[clangd] Handle additional includes while parsing ASTs

Summary:
Enables building ASTs with stale preambles by handling additional preamble
includes. Sets the correct location information for those imaginary includes so
that features like gotodef/documentlink keeps functioning propoerly.

Reviewers: sammccall

Subscribers: ilya-biryukov, MaskRay, jkorous, mgrang, arphaman, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D77644
This commit is contained in:
Kadir Cetinkaya 2020-04-02 10:53:45 +02:00
parent b9bb3ad3ed
commit b742eaa321
No known key found for this signature in database
GPG Key ID: E39E36B8D2057ED6
7 changed files with 252 additions and 54 deletions

View File

@ -1031,7 +1031,7 @@ struct SemaCompleteInput {
PathRef FileName;
const tooling::CompileCommand &Command;
const PreambleData &Preamble;
const PreamblePatch &Patch;
llvm::Optional<const PreamblePatch> Patch;
llvm::StringRef Contents;
size_t Offset;
llvm::IntrusiveRefCntPtr<llvm::vfs::FileSystem> VFS;
@ -1105,7 +1105,8 @@ bool semaCodeComplete(std::unique_ptr<CodeCompleteConsumer> Consumer,
PreambleBounds PreambleRegion =
ComputePreambleBounds(*CI->getLangOpts(), ContentsBuffer.get(), 0);
bool CompletingInPreamble = PreambleRegion.Size > Input.Offset;
Input.Patch.apply(*CI);
if (Input.Patch)
Input.Patch->apply(*CI);
// NOTE: we must call BeginSourceFile after prepareCompilerInstance. Otherwise
// the remapped buffers do not get freed.
auto Clang = prepareCompilerInstance(
@ -1767,7 +1768,8 @@ codeComplete(PathRef FileName, const tooling::CompileCommand &Command,
: std::move(Flow).run({FileName, Command, *Preamble,
// We want to serve code completions with
// low latency, so don't bother patching.
PreamblePatch(), Contents, *Offset, VFS});
/*PreamblePatch=*/llvm::None, Contents,
*Offset, VFS});
}
SignatureHelp signatureHelp(PathRef FileName,
@ -1792,10 +1794,11 @@ SignatureHelp signatureHelp(PathRef FileName,
PI.CompileCommand = Command;
PI.Contents = Contents.str();
PI.FS = std::move(VFS);
auto PP = PreamblePatch::create(FileName, PI, Preamble);
semaCodeComplete(
std::make_unique<SignatureHelpCollector>(Options, Index, Result), Options,
{FileName, Command, Preamble, PP, Contents, *Offset, std::move(PI.FS)});
{FileName, Command, Preamble,
PreamblePatch::create(FileName, PI, Preamble), Contents, *Offset,
std::move(PI.FS)});
return Result;
}

View File

@ -14,6 +14,7 @@
#include "Diagnostics.h"
#include "Headers.h"
#include "IncludeFixer.h"
#include "Preamble.h"
#include "SourceCode.h"
#include "index/CanonicalIncludes.h"
#include "index/Index.h"
@ -48,6 +49,7 @@
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <memory>
#include <vector>
// Force the linker to link in Clang-tidy modules.
// clangd doesn't support the static analyzer.
@ -268,6 +270,11 @@ ParsedAST::build(llvm::StringRef Filename, const ParseInputs &Inputs,
StoreDiags ASTDiags;
llvm::Optional<PreamblePatch> Patch;
if (Preamble) {
Patch = PreamblePatch::create(Filename, Inputs, *Preamble);
Patch->apply(*CI);
}
auto Clang = prepareCompilerInstance(
std::move(CI), PreamblePCH,
llvm::MemoryBuffer::getMemBufferCopy(Inputs.Contents, Filename), VFS,
@ -369,12 +376,14 @@ ParsedAST::build(llvm::StringRef Filename, const ParseInputs &Inputs,
Clang->setExternalSemaSource(FixIncludes->unresolvedNameRecorder());
}
// Copy over the includes from the preamble, then combine with the
// non-preamble includes below.
auto Includes = Preamble ? Preamble->Includes : IncludeStructure{};
// Replay the preamble includes so that clang-tidy checks can see them.
if (Preamble)
IncludeStructure Includes;
// If we are using a preamble, copy existing includes.
if (Preamble) {
Includes = Preamble->Includes;
Includes.MainFileIncludes = Patch->preambleIncludes();
// Replay the preamble includes so that clang-tidy checks can see them.
ReplayPreamble::attach(Includes, *Clang, Preamble->Preamble.getBounds());
}
// Important: collectIncludeStructure is registered *after* ReplayPreamble!
// Otherwise we would collect the replayed includes again...
// (We can't *just* use the replayed includes, they don't have Resolved path).

