Commit | Line | Data |
---|---|---|
492700bc | 1 | /******************************************************************************* |
60ae41e1 | 2 | * Copyright (c) 2013, 2014 Etienne Bergeron |
492700bc EB |
3 | * |
4 | * All rights reserved. This program and the accompanying materials are | |
5 | * made available under the terms of the Eclipse Public License v1.0 which | |
6 | * accompanies this distribution, and is available at | |
7 | * http://www.eclipse.org/legal/epl-v10.html | |
8 | * | |
9 | * Contributors: | |
10 | * Etienne Bergeron - Initial API and implementation | |
11 | *******************************************************************************/ | |
12 | ||
13 | package org.eclipse.linuxtools.ctf.parser.tests; | |
14 | ||
15 | import static org.junit.Assert.fail; | |
16 | ||
17 | import java.util.LinkedList; | |
18 | import java.util.List; | |
19 | ||
20 | import org.antlr.runtime.ANTLRStringStream; | |
21 | import org.antlr.runtime.CharStream; | |
22 | import org.antlr.runtime.Token; | |
23 | import org.eclipse.linuxtools.ctf.parser.CTFLexer; | |
24 | import org.junit.Ignore; | |
25 | import org.junit.Test; | |
26 | ||
27 | /** | |
28 | * This test validates the CTF-Lexer implementation. | |
29 | * | |
30 | * The test splits a string into tokens with the compiled lexer and | |
31 | * validates the sequences of tokens produced by comparing their type | |
32 | * and content. | |
33 | * | |
34 | * @author Etienne Bergeron | |
35 | */ | |
36 | public class CtfLexerTest { | |
37 | ||
38 | // ------------------------------------------------------------------------ | |
39 | // Attributes | |
40 | // ------------------------------------------------------------------------ | |
41 | ||
3de23137 | 42 | private final List<Token> tokens = new LinkedList<>(); |
492700bc EB |
43 | |
44 | // ------------------------------------------------------------------------ | |
45 | // Operations | |
46 | // ------------------------------------------------------------------------ | |
47 | ||
48 | private void tokenize(String content) { | |
49 | CharStream cs = new ANTLRStringStream(content); | |
50 | CTFLexer lexer = new CTFLexer(cs); | |
51 | ||
52 | tokens.clear(); | |
53 | for (;;) { | |
54 | Token token = lexer.nextToken(); | |
55 | if (token == Token.EOF_TOKEN) { | |
56 | return; | |
57 | } | |
58 | tokens.add(token); | |
59 | } | |
60 | } | |
61 | ||
62 | private void checkToken(int type, String content) { | |
63 | Token token = tokens.remove(0); | |
64 | if (token.getType() != type) { | |
65 | fail("Invalid type [value " + token.getType() | |
66 | + " but expect " + type + "]." | |
67 | + " Fail to tokenize:" + content); | |
68 | } else if (token.getText().compareTo(content) != 0) { | |
69 | fail("Invalid content [value " + token.getText() | |
70 | + " but expect " + content + "]."); | |
71 | } | |
72 | } | |
73 | ||
74 | private void checkSingle(int type, String content) { | |
75 | tokenize(content); | |
76 | checkToken(type, content); | |
77 | } | |
78 | ||
79 | // ------------------------------------------------------------------------ | |
80 | // Test cases | |
81 | // ------------------------------------------------------------------------ | |
82 | ||
83 | /** | |
84 | * Validate the parsing of keywords | |
85 | */ | |
86 | @Test | |
87 | public void testKeywords() { | |
88 | checkSingle(CTFLexer.ALIGNTOK, "align"); | |
89 | checkSingle(CTFLexer.CONSTTOK, "const"); | |
90 | checkSingle(CTFLexer.CHARTOK, "char"); | |
91 | checkSingle(CTFLexer.DOUBLETOK, "double"); | |
92 | checkSingle(CTFLexer.ENUMTOK, "enum"); | |
93 | checkSingle(CTFLexer.EVENTTOK, "event"); | |
94 | checkSingle(CTFLexer.FLOATINGPOINTTOK, "floating_point"); | |
