Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(618)

Side by Side Diff: chrome/renderer/spellchecker/spellcheck_unittest.cc

Issue 395007: Move Mac to using renderer spellchecker. (Closed) Base URL: svn://chrome-svn/chrome/trunk/src/
Patch Set: ui test fix Created 11 years, 1 month ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View unified diff | Download patch | Annotate | Revision Log
« no previous file with comments | « chrome/renderer/spellchecker/spellcheck.cc ('k') | chrome/test/testing_profile.h » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
1 // Copyright (c) 2006-2008 The Chromium Authors. All rights reserved. 1 // Copyright (c) 2006-2008 The Chromium Authors. All rights reserved.
2 // Use of this source code is governed by a BSD-style license that can be 2 // Use of this source code is governed by a BSD-style license that can be
3 // found in the LICENSE file. 3 // found in the LICENSE file.
4 4
5 #include "webkit/glue/webkit_glue.h" 5 #include "webkit/glue/webkit_glue.h"
6 6
7 #include "base/file_util.h" 7 #include "base/file_util.h"
8 #include "base/message_loop.h" 8 #include "base/message_loop.h"
9 #include "base/path_service.h" 9 #include "base/path_service.h"
10 #include "base/platform_file.h"
10 #include "base/sys_string_conversions.h" 11 #include "base/sys_string_conversions.h"
11 #include "chrome/browser/chrome_thread.h" 12 #include "chrome/renderer/spellchecker/spellcheck.h"
12 #include "chrome/browser/spellchecker.h"
13 #include "chrome/browser/spellchecker_platform_engine.h"
14 #include "chrome/common/chrome_paths.h" 13 #include "chrome/common/chrome_paths.h"
14 #include "chrome/common/spellcheck_common.h"
15 #include "testing/gtest/include/gtest/gtest.h" 15 #include "testing/gtest/include/gtest/gtest.h"
16 16
17 namespace { 17 namespace {
18 const FilePath::CharType kTempCustomDictionaryFile[] =
19 FILE_PATH_LITERAL("temp_custom_dictionary.txt");
20 } // namespace
21
22 class SpellCheckTest : public testing::Test {
23 public:
24 SpellCheckTest()
25 : file_thread_(ChromeThread::FILE, &message_loop_),
26 io_thread_(ChromeThread::IO, &message_loop_) {}
27
28 protected:
29 MessageLoop message_loop_;
30
31 private:
32 ChromeThread file_thread_;
33 ChromeThread io_thread_; // To keep DCHECKs inside spell checker happy.
34 };
35 18
36 // Represents a special initialization function used only for the unit tests 19 // Represents a special initialization function used only for the unit tests
37 // in this file. 20 // in this file.
38 extern void InitHunspellWithFiles(FILE* file_aff_hunspell, 21 extern void InitHunspellWithFiles(FILE* file_aff_hunspell,
39 FILE* file_dic_hunspell); 22 FILE* file_dic_hunspell);
40 23
41 FilePath GetHunspellDirectory() { 24 FilePath GetHunspellDirectory() {
42 FilePath hunspell_directory; 25 FilePath hunspell_directory;
43 if (!PathService::Get(base::DIR_SOURCE_ROOT, &hunspell_directory)) 26 if (!PathService::Get(base::DIR_SOURCE_ROOT, &hunspell_directory))
44 return FilePath(); 27 return FilePath();
45 28
46 hunspell_directory = hunspell_directory.AppendASCII("third_party"); 29 hunspell_directory = hunspell_directory.AppendASCII("third_party");
47 hunspell_directory = hunspell_directory.AppendASCII("hunspell"); 30 hunspell_directory = hunspell_directory.AppendASCII("hunspell");
48 hunspell_directory = hunspell_directory.AppendASCII("dictionaries"); 31 hunspell_directory = hunspell_directory.AppendASCII("dictionaries");
49 return hunspell_directory; 32 return hunspell_directory;
50 } 33 }
51 34
35 class SpellCheckTest : public testing::Test {
36 public:
37 SpellCheckTest() {
38 ReinitializeSpellCheck("en-US");
39 }
40
41 void ReinitializeSpellCheck(const std::string& language) {
42 spell_check_.reset(new SpellCheck());
43
44 FilePath hunspell_directory = GetHunspellDirectory();
45 EXPECT_FALSE(hunspell_directory.empty());
46 base::PlatformFile file = base::CreatePlatformFile(
47 SpellCheckCommon::GetVersionedFileName(language, hunspell_directory),
48 base::PLATFORM_FILE_OPEN | base::PLATFORM_FILE_READ, NULL);
49 spell_check_->Init(
50 file, std::vector<std::string>(), language);
51 }
52
53 virtual ~SpellCheckTest() {
54 }
55
56 SpellCheck* spell_check() { return spell_check_.get(); }
57
58 private:
59 scoped_ptr<SpellCheck> spell_check_;
60 };
61
52 // Operates unit tests for the webkit_glue::SpellCheckWord() function 62 // Operates unit tests for the webkit_glue::SpellCheckWord() function
53 // with the US English dictionary. 63 // with the US English dictionary.
54 // The unit tests in this function consist of: 64 // The unit tests in this function consist of:
55 // * Tests for the function with empty strings; 65 // * Tests for the function with empty strings;
56 // * Tests for the function with a valid English word; 66 // * Tests for the function with a valid English word;
57 // * Tests for the function with a valid non-English word; 67 // * Tests for the function with a valid non-English word;
58 // * Tests for the function with a valid English word with a preceding 68 // * Tests for the function with a valid English word with a preceding
59 // space character; 69 // space character;
60 // * Tests for the function with a valid English word with a preceding 70 // * Tests for the function with a valid English word with a preceding
61 // non-English word; 71 // non-English word;
(...skipping 207 matching lines...) Expand 10 before | Expand all | Expand 10 after
269 // [ROBUSTNESS] Two invalid English words concatenated with a contraction 279 // [ROBUSTNESS] Two invalid English words concatenated with a contraction
270 // character. 280 // character.