View File

@ -24,6 +24,8 @@
#include "clang/Lex/PreprocessorOptions.h"
#include "clang/Tooling/CompilationDatabase.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/IntrusiveRefCntPtr.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
@ -274,6 +276,7 @@ void escapeBackslashAndQuotes(llvm::StringRef Text, llvm::raw_ostream &OS) {
PreamblePatch PreamblePatch::create(llvm::StringRef FileName,
const ParseInputs &Modified,
const PreambleData &Baseline) {
assert(llvm::sys::path::is_absolute(FileName) && "relative FileName!");
// First scan the include directives in Baseline and Modified. These will be
// used to figure out newly added directives in Modified. Scanning can fail,
// the code just bails out and creates an empty patch in such cases, as:
@ -301,7 +304,7 @@ PreamblePatch PreamblePatch::create(llvm::StringRef FileName,
}
// No patch needed if includes are equal.
if (*BaselineIncludes == *ModifiedIncludes)
return {};
return PreamblePatch::unmodified(Baseline);
PreamblePatch PP;
// This shouldn't coincide with any real file name.
@ -312,10 +315,15 @@ PreamblePatch PreamblePatch::create(llvm::StringRef FileName,
// We are only interested in newly added includes, record the ones in Baseline
// for exclusion.
llvm::DenseSet<std::pair<tok::PPKeywordKind, llvm::StringRef>>
llvm::DenseMap<std::pair<tok::PPKeywordKind, llvm::StringRef>,
/*Resolved=*/llvm::StringRef>
ExistingIncludes;
for (const auto &Inc : Baseline.Includes.MainFileIncludes)
ExistingIncludes[{Inc.Directive, Inc.Written}] = Inc.Resolved;
// There might be includes coming from disabled regions, record these for
// exclusion too. note that we don't have resolved paths for those.
for (const auto &Inc : *BaselineIncludes)
ExistingIncludes.insert({Inc.Directive, Inc.Written});
ExistingIncludes.try_emplace({Inc.Directive, Inc.Written});
// Calculate extra includes that needs to be inserted.
llvm::raw_string_ostream Patch(PP.PatchContents);
// Set default filename for subsequent #line directives
@ -324,9 +332,15 @@ PreamblePatch PreamblePatch::create(llvm::StringRef FileName,
// might lead to problems on windows especially.
escapeBackslashAndQuotes(FileName, Patch);
Patch << "\"\n";
for (const auto &Inc : *ModifiedIncludes) {
if (ExistingIncludes.count({Inc.Directive, Inc.Written}))
for (auto &Inc : *ModifiedIncludes) {
auto It = ExistingIncludes.find({Inc.Directive, Inc.Written});
// Include already present in the baseline preamble. Set resolved path and
// put into preamble includes.
if (It != ExistingIncludes.end()) {
Inc.Resolved = It->second.str();
PP.PreambleIncludes.push_back(Inc);
continue;
}
// Include is new in the modified preamble. Inject it into the patch and use
// #line to set the presumed location to where it is spelled.
auto LineCol = offsetToClangLineColumn(Modified.Contents, Inc.HashOffset);
@ -356,5 +370,15 @@ void PreamblePatch::apply(CompilerInvocation &CI) const {
PPOpts.Includes.push_back(PatchFileName);
}
std::vector<Inclusion> PreamblePatch::preambleIncludes() const {
return PreambleIncludes;
}
PreamblePatch PreamblePatch::unmodified(const PreambleData &Preamble) {
PreamblePatch PP;
PP.PreambleIncludes = Preamble.Includes.MainFileIncludes;
return PP;
}
} // namespace clangd
} // namespace clang