95 | checkSingle(CTFLexer.FLOATTOK, "float"); | |
96 | checkSingle(CTFLexer.INTEGERTOK, "integer"); | |
97 | checkSingle(CTFLexer.INTTOK, "int"); | |
98 | checkSingle(CTFLexer.LONGTOK, "long"); | |
99 | checkSingle(CTFLexer.SHORTTOK, "short"); | |
100 | checkSingle(CTFLexer.SIGNEDTOK, "signed"); | |
101 | checkSingle(CTFLexer.STREAMTOK, "stream"); | |
102 | checkSingle(CTFLexer.STRINGTOK, "string"); | |
103 | checkSingle(CTFLexer.STRUCTTOK, "struct"); | |
104 | checkSingle(CTFLexer.TRACETOK, "trace"); | |
105 | checkSingle(CTFLexer.TYPEALIASTOK, "typealias"); | |
106 | checkSingle(CTFLexer.TYPEDEFTOK, "typedef"); | |
107 | checkSingle(CTFLexer.UNSIGNEDTOK, "unsigned"); | |
108 | checkSingle(CTFLexer.VARIANTTOK, "variant"); | |
109 | checkSingle(CTFLexer.VOIDTOK, "void"); | |
110 | checkSingle(CTFLexer.BOOLTOK, "_Bool"); | |
111 | checkSingle(CTFLexer.COMPLEXTOK, "_Complex"); | |
112 | checkSingle(CTFLexer.IMAGINARYTOK, "_Imaginary"); | |
113 | checkSingle(CTFLexer.ENVTOK, "env"); | |
114 | checkSingle(CTFLexer.CLOCKTOK, "clock"); | |
115 | checkSingle(CTFLexer.CALLSITETOK, "callsite"); | |
116 | checkSingle(CTFLexer.NANNUMBERTOK, "NaN"); | |
117 | checkSingle(CTFLexer.INFINITYTOK, "+inf"); | |
118 | checkSingle(CTFLexer.NINFINITYTOK, "-inf"); | |
119 | } | |
120 | ||
121 | /** | |
122 | * Validate the parsing of symbols | |
123 | */ | |
124 | @Test | |
125 | public void testSymbols() { | |
126 | tokenize(" , : ... "); | |
127 | checkToken(CTFLexer.WS, " "); | |
128 | checkToken(CTFLexer.SEPARATOR, ","); | |
129 | checkToken(CTFLexer.WS, " "); | |
130 | checkToken(CTFLexer.COLON, ":"); | |
131 | checkToken(CTFLexer.WS, " "); | |
132 | checkToken(CTFLexer.ELIPSES, "..."); | |
133 | checkToken(CTFLexer.WS, " "); | |
134 | ||
135 | tokenize(" = := = "); | |
136 | checkToken(CTFLexer.WS, " "); | |
137 | checkToken(CTFLexer.ASSIGNMENT, "="); | |
138 | checkToken(CTFLexer.WS, " "); | |
139 | checkToken(CTFLexer.TYPE_ASSIGNMENT, ":="); | |
140 | checkToken(CTFLexer.WS, " "); | |
141 | ||
142 | tokenize(" <<>> "); | |
143 | checkToken(CTFLexer.WS, " "); | |
144 | checkToken(CTFLexer.LT, "<"); | |
145 | checkToken(CTFLexer.LT, "<"); | |
146 | checkToken(CTFLexer.GT, ">"); | |
147 | checkToken(CTFLexer.GT, ">"); | |
148 | checkToken(CTFLexer.WS, " "); | |
149 | ||
150 | tokenize(" ({[]}) "); | |
151 | checkToken(CTFLexer.WS, " "); | |
152 | checkToken(CTFLexer.LPAREN, "("); | |
153 | checkToken(CTFLexer.LCURL, "{"); | |
154 | checkToken(CTFLexer.OPENBRAC, "["); | |
155 | checkToken(CTFLexer.CLOSEBRAC, "]"); | |
156 | checkToken(CTFLexer.RCURL, "}"); | |
157 | checkToken(CTFLexer.RPAREN, ")"); | |
158 | checkToken(CTFLexer.WS, " "); | |
159 | ||
160 | tokenize(";;"); | |
161 | checkToken(CTFLexer.TERM, ";"); | |
162 | checkToken(CTFLexer.TERM, ";"); | |
163 | ||
164 | tokenize(" ++ -- "); | |
165 | checkToken(CTFLexer.WS, " "); | |
166 | checkToken(CTFLexer.SIGN, "+"); | |
167 | checkToken(CTFLexer.SIGN, "+"); | |
168 | checkToken(CTFLexer.WS, " "); | |
169 | checkToken(CTFLexer.SIGN, "-"); | |
170 | checkToken(CTFLexer.SIGN, "-"); | |
171 | checkToken(CTFLexer.WS, " "); | |
172 | ||
173 | tokenize("-> .*."); | |
174 | checkToken(CTFLexer.ARROW, "->"); | |
175 | checkToken(CTFLexer.WS, " "); | |
176 | checkToken(CTFLexer.DOT, "."); | |
177 | checkToken(CTFLexer.POINTER, "*"); | |
178 | checkToken(CTFLexer.DOT, "."); | |
179 | } | |
180 | ||
181 | /** | |
182 | * Validate the parsing of literals | |
183 | */ | |
184 | @Test | |
185 | public void testLiterals() { | |
186 | tokenize("01 02 010"); | |
187 | checkToken(CTFLexer.OCTAL_LITERAL, "01"); | |
188 | checkToken(CTFLexer.WS, " "); | |
189 | checkToken(CTFLexer.OCTAL_LITERAL, "02"); | |
