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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
| //===-- ClangHighlighter.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
//
//===----------------------------------------------------------------------===//
#include "ClangHighlighter.h"
#include "lldb/Host/FileSystem.h"
#include "lldb/Target/Language.h"
#include "lldb/Utility/AnsiTerminal.h"
#include "lldb/Utility/StreamString.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
#include "llvm/ADT/StringSet.h"
#include "llvm/Support/MemoryBuffer.h"
using namespace lldb_private;
bool ClangHighlighter::isKeyword(llvm::StringRef token) const {
return keywords.find(token) != keywords.end();
}
ClangHighlighter::ClangHighlighter() {
#define KEYWORD(X, N) keywords.insert(#X);
#include "clang/Basic/TokenKinds.def"
}
/// Determines which style should be applied to the given token.
/// \param highlighter
/// The current highlighter that should use the style.
/// \param token
/// The current token.
/// \param tok_str
/// The string in the source code the token represents.
/// \param options
/// The style we use for coloring the source code.
/// \param in_pp_directive
/// If we are currently in a preprocessor directive. NOTE: This is
/// passed by reference and will be updated if the current token starts
/// or ends a preprocessor directive.
/// \return
/// The ColorStyle that should be applied to the token.
static HighlightStyle::ColorStyle
determineClangStyle(const ClangHighlighter &highlighter,
const clang::Token &token, llvm::StringRef tok_str,
const HighlightStyle &options, bool &in_pp_directive) {
using namespace clang;
if (token.is(tok::comment)) {
// If we were in a preprocessor directive before, we now left it.
in_pp_directive = false;
return options.comment;
} else if (in_pp_directive || token.getKind() == tok::hash) {
// Let's assume that the rest of the line is a PP directive.
in_pp_directive = true;
// Preprocessor directives are hard to match, so we have to hack this in.
return options.pp_directive;
} else if (tok::isStringLiteral(token.getKind()))
return options.string_literal;
else if (tok::isLiteral(token.getKind()))
return options.scalar_literal;
else if (highlighter.isKeyword(tok_str))
return options.keyword;
else
switch (token.getKind()) {
case tok::raw_identifier:
case tok::identifier:
return options.identifier;
case tok::l_brace:
case tok::r_brace:
return options.braces;
case tok::l_square:
case tok::r_square:
return options.square_brackets;
case tok::l_paren:
case tok::r_paren:
return options.parentheses;
case tok::comma:
return options.comma;
case tok::coloncolon:
case tok::colon:
return options.colon;
case tok::amp:
case tok::ampamp:
case tok::ampequal:
case tok::star:
case tok::starequal:
case tok::plus:
case tok::plusplus:
case tok::plusequal:
case tok::minus:
case tok::arrow:
case tok::minusminus:
case tok::minusequal:
case tok::tilde:
case tok::exclaim:
case tok::exclaimequal:
case tok::slash:
case tok::slashequal:
case tok::percent:
case tok::percentequal:
case tok::less:
case tok::lessless:
case tok::lessequal:
case tok::lesslessequal:
case tok::spaceship:
case tok::greater:
case tok::greatergreater:
case tok::greaterequal:
case tok::greatergreaterequal:
case tok::caret:
case tok::caretequal:
case tok::pipe:
case tok::pipepipe:
case tok::pipeequal:
case tok::question:
case tok::equal:
case tok::equalequal:
return options.operators;
default:
break;
}
return HighlightStyle::ColorStyle();
}
void ClangHighlighter::Highlight(const HighlightStyle &options,
llvm::StringRef line,
llvm::Optional<size_t> cursor_pos,
llvm::StringRef previous_lines,
Stream &result) const {
using namespace clang;
FileSystemOptions file_opts;
FileManager file_mgr(file_opts,
FileSystem::Instance().GetVirtualFileSystem());
unsigned line_number = previous_lines.count('\n') + 1U;
// Let's build the actual source code Clang needs and setup some utility
// objects.
std::string full_source = previous_lines.str() + line.str();
llvm::IntrusiveRefCntPtr<DiagnosticIDs> diag_ids(new DiagnosticIDs());
llvm::IntrusiveRefCntPtr<DiagnosticOptions> diags_opts(
new DiagnosticOptions());
DiagnosticsEngine diags(diag_ids, diags_opts);
clang::SourceManager SM(diags, file_mgr);
auto buf = llvm::MemoryBuffer::getMemBuffer(full_source);
FileID FID = SM.createFileID(clang::SourceManager::Unowned, buf.get());
// Let's just enable the latest ObjC and C++ which should get most tokens
// right.
LangOptions Opts;
Opts.ObjC = true;
// FIXME: This should probably set CPlusPlus, CPlusPlus11, ... too
Opts.CPlusPlus17 = true;
Opts.LineComment = true;
Lexer lex(FID, buf.get(), SM, Opts);
// The lexer should keep whitespace around.
lex.SetKeepWhitespaceMode(true);
// Keeps track if we have entered a PP directive.
bool in_pp_directive = false;
// True once we actually lexed the user provided line.
bool found_user_line = false;
// True if we already highlighted the token under the cursor, false otherwise.
bool highlighted_cursor = false;
Token token;
bool exit = false;
while (!exit) {
// Returns true if this is the last token we get from the lexer.
exit = lex.LexFromRawLexer(token);
bool invalid = false;
unsigned current_line_number =
SM.getSpellingLineNumber(token.getLocation(), &invalid);
if (current_line_number != line_number)
continue;
found_user_line = true;
// We don't need to print any tokens without a spelling line number.
if (invalid)
continue;
// Same as above but with the column number.
invalid = false;
unsigned start = SM.getSpellingColumnNumber(token.getLocation(), &invalid);
if (invalid)
continue;
// Column numbers start at 1, but indexes in our string start at 0.
--start;
// Annotations don't have a length, so let's skip them.
if (token.isAnnotation())
continue;
// Extract the token string from our source code.
llvm::StringRef tok_str = line.substr(start, token.getLength());
// If the token is just an empty string, we can skip all the work below.
if (tok_str.empty())
continue;
// If the cursor is inside this token, we have to apply the 'selected'
// highlight style before applying the actual token color.
llvm::StringRef to_print = tok_str;
StreamString storage;
auto end = start + token.getLength();
if (cursor_pos && end > *cursor_pos && !highlighted_cursor) {
highlighted_cursor = true;
options.selected.Apply(storage, tok_str);
to_print = storage.GetString();
}
// See how we are supposed to highlight this token.
HighlightStyle::ColorStyle color =
determineClangStyle(*this, token, tok_str, options, in_pp_directive);
color.Apply(result, to_print);
}
// If we went over the whole file but couldn't find our own file, then
// somehow our setup was wrong. When we're in release mode we just give the
// user the normal line and pretend we don't know how to highlight it. In
// debug mode we bail out with an assert as this should never happen.
if (!found_user_line) {
result << line;
assert(false && "We couldn't find the user line in the input file?");
}
}
|