View File

@ -91,12 +91,14 @@ bool isPreambleCompatible(const PreambleData &Preamble,
const CompilerInvocation &CI);
/// Stores information required to parse a TU using a (possibly stale) Baseline
/// preamble. Updates compiler invocation to approximately reflect additions to
/// the preamble section of Modified contents, e.g. new include directives.
/// preamble. Later on this information can be injected into the main file by
/// updating compiler invocation with \c apply. This injected section
/// approximately reflects additions to the preamble in Modified contents, e.g.
/// new include directives.
class PreamblePatch {
public:
// With an empty patch, the preamble is used verbatim.
PreamblePatch() = default;
/// \p Preamble is used verbatim.
static PreamblePatch unmodified(const PreambleData &Preamble);
/// Builds a patch that contains new PP directives introduced to the preamble
/// section of \p Modified compared to \p Baseline.
/// FIXME: This only handles include directives, we should at least handle
@ -109,9 +111,21 @@ public:
/// \p CI that contains new directives calculated in create.
void apply(CompilerInvocation &CI) const;
/// Returns #include directives from the \c Modified preamble that were
/// resolved using the \c Baseline preamble. This covers the new locations of
/// inclusions that were moved around, but not inclusions of new files. Those
/// will be recorded when parsing the main file: the includes in the injected
/// section will be resolved back to their spelled positions in the main file
/// using the presumed-location mechanism.
std::vector<Inclusion> preambleIncludes() const;
private:
PreamblePatch() = default;
std::string PatchContents;
std::string PatchFileName;
/// Includes that are present in both \p Baseline and \p Modified. Used for
/// patching includes of baseline preamble.
std::vector<Inclusion> PreambleIncludes;
};
} // namespace clangd

View File

@ -666,7 +666,8 @@ TEST_F(DocumentSymbolsTest, UsingDirectives) {
}
TEST_F(DocumentSymbolsTest, TempSpecs) {
addFile("foo.cpp", R"cpp(
std::string FilePath = testPath("foo.cpp");
addFile(FilePath, R"cpp(
template <typename T, typename U, int X = 5> class Foo {};
template <typename T> class Foo<int, T> {};
template <> class Foo<bool, int> {};
@ -674,7 +675,7 @@ TEST_F(DocumentSymbolsTest, TempSpecs) {
)cpp");
// Foo is higher ranked because of exact name match.
EXPECT_THAT(
getSymbols("foo.cpp"),
getSymbols(FilePath),
UnorderedElementsAre(
AllOf(WithName("Foo"), WithKind(SymbolKind::Class)),
AllOf(WithName("Foo<int, T>"), WithKind(SymbolKind::Class)),
@ -683,7 +684,8 @@ TEST_F(DocumentSymbolsTest, TempSpecs) {
}
TEST_F(DocumentSymbolsTest, Qualifiers) {
addFile("foo.cpp", R"cpp(
std::string FilePath = testPath("foo.cpp");
addFile(FilePath, R"cpp(
namespace foo { namespace bar {
struct Cls;
@ -706,7 +708,7 @@ TEST_F(DocumentSymbolsTest, Qualifiers) {
)cpp");
// All the qualifiers should be preserved exactly as written.
EXPECT_THAT(getSymbols("foo.cpp"),
EXPECT_THAT(getSymbols(FilePath),
UnorderedElementsAre(
WithName("foo"), WithName("foo::bar::Cls"),
WithName("foo::bar::func1"), WithName("::foo::bar::func2"),
@ -715,7 +717,8 @@ TEST_F(DocumentSymbolsTest, Qualifiers) {
}
TEST_F(DocumentSymbolsTest, QualifiersWithTemplateArgs) {
addFile("foo.cpp", R"cpp(
std::string FilePath = testPath("foo.cpp");
addFile(FilePath, R"cpp(
template <typename T, typename U = double> class Foo;
template <>
@ -738,7 +741,7 @@ TEST_F(DocumentSymbolsTest, QualifiersWithTemplateArgs) {
int Foo_type::method3() { return 30; }
)cpp");
EXPECT_THAT(
getSymbols("foo.cpp"),
getSymbols(FilePath),
UnorderedElementsAre(WithName("Foo"), WithName("Foo<int, double>"),
WithName("int_type"),
WithName("Foo<int_type, double>::method1"),