190 | checkToken(CTFLexer.WS, " "); | |
191 | checkToken(CTFLexer.OCTAL_LITERAL, "010"); | |
192 | ||
193 | tokenize("1 2 10 1024 "); | |
194 | checkToken(CTFLexer.DECIMAL_LITERAL, "1"); | |
195 | checkToken(CTFLexer.WS, " "); | |
196 | checkToken(CTFLexer.DECIMAL_LITERAL, "2"); | |
197 | checkToken(CTFLexer.WS, " "); | |
198 | checkToken(CTFLexer.DECIMAL_LITERAL, "10"); | |
199 | checkToken(CTFLexer.WS, " "); | |
200 | checkToken(CTFLexer.DECIMAL_LITERAL, "1024"); | |
201 | checkToken(CTFLexer.WS, " "); | |
202 | ||
203 | tokenize("0x01 0x02 0x0F0"); | |
204 | checkToken(CTFLexer.HEX_LITERAL, "0x01"); | |
205 | checkToken(CTFLexer.WS, " "); | |
206 | checkToken(CTFLexer.HEX_LITERAL, "0x02"); | |
207 | checkToken(CTFLexer.WS, " "); | |
208 | checkToken(CTFLexer.HEX_LITERAL, "0x0F0"); | |
209 | } | |
210 | ||
211 | /** | |
212 | * Validate the parsing of literals with hexa prefix | |
213 | */ | |
214 | @Test | |
215 | public void testLiteralPrefixes() { | |
216 | checkSingle(CTFLexer.HEX_LITERAL, "0x1"); | |
217 | checkSingle(CTFLexer.HEX_LITERAL, "0X1"); | |
218 | } | |
219 | ||
220 | /** | |
221 | * Validate the parsing of literals with type suffix | |
222 | */ | |
223 | @Test | |
224 | public void testLiteralSuffixes() { | |
225 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0l"); | |
226 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0L"); | |
227 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0ll"); | |
228 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0LL"); | |
229 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0ul"); | |
230 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0uL"); | |
231 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0ull"); | |
232 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0uLL"); | |
233 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0Ul"); | |
234 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0UL"); | |
235 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0Ull"); | |
236 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0ULL"); | |
237 | } | |
238 | ||
239 | /** | |
240 | * Validate the accepted characters in literals. | |
241 | */ | |
242 | @Test | |
243 | public void testLiteralDigits() { | |
244 | checkSingle(CTFLexer.OCTAL_LITERAL, "001234567"); | |
245 | ||
246 | checkSingle(CTFLexer.DECIMAL_LITERAL, "123456"); | |
247 | checkSingle(CTFLexer.DECIMAL_LITERAL, "987654"); | |
248 | ||
249 | checkSingle(CTFLexer.HEX_LITERAL, "0x012345"); | |
250 | checkSingle(CTFLexer.HEX_LITERAL, "0x678990"); | |
251 | checkSingle(CTFLexer.HEX_LITERAL, "0xABCDEF"); | |
252 | checkSingle(CTFLexer.HEX_LITERAL, "0xabcdef"); | |
253 | } | |
254 | ||
255 | /** | |
256 | * Validate zero literal to be the right token. | |
257 | */ | |
258 | @Test | |
259 | public void testLiteralZero() { | |
260 | checkSingle(CTFLexer.OCTAL_LITERAL, "00"); | |
261 | checkSingle(CTFLexer.DECIMAL_LITERAL, "0"); | |
262 | checkSingle(CTFLexer.HEX_LITERAL, "0x0"); | |
263 | } | |
264 | ||
265 | /** | |
266 | * Validate character literals | |
267 | */ | |
268 | @Test | |
269 | public void testCharLiteral() { | |
270 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'x'"); | |
271 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\''"); | |
272 | checkSingle(CTFLexer.CHARACTER_LITERAL, "' '"); | |
273 | checkSingle(CTFLexer.CHARACTER_LITERAL, "L'1'"); | |
274 | } | |
275 | ||
276 | /** | |
277 | * Validate escaped character literals | |
278 | */ | |
279 | @Test | |
280 | public void testEscapeCharLiteral() { | |
281 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\a'"); | |
282 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\b'"); | |
