llvm-project/clang-tools-extra/clangd/SourceCode.h

202 lines
8.8 KiB
C
Raw Normal View History

//===--- SourceCode.h - Manipulating source code as strings -----*- 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
//
//===----------------------------------------------------------------------===//
//
// Various code that examines C++ source code without using heavy AST machinery
// (and often not even the lexer). To be used sparingly!
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_TOOLS_EXTRA_CLANGD_SOURCECODE_H
#define LLVM_CLANG_TOOLS_EXTRA_CLANGD_SOURCECODE_H
#include "Context.h"
#include "Protocol.h"
#include "clang/Basic/Diagnostic.h"
#include "clang/Basic/LangOptions.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "clang/Tooling/Core/Replacement.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/SHA1.h"
namespace clang {
class SourceManager;
namespace clangd {
// We tend to generate digests for source codes in a lot of different places.
// This represents the type for those digests to prevent us hard coding details
// of hashing function at every place that needs to store this information.
using FileDigest = decltype(llvm::SHA1::hash({}));
FileDigest digest(StringRef Content);
Optional<FileDigest> digestFile(const SourceManager &SM, FileID FID);
// This context variable controls the behavior of functions in this file
// that convert between LSP offsets and native clang byte offsets.
// If not set, defaults to UTF-16 for backwards-compatibility.
extern Key<OffsetEncoding> kCurrentOffsetEncoding;
// Counts the number of UTF-16 code units needed to represent a string (LSP
// specifies string lengths in UTF-16 code units).
// Use of UTF-16 may be overridden by kCurrentOffsetEncoding.
size_t lspLength(StringRef Code);
/// Turn a [line, column] pair into an offset in Code.
///
[clangd] Fix unicode handling, using UTF-16 where LSP requires it. Summary: The Language Server Protocol unfortunately mandates that locations in files be represented by line/column pairs, where the "column" is actually an index into the UTF-16-encoded text of the line. (This is because VSCode is written in JavaScript, which is UTF-16-native). Internally clangd treats source files at UTF-8, the One True Encoding, and generally deals with byte offsets (though there are exceptions). Before this patch, conversions between offsets and LSP Position pretended that Position.character was UTF-8 bytes, which is only true for ASCII lines. Now we examine the text to convert correctly (but don't actually need to transcode it, due to some nice details of the encodings). The updated functions in SourceCode are the blessed way to interact with the Position.character field, and anything else is likely to be wrong. So I also updated the other accesses: - CodeComplete needs a "clang-style" line/column, with column in utf-8 bytes. This is now converted via Position -> offset -> clang line/column (a new function is added to SourceCode.h for the second conversion). - getBeginningOfIdentifier skipped backwards in UTF-16 space, which is will behave badly when it splits a surrogate pair. Skipping backwards in UTF-8 coordinates gives the lexer a fighting chance of getting this right. While here, I clarified(?) the logic comments, fixed a bug with identifiers containing digits, simplified the signature slightly and added a test. This seems likely to cause problems with editors that have the same bug, and treat the protocol as if columns are UTF-8 bytes. But we can find and fix those. Reviewers: hokein Subscribers: klimek, ilya-biryukov, ioeric, MaskRay, jkorous, cfe-commits Differential Revision: https://reviews.llvm.org/D46035 llvm-svn: 331029
2018-04-27 19:59:28 +08:00
/// If P.character exceeds the line length, returns the offset at end-of-line.
/// (If !AllowColumnsBeyondLineLength, then returns an error instead).
/// If the line number is out of range, returns an error.
///
/// The returned value is in the range [0, Code.size()].
llvm::Expected<size_t>
positionToOffset(llvm::StringRef Code, Position P,
bool AllowColumnsBeyondLineLength = true);
/// Turn an offset in Code into a [line, column] pair.
[clangd] Fix unicode handling, using UTF-16 where LSP requires it. Summary: The Language Server Protocol unfortunately mandates that locations in files be represented by line/column pairs, where the "column" is actually an index into the UTF-16-encoded text of the line. (This is because VSCode is written in JavaScript, which is UTF-16-native). Internally clangd treats source files at UTF-8, the One True Encoding, and generally deals with byte offsets (though there are exceptions). Before this patch, conversions between offsets and LSP Position pretended that Position.character was UTF-8 bytes, which is only true for ASCII lines. Now we examine the text to convert correctly (but don't actually need to transcode it, due to some nice details of the encodings). The updated functions in SourceCode are the blessed way to interact with the Position.character field, and anything else is likely to be wrong. So I also updated the other accesses: - CodeComplete needs a "clang-style" line/column, with column in utf-8 bytes. This is now converted via Position -> offset -> clang line/column (a new function is added to SourceCode.h for the second conversion). - getBeginningOfIdentifier skipped backwards in UTF-16 space, which is will behave badly when it splits a surrogate pair. Skipping backwards in UTF-8 coordinates gives the lexer a fighting chance of getting this right. While here, I clarified(?) the logic comments, fixed a bug with identifiers containing digits, simplified the signature slightly and added a test. This seems likely to cause problems with editors that have the same bug, and treat the protocol as if columns are UTF-8 bytes. But we can find and fix those. Reviewers: hokein Subscribers: klimek, ilya-biryukov, ioeric, MaskRay, jkorous, cfe-commits Differential Revision: https://reviews.llvm.org/D46035 llvm-svn: 331029
2018-04-27 19:59:28 +08:00
/// The offset must be in range [0, Code.size()].
