001 /*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements. See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License. You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018 package org.apache.commons.codec.language;
019
020 import static org.junit.Assert.assertEquals;
021 import static org.junit.Assert.assertFalse;
022 import static org.junit.Assert.assertTrue;
023 import static org.junit.Assert.fail;
024
025 import org.apache.commons.codec.EncoderException;
026 import org.apache.commons.codec.StringEncoderAbstractTest;
027 import org.junit.Test;
028
029 /**
030 * Tests {@link DoubleMetaphone}.
031 *
032 * <p>Keep this file in UTF-8 encoding for proper Javadoc processing.</p>
033 *
034 * @see "http://www.cuj.com/documents/s=8038/cuj0006philips/"
035 * @version $Id: DoubleMetaphoneTest.html 889935 2013-12-11 05:05:13Z ggregory $
036 */
037 public class DoubleMetaphoneTest extends StringEncoderAbstractTest<DoubleMetaphone> {
038
039 /**
040 * Test data from http://aspell.net/test/orig/batch0.tab.
041 *
042 * "Copyright (C) 2002 Kevin Atkinson (kevina@gnu.org). Verbatim copying
043 * and distribution of this entire article is permitted in any medium,
044 * provided this notice is preserved."
045 *
046 * Massaged the test data in the array below.
047 */
048 private static final String[][] FIXTURE = { { "Accosinly", "Occasionally" }, {
049 "Ciculer", "Circler" }, {
050 "Circue", "Circle" }, {
051 "Maddness", "Madness" }, {
052 "Occusionaly", "Occasionally" }, {
053 "Steffen", "Stephen" }, {
054 "Thw", "The" }, {
055 "Unformanlly", "Unfortunately" }, {
056 "Unfortally", "Unfortunately" }, {
057 "abilitey", "ability" }, {
058 "abouy", "about" }, {
059 "absorbtion", "absorption" }, {
060 "accidently", "accidentally" }, {
061 "accomodate", "accommodate" }, {
062 "acommadate", "accommodate" }, {
063 "acord", "accord" }, {
064 "adultry", "adultery" }, {
065 "aggresive", "aggressive" }, {
066 "alchohol", "alcohol" }, {
067 "alchoholic", "alcoholic" }, {
068 "allieve", "alive" }, {
069 "alot", "a lot" }, {
070 "alright", "all right" }, {
071 "amature", "amateur" }, {
072 "ambivilant", "ambivalent" }, {
073 "amification", "amplification" }, {
074 "amourfous", "amorphous" }, {
075 "annoint", "anoint" }, {
076 "annonsment", "announcement" }, {
077 "annoyting", "anting" }, {
078 "annuncio", "announce" }, {
079 "anonomy", "anatomy" }, {
080 "anotomy", "anatomy" }, {
081 "antidesestablishmentarianism", "antidisestablishmentarianism" }, {
082 "antidisestablishmentarism", "antidisestablishmentarianism" }, {
083 "anynomous", "anonymous" }, {
084 "appelet", "applet" }, {
085 "appreceiated", "appreciated" }, {
086 "appresteate", "appreciate" }, {
087 "aquantance", "acquaintance" }, {
088 "aratictature", "architecture" }, {
089 "archeype", "archetype" }, {
090 "aricticure", "architecture" }, {
091 "artic", "arctic" }, {
092 "asentote", "asymptote" }, {
093 "ast", "at" }, {
094 "asterick", "asterisk" }, {
095 "asymetric", "asymmetric" }, {
096 "atentively", "attentively" }, {
097 "autoamlly", "automatically" }, {
098 "bankrot", "bankrupt" }, {
099 "basicly", "basically" }, {
100 "batallion", "battalion" }, {
101 "bbrose", "browse" }, {
102 "beauro", "bureau" }, {
103 "beaurocracy", "bureaucracy" }, {
104 "beggining", "beginning" }, {
105 "beging", "beginning" }, {
106 "behaviour", "behavior" }, {
107 "beleive", "believe" }, {
108 "belive", "believe" }, {
109 "benidifs", "benefits" }, {
110 "bigginging", "beginning" }, {
111 "blait", "bleat" }, {
112 "bouyant", "buoyant" }, {
113 "boygot", "boycott" }, {
114 "brocolli", "broccoli" }, {
115 "buch", "bush" }, {
116 "buder", "butter" }, {
117 "budr", "butter" }, {
118 "budter", "butter" }, {
119 "buracracy", "bureaucracy" }, {
120 "burracracy", "bureaucracy" }, {
121 "buton", "button" }, {
122 "byby", "by by" }, {
123 "cauler", "caller" }, {
124 "ceasar", "caesar" }, {
125 "cemetary", "cemetery" }, {
126 "changeing", "changing" }, {
127 "cheet", "cheat" }, {
128 "cicle", "circle" }, {
129 "cimplicity", "simplicity" }, {
130 "circumstaces", "circumstances" }, {
131 "clob", "club" }, {
132 "coaln", "colon" }, {
133 "cocamena", "cockamamie" }, {
134 "colleaque", "colleague" }, {
135 "colloquilism", "colloquialism" }, {
136 "columne", "column" }, {
137 "comiler", "compiler" }, {
138 "comitmment", "commitment" }, {
139 "comitte", "committee" }, {
140 "comittmen", "commitment" }, {
141 "comittmend", "commitment" }, {
142 "commerciasl", "commercials" }, {
143 "commited", "committed" }, {
144 "commitee", "committee" }, {
145 "companys", "companies" }, {
146 "compicated", "complicated" }, {
147 "comupter", "computer" }, {
148 "concensus", "consensus" }, {
149 "confusionism", "confucianism" }, {
150 "congradulations", "congratulations" }, {
151 "conibation", "contribution" }, {
152 "consident", "consistent" }, {
153 "consident", "consonant" }, {
154 "contast", "constant" }, {
155 "contastant", "constant" }, {
156 "contunie", "continue" }, {
157 "cooly", "coolly" }, {
158 "copping", "coping" }, {
159 "cosmoplyton", "cosmopolitan" }, {
160 "courst", "court" }, {
161 "crasy", "crazy" }, {
162 "cravets", "caveats" }, {
163 "credetability", "credibility" }, {
