "llvm/Support/FileSystem.h" @@ -419,8 +420,8 @@ getFrameworkHeaderIncludeSpelling(FE, HFI->Framework, HS)) return *Spelling; - if (!isSelfContainedHeader(FE, FID, PP->getSourceManager(), - PP->getHeaderSearchInfo())) { + if (!tooling::isSelfContainedHeader(FE, PP->getSourceManager(), + PP->getHeaderSearchInfo())) { // A .inc or .def file is often included into a real header to define // symbols (e.g. LLVM tablegen files). if (Filename.endswith(".inc") || Filename.endswith(".def")) Index: clang-tools-extra/clangd/SourceCode.h =================================================================== --- clang-tools-extra/clangd/SourceCode.h +++ clang-tools-extra/clangd/SourceCode.h @@ -325,11 +325,6 @@ /// Returns true if the given location is in a generated protobuf file. bool isProtoFile(SourceLocation Loc, const SourceManager &SourceMgr); -/// This scans source code, and should not be called when using a preamble. -/// Prefer to access the cache in IncludeStructure::isSelfContained if you can. -bool isSelfContainedHeader(const FileEntry *FE, FileID ID, - const SourceManager &SM, HeaderSearch &HeaderInfo); - /// Returns true if Name is reserved, like _Foo or __Vector_base. inline bool isReservedName(llvm::StringRef Name) { // This doesn't catch all cases, but the most common. Index: clang-tools-extra/clangd/SourceCode.cpp =================================================================== --- clang-tools-extra/clangd/SourceCode.cpp +++ clang-tools-extra/clangd/SourceCode.cpp @@ -1183,58 +1183,5 @@ return SM.getBufferData(FID).startswith(ProtoHeaderComment); } -namespace { - -// Is Line an #if or #ifdef directive? -// FIXME: This makes headers with #ifdef LINUX/WINDOWS/MACOS marked as non -// self-contained and is probably not what we want. -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? -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_insensitive( - "includ"); // Matches "include" or "including". -} - -// Heuristically headers that only want to be included via an umbrella. -bool 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 - -bool isSelfContainedHeader(const FileEntry *FE, FileID FID, - const SourceManager &SM, HeaderSearch &HeaderInfo) { - // FIXME: Should files that have been #import'd be considered - // self-contained? That's really a property of the includer, - // not of the file. - if (!HeaderInfo.isFileMultipleIncludeGuarded(FE) && - !HeaderInfo.hasFileBeenImported(FE)) - return false; - // This pattern indicates that a header can't be used without - // particular preprocessor state, usually set up by another header. - return !isDontIncludeMeHeader(SM.getBufferData(FID)); -} - } // namespace clangd } // namespace clang Index: clang-tools-extra/clangd/Headers.cpp =================================================================== --- clang-tools-extra/clangd/Headers.cpp +++ clang-tools-extra/clangd/Headers.cpp @@ -15,6 +15,7 @@ #include "clang/Lex/HeaderSearch.h" #include "clang/Lex/PPCallbacks.h" #include "clang/Lex/Preprocessor.h" +#include "clang/Tooling/Inclusions/Header.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/Path.h" #include <cstring> @@ -121,7 +122,7 @@ // isSelfContainedHeader only returns true once the full header-guard // structure has been seen, i.e. when exiting the *outer* copy of the // file. So last result wins. - if (isSelfContainedHeader(FE, PrevFID, SM, HeaderInfo)) + if (tooling::isSelfContainedHeader(FE, SM, HeaderInfo)) Out->NonSelfContained.erase( *Out->getID(SM.getFileEntryForID(PrevFID))); else
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
