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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
|
//===- unittests/Ninja/lexer.cpp ------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2014 - 2015 Apple Inc. and the Swift project authors
// Licensed under Apache License v2.0 with Runtime Library Exception
//
// See http://swift.org/LICENSE.txt for license information
// See http://swift.org/CONTRIBUTORS.txt for the list of Swift project authors
//
//===----------------------------------------------------------------------===//
#include "llbuild/Ninja/Lexer.h"
#include "llbuild/Basic/LLVM.h"
#include "gtest/gtest.h"
using namespace llbuild;
namespace {
TEST(LexerTest, basic) {
StringRef input = "| : || # Comment\n";
ninja::Lexer lexer(input);
// Check that we get the appropriate tokens.
ninja::Token tok;
ninja::Token& result = lexer.lex(tok);
// Check .lex() result.
EXPECT_EQ(&result, &tok);
// Check first token.
EXPECT_EQ(ninja::Token::Kind::Pipe, tok.tokenKind);
EXPECT_EQ(&input.data()[0], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(0U, tok.column);
// Check second token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Colon, tok.tokenKind);
EXPECT_EQ(&input.data()[2], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(2U, tok.column);
// Check third token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::PipePipe, tok.tokenKind);
EXPECT_EQ(&input.data()[4], tok.start);
EXPECT_EQ(2U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(4U, tok.column);
// Check fourth token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Comment, tok.tokenKind);
EXPECT_EQ(&input.data()[7], tok.start);
EXPECT_EQ(9U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(7U, tok.column);
// Check fifth token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
EXPECT_EQ(&input.data()[16], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(16U, tok.column);
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
EXPECT_EQ(input.end(), tok.start);
EXPECT_EQ(0U, tok.length);
EXPECT_EQ(2U, tok.line);
EXPECT_EQ(0U, tok.column);
// Check we continue to get EOF.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, indentation) {
StringRef input = "\
|\n\
| |";
ninja::Lexer lexer(input);
// Check that we get an indentation token for whitespace, but only at the
// start of a line.
ninja::Token tok;
lexer.lex(tok);
// Check first token.
EXPECT_EQ(ninja::Token::Kind::Pipe, tok.tokenKind);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(0U, tok.column);
// Check second token (the newline).
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(1U, tok.column);
// Check third token (our indentation token).
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Indentation, tok.tokenKind);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(2U, tok.line);
EXPECT_EQ(0U, tok.column);
// Check fourth token (the pipe following indentation).
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Pipe, tok.tokenKind);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(2U, tok.line);
EXPECT_EQ(1U, tok.column);
// Check fifth token (skipping whitespace).
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Pipe, tok.tokenKind);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(2U, tok.line);
EXPECT_EQ(3U, tok.column);
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, basicIdentifierHandling) {
StringRef input = "a b$c";
ninja::Lexer lexer(input);
ninja::Token tok;
// Check first token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(&input.data()[0], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(0U, tok.column);
// Check second token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(&input.data()[2], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(2U, tok.column);
// Check third token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Unknown, tok.tokenKind);
EXPECT_EQ(&input.data()[3], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(3U, tok.column);
// Check fourth token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(&input.data()[4], tok.start);
EXPECT_EQ(1U, tok.length);
EXPECT_EQ(1U, tok.line);
EXPECT_EQ(4U, tok.column);
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, identifierKeywords) {
StringRef input = "notakeyword build default include \
pool rule subninja";
ninja::Lexer lexer(input);
ninja::Token tok;
// Check first token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "notakeyword", tok.length));
// Check the various keywords.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWBuild, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "build", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWDefault, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "default", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWInclude, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "include", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWPool, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "pool", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWRule, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "rule", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::KWSubninja, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "subninja", tok.length));
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, pathStrings) {
StringRef input = "this is: a| path$ str$:ing$\ncontext\n\
#hash-is-ok\n\
=equal-is-too\n";
ninja::Lexer lexer(input);
ninja::Token tok;
// Put the lexer into "path" string mode.
lexer.setMode(ninja::Lexer::LexingMode::PathString);
// Check we still split on spaces.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "this", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "is", tok.length));
// Check that we recognized the other tokens.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Colon, tok.tokenKind);
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "a", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Pipe, tok.tokenKind);
// Check that we honor escape sequences.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "path$ str$:ing$\ncontext", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
// Check that we allow '#' and '=' in path strings.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "#hash-is-ok", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "=equal-is-too", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, variableStrings) {
StringRef input = "\
this is one string\n\
this string crosses a $\nnewline\n\
:\n\
|\n";
ninja::Lexer lexer(input);
ninja::Token tok;
// Put the lexer into "variable" string mode.
lexer.setMode(ninja::Lexer::LexingMode::VariableString);
// Check we consume spaces in strings.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(std::string("String"), tok.getKindName());
EXPECT_EQ(0, memcmp(tok.start, "this is one string", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
// Check that we honor the newline escape.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "this string crosses a $\nnewline",
tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
// Check that we respect special characters at the start of the token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, ":", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::String, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "|", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Newline, tok.tokenKind);
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
TEST(LexerTest, identifierSpecific) {
StringRef input = "rule pool build default include subninja random";
ninja::Lexer lexer(input);
ninja::Token tok;
// Put the lexer into "identifier specific" string mode.
lexer.setMode(ninja::Lexer::LexingMode::IdentifierSpecific);
// Check we recognize all of the keywords as identifiers.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "rule", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "pool", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "build", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "default", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "include", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "subninja", tok.length));
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::Identifier, tok.tokenKind);
EXPECT_EQ(0, memcmp(tok.start, "random", tok.length));
// Check final token.
lexer.lex(tok);
EXPECT_EQ(ninja::Token::Kind::EndOfFile, tok.tokenKind);
}
}
|