164 "criqitue", "critique" }, {
165 "croke", "croak" }, {
166 "crucifiction", "crucifixion" }, {
167 "crusifed", "crucified" }, {
168 "ctitique", "critique" }, {
169 "cumba", "combo" }, {
170 "custamisation", "customization" }, {
171 "dag", "dog" }, {
172 "daly", "daily" }, {
173 "danguages", "dangerous" }, {
174 "deaft", "draft" }, {
175 "defence", "defense" }, {
176 "defenly", "defiantly" }, {
177 "definate", "definite" }, {
178 "definately", "definitely" }, {
179 "dependeble", "dependable" }, {
180 "descrption", "description" }, {
181 "descrptn", "description" }, {
182 "desparate", "desperate" }, {
183 "dessicate", "desiccate" }, {
184 "destint", "distant" }, {
185 "develepment", "developments" }, {
186 "developement", "development" }, {
187 "develpond", "development" }, {
188 "devulge", "divulge" }, {
189 "diagree", "disagree" }, {
190 "dieties", "deities" }, {
191 "dinasaur", "dinosaur" }, {
192 "dinasour", "dinosaur" }, {
193 "direcyly", "directly" }, {
194 "discuess", "discuss" }, {
195 "disect", "dissect" }, {
196 "disippate", "dissipate" }, {
197 "disition", "decision" }, {
198 "dispair", "despair" }, {
199 "disssicion", "discussion" }, {
200 "distarct", "distract" }, {
201 "distart", "distort" }, {
202 "distroy", "destroy" }, {
203 "documtations", "documentation" }, {
204 "doenload", "download" }, {
205 "dongle", "dangle" }, {
206 "doog", "dog" }, {
207 "dramaticly", "dramatically" }, {
208 "drunkeness", "drunkenness" }, {
209 "ductioneery", "dictionary" }, {
210 "dur", "due" }, {
211 "duren", "during" }, {
212 "dymatic", "dynamic" }, {
213 "dynaic", "dynamic" }, {
214 "ecstacy", "ecstasy" }, {
215 "efficat", "efficient" }, {
216 "efficity", "efficacy" }, {
217 "effots", "efforts" }, {
218 "egsistence", "existence" }, {
219 "eitiology", "etiology" }, {
220 "elagent", "elegant" }, {
221 "elligit", "elegant" }, {
222 "embarass", "embarrass" }, {
223 "embarassment", "embarrassment" }, {
224 "embaress", "embarrass" }, {
225 "encapsualtion", "encapsulation" }, {
226 "encyclapidia", "encyclopedia" }, {
227 "encyclopia", "encyclopedia" }, {
228 "engins", "engine" }, {
229 "enhence", "enhance" }, {
230 "enligtment", "Enlightenment" }, {
231 "ennuui", "ennui" }, {
232 "enought", "enough" }, {
233 "enventions", "inventions" }, {
234 "envireminakl", "environmental" }, {
235 "enviroment", "environment" }, {
236 "epitomy", "epitome" }, {
237 "equire", "acquire" }, {
238 "errara", "error" }, {
239 "erro", "error" }, {
240 "evaualtion", "evaluation" }, {
241 "evething", "everything" }, {
242 "evtually", "eventually" }, {
243 "excede", "exceed" }, {
244 "excercise", "exercise" }, {
245 "excpt", "except" }, {
246 "excution", "execution" }, {
247 "exhileration", "exhilaration" }, {
248 "existance", "existence" }, {
249 "expleyly", "explicitly" }, {
250 "explity", "explicitly" }, {
251 "expresso", "espresso" }, {
252 "exspidient", "expedient" }, {
253 "extions", "extensions" }, {
254 "factontion", "factorization" }, {
255 "failer", "failure" }, {
256 "famdasy", "fantasy" }, {
257 "faver", "favor" }, {
258 "faxe", "fax" }, {
259 "febuary", "february" }, {
260 "firey", "fiery" }, {
261 "fistival", "festival" }, {
262 "flatterring", "flattering" }, {
263 "fluk", "flux" }, {
264 "flukse", "flux" }, {
265 "fone", "phone" }, {
266 "forsee", "foresee" }, {
267 "frustartaion", "frustrating" }, {
268 "fuction", "function" }, {
269 "funetik", "phonetic" }, {
270 "futs", "guts" }, {
271 "gamne", "came" }, {
272 "gaurd", "guard" }, {
273 "generly", "generally" }, {
274 "ghandi", "gandhi" }, {
275 "goberment", "government" }, {
276 "gobernement", "government" }, {
277 "gobernment", "government" }, {
278 "gotton", "gotten" }, {
279 "gracefull", "graceful" }, {
280 "gradualy", "gradually" }, {
281 "grammer", "grammar" }, {
282 "hallo", "hello" }, {
283 "hapily", "happily" }, {
284 "harrass", "harass" }, {
285 "havne", "have" }, {
286 "heellp", "help" }, {
287 "heighth", "height" }, {
288 "hellp", "help" }, {
289 "helo", "hello" }, {
290 "herlo", "hello" }, {
291 "hifin", "hyphen" }, {
292 "hifine", "hyphen" }, {
293 "higer", "higher" }, {
294 "hiphine", "hyphen" }, {
295 "hippie", "hippy" }, {
296 "hippopotamous", "hippopotamus" }, {
297 "hlp", "help" }, {
298 "hourse", "horse" }, {
299 "houssing", "housing" }, {
300 "howaver", "however" }, {
301 "howver", "however" }, {
302 "humaniti", "humanity" }, {
303 "hyfin", "hyphen" }, {
304 "hypotathes", "hypothesis" }, {
305 "hypotathese", "hypothesis" }, {
306 "hystrical", "hysterical" }, {
307 "ident", "indent" }, {
308 "illegitament", "illegitimate" }, {
309 "imbed", "embed" }, {
310 "imediaetly", "immediately" }, {
311 "imfamy", "infamy" }, {
312 "immenant", "immanent" }, {
313 "implemtes", "implements" }, {
314 "inadvertant", "inadvertent" }, {
315 "incase", "in case" }, {
316 "incedious", "insidious" }, {
317 "incompleet", "incomplete" }, {
318 "incomplot", "incomplete" }, {
319 "inconvenant", "inconvenient" }, {
320 "inconvience", "inconvenience" }, {
321 "independant", "independent" }, {
322 "independenent", "independent" }, {
323 "indepnends", "independent" }, {
324 "indepth", "in depth" }, {
325 "indispensible", "indispensable" }, {
326 "inefficite", "inefficient" }, {