271 {L"ifmmp:ifmmp", false, 0, 11}, 281 {L"ifmmp:ifmmp", false, 0, 11},
272 282
273 // [REGRESSION] Issue 13432: "Any word of 13 or 14 characters is not 283 // [REGRESSION] Issue 13432: "Any word of 13 or 14 characters is not
274 // spellcheck" <http://crbug.com/13432>. 284 // spellcheck" <http://crbug.com/13432>.
275 {L"qwertyuiopasd", false, 0, 13}, 285 {L"qwertyuiopasd", false, 0, 13},
276 {L"qwertyuiopasdf", false, 0, 14}, 286 {L"qwertyuiopasdf", false, 0, 14},
277 }; 287 };
278 288
279 FilePath hunspell_directory = GetHunspellDirectory();
280 ASSERT_FALSE(hunspell_directory.empty());
281
282 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
283 hunspell_directory, "en-US", NULL, FilePath()));
284 spell_checker->Initialize();
285 message_loop_.RunAllPending();
286
287 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) { 289 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
288 size_t input_length = 0; 290 size_t input_length = 0;
289 if (kTestCases[i].input != NULL) { 291 if (kTestCases[i].input != NULL) {
290 input_length = wcslen(kTestCases[i].input); 292 input_length = wcslen(kTestCases[i].input);
291 } 293 }
292 int misspelling_start; 294 int misspelling_start;
293 int misspelling_length; 295 int misspelling_length;
294 bool result = spell_checker->SpellCheckWord( 296 bool result = spell_check()->SpellCheckWord(
295 WideToUTF16(kTestCases[i].input).c_str(), 297 WideToUTF16(kTestCases[i].input).c_str(),
296 static_cast<int>(input_length), 298 static_cast<int>(input_length),
297 0, 299 0,
298 &misspelling_start, 300 &misspelling_start,
299 &misspelling_length, NULL); 301 &misspelling_length, NULL);
300 302
301 EXPECT_EQ(kTestCases[i].expected_result, result); 303 EXPECT_EQ(kTestCases[i].expected_result, result);
302 EXPECT_EQ(kTestCases[i].misspelling_start, misspelling_start); 304 EXPECT_EQ(kTestCases[i].misspelling_start, misspelling_start);
303 EXPECT_EQ(kTestCases[i].misspelling_length, misspelling_length); 305 EXPECT_EQ(kTestCases[i].misspelling_length, misspelling_length);
304 } 306 }
305 } 307 }
306 308
307 TEST_F(SpellCheckTest, SpellCheckSuggestions_EN_US) { 309 TEST_F(SpellCheckTest, SpellCheckSuggestions_EN_US) {
308 static const struct { 310 static const struct {
309 // A string to be tested. 311 // A string to be tested.
310 const wchar_t* input; 312 const wchar_t* input;
311 // An expected result for this test case. 313 // An expected result for this test case.
312 // * true: the input string does not have any invalid words. 314 // * true: the input string does not have any invalid words.
313 // * false: the input string has one or more invalid words. 315 // * false: the input string has one or more invalid words.
314 bool expected_result; 316 bool expected_result;
315 // The position and the length of the first invalid word. 317 // The position and the length of the first invalid word.
316 int misspelling_start; 318 int misspelling_start;
317 int misspelling_length; 319 int misspelling_length;
318 320
319 // A suggested word that should occur. 321 // A suggested word that should occur.
320 const wchar_t* suggested_word; 322 const wchar_t* suggested_word;
321 } kTestCases[] = { // A valid English word with a preceding whitespace 323 } kTestCases[] = {
322 // We need to have separate test cases here, since hunspell and the OS X
323 // spellchecking service occasionally differ on what they consider a valid
324 // suggestion for a given word, although these lists could likely be
325 // integrated somewhat.
326 #if defined(OS_MACOSX)
327 // These words come from the wikipedia page of the most commonly
328 // misspelled words in english.
329 // (http://en.wikipedia.org/wiki/Commonly_misspelled_words).
330 {L"absense", false, 0, 0, L"absence"},
331 {L"acceptible", false, 0, 0, L"acceptable"},
332 {L"accidentaly", false, 0, 0, L"accidentally"},
333 {L"accomodate", false, 0, 0, L"accommodate"},
334 {L"acheive", false, 0, 0, L"achieve"},
335 {L"acknowlege", false, 0, 0, L"acknowledge"},
336 {L"acquaintence", false, 0, 0, L"acquaintance"},
337 {L"aquire", false, 0, 0, L"acquire"},
338 {L"aquit", false, 0, 0, L"acquit"},
339 {L"acrage", false, 0, 0, L"acreage"},
340 {L"adress", false, 0, 0, L"address"},
341 {L"adultary", false, 0, 0, L"adultery"},
342 {L"advertize", false, 0, 0, L"advertise"},
343 {L"adviseable", false, 0, 0, L"advisable"},
344 {L"agression", false, 0, 0, L"aggression"},
345 {L"alchohol", false, 0, 0, L"alcohol"},
346 {L"alege", false, 0, 0, L"allege"},
347 {L"allegaince", false, 0, 0, L"allegiance"},
348 {L"allmost", false, 0, 0, L"almost"},
349 // Ideally, this test should pass. It works in firefox, but not in hunspell
350 // or OS X.