View File

@ -17,7 +17,9 @@
#include "Annotations.h"
#include "Compiler.h"
#include "Diagnostics.h"
#include "Headers.h"
#include "ParsedAST.h"
#include "Preamble.h"
#include "SourceCode.h"
#include "TestFS.h"
#include "TestTU.h"
@ -28,6 +30,7 @@
#include "clang/Lex/PPCallbacks.h"
#include "clang/Lex/Token.h"
#include "clang/Tooling/Syntax/Tokens.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/ScopedPrinter.h"
#include "gmock/gmock-matchers.h"
@ -82,6 +85,13 @@ MATCHER_P(RangeIs, R, "") {
return arg.beginOffset() == R.Begin && arg.endOffset() == R.End;
}
MATCHER(EqInc, "") {
Inclusion Actual = testing::get<0>(arg);
Inclusion Expected = testing::get<1>(arg);
return std::tie(Actual.HashLine, Actual.Written) ==
std::tie(Expected.HashLine, Expected.Written);
}
TEST(ParsedASTTest, TopLevelDecls) {
TestTU TU;
TU.HeaderCode = R"(
@ -431,6 +441,105 @@ TEST(ParsedASTTest, ReplayPreambleForTidyCheckers) {
}
}
TEST(ParsedASTTest, PatchesAdditionalIncludes) {
llvm::StringLiteral ModifiedContents = R"cpp(
#include "baz.h"
#include "foo.h"
#include "sub/aux.h"
void bar() {
foo();
baz();
aux();
})cpp";
// Build expected ast with symbols coming from headers.
TestTU TU;
TU.Filename = "foo.cpp";
TU.AdditionalFiles["foo.h"] = "void foo();";
TU.AdditionalFiles["sub/baz.h"] = "void baz();";
TU.AdditionalFiles["sub/aux.h"] = "void aux();";
TU.ExtraArgs = {"-I" + testPath("sub")};
TU.Code = ModifiedContents.str();
auto ExpectedAST = TU.build();
// Build preamble with no includes.
TU.Code = "";
StoreDiags Diags;
auto Inputs = TU.inputs();
auto CI = buildCompilerInvocation(Inputs, Diags);
auto EmptyPreamble =
buildPreamble(testPath("foo.cpp"), *CI, Inputs, true, nullptr);
ASSERT_TRUE(EmptyPreamble);
EXPECT_THAT(EmptyPreamble->Includes.MainFileIncludes, testing::IsEmpty());
// Now build an AST using empty preamble and ensure patched includes worked.
TU.Code = ModifiedContents.str();
Inputs = TU.inputs();
auto PatchedAST = ParsedAST::build(testPath("foo.cpp"), Inputs, std::move(CI),
{}, EmptyPreamble);
ASSERT_TRUE(PatchedAST);
ASSERT_TRUE(PatchedAST->getDiagnostics().empty());
// Ensure source location information is correct, including resolved paths.
EXPECT_THAT(PatchedAST->getIncludeStructure().MainFileIncludes,
testing::Pointwise(
EqInc(), ExpectedAST.getIncludeStructure().MainFileIncludes));
auto StringMapToVector = [](const llvm::StringMap<unsigned> SM) {
std::vector<std::pair<std::string, unsigned>> Res;
for (const auto &E : SM)
Res.push_back({E.first().str(), E.second});
llvm::sort(Res);
return Res;
};
// Ensure file proximity signals are correct.
EXPECT_EQ(StringMapToVector(PatchedAST->getIncludeStructure().includeDepth(
testPath("foo.cpp"))),
StringMapToVector(ExpectedAST.getIncludeStructure().includeDepth(
testPath("foo.cpp"))));
}
TEST(ParsedASTTest, PatchesDeletedIncludes) {
TestTU TU;
TU.Filename = "foo.cpp";
TU.Code = "";
auto ExpectedAST = TU.build();
// Build preamble with no includes.
TU.Code = R"cpp(#include <foo.h>)cpp";
StoreDiags Diags;
auto Inputs = TU.inputs();
auto CI = buildCompilerInvocation(Inputs, Diags);
auto BaselinePreamble =
buildPreamble(testPath("foo.cpp"), *CI, Inputs, true, nullptr);
ASSERT_TRUE(BaselinePreamble);
EXPECT_THAT(BaselinePreamble->Includes.MainFileIncludes,
ElementsAre(testing::Field(&Inclusion::Written, "<foo.h>")));
// Now build an AST using additional includes and check that locations are
// correctly parsed.
TU.Code = "";
Inputs = TU.inputs();
auto PatchedAST = ParsedAST::build(testPath("foo.cpp"), Inputs, std::move(CI),
{}, BaselinePreamble);
ASSERT_TRUE(PatchedAST);
// Ensure source location information is correct.
EXPECT_THAT(PatchedAST->getIncludeStructure().MainFileIncludes,
testing::Pointwise(
EqInc(), ExpectedAST.getIncludeStructure().MainFileIncludes));
auto StringMapToVector = [](const llvm::StringMap<unsigned> SM) {
std::vector<std::pair<std::string, unsigned>> Res;
for (const auto &E : SM)
Res.push_back({E.first().str(), E.second});
llvm::sort(Res);
return Res;
};
// Ensure file proximity signals are correct.
EXPECT_EQ(StringMapToVector(PatchedAST->getIncludeStructure().includeDepth(
testPath("foo.cpp"))),
StringMapToVector(ExpectedAST.getIncludeStructure().includeDepth(
testPath("foo.cpp"))));
}
} // namespace
} // namespace clangd
} // namespace clang