327 "inerface", "interface" }, {
328 "infact", "in fact" }, {
329 "influencial", "influential" }, {
330 "inital", "initial" }, {
331 "initinized", "initialized" }, {
332 "initized", "initialized" }, {
333 "innoculate", "inoculate" }, {
334 "insistant", "insistent" }, {
335 "insistenet", "insistent" }, {
336 "instulation", "installation" }, {
337 "intealignt", "intelligent" }, {
338 "intejilent", "intelligent" }, {
339 "intelegent", "intelligent" }, {
340 "intelegnent", "intelligent" }, {
341 "intelejent", "intelligent" }, {
342 "inteligent", "intelligent" }, {
343 "intelignt", "intelligent" }, {
344 "intellagant", "intelligent" }, {
345 "intellegent", "intelligent" }, {
346 "intellegint", "intelligent" }, {
347 "intellgnt", "intelligent" }, {
348 "intensionality", "intensionally" }, {
349 "interate", "iterate" }, {
350 "internation", "international" }, {
351 "interpretate", "interpret" }, {
352 "interpretter", "interpreter" }, {
353 "intertes", "interested" }, {
354 "intertesd", "interested" }, {
355 "invermeantial", "environmental" }, {
356 "irregardless", "regardless" }, {
357 "irresistable", "irresistible" }, {
358 "irritible", "irritable" }, {
359 "islams", "muslims" }, {
360 "isotrop", "isotope" }, {
361 "isreal", "israel" }, {
362 "johhn", "john" }, {
363 "judgement", "judgment" }, {
364 "kippur", "kipper" }, {
365 "knawing", "knowing" }, {
366 "latext", "latest" }, {
367 "leasve", "leave" }, {
368 "lesure", "leisure" }, {
369 "liasion", "lesion" }, {
370 "liason", "liaison" }, {
371 "libary", "library" }, {
372 "likly", "likely" }, {
373 "lilometer", "kilometer" }, {
374 "liquify", "liquefy" }, {
375 "lloyer", "layer" }, {
376 "lossing", "losing" }, {
377 "luser", "laser" }, {
378 "maintanence", "maintenance" }, {
379 "majaerly", "majority" }, {
380 "majoraly", "majority" }, {
381 "maks", "masks" }, {
382 "mandelbrot", "Mandelbrot" }, {
383 "mant", "want" }, {
384 "marshall", "marshal" }, {
385 "maxium", "maximum" }, {
386 "meory", "memory" }, {
387 "metter", "better" }, {
388 "mic", "mike" }, {
389 "midia", "media" }, {
390 "millenium", "millennium" }, {
391 "miniscule", "minuscule" }, {
392 "minkay", "monkey" }, {
393 "minum", "minimum" }, {
394 "mischievious", "mischievous" }, {
395 "misilous", "miscellaneous" }, {
396 "momento", "memento" }, {
397 "monkay", "monkey" }, {
398 "mosaik", "mosaic" }, {
399 "mostlikely", "most likely" }, {
400 "mousr", "mouser" }, {
401 "mroe", "more" }, {
402 "neccessary", "necessary" }, {
403 "necesary", "necessary" }, {
404 "necesser", "necessary" }, {
405 "neice", "niece" }, {
406 "neighbour", "neighbor" }, {
407 "nemonic", "pneumonic" }, {
408 "nevade", "Nevada" }, {
409 "nickleodeon", "nickelodeon" }, {
410 "nieve", "naive" }, {
411 "noone", "no one" }, {
412 "noticably", "noticeably" }, {
413 "notin", "not in" }, {
414 "nozled", "nuzzled" }, {
415 "objectsion", "objects" }, {
416 "obsfuscate", "obfuscate" }, {
417 "ocassion", "occasion" }, {
418 "occuppied", "occupied" }, {
419 "occurence", "occurrence" }, {
420 "octagenarian", "octogenarian" }, {
421 "olf", "old" }, {
422 "opposim", "opossum" }, {
423 "organise", "organize" }, {
424 "organiz", "organize" }, {
425 "orientate", "orient" }, {
426 "oscilascope", "oscilloscope" }, {
427 "oving", "moving" }, {
428 "paramers", "parameters" }, {
429 "parametic", "parameter" }, {
430 "paranets", "parameters" }, {
431 "partrucal", "particular" }, {
432 "pataphysical", "metaphysical" }, {
433 "patten", "pattern" }, {
434 "permissable", "permissible" }, {
435 "permition", "permission" }, {
436 "permmasivie", "permissive" }, {
437 "perogative", "prerogative" }, {
438 "persue", "pursue" }, {
439 "phantasia", "fantasia" }, {
440 "phenominal", "phenomenal" }, {
441 "picaresque", "picturesque" }, {
442 "playwrite", "playwright" }, {
443 "poeses", "poesies" }, {
444 "polation", "politician" }, {
445 "poligamy", "polygamy" }, {
446 "politict", "politic" }, {
447 "pollice", "police" }, {
448 "polypropalene", "polypropylene" }, {
449 "pompom", "pompon" }, {
450 "possable", "possible" }, {
451 "practicle", "practical" }, {
452 "pragmaticism", "pragmatism" }, {
453 "preceeding", "preceding" }, {
454 "precion", "precision" }, {
455 "precios", "precision" }, {
456 "preemptory", "peremptory" }, {
457 "prefices", "prefixes" }, {
458 "prefixt", "prefixed" }, {
459 "presbyterian", "Presbyterian" }, {
460 "presue", "pursue" }, {
461 "presued", "pursued" }, {
462 "privielage", "privilege" }, {
463 "priviledge", "privilege" }, {
464 "proceedures", "procedures" }, {
465 "pronensiation", "pronunciation" }, {
466 "pronisation", "pronunciation" }, {
467 "pronounciation", "pronunciation" }, {
468 "properally", "properly" }, {
469 "proplematic", "problematic" }, {
470 "protray", "portray" }, {
471 "pscolgst", "psychologist" }, {
472 "psicolagest", "psychologist" }, {
473 "psycolagest", "psychologist" }, {
474 "quoz", "quiz" }, {
475 "radious", "radius" }, {
476 "ramplily", "rampantly" }, {
477 "reccomend", "recommend" }, {
478 "reccona", "raccoon" }, {
479 "recieve", "receive" }, {
480 "reconise", "recognize" }, {
481 "rectangeles", "rectangle" }, {
482 "redign", "redesign" }, {
483 "reoccurring", "recurring" }, {
