mapping-FoldToASCII.txt 80 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813
  1. # The ASF licenses this file to You under the Apache License, Version 2.0
  2. # (the "License"); you may not use this file except in compliance with
  3. # the License. You may obtain a copy of the License at
  4. #
  5. # http://www.apache.org/licenses/LICENSE-2.0
  6. #
  7. # Unless required by applicable law or agreed to in writing, software
  8. # distributed under the License is distributed on an "AS IS" BASIS,
  9. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  10. # See the License for the specific language governing permissions and
  11. # limitations under the License.
  12. # This map converts alphabetic, numeric, and symbolic Unicode characters
  13. # which are not in the first 127 ASCII characters (the "Basic Latin" Unicode
  14. # block) into their ASCII equivalents, if one exists.
  15. #
  16. # Characters from the following Unicode blocks are converted; however, only
  17. # those characters with reasonable ASCII alternatives are converted:
  18. #
  19. # - C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf
  20. # - Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf
  21. # - Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf
  22. # - Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf
  23. # - Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf
  24. # - Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf
  25. # - IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf
  26. # - Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf
  27. # - Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf
  28. # - General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf
  29. # - Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf
  30. # - Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf
  31. # - Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf
  32. # - Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf
  33. # - Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf
  34. # - Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf
  35. #
  36. # See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode
  37. #
  38. # The set of character conversions supported by this map is a superset of
  39. # those supported by the map represented by mapping-ISOLatin1Accent.txt.
  40. #
  41. # See the bottom of this file for the Perl script used to generate the contents
  42. # of this file (without this header) from ASCIIFoldingFilter.java.
  43. # Syntax:
  44. # "source" => "target"
  45. # "source".length() > 0 (source cannot be empty.)
  46. # "target".length() >= 0 (target can be empty.)
  47. # À [LATIN CAPITAL LETTER A WITH GRAVE]
  48. "\u00C0" => "A"
  49. # Á [LATIN CAPITAL LETTER A WITH ACUTE]
  50. "\u00C1" => "A"
  51. # Â [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
  52. "\u00C2" => "A"
  53. # Ã [LATIN CAPITAL LETTER A WITH TILDE]
  54. "\u00C3" => "A"
  55. # Ä [LATIN CAPITAL LETTER A WITH DIAERESIS]
  56. "\u00C4" => "A"
  57. # Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
  58. "\u00C5" => "A"
  59. # Ā [LATIN CAPITAL LETTER A WITH MACRON]
  60. "\u0100" => "A"
  61. # Ă [LATIN CAPITAL LETTER A WITH BREVE]
  62. "\u0102" => "A"
  63. # Ą [LATIN CAPITAL LETTER A WITH OGONEK]
  64. "\u0104" => "A"
  65. # Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
  66. "\u018F" => "A"
  67. # Ǎ [LATIN CAPITAL LETTER A WITH CARON]
  68. "\u01CD" => "A"
  69. # Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
  70. "\u01DE" => "A"
  71. # Ǡ [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
  72. "\u01E0" => "A"
  73. # Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
  74. "\u01FA" => "A"
  75. # Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
  76. "\u0200" => "A"
  77. # Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
  78. "\u0202" => "A"
  79. # Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE]
  80. "\u0226" => "A"
  81. # Ⱥ [LATIN CAPITAL LETTER A WITH STROKE]
  82. "\u023A" => "A"
  83. # ᴀ [LATIN LETTER SMALL CAPITAL A]
  84. "\u1D00" => "A"
  85. # Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW]
  86. "\u1E00" => "A"
  87. # Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW]
  88. "\u1EA0" => "A"
  89. # Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
  90. "\u1EA2" => "A"
  91. # Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
  92. "\u1EA4" => "A"
  93. # Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
  94. "\u1EA6" => "A"
  95. # Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
  96. "\u1EA8" => "A"
  97. # Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
  98. "\u1EAA" => "A"
  99. # Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
  100. "\u1EAC" => "A"
  101. # Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
  102. "\u1EAE" => "A"
  103. # Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
  104. "\u1EB0" => "A"
  105. # Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
  106. "\u1EB2" => "A"
  107. # Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
  108. "\u1EB4" => "A"
  109. # Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
  110. "\u1EB6" => "A"
  111. # Ⓐ [CIRCLED LATIN CAPITAL LETTER A]
  112. "\u24B6" => "A"
  113. # A [FULLWIDTH LATIN CAPITAL LETTER A]
  114. "\uFF21" => "A"
  115. # à [LATIN SMALL LETTER A WITH GRAVE]
  116. "\u00E0" => "a"
  117. # á [LATIN SMALL LETTER A WITH ACUTE]
  118. "\u00E1" => "a"
  119. # â [LATIN SMALL LETTER A WITH CIRCUMFLEX]
  120. "\u00E2" => "a"
  121. # ã [LATIN SMALL LETTER A WITH TILDE]
  122. "\u00E3" => "a"
  123. # ä [LATIN SMALL LETTER A WITH DIAERESIS]
  124. "\u00E4" => "a"
  125. # å [LATIN SMALL LETTER A WITH RING ABOVE]
  126. "\u00E5" => "a"
  127. # ā [LATIN SMALL LETTER A WITH MACRON]
  128. "\u0101" => "a"
  129. # ă [LATIN SMALL LETTER A WITH BREVE]
  130. "\u0103" => "a"
  131. # ą [LATIN SMALL LETTER A WITH OGONEK]
  132. "\u0105" => "a"
  133. # ǎ [LATIN SMALL LETTER A WITH CARON]
  134. "\u01CE" => "a"
  135. # ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
  136. "\u01DF" => "a"
  137. # ǡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
  138. "\u01E1" => "a"
  139. # ǻ [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
  140. "\u01FB" => "a"
  141. # ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
  142. "\u0201" => "a"
  143. # ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE]
  144. "\u0203" => "a"
  145. # ȧ [LATIN SMALL LETTER A WITH DOT ABOVE]
  146. "\u0227" => "a"
  147. # ɐ [LATIN SMALL LETTER TURNED A]
  148. "\u0250" => "a"
  149. # ə [LATIN SMALL LETTER SCHWA]
  150. "\u0259" => "a"
  151. # ɚ [LATIN SMALL LETTER SCHWA WITH HOOK]
  152. "\u025A" => "a"
  153. # ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
  154. "\u1D8F" => "a"
  155. # ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
  156. "\u1D95" => "a"
  157. # ạ [LATIN SMALL LETTER A WITH RING BELOW]
  158. "\u1E01" => "a"
  159. # ả [LATIN SMALL LETTER A WITH RIGHT HALF RING]
  160. "\u1E9A" => "a"
  161. # ạ [LATIN SMALL LETTER A WITH DOT BELOW]
  162. "\u1EA1" => "a"
  163. # ả [LATIN SMALL LETTER A WITH HOOK ABOVE]
  164. "\u1EA3" => "a"
  165. # ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
  166. "\u1EA5" => "a"
  167. # ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
  168. "\u1EA7" => "a"
  169. # ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
  170. "\u1EA9" => "a"
  171. # ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
  172. "\u1EAB" => "a"
  173. # ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
  174. "\u1EAD" => "a"
  175. # ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
  176. "\u1EAF" => "a"
  177. # ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
  178. "\u1EB1" => "a"
  179. # ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
  180. "\u1EB3" => "a"
  181. # ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE]
  182. "\u1EB5" => "a"
  183. # ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
  184. "\u1EB7" => "a"
  185. # ₐ [LATIN SUBSCRIPT SMALL LETTER A]
  186. "\u2090" => "a"
  187. # ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA]
  188. "\u2094" => "a"
  189. # ⓐ [CIRCLED LATIN SMALL LETTER A]
  190. "\u24D0" => "a"
  191. # ⱥ [LATIN SMALL LETTER A WITH STROKE]
  192. "\u2C65" => "a"
  193. # Ɐ [LATIN CAPITAL LETTER TURNED A]
  194. "\u2C6F" => "a"
  195. # a [FULLWIDTH LATIN SMALL LETTER A]
  196. "\uFF41" => "a"
  197. # Ꜳ [LATIN CAPITAL LETTER AA]
  198. "\uA732" => "AA"
  199. # Æ [LATIN CAPITAL LETTER AE]
  200. "\u00C6" => "AE"
  201. # Ǣ [LATIN CAPITAL LETTER AE WITH MACRON]
  202. "\u01E2" => "AE"
  203. # Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE]
  204. "\u01FC" => "AE"
  205. # ᴁ [LATIN LETTER SMALL CAPITAL AE]
  206. "\u1D01" => "AE"
  207. # Ꜵ [LATIN CAPITAL LETTER AO]
  208. "\uA734" => "AO"
  209. # Ꜷ [LATIN CAPITAL LETTER AU]
  210. "\uA736" => "AU"
  211. # Ꜹ [LATIN CAPITAL LETTER AV]
  212. "\uA738" => "AV"
  213. # Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR]
  214. "\uA73A" => "AV"
  215. # Ꜽ [LATIN CAPITAL LETTER AY]
  216. "\uA73C" => "AY"
  217. # ⒜ [PARENTHESIZED LATIN SMALL LETTER A]
  218. "\u249C" => "(a)"
  219. # ꜳ [LATIN SMALL LETTER AA]
  220. "\uA733" => "aa"
  221. # æ [LATIN SMALL LETTER AE]
  222. "\u00E6" => "ae"
  223. # ǣ [LATIN SMALL LETTER AE WITH MACRON]
  224. "\u01E3" => "ae"
  225. # ǽ [LATIN SMALL LETTER AE WITH ACUTE]
  226. "\u01FD" => "ae"
  227. # ᴂ [LATIN SMALL LETTER TURNED AE]
  228. "\u1D02" => "ae"
  229. # ꜵ [LATIN SMALL LETTER AO]
  230. "\uA735" => "ao"
  231. # ꜷ [LATIN SMALL LETTER AU]
  232. "\uA737" => "au"
  233. # ꜹ [LATIN SMALL LETTER AV]
  234. "\uA739" => "av"
  235. # ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR]
  236. "\uA73B" => "av"
  237. # ꜽ [LATIN SMALL LETTER AY]
  238. "\uA73D" => "ay"
  239. # Ɓ [LATIN CAPITAL LETTER B WITH HOOK]
  240. "\u0181" => "B"
  241. # Ƃ [LATIN CAPITAL LETTER B WITH TOPBAR]
  242. "\u0182" => "B"
  243. # Ƀ [LATIN CAPITAL LETTER B WITH STROKE]
  244. "\u0243" => "B"
  245. # ʙ [LATIN LETTER SMALL CAPITAL B]
  246. "\u0299" => "B"
  247. # ᴃ [LATIN LETTER SMALL CAPITAL BARRED B]
  248. "\u1D03" => "B"
  249. # Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE]
  250. "\u1E02" => "B"
  251. # Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW]
  252. "\u1E04" => "B"
  253. # Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW]
  254. "\u1E06" => "B"
  255. # Ⓑ [CIRCLED LATIN CAPITAL LETTER B]
  256. "\u24B7" => "B"
  257. # B [FULLWIDTH LATIN CAPITAL LETTER B]
  258. "\uFF22" => "B"
  259. # ƀ [LATIN SMALL LETTER B WITH STROKE]
  260. "\u0180" => "b"
  261. # ƃ [LATIN SMALL LETTER B WITH TOPBAR]
  262. "\u0183" => "b"
  263. # ɓ [LATIN SMALL LETTER B WITH HOOK]
  264. "\u0253" => "b"
  265. # ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE]
  266. "\u1D6C" => "b"
  267. # ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK]
  268. "\u1D80" => "b"
  269. # ḃ [LATIN SMALL LETTER B WITH DOT ABOVE]
  270. "\u1E03" => "b"
  271. # ḅ [LATIN SMALL LETTER B WITH DOT BELOW]
  272. "\u1E05" => "b"
  273. # ḇ [LATIN SMALL LETTER B WITH LINE BELOW]
  274. "\u1E07" => "b"
  275. # ⓑ [CIRCLED LATIN SMALL LETTER B]
  276. "\u24D1" => "b"
  277. # b [FULLWIDTH LATIN SMALL LETTER B]
  278. "\uFF42" => "b"
  279. # ⒝ [PARENTHESIZED LATIN SMALL LETTER B]