View File

@ -8,6 +8,7 @@
#include "Annotations.h"
#include "Compiler.h"
#include "Headers.h"
#include "Preamble.h"
#include "TestFS.h"
#include "TestTU.h"
@ -21,6 +22,7 @@
#include "gmock/gmock.h"
#include "gtest/gtest.h"
#include <clang/Frontend/FrontendActions.h>
#include <memory>
#include <string>
#include <vector>
@ -30,51 +32,58 @@ namespace clang {
namespace clangd {
namespace {
MATCHER_P2(Distance, File, D, "") {
return arg.first() == File && arg.second == D;
}
std::shared_ptr<const PreambleData>
createPreamble(llvm::StringRef Contents = "") {
auto TU = TestTU::withCode(Contents);
// ms-compatibility changes meaning of #import, make sure it is turned off.
TU.ExtraArgs = {"-fno-ms-compatibility"};
TU.Filename = "preamble.cpp";
auto PI = TU.inputs();
IgnoreDiagnostics Diags;
auto CI = buildCompilerInvocation(PI, Diags);
if (!CI) {
ADD_FAILURE() << "failed to build compiler invocation";
return nullptr;
}
if (auto Preamble = buildPreamble(TU.Filename, *CI, PI, true, nullptr))
return Preamble;
ADD_FAILURE() << "failed to build preamble";
return nullptr;
}
// Builds a preamble for BaselineContents, patches it for ModifiedContents and
// returns the includes in the patch.
IncludeStructure
collectPatchedIncludes(llvm::StringRef ModifiedContents,
llvm::StringRef BaselineContents,
llvm::StringRef MainFileName = "main.cpp") {
std::string MainFile = testPath(MainFileName);
ParseInputs PI;
PI.FS = new llvm::vfs::InMemoryFileSystem;
MockCompilationDatabase CDB;
auto BaselinePreamble = createPreamble(BaselineContents);
// Create the patch.
auto TU = TestTU::withCode(ModifiedContents);
TU.Filename = MainFileName.str();
// ms-compatibility changes meaning of #import, make sure it is turned off.
CDB.ExtraClangFlags.push_back("-fno-ms-compatibility");
PI.CompileCommand = CDB.getCompileCommand(MainFile).getValue();
// Create invocation
TU.ExtraArgs = {"-fno-ms-compatibility"};
auto PI = TU.inputs();
auto PP = PreamblePatch::create(testPath(TU.Filename), PI, *BaselinePreamble);
// Collect patch contents.
IgnoreDiagnostics Diags;
auto CI = buildCompilerInvocation(PI, Diags);
assert(CI && "failed to create compiler invocation");
// Build baseline preamble.
PI.Contents = BaselineContents.str();
PI.Version = "baseline preamble";
auto BaselinePreamble = buildPreamble(MainFile, *CI, PI, true, nullptr);
assert(BaselinePreamble && "failed to build baseline preamble");
// Create the patch.
PI.Contents = ModifiedContents.str();