484 "repitition", "repetition" }, {
485 "replasments", "replacement" }, {
486 "reposable", "responsible" }, {
487 "reseblence", "resemblance" }, {
488 "respct", "respect" }, {
489 "respecally", "respectfully" }, {
490 "roon", "room" }, {
491 "rought", "roughly" }, {
492 "rsx", "RSX" }, {
493 "rudemtry", "rudimentary" }, {
494 "runnung", "running" }, {
495 "sacreligious", "sacrilegious" }, {
496 "saftly", "safely" }, {
497 "salut", "salute" }, {
498 "satifly", "satisfy" }, {
499 "scrabdle", "scrabble" }, {
500 "searcheable", "searchable" }, {
501 "secion", "section" }, {
502 "seferal", "several" }, {
503 "segements", "segments" }, {
504 "sence", "sense" }, {
505 "seperate", "separate" }, {
506 "sherbert", "sherbet" }, {
507 "sicolagest", "psychologist" }, {
508 "sieze", "seize" }, {
509 "simpfilty", "simplicity" }, {
510 "simplye", "simply" }, {
511 "singal", "signal" }, {
512 "sitte", "site" }, {
513 "situration", "situation" }, {
514 "slyph", "sylph" }, {
515 "smil", "smile" }, {
516 "snuck", "sneaked" }, {
517 "sometmes", "sometimes" }, {
518 "soonec", "sonic" }, {
519 "specificialy", "specifically" }, {
520 "spel", "spell" }, {
521 "spoak", "spoke" }, {
522 "sponsered", "sponsored" }, {
523 "stering", "steering" }, {
524 "straightjacket", "straitjacket" }, {
525 "stumach", "stomach" }, {
526 "stutent", "student" }, {
527 "styleguide", "style guide" }, {
528 "subisitions", "substitutions" }, {
529 "subjecribed", "subscribed" }, {
530 "subpena", "subpoena" }, {
531 "substations", "substitutions" }, {
532 "suger", "sugar" }, {
533 "supercede", "supersede" }, {
534 "superfulous", "superfluous" }, {
535 "susan", "Susan" }, {
536 "swimwear", "swim wear" }, {
537 "syncorization", "synchronization" }, {
538 "taff", "tough" }, {
539 "taht", "that" }, {
540 "tattos", "tattoos" }, {
541 "techniquely", "technically" }, {
542 "teh", "the" }, {
543 "tem", "team" }, {
544 "teo", "two" }, {
545 "teridical", "theoretical" }, {
546 "tesst", "test" }, {
547 "tets", "tests" }, {
548 "thanot", "than or" }, {
549 "theirselves", "themselves" }, {
550 "theridically", "theoretical" }, {
551 "thredically", "theoretically" }, {
552 "thruout", "throughout" }, {
553 "ths", "this" }, {
554 "titalate", "titillate" }, {
555 "tobagan", "tobaggon" }, {
556 "tommorrow", "tomorrow" }, {
557 "tomorow", "tomorrow" }, {
558 "tradegy", "tragedy" }, {
559 "trubbel", "trouble" }, {
560 "ttest", "test" }, {
561 "tunnellike", "tunnel like" }, {
562 "tured", "turned" }, {
563 "tyrrany", "tyranny" }, {
564 "unatourral", "unnatural" }, {
565 "unaturral", "unnatural" }, {
566 "unconisitional", "unconstitutional" }, {
567 "unconscience", "unconscious" }, {
568 "underladder", "under ladder" }, {
569 "unentelegible", "unintelligible" }, {
570 "unfortunently", "unfortunately" }, {
571 "unnaturral", "unnatural" }, {
572 "upcast", "up cast" }, {
573 "upmost", "utmost" }, {
574 "uranisium", "uranium" }, {
575 "verison", "version" }, {
576 "vinagarette", "vinaigrette" }, {
577 "volumptuous", "voluptuous" }, {
578 "volunteerism", "voluntarism" }, {
579 "volye", "volley" }, {
580 "wadting", "wasting" }, {
581 "waite", "wait" }, {
582 "wan't", "won't" }, {
583 "warloord", "warlord" }, {
584 "whaaat", "what" }, {
585 "whard", "ward" }, {
586 "whimp", "wimp" }, {
587 "wicken", "weaken" }, {
588 "wierd", "weird" }, {
589 "wrank", "rank" }, {
590 "writeen", "righten" }, {
591 "writting", "writing" }, {
592 "wundeews", "windows" }, {
593 "yeild", "yield" }, {
594 "youe", "your" }
595 };
596
597 /**
598 * A subset of FIXTURE generated by this test.
599 */
600 private static final String[][] MATCHES = { { "Accosinly", "Occasionally" }, {
601 "Maddness", "Madness" }, {
602 "Occusionaly", "Occasionally" }, {
603 "Steffen", "Stephen" }, {
604 "Thw", "The" }, {
605 "Unformanlly", "Unfortunately" }, {
606 "Unfortally", "Unfortunately" }, {
607 "abilitey", "ability" }, {
608 "absorbtion", "absorption" }, {
609 "accidently", "accidentally" }, {
610 "accomodate", "accommodate" }, {
611 "acommadate", "accommodate" }, {
612 "acord", "accord" }, {
613 "adultry", "adultery" }, {
614 "aggresive", "aggressive" }, {
615 "alchohol", "alcohol" }, {
616 "alchoholic", "alcoholic" }, {
617 "allieve", "alive" }, {
618 "alot", "a lot" }, {
619 "alright", "all right" }, {
620 "amature", "amateur" }, {
621 "ambivilant", "ambivalent" }, {
622 "amourfous", "amorphous" }, {
623 "annoint", "anoint" }, {
624 "annonsment", "announcement" }, {
625 "annoyting", "anting" }, {
626 "annuncio", "announce" }, {
627 "anotomy", "anatomy" }, {
628 "antidesestablishmentarianism", "antidisestablishmentarianism" }, {
629 "antidisestablishmentarism", "antidisestablishmentarianism" }, {
630 "anynomous", "anonymous" }, {
631 "appelet", "applet" }, {
632 "appreceiated", "appreciated" }, {
633 "appresteate", "appreciate" }, {
634 "aquantance", "acquaintance" }, {
635 "aricticure", "architecture" }, {
636 "asterick", "asterisk" }, {
637 "asymetric", "asymmetric" }, {
638 "atentively", "attentively" }, {
639 "bankrot", "bankrupt" }, {
640 "basicly", "basically" }, {
641 "batallion", "battalion" }, {
642 "bbrose", "browse" }, {
643 "beauro", "bureau" }, {
644 "beaurocracy", "bureaucracy" }, {
645 "beggining", "beginning" }, {
