1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
|
//===--- SourceCode.h - Manipulating source code as strings -----*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "SourceCode.h"
#include "Logger.h"
#include "clang/AST/ASTContext.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/Path.h"
namespace clang {
namespace clangd {
using namespace llvm;
// Here be dragons. LSP positions use columns measured in *UTF-16 code units*!
// Clangd uses UTF-8 and byte-offsets internally, so conversion is nontrivial.
// Iterates over unicode codepoints in the (UTF-8) string. For each,
// invokes CB(UTF-8 length, UTF-16 length), and breaks if it returns true.
// Returns true if CB returned true, false if we hit the end of string.
template <typename Callback>
static bool iterateCodepoints(StringRef U8, const Callback &CB) {
for (size_t I = 0; I < U8.size();) {
unsigned char C = static_cast<unsigned char>(U8[I]);
if (LLVM_LIKELY(!(C & 0x80))) { // ASCII character.
if (CB(1, 1))
return true;
++I;
continue;
}
// This convenient property of UTF-8 holds for all non-ASCII characters.
size_t UTF8Length = countLeadingOnes(C);
// 0xxx is ASCII, handled above. 10xxx is a trailing byte, invalid here.
// 11111xxx is not valid UTF-8 at all. Assert because it's probably our bug.
assert((UTF8Length >= 2 && UTF8Length <= 4) &&
"Invalid UTF-8, or transcoding bug?");
I += UTF8Length; // Skip over all trailing bytes.
// A codepoint takes two UTF-16 code unit if it's astral (outside BMP).
// Astral codepoints are encoded as 4 bytes in UTF-8 (11110xxx ...)
if (CB(UTF8Length, UTF8Length == 4 ? 2 : 1))
return true;
}
return false;
}
// Returns the offset into the string that matches \p Units UTF-16 code units.
// Conceptually, this converts to UTF-16, truncates to CodeUnits, converts back
// to UTF-8, and returns the length in bytes.
static size_t measureUTF16(StringRef U8, int U16Units, bool &Valid) {
size_t Result = 0;
Valid = U16Units == 0 || iterateCodepoints(U8, [&](int U8Len, int U16Len) {
Result += U8Len;
U16Units -= U16Len;
return U16Units <= 0;
});
if (U16Units < 0) // Offset was into the middle of a surrogate pair.
Valid = false;
// Don't return an out-of-range index if we overran.
return std::min(Result, U8.size());
}
// Counts the number of UTF-16 code units needed to represent a string.
// Like most strings in clangd, the input is UTF-8 encoded.
static size_t utf16Len(StringRef U8) {
// A codepoint takes two UTF-16 code unit if it's astral (outside BMP).
// Astral codepoints are encoded as 4 bytes in UTF-8, starting with 11110xxx.
size_t Count = 0;
iterateCodepoints(U8, [&](int U8Len, int U16Len) {
Count += U16Len;
return false;
});
return Count;
}
llvm::Expected<size_t> positionToOffset(StringRef Code, Position P,
bool AllowColumnsBeyondLineLength) {
if (P.line < 0)
return llvm::make_error<llvm::StringError>(
llvm::formatv("Line value can't be negative ({0})", P.line),
llvm::errc::invalid_argument);
if (P.character < 0)
return llvm::make_error<llvm::StringError>(
llvm::formatv("Character value can't be negative ({0})", P.character),
llvm::errc::invalid_argument);
size_t StartOfLine = 0;
for (int I = 0; I != P.line; ++I) {
size_t NextNL = Code.find('\n', StartOfLine);
if (NextNL == StringRef::npos)
return llvm::make_error<llvm::StringError>(
llvm::formatv("Line value is out of range ({0})", P.line),
llvm::errc::invalid_argument);
StartOfLine = NextNL + 1;
}
size_t NextNL = Code.find('\n', StartOfLine);
if (NextNL == StringRef::npos)
NextNL = Code.size();
bool Valid;
size_t ByteOffsetInLine = measureUTF16(
Code.substr(StartOfLine, NextNL - StartOfLine), P.character, Valid);
if (!Valid && !AllowColumnsBeyondLineLength)
return llvm::make_error<llvm::StringError>(
llvm::formatv("UTF-16 offset {0} is invalid for line {1}", P.character,
P.line),
llvm::errc::invalid_argument);
return StartOfLine + ByteOffsetInLine;
}
Position offsetToPosition(StringRef Code, size_t Offset) {
Offset = std::min(Code.size(), Offset);
StringRef Before = Code.substr(0, Offset);
int Lines = Before.count('\n');
size_t PrevNL = Before.rfind('\n');
size_t StartOfLine = (PrevNL == StringRef::npos) ? 0 : (PrevNL + 1);
Position Pos;
Pos.line = Lines;
Pos.character = utf16Len(Before.substr(StartOfLine));
return Pos;
}
Position sourceLocToPosition(const SourceManager &SM, SourceLocation Loc) {
// We use the SourceManager's line tables, but its column number is in bytes.