351 // {L"alot", false, 0, 0, L"a lot"},
352 {L"amatuer", false, 0, 0, L"amateur"},
353 {L"ammend", false, 0, 0, L"amend"},
354 {L"amung", false, 0, 0, L"among"},
355 {L"anually", false, 0, 0, L"annually"},
356 {L"apparant", false, 0, 0, L"apparent"},
357 {L"artic", false, 0, 0, L"arctic"},
358 {L"arguement", false, 0, 0, L"argument"},
359 {L"athiest", false, 0, 0, L"atheist"},
360 {L"athelete", false, 0, 0, L"athlete"},
361 {L"avrage", false, 0, 0, L"average"},
362 {L"awfull", false, 0, 0, L"awful"},
363 {L"ballance", false, 0, 0, L"balance"},
364 {L"basicly", false, 0, 0, L"basically"},
365 {L"becuase", false, 0, 0, L"because"},
366 {L"becomeing", false, 0, 0, L"becoming"},
367 {L"befor", false, 0, 0, L"before"},
368 {L"begining", false, 0, 0, L"beginning"},
369 {L"beleive", false, 0, 0, L"believe"},
370 {L"bellweather", false, 0, 0, L"bellwether"},
371 {L"benifit", false, 0, 0, L"benefit"},
372 {L"bouy", false, 0, 0, L"buoy"},
373 {L"briliant", false, 0, 0, L"brilliant"},
374 {L"burgler", false, 0, 0, L"burglar"},
375 {L"camoflage", false, 0, 0, L"camouflage"},
376 {L"carrer", false, 0, 0, L"career"},
377 {L"carefull", false, 0, 0, L"careful"},
378 {L"Carribean", false, 0, 0, L"Caribbean"},
379 {L"catagory", false, 0, 0, L"category"},
380 {L"cauhgt", false, 0, 0, L"caught"},
381 {L"cieling", false, 0, 0, L"ceiling"},
382 {L"cemetary", false, 0, 0, L"cemetery"},
383 {L"certin", false, 0, 0, L"certain"},
384 {L"changable", false, 0, 0, L"changeable"},
385 {L"cheif", false, 0, 0, L"chief"},
386 {L"citezen", false, 0, 0, L"citizen"},
387 {L"collaegue", false, 0, 0, L"colleague"},
388 {L"colum", false, 0, 0, L"column"},
389 {L"comming", false, 0, 0, L"coming"},
390 {L"commited", false, 0, 0, L"committed"},
391 {L"compitition", false, 0, 0, L"competition"},
392 {L"conceed", false, 0, 0, L"concede"},
393 {L"congradulate", false, 0, 0, L"congratulate"},
394 {L"consciencious", false, 0, 0, L"conscientious"},
395 {L"concious", false, 0, 0, L"conscious"},
396 {L"concensus", false, 0, 0, L"consensus"},
397 {L"contraversy", false, 0, 0, L"controversy"},
398 {L"conveniance", false, 0, 0, L"convenience"},
399 {L"critecize", false, 0, 0, L"criticize"},
400 {L"dacquiri", false, 0, 0, L"daiquiri"},
401 {L"decieve", false, 0, 0, L"deceive"},
402 {L"dicide", false, 0, 0, L"decide"},
403 {L"definate", false, 0, 0, L"definite"},
404 {L"definitly", false, 0, 0, L"definitely"},
405 {L"deposite", false, 0, 0, L"deposit"},
406 {L"desparate", false, 0, 0, L"desperate"},
407 {L"develope", false, 0, 0, L"develop"},
408 {L"diffrence", false, 0, 0, L"difference"},
409 {L"dilema", false, 0, 0, L"dilemma"},
410 {L"disapear", false, 0, 0, L"disappear"},
411 {L"disapoint", false, 0, 0, L"disappoint"},
412 {L"disasterous", false, 0, 0, L"disastrous"},
413 {L"disipline", false, 0, 0, L"discipline"},
414 {L"drunkeness", false, 0, 0, L"drunkenness"},
415 {L"dumbell", false, 0, 0, L"dumbbell"},
416 {L"durring", false, 0, 0, L"during"},
417 {L"easely", false, 0, 0, L"easily"},
418 {L"eigth", false, 0, 0, L"eight"},
419 {L"embarass", false, 0, 0, L"embarrass"},
420 {L"enviroment", false, 0, 0, L"environment"},
421 {L"equiped", false, 0, 0, L"equipped"},
422 {L"equiptment", false, 0, 0, L"equipment"},
423 {L"exagerate", false, 0, 0, L"exaggerate"},
424 {L"excede", false, 0, 0, L"exceed"},
425 {L"exellent", false, 0, 0, L"excellent"},
426 {L"exsept", false, 0, 0, L"except"},
427 {L"exercize", false, 0, 0, L"exercise"},
428 {L"exilerate", false, 0, 0, L"exhilarate"},
429 {L"existance", false, 0, 0, L"existence"},
430 {L"experiance", false, 0, 0, L"experience"},
431 {L"experament", false, 0, 0, L"experiment"},
432 {L"explaination", false, 0, 0, L"explanation"},
433 {L"extreem", false, 0, 0, L"extreme"},
434 {L"familier", false, 0, 0, L"familiar"},
435 {L"facinating", false, 0, 0, L"fascinating"},
436 {L"firey", false, 0, 0, L"fiery"},
437 {L"finaly", false, 0, 0, L"finally"},
438 {L"flourescent", false, 0, 0, L"fluorescent"},
439 {L"foriegn", false, 0, 0, L"foreign"},
440 {L"fourty", false, 0, 0, L"forty"},
441 {L"foreward", false, 0, 0, L"forward"},
442 {L"freind", false, 0, 0, L"friend"},
443 {L"fullfil", false, 0, 0, L"fulfill"},
444 {L"fundemental", false, 0, 0, L"fundamental"},
445 {L"guage", false, 0, 0, L"gauge"},
446 {L"generaly", false, 0, 0, L"generally"},
447 {L"goverment", false, 0, 0, L"government"},