283 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\f'"); | |
284 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\n'"); | |
285 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\r'"); | |
286 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\t'"); | |
287 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\v'"); | |
288 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\''"); | |
289 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\\"'"); | |
290 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\\\'"); | |
291 | ||
292 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\001'"); | |
293 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\01'"); | |
294 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\1'"); | |
295 | ||
296 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\x1A'"); | |
297 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\x1a'"); | |
298 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\xa'"); | |
299 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\\x0'"); | |
300 | ||
301 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\uABCD'"); | |
302 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\u0123'"); | |
303 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\u012345678'"); | |
304 | checkSingle(CTFLexer.CHARACTER_LITERAL, "'\uFEDCBA987'"); | |
305 | } | |
306 | ||
307 | /** | |
308 | * Validate string literals | |
309 | */ | |
310 | @Test | |
311 | public void testStringLiteral() { | |
312 | checkSingle(CTFLexer.STRING_LITERAL, "\"\""); | |
313 | checkSingle(CTFLexer.STRING_LITERAL, "\"x\""); | |
314 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\\"\""); | |
315 | checkSingle(CTFLexer.STRING_LITERAL, "\" \""); | |
316 | checkSingle(CTFLexer.STRING_LITERAL, "L\"1\""); | |
317 | ||
318 | checkSingle(CTFLexer.STRING_LITERAL, "\"This is \\n a multiline\\r\\n\""); | |
319 | checkSingle(CTFLexer.STRING_LITERAL, "L\"This is \\n a multiline\\r\\n\""); | |
320 | } | |
321 | ||
322 | /** | |
323 | * Validate string literals with escape sequence | |
324 | */ | |
325 | @Test | |
326 | public void testEscapeStringLiteral() { | |
327 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\a\""); | |
328 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\b\""); | |
329 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\f\""); | |
330 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\n\""); | |
331 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\r\""); | |
332 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\t\""); | |
333 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\v\""); | |
334 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\'\""); | |
335 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\\"\""); | |
336 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\\\\""); | |
337 | ||
338 | checkSingle(CTFLexer.STRING_LITERAL, "\"\001\""); | |
339 | checkSingle(CTFLexer.STRING_LITERAL, "\"\01\""); | |
340 | checkSingle(CTFLexer.STRING_LITERAL, "\"\1\""); | |
341 | ||
342 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\x1A\""); | |
343 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\x1a\""); | |
344 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\xa\""); | |
345 | checkSingle(CTFLexer.STRING_LITERAL, "\"\\x0\""); | |
346 | ||
347 | checkSingle(CTFLexer.STRING_LITERAL, "\"\uABCD\""); | |
348 | checkSingle(CTFLexer.STRING_LITERAL, "\"\u0123\""); | |
349 | checkSingle(CTFLexer.STRING_LITERAL, "\"\u012345678\""); | |
350 | checkSingle(CTFLexer.STRING_LITERAL, "\"\uFEDCBA987\""); | |
351 | } | |
352 | ||
353 | /** | |
354 | * Validate spaces parsing | |
355 | */ | |
356 | @Test | |
357 | public void testWhitespaces() { | |
