Index: include/clang/Tooling/CompilationDatabase.h =================================================================== --- include/clang/Tooling/CompilationDatabase.h +++ include/clang/Tooling/CompilationDatabase.h @@ -213,6 +213,13 @@ std::vector CompileCommands; }; +/// Returns a wrapped CompilationDatabase that defers to the provided one, +/// but getCompileCommands() will infer commands for unknown files. +/// The return value of getAllFiles() or getAllCompileCommands() is unchanged. +/// See InterpolatingCompilationDatabase.cpp for details on heuristics. +std::unique_ptr + inferMissingCompileCommands(std::unique_ptr); + } // namespace tooling } // namespace clang Index: lib/Tooling/CMakeLists.txt =================================================================== --- lib/Tooling/CMakeLists.txt +++ lib/Tooling/CMakeLists.txt @@ -15,6 +15,7 @@ Execution.cpp FileMatchTrie.cpp FixIt.cpp + InterpolatingCompilationDatabase.cpp JSONCompilationDatabase.cpp Refactoring.cpp RefactoringCallbacks.cpp Index: lib/Tooling/InterpolatingCompilationDatabase.cpp =================================================================== --- /dev/null +++ lib/Tooling/InterpolatingCompilationDatabase.cpp @@ -0,0 +1,332 @@ +//===- InterpolatingCompilationDatabase.cpp ---------------------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// InterpolatingCompilationDatabase wraps another CompilationDatabase and +// attempts to heuristically determine appropriate compile commands for files +// that are not included, such as headers or newly created files. +// +// Motivating cases include: +// Header files that live next to their implementation files. These typically +// share a base filename. (libclang/CXString.h, libclang/CXString.cpp). +// Some projects separate headers from includes. Filenames still typically +// match, maybe other path segments too. (include/llvm/IR/Use.h, lib/IR/Use.cc). +// Matches are sometimes only approximate (Sema.h, SemaDecl.cpp). This goes +// for directories too (Support/Unix/Process.inc, lib/Support/Process.cpp). +// Even if we can't find a "right" compile command, even a random one from +// the project will tend to get important flags like -I and -x right. +// +// We "borrow" the compile command for the closest available file: +// - points are awarded if the filename matches (ignoring extension) +// - points are awarded if the directory structure matches +// - ties are broken by length of path prefix match +// +// The compile command is adjusted: +// - the input filename is replaced +// - if the extension differs, an "-x" flag is added to preserve the language +// - output file arguments are removed +// +// This class is only useful when wrapping databases that can enumerate all +// their compile commands. If getAllFilenames() is empty, no inference occurs. +// +//===----------------------------------------------------------------------===// + +#include "clang/Driver/Options.h" +#include "clang/Driver/Types.h" +#include "clang/Tooling/CompilationDatabase.h" +#include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/StringExtras.h" +#include "llvm/Option/ArgList.h" +#include "llvm/Option/OptTable.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/Path.h" +#include "llvm/Support/StringSaver.h" +#include "llvm/Support/raw_ostream.h" +#include + +namespace clang { +namespace tooling { +namespace { +using namespace llvm; + +// First, a bunch of helpers for comparing strings. +// These are used for lookups into the index, and for comparing results. +// As well as normal string lookups, we need prefix lookups. + +// The length of the prefix these two strings have in common. +size_t matchingPrefix(StringRef L, StringRef R) { + size_t Limit = std::min(L.size(), R.size()); + for (size_t I = 0; I < Limit; ++I) + if (L[I] != R[I]) + return I; + return Limit; +} + +// A comparator for searching SubstringWithIndexes with std::equal_range etc. +// Optionaly prefix semantics: compares equal if the key is a prefix. +template struct Less { + bool operator()(StringRef Key, std::pair Value) const { + StringRef V = Prefix ? Value.first.substr(0, Key.size()) : Value.first; + return Key < V; + } + bool operator()(std::pair Value, StringRef Key) const { + StringRef V = Prefix ? Value.first.substr(0, Key.size()) : Value.first; + return V < Key; + } +}; + +// FilenameIndex does the real work: given a filename, it produces the best +// matching candidate filename. Basic strategy: +// - On startup, capture all the