448 {L"grammer", false, 0, 0, L"grammar"},
449 {L"gratefull", false, 0, 0, L"grateful"},
450 {L"garantee", false, 0, 0, L"guarantee"},
451 {L"guidence", false, 0, 0, L"guidance"},
452 {L"happyness", false, 0, 0, L"happiness"},
453 {L"harrass", false, 0, 0, L"harass"},
454 {L"heighth", false, 0, 0, L"height"},
455 {L"heirarchy", false, 0, 0, L"hierarchy"},
456 {L"humerous", false, 0, 0, L"humorous"},
457 {L"hygene", false, 0, 0, L"hygiene"},
458 {L"hipocrit", false, 0, 0, L"hypocrite"},
459 {L"idenity", false, 0, 0, L"identity"},
460 {L"ignorence", false, 0, 0, L"ignorance"},
461 {L"imaginery", false, 0, 0, L"imaginary"},
462 {L"immitate", false, 0, 0, L"imitate"},
463 {L"immitation", false, 0, 0, L"imitation"},
464 {L"imediately", false, 0, 0, L"immediately"},
465 {L"incidently", false, 0, 0, L"incidentally"},
466 {L"independant", false, 0, 0, L"independent"},
467 {L"indispensible", false, 0, 0, L"indispensable"},
468 {L"innoculate", false, 0, 0, L"inoculate"},
469 {L"inteligence", false, 0, 0, L"intelligence"},
470 {L"intresting", false, 0, 0, L"interesting"},
471 {L"interuption", false, 0, 0, L"interruption"},
472 {L"irrelevent", false, 0, 0, L"irrelevant"},
473 {L"irritible", false, 0, 0, L"irritable"},
474 {L"iland", false, 0, 0, L"island"},
475 {L"jellous", false, 0, 0, L"jealous"},
476 {L"knowlege", false, 0, 0, L"knowledge"},
477 {L"labratory", false, 0, 0, L"laboratory"},
478 {L"liesure", false, 0, 0, L"leisure"},
479 {L"lenght", false, 0, 0, L"length"},
480 {L"liason", false, 0, 0, L"liaison"},
481 {L"libary", false, 0, 0, L"library"},
482 {L"lisence", false, 0, 0, L"license"},
483 {L"lonelyness", false, 0, 0, L"loneliness"},
484 {L"lieing", false, 0, 0, L"lying"},
485 {L"maintenence", false, 0, 0, L"maintenance"},
486 {L"manuever", false, 0, 0, L"maneuver"},
487 {L"marrige", false, 0, 0, L"marriage"},
488 {L"mathmatics", false, 0, 0, L"mathematics"},
489 {L"medcine", false, 0, 0, L"medicine"},
490 {L"medeval", false, 0, 0, L"medieval"},
491 {L"momento", false, 0, 0, L"memento"},
492 {L"millenium", false, 0, 0, L"millennium"},
493 {L"miniture", false, 0, 0, L"miniature"},
494 {L"minite", false, 0, 0, L"minute"},
495 {L"mischevous", false, 0, 0, L"mischievous"},
496 {L"mispell", false, 0, 0, L"misspell"},
497 // Maybe this one should pass, as it works in hunspell, but not in firefox.
498 // {L"misterius", false, 0, 0, L"mysterious"},
499 {L"naturaly", false, 0, 0, L"naturally"},
500 {L"neccessary", false, 0, 0, L"necessary"},
501 {L"neice", false, 0, 0, L"niece"},
502 {L"nieghbor", false, 0, 0, L"neighbor"},
503 {L"nieghbour", false, 0, 0, L"neighbor"},
504 {L"niether", false, 0, 0, L"neither"},
505 {L"noticable", false, 0, 0, L"noticeable"},
506 {L"occassion", false, 0, 0, L"occasion"},
507 {L"occasionaly", false, 0, 0, L"occasionally"},
508 {L"occurrance", false, 0, 0, L"occurrence"},
509 {L"occured", false, 0, 0, L"occurred"},
510 {L"oficial", false, 0, 0, L"official"},
511 {L"offen", false, 0, 0, L"often"},
512 {L"ommision", false, 0, 0, L"omission"},
513 {L"oprate", false, 0, 0, L"operate"},
514 {L"oppurtunity", false, 0, 0, L"opportunity"},
515 {L"orignal", false, 0, 0, L"original"},
516 {L"outragous", false, 0, 0, L"outrageous"},
517 {L"parrallel", false, 0, 0, L"parallel"},
518 {L"parliment", false, 0, 0, L"parliament"},
519 {L"particurly", false, 0, 0, L"particularly"},
520 {L"passtime", false, 0, 0, L"pastime"},
521 {L"peculier", false, 0, 0, L"peculiar"},
522 {L"percieve", false, 0, 0, L"perceive"},
523 {L"pernament", false, 0, 0, L"permanent"},
524 {L"perseverence", false, 0, 0, L"perseverance"},
525 {L"personaly", false, 0, 0, L"personally"},
526 {L"personell", false, 0, 0, L"personnel"},
527 {L"persaude", false, 0, 0, L"persuade"},
528 {L"pichure", false, 0, 0, L"picture"},
529 {L"peice", false, 0, 0, L"piece"},
530 {L"plagerize", false, 0, 0, L"plagiarize"},
531 {L"playright", false, 0, 0, L"playwright"},
532 {L"plesant", false, 0, 0, L"pleasant"},
533 {L"pollitical", false, 0, 0, L"political"},
534 {L"posession", false, 0, 0, L"possession"},
535 {L"potatos", false, 0, 0, L"potatoes"},
536 {L"practicle", false, 0, 0, L"practical"},
537 {L"preceed", false, 0, 0, L"precede"},
538 {L"predjudice", false, 0, 0, L"prejudice"},
539 {L"presance", false, 0, 0, L"presence"},
540 {L"privelege", false, 0, 0, L"privilege"},
541 // This one should probably work. It does in FF and Hunspell.
