InterpolatingCompilationDatabase.cpp

//===- InterpolatingCompilationDatabase.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
//
//===----------------------------------------------------------------------===//
//
// 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, replacing the filename and removing output
// file arguments. The -x and -std flags may be affected too.
//
// Source language is a tricky issue: is it OK to use a .c file's command
// for building a .cc file? What language is a .h file in?
//   - We only consider compile commands for c-family languages as candidates.
//   - For files whose language is implied by the filename (e.g. .m, .hpp)
//     we prefer candidates from the same language.
//     If we must cross languages, we drop any -x and -std flags.
//   - For .h files, candidates from any c-family language are acceptable.
//     We use the candidate's language, inserting  e.g. -x c++-header.
//
// This class is only useful when wrapping databases that can enumerate all
// their compile commands. If getAllFilenames() is empty, no inference occurs.
//
//===----------------------------------------------------------------------===//

#include "clang/Basic/LangStandard.h"
#include "clang/Driver/Driver.h"
#include "clang/Driver/Options.h"
#include "clang/Driver/Types.h"
#include "clang/Tooling/CompilationDatabase.h"
#include "llvm/ADT/ArrayRef.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 <memory>
#include <optional>

namespace clang {
namespace tooling {
namespace {
usingnamespacellvm;
types;
path;

// The length of the prefix these two strings have in common.
size_t matchingPrefix(StringRef L, StringRef R) { … }

// A comparator for searching SubstringWithIndexes with std::equal_range etc.
// Optionaly prefix semantics: compares equal if the key is a prefix.
template <bool Prefix> struct Less { … };

// Infer type from filename. If we might have gotten it wrong, set *Certain.
// *.h will be inferred as a C header, but not certain.
types::ID guessType(StringRef Filename, bool *Certain = nullptr) { … }

// Return Lang as one of the canonical supported types.
// e.g. c-header --> c; fortran --> TY_INVALID
static types::ID foldType(types::ID Lang) { … }

// A CompileCommand that can be applied to another file.
struct TransferableCommand { … };

// Given a filename, FileIndex picks the best matching file from the underlying
// DB. This is the proxy file whose CompileCommand will be reused. The
// heuristics incorporate file name, extension, and directory structure.
// Strategy:
// - Build indexes of each of the substrings we want to look up by.
//   These indexes are just sorted lists of the substrings.
// - Each criterion corresponds to a range lookup into the index, so we only
//   need O(log N) string comparisons to determine scores.
//
// Apart from path proximity signals, also takes file extensions into account
// when scoring the candidates.
class FileIndex { … };

// The actual CompilationDatabase wrapper delegates to its inner database.
// If no match, looks up a proxy file in FileIndex and transfers its
// command to the requested file.
class InterpolatingCompilationDatabase : public CompilationDatabase { … };

} // namespace

std::unique_ptr<CompilationDatabase>
inferMissingCompileCommands(std::unique_ptr<CompilationDatabase> Inner) { … }

tooling::CompileCommand transferCompileCommand(CompileCommand Cmd,
                                               StringRef Filename) { … }

} // namespace tooling
} // namespace clang
llvm/clang/lib/Tooling/InterpolatingCompilationDatabase.cpp