FileID FID;
unsigned Offset;
std::tie(FID, Offset) = SM.getDecomposedSpellingLoc(Loc);
Position P;
P.line = static_cast<int>(SM.getLineNumber(FID, Offset)) - 1;
bool Invalid = false;
StringRef Code = SM.getBufferData(FID, &Invalid);
if (!Invalid) {
auto ColumnInBytes = SM.getColumnNumber(FID, Offset) - 1;
auto LineSoFar = Code.substr(Offset - ColumnInBytes, ColumnInBytes);
P.character = utf16Len(LineSoFar);
}
return P;
}
Range halfOpenToRange(const SourceManager &SM, CharSourceRange R) {
// Clang is 1-based, LSP uses 0-based indexes.
Position Begin = sourceLocToPosition(SM, R.getBegin());
Position End = sourceLocToPosition(SM, R.getEnd());
return {Begin, End};
}
std::pair<size_t, size_t> offsetToClangLineColumn(StringRef Code,
size_t Offset) {
Offset = std::min(Code.size(), Offset);
StringRef Before = Code.substr(0, Offset);
int Lines = Before.count('\n');
size_t PrevNL = Before.rfind('\n');
size_t StartOfLine = (PrevNL == StringRef::npos) ? 0 : (PrevNL + 1);
return {Lines + 1, Offset - StartOfLine + 1};
}
std::pair<llvm::StringRef, llvm::StringRef>
splitQualifiedName(llvm::StringRef QName) {
size_t Pos = QName.rfind("::");
if (Pos == llvm::StringRef::npos)
return {StringRef(), QName};
return {QName.substr(0, Pos + 2), QName.substr(Pos + 2)};
}
TextEdit replacementToEdit(StringRef Code, const tooling::Replacement &R) {
Range ReplacementRange = {
offsetToPosition(Code, R.getOffset()),
offsetToPosition(Code, R.getOffset() + R.getLength())};
return {ReplacementRange, R.getReplacementText()};
}
std::vector<TextEdit> replacementsToEdits(StringRef Code,
const tooling::Replacements &Repls) {
std::vector<TextEdit> Edits;
for (const auto &R : Repls)
Edits.push_back(replacementToEdit(Code, R));
return Edits;
}
llvm::Optional<std::string>
getAbsoluteFilePath(const FileEntry *F, const SourceManager &SourceMgr) {
SmallString<64> FilePath = F->tryGetRealPathName();
if (FilePath.empty())
FilePath = F->getName();
if (!llvm::sys::path::is_absolute(FilePath)) {
if (!SourceMgr.getFileManager().makeAbsolutePath(FilePath)) {
log("Could not turn relative path to absolute: {0}", FilePath);
return llvm::None;
}
}
return FilePath.str().str();
}
TextEdit toTextEdit(const FixItHint &FixIt, const SourceManager &M,
const LangOptions &L) {
TextEdit Result;
Result.range =
halfOpenToRange(M, Lexer::makeFileCharRange(FixIt.RemoveRange, M, L));
Result.newText = FixIt.CodeToInsert;
return Result;
}
} // namespace clangd
} // namespace clang
|