542 // {L"probly", false, 0, 0, L"probably"},
543 {L"proffesional", false, 0, 0, L"professional"},
544 {L"professer", false, 0, 0, L"professor"},
545 {L"promiss", false, 0, 0, L"promise"},
546 {L"pronounciation", false, 0, 0, L"pronunciation"},
547 {L"prufe", false, 0, 0, L"proof"},
548 {L"psycology", false, 0, 0, L"psychology"},
549 {L"publically", false, 0, 0, L"publicly"},
550 {L"quanity", false, 0, 0, L"quantity"},
551 {L"quarentine", false, 0, 0, L"quarantine"},
552 {L"questionaire", false, 0, 0, L"questionnaire"},
553 {L"readible", false, 0, 0, L"readable"},
554 {L"realy", false, 0, 0, L"really"},
555 {L"recieve", false, 0, 0, L"receive"},
556 {L"reciept", false, 0, 0, L"receipt"},
557 {L"reconize", false, 0, 0, L"recognize"},
558 {L"recomend", false, 0, 0, L"recommend"},
559 {L"refered", false, 0, 0, L"referred"},
560 {L"referance", false, 0, 0, L"reference"},
561 {L"relevent", false, 0, 0, L"relevant"},
562 {L"religous", false, 0, 0, L"religious"},
563 {L"repitition", false, 0, 0, L"repetition"},
564 {L"restarant", false, 0, 0, L"restaurant"},
565 {L"rythm", false, 0, 0, L"rhythm"},
566 {L"rediculous", false, 0, 0, L"ridiculous"},
567 {L"sacrefice", false, 0, 0, L"sacrifice"},
568 {L"saftey", false, 0, 0, L"safety"},
569 {L"sissors", false, 0, 0, L"scissors"},
570 {L"secratary", false, 0, 0, L"secretary"},
571 {L"sieze", false, 0, 0, L"seize"},
572 {L"seperate", false, 0, 0, L"separate"},
573 {L"sargent", false, 0, 0, L"sergeant"},
574 {L"shineing", false, 0, 0, L"shining"},
575 {L"similer", false, 0, 0, L"similar"},
576 {L"sinceerly", false, 0, 0, L"sincerely"},
577 {L"speach", false, 0, 0, L"speech"},
578 {L"stoping", false, 0, 0, L"stopping"},
579 {L"strenght", false, 0, 0, L"strength"},
580 {L"succede", false, 0, 0, L"succeed"},
581 {L"succesful", false, 0, 0, L"successful"},
582 {L"supercede", false, 0, 0, L"supersede"},
583 {L"surelly", false, 0, 0, L"surely"},
584 {L"suprise", false, 0, 0, L"surprise"},
585 {L"temperture", false, 0, 0, L"temperature"},
586 {L"temprary", false, 0, 0, L"temporary"},
587 {L"tomatos", false, 0, 0, L"tomatoes"},
588 {L"tommorrow", false, 0, 0, L"tomorrow"},
589 {L"tounge", false, 0, 0, L"tongue"},
590 {L"truely", false, 0, 0, L"truly"},
591 {L"twelth", false, 0, 0, L"twelfth"},
592 {L"tyrany", false, 0, 0, L"tyranny"},
593 {L"underate", false, 0, 0, L"underrate"},
594 {L"untill", false, 0, 0, L"until"},
595 {L"unuseual", false, 0, 0, L"unusual"},
596 {L"upholstry", false, 0, 0, L"upholstery"},
597 {L"usible", false, 0, 0, L"usable"},
598 {L"useing", false, 0, 0, L"using"},
599 {L"usualy", false, 0, 0, L"usually"},
600 {L"vaccuum", false, 0, 0, L"vacuum"},
601 {L"vegatarian", false, 0, 0, L"vegetarian"},
602 {L"vehical", false, 0, 0, L"vehicle"},
603 {L"visious", false, 0, 0, L"vicious"},
604 {L"villege", false, 0, 0, L"village"},
605 {L"wierd", false, 0, 0, L"weird"},
606 {L"wellcome", false, 0, 0, L"welcome"},
607 {L"wellfare", false, 0, 0, L"welfare"},
608 {L"wilfull", false, 0, 0, L"willful"},
609 {L"withold", false, 0, 0, L"withhold"},
610 {L"writting", false, 0, 0, L"writing"},
611 #else
612 {L"ello", false, 0, 0, L"hello"}, 324 {L"ello", false, 0, 0, L"hello"},
613 {L"ello", false, 0, 0, L"cello"}, 325 {L"ello", false, 0, 0, L"cello"},
614 {L"wate", false, 0, 0, L"water"}, 326 {L"wate", false, 0, 0, L"water"},
615 {L"wate", false, 0, 0, L"waste"}, 327 {L"wate", false, 0, 0, L"waste"},
616 {L"wate", false, 0, 0, L"sate"}, 328 {L"wate", false, 0, 0, L"sate"},
617 {L"wate", false, 0, 0, L"ate"}, 329 {L"wate", false, 0, 0, L"ate"},
618 {L"jum", false, 0, 0, L"jump"}, 330 {L"jum", false, 0, 0, L"jump"},
619 {L"jum", false, 0, 0, L"hum"}, 331 {L"jum", false, 0, 0, L"hum"},
620 {L"jum", false, 0, 0, L"sum"}, 332 {L"jum", false, 0, 0, L"sum"},
621 {L"jum", false, 0, 0, L"um"}, 333 {L"jum", false, 0, 0, L"um"},
622 #endif // !OS_MACOSX
623 // TODO (Sidchat): add many more examples. 334 // TODO (Sidchat): add many more examples.