filenames from the inner CDB +// - Build indexes of each of the substrings we want to look up by. +// These indexes are just sorted lists of the substrings. +// - Forward requests to the inner CDB. If it fails, we must pick a proxy. +// - Each criterion corresponds to a range lookup into the index, so we only +// need O(log N) string comparisons to determine scores. +// - We then break ties among the candidates with the highest score. +class FilenameIndex { +public: + FilenameIndex(std::vector Filenames) : Strings(Arena) { + // Sort input for determinism (index is used as a tiebreaker). + llvm::sort(OriginalPaths.begin(), OriginalPaths.end()); + for (size_t I = 0; I < Filenames.size(); ++I) { + OriginalPaths.emplace_back(Strings.save(Filenames[I])); + StringRef Path = Strings.save(OriginalPaths.back().lower()); + Paths.push_back({Path, I}); + Stems.emplace_back(sys::path::stem(Path), I); + auto Dir = ++sys::path::rbegin(Path), DirEnd = sys::path::rend(Path); + for (int J = 0; J < DirectorySegmentsIndexed && Dir != DirEnd; ++J, ++Dir) + if (Dir->size() > ShortDirectorySegment) // not trivial ones + Components.emplace_back(*Dir, I); + } + llvm::sort(Paths.begin(), Paths.end()); + llvm::sort(Stems.begin(), Stems.end()); + llvm::sort(Components.begin(), Components.end()); + } + + bool empty() const { return OriginalPaths.empty(); } + + StringRef chooseProxy(StringRef OriginalFilename) const { + assert(!empty() && "need at least one candidate!"); + std::string Filename = OriginalFilename.lower(); + auto Candidates = scoreCandidates(Filename); + std::pair Best = breakTies(Candidates, Filename); + + DEBUG_WITH_TYPE("interpolate", llvm::dbgs() + << "interpolate: chose " + << OriginalPaths[Best.first] + << " as proxy for " << OriginalFilename + << " score=" << Best.second << "\n"); + return OriginalPaths[Best.first]; + } + +private: + using SubstringAndIndex = std::pair; + // Directory matching parameters: we look at the last two segments of the + // parent directory (usually the semantically significant ones in practice). + // We search only the last four of each candidate (for efficiency). + constexpr static int DirectorySegmentsIndexed = 4; + constexpr static int DirectorySegmentsQueried = 2; + constexpr static int ShortDirectorySegment = 1; // Only look at longer names. + + // Award points to candidate entries that should be considered for the file. + // Returned keys are indexes into paths, and the values are (nonzero) scores. + DenseMap scoreCandidates(StringRef Filename) const { + // Decompose Filename into the parts we care about. + // /some/path/complicated/project/Interesting.h + // [-prefix--][---dir---] [-dir-] [--stem---] + StringRef Stem = sys::path::stem(Filename); + llvm::SmallVector Dirs; + llvm::StringRef Prefix; + auto Dir = ++sys::path::rbegin(Filename), + DirEnd = sys::path::rend(Filename); + for (int I = 0; I < DirectorySegmentsQueried && Dir != DirEnd; ++I, ++Dir) { + if (Dir->size() > ShortDirectorySegment) + Dirs.push_back(*Dir); + Prefix = Filename.substr(0, Dir - DirEnd); + } + + // Now award points based on lookups into our various indexes. + DenseMap Candidates; // Index -> score. + auto Award = [&](int Points, ArrayRef Range) { + for (const auto &Entry : Range) + Candidates[Entry.second] += Points; + }; + // Award one point if the file's basename is a prefix of the candidate, + // and another if it's an exact match (so exact matches get two points). + Award(1, indexLookup(Stem, Stems)); + Award(1, indexLookup(Stem, Stems)); + // For each of the last few directories in the Filename, award a point + // if it's present in the candidate. + for (StringRef Dir : Dirs) + Award(1, indexLookup(Dir, Components)); + // Award one more point if the whole rest of the path matches. + if (sys::path::root_directory(Prefix) != Prefix) + Award(1, indexLookup(Prefix, Paths)); + return Candidates; + } + + // Pick a single winner from the set of scored candidates. + // Returns (index, score). + std::pair breakTies(const DenseMap &Candidates, + StringRef Filename) const { + // Choose the best candidate by (points, prefix length, alpha). + size_t Best = -1; + int BestPoints = 0; + size_t BestPrefixLength = 0; + for (const auto &Candidate : Candidates) { + if (Candidate.second < BestPoints) + continue; + StringRef CandidatePath = Paths[Candidate.first].first; + size_t PrefixLength = matchingPrefix(Filename, CandidatePath); + if (Candidate.second == BestPoints) { + if (PrefixLength < BestPrefixLength) + continue; + // hidden heuristics should at least be deterministic! + if (PrefixLength == BestPrefixLength) + if (Candidate.first > Best) + continue; + } + Best = Candidate.first; + BestPoints = Candidate.second; + BestPrefixLength = PrefixLength; + } + if (Candidates.empty()) // Edge case: no candidate got any points. + Best = longestMatch(Filename, Paths).second; + return {Best, BestPoints}; + } + + // Returns the range within a sorted index that compares equal to Key. + // If Prefix is true, it's instead the range starting with Key. + template + ArrayRef + indexLookup(StringRef Key, const std::vector &Idx) const { + // Use pointers as iteratiors to ease conversion of result to ArrayRef. + auto Range = + std::equal_range(&Idx[0], &Idx[Idx.size()], Key, Less()); + return {Range.first, Range.second}; + } + + // Performs a point lookup into a nonempty index, returning a longest match. + SubstringAndIndex + longestMatch(StringRef Key, const std::vector &Idx) const { + // Longest substring match will be adjacent to a direct lookup. + auto It = + std::lower_bound(Idx.begin(), Idx.end(), SubstringAndIndex{Key, 0}); + if (It == Paths.begin()) + return *It; + if (It == Paths.end()) + return *--It; + // Have to choose between It and It-1 + size_t Prefix = matchingPrefix(Key, It->first); + size_t PrevPrefix = matchingPrefix(Key, (It - 1)->first); + return Prefix > PrevPrefix ? *It : *--It; + } + + BumpPtrAllocator Arena; + StringSaver Strings; + // Original candidates with case preserved. Indexes point into this. + std::vector OriginalPaths; + + // Indexes of candidates by certain substrings. + // String is lowercase and sorted, index points into OriginalPaths. + std::vector Paths; // Full path. + std::vector Stems; // Basename, without extension. + std::vector Components; // Last path components. +}; + +// The actual CompilationDatabase wrapper delegates to its inner database, and +// to FilenameIndex if no match is found. +// The only remaining work is fixing up the command for the new file. +class InterpolatingCompilationDatabase : public CompilationDatabase { +public: + InterpolatingCompilationDatabase(std::unique_ptr Inner) + : Inner(std::move(Inner)), Index(getAllFiles()) {} + + std::vector + getCompileCommands(StringRef Filename) const override { + auto Known = Inner->getCompileCommands(Filename); + if (Index.empty() || !Known.empty()) + return Known; + StringRef Proxy = Index.chooseProxy(Filename); + auto Result = Inner->getCompileCommands(Proxy); + assert(!Result.empty() && + "candidates returned by getFiles() should have compile commands!"); + return {adjust(std::move(Result[0]), Filename)}; + } + + std::vector getAllFiles() const override { + return Inner->getAllFiles(); + } + + std::vector getAllCompileCommands() const override { + return Inner->getAllCompileCommands(); + } + +private: + // Tweaks the CompileCommand for use with a different file. + // We use the real options parser to avoid fragile string replacements. + CompileCommand adjust(CompileCommand Base, StringRef Filename) const { + auto OptTable = clang::driver::createDriverOptTable(); + std::vector Argv; + for (unsigned I = 1; I < Base.CommandLine.size(); ++I) + Argv.push_back(Base.CommandLine[I].c_str()); + unsigned MissingI, MissingC; + auto ArgList = OptTable->ParseArgs(Argv, MissingI, MissingC); + + // Parse the old args in order to strip out input and -o. + std::vector NewArgs; + bool HasLanguageFlag = false; + for (const auto *Arg : ArgList) { + const auto &option = Arg->getOption(); + if (option.matches(clang::driver::options::OPT_INPUT) || + option.matches(clang::driver::options::OPT_o)) { + continue; + } + if (option.matches(clang::driver::options::OPT_x)) + HasLanguageFlag = true; + llvm::opt::ArgStringList ArgStrs; + Arg->render(ArgList, ArgStrs); + NewArgs.insert(NewArgs.end(), ArgStrs.begin(), ArgStrs.end()); + } + NewArgs.emplace_back(Filename); + + // Finally, build the final CompileCommand. + Base.CommandLine.resize(1); // keep argv[0] + if (!HasLanguageFlag) { + // Language was inferred from the extension. We may need to propagate it. + // Add an -x flag if needed, to preserve the parsing language. + auto OldLang = driver::types::lookupTypeForExtension( + llvm::sys::path::extension(Base.Filename).substr(1)), + NewLang = driver::types::lookupTypeForExtension( + llvm::sys::path::extension(Filename).substr(1)); + if (OldLang && NewLang != OldLang) { + Base.CommandLine.push_back("-x"); + Base.CommandLine.push_back(driver::types::getTypeName(OldLang)); + } + } + Base.CommandLine.insert(Base.CommandLine.end(), NewArgs.begin(), + NewArgs.end()); + Base.Filename = Filename; + Base.Output.clear(); + return Base; + } + + std::unique_ptr Inner; + FilenameIndex Index; +}; + +} // namespace + +std::unique_ptr +inferMissingCompileCommands(std::unique_ptr Inner) { + return llvm::make_unique(std::move(Inner)); +} + +} // namespace tooling +} // namespace clang Index: unittests/Tooling/CompilationDatabaseTest.cpp =================================================================== --- unittests/Tooling/CompilationDatabaseTest.cpp +++ unittests/Tooling/CompilationDatabaseTest.cpp @@ -626,5 +626,108 @@ EXPECT_EQ(2, Argc); } +struct MemCDB : public CompilationDatabase { + using EntryMap = llvm::StringMap>; + EntryMap Entries; + MemCDB(const EntryMap &E) : Entries(E) {} + + std::vector getCompileCommands(StringRef F) const override { + auto Ret = Entries.lookup(F); + return {Ret.begin(), Ret.end()}; + } + + std::vector getAllFiles() const override { + std::vector Result; + for (const auto &Entry : Entries) + Result.push_back(Entry.first()); + return Result; + } +}; + +class InterpolateTest : public ::testing::Test { +protected: + // Adds an entry to the underlying compilation database. + // A flag is injected: -D , so the command used can be identified. + void add(llvm::StringRef File, llvm::StringRef Flags = "") { + llvm::SmallVector Argv = {"clang", File, "-D", File}; + llvm::SplitString(Flags, Argv); + llvm::SmallString<32> Dir; + llvm::sys::path::system_temp_directory(false, Dir); + Entries[path(File)].push_back( + {Dir, File, {Argv.begin(), Argv.end()}, "foo.o"}); + } + + // Turn a unix path fragment (foo/bar.h) into a native path (C:\tmp\foo\bar.h) + std::string path(llvm::SmallString<32> File) { + llvm::SmallString<32> Dir; + llvm::sys::path::system_temp_directory(false, Dir); + llvm::sys::path::native(File); + llvm::SmallString<64> Result; + llvm::sys::path::append(Result, Dir, File); + return Result.str(); + } + + // Look up the command from a relative path, and return it in string form. + // The input file is not included in the returned command. + std::string getCommand(llvm::StringRef F) { + auto Results = + inferMissingCompileCommands(llvm::make_unique(Entries)) + ->getCompileCommands(path(F)); + if (Results.empty()) + return "none"; + // drop the input file argument, so tests don't have to deal with path(). + EXPECT_EQ(Results[0].CommandLine.back(), path(F)) + << "Last arg should be the file"; + Results[0].CommandLine.pop_back(); + return llvm::join(Results[0].CommandLine, " "); + } + + MemCDB::EntryMap Entries; +}; + +TEST_F(InterpolateTest, Nearby) { + add("dir/foo.cpp"); + add("dir/bar.cpp"); + add("an/other/foo.cpp"); + + // great: dir and name both match (prefix or full, case insensitive) + EXPECT_EQ(getCommand("dir/f.cpp"), "clang -D dir/foo.cpp"); + EXPECT_EQ(getCommand("dir/FOO.cpp"), "clang -D dir/foo.cpp"); + // no name match. prefer matching dir, break ties by alpha + EXPECT_EQ(getCommand("dir/a.cpp"), "clang -D dir/bar.cpp"); + // an exact name match beats one segment of directory match + EXPECT_EQ(getCommand("some/other/bar.h"), "clang -x c++ -D dir/bar.cpp"); + // two segments of directory match beat a prefix name match + EXPECT_EQ(getCommand("an/other/b.cpp"), "clang -D an/other/foo.cpp"); + // if nothing matches at all, we still get the closest alpha match + EXPECT_EQ(getCommand("below/some/obscure/path.cpp"), + "clang -D an/other/foo.cpp"); +} + +TEST_F(InterpolateTest, Language) { + add("dir/foo.cpp"); + add("dir/baz.cee", "-x c"); + + // extension changed, so we add explicit language flags + EXPECT_EQ(getCommand("foo.h"), "clang -x c++ -D dir/foo.cpp"); + // but we don't add -x if it's already there + EXPECT_EQ(getCommand("baz.h"), "clang -D dir/baz.cee -x c"); + // and don't add -x if the inferred language didn't change + EXPECT_EQ(getCommand("foo.cc"), "clang -D dir/foo.cpp"); +} + +TEST_F(InterpolateTest, Strip) { + add("dir/foo.cpp", "-o foo.o -Wall"); + // the -o option and the input file are removed, but -Wall is preserved. + EXPECT_EQ(getCommand("dir/bar.cpp"), "clang -D dir/foo.cpp -Wall"); +} + +TEST_F(InterpolateTest, Case) { + add("FOO/BAR/BAZ/SHOUT.cc"); + add("foo/bar/baz/quiet.cc"); + // Case mismatches are completely ignored, so we choose the name match. + EXPECT_EQ(getCommand("foo/bar/baz/shout.C"), "clang -D FOO/BAR/BAZ/SHOUT.cc"); +} + } // end namespace tooling } // end namespace clang