Position offsetToPosition(llvm::StringRef Code, size_t Offset);
/// Turn a SourceLocation into a [line, column] pair.
/// FIXME: This should return an error if the location is invalid.
Position sourceLocToPosition(const SourceManager &SM, SourceLocation Loc);
/// Return the file location, corresponding to \p P. Note that one should take
/// care to avoid comparing the result with expansion locations.
llvm::Expected<SourceLocation> sourceLocationInMainFile(const SourceManager &SM,
Position P);
/// Turns a token range into a half-open range and checks its correctness.
/// The resulting range will have only valid source location on both sides, both
/// of which are file locations.
///
/// File locations always point to a particular offset in a file, i.e. they
/// never refer to a location inside a macro expansion. Turning locations from
/// macro expansions into file locations is ambiguous - one can use
/// SourceManager::{getExpansion|getFile|getSpelling}Loc. This function
/// calls SourceManager::getFileLoc on both ends of \p R to do the conversion.
///
/// User input (e.g. cursor position) is expressed as a file location, so this
/// function can be viewed as a way to normalize the ranges used in the clang
/// AST so that they are comparable with ranges coming from the user input.
llvm::Optional<SourceRange> toHalfOpenFileRange(const SourceManager &Mgr,
const LangOptions &LangOpts,
SourceRange R);
/// Returns true iff all of the following conditions hold:
/// - start and end locations are valid,
/// - start and end locations are file locations from the same file
/// (i.e. expansion locations are not taken into account).
/// - start offset <= end offset.
/// FIXME: introduce a type for source range with this invariant.
bool isValidFileRange(const SourceManager &Mgr, SourceRange R);
/// Returns true iff \p L is contained in \p R.
/// EXPECTS: isValidFileRange(R) == true, L is a file location.
bool halfOpenRangeContains(const SourceManager &Mgr, SourceRange R,
SourceLocation L);
/// Returns true iff \p L is contained in \p R or \p L is equal to the end point
/// of \p R.
/// EXPECTS: isValidFileRange(R) == true, L is a file location.
bool halfOpenRangeTouches(const SourceManager &Mgr, SourceRange R,
SourceLocation L);
/// Returns the source code covered by the source range.
/// EXPECTS: isValidFileRange(R) == true.
llvm::StringRef toSourceCode(const SourceManager &SM, SourceRange R);
// Converts a half-open clang source range to an LSP range.
// Note that clang also uses closed source ranges, which this can't handle!
Range halfOpenToRange(const SourceManager &SM, CharSourceRange R);
[clangd] Fix unicode handling, using UTF-16 where LSP requires it. Summary: The Language Server Protocol unfortunately mandates that locations in files be represented by line/column pairs, where the "column" is actually an index into the UTF-16-encoded text of the line. (This is because VSCode is written in JavaScript, which is UTF-16-native). Internally clangd treats source files at UTF-8, the One True Encoding, and generally deals with byte offsets (though there are exceptions). Before this patch, conversions between offsets and LSP Position pretended that Position.character was UTF-8 bytes, which is only true for ASCII lines. Now we examine the text to convert correctly (but don't actually need to transcode it, due to some nice details of the encodings). The updated functions in SourceCode are the blessed way to interact with the Position.character field, and anything else is likely to be wrong. So I also updated the other accesses: - CodeComplete needs a "clang-style" line/column, with column in utf-8 bytes. This is now converted via Position -> offset -> clang line/column (a new function is added to SourceCode.h for the second conversion). - getBeginningOfIdentifier skipped backwards in UTF-16 space, which is will behave badly when it splits a surrogate pair. Skipping backwards in UTF-8 coordinates gives the lexer a fighting chance of getting this right. While here, I clarified(?) the logic comments, fixed a bug with identifiers containing digits, simplified the signature slightly and added a test. This seems likely to cause problems with editors that have the same bug, and treat the protocol as if columns are UTF-8 bytes. But we can find and fix those. Reviewers: hokein Subscribers: klimek, ilya-biryukov, ioeric, MaskRay, jkorous, cfe-commits Differential Revision: https://reviews.llvm.org/D46035 llvm-svn: 331029
2018-04-27 19:59:28 +08:00
// Converts an offset to a clang line/column (1-based, columns are bytes).