624 }; 335 };
625 336
626 FilePath hunspell_directory = GetHunspellDirectory();
627 ASSERT_FALSE(hunspell_directory.empty());
628
629 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
630 hunspell_directory, "en-US", NULL, FilePath()));
631 spell_checker->Initialize();
632 message_loop_.RunAllPending();
633
634 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) { 337 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
635 std::vector<string16> suggestions; 338 std::vector<string16> suggestions;
636 size_t input_length = 0; 339 size_t input_length = 0;
637 if (kTestCases[i].input != NULL) { 340 if (kTestCases[i].input != NULL) {
638 input_length = wcslen(kTestCases[i].input); 341 input_length = wcslen(kTestCases[i].input);
639 } 342 }
640 int misspelling_start; 343 int misspelling_start;
641 int misspelling_length; 344 int misspelling_length;
642 bool result = spell_checker->SpellCheckWord( 345 bool result = spell_check()->SpellCheckWord(
643 WideToUTF16(kTestCases[i].input).c_str(), 346 WideToUTF16(kTestCases[i].input).c_str(),
644 static_cast<int>(input_length), 347 static_cast<int>(input_length),
645 0, 348 0,
646 &misspelling_start, 349 &misspelling_start,
647 &misspelling_length, 350 &misspelling_length,
648 &suggestions); 351 &suggestions);
649 352
650 // Check for spelling. 353 // Check for spelling.
651 EXPECT_EQ(kTestCases[i].expected_result, result); 354 EXPECT_EQ(kTestCases[i].expected_result, result);
652 355
(...skipping 237 matching lines...) Expand 10 before | Expand all | Expand 10 after
890 // Vietnamese 593 // Vietnamese
891 "vi-VN", 594 "vi-VN",
892 L"Nhi\x1EC7m v\x1EE5 c\x1EE7\x0061 " 595 L"Nhi\x1EC7m v\x1EE5 c\x1EE7\x0061 "
893 L"Google la \x0111\x1EC3 t\x1ED5 ch\x1EE9\x0063 " 596 L"Google la \x0111\x1EC3 t\x1ED5 ch\x1EE9\x0063 "
894 L"c\x00E1\x0063 th\x00F4ng tin c\x1EE7\x0061 " 597 L"c\x00E1\x0063 th\x00F4ng tin c\x1EE7\x0061 "
895 L"th\x1EBF gi\x1EDBi va l\x00E0m cho n\x00F3 universal c\x00F3 " 598 L"th\x1EBF gi\x1EDBi va l\x00E0m cho n\x00F3 universal c\x00F3 "
896 L"th\x1EC3 truy c\x1EADp va h\x1EEFu d\x1EE5ng h\x01A1n." 599 L"th\x1EC3 truy c\x1EADp va h\x1EEFu d\x1EE5ng h\x01A1n."
897 }, 600 },
898 }; 601 };
899 602
900 FilePath hunspell_directory = GetHunspellDirectory();
901 ASSERT_FALSE(hunspell_directory.empty());
902
903 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) { 603 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
904 scoped_refptr<SpellChecker> spell_checker(new SpellChecker( 604 ReinitializeSpellCheck(kTestCases[i].language);
905 hunspell_directory, kTestCases[i].language, NULL, FilePath()));
906 spell_checker->Initialize();
907 message_loop_.RunAllPending();
908
909 size_t input_length = 0; 605 size_t input_length = 0;
910 if (kTestCases[i].input != NULL) 606 if (kTestCases[i].input != NULL)
911 input_length = wcslen(kTestCases[i].input); 607 input_length = wcslen(kTestCases[i].input);
912 608
913 int misspelling_start = 0; 609 int misspelling_start = 0;
914 int misspelling_length = 0; 610 int misspelling_length = 0;
915 bool result = spell_checker->SpellCheckWord( 611 bool result = spell_check()->SpellCheckWord(
916 WideToUTF16(kTestCases[i].input).c_str(), 612 WideToUTF16(kTestCases[i].input).c_str(),
917 static_cast<int>(input_length), 613 static_cast<int>(input_length),
918 0, 614 0,
919 &misspelling_start, 615 &misspelling_start,
920 &misspelling_length, NULL); 616 &misspelling_length, NULL);
921 617
922 EXPECT_EQ(true, result) << kTestCases[i].language; 618 EXPECT_EQ(true, result) << kTestCases[i].language;
923 EXPECT_EQ(0, misspelling_start); 619 EXPECT_EQ(0, misspelling_start);
924 EXPECT_EQ(0, misspelling_length); 620 EXPECT_EQ(0, misspelling_length);
925 } 621 }
926 } 622 }
927 623
928 // This test Adds words to the SpellChecker and veifies that it remembers them.
929 TEST_F(SpellCheckTest, DISABLED_SpellCheckAddToDictionary_EN_US) {
930 static const struct {
931 // A string to be added to SpellChecker.
932 const wchar_t* word_to_add;
933 } kTestCases[] = { // Words to be added to the SpellChecker.