646 "behaviour", "behavior" }, {
647 "beleive", "believe" }, {
648 "belive", "believe" }, {
649 "blait", "bleat" }, {
650 "bouyant", "buoyant" }, {
651 "boygot", "boycott" }, {
652 "brocolli", "broccoli" }, {
653 "buder", "butter" }, {
654 "budr", "butter" }, {
655 "budter", "butter" }, {
656 "buracracy", "bureaucracy" }, {
657 "burracracy", "bureaucracy" }, {
658 "buton", "button" }, {
659 "byby", "by by" }, {
660 "cauler", "caller" }, {
661 "ceasar", "caesar" }, {
662 "cemetary", "cemetery" }, {
663 "changeing", "changing" }, {
664 "cheet", "cheat" }, {
665 "cimplicity", "simplicity" }, {
666 "circumstaces", "circumstances" }, {
667 "clob", "club" }, {
668 "coaln", "colon" }, {
669 "colleaque", "colleague" }, {
670 "colloquilism", "colloquialism" }, {
671 "columne", "column" }, {
672 "comitmment", "commitment" }, {
673 "comitte", "committee" }, {
674 "comittmen", "commitment" }, {
675 "comittmend", "commitment" }, {
676 "commerciasl", "commercials" }, {
677 "commited", "committed" }, {
678 "commitee", "committee" }, {
679 "companys", "companies" }, {
680 "comupter", "computer" }, {
681 "concensus", "consensus" }, {
682 "confusionism", "confucianism" }, {
683 "congradulations", "congratulations" }, {
684 "contunie", "continue" }, {
685 "cooly", "coolly" }, {
686 "copping", "coping" }, {
687 "cosmoplyton", "cosmopolitan" }, {
688 "crasy", "crazy" }, {
689 "croke", "croak" }, {
690 "crucifiction", "crucifixion" }, {
691 "crusifed", "crucified" }, {
692 "cumba", "combo" }, {
693 "custamisation", "customization" }, {
694 "dag", "dog" }, {
695 "daly", "daily" }, {
696 "defence", "defense" }, {
697 "definate", "definite" }, {
698 "definately", "definitely" }, {
699 "dependeble", "dependable" }, {
700 "descrption", "description" }, {
701 "descrptn", "description" }, {
702 "desparate", "desperate" }, {
703 "dessicate", "desiccate" }, {
704 "destint", "distant" }, {
705 "develepment", "developments" }, {
706 "developement", "development" }, {
707 "develpond", "development" }, {
708 "devulge", "divulge" }, {
709 "dieties", "deities" }, {
710 "dinasaur", "dinosaur" }, {
711 "dinasour", "dinosaur" }, {
712 "discuess", "discuss" }, {
713 "disect", "dissect" }, {
714 "disippate", "dissipate" }, {
715 "disition", "decision" }, {
716 "dispair", "despair" }, {
717 "distarct", "distract" }, {
718 "distart", "distort" }, {
719 "distroy", "destroy" }, {
720 "doenload", "download" }, {
721 "dongle", "dangle" }, {
722 "doog", "dog" }, {
723 "dramaticly", "dramatically" }, {
724 "drunkeness", "drunkenness" }, {
725 "ductioneery", "dictionary" }, {
726 "ecstacy", "ecstasy" }, {
727 "egsistence", "existence" }, {
728 "eitiology", "etiology" }, {
729 "elagent", "elegant" }, {
730 "embarass", "embarrass" }, {
731 "embarassment", "embarrassment" }, {
732 "embaress", "embarrass" }, {
733 "encapsualtion", "encapsulation" }, {
734 "encyclapidia", "encyclopedia" }, {
735 "encyclopia", "encyclopedia" }, {
736 "engins", "engine" }, {
737 "enhence", "enhance" }, {
738 "ennuui", "ennui" }, {
739 "enventions", "inventions" }, {
740 "envireminakl", "environmental" }, {
741 "enviroment", "environment" }, {
742 "epitomy", "epitome" }, {
743 "equire", "acquire" }, {
744 "errara", "error" }, {
745 "evaualtion", "evaluation" }, {
746 "excede", "exceed" }, {
747 "excercise", "exercise" }, {
748 "excpt", "except" }, {
749 "exhileration", "exhilaration" }, {
750 "existance", "existence" }, {
751 "expleyly", "explicitly" }, {
752 "explity", "explicitly" }, {
753 "failer", "failure" }, {
754 "faver", "favor" }, {
755 "faxe", "fax" }, {
756 "firey", "fiery" }, {
757 "fistival", "festival" }, {
758 "flatterring", "flattering" }, {
759 "flukse", "flux" }, {
760 "fone", "phone" }, {
761 "forsee", "foresee" }, {
762 "frustartaion", "frustrating" }, {
763 "funetik", "phonetic" }, {
764 "gaurd", "guard" }, {
765 "generly", "generally" }, {
766 "ghandi", "gandhi" }, {
767 "gotton", "gotten" }, {
768 "gracefull", "graceful" }, {
769 "gradualy", "gradually" }, {
770 "grammer", "grammar" }, {
771 "hallo", "hello" }, {
772 "hapily", "happily" }, {
773 "harrass", "harass" }, {
774 "heellp", "help" }, {
775 "heighth", "height" }, {
776 "hellp", "help" }, {
777 "helo", "hello" }, {
778 "hifin", "hyphen" }, {
779 "hifine", "hyphen" }, {
780 "hiphine", "hyphen" }, {
781 "hippie", "hippy" }, {
782 "hippopotamous", "hippopotamus" }, {
783 "hourse", "horse" }, {
784 "houssing", "housing" }, {
785 "howaver", "however" }, {
786 "howver", "however" }, {
787 "humaniti", "humanity" }, {
788 "hyfin", "hyphen" }, {
789 "hystrical", "hysterical" }, {
790 "illegitament", "illegitimate" }, {
791 "imbed", "embed" }, {
792 "imediaetly", "immediately" }, {
793 "immenant", "immanent" }, {
794 "implemtes", "implements" }, {
795 "inadvertant", "inadvertent" }, {
796 "incase", "in case" }, {
797 "incedious", "insidious" }, {
798 "incompleet", "incomplete" }, {
799 "incomplot", "incomplete" }, {
800 "inconvenant", "inconvenient" }, {
801 "inconvience", "inconvenience" }, {
802 "independant", "independent" }, {
803 "independenent", "independent" }, {
804 "indepnends", "independent" }, {
805 "indepth", "in depth" }, {
806 "indispensible", "indispensable" }, {