PI.Version = "modified contents";
auto PP = PreamblePatch::create(MainFile, PI, *BaselinePreamble);
// Collect patch contents.
PP.apply(*CI);
llvm::StringRef PatchContents;
for (const auto &Rempaped : CI->getPreprocessorOpts().RemappedFileBuffers) {
if (Rempaped.first == testPath("__preamble_patch__.h")) {
PatchContents = Rempaped.second->getBuffer();
break;
}
}
// Run preprocessor over the modified contents with patched Invocation to and
// BaselinePreamble to collect includes in the patch. We trim the input to
// only preamble section to not collect includes in the mainfile.
// Run preprocessor over the modified contents with patched Invocation. We
// provide a preamble and trim contents to ensure only the implicit header
// introduced by the patch is parsed and nothing else.
// We don't run PP directly over the patch cotents to test production
// behaviour.
auto Bounds = Lexer::ComputePreamble(ModifiedContents, *CI->getLangOpts());
auto Clang =
prepareCompilerInstance(std::move(CI), &BaselinePreamble->Preamble,
llvm::MemoryBuffer::getMemBufferCopy(
ModifiedContents.slice(0, Bounds.Size).str()),
PI.FS, Diags);
Clang->getPreprocessorOpts().ImplicitPCHInclude.clear();
PreprocessOnlyAction Action;
if (!Action.BeginSourceFile(*Clang, Clang->getFrontendOpts().Inputs[0])) {
ADD_FAILURE() << "failed begin source file";
@ -163,6 +172,33 @@ TEST(PreamblePatchTest, MainFileIsEscaped) {
EXPECT_THAT(Includes, ElementsAre(AllOf(Field(&Inclusion::Written, "<a.h>"),
Field(&Inclusion::HashLine, 0))));
}
TEST(PreamblePatchTest, PatchesPreambleIncludes) {
IgnoreDiagnostics Diags;
auto TU = TestTU::withCode(R"cpp(
#include "a.h"
#include "c.h"
)cpp");
TU.AdditionalFiles["a.h"] = "#include \"b.h\"";
TU.AdditionalFiles["b.h"] = "";
TU.AdditionalFiles["c.h"] = "";
auto PI = TU.inputs();
auto BaselinePreamble = buildPreamble(
TU.Filename, *buildCompilerInvocation(PI, Diags), PI, true, nullptr);
// We drop c.h from modified and add a new header. Since the latter is patched
// we should only get a.h in preamble includes.
TU.Code = R"cpp(
#include "a.h"
#include "b.h"
)cpp";
auto PP = PreamblePatch::create(testPath(TU.Filename), TU.inputs(),
*BaselinePreamble);
// Only a.h should exists in the preamble, as c.h has been dropped and b.h was
// newly introduced.
EXPECT_THAT(PP.preambleIncludes(),
ElementsAre(AllOf(Field(&Inclusion::Written, "\"a.h\""),
Field(&Inclusion::Resolved, testPath("a.h")))));
}
} // namespace
} // namespace clangd
} // namespace clang