934 {L"Googley"},
935 {L"Googleplex"},
936 {L"Googler"},
937 };
938
939 FilePath custom_dictionary_file(kTempCustomDictionaryFile);
940 FilePath hunspell_directory = GetHunspellDirectory();
941 ASSERT_FALSE(hunspell_directory.empty());
942
943 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
944 hunspell_directory, "en-US", NULL, custom_dictionary_file));
945 spell_checker->Initialize();
946 message_loop_.RunAllPending();
947
948 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
949 // Add the word to spellchecker.
950 spell_checker->AddWord(WideToUTF16(kTestCases[i].word_to_add));
951
952 // Now check whether it is added to Spellchecker.
953 std::vector<string16> suggestions;
954 size_t input_length = 0;
955 if (kTestCases[i].word_to_add != NULL) {
956 input_length = wcslen(kTestCases[i].word_to_add);
957 }
958 int misspelling_start;
959 int misspelling_length;
960 bool result = spell_checker->SpellCheckWord(
961 WideToUTF16(kTestCases[i].word_to_add).c_str(),
962 static_cast<int>(input_length),
963 0,
964 &misspelling_start,
965 &misspelling_length,
966 &suggestions);
967
968 // Check for spelling.
969 EXPECT_TRUE(result);
970 }
971
972 // Now initialize another spellchecker to see that AddToWord is permanent.
973 scoped_refptr<SpellChecker> spell_checker_new(new SpellChecker(
974 hunspell_directory, "en-US", NULL, custom_dictionary_file));
975 spell_checker->Initialize();
976 message_loop_.RunAllPending();
977
978 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
979 // Now check whether it is added to Spellchecker.
980 std::vector<string16> suggestions;
981 size_t input_length = 0;
982 if (kTestCases[i].word_to_add != NULL) {
983 input_length = wcslen(kTestCases[i].word_to_add);
984 }
985 int misspelling_start;
986 int misspelling_length;
987 bool result = spell_checker_new->SpellCheckWord(
988 WideToUTF16(kTestCases[i].word_to_add).c_str(),
989 static_cast<int>(input_length),
990 0,
991 &misspelling_start,
992 &misspelling_length,
993 &suggestions);
994
995 // Check for spelling.
996 EXPECT_TRUE(result);
997 }
998
999 // Remove the temp custom dictionary file.
1000 file_util::Delete(custom_dictionary_file, false);
1001 }
1002
1003 // SpellChecker should suggest custome words for misspelled words.
1004 TEST_F(SpellCheckTest, DISABLED_SpellCheckSuggestionsAddToDictionary_EN_US) {
1005 static const struct {
1006 // A string to be added to SpellChecker.
1007 const wchar_t* word_to_add;
1008 } kTestCases[] = { // word to be added to SpellChecker
1009 {L"Googley"},
1010 {L"Googleplex"},
1011 {L"Googler"},
1012 };
1013
1014 FilePath custom_dictionary_file(kTempCustomDictionaryFile);
1015 FilePath hunspell_directory = GetHunspellDirectory();
1016 ASSERT_FALSE(hunspell_directory.empty());
1017
1018 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
1019 hunspell_directory, "en-US", NULL, custom_dictionary_file));
1020 spell_checker->Initialize();
1021 message_loop_.RunAllPending();
1022
1023 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
1024 // Add the word to spellchecker.
1025 spell_checker->AddWord(WideToUTF16(kTestCases[i].word_to_add));
1026 }
1027
1028 // Now check to see whether the custom words are suggested for
1029 // misspelled but similar words.
1030 static const struct {
1031 // A string to be tested.
1032 const wchar_t* input;
1033 // An expected result for this test case.
1034 // * true: the input string does not have any invalid words.
1035 // * false: the input string has one or more invalid words.
1036 bool expected_result;
1037 // The position and the length of the first invalid word.
1038 int misspelling_start;
1039 int misspelling_length;
1040
1041 // A suggested word that should occur.
1042 const wchar_t* suggested_word;
1043 } kTestCasesToBeTested[] = {
1044 {L"oogley", false, 0, 0, L"Googley"},
1045 {L"oogler", false, 0, 0, L"Googler"},
1046 {L"oogleplex", false, 0, 0, L"Googleplex"},
1047 };
1048
1049 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCasesToBeTested); ++i) {
1050 std::vector<string16> suggestions;
1051 size_t input_length = 0;
1052 if (kTestCasesToBeTested[i].input != NULL) {
1053 input_length = wcslen(kTestCasesToBeTested[i].input);
1054 }
1055 int misspelling_start;
1056 int misspelling_length;
1057 bool result = spell_checker->SpellCheckWord(
1058 WideToUTF16(kTestCasesToBeTested[i].input).c_str(),
1059 static_cast<int>(input_length),
1060 0,
1061 &misspelling_start,
1062 &misspelling_length,
1063 &suggestions);
1064
1065 // Check for spelling.
1066 EXPECT_EQ(result, kTestCasesToBeTested[i].expected_result);
1067
1068 // Check if the suggested words occur.
1069 bool suggested_word_is_present = false;
1070 for (int j=0; j < static_cast<int>(suggestions.size()); j++) {
1071 if (suggestions.at(j).compare(
1072 WideToUTF16(kTestCasesToBeTested[i].suggested_word)) ==
1073 0) {
1074 suggested_word_is_present = true;
1075 break;
1076 }
1077 }
1078
1079 EXPECT_TRUE(suggested_word_is_present);
1080 }
1081
1082 // Remove the temp custom dictionary file.