807 "inefficite", "inefficient" }, {
808 "infact", "in fact" }, {
809 "influencial", "influential" }, {
810 "innoculate", "inoculate" }, {
811 "insistant", "insistent" }, {
812 "insistenet", "insistent" }, {
813 "instulation", "installation" }, {
814 "intealignt", "intelligent" }, {
815 "intelegent", "intelligent" }, {
816 "intelegnent", "intelligent" }, {
817 "intelejent", "intelligent" }, {
818 "inteligent", "intelligent" }, {
819 "intelignt", "intelligent" }, {
820 "intellagant", "intelligent" }, {
821 "intellegent", "intelligent" }, {
822 "intellegint", "intelligent" }, {
823 "intellgnt", "intelligent" }, {
824 "intensionality", "intensionally" }, {
825 "internation", "international" }, {
826 "interpretate", "interpret" }, {
827 "interpretter", "interpreter" }, {
828 "intertes", "interested" }, {
829 "intertesd", "interested" }, {
830 "invermeantial", "environmental" }, {
831 "irresistable", "irresistible" }, {
832 "irritible", "irritable" }, {
833 "isreal", "israel" }, {
834 "johhn", "john" }, {
835 "kippur", "kipper" }, {
836 "knawing", "knowing" }, {
837 "lesure", "leisure" }, {
838 "liasion", "lesion" }, {
839 "liason", "liaison" }, {
840 "likly", "likely" }, {
841 "liquify", "liquefy" }, {
842 "lloyer", "layer" }, {
843 "lossing", "losing" }, {
844 "luser", "laser" }, {
845 "maintanence", "maintenance" }, {
846 "mandelbrot", "Mandelbrot" }, {
847 "marshall", "marshal" }, {
848 "maxium", "maximum" }, {
849 "mic", "mike" }, {
850 "midia", "media" }, {
851 "millenium", "millennium" }, {
852 "miniscule", "minuscule" }, {
853 "minkay", "monkey" }, {
854 "mischievious", "mischievous" }, {
855 "momento", "memento" }, {
856 "monkay", "monkey" }, {
857 "mosaik", "mosaic" }, {
858 "mostlikely", "most likely" }, {
859 "mousr", "mouser" }, {
860 "mroe", "more" }, {
861 "necesary", "necessary" }, {
862 "necesser", "necessary" }, {
863 "neice", "niece" }, {
864 "neighbour", "neighbor" }, {
865 "nemonic", "pneumonic" }, {
866 "nevade", "Nevada" }, {
867 "nickleodeon", "nickelodeon" }, {
868 "nieve", "naive" }, {
869 "noone", "no one" }, {
870 "notin", "not in" }, {
871 "nozled", "nuzzled" }, {
872 "objectsion", "objects" }, {
873 "ocassion", "occasion" }, {
874 "occuppied", "occupied" }, {
875 "occurence", "occurrence" }, {
876 "octagenarian", "octogenarian" }, {
877 "opposim", "opossum" }, {
878 "organise", "organize" }, {
879 "organiz", "organize" }, {
880 "orientate", "orient" }, {
881 "oscilascope", "oscilloscope" }, {
882 "parametic", "parameter" }, {
883 "permissable", "permissible" }, {
884 "permmasivie", "permissive" }, {
885 "persue", "pursue" }, {
886 "phantasia", "fantasia" }, {
887 "phenominal", "phenomenal" }, {
888 "playwrite", "playwright" }, {
889 "poeses", "poesies" }, {
890 "poligamy", "polygamy" }, {
891 "politict", "politic" }, {
892 "pollice", "police" }, {
893 "polypropalene", "polypropylene" }, {
894 "possable", "possible" }, {
895 "practicle", "practical" }, {
896 "pragmaticism", "pragmatism" }, {
897 "preceeding", "preceding" }, {
898 "precios", "precision" }, {
899 "preemptory", "peremptory" }, {
900 "prefixt", "prefixed" }, {
901 "presbyterian", "Presbyterian" }, {
902 "presue", "pursue" }, {
903 "presued", "pursued" }, {
904 "privielage", "privilege" }, {
905 "priviledge", "privilege" }, {
906 "proceedures", "procedures" }, {
907 "pronensiation", "pronunciation" }, {
908 "pronounciation", "pronunciation" }, {
909 "properally", "properly" }, {
910 "proplematic", "problematic" }, {
911 "protray", "portray" }, {
912 "pscolgst", "psychologist" }, {
913 "psicolagest", "psychologist" }, {
914 "psycolagest", "psychologist" }, {
915 "quoz", "quiz" }, {
916 "radious", "radius" }, {
917 "reccomend", "recommend" }, {
918 "reccona", "raccoon" }, {
919 "recieve", "receive" }, {
920 "reconise", "recognize" }, {
921 "rectangeles", "rectangle" }, {
922 "reoccurring", "recurring" }, {
923 "repitition", "repetition" }, {
924 "replasments", "replacement" }, {
925 "respct", "respect" }, {
926 "respecally", "respectfully" }, {
927 "rsx", "RSX" }, {
928 "runnung", "running" }, {
929 "sacreligious", "sacrilegious" }, {
930 "salut", "salute" }, {
931 "searcheable", "searchable" }, {
932 "seferal", "several" }, {
933 "segements", "segments" }, {
934 "sence", "sense" }, {
935 "seperate", "separate" }, {
936 "sicolagest", "psychologist" }, {
937 "sieze", "seize" }, {
938 "simplye", "simply" }, {
939 "sitte", "site" }, {
940 "slyph", "sylph" }, {
941 "smil", "smile" }, {
942 "sometmes", "sometimes" }, {
943 "soonec", "sonic" }, {
944 "specificialy", "specifically" }, {
945 "spel", "spell" }, {
946 "spoak", "spoke" }, {
947 "sponsered", "sponsored" }, {
948 "stering", "steering" }, {
949 "straightjacket", "straitjacket" }, {
950 "stumach", "stomach" }, {
951 "stutent", "student" }, {
952 "styleguide", "style guide" }, {
953 "subpena", "subpoena" }, {
954 "substations", "substitutions" }, {
955 "supercede", "supersede" }, {
956 "superfulous", "superfluous" }, {
957 "susan", "Susan" }, {
958 "swimwear", "swim wear" }, {
959 "syncorization", "synchronization" }, {
960 "taff", "tough" }, {
961 "taht", "that" }, {
962 "tattos", "tattoos" }, {
963 "techniquely", "technically" }, {
964 "teh", "the" }, {