358 | tokenize(" \r\t\n\u000C "); | |
359 | checkToken(CTFLexer.WS, " "); | |
360 | checkToken(CTFLexer.WS, " "); | |
361 | checkToken(CTFLexer.WS, "\r"); | |
362 | checkToken(CTFLexer.WS, "\t"); | |
363 | checkToken(CTFLexer.WS, "\n"); | |
364 | checkToken(CTFLexer.WS, "\u000C"); | |
365 | checkToken(CTFLexer.WS, " "); | |
366 | } | |
367 | ||
368 | /** | |
369 | * Validate comments parsing | |
370 | */ | |
371 | @Test | |
372 | public void testComment() { | |
373 | tokenize(" /* test */ "); | |
374 | checkToken(CTFLexer.WS, " "); | |
375 | checkToken(CTFLexer.COMMENT, "/* test */"); | |
376 | checkToken(CTFLexer.WS, " "); | |
377 | } | |
378 | ||
379 | /** | |
380 | * Validate complex nested comments parsing | |
381 | */ | |
382 | @Test | |
383 | public void testNestedComment() { | |
384 | tokenize(" /* /* */ "); | |
385 | checkToken(CTFLexer.WS, " "); | |
386 | checkToken(CTFLexer.COMMENT, "/* /* */"); | |
387 | checkToken(CTFLexer.WS, " "); | |
388 | ||
389 | tokenize(" /* /* * ** / */ "); | |
390 | checkToken(CTFLexer.WS, " "); | |
391 | checkToken(CTFLexer.COMMENT, "/* /* * ** / */"); | |
392 | checkToken(CTFLexer.WS, " "); | |
393 | } | |
394 | ||
395 | /** | |
396 | * Validate multi-lines comments | |
397 | */ | |
398 | @Test | |
399 | public void testMultiLineComment() { | |
400 | tokenize(" /*\ntest\n*/ "); | |
401 | checkToken(CTFLexer.WS, " "); | |
402 | checkToken(CTFLexer.COMMENT, "/*\ntest\n*/"); | |
403 | checkToken(CTFLexer.WS, " "); | |
404 | } | |
405 | ||
406 | /** | |
407 | * Validate single line comments | |
408 | */ | |
409 | @Test | |
410 | public void testLineComment() { | |
411 | tokenize(" // asdad\r\n "); | |
412 | checkToken(CTFLexer.WS, " "); | |
413 | checkToken(CTFLexer.LINE_COMMENT, "// asdad\r\n"); | |
414 | checkToken(CTFLexer.WS, " "); | |
415 | } | |
416 | ||
417 | /** | |
418 | * Validate incomplete comments parsing | |
419 | */ | |
420 | @Ignore("Lexer must be fixed first") | |
421 | @Test | |
422 | public void testLineCommentWithEOF() { | |
423 | tokenize("//"); | |
424 | checkToken(CTFLexer.LINE_COMMENT, "//"); | |
425 | } | |
426 | ||
427 | /** | |
428 | * Validate parsing of mixed kind of comments | |
429 | */ | |
430 | @Test | |
431 | public void testMixedComment() { | |
432 | tokenize(" // /*\n"); | |
433 | checkToken(CTFLexer.WS, " "); | |
434 | checkToken(CTFLexer.LINE_COMMENT, "// /*\n"); | |
435 | ||
436 | tokenize(" /*\n//\n*/ "); | |
437 | checkToken(CTFLexer.WS, " "); | |
438 | checkToken(CTFLexer.COMMENT, "/*\n//\n*/"); | |
439 | checkToken(CTFLexer.WS, " "); | |
440 | } | |
441 | ||
442 | /** | |
443 | * Validate parsing identifiers | |
444 | */ | |
445 | @Test | |
446 | public void testIdentifier() { | |
447 | tokenize("_ a a1 B "); | |
448 | checkToken(CTFLexer.IDENTIFIER, "_"); | |
449 | checkToken(CTFLexer.WS, " "); | |
450 | checkToken(CTFLexer.IDENTIFIER, "a"); | |
451 | checkToken(CTFLexer.WS, " "); | |
452 | checkToken(CTFLexer.IDENTIFIER, "a1"); | |
453 | checkToken(CTFLexer.WS, " "); | |
454 | checkToken(CTFLexer.IDENTIFIER, "B"); | |
455 | checkToken(CTFLexer.WS, " "); | |
456 | } | |
457 | ||
458 | /** | |
459 | * Validate accepted characters within an identifier | |
460 | */ | |
461 | @Test | |
462 | public void testIdentifierLetters() { | |
463 | checkSingle(CTFLexer.IDENTIFIER, "ABCDEFGHI"); | |
464 | checkSingle(CTFLexer.IDENTIFIER, "JKLMNOPQR"); | |
465 | checkSingle(CTFLexer.IDENTIFIER, "STUVWXYZ"); | |
466 | checkSingle(CTFLexer.IDENTIFIER, "abcdefghi"); | |
467 | checkSingle(CTFLexer.IDENTIFIER, "jklmnopqr"); | |
468 | checkSingle(CTFLexer.IDENTIFIER, "stuvwxyz"); | |
469 | checkSingle(CTFLexer.IDENTIFIER, "_0123456789"); | |
470 | } | |
471 | } |