1083 file_util::Delete(custom_dictionary_file, false);
1084 }
1085
1086 TEST_F(SpellCheckTest, GetAutoCorrectionWord_EN_US) { 624 TEST_F(SpellCheckTest, GetAutoCorrectionWord_EN_US) {
1087 static const struct { 625 static const struct {
1088 // A misspelled word. 626 // A misspelled word.
1089 const char* input; 627 const char* input;
1090 628
1091 // An expected result for this test case. 629 // An expected result for this test case.
1092 // Should be an empty string if there are no suggestions for auto correct. 630 // Should be an empty string if there are no suggestions for auto correct.
1093 const char* expected_result; 631 const char* expected_result;
1094 } kTestCases[] = { 632 } kTestCases[] = {
1095 {"teh", "the"}, 633 {"teh", "the"},
1096 {"moer", "more"}, 634 {"moer", "more"},
1097 {"watre", "water"}, 635 {"watre", "water"},
1098 {"noen", ""}, 636 {"noen", ""},
1099 {"what", ""}, 637 {"what", ""},
1100 }; 638 };
1101 639 spell_check()->EnableAutoSpellCorrect(true);
1102 FilePath hunspell_directory = GetHunspellDirectory();
1103 ASSERT_FALSE(hunspell_directory.empty());
1104
1105 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
1106 hunspell_directory, "en-US", NULL, FilePath()));
1107 spell_checker->EnableAutoSpellCorrect(true);
1108 spell_checker->Initialize();
1109 message_loop_.RunAllPending();
1110 640
1111 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) { 641 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
1112 string16 misspelled_word(UTF8ToUTF16(kTestCases[i].input)); 642 string16 misspelled_word(UTF8ToUTF16(kTestCases[i].input));
1113 string16 expected_autocorrect_word( 643 string16 expected_autocorrect_word(
1114 UTF8ToUTF16(kTestCases[i].expected_result)); 644 UTF8ToUTF16(kTestCases[i].expected_result));
1115 string16 autocorrect_word = spell_checker->GetAutoCorrectionWord( 645 string16 autocorrect_word = spell_check()->GetAutoCorrectionWord(
1116 misspelled_word, 0); 646 misspelled_word, 0);
1117 647
1118 // Check for spelling. 648 // Check for spelling.
1119 EXPECT_EQ(expected_autocorrect_word, autocorrect_word); 649 EXPECT_EQ(expected_autocorrect_word, autocorrect_word);
1120 } 650 }
1121 } 651 }
1122 652
1123 #if defined(OS_MACOSX) 653 } // namespace
1124 // Tests that words are properly ignored. Currently only enabled on OS X as it
1125 // is the only platform to support ignoring words. Note that in this test, we
1126 // supply a non-zero doc_tag, in order to test that ignored words are matched to
1127 // the correct document.
1128 TEST_F(SpellCheckTest, IgnoreWords_EN_US) {
1129 static const struct {
1130 // A misspelled word.
1131 const char* input;
1132 bool input_result;
1133 } kTestCases[] = {
1134 {"teh", false},
1135 {"moer", false},
1136 {"watre", false},
1137 {"noen", false},
1138 };
1139
1140 FilePath hunspell_directory = GetHunspellDirectory();
1141 ASSERT_FALSE(hunspell_directory.empty());
1142
1143 scoped_refptr<SpellChecker> spell_checker(new SpellChecker(
1144 hunspell_directory, "en-US", NULL, FilePath()));
1145 spell_checker->Initialize();
1146 message_loop_.RunAllPending();
1147
1148 for (size_t i = 0; i < ARRAYSIZE_UNSAFE(kTestCases); ++i) {
1149 string16 word(UTF8ToUTF16(kTestCases[i].input));
1150 std::vector<string16> suggestions;
1151 size_t input_length = 0;
1152 if (kTestCases[i].input != NULL) {
1153 input_length = word.length();
1154 }
1155 int misspelling_start;
1156 int misspelling_length;
1157
1158 int doc_tag = SpellCheckerPlatform::GetDocumentTag();
1159 bool result = spell_checker->SpellCheckWord(word.c_str(),
1160 static_cast<int>(input_length),
1161 doc_tag,
1162 &misspelling_start,
1163 &misspelling_length,
1164 &suggestions);
1165
1166 // The word should show up as misspelled.
1167 EXPECT_EQ(kTestCases[i].input_result, result);
1168
1169 // Ignore the word.
1170 SpellCheckerPlatform::IgnoreWord(word);
1171
1172 // Spellcheck again.
1173 result = spell_checker->SpellCheckWord(word.c_str(),
1174 static_cast<int>(input_length),
1175 doc_tag,
1176 &misspelling_start,
1177 &misspelling_length,
1178 &suggestions);
1179
1180 // The word should now show up as correctly spelled.
1181 EXPECT_EQ(!(kTestCases[i].input_result), result);
1182
1183 // Close the docuemnt. Any words that we had previously ignored should no
1184 // longer be ignored and thus should show up as misspelled.
1185 SpellCheckerPlatform::CloseDocumentWithTag(doc_tag);
1186
1187 // Spellcheck one more time.
1188 result = spell_checker->SpellCheckWord(word.c_str(),
1189 static_cast<int>(input_length),
1190 doc_tag,
1191 &misspelling_start,
1192 &misspelling_length,
1193 &suggestions);
1194
1195 // The word should now show be spelled wrong again
1196 EXPECT_EQ(kTestCases[i].input_result, result);
1197 }
1198 } // Test IgnoreWords_EN_US
1199 #endif // OS_MACOSX
OLDNEW
« no previous file with comments | « chrome/renderer/spellchecker/spellcheck.cc ('k') | chrome/test/testing_profile.h » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698