965 "tem", "team" }, {
966 "teo", "two" }, {
967 "teridical", "theoretical" }, {
968 "tesst", "test" }, {
969 "theridically", "theoretical" }, {
970 "thredically", "theoretically" }, {
971 "thruout", "throughout" }, {
972 "ths", "this" }, {
973 "titalate", "titillate" }, {
974 "tobagan", "tobaggon" }, {
975 "tommorrow", "tomorrow" }, {
976 "tomorow", "tomorrow" }, {
977 "trubbel", "trouble" }, {
978 "ttest", "test" }, {
979 "tyrrany", "tyranny" }, {
980 "unatourral", "unnatural" }, {
981 "unaturral", "unnatural" }, {
982 "unconisitional", "unconstitutional" }, {
983 "unconscience", "unconscious" }, {
984 "underladder", "under ladder" }, {
985 "unentelegible", "unintelligible" }, {
986 "unfortunently", "unfortunately" }, {
987 "unnaturral", "unnatural" }, {
988 "upcast", "up cast" }, {
989 "verison", "version" }, {
990 "vinagarette", "vinaigrette" }, {
991 "volunteerism", "voluntarism" }, {
992 "volye", "volley" }, {
993 "waite", "wait" }, {
994 "wan't", "won't" }, {
995 "warloord", "warlord" }, {
996 "whaaat", "what" }, {
997 "whard", "ward" }, {
998 "whimp", "wimp" }, {
999 "wicken", "weaken" }, {
1000 "wierd", "weird" }, {
1001 "wrank", "rank" }, {
1002 "writeen", "righten" }, {
1003 "writting", "writing" }, {
1004 "wundeews", "windows" }, {
1005 "yeild", "yield" }, };
1006
1007 /**
1008 * Tests encoding APIs in one place.
1009 */
1010 private void assertDoubleMetaphone(final String expected, final String source) {
1011 assertEquals(expected, this.getStringEncoder().encode(source));
1012 try {
1013 assertEquals(expected, this.getStringEncoder().encode((Object) source));
1014 } catch (final EncoderException e) {
1015 fail("Unexpected expection: " + e);
1016 }
1017 assertEquals(expected, this.getStringEncoder().doubleMetaphone(source));
1018 assertEquals(expected, this.getStringEncoder().doubleMetaphone(source, false));
1019 }
1020
1021 /**
1022 * Tests encoding APIs in one place.
1023 */
1024 public void assertDoubleMetaphoneAlt(final String expected, final String source) {
1025 assertEquals(expected, this.getStringEncoder().doubleMetaphone(source, true));
1026 }
1027
1028 public void doubleMetaphoneEqualTest(final String[][] pairs, final boolean useAlternate) {
1029 this.validateFixture(pairs);
1030 for (final String[] pair : pairs) {
1031 final String name0 = pair[0];
1032 final String name1 = pair[1];
1033 final String failMsg = "Expected match between " + name0 + " and " + name1 + " (use alternate: " + useAlternate + ")";
1034 assertTrue(failMsg, this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1, useAlternate));
1035 assertTrue(failMsg, this.getStringEncoder().isDoubleMetaphoneEqual(name1, name0, useAlternate));
1036 if (!useAlternate) {
1037 assertTrue(failMsg, this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1));
1038 assertTrue(failMsg, this.getStringEncoder().isDoubleMetaphoneEqual(name1, name0));
1039 }
1040 }
1041 }
1042
1043 public void doubleMetaphoneNotEqualTest(final boolean alternate) {
1044 assertFalse(this.getStringEncoder().isDoubleMetaphoneEqual("Brain", "Band", alternate));
1045 assertFalse(this.getStringEncoder().isDoubleMetaphoneEqual("Band", "Brain", alternate));
1046
1047 if (!alternate) {
1048 assertFalse(this.getStringEncoder().isDoubleMetaphoneEqual("Brain", "Band"));
1049 assertFalse(this.getStringEncoder().isDoubleMetaphoneEqual("Band", "Brain"));
1050 }
1051 }
1052
1053 @Override
1054 protected DoubleMetaphone createStringEncoder() {
1055 return new DoubleMetaphone();
1056 }
1057
1058 @Test
1059 public void testDoubleMetaphone() {
1060 assertDoubleMetaphone("TSTN", "testing");
1061 assertDoubleMetaphone("0", "The");
1062 assertDoubleMetaphone("KK", "quick");
1063 assertDoubleMetaphone("PRN", "brown");
1064 assertDoubleMetaphone("FKS", "fox");
1065 assertDoubleMetaphone("JMPT", "jumped");
1066 assertDoubleMetaphone("AFR", "over");
1067 assertDoubleMetaphone("0", "the");
1068 assertDoubleMetaphone("LS", "lazy");
1069 assertDoubleMetaphone("TKS", "dogs");
1070 assertDoubleMetaphone("MKFR", "MacCafferey");
1071 assertDoubleMetaphone("STFN", "Stephan");
1072 assertDoubleMetaphone("KSSK", "Kuczewski");
1073 assertDoubleMetaphone("MKLL", "McClelland");
1074 assertDoubleMetaphone("SNHS", "san jose");
1075 assertDoubleMetaphone("SNFP", "xenophobia");
1076
1077 assertDoubleMetaphoneAlt("TSTN", "testing");
1078 assertDoubleMetaphoneAlt("T", "The");
1079 assertDoubleMetaphoneAlt("KK", "quick");
1080 assertDoubleMetaphoneAlt("PRN", "brown");
1081 assertDoubleMetaphoneAlt("FKS", "fox");
1082 assertDoubleMetaphoneAlt("AMPT", "jumped");
1083 assertDoubleMetaphoneAlt("AFR", "over");
1084 assertDoubleMetaphoneAlt("T", "the");
1085 assertDoubleMetaphoneAlt("LS", "lazy");
1086 assertDoubleMetaphoneAlt("TKS", "dogs");
1087 assertDoubleMetaphoneAlt("MKFR", "MacCafferey");
1088 assertDoubleMetaphoneAlt("STFN", "Stephan");
1089 assertDoubleMetaphoneAlt("KXFS", "Kutchefski");
1090 assertDoubleMetaphoneAlt("MKLL", "McClelland");
1091 assertDoubleMetaphoneAlt("SNHS", "san jose");
1092 assertDoubleMetaphoneAlt("SNFP", "xenophobia");
1093 assertDoubleMetaphoneAlt("FKR", "Fokker");
1094 assertDoubleMetaphoneAlt("AK", "Joqqi");
1095 assertDoubleMetaphoneAlt("HF", "Hovvi");