// The offset must be in range [0, Code.size()].
// Prefer to use SourceManager if one is available.
std::pair<size_t, size_t> offsetToClangLineColumn(llvm::StringRef Code,
size_t Offset);
[clangd] Fix unicode handling, using UTF-16 where LSP requires it. Summary: The Language Server Protocol unfortunately mandates that locations in files be represented by line/column pairs, where the "column" is actually an index into the UTF-16-encoded text of the line. (This is because VSCode is written in JavaScript, which is UTF-16-native). Internally clangd treats source files at UTF-8, the One True Encoding, and generally deals with byte offsets (though there are exceptions). Before this patch, conversions between offsets and LSP Position pretended that Position.character was UTF-8 bytes, which is only true for ASCII lines. Now we examine the text to convert correctly (but don't actually need to transcode it, due to some nice details of the encodings). The updated functions in SourceCode are the blessed way to interact with the Position.character field, and anything else is likely to be wrong. So I also updated the other accesses: - CodeComplete needs a "clang-style" line/column, with column in utf-8 bytes. This is now converted via Position -> offset -> clang line/column (a new function is added to SourceCode.h for the second conversion). - getBeginningOfIdentifier skipped backwards in UTF-16 space, which is will behave badly when it splits a surrogate pair. Skipping backwards in UTF-8 coordinates gives the lexer a fighting chance of getting this right. While here, I clarified(?) the logic comments, fixed a bug with identifiers containing digits, simplified the signature slightly and added a test. This seems likely to cause problems with editors that have the same bug, and treat the protocol as if columns are UTF-8 bytes. But we can find and fix those. Reviewers: hokein Subscribers: klimek, ilya-biryukov, ioeric, MaskRay, jkorous, cfe-commits Differential Revision: https://reviews.llvm.org/D46035 llvm-svn: 331029
2018-04-27 19:59:28 +08:00
/// From "a::b::c", return {"a::b::", "c"}. Scope is empty if there's no
/// qualifier.
std::pair<llvm::StringRef, llvm::StringRef>
splitQualifiedName(llvm::StringRef QName);
TextEdit replacementToEdit(StringRef Code, const tooling::Replacement &R);
std::vector<TextEdit> replacementsToEdits(StringRef Code,
const tooling::Replacements &Repls);
TextEdit toTextEdit(const FixItHint &FixIt, const SourceManager &M,
const LangOptions &L);
/// Get the canonical path of \p F. This means:
///
/// - Absolute path
/// - Symlinks resolved
/// - No "." or ".." component
/// - No duplicate or trailing directory separator
///
/// This function should be used when paths needs to be used outside the
/// component that generate it, so that paths are normalized as much as
/// possible.
llvm::Optional<std::string> getCanonicalPath(const FileEntry *F,
const SourceManager &SourceMgr);
bool isRangeConsecutive(const Range &Left, const Range &Right);
/// Choose the clang-format style we should apply to a certain file.
/// This will usually use FS to look for .clang-format directories.
/// FIXME: should we be caching the .clang-format file search?
/// This uses format::DefaultFormatStyle and format::DefaultFallbackStyle,
/// though the latter may have been overridden in main()!
format::FormatStyle getFormatStyleForFile(llvm::StringRef File,
llvm::StringRef Content,
llvm::vfs::FileSystem *FS);
// Cleanup and format the given replacements.
llvm::Expected<tooling::Replacements>
cleanupAndFormat(StringRef Code, const tooling::Replacements &Replaces,
const format::FormatStyle &Style);
/// Collects identifiers with counts in the source code.
llvm::StringMap<unsigned> collectIdentifiers(llvm::StringRef Content,
const format::FormatStyle &Style);
/// Collects words from the source code.
/// Unlike collectIdentifiers:
/// - also finds text in comments:
/// - splits text into words
/// - drops stopwords like "get" and "for"
llvm::StringSet<> collectWords(llvm::StringRef Content);
/// Heuristically determine namespaces visible at a point, without parsing Code.
/// This considers using-directives and enclosing namespace-declarations that
/// are visible (and not obfuscated) in the file itself (not headers).
/// Code should be truncated at the point of interest.
///
/// The returned vector is always non-empty.
/// - The first element is the namespace that encloses the point: a declaration
/// near the point would be within this namespace.
/// - The elements are the namespaces in scope at the point: an unqualified
/// lookup would search within these namespaces.
///
/// Using directives are resolved against all enclosing scopes, but no other
/// namespace directives.
///
/// example:
/// using namespace a;
/// namespace foo {
/// using namespace b;
///
/// visibleNamespaces are {"foo::", "", "a::", "b::", "foo::b::"}, not "a::b::".
std::vector<std::string> visibleNamespaces(llvm::StringRef Code,
const format::FormatStyle &Style);
} // namespace clangd
} // namespace clang
#endif