  280. "\u249D" => "(b)"
  281. # Ç [LATIN CAPITAL LETTER C WITH CEDILLA]
  282. "\u00C7" => "C"
  283. # Ć [LATIN CAPITAL LETTER C WITH ACUTE]
  284. "\u0106" => "C"
  285. # Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX]
  286. "\u0108" => "C"
  287. # Ċ [LATIN CAPITAL LETTER C WITH DOT ABOVE]
  288. "\u010A" => "C"
  289. # Č [LATIN CAPITAL LETTER C WITH CARON]
  290. "\u010C" => "C"
  291. # Ƈ [LATIN CAPITAL LETTER C WITH HOOK]
  292. "\u0187" => "C"
  293. # Ȼ [LATIN CAPITAL LETTER C WITH STROKE]
  294. "\u023B" => "C"
  295. # ʗ [LATIN LETTER STRETCHED C]
  296. "\u0297" => "C"
  297. # ᴄ [LATIN LETTER SMALL CAPITAL C]
  298. "\u1D04" => "C"
  299. # Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE]
  300. "\u1E08" => "C"
  301. # Ⓒ [CIRCLED LATIN CAPITAL LETTER C]
  302. "\u24B8" => "C"
  303. # C [FULLWIDTH LATIN CAPITAL LETTER C]
  304. "\uFF23" => "C"
  305. # ç [LATIN SMALL LETTER C WITH CEDILLA]
  306. "\u00E7" => "c"
  307. # ć [LATIN SMALL LETTER C WITH ACUTE]
  308. "\u0107" => "c"
  309. # ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX]
  310. "\u0109" => "c"
  311. # ċ [LATIN SMALL LETTER C WITH DOT ABOVE]
  312. "\u010B" => "c"
  313. # č [LATIN SMALL LETTER C WITH CARON]
  314. "\u010D" => "c"
  315. # ƈ [LATIN SMALL LETTER C WITH HOOK]
  316. "\u0188" => "c"
  317. # ȼ [LATIN SMALL LETTER C WITH STROKE]
  318. "\u023C" => "c"
  319. # ɕ [LATIN SMALL LETTER C WITH CURL]
  320. "\u0255" => "c"
  321. # ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE]
  322. "\u1E09" => "c"
  323. # ↄ [LATIN SMALL LETTER REVERSED C]
  324. "\u2184" => "c"
  325. # ⓒ [CIRCLED LATIN SMALL LETTER C]
  326. "\u24D2" => "c"
  327. # Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT]
  328. "\uA73E" => "c"
  329. # ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT]
  330. "\uA73F" => "c"
  331. # c [FULLWIDTH LATIN SMALL LETTER C]
  332. "\uFF43" => "c"
  333. # ⒞ [PARENTHESIZED LATIN SMALL LETTER C]
  334. "\u249E" => "(c)"
  335. # Ð [LATIN CAPITAL LETTER ETH]
  336. "\u00D0" => "D"
  337. # Ď [LATIN CAPITAL LETTER D WITH CARON]
  338. "\u010E" => "D"
  339. # Đ [LATIN CAPITAL LETTER D WITH STROKE]
  340. "\u0110" => "D"
  341. # Ɖ [LATIN CAPITAL LETTER AFRICAN D]
  342. "\u0189" => "D"
  343. # Ɗ [LATIN CAPITAL LETTER D WITH HOOK]
  344. "\u018A" => "D"
  345. # Ƌ [LATIN CAPITAL LETTER D WITH TOPBAR]
  346. "\u018B" => "D"
  347. # ᴅ [LATIN LETTER SMALL CAPITAL D]
  348. "\u1D05" => "D"
  349. # ᴆ [LATIN LETTER SMALL CAPITAL ETH]
  350. "\u1D06" => "D"
  351. # Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE]
  352. "\u1E0A" => "D"
  353. # Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW]
  354. "\u1E0C" => "D"
  355. # Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW]
  356. "\u1E0E" => "D"
  357. # Ḑ [LATIN CAPITAL LETTER D WITH CEDILLA]
  358. "\u1E10" => "D"
  359. # Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW]
  360. "\u1E12" => "D"
  361. # Ⓓ [CIRCLED LATIN CAPITAL LETTER D]
  362. "\u24B9" => "D"
  363. # Ꝺ [LATIN CAPITAL LETTER INSULAR D]
  364. "\uA779" => "D"
  365. # D [FULLWIDTH LATIN CAPITAL LETTER D]
  366. "\uFF24" => "D"
  367. # ð [LATIN SMALL LETTER ETH]
  368. "\u00F0" => "d"
  369. # ď [LATIN SMALL LETTER D WITH CARON]
  370. "\u010F" => "d"
  371. # đ [LATIN SMALL LETTER D WITH STROKE]
  372. "\u0111" => "d"
  373. # ƌ [LATIN SMALL LETTER D WITH TOPBAR]
  374. "\u018C" => "d"
  375. # ȡ [LATIN SMALL LETTER D WITH CURL]
  376. "\u0221" => "d"
  377. # ɖ [LATIN SMALL LETTER D WITH TAIL]
  378. "\u0256" => "d"
  379. # ɗ [LATIN SMALL LETTER D WITH HOOK]
  380. "\u0257" => "d"
  381. # ᵭ [LATIN SMALL LETTER D WITH MIDDLE TILDE]
  382. "\u1D6D" => "d"
  383. # ᶁ [LATIN SMALL LETTER D WITH PALATAL HOOK]
  384. "\u1D81" => "d"
  385. # ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL]
  386. "\u1D91" => "d"
  387. # ḋ [LATIN SMALL LETTER D WITH DOT ABOVE]
  388. "\u1E0B" => "d"
  389. # ḍ [LATIN SMALL LETTER D WITH DOT BELOW]
  390. "\u1E0D" => "d"
  391. # ḏ [LATIN SMALL LETTER D WITH LINE BELOW]
  392. "\u1E0F" => "d"
  393. # ḑ [LATIN SMALL LETTER D WITH CEDILLA]
  394. "\u1E11" => "d"
  395. # ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW]
  396. "\u1E13" => "d"
  397. # ⓓ [CIRCLED LATIN SMALL LETTER D]
  398. "\u24D3" => "d"
  399. # ꝺ [LATIN SMALL LETTER INSULAR D]
  400. "\uA77A" => "d"
  401. # d [FULLWIDTH LATIN SMALL LETTER D]
  402. "\uFF44" => "d"
  403. # DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
  404. "\u01C4" => "DZ"
  405. # DZ [LATIN CAPITAL LETTER DZ]
  406. "\u01F1" => "DZ"
  407. # Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
  408. "\u01C5" => "Dz"
  409. # Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
  410. "\u01F2" => "Dz"
  411. # ⒟ [PARENTHESIZED LATIN SMALL LETTER D]
  412. "\u249F" => "(d)"
  413. # ȸ [LATIN SMALL LETTER DB DIGRAPH]
  414. "\u0238" => "db"
  415. # dž [LATIN SMALL LETTER DZ WITH CARON]
  416. "\u01C6" => "dz"
  417. # dz [LATIN SMALL LETTER DZ]
  418. "\u01F3" => "dz"
  419. # ʣ [LATIN SMALL LETTER DZ DIGRAPH]
  420. "\u02A3" => "dz"
  421. # ʥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL]
  422. "\u02A5" => "dz"
  423. # È [LATIN CAPITAL LETTER E WITH GRAVE]
  424. "\u00C8" => "E"
  425. # É [LATIN CAPITAL LETTER E WITH ACUTE]
  426. "\u00C9" => "E"
  427. # Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX]
  428. "\u00CA" => "E"
  429. # Ë [LATIN CAPITAL LETTER E WITH DIAERESIS]
  430. "\u00CB" => "E"
  431. # Ē [LATIN CAPITAL LETTER E WITH MACRON]
  432. "\u0112" => "E"
  433. # Ĕ [LATIN CAPITAL LETTER E WITH BREVE]
  434. "\u0114" => "E"
  435. # Ė [LATIN CAPITAL LETTER E WITH DOT ABOVE]
  436. "\u0116" => "E"
  437. # Ę [LATIN CAPITAL LETTER E WITH OGONEK]
  438. "\u0118" => "E"
  439. # Ě [LATIN CAPITAL LETTER E WITH CARON]
  440. "\u011A" => "E"
  441. # Ǝ [LATIN CAPITAL LETTER REVERSED E]
  442. "\u018E" => "E"
  443. # Ɛ [LATIN CAPITAL LETTER OPEN E]
  444. "\u0190" => "E"
  445. # Ȅ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE]
  446. "\u0204" => "E"
  447. # Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE]
  448. "\u0206" => "E"
  449. # Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA]
  450. "\u0228" => "E"
  451. # Ɇ [LATIN CAPITAL LETTER E WITH STROKE]
  452. "\u0246" => "E"
  453. # ᴇ [LATIN LETTER SMALL CAPITAL E]
  454. "\u1D07" => "E"
  455. # Ḕ [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE]
  456. "\u1E14" => "E"
  457. # Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE]
  458. "\u1E16" => "E"
  459. # Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW]
  460. "\u1E18" => "E"
  461. # Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW]
  462. "\u1E1A" => "E"
  463. # Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE]
  464. "\u1E1C" => "E"
  465. # Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW]
  466. "\u1EB8" => "E"
  467. # Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE]
  468. "\u1EBA" => "E"
  469. # Ẽ [LATIN CAPITAL LETTER E WITH TILDE]
  470. "\u1EBC" => "E"
  471. # Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE]
  472. "\u1EBE" => "E"
  473. # Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE]
  474. "\u1EC0" => "E"
  475. # Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
  476. "\u1EC2" => "E"
  477. # Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE]
  478. "\u1EC4" => "E"
  479. # Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
  480. "\u1EC6" => "E"
  481. # Ⓔ [CIRCLED LATIN CAPITAL LETTER E]
  482. "\u24BA" => "E"
  483. # ⱻ [LATIN LETTER SMALL CAPITAL TURNED E]
  484. "\u2C7B" => "E"
  485. # E [FULLWIDTH LATIN CAPITAL LETTER E]
  486. "\uFF25" => "E"
  487. # è [LATIN SMALL LETTER E WITH GRAVE]
  488. "\u00E8" => "e"
  489. # é [LATIN SMALL LETTER E WITH ACUTE]
  490. "\u00E9" => "e"
  491. # ê [LATIN SMALL LETTER E WITH CIRCUMFLEX]
  492. "\u00EA" => "e"
  493. # ë [LATIN SMALL LETTER E WITH DIAERESIS]
  494. "\u00EB" => "e"
  495. # ē [LATIN SMALL LETTER E WITH MACRON]
  496. "\u0113" => "e"
  497. # ĕ [LATIN SMALL LETTER E WITH BREVE]
  498. "\u0115" => "e"
  499. # ė [LATIN SMALL LETTER E WITH DOT ABOVE]
  500. "\u0117" => "e"
  501. # ę [LATIN SMALL LETTER E WITH OGONEK]
  502. "\u0119" => "e"
  503. # ě [LATIN SMALL LETTER E WITH CARON]
  504. "\u011B" => "e"
  505. # ǝ [LATIN SMALL LETTER TURNED E]
  506. "\u01DD" => "e"
  507. # ȅ [LATIN SMALL LETTER E WITH DOUBLE GRAVE]
  508. "\u0205" => "e"
  509. # ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE]
  510. "\u0207" => "e"
  511. # ȩ [LATIN SMALL LETTER E WITH CEDILLA]
  512. "\u0229" => "e"
  513. # ɇ [LATIN SMALL LETTER E WITH STROKE]
  514. "\u0247" => "e"
  515. # ɘ [LATIN SMALL LETTER REVERSED E]
  516. "\u0258" => "e"
  517. # ɛ [LATIN SMALL LETTER OPEN E]
  518. "\u025B" => "e"
  519. # ɜ [LATIN SMALL LETTER REVERSED OPEN E]
  520. "\u025C" => "e"
  521. # ɝ [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK]
  522. "\u025D" => "e"
  523. # ɞ [LATIN SMALL LETTER CLOSED REVERSED OPEN E]
  524. "\u025E" => "e"
  525. # ʚ [LATIN SMALL LETTER CLOSED OPEN E]
  526. "\u029A" => "e"
  527. # ᴈ [LATIN SMALL LETTER TURNED OPEN E]
  528. "\u1D08" => "e"
  529. # ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK]
  530. "\u1D92" => "e"
  531. # ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK]
  532. "\u1D93" => "e"
  533. # ᶔ [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK]
  534. "\u1D94" => "e"
  535. # ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE]
  536. "\u1E15" => "e"
  537. # ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE]
  538. "\u1E17" => "e"
  539. # ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW]
  540. "\u1E19" => "e"
  541. # ḛ [LATIN SMALL LETTER E WITH TILDE BELOW]
  542. "\u1E1B" => "e"
  543. # ḝ [LATIN SMALL LETTER E WITH CEDILLA AND BREVE]
  544. "\u1E1D" => "e"
  545. # ẹ [LATIN SMALL LETTER E WITH DOT BELOW]
  546. "\u1EB9" => "e"
  547. # ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE]
  548. "\u1EBB" => "e"
  549. # ẽ [LATIN SMALL LETTER E WITH TILDE]
  550. "\u1EBD" => "e"
  551. # ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE]
  552. "\u1EBF" => "e"
  553. # ề [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE]
  554. "\u1EC1" => "e"
  555. # ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
  556. "\u1EC3" => "e"
  557. # ễ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE]
  558. "\u1EC5" => "e"
  559. # ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
  560. "\u1EC7" => "e"
  561. # ₑ [LATIN SUBSCRIPT SMALL LETTER E]
  562. "\u2091" => "e"
  563. # ⓔ [CIRCLED LATIN SMALL LETTER E]
  564. "\u24D4" => "e"
  565. # ⱸ [LATIN SMALL LETTER E WITH NOTCH]
  566. "\u2C78" => "e"
  567. # e [FULLWIDTH LATIN SMALL LETTER E]
  568. "\uFF45" => "e"
  569. # ⒠ [PARENTHESIZED LATIN SMALL LETTER E]
  570. "\u24A0" => "(e)"
  571. # Ƒ [LATIN CAPITAL LETTER F WITH HOOK]
  572. "\u0191" => "F"
  573. # Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE]
  574. "\u1E1E" => "F"
  575. # Ⓕ [CIRCLED LATIN CAPITAL LETTER F]
  576. "\u24BB" => "F"
  577. # ꜰ [LATIN LETTER SMALL CAPITAL F]
  578. "\uA730" => "F"
  579. # Ꝼ [LATIN CAPITAL LETTER INSULAR F]
  580. "\uA77B" => "F"
  581. # ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F]
  582. "\uA7FB" => "F"
  583. # F [FULLWIDTH LATIN CAPITAL LETTER F]
  584. "\uFF26" => "F"
  585. # ƒ [LATIN SMALL LETTER F WITH HOOK]
  586. "\u0192" => "f"
  587. # ᵮ [LATIN SMALL LETTER F WITH MIDDLE TILDE]
  588. "\u1D6E" => "f"
  589. # ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK]
  590. "\u1D82" => "f"
  591. # ḟ [LATIN SMALL LETTER F WITH DOT ABOVE]
  592. "\u1E1F" => "f"
  593. # ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
  594. "\u1E9B" => "f"
  595. # ⓕ [CIRCLED LATIN SMALL LETTER F]
  596. "\u24D5" => "f"
  597. # ꝼ [LATIN SMALL LETTER INSULAR F]
  598. "\uA77C" => "f"
  599. # f [FULLWIDTH LATIN SMALL LETTER F]
  600. "\uFF46" => "f"
  601. # ⒡ [PARENTHESIZED LATIN SMALL LETTER F]
  602. "\u24A1" => "(f)"
  603. # ff [LATIN SMALL LIGATURE FF]
  604. "\uFB00" => "ff"
  605. # ffi [LATIN SMALL LIGATURE FFI]
  606. "\uFB03" => "ffi"
  607. # ffl [LATIN SMALL LIGATURE FFL]
  608. "\uFB04" => "ffl"
  609. # fi [LATIN SMALL LIGATURE FI]
  610. "\uFB01" => "fi"
  611. # fl [LATIN SMALL LIGATURE FL]
  612. "\uFB02" => "fl"
  613. # Ĝ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX]
  614. "\u011C" => "G"
  615. # Ğ [LATIN CAPITAL LETTER G WITH BREVE]
  616. "\u011E" => "G"
  617. # Ġ [LATIN CAPITAL LETTER G WITH DOT ABOVE]
  618. "\u0120" => "G"
  619. # Ģ [LATIN CAPITAL LETTER G WITH CEDILLA]
  620. "\u0122" => "G"
  621. # Ɠ [LATIN CAPITAL LETTER G WITH HOOK]
  622. "\u0193" => "G"
  623. # Ǥ [LATIN CAPITAL LETTER G WITH STROKE]
  624. "\u01E4" => "G"
  625. # ǥ [LATIN SMALL LETTER G WITH STROKE]
  626. "\u01E5" => "G"
  627. # Ǧ [LATIN CAPITAL LETTER G WITH CARON]
  628. "\u01E6" => "G"
  629. # ǧ [LATIN SMALL LETTER G WITH CARON]
  630. "\u01E7" => "G"
  631. # Ǵ [LATIN CAPITAL LETTER G WITH ACUTE]
  632. "\u01F4" => "G"
  633. # ɢ [LATIN LETTER SMALL CAPITAL G]
  634. "\u0262" => "G"
  635. # ʛ [LATIN LETTER SMALL CAPITAL G WITH HOOK]
  636. "\u029B" => "G"
  637. # Ḡ [LATIN CAPITAL LETTER G WITH MACRON]
  638. "\u1E20" => "G"
  639. # Ⓖ [CIRCLED LATIN CAPITAL LETTER G]
  640. "\u24BC" => "G"
  641. # Ᵹ [LATIN CAPITAL LETTER INSULAR G]
  642. "\uA77D" => "G"
  643. # Ꝿ [LATIN CAPITAL LETTER TURNED INSULAR G]
  644. "\uA77E" => "G"
  645. # G [FULLWIDTH LATIN CAPITAL LETTER G]
  646. "\uFF27" => "G"
  647. # ĝ [LATIN SMALL LETTER G WITH CIRCUMFLEX]
  648. "\u011D" => "g"
  649. # ğ [LATIN SMALL LETTER G WITH BREVE]
  650. "\u011F" => "g"
  651. # ġ [LATIN SMALL LETTER G WITH DOT ABOVE]
  652. "\u0121" => "g"
  653. # ģ [LATIN SMALL LETTER G WITH CEDILLA]
  654. "\u0123" => "g"
  655. # ǵ [LATIN SMALL LETTER G WITH ACUTE]
  656. "\u01F5" => "g"
  657. # ɠ [LATIN SMALL LETTER G WITH HOOK]
  658. "\u0260" => "g"
  659. # ɡ [LATIN SMALL LETTER SCRIPT G]
  660. "\u0261" => "g"
  661. # ᵷ [LATIN SMALL LETTER TURNED G]
  662. "\u1D77" => "g"
  663. # ᵹ [LATIN SMALL LETTER INSULAR G]
  664. "\u1D79" => "g"
  665. # ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK]
  666. "\u1D83" => "g"
  667. # ḡ [LATIN SMALL LETTER G WITH MACRON]
  668. "\u1E21" => "g"
  669. # ⓖ [CIRCLED LATIN SMALL LETTER G]
  670. "\u24D6" => "g"
  671. # ꝿ [LATIN SMALL LETTER TURNED INSULAR G]
  672. "\uA77F" => "g"
  673. # g [FULLWIDTH LATIN SMALL LETTER G]
  674. "\uFF47" => "g"
  675. # ⒢ [PARENTHESIZED LATIN SMALL LETTER G]
  676. "\u24A2" => "(g)"
  677. # Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX]
  678. "\u0124" => "H"
  679. # Ħ [LATIN CAPITAL LETTER H WITH STROKE]
  680. "\u0126" => "H"
  681. # Ȟ [LATIN CAPITAL LETTER H WITH CARON]
  682. "\u021E" => "H"
  683. # ʜ [LATIN LETTER SMALL CAPITAL H]
  684. "\u029C" => "H"
  685. # Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE]
  686. "\u1E22" => "H"
  687. # Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW]
  688. "\u1E24" => "H"
  689. # Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS]
  690. "\u1E26" => "H"
  691. # Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA]
  692. "\u1E28" => "H"
  693. # Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW]
  694. "\u1E2A" => "H"
  695. # Ⓗ [CIRCLED LATIN CAPITAL LETTER H]
  696. "\u24BD" => "H"
  697. # Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER]
  698. "\u2C67" => "H"
  699. # Ⱶ [LATIN CAPITAL LETTER HALF H]
  700. "\u2C75" => "H"
  701. # H [FULLWIDTH LATIN CAPITAL LETTER H]
  702. "\uFF28" => "H"
  703. # ĥ [LATIN SMALL LETTER H WITH CIRCUMFLEX]
  704. "\u0125" => "h"
  705. # ħ [LATIN SMALL LETTER H WITH STROKE]
  706. "\u0127" => "h"
  707. # ȟ [LATIN SMALL LETTER H WITH CARON]
  708. "\u021F" => "h"
  709. # ɥ [LATIN SMALL LETTER TURNED H]
  710. "\u0265" => "h"
  711. # ɦ [LATIN SMALL LETTER H WITH HOOK]
  712. "\u0266" => "h"
  713. # ʮ [LATIN SMALL LETTER TURNED H WITH FISHHOOK]
  714. "\u02AE" => "h"
  715. # ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL]
  716. "\u02AF" => "h"
  717. # ḣ [LATIN SMALL LETTER H WITH DOT ABOVE]
  718. "\u1E23" => "h"
  719. # ḥ [LATIN SMALL LETTER H WITH DOT BELOW]
  720. "\u1E25" => "h"
  721. # ḧ [LATIN SMALL LETTER H WITH DIAERESIS]
  722. "\u1E27" => "h"
  723. # ḩ [LATIN SMALL LETTER H WITH CEDILLA]
  724. "\u1E29" => "h"
  725. # ḫ [LATIN SMALL LETTER H WITH BREVE BELOW]
  726. "\u1E2B" => "h"
  727. # ẖ [LATIN SMALL LETTER H WITH LINE BELOW]
  728. "\u1E96" => "h"
  729. # ⓗ [CIRCLED LATIN SMALL LETTER H]
  730. "\u24D7" => "h"
  731. # ⱨ [LATIN SMALL LETTER H WITH DESCENDER]
  732. "\u2C68" => "h"
  733. # ⱶ [LATIN SMALL LETTER HALF H]
  734. "\u2C76" => "h"
  735. # h [FULLWIDTH LATIN SMALL LETTER H]
  736. "\uFF48" => "h"
  737. # Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR]
  738. "\u01F6" => "HV"
  739. # ⒣ [PARENTHESIZED LATIN SMALL LETTER H]
  740. "\u24A3" => "(h)"
  741. # ƕ [LATIN SMALL LETTER HV]
  742. "\u0195" => "hv"
  743. # Ì [LATIN CAPITAL LETTER I WITH GRAVE]
  744. "\u00CC" => "I"
  745. # Í [LATIN CAPITAL LETTER I WITH ACUTE]
  746. "\u00CD" => "I"
  747. # Î [LATIN CAPITAL LETTER I WITH CIRCUMFLEX]
  748. "\u00CE" => "I"
  749. # Ï [LATIN CAPITAL LETTER I WITH DIAERESIS]
  750. "\u00CF" => "I"
  751. # Ĩ [LATIN CAPITAL LETTER I WITH TILDE]
  752. "\u0128" => "I"
  753. # Ī [LATIN CAPITAL LETTER I WITH MACRON]
  754. "\u012A" => "I"
  755. # Ĭ [LATIN CAPITAL LETTER I WITH BREVE]
  756. "\u012C" => "I"
  757. # Į [LATIN CAPITAL LETTER I WITH OGONEK]
  758. "\u012E" => "I"
  759. # İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
  760. "\u0130" => "I"
  761. # Ɩ [LATIN CAPITAL LETTER IOTA]
  762. "\u0196" => "I"
  763. # Ɨ [LATIN CAPITAL LETTER I WITH STROKE]
  764. "\u0197" => "I"
  765. # Ǐ [LATIN CAPITAL LETTER I WITH CARON]
  766. "\u01CF" => "I"
  767. # Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE]
  768. "\u0208" => "I"
  769. # Ȋ [LATIN CAPITAL LETTER I WITH INVERTED BREVE]
  770. "\u020A" => "I"
  771. # ɪ [LATIN LETTER SMALL CAPITAL I]
  772. "\u026A" => "I"
  773. # ᵻ [LATIN SMALL CAPITAL LETTER I WITH STROKE]
  774. "\u1D7B" => "I"
  775. # Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW]
  776. "\u1E2C" => "I"
  777. # Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE]
  778. "\u1E2E" => "I"
  779. # Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE]
  780. "\u1EC8" => "I"
  781. # Ị [LATIN CAPITAL LETTER I WITH DOT BELOW]
  782. "\u1ECA" => "I"
  783. # Ⓘ [CIRCLED LATIN CAPITAL LETTER I]
  784. "\u24BE" => "I"
  785. # ꟾ [LATIN EPIGRAPHIC LETTER I LONGA]
  786. "\uA7FE" => "I"
  787. # I [FULLWIDTH LATIN CAPITAL LETTER I]
  788. "\uFF29" => "I"
  789. # ì [LATIN SMALL LETTER I WITH GRAVE]
  790. "\u00EC" => "i"
  791. # í [LATIN SMALL LETTER I WITH ACUTE]
  792. "\u00ED" => "i"
  793. # î [LATIN SMALL LETTER I WITH CIRCUMFLEX]
  794. "\u00EE" => "i"
  795. # ï [LATIN SMALL LETTER I WITH DIAERESIS]
  796. "\u00EF" => "i"
  797. # ĩ [LATIN SMALL LETTER I WITH TILDE]
  798. "\u0129" => "i"
  799. # ī [LATIN SMALL LETTER I WITH MACRON]
  800. "\u012B" => "i"
  801. # ĭ [LATIN SMALL LETTER I WITH BREVE]
  802. "\u012D" => "i"
  803. # į [LATIN SMALL LETTER I WITH OGONEK]
  804. "\u012F" => "i"
  805. # ı [LATIN SMALL LETTER DOTLESS I]
  806. "\u0131" => "i"
  807. # ǐ [LATIN SMALL LETTER I WITH CARON]
  808. "\u01D0" => "i"
  809. # ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE]
  810. "\u0209" => "i"
  811. # ȋ [LATIN SMALL LETTER I WITH INVERTED BREVE]
  812. "\u020B" => "i"
  813. # ɨ [LATIN SMALL LETTER I WITH STROKE]
  814. "\u0268" => "i"
  815. # ᴉ [LATIN SMALL LETTER TURNED I]
  816. "\u1D09" => "i"
  817. # ᵢ [LATIN SUBSCRIPT SMALL LETTER I]
  818. "\u1D62" => "i"
  819. # ᵼ [LATIN SMALL LETTER IOTA WITH STROKE]
  820. "\u1D7C" => "i"
  821. # ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK]
  822. "\u1D96" => "i"
  823. # ḭ [LATIN SMALL LETTER I WITH TILDE BELOW]
  824. "\u1E2D" => "i"
  825. # ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE]
  826. "\u1E2F" => "i"
  827. # ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE]
  828. "\u1EC9" => "i"
  829. # ị [LATIN SMALL LETTER I WITH DOT BELOW]
  830. "\u1ECB" => "i"
  831. # ⁱ [SUPERSCRIPT LATIN SMALL LETTER I]
  832. "\u2071" => "i"
  833. # ⓘ [CIRCLED LATIN SMALL LETTER I]
  834. "\u24D8" => "i"
  835. # i [FULLWIDTH LATIN SMALL LETTER I]
  836. "\uFF49" => "i"
  837. # IJ [LATIN CAPITAL LIGATURE IJ]
  838. "\u0132" => "IJ"
  839. # ⒤ [PARENTHESIZED LATIN SMALL LETTER I]
  840. "\u24A4" => "(i)"
  841. # ij [LATIN SMALL LIGATURE IJ]
  842. "\u0133" => "ij"
  843. # Ĵ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX]
  844. "\u0134" => "J"
  845. # Ɉ [LATIN CAPITAL LETTER J WITH STROKE]
  846. "\u0248" => "J"
  847. # ᴊ [LATIN LETTER SMALL CAPITAL J]
  848. "\u1D0A" => "J"
  849. # Ⓙ [CIRCLED LATIN CAPITAL LETTER J]
  850. "\u24BF" => "J"
  851. # J [FULLWIDTH LATIN CAPITAL LETTER J]
  852. "\uFF2A" => "J"
  853. # ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX]
  854. "\u0135" => "j"
  855. # ǰ [LATIN SMALL LETTER J WITH CARON]
  856. "\u01F0" => "j"
  857. # ȷ [LATIN SMALL LETTER DOTLESS J]
  858. "\u0237" => "j"
  859. # ɉ [LATIN SMALL LETTER J WITH STROKE]
  860. "\u0249" => "j"
  861. # ɟ [LATIN SMALL LETTER DOTLESS J WITH STROKE]
  862. "\u025F" => "j"
  863. # ʄ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK]
  864. "\u0284" => "j"
  865. # ʝ [LATIN SMALL LETTER J WITH CROSSED-TAIL]
  866. "\u029D" => "j"
  867. # ⓙ [CIRCLED LATIN SMALL LETTER J]
  868. "\u24D9" => "j"
  869. # ⱼ [LATIN SUBSCRIPT SMALL LETTER J]
  870. "\u2C7C" => "j"
  871. # j [FULLWIDTH LATIN SMALL LETTER J]
  872. "\uFF4A" => "j"
  873. # ⒥ [PARENTHESIZED LATIN SMALL LETTER J]
  874. "\u24A5" => "(j)"
  875. # Ķ [LATIN CAPITAL LETTER K WITH CEDILLA]
  876. "\u0136" => "K"
  877. # Ƙ [LATIN CAPITAL LETTER K WITH HOOK]
  878. "\u0198" => "K"
  879. # Ǩ [LATIN CAPITAL LETTER K WITH CARON]
  880. "\u01E8" => "K"
  881. # ᴋ [LATIN LETTER SMALL CAPITAL K]
  882. "\u1D0B" => "K"
  883. # Ḱ [LATIN CAPITAL LETTER K WITH ACUTE]
  884. "\u1E30" => "K"
  885. # Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW]
  886. "\u1E32" => "K"
  887. # Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW]
  888. "\u1E34" => "K"
  889. # Ⓚ [CIRCLED LATIN CAPITAL LETTER K]
  890. "\u24C0" => "K"
  891. # Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER]
  892. "\u2C69" => "K"
  893. # Ꝁ [LATIN CAPITAL LETTER K WITH STROKE]
  894. "\uA740" => "K"
  895. # Ꝃ [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE]
  896. "\uA742" => "K"
  897. # Ꝅ [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE]
  898. "\uA744" => "K"
  899. # K [FULLWIDTH LATIN CAPITAL LETTER K]
  900. "\uFF2B" => "K"
  901. # ķ [LATIN SMALL LETTER K WITH CEDILLA]
  902. "\u0137" => "k"
  903. # ƙ [LATIN SMALL LETTER K WITH HOOK]
  904. "\u0199" => "k"
  905. # ǩ [LATIN SMALL LETTER K WITH CARON]
  906. "\u01E9" => "k"
  907. # ʞ [LATIN SMALL LETTER TURNED K]
  908. "\u029E" => "k"
  909. # ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK]
  910. "\u1D84" => "k"
  911. # ḱ [LATIN SMALL LETTER K WITH ACUTE]
  912. "\u1E31" => "k"
  913. # ḳ [LATIN SMALL LETTER K WITH DOT BELOW]
  914. "\u1E33" => "k"
  915. # ḵ [LATIN SMALL LETTER K WITH LINE BELOW]
  916. "\u1E35" => "k"
  917. # ⓚ [CIRCLED LATIN SMALL LETTER K]
  918. "\u24DA" => "k"
  919. # ⱪ [LATIN SMALL LETTER K WITH DESCENDER]
  920. "\u2C6A" => "k"
  921. # ꝁ [LATIN SMALL LETTER K WITH STROKE]
  922. "\uA741" => "k"
  923. # ꝃ [LATIN SMALL LETTER K WITH DIAGONAL STROKE]
  924. "\uA743" => "k"
  925. # ꝅ [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE]
  926. "\uA745" => "k"
  927. # k [FULLWIDTH LATIN SMALL LETTER K]
  928. "\uFF4B" => "k"
  929. # ⒦ [PARENTHESIZED LATIN SMALL LETTER K]
  930. "\u24A6" => "(k)"
  931. # Ĺ [LATIN CAPITAL LETTER L WITH ACUTE]
  932. "\u0139" => "L"
  933. # Ļ [LATIN CAPITAL LETTER L WITH CEDILLA]
  934. "\u013B" => "L"
  935. # Ľ [LATIN CAPITAL LETTER L WITH CARON]
  936. "\u013D" => "L"
  937. # Ŀ [LATIN CAPITAL LETTER L WITH MIDDLE DOT]
  938. "\u013F" => "L"
  939. # Ł [LATIN CAPITAL LETTER L WITH STROKE]
  940. "\u0141" => "L"
  941. # Ƚ [LATIN CAPITAL LETTER L WITH BAR]
  942. "\u023D" => "L"
  943. # ʟ [LATIN LETTER SMALL CAPITAL L]
  944. "\u029F" => "L"
  945. # ᴌ [LATIN LETTER SMALL CAPITAL L WITH STROKE]
  946. "\u1D0C" => "L"
  947. # Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW]
  948. "\u1E36" => "L"
  949. # Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON]
  950. "\u1E38" => "L"
  951. # Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW]
  952. "\u1E3A" => "L"
  953. # Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW]
  954. "\u1E3C" => "L"
  955. # Ⓛ [CIRCLED LATIN CAPITAL LETTER L]
  956. "\u24C1" => "L"
  957. # Ⱡ [LATIN CAPITAL LETTER L WITH DOUBLE BAR]
  958. "\u2C60" => "L"
  959. # Ɫ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE]
  960. "\u2C62" => "L"
  961. # Ꝇ [LATIN CAPITAL LETTER BROKEN L]
  962. "\uA746" => "L"
  963. # Ꝉ [LATIN CAPITAL LETTER L WITH HIGH STROKE]
  964. "\uA748" => "L"
  965. # Ꞁ [LATIN CAPITAL LETTER TURNED L]
  966. "\uA780" => "L"
  967. # L [FULLWIDTH LATIN CAPITAL LETTER L]
  968. "\uFF2C" => "L"
  969. # ĺ [LATIN SMALL LETTER L WITH ACUTE]
  970. "\u013A" => "l"
  971. # ļ [LATIN SMALL LETTER L WITH CEDILLA]
  972. "\u013C" => "l"
  973. # ľ [LATIN SMALL LETTER L WITH CARON]
  974. "\u013E" => "l"
  975. # ŀ [LATIN SMALL LETTER L WITH MIDDLE DOT]
  976. "\u0140" => "l"
  977. # ł [LATIN SMALL LETTER L WITH STROKE]
  978. "\u0142" => "l"
  979. # ƚ [LATIN SMALL LETTER L WITH BAR]
  980. "\u019A" => "l"
  981. # ȴ [LATIN SMALL LETTER L WITH CURL]
  982. "\u0234" => "l"
  983. # ɫ [LATIN SMALL LETTER L WITH MIDDLE TILDE]
  984. "\u026B" => "l"
  985. # ɬ [LATIN SMALL LETTER L WITH BELT]
  986. "\u026C" => "l"
  987. # ɭ [LATIN SMALL LETTER L WITH RETROFLEX HOOK]
  988. "\u026D" => "l"
  989. # ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK]
  990. "\u1D85" => "l"
  991. # ḷ [LATIN SMALL LETTER L WITH DOT BELOW]
  992. "\u1E37" => "l"
  993. # ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON]
  994. "\u1E39" => "l"
  995. # ḻ [LATIN SMALL LETTER L WITH LINE BELOW]
  996. "\u1E3B" => "l"
  997. # ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW]
  998. "\u1E3D" => "l"
  999. # ⓛ [CIRCLED LATIN SMALL LETTER L]
  1000. "\u24DB" => "l"
  1001. # ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR]
  1002. "\u2C61" => "l"
  1003. # ꝇ [LATIN SMALL LETTER BROKEN L]
  1004. "\uA747" => "l"
  1005. # ꝉ [LATIN SMALL LETTER L WITH HIGH STROKE]
  1006. "\uA749" => "l"
  1007. # ꞁ [LATIN SMALL LETTER TURNED L]
  1008. "\uA781" => "l"
  1009. # l [FULLWIDTH LATIN SMALL LETTER L]
  1010. "\uFF4C" => "l"
  1011. # LJ [LATIN CAPITAL LETTER LJ]
  1012. "\u01C7" => "LJ"
  1013. # Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL]
  1014. "\u1EFA" => "LL"
  1015. # Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
  1016. "\u01C8" => "Lj"
  1017. # ⒧ [PARENTHESIZED LATIN SMALL LETTER L]
  1018. "\u24A7" => "(l)"
  1019. # lj [LATIN SMALL LETTER LJ]
  1020. "\u01C9" => "lj"
  1021. # ỻ [LATIN SMALL LETTER MIDDLE-WELSH LL]
  1022. "\u1EFB" => "ll"
  1023. # ʪ [LATIN SMALL LETTER LS DIGRAPH]
  1024. "\u02AA" => "ls"
  1025. # ʫ [LATIN SMALL LETTER LZ DIGRAPH]
  1026. "\u02AB" => "lz"
  1027. # Ɯ [LATIN CAPITAL LETTER TURNED M]
  1028. "\u019C" => "M"
  1029. # ᴍ [LATIN LETTER SMALL CAPITAL M]
  1030. "\u1D0D" => "M"
  1031. # Ḿ [LATIN CAPITAL LETTER M WITH ACUTE]
  1032. "\u1E3E" => "M"
  1033. # Ṁ [LATIN CAPITAL LETTER M WITH DOT ABOVE]
  1034. "\u1E40" => "M"
  1035. # Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW]
  1036. "\u1E42" => "M"
  1037. # Ⓜ [CIRCLED LATIN CAPITAL LETTER M]
  1038. "\u24C2" => "M"
  1039. # Ɱ [LATIN CAPITAL LETTER M WITH HOOK]
  1040. "\u2C6E" => "M"
  1041. # ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M]
  1042. "\uA7FD" => "M"
  1043. # ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M]
  1044. "\uA7FF" => "M"
  1045. # M [FULLWIDTH LATIN CAPITAL LETTER M]
  1046. "\uFF2D" => "M"
  1047. # ɯ [LATIN SMALL LETTER TURNED M]
  1048. "\u026F" => "m"
  1049. # ɰ [LATIN SMALL LETTER TURNED M WITH LONG LEG]
  1050. "\u0270" => "m"
  1051. # ɱ [LATIN SMALL LETTER M WITH HOOK]
  1052. "\u0271" => "m"
  1053. # ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE]
  1054. "\u1D6F" => "m"
  1055. # ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK]
  1056. "\u1D86" => "m"
  1057. # ḿ [LATIN SMALL LETTER M WITH ACUTE]
  1058. "\u1E3F" => "m"
  1059. # ṁ [LATIN SMALL LETTER M WITH DOT ABOVE]
  1060. "\u1E41" => "m"
  1061. # ṃ [LATIN SMALL LETTER M WITH DOT BELOW]
  1062. "\u1E43" => "m"
  1063. # ⓜ [CIRCLED LATIN SMALL LETTER M]
  1064. "\u24DC" => "m"
  1065. # m [FULLWIDTH LATIN SMALL LETTER M]
  1066. "\uFF4D" => "m"
  1067. # ⒨ [PARENTHESIZED LATIN SMALL LETTER M]
  1068. "\u24A8" => "(m)"
  1069. # Ñ [LATIN CAPITAL LETTER N WITH TILDE]
  1070. "\u00D1" => "N"
  1071. # Ń [LATIN CAPITAL LETTER N WITH ACUTE]
  1072. "\u0143" => "N"
  1073. # Ņ [LATIN CAPITAL LETTER N WITH CEDILLA]
  1074. "\u0145" => "N"
  1075. # Ň [LATIN CAPITAL LETTER N WITH CARON]
  1076. "\u0147" => "N"
  1077. # Ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG]
  1078. "\u014A" => "N"
  1079. # Ɲ [LATIN CAPITAL LETTER N WITH LEFT HOOK]
  1080. "\u019D" => "N"
  1081. # Ǹ [LATIN CAPITAL LETTER N WITH GRAVE]
  1082. "\u01F8" => "N"
  1083. # Ƞ [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG]
  1084. "\u0220" => "N"
  1085. # ɴ [LATIN LETTER SMALL CAPITAL N]
  1086. "\u0274" => "N"
  1087. # ᴎ [LATIN LETTER SMALL CAPITAL REVERSED N]
  1088. "\u1D0E" => "N"
  1089. # Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE]
  1090. "\u1E44" => "N"
  1091. # Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW]
  1092. "\u1E46" => "N"
  1093. # Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW]
  1094. "\u1E48" => "N"
  1095. # Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW]
  1096. "\u1E4A" => "N"
  1097. # Ⓝ [CIRCLED LATIN CAPITAL LETTER N]
  1098. "\u24C3" => "N"
  1099. # N [FULLWIDTH LATIN CAPITAL LETTER N]
  1100. "\uFF2E" => "N"
  1101. # ñ [LATIN SMALL LETTER N WITH TILDE]
  1102. "\u00F1" => "n"
  1103. # ń [LATIN SMALL LETTER N WITH ACUTE]
  1104. "\u0144" => "n"
  1105. # ņ [LATIN SMALL LETTER N WITH CEDILLA]
  1106. "\u0146" => "n"
  1107. # ň [LATIN SMALL LETTER N WITH CARON]
  1108. "\u0148" => "n"
  1109. # ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE]
  1110. "\u0149" => "n"
  1111. # ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG]
  1112. "\u014B" => "n"
  1113. # ƞ [LATIN SMALL LETTER N WITH LONG RIGHT LEG]
  1114. "\u019E" => "n"
  1115. # ǹ [LATIN SMALL LETTER N WITH GRAVE]
  1116. "\u01F9" => "n"
  1117. # ȵ [LATIN SMALL LETTER N WITH CURL]
  1118. "\u0235" => "n"
  1119. # ɲ [LATIN SMALL LETTER N WITH LEFT HOOK]
  1120. "\u0272" => "n"
  1121. # ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK]
  1122. "\u0273" => "n"
  1123. # ᵰ [LATIN SMALL LETTER N WITH MIDDLE TILDE]
  1124. "\u1D70" => "n"
  1125. # ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK]
  1126. "\u1D87" => "n"
  1127. # ṅ [LATIN SMALL LETTER N WITH DOT ABOVE]
  1128. "\u1E45" => "n"
  1129. # ṇ [LATIN SMALL LETTER N WITH DOT BELOW]
  1130. "\u1E47" => "n"
  1131. # ṉ [LATIN SMALL LETTER N WITH LINE BELOW]
  1132. "\u1E49" => "n"
  1133. # ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW]
  1134. "\u1E4B" => "n"
  1135. # ⁿ [SUPERSCRIPT LATIN SMALL LETTER N]
  1136. "\u207F" => "n"
  1137. # ⓝ [CIRCLED LATIN SMALL LETTER N]
  1138. "\u24DD" => "n"
  1139. # n [FULLWIDTH LATIN SMALL LETTER N]
  1140. "\uFF4E" => "n"
  1141. # NJ [LATIN CAPITAL LETTER NJ]
  1142. "\u01CA" => "NJ"
  1143. # Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
  1144. "\u01CB" => "Nj"
  1145. # ⒩ [PARENTHESIZED LATIN SMALL LETTER N]
  1146. "\u24A9" => "(n)"
  1147. # nj [LATIN SMALL LETTER NJ]
  1148. "\u01CC" => "nj"
  1149. # Ò [LATIN CAPITAL LETTER O WITH GRAVE]
  1150. "\u00D2" => "O"
  1151. # Ó [LATIN CAPITAL LETTER O WITH ACUTE]
  1152. "\u00D3" => "O"
  1153. # Ô [LATIN CAPITAL LETTER O WITH CIRCUMFLEX]
  1154. "\u00D4" => "O"
  1155. # Õ [LATIN CAPITAL LETTER O WITH TILDE]
  1156. "\u00D5" => "O"
  1157. # Ö [LATIN CAPITAL LETTER O WITH DIAERESIS]
  1158. "\u00D6" => "O"
  1159. # Ø [LATIN CAPITAL LETTER O WITH STROKE]
  1160. "\u00D8" => "O"
  1161. # Ō [LATIN CAPITAL LETTER O WITH MACRON]
  1162. "\u014C" => "O"
  1163. # Ŏ [LATIN CAPITAL LETTER O WITH BREVE]
  1164. "\u014E" => "O"
  1165. # Ő [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE]
  1166. "\u0150" => "O"
  1167. # Ɔ [LATIN CAPITAL LETTER OPEN O]
  1168. "\u0186" => "O"
  1169. # Ɵ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE]
  1170. "\u019F" => "O"
  1171. # Ơ [LATIN CAPITAL LETTER O WITH HORN]
  1172. "\u01A0" => "O"
  1173. # Ǒ [LATIN CAPITAL LETTER O WITH CARON]
  1174. "\u01D1" => "O"
  1175. # Ǫ [LATIN CAPITAL LETTER O WITH OGONEK]
  1176. "\u01EA" => "O"
  1177. # Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON]
  1178. "\u01EC" => "O"
  1179. # Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE]
  1180. "\u01FE" => "O"
  1181. # Ȍ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE]
  1182. "\u020C" => "O"
  1183. # Ȏ [LATIN CAPITAL LETTER O WITH INVERTED BREVE]
  1184. "\u020E" => "O"
  1185. # Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON]
  1186. "\u022A" => "O"
  1187. # Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON]
  1188. "\u022C" => "O"
  1189. # Ȯ [LATIN CAPITAL LETTER O WITH DOT ABOVE]
  1190. "\u022E" => "O"
  1191. # Ȱ [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON]
  1192. "\u0230" => "O"
  1193. # ᴏ [LATIN LETTER SMALL CAPITAL O]
  1194. "\u1D0F" => "O"
  1195. # ᴐ [LATIN LETTER SMALL CAPITAL OPEN O]
  1196. "\u1D10" => "O"
  1197. # Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE]
  1198. "\u1E4C" => "O"
  1199. # Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS]
  1200. "\u1E4E" => "O"
  1201. # Ṑ [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE]
  1202. "\u1E50" => "O"
  1203. # Ṓ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE]
  1204. "\u1E52" => "O"
  1205. # Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW]
  1206. "\u1ECC" => "O"
  1207. # Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE]
  1208. "\u1ECE" => "O"
  1209. # Ố [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE]
  1210. "\u1ED0" => "O"
  1211. # Ồ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE]
  1212. "\u1ED2" => "O"
  1213. # Ổ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
  1214. "\u1ED4" => "O"
  1215. # Ỗ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE]
  1216. "\u1ED6" => "O"
  1217. # Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
  1218. "\u1ED8" => "O"
  1219. # Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE]
  1220. "\u1EDA" => "O"
  1221. # Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE]
  1222. "\u1EDC" => "O"
  1223. # Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE]
  1224. "\u1EDE" => "O"
  1225. # Ỡ [LATIN CAPITAL LETTER O WITH HORN AND TILDE]
  1226. "\u1EE0" => "O"
  1227. # Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW]
  1228. "\u1EE2" => "O"
  1229. # Ⓞ [CIRCLED LATIN CAPITAL LETTER O]
  1230. "\u24C4" => "O"
  1231. # Ꝋ [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY]
  1232. "\uA74A" => "O"
  1233. # Ꝍ [LATIN CAPITAL LETTER O WITH LOOP]
  1234. "\uA74C" => "O"
  1235. # O [FULLWIDTH LATIN CAPITAL LETTER O]
  1236. "\uFF2F" => "O"
  1237. # ò [LATIN SMALL LETTER O WITH GRAVE]
  1238. "\u00F2" => "o"
  1239. # ó [LATIN SMALL LETTER O WITH ACUTE]
  1240. "\u00F3" => "o"
  1241. # ô [LATIN SMALL LETTER O WITH CIRCUMFLEX]
  1242. "\u00F4" => "o"
  1243. # õ [LATIN SMALL LETTER O WITH TILDE]
  1244. "\u00F5" => "o"
  1245. # ö [LATIN SMALL LETTER O WITH DIAERESIS]
  1246. "\u00F6" => "o"
  1247. # ø [LATIN SMALL LETTER O WITH STROKE]
  1248. "\u00F8" => "o"
  1249. # ō [LATIN SMALL LETTER O WITH MACRON]
  1250. "\u014D" => "o"
  1251. # ŏ [LATIN SMALL LETTER O WITH BREVE]
  1252. "\u014F" => "o"
  1253. # ő [LATIN SMALL LETTER O WITH DOUBLE ACUTE]
  1254. "\u0151" => "o"
  1255. # ơ [LATIN SMALL LETTER O WITH HORN]
  1256. "\u01A1" => "o"
  1257. # ǒ [LATIN SMALL LETTER O WITH CARON]
  1258. "\u01D2" => "o"
  1259. # ǫ [LATIN SMALL LETTER O WITH OGONEK]
  1260. "\u01EB" => "o"
  1261. # ǭ [LATIN SMALL LETTER O WITH OGONEK AND MACRON]
  1262. "\u01ED" => "o"
  1263. # ǿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE]
  1264. "\u01FF" => "o"
  1265. # ȍ [LATIN SMALL LETTER O WITH DOUBLE GRAVE]
  1266. "\u020D" => "o"
  1267. # ȏ [LATIN SMALL LETTER O WITH INVERTED BREVE]
  1268. "\u020F" => "o"
  1269. # ȫ [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON]
  1270. "\u022B" => "o"
  1271. # ȭ [LATIN SMALL LETTER O WITH TILDE AND MACRON]
  1272. "\u022D" => "o"
  1273. # ȯ [LATIN SMALL LETTER O WITH DOT ABOVE]
  1274. "\u022F" => "o"
  1275. # ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON]
  1276. "\u0231" => "o"
  1277. # ɔ [LATIN SMALL LETTER OPEN O]
  1278. "\u0254" => "o"
  1279. # ɵ [LATIN SMALL LETTER BARRED O]
  1280. "\u0275" => "o"
  1281. # ᴖ [LATIN SMALL LETTER TOP HALF O]
  1282. "\u1D16" => "o"
  1283. # ᴗ [LATIN SMALL LETTER BOTTOM HALF O]
  1284. "\u1D17" => "o"
  1285. # ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK]
  1286. "\u1D97" => "o"
  1287. # ṍ [LATIN SMALL LETTER O WITH TILDE AND ACUTE]
  1288. "\u1E4D" => "o"
  1289. # ṏ [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS]
  1290. "\u1E4F" => "o"
  1291. # ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE]
  1292. "\u1E51" => "o"
  1293. # ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE]
  1294. "\u1E53" => "o"
  1295. # ọ [LATIN SMALL LETTER O WITH DOT BELOW]
  1296. "\u1ECD" => "o"
  1297. # ỏ [LATIN SMALL LETTER O WITH HOOK ABOVE]
  1298. "\u1ECF" => "o"
  1299. # ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE]
  1300. "\u1ED1" => "o"
  1301. # ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE]
  1302. "\u1ED3" => "o"
  1303. # ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
  1304. "\u1ED5" => "o"
  1305. # ỗ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE]
  1306. "\u1ED7" => "o"
  1307. # ộ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
  1308. "\u1ED9" => "o"
  1309. # ớ [LATIN SMALL LETTER O WITH HORN AND ACUTE]
  1310. "\u1EDB" => "o"
  1311. # ờ [LATIN SMALL LETTER O WITH HORN AND GRAVE]
  1312. "\u1EDD" => "o"
  1313. # ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE]
  1314. "\u1EDF" => "o"
  1315. # ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE]
  1316. "\u1EE1" => "o"
  1317. # ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW]
  1318. "\u1EE3" => "o"
  1319. # ₒ [LATIN SUBSCRIPT SMALL LETTER O]
  1320. "\u2092" => "o"
  1321. # ⓞ [CIRCLED LATIN SMALL LETTER O]
  1322. "\u24DE" => "o"
  1323. # ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE]
  1324. "\u2C7A" => "o"
  1325. # ꝋ [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY]
  1326. "\uA74B" => "o"
  1327. # ꝍ [LATIN SMALL LETTER O WITH LOOP]
  1328. "\uA74D" => "o"
  1329. # o [FULLWIDTH LATIN SMALL LETTER O]
  1330. "\uFF4F" => "o"
  1331. # Π[LATIN CAPITAL LIGATURE OE]
  1332. "\u0152" => "OE"
  1333. # ɶ [LATIN LETTER SMALL CAPITAL OE]
  1334. "\u0276" => "OE"
  1335. # Ꝏ [LATIN CAPITAL LETTER OO]
  1336. "\uA74E" => "OO"
  1337. # Ȣ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU]
  1338. "\u0222" => "OU"
  1339. # ᴕ [LATIN LETTER SMALL CAPITAL OU]
  1340. "\u1D15" => "OU"
  1341. # ⒪ [PARENTHESIZED LATIN SMALL LETTER O]
  1342. "\u24AA" => "(o)"
  1343. # œ [LATIN SMALL LIGATURE OE]
  1344. "\u0153" => "oe"
  1345. # ᴔ [LATIN SMALL LETTER TURNED OE]
  1346. "\u1D14" => "oe"
  1347. # ꝏ [LATIN SMALL LETTER OO]
  1348. "\uA74F" => "oo"
  1349. # ȣ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU]
  1350. "\u0223" => "ou"
  1351. # Ƥ [LATIN CAPITAL LETTER P WITH HOOK]
  1352. "\u01A4" => "P"
  1353. # ᴘ [LATIN LETTER SMALL CAPITAL P]
  1354. "\u1D18" => "P"
  1355. # Ṕ [LATIN CAPITAL LETTER P WITH ACUTE]
  1356. "\u1E54" => "P"
  1357. # Ṗ [LATIN CAPITAL LETTER P WITH DOT ABOVE]
  1358. "\u1E56" => "P"
  1359. # Ⓟ [CIRCLED LATIN CAPITAL LETTER P]
  1360. "\u24C5" => "P"
  1361. # Ᵽ [LATIN CAPITAL LETTER P WITH STROKE]
  1362. "\u2C63" => "P"
  1363. # Ꝑ [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER]
  1364. "\uA750" => "P"
  1365. # Ꝓ [LATIN CAPITAL LETTER P WITH FLOURISH]
  1366. "\uA752" => "P"
  1367. # Ꝕ [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL]
  1368. "\uA754" => "P"
  1369. # P [FULLWIDTH LATIN CAPITAL LETTER P]
  1370. "\uFF30" => "P"
  1371. # ƥ [LATIN SMALL LETTER P WITH HOOK]
  1372. "\u01A5" => "p"
  1373. # ᵱ [LATIN SMALL LETTER P WITH MIDDLE TILDE]
  1374. "\u1D71" => "p"
  1375. # ᵽ [LATIN SMALL LETTER P WITH STROKE]
  1376. "\u1D7D" => "p"
  1377. # ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK]
  1378. "\u1D88" => "p"
  1379. # ṕ [LATIN SMALL LETTER P WITH ACUTE]
  1380. "\u1E55" => "p"
  1381. # ṗ [LATIN SMALL LETTER P WITH DOT ABOVE]
  1382. "\u1E57" => "p"
  1383. # ⓟ [CIRCLED LATIN SMALL LETTER P]
  1384. "\u24DF" => "p"
  1385. # ꝑ [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER]
  1386. "\uA751" => "p"
  1387. # ꝓ [LATIN SMALL LETTER P WITH FLOURISH]
  1388. "\uA753" => "p"
  1389. # ꝕ [LATIN SMALL LETTER P WITH SQUIRREL TAIL]
  1390. "\uA755" => "p"
  1391. # ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P]
  1392. "\uA7FC" => "p"
  1393. # p [FULLWIDTH LATIN SMALL LETTER P]
  1394. "\uFF50" => "p"
  1395. # ⒫ [PARENTHESIZED LATIN SMALL LETTER P]
  1396. "\u24AB" => "(p)"
  1397. # Ɋ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL]
  1398. "\u024A" => "Q"
  1399. # Ⓠ [CIRCLED LATIN CAPITAL LETTER Q]
  1400. "\u24C6" => "Q"
  1401. # Ꝗ [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER]
  1402. "\uA756" => "Q"
  1403. # Ꝙ [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE]
  1404. "\uA758" => "Q"
  1405. # Q [FULLWIDTH LATIN CAPITAL LETTER Q]
  1406. "\uFF31" => "Q"
  1407. # ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA]
  1408. "\u0138" => "q"
  1409. # ɋ [LATIN SMALL LETTER Q WITH HOOK TAIL]
  1410. "\u024B" => "q"
  1411. # ʠ [LATIN SMALL LETTER Q WITH HOOK]
  1412. "\u02A0" => "q"
  1413. # ⓠ [CIRCLED LATIN SMALL LETTER Q]
  1414. "\u24E0" => "q"
  1415. # ꝗ [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER]
  1416. "\uA757" => "q"
  1417. # ꝙ [LATIN SMALL LETTER Q WITH DIAGONAL STROKE]
  1418. "\uA759" => "q"
  1419. # q [FULLWIDTH LATIN SMALL LETTER Q]
  1420. "\uFF51" => "q"
  1421. # ⒬ [PARENTHESIZED LATIN SMALL LETTER Q]
  1422. "\u24AC" => "(q)"
  1423. # ȹ [LATIN SMALL LETTER QP DIGRAPH]
  1424. "\u0239" => "qp"
  1425. # Ŕ [LATIN CAPITAL LETTER R WITH ACUTE]
  1426. "\u0154" => "R"
  1427. # Ŗ [LATIN CAPITAL LETTER R WITH CEDILLA]
  1428. "\u0156" => "R"
  1429. # Ř [LATIN CAPITAL LETTER R WITH CARON]
  1430. "\u0158" => "R"
  1431. # Ȓ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE]
  1432. "\u0210" => "R"
  1433. # Ȓ [LATIN CAPITAL LETTER R WITH INVERTED BREVE]
  1434. "\u0212" => "R"
  1435. # Ɍ [LATIN CAPITAL LETTER R WITH STROKE]
  1436. "\u024C" => "R"
  1437. # ʀ [LATIN LETTER SMALL CAPITAL R]
  1438. "\u0280" => "R"
  1439. # ʁ [LATIN LETTER SMALL CAPITAL INVERTED R]
  1440. "\u0281" => "R"
  1441. # ᴙ [LATIN LETTER SMALL CAPITAL REVERSED R]
  1442. "\u1D19" => "R"
  1443. # ᴚ [LATIN LETTER SMALL CAPITAL TURNED R]
  1444. "\u1D1A" => "R"
  1445. # Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE]
  1446. "\u1E58" => "R"
  1447. # Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW]
  1448. "\u1E5A" => "R"
  1449. # Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON]
  1450. "\u1E5C" => "R"
  1451. # Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW]
  1452. "\u1E5E" => "R"
  1453. # Ⓡ [CIRCLED LATIN CAPITAL LETTER R]
  1454. "\u24C7" => "R"
  1455. # Ɽ [LATIN CAPITAL LETTER R WITH TAIL]
  1456. "\u2C64" => "R"
  1457. # Ꝛ [LATIN CAPITAL LETTER R ROTUNDA]
  1458. "\uA75A" => "R"
  1459. # Ꞃ [LATIN CAPITAL LETTER INSULAR R]
  1460. "\uA782" => "R"
  1461. # R [FULLWIDTH LATIN CAPITAL LETTER R]
  1462. "\uFF32" => "R"
  1463. # ŕ [LATIN SMALL LETTER R WITH ACUTE]
  1464. "\u0155" => "r"
  1465. # ŗ [LATIN SMALL LETTER R WITH CEDILLA]
  1466. "\u0157" => "r"
  1467. # ř [LATIN SMALL LETTER R WITH CARON]
  1468. "\u0159" => "r"
  1469. # ȑ [LATIN SMALL LETTER R WITH DOUBLE GRAVE]
  1470. "\u0211" => "r"
  1471. # ȓ [LATIN SMALL LETTER R WITH INVERTED BREVE]
  1472. "\u0213" => "r"
  1473. # ɍ [LATIN SMALL LETTER R WITH STROKE]
  1474. "\u024D" => "r"
  1475. # ɼ [LATIN SMALL LETTER R WITH LONG LEG]
  1476. "\u027C" => "r"
  1477. # ɽ [LATIN SMALL LETTER R WITH TAIL]
  1478. "\u027D" => "r"
  1479. # ɾ [LATIN SMALL LETTER R WITH FISHHOOK]
  1480. "\u027E" => "r"
  1481. # ɿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK]
  1482. "\u027F" => "r"
  1483. # ᵣ [LATIN SUBSCRIPT SMALL LETTER R]
  1484. "\u1D63" => "r"
  1485. # ᵲ [LATIN SMALL LETTER R WITH MIDDLE TILDE]
  1486. "\u1D72" => "r"
  1487. # ᵳ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE]
  1488. "\u1D73" => "r"
  1489. # ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK]
  1490. "\u1D89" => "r"
  1491. # ṙ [LATIN SMALL LETTER R WITH DOT ABOVE]
  1492. "\u1E59" => "r"
  1493. # ṛ [LATIN SMALL LETTER R WITH DOT BELOW]
  1494. "\u1E5B" => "r"
  1495. # ṝ [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON]
  1496. "\u1E5D" => "r"
  1497. # ṟ [LATIN SMALL LETTER R WITH LINE BELOW]
  1498. "\u1E5F" => "r"
  1499. # ⓡ [CIRCLED LATIN SMALL LETTER R]
  1500. "\u24E1" => "r"
  1501. # ꝛ [LATIN SMALL LETTER R ROTUNDA]
  1502. "\uA75B" => "r"
  1503. # ꞃ [LATIN SMALL LETTER INSULAR R]
  1504. "\uA783" => "r"
  1505. # r [FULLWIDTH LATIN SMALL LETTER R]
  1506. "\uFF52" => "r"
  1507. # ⒭ [PARENTHESIZED LATIN SMALL LETTER R]
  1508. "\u24AD" => "(r)"
  1509. # Ś [LATIN CAPITAL LETTER S WITH ACUTE]
  1510. "\u015A" => "S"
  1511. # Ŝ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX]
  1512. "\u015C" => "S"
  1513. # Ş [LATIN CAPITAL LETTER S WITH CEDILLA]
  1514. "\u015E" => "S"
  1515. # Š [LATIN CAPITAL LETTER S WITH CARON]
  1516. "\u0160" => "S"
  1517. # Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW]
  1518. "\u0218" => "S"
  1519. # Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
  1520. "\u1E60" => "S"
  1521. # Ṣ [LATIN CAPITAL LETTER S WITH DOT BELOW]
  1522. "\u1E62" => "S"
  1523. # Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE]
  1524. "\u1E64" => "S"
  1525. # Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE]
  1526. "\u1E66" => "S"
  1527. # Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE]
  1528. "\u1E68" => "S"
  1529. # Ⓢ [CIRCLED LATIN CAPITAL LETTER S]
  1530. "\u24C8" => "S"
  1531. # ꜱ [LATIN LETTER SMALL CAPITAL S]
  1532. "\uA731" => "S"
  1533. # ꞅ [LATIN SMALL LETTER INSULAR S]
  1534. "\uA785" => "S"
  1535. # S [FULLWIDTH LATIN CAPITAL LETTER S]
  1536. "\uFF33" => "S"
  1537. # ś [LATIN SMALL LETTER S WITH ACUTE]
  1538. "\u015B" => "s"
  1539. # ŝ [LATIN SMALL LETTER S WITH CIRCUMFLEX]
  1540. "\u015D" => "s"
  1541. # ş [LATIN SMALL LETTER S WITH CEDILLA]
  1542. "\u015F" => "s"
  1543. # š [LATIN SMALL LETTER S WITH CARON]
  1544. "\u0161" => "s"
  1545. # ſ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S]
  1546. "\u017F" => "s"
  1547. # ș [LATIN SMALL LETTER S WITH COMMA BELOW]
  1548. "\u0219" => "s"
  1549. # ȿ [LATIN SMALL LETTER S WITH SWASH TAIL]
  1550. "\u023F" => "s"
  1551. # ʂ [LATIN SMALL LETTER S WITH HOOK]
  1552. "\u0282" => "s"
  1553. # ᵴ [LATIN SMALL LETTER S WITH MIDDLE TILDE]
  1554. "\u1D74" => "s"
  1555. # ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK]
  1556. "\u1D8A" => "s"
  1557. # ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
  1558. "\u1E61" => "s"
  1559. # ṣ [LATIN SMALL LETTER S WITH DOT BELOW]
  1560. "\u1E63" => "s"
  1561. # ṥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE]
  1562. "\u1E65" => "s"
  1563. # ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE]
  1564. "\u1E67" => "s"
  1565. # ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE]
  1566. "\u1E69" => "s"
  1567. # ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE]
  1568. "\u1E9C" => "s"
  1569. # ẝ [LATIN SMALL LETTER LONG S WITH HIGH STROKE]
  1570. "\u1E9D" => "s"
  1571. # ⓢ [CIRCLED LATIN SMALL LETTER S]
  1572. "\u24E2" => "s"
  1573. # Ꞅ [LATIN CAPITAL LETTER INSULAR S]
  1574. "\uA784" => "s"
  1575. # s [FULLWIDTH LATIN SMALL LETTER S]
  1576. "\uFF53" => "s"
  1577. # ẞ [LATIN CAPITAL LETTER SHARP S]
  1578. "\u1E9E" => "SS"
  1579. # ⒮ [PARENTHESIZED LATIN SMALL LETTER S]
  1580. "\u24AE" => "(s)"
  1581. # ß [LATIN SMALL LETTER SHARP S]
  1582. "\u00DF" => "ss"
  1583. # st [LATIN SMALL LIGATURE ST]
  1584. "\uFB06" => "st"
  1585. # Ţ [LATIN CAPITAL LETTER T WITH CEDILLA]
  1586. "\u0162" => "T"
  1587. # Ť [LATIN CAPITAL LETTER T WITH CARON]
  1588. "\u0164" => "T"
  1589. # Ŧ [LATIN CAPITAL LETTER T WITH STROKE]
  1590. "\u0166" => "T"
  1591. # Ƭ [LATIN CAPITAL LETTER T WITH HOOK]
  1592. "\u01AC" => "T"
  1593. # Ʈ [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK]
  1594. "\u01AE" => "T"
  1595. # Ț [LATIN CAPITAL LETTER T WITH COMMA BELOW]
  1596. "\u021A" => "T"
  1597. # Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE]
  1598. "\u023E" => "T"
  1599. # ᴛ [LATIN LETTER SMALL CAPITAL T]
  1600. "\u1D1B" => "T"
  1601. # Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE]
  1602. "\u1E6A" => "T"
  1603. # Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW]
  1604. "\u1E6C" => "T"
  1605. # Ṯ [LATIN CAPITAL LETTER T WITH LINE BELOW]
  1606. "\u1E6E" => "T"
  1607. # Ṱ [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW]
  1608. "\u1E70" => "T"
  1609. # Ⓣ [CIRCLED LATIN CAPITAL LETTER T]
  1610. "\u24C9" => "T"
  1611. # Ꞇ [LATIN CAPITAL LETTER INSULAR T]
  1612. "\uA786" => "T"
  1613. # T [FULLWIDTH LATIN CAPITAL LETTER T]
  1614. "\uFF34" => "T"
  1615. # ţ [LATIN SMALL LETTER T WITH CEDILLA]
  1616. "\u0163" => "t"
  1617. # ť [LATIN SMALL LETTER T WITH CARON]
  1618. "\u0165" => "t"
  1619. # ŧ [LATIN SMALL LETTER T WITH STROKE]
  1620. "\u0167" => "t"
  1621. # ƫ [LATIN SMALL LETTER T WITH PALATAL HOOK]
  1622. "\u01AB" => "t"
  1623. # ƭ [LATIN SMALL LETTER T WITH HOOK]
  1624. "\u01AD" => "t"
  1625. # ț [LATIN SMALL LETTER T WITH COMMA BELOW]
  1626. "\u021B" => "t"
  1627. # ȶ [LATIN SMALL LETTER T WITH CURL]
  1628. "\u0236" => "t"
  1629. # ʇ [LATIN SMALL LETTER TURNED T]
  1630. "\u0287" => "t"
  1631. # ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK]
  1632. "\u0288" => "t"
  1633. # ᵵ [LATIN SMALL LETTER T WITH MIDDLE TILDE]
  1634. "\u1D75" => "t"
  1635. # ṫ [LATIN SMALL LETTER T WITH DOT ABOVE]
  1636. "\u1E6B" => "t"
  1637. # ṭ [LATIN SMALL LETTER T WITH DOT BELOW]
  1638. "\u1E6D" => "t"
  1639. # ṯ [LATIN SMALL LETTER T WITH LINE BELOW]
  1640. "\u1E6F" => "t"
  1641. # ṱ [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW]
  1642. "\u1E71" => "t"
  1643. # ẗ [LATIN SMALL LETTER T WITH DIAERESIS]
  1644. "\u1E97" => "t"
  1645. # ⓣ [CIRCLED LATIN SMALL LETTER T]
  1646. "\u24E3" => "t"
  1647. # ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE]
  1648. "\u2C66" => "t"
  1649. # t [FULLWIDTH LATIN SMALL LETTER T]
  1650. "\uFF54" => "t"
  1651. # Þ [LATIN CAPITAL LETTER THORN]
  1652. "\u00DE" => "TH"
  1653. # Ꝧ [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER]
  1654. "\uA766" => "TH"
  1655. # Ꜩ [LATIN CAPITAL LETTER TZ]
  1656. "\uA728" => "TZ"
  1657. # ⒯ [PARENTHESIZED LATIN SMALL LETTER T]
  1658. "\u24AF" => "(t)"
  1659. # ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL]
  1660. "\u02A8" => "tc"
  1661. # þ [LATIN SMALL LETTER THORN]
  1662. "\u00FE" => "th"
  1663. # ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH]
  1664. "\u1D7A" => "th"
  1665. # ꝧ [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER]
  1666. "\uA767" => "th"
  1667. # ʦ [LATIN SMALL LETTER TS DIGRAPH]
  1668. "\u02A6" => "ts"
  1669. # ꜩ [LATIN SMALL LETTER TZ]
  1670. "\uA729" => "tz"
  1671. # Ù [LATIN CAPITAL LETTER U WITH GRAVE]
  1672. "\u00D9" => "U"
  1673. # Ú [LATIN CAPITAL LETTER U WITH ACUTE]
  1674. "\u00DA" => "U"
  1675. # Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX]
  1676. "\u00DB" => "U"
  1677. # Ü [LATIN CAPITAL LETTER U WITH DIAERESIS]
  1678. "\u00DC" => "U"
  1679. # Ũ [LATIN CAPITAL LETTER U WITH TILDE]
  1680. "\u0168" => "U"
  1681. # Ū [LATIN CAPITAL LETTER U WITH MACRON]
  1682. "\u016A" => "U"
  1683. # Ŭ [LATIN CAPITAL LETTER U WITH BREVE]
  1684. "\u016C" => "U"
  1685. # Ů [LATIN CAPITAL LETTER U WITH RING ABOVE]
  1686. "\u016E" => "U"
  1687. # Ű [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE]
  1688. "\u0170" => "U"
  1689. # Ų [LATIN CAPITAL LETTER U WITH OGONEK]
  1690. "\u0172" => "U"
  1691. # Ư [LATIN CAPITAL LETTER U WITH HORN]
  1692. "\u01AF" => "U"
  1693. # Ǔ [LATIN CAPITAL LETTER U WITH CARON]
  1694. "\u01D3" => "U"
  1695. # Ǖ [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON]
  1696. "\u01D5" => "U"
  1697. # Ǘ [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE]
  1698. "\u01D7" => "U"
  1699. # Ǚ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON]
  1700. "\u01D9" => "U"
  1701. # Ǜ [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE]
  1702. "\u01DB" => "U"
  1703. # Ȕ [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE]
  1704. "\u0214" => "U"
  1705. # Ȗ [LATIN CAPITAL LETTER U WITH INVERTED BREVE]
  1706. "\u0216" => "U"
  1707. # Ʉ [LATIN CAPITAL LETTER U BAR]
  1708. "\u0244" => "U"
  1709. # ᴜ [LATIN LETTER SMALL CAPITAL U]
  1710. "\u1D1C" => "U"
  1711. # ᵾ [LATIN SMALL CAPITAL LETTER U WITH STROKE]
  1712. "\u1D7E" => "U"
  1713. # Ṳ [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW]
  1714. "\u1E72" => "U"
  1715. # Ṵ [LATIN CAPITAL LETTER U WITH TILDE BELOW]
  1716. "\u1E74" => "U"
  1717. # Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW]
  1718. "\u1E76" => "U"
  1719. # Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE]
  1720. "\u1E78" => "U"
  1721. # Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS]
  1722. "\u1E7A" => "U"
  1723. # Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW]
  1724. "\u1EE4" => "U"
  1725. # Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE]
  1726. "\u1EE6" => "U"
  1727. # Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE]
  1728. "\u1EE8" => "U"
  1729. # Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE]
  1730. "\u1EEA" => "U"
  1731. # Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE]
  1732. "\u1EEC" => "U"
  1733. # Ữ [LATIN CAPITAL LETTER U WITH HORN AND TILDE]
  1734. "\u1EEE" => "U"
  1735. # Ự [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW]
  1736. "\u1EF0" => "U"
  1737. # Ⓤ [CIRCLED LATIN CAPITAL LETTER U]
  1738. "\u24CA" => "U"
  1739. # U [FULLWIDTH LATIN CAPITAL LETTER U]
  1740. "\uFF35" => "U"
  1741. # ù [LATIN SMALL LETTER U WITH GRAVE]
  1742. "\u00F9" => "u"
  1743. # ú [LATIN SMALL LETTER U WITH ACUTE]
  1744. "\u00FA" => "u"
  1745. # û [LATIN SMALL LETTER U WITH CIRCUMFLEX]
  1746. "\u00FB" => "u"
  1747. # ü [LATIN SMALL LETTER U WITH DIAERESIS]
  1748. "\u00FC" => "u"
  1749. # ũ [LATIN SMALL LETTER U WITH TILDE]
  1750. "\u0169" => "u"
  1751. # ū [LATIN SMALL LETTER U WITH MACRON]
  1752. "\u016B" => "u"
  1753. # ŭ [LATIN SMALL LETTER U WITH BREVE]
  1754. "\u016D" => "u"
  1755. # ů [LATIN SMALL LETTER U WITH RING ABOVE]
  1756. "\u016F" => "u"
  1757. # ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE]
  1758. "\u0171" => "u"
  1759. # ų [LATIN SMALL LETTER U WITH OGONEK]
  1760. "\u0173" => "u"
  1761. # ư [LATIN SMALL LETTER U WITH HORN]
  1762. "\u01B0" => "u"
  1763. # ǔ [LATIN SMALL LETTER U WITH CARON]
  1764. "\u01D4" => "u"
  1765. # ǖ [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON]
  1766. "\u01D6" => "u"
  1767. # ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE]
  1768. "\u01D8" => "u"
  1769. # ǚ [LATIN SMALL LETTER U WITH DIAERESIS AND CARON]
  1770. "\u01DA" => "u"
  1771. # ǜ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE]
  1772. "\u01DC" => "u"
  1773. # ȕ [LATIN SMALL LETTER U WITH DOUBLE GRAVE]
  1774. "\u0215" => "u"
  1775. # ȗ [LATIN SMALL LETTER U WITH INVERTED BREVE]
  1776. "\u0217" => "u"
  1777. # ʉ [LATIN SMALL LETTER U BAR]
  1778. "\u0289" => "u"
  1779. # ᵤ [LATIN SUBSCRIPT SMALL LETTER U]
  1780. "\u1D64" => "u"
  1781. # ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK]
  1782. "\u1D99" => "u"
  1783. # ṳ [LATIN SMALL LETTER U WITH DIAERESIS BELOW]
  1784. "\u1E73" => "u"
  1785. # ṵ [LATIN SMALL LETTER U WITH TILDE BELOW]
  1786. "\u1E75" => "u"
  1787. # ṷ [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW]
  1788. "\u1E77" => "u"
  1789. # ṹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE]
  1790. "\u1E79" => "u"
  1791. # ṻ [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS]
  1792. "\u1E7B" => "u"
  1793. # ụ [LATIN SMALL LETTER U WITH DOT BELOW]
  1794. "\u1EE5" => "u"
  1795. # ủ [LATIN SMALL LETTER U WITH HOOK ABOVE]
  1796. "\u1EE7" => "u"
  1797. # ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE]
  1798. "\u1EE9" => "u"
  1799. # ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE]
  1800. "\u1EEB" => "u"
  1801. # ử [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE]
  1802. "\u1EED" => "u"
  1803. # ữ [LATIN SMALL LETTER U WITH HORN AND TILDE]
  1804. "\u1EEF" => "u"
  1805. # ự [LATIN SMALL LETTER U WITH HORN AND DOT BELOW]
  1806. "\u1EF1" => "u"
  1807. # ⓤ [CIRCLED LATIN SMALL LETTER U]
  1808. "\u24E4" => "u"
  1809. # u [FULLWIDTH LATIN SMALL LETTER U]
  1810. "\uFF55" => "u"
  1811. # ⒰ [PARENTHESIZED LATIN SMALL LETTER U]
  1812. "\u24B0" => "(u)"
  1813. # ᵫ [LATIN SMALL LETTER UE]
  1814. "\u1D6B" => "ue"
  1815. # Ʋ [LATIN CAPITAL LETTER V WITH HOOK]
  1816. "\u01B2" => "V"
  1817. # Ʌ [LATIN CAPITAL LETTER TURNED V]
  1818. "\u0245" => "V"
  1819. # ᴠ [LATIN LETTER SMALL CAPITAL V]
  1820. "\u1D20" => "V"
  1821. # Ṽ [LATIN CAPITAL LETTER V WITH TILDE]
  1822. "\u1E7C" => "V"
  1823. # Ṿ [LATIN CAPITAL LETTER V WITH DOT BELOW]
  1824. "\u1E7E" => "V"
  1825. # Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V]
  1826. "\u1EFC" => "V"
  1827. # Ⓥ [CIRCLED LATIN CAPITAL LETTER V]
  1828. "\u24CB" => "V"
  1829. # Ꝟ [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE]
  1830. "\uA75E" => "V"
  1831. # Ꝩ [LATIN CAPITAL LETTER VEND]
  1832. "\uA768" => "V"
  1833. # V [FULLWIDTH LATIN CAPITAL LETTER V]
  1834. "\uFF36" => "V"
  1835. # ʋ [LATIN SMALL LETTER V WITH HOOK]
  1836. "\u028B" => "v"
  1837. # ʌ [LATIN SMALL LETTER TURNED V]
  1838. "\u028C" => "v"
  1839. # ᵥ [LATIN SUBSCRIPT SMALL LETTER V]
  1840. "\u1D65" => "v"
  1841. # ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK]
  1842. "\u1D8C" => "v"
  1843. # ṽ [LATIN SMALL LETTER V WITH TILDE]
  1844. "\u1E7D" => "v"
  1845. # ṿ [LATIN SMALL LETTER V WITH DOT BELOW]
  1846. "\u1E7F" => "v"
  1847. # ⓥ [CIRCLED LATIN SMALL LETTER V]
  1848. "\u24E5" => "v"
  1849. # ⱱ [LATIN SMALL LETTER V WITH RIGHT HOOK]
  1850. "\u2C71" => "v"
  1851. # ⱴ [LATIN SMALL LETTER V WITH CURL]
  1852. "\u2C74" => "v"
  1853. # ꝟ [LATIN SMALL LETTER V WITH DIAGONAL STROKE]
  1854. "\uA75F" => "v"
  1855. # v [FULLWIDTH LATIN SMALL LETTER V]
  1856. "\uFF56" => "v"
  1857. # Ꝡ [LATIN CAPITAL LETTER VY]
  1858. "\uA760" => "VY"
  1859. # ⒱ [PARENTHESIZED LATIN SMALL LETTER V]
  1860. "\u24B1" => "(v)"
  1861. # ꝡ [LATIN SMALL LETTER VY]
  1862. "\uA761" => "vy"
  1863. # Ŵ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX]
  1864. "\u0174" => "W"
  1865. # Ƿ http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN]
  1866. "\u01F7" => "W"
  1867. # ᴡ [LATIN LETTER SMALL CAPITAL W]
  1868. "\u1D21" => "W"
  1869. # Ẁ [LATIN CAPITAL LETTER W WITH GRAVE]
  1870. "\u1E80" => "W"
  1871. # Ẃ [LATIN CAPITAL LETTER W WITH ACUTE]
  1872. "\u1E82" => "W"
  1873. # Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS]
  1874. "\u1E84" => "W"
  1875. # Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE]
  1876. "\u1E86" => "W"
  1877. # Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW]
  1878. "\u1E88" => "W"
  1879. # Ⓦ [CIRCLED LATIN CAPITAL LETTER W]
  1880. "\u24CC" => "W"
  1881. # Ⱳ [LATIN CAPITAL LETTER W WITH HOOK]
  1882. "\u2C72" => "W"
  1883. # W [FULLWIDTH LATIN CAPITAL LETTER W]
  1884. "\uFF37" => "W"
  1885. # ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX]
  1886. "\u0175" => "w"
  1887. # ƿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN]
  1888. "\u01BF" => "w"
  1889. # ʍ [LATIN SMALL LETTER TURNED W]
  1890. "\u028D" => "w"
  1891. # ẁ [LATIN SMALL LETTER W WITH GRAVE]
  1892. "\u1E81" => "w"
  1893. # ẃ [LATIN SMALL LETTER W WITH ACUTE]
  1894. "\u1E83" => "w"
  1895. # ẅ [LATIN SMALL LETTER W WITH DIAERESIS]
  1896. "\u1E85" => "w"
  1897. # ẇ [LATIN SMALL LETTER W WITH DOT ABOVE]
  1898. "\u1E87" => "w"
  1899. # ẉ [LATIN SMALL LETTER W WITH DOT BELOW]
  1900. "\u1E89" => "w"
  1901. # ẘ [LATIN SMALL LETTER W WITH RING ABOVE]
  1902. "\u1E98" => "w"
  1903. # ⓦ [CIRCLED LATIN SMALL LETTER W]
  1904. "\u24E6" => "w"
  1905. # ⱳ [LATIN SMALL LETTER W WITH HOOK]
  1906. "\u2C73" => "w"
  1907. # w [FULLWIDTH LATIN SMALL LETTER W]
  1908. "\uFF57" => "w"
  1909. # ⒲ [PARENTHESIZED LATIN SMALL LETTER W]
  1910. "\u24B2" => "(w)"
  1911. # Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE]
  1912. "\u1E8A" => "X"
  1913. # Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS]
  1914. "\u1E8C" => "X"
  1915. # Ⓧ [CIRCLED LATIN CAPITAL LETTER X]
  1916. "\u24CD" => "X"
  1917. # X [FULLWIDTH LATIN CAPITAL LETTER X]
  1918. "\uFF38" => "X"
  1919. # ᶍ [LATIN SMALL LETTER X WITH PALATAL HOOK]
  1920. "\u1D8D" => "x"
  1921. # ẋ [LATIN SMALL LETTER X WITH DOT ABOVE]
  1922. "\u1E8B" => "x"
  1923. # ẍ [LATIN SMALL LETTER X WITH DIAERESIS]
  1924. "\u1E8D" => "x"
  1925. # ₓ [LATIN SUBSCRIPT SMALL LETTER X]
  1926. "\u2093" => "x"
  1927. # ⓧ [CIRCLED LATIN SMALL LETTER X]
  1928. "\u24E7" => "x"
  1929. # x [FULLWIDTH LATIN SMALL LETTER X]
  1930. "\uFF58" => "x"
  1931. # ⒳ [PARENTHESIZED LATIN SMALL LETTER X]
  1932. "\u24B3" => "(x)"
  1933. # Ý [LATIN CAPITAL LETTER Y WITH ACUTE]
  1934. "\u00DD" => "Y"
  1935. # Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX]
  1936. "\u0176" => "Y"
  1937. # Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS]
  1938. "\u0178" => "Y"
  1939. # Ƴ [LATIN CAPITAL LETTER Y WITH HOOK]
  1940. "\u01B3" => "Y"
  1941. # Ȳ [LATIN CAPITAL LETTER Y WITH MACRON]
  1942. "\u0232" => "Y"
  1943. # Ɏ [LATIN CAPITAL LETTER Y WITH STROKE]
  1944. "\u024E" => "Y"
  1945. # ʏ [LATIN LETTER SMALL CAPITAL Y]
  1946. "\u028F" => "Y"
  1947. # Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE]
  1948. "\u1E8E" => "Y"
  1949. # Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE]
  1950. "\u1EF2" => "Y"
  1951. # Ỵ [LATIN CAPITAL LETTER Y WITH DOT BELOW]
  1952. "\u1EF4" => "Y"
  1953. # Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE]
  1954. "\u1EF6" => "Y"
  1955. # Ỹ [LATIN CAPITAL LETTER Y WITH TILDE]
  1956. "\u1EF8" => "Y"
  1957. # Ỿ [LATIN CAPITAL LETTER Y WITH LOOP]
  1958. "\u1EFE" => "Y"
  1959. # Ⓨ [CIRCLED LATIN CAPITAL LETTER Y]
  1960. "\u24CE" => "Y"
  1961. # Y [FULLWIDTH LATIN CAPITAL LETTER Y]
  1962. "\uFF39" => "Y"
  1963. # ý [LATIN SMALL LETTER Y WITH ACUTE]
  1964. "\u00FD" => "y"
  1965. # ÿ [LATIN SMALL LETTER Y WITH DIAERESIS]
  1966. "\u00FF" => "y"
  1967. # ŷ [LATIN SMALL LETTER Y WITH CIRCUMFLEX]
  1968. "\u0177" => "y"
  1969. # ƴ [LATIN SMALL LETTER Y WITH HOOK]
  1970. "\u01B4" => "y"
  1971. # ȳ [LATIN SMALL LETTER Y WITH MACRON]
  1972. "\u0233" => "y"
  1973. # ɏ [LATIN SMALL LETTER Y WITH STROKE]
  1974. "\u024F" => "y"
  1975. # ʎ [LATIN SMALL LETTER TURNED Y]
  1976. "\u028E" => "y"
  1977. # ẏ [LATIN SMALL LETTER Y WITH DOT ABOVE]
  1978. "\u1E8F" => "y"
  1979. # ẙ [LATIN SMALL LETTER Y WITH RING ABOVE]
  1980. "\u1E99" => "y"
  1981. # ỳ [LATIN SMALL LETTER Y WITH GRAVE]
  1982. "\u1EF3" => "y"
  1983. # ỵ [LATIN SMALL LETTER Y WITH DOT BELOW]
  1984. "\u1EF5" => "y"
  1985. # ỷ [LATIN SMALL LETTER Y WITH HOOK ABOVE]
  1986. "\u1EF7" => "y"
  1987. # ỹ [LATIN SMALL LETTER Y WITH TILDE]
  1988. "\u1EF9" => "y"
  1989. # ỿ [LATIN SMALL LETTER Y WITH LOOP]
  1990. "\u1EFF" => "y"
  1991. # ⓨ [CIRCLED LATIN SMALL LETTER Y]
  1992. "\u24E8" => "y"
  1993. # y [FULLWIDTH LATIN SMALL LETTER Y]
  1994. "\uFF59" => "y"
  1995. # ⒴ [PARENTHESIZED LATIN SMALL LETTER Y]
  1996. "\u24B4" => "(y)"
  1997. # Ź [LATIN CAPITAL LETTER Z WITH ACUTE]
  1998. "\u0179" => "Z"
  1999. # Ż [LATIN CAPITAL LETTER Z WITH DOT ABOVE]
  2000. "\u017B" => "Z"
  2001. # Ž [LATIN CAPITAL LETTER Z WITH CARON]
  2002. "\u017D" => "Z"
  2003. # Ƶ [LATIN CAPITAL LETTER Z WITH STROKE]
  2004. "\u01B5" => "Z"
  2005. # Ȝ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH]
  2006. "\u021C" => "Z"
  2007. # Ȥ [LATIN CAPITAL LETTER Z WITH HOOK]
  2008. "\u0224" => "Z"
  2009. # ᴢ [LATIN LETTER SMALL CAPITAL Z]
  2010. "\u1D22" => "Z"
  2011. # Ẑ [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX]
  2012. "\u1E90" => "Z"
  2013. # Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW]
  2014. "\u1E92" => "Z"
  2015. # Ẕ [LATIN CAPITAL LETTER Z WITH LINE BELOW]
  2016. "\u1E94" => "Z"
  2017. # Ⓩ [CIRCLED LATIN CAPITAL LETTER Z]
  2018. "\u24CF" => "Z"
  2019. # Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER]
  2020. "\u2C6B" => "Z"
  2021. # Ꝣ [LATIN CAPITAL LETTER VISIGOTHIC Z]
  2022. "\uA762" => "Z"
  2023. # Z [FULLWIDTH LATIN CAPITAL LETTER Z]
  2024. "\uFF3A" => "Z"
  2025. # ź [LATIN SMALL LETTER Z WITH ACUTE]
  2026. "\u017A" => "z"
  2027. # ż [LATIN SMALL LETTER Z WITH DOT ABOVE]
  2028. "\u017C" => "z"
  2029. # ž [LATIN SMALL LETTER Z WITH CARON]
  2030. "\u017E" => "z"
  2031. # ƶ [LATIN SMALL LETTER Z WITH STROKE]
  2032. "\u01B6" => "z"
  2033. # ȝ http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH]
  2034. "\u021D" => "z"
  2035. # ȥ [LATIN SMALL LETTER Z WITH HOOK]
  2036. "\u0225" => "z"
  2037. # ɀ [LATIN SMALL LETTER Z WITH SWASH TAIL]
  2038. "\u0240" => "z"
  2039. # ʐ [LATIN SMALL LETTER Z WITH RETROFLEX HOOK]
  2040. "\u0290" => "z"
  2041. # ʑ [LATIN SMALL LETTER Z WITH CURL]
  2042. "\u0291" => "z"
  2043. # ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE]
  2044. "\u1D76" => "z"
  2045. # ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK]
  2046. "\u1D8E" => "z"
  2047. # ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX]
  2048. "\u1E91" => "z"
  2049. # ẓ [LATIN SMALL LETTER Z WITH DOT BELOW]
  2050. "\u1E93" => "z"
  2051. # ẕ [LATIN SMALL LETTER Z WITH LINE BELOW]
  2052. "\u1E95" => "z"
  2053. # ⓩ [CIRCLED LATIN SMALL LETTER Z]
  2054. "\u24E9" => "z"
  2055. # ⱬ [LATIN SMALL LETTER Z WITH DESCENDER]
  2056. "\u2C6C" => "z"
  2057. # ꝣ [LATIN SMALL LETTER VISIGOTHIC Z]
  2058. "\uA763" => "z"
  2059. # z [FULLWIDTH LATIN SMALL LETTER Z]
  2060. "\uFF5A" => "z"
  2061. # ⒵ [PARENTHESIZED LATIN SMALL LETTER Z]
  2062. "\u24B5" => "(z)"
  2063. # ⁰ [SUPERSCRIPT ZERO]
  2064. "\u2070" => "0"
  2065. # ₀ [SUBSCRIPT ZERO]
  2066. "\u2080" => "0"
  2067. # ⓪ [CIRCLED DIGIT ZERO]
  2068. "\u24EA" => "0"
  2069. # ⓿ [NEGATIVE CIRCLED DIGIT ZERO]
  2070. "\u24FF" => "0"
  2071. # 0 [FULLWIDTH DIGIT ZERO]
  2072. "\uFF10" => "0"
  2073. # ¹ [SUPERSCRIPT ONE]
  2074. "\u00B9" => "1"
  2075. # ₁ [SUBSCRIPT ONE]
  2076. "\u2081" => "1"
  2077. # ① [CIRCLED DIGIT ONE]
  2078. "\u2460" => "1"
  2079. # ⓵ [DOUBLE CIRCLED DIGIT ONE]
  2080. "\u24F5" => "1"
  2081. # ❶ [DINGBAT NEGATIVE CIRCLED DIGIT ONE]
  2082. "\u2776" => "1"
  2083. # ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE]
  2084. "\u2780" => "1"
  2085. # ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE]
  2086. "\u278A" => "1"
  2087. # 1 [FULLWIDTH DIGIT ONE]
  2088. "\uFF11" => "1"
  2089. # ⒈ [DIGIT ONE FULL STOP]
  2090. "\u2488" => "1."
  2091. # ⑴ [PARENTHESIZED DIGIT ONE]
  2092. "\u2474" => "(1)"
  2093. # ² [SUPERSCRIPT TWO]
  2094. "\u00B2" => "2"
  2095. # ₂ [SUBSCRIPT TWO]
  2096. "\u2082" => "2"
  2097. # ② [CIRCLED DIGIT TWO]
  2098. "\u2461" => "2"
  2099. # ⓶ [DOUBLE CIRCLED DIGIT TWO]
  2100. "\u24F6" => "2"
  2101. # ❷ [DINGBAT NEGATIVE CIRCLED DIGIT TWO]
  2102. "\u2777" => "2"
  2103. # ➁ [DINGBAT CIRCLED SANS-SERIF DIGIT TWO]
  2104. "\u2781" => "2"
  2105. # ➋ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO]
  2106. "\u278B" => "2"
  2107. # 2 [FULLWIDTH DIGIT TWO]
  2108. "\uFF12" => "2"
  2109. # ⒉ [DIGIT TWO FULL STOP]
  2110. "\u2489" => "2."
  2111. # ⑵ [PARENTHESIZED DIGIT TWO]
  2112. "\u2475" => "(2)"
  2113. # ³ [SUPERSCRIPT THREE]
  2114. "\u00B3" => "3"
  2115. # ₃ [SUBSCRIPT THREE]
  2116. "\u2083" => "3"
  2117. # ③ [CIRCLED DIGIT THREE]
  2118. "\u2462" => "3"
  2119. # ⓷ [DOUBLE CIRCLED DIGIT THREE]
  2120. "\u24F7" => "3"
  2121. # ❸ [DINGBAT NEGATIVE CIRCLED DIGIT THREE]
  2122. "\u2778" => "3"
  2123. # ➂ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE]
  2124. "\u2782" => "3"
  2125. # ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE]
  2126. "\u278C" => "3"
  2127. # 3 [FULLWIDTH DIGIT THREE]
  2128. "\uFF13" => "3"
  2129. # ⒊ [DIGIT THREE FULL STOP]
  2130. "\u248A" => "3."
  2131. # ⑶ [PARENTHESIZED DIGIT THREE]
  2132. "\u2476" => "(3)"
  2133. # ⁴ [SUPERSCRIPT FOUR]
  2134. "\u2074" => "4"
  2135. # ₄ [SUBSCRIPT FOUR]
  2136. "\u2084" => "4"
  2137. # ④ [CIRCLED DIGIT FOUR]
  2138. "\u2463" => "4"
  2139. # ⓸ [DOUBLE CIRCLED DIGIT FOUR]
  2140. "\u24F8" => "4"
  2141. # ❹ [DINGBAT NEGATIVE CIRCLED DIGIT FOUR]
  2142. "\u2779" => "4"
  2143. # ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR]
  2144. "\u2783" => "4"
  2145. # ➍ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR]
  2146. "\u278D" => "4"
  2147. # 4 [FULLWIDTH DIGIT FOUR]
  2148. "\uFF14" => "4"
  2149. # ⒋ [DIGIT FOUR FULL STOP]
  2150. "\u248B" => "4."
  2151. # ⑷ [PARENTHESIZED DIGIT FOUR]
  2152. "\u2477" => "(4)"
  2153. # ⁵ [SUPERSCRIPT FIVE]
  2154. "\u2075" => "5"
  2155. # ₅ [SUBSCRIPT FIVE]
  2156. "\u2085" => "5"
  2157. # ⑤ [CIRCLED DIGIT FIVE]
  2158. "\u2464" => "5"
  2159. # ⓹ [DOUBLE CIRCLED DIGIT FIVE]
  2160. "\u24F9" => "5"
  2161. # ❺ [DINGBAT NEGATIVE CIRCLED DIGIT FIVE]
  2162. "\u277A" => "5"
  2163. # ➄ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE]
  2164. "\u2784" => "5"
  2165. # ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE]
  2166. "\u278E" => "5"
  2167. # 5 [FULLWIDTH DIGIT FIVE]
  2168. "\uFF15" => "5"
  2169. # ⒌ [DIGIT FIVE FULL STOP]
  2170. "\u248C" => "5."
  2171. # ⑸ [PARENTHESIZED DIGIT FIVE]
  2172. "\u2478" => "(5)"
  2173. # ⁶ [SUPERSCRIPT SIX]
  2174. "\u2076" => "6"
  2175. # ₆ [SUBSCRIPT SIX]
  2176. "\u2086" => "6"
  2177. # ⑥ [CIRCLED DIGIT SIX]
  2178. "\u2465" => "6"
  2179. # ⓺ [DOUBLE CIRCLED DIGIT SIX]
  2180. "\u24FA" => "6"
  2181. # ❻ [DINGBAT NEGATIVE CIRCLED DIGIT SIX]
  2182. "\u277B" => "6"
  2183. # ➅ [DINGBAT CIRCLED SANS-SERIF DIGIT SIX]
  2184. "\u2785" => "6"
  2185. # ➏ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX]
  2186. "\u278F" => "6"
  2187. # 6 [FULLWIDTH DIGIT SIX]
  2188. "\uFF16" => "6"
  2189. # ⒍ [DIGIT SIX FULL STOP]
  2190. "\u248D" => "6."
  2191. # ⑹ [PARENTHESIZED DIGIT SIX]
  2192. "\u2479" => "(6)"
  2193. # ⁷ [SUPERSCRIPT SEVEN]
  2194. "\u2077" => "7"
  2195. # ₇ [SUBSCRIPT SEVEN]
  2196. "\u2087" => "7"
  2197. # ⑦ [CIRCLED DIGIT SEVEN]
  2198. "\u2466" => "7"
  2199. # ⓻ [DOUBLE CIRCLED DIGIT SEVEN]
  2200. "\u24FB" => "7"
  2201. # ❼ [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN]
  2202. "\u277C" => "7"
  2203. # ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN]
  2204. "\u2786" => "7"
  2205. # ➐ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN]
  2206. "\u2790" => "7"
  2207. # 7 [FULLWIDTH DIGIT SEVEN]
  2208. "\uFF17" => "7"
  2209. # ⒎ [DIGIT SEVEN FULL STOP]
  2210. "\u248E" => "7."
  2211. # ⑺ [PARENTHESIZED DIGIT SEVEN]
  2212. "\u247A" => "(7)"
  2213. # ⁸ [SUPERSCRIPT EIGHT]
  2214. "\u2078" => "8"
  2215. # ₈ [SUBSCRIPT EIGHT]
  2216. "\u2088" => "8"
  2217. # ⑧ [CIRCLED DIGIT EIGHT]
  2218. "\u2467" => "8"
  2219. # ⓼ [DOUBLE CIRCLED DIGIT EIGHT]
  2220. "\u24FC" => "8"
  2221. # ❽ [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT]
  2222. "\u277D" => "8"
  2223. # ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT]
  2224. "\u2787" => "8"
  2225. # ➑ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT]
  2226. "\u2791" => "8"
  2227. # 8 [FULLWIDTH DIGIT EIGHT]
  2228. "\uFF18" => "8"
  2229. # ⒏ [DIGIT EIGHT FULL STOP]
  2230. "\u248F" => "8."
  2231. # ⑻ [PARENTHESIZED DIGIT EIGHT]
  2232. "\u247B" => "(8)"
  2233. # ⁹ [SUPERSCRIPT NINE]
  2234. "\u2079" => "9"
  2235. # ₉ [SUBSCRIPT NINE]
  2236. "\u2089" => "9"
  2237. # ⑨ [CIRCLED DIGIT NINE]
  2238. "\u2468" => "9"
  2239. # ⓽ [DOUBLE CIRCLED DIGIT NINE]
  2240. "\u24FD" => "9"
  2241. # ❾ [DINGBAT NEGATIVE CIRCLED DIGIT NINE]
  2242. "\u277E" => "9"
  2243. # ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE]
  2244. "\u2788" => "9"
  2245. # ➒ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE]
  2246. "\u2792" => "9"
  2247. # 9 [FULLWIDTH DIGIT NINE]
  2248. "\uFF19" => "9"
  2249. # ⒐ [DIGIT NINE FULL STOP]
  2250. "\u2490" => "9."
  2251. # ⑼ [PARENTHESIZED DIGIT NINE]
  2252. "\u247C" => "(9)"
  2253. # ⑩ [CIRCLED NUMBER TEN]
  2254. "\u2469" => "10"
  2255. # ⓾ [DOUBLE CIRCLED NUMBER TEN]
  2256. "\u24FE" => "10"
  2257. # ❿ [DINGBAT NEGATIVE CIRCLED NUMBER TEN]
  2258. "\u277F" => "10"
  2259. # ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN]
  2260. "\u2789" => "10"
  2261. # ➓ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN]
  2262. "\u2793" => "10"
  2263. # ⒑ [NUMBER TEN FULL STOP]
  2264. "\u2491" => "10."
  2265. # ⑽ [PARENTHESIZED NUMBER TEN]
  2266. "\u247D" => "(10)"
  2267. # ⑪ [CIRCLED NUMBER ELEVEN]
  2268. "\u246A" => "11"
  2269. # ⓫ [NEGATIVE CIRCLED NUMBER ELEVEN]
  2270. "\u24EB" => "11"
  2271. # ⒒ [NUMBER ELEVEN FULL STOP]
  2272. "\u2492" => "11."
  2273. # ⑾ [PARENTHESIZED NUMBER ELEVEN]
  2274. "\u247E" => "(11)"
  2275. # ⑫ [CIRCLED NUMBER TWELVE]
  2276. "\u246B" => "12"
  2277. # ⓬ [NEGATIVE CIRCLED NUMBER TWELVE]
  2278. "\u24EC" => "12"
  2279. # ⒓ [NUMBER TWELVE FULL STOP]
  2280. "\u2493" => "12."
  2281. # ⑿ [PARENTHESIZED NUMBER TWELVE]
  2282. "\u247F" => "(12)"
  2283. # ⑬ [CIRCLED NUMBER THIRTEEN]
  2284. "\u246C" => "13"
  2285. # ⓭ [NEGATIVE CIRCLED NUMBER THIRTEEN]
  2286. "\u24ED" => "13"
  2287. # ⒔ [NUMBER THIRTEEN FULL STOP]
  2288. "\u2494" => "13."
  2289. # ⒀ [PARENTHESIZED NUMBER THIRTEEN]
  2290. "\u2480" => "(13)"
  2291. # ⑭ [CIRCLED NUMBER FOURTEEN]
  2292. "\u246D" => "14"
  2293. # ⓮ [NEGATIVE CIRCLED NUMBER FOURTEEN]
  2294. "\u24EE" => "14"
  2295. # ⒕ [NUMBER FOURTEEN FULL STOP]
  2296. "\u2495" => "14."
  2297. # ⒁ [PARENTHESIZED NUMBER FOURTEEN]
  2298. "\u2481" => "(14)"
  2299. # ⑮ [CIRCLED NUMBER FIFTEEN]
  2300. "\u246E" => "15"
  2301. # ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN]
  2302. "\u24EF" => "15"
  2303. # ⒖ [NUMBER FIFTEEN FULL STOP]
  2304. "\u2496" => "15."
  2305. # ⒂ [PARENTHESIZED NUMBER FIFTEEN]
  2306. "\u2482" => "(15)"
  2307. # ⑯ [CIRCLED NUMBER SIXTEEN]
  2308. "\u246F" => "16"
  2309. # ⓰ [NEGATIVE CIRCLED NUMBER SIXTEEN]
  2310. "\u24F0" => "16"
  2311. # ⒗ [NUMBER SIXTEEN FULL STOP]
  2312. "\u2497" => "16."
  2313. # ⒃ [PARENTHESIZED NUMBER SIXTEEN]
  2314. "\u2483" => "(16)"
  2315. # ⑰ [CIRCLED NUMBER SEVENTEEN]
  2316. "\u2470" => "17"
  2317. # ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN]
  2318. "\u24F1" => "17"
  2319. # ⒘ [NUMBER SEVENTEEN FULL STOP]
  2320. "\u2498" => "17."
  2321. # ⒄ [PARENTHESIZED NUMBER SEVENTEEN]
  2322. "\u2484" => "(17)"
  2323. # ⑱ [CIRCLED NUMBER EIGHTEEN]
  2324. "\u2471" => "18"
  2325. # ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN]
  2326. "\u24F2" => "18"
  2327. # ⒙ [NUMBER EIGHTEEN FULL STOP]
  2328. "\u2499" => "18."
  2329. # ⒅ [PARENTHESIZED NUMBER EIGHTEEN]
  2330. "\u2485" => "(18)"
  2331. # ⑲ [CIRCLED NUMBER NINETEEN]
  2332. "\u2472" => "19"
  2333. # ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN]
  2334. "\u24F3" => "19"
  2335. # ⒚ [NUMBER NINETEEN FULL STOP]
  2336. "\u249A" => "19."
  2337. # ⒆ [PARENTHESIZED NUMBER NINETEEN]
  2338. "\u2486" => "(19)"
  2339. # ⑳ [CIRCLED NUMBER TWENTY]
  2340. "\u2473" => "20"
  2341. # ⓴ [NEGATIVE CIRCLED NUMBER TWENTY]
  2342. "\u24F4" => "20"
  2343. # ⒛ [NUMBER TWENTY FULL STOP]
  2344. "\u249B" => "20."
  2345. # ⒇ [PARENTHESIZED NUMBER TWENTY]
  2346. "\u2487" => "(20)"
  2347. # « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK]
  2348. "\u00AB" => "\""
  2349. # » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK]
  2350. "\u00BB" => "\""
  2351. # “ [LEFT DOUBLE QUOTATION MARK]
  2352. "\u201C" => "\""
  2353. # ” [RIGHT DOUBLE QUOTATION MARK]
  2354. "\u201D" => "\""
  2355. # „ [DOUBLE LOW-9 QUOTATION MARK]
  2356. "\u201E" => "\""
  2357. # ″ [DOUBLE PRIME]
  2358. "\u2033" => "\""
  2359. # ‶ [REVERSED DOUBLE PRIME]
  2360. "\u2036" => "\""
  2361. # ❝ [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT]
  2362. "\u275D" => "\""
  2363. # ❞ [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT]
  2364. "\u275E" => "\""
  2365. # ❮ [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT]
  2366. "\u276E" => "\""
  2367. # ❯ [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT]
  2368. "\u276F" => "\""
  2369. # " [FULLWIDTH QUOTATION MARK]
  2370. "\uFF02" => "\""
  2371. # ‘ [LEFT SINGLE QUOTATION MARK]
  2372. "\u2018" => "\'"
  2373. # ’ [RIGHT SINGLE QUOTATION MARK]
  2374. "\u2019" => "\'"
  2375. # ‚ [SINGLE LOW-9 QUOTATION MARK]
  2376. "\u201A" => "\'"
  2377. # ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK]
  2378. "\u201B" => "\'"
  2379. # ′ [PRIME]
  2380. "\u2032" => "\'"
  2381. # ‵ [REVERSED PRIME]
  2382. "\u2035" => "\'"
  2383. # ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK]
  2384. "\u2039" => "\'"
  2385. # › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK]
  2386. "\u203A" => "\'"
  2387. # ❛ [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT]
  2388. "\u275B" => "\'"
  2389. # ❜ [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT]
  2390. "\u275C" => "\'"
  2391. # ' [FULLWIDTH APOSTROPHE]