1096 assertDoubleMetaphoneAlt("XRN", "Czerny");
1097 }
1098
1099 @Test
1100 public void testEmpty() {
1101 assertEquals(null, this.getStringEncoder().doubleMetaphone(null));
1102 assertEquals(null, this.getStringEncoder().doubleMetaphone(""));
1103 assertEquals(null, this.getStringEncoder().doubleMetaphone(" "));
1104 assertEquals(null, this.getStringEncoder().doubleMetaphone("\t\n\r "));
1105 }
1106
1107 /**
1108 * Test setting maximum length
1109 */
1110 @Test
1111 public void testSetMaxCodeLength() {
1112 final String value = "jumped";
1113
1114 final DoubleMetaphone doubleMetaphone = new DoubleMetaphone();
1115
1116 // Sanity check of default settings
1117 assertEquals("Default Max Code Length", 4, doubleMetaphone.getMaxCodeLen());
1118 assertEquals("Default Primary", "JMPT", doubleMetaphone.doubleMetaphone(value, false));
1119 assertEquals("Default Alternate", "AMPT", doubleMetaphone.doubleMetaphone(value, true));
1120
1121 // Check setting Max Code Length
1122 doubleMetaphone.setMaxCodeLen(3);
1123 assertEquals("Set Max Code Length", 3, doubleMetaphone.getMaxCodeLen());
1124 assertEquals("Max=3 Primary", "JMP", doubleMetaphone.doubleMetaphone(value, false));
1125 assertEquals("Max=3 Alternate", "AMP", doubleMetaphone.doubleMetaphone(value, true));
1126 }
1127
1128 @Test
1129 public void testIsDoubleMetaphoneEqualBasic() {
1130 final String[][] testFixture = new String[][] { { "Case", "case" }, {
1131 "CASE", "Case" }, {
1132 "caSe", "cAsE" }, {
1133 "cookie", "quick" }, {
1134 "quick", "cookie" }, {
1135 "Brian", "Bryan" }, {
1136 "Auto", "Otto" }, {
1137 "Steven", "Stefan" }, {
1138 "Philipowitz", "Filipowicz" }
1139 };
1140 doubleMetaphoneEqualTest(testFixture, false);
1141 doubleMetaphoneEqualTest(testFixture, true);
1142 }
1143
1144 /**
1145 * Example in the original article but failures in this Java impl:
1146 */
1147 @Test
1148 public void testIsDoubleMetaphoneEqualExtended1() {
1149 // String[][] testFixture = new String[][] { { "Smith", "Schmidt" }
1150 // };
1151 // doubleMetaphoneEqualTest(testFixture, false);
1152 // doubleMetaphoneEqualTest(testFixture, true);
1153 }
1154
1155 @Test
1156 public void testIsDoubleMetaphoneEqualExtended2() {
1157 final String[][] testFixture = new String[][] { { "Jablonski", "Yablonsky" }
1158 };
1159 //doubleMetaphoneEqualTest(testFixture, false);
1160 doubleMetaphoneEqualTest(testFixture, true);
1161 }
1162
1163 /**
1164 * Used to generate the MATCHES array and test possible matches from the
1165 * FIXTURE array.
1166 */
1167 @Test
1168 public void testIsDoubleMetaphoneEqualExtended3() {
1169 this.validateFixture(FIXTURE);
1170 final StringBuilder failures = new StringBuilder();
1171 final StringBuilder matches = new StringBuilder();
1172 final String cr = System.getProperty("line.separator");
1173 matches.append("private static final String[][] MATCHES = {" + cr);
1174 int failCount = 0;
1175 for (int i = 0; i < FIXTURE.length; i++) {
1176 final String name0 = FIXTURE[i][0];
1177 final String name1 = FIXTURE[i][1];
1178 final boolean match1 = this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1, false);
1179 final boolean match2 = this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1, true);
1180 if (match1 == false && match2 == false) {
1181 final String failMsg = "[" + i + "] " + name0 + " and " + name1 + cr;
1182 failures.append(failMsg);
1183 failCount++;
1184 } else {
1185 matches.append("{\"" + name0 + "\", \"" + name1 + "\"}," + cr);
1186 }
1187 }
1188 matches.append("};");
1189 // Turn on to print a new MATCH array
1190 //System.out.println(matches.toString());
1191 if (failCount > 0) {
1192 // Turn on to see which pairs do NOT match.
1193 // String msg = failures.toString();
1194 //fail(failCount + " failures out of " + FIXTURE.length + ". The
1195 // following could be made to match: " + cr + msg);
1196 }
1197 }
1198
1199 @Test
1200 public void testIsDoubleMetaphoneEqualWithMATCHES() {
1201 this.validateFixture(MATCHES);
1202 for (int i = 0; i < MATCHES.length; i++) {
1203 final String name0 = MATCHES[i][0];
1204 final String name1 = MATCHES[i][1];
1205 final boolean match1 = this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1, false);
1206 final boolean match2 = this.getStringEncoder().isDoubleMetaphoneEqual(name0, name1, true);
1207 if (match1 == false && match2 == false) {
1208 fail("Expected match [" + i + "] " + name0 + " and " + name1);
1209 }
1210 }
1211 }
1212
1213 @Test
1214 public void testIsDoubleMetaphoneNotEqual() {
1215 doubleMetaphoneNotEqualTest(false);
1216 doubleMetaphoneNotEqualTest(true);
1217 }
1218
1219 @Test
1220 public void testCCedilla() {
1221 assertTrue(this.getStringEncoder().isDoubleMetaphoneEqual("\u00e7", "S")); // c-cedilla
1222 }
1223
1224 @Test
1225 public void testNTilde() {
1226 assertTrue(this.getStringEncoder().isDoubleMetaphoneEqual("\u00f1", "N")); // n-tilde
1227 }
1228
1229 public void validateFixture(final String[][] pairs) {
1230 if (pairs.length == 0) {
1231 fail("Test fixture is empty");
1232 }
1233 for (int i = 0; i < pairs.length; i++) {
1234 if (pairs[i].length != 2) {
1235 fail("Error in test fixture in the data array at index " + i);
1236 }
1237 }
1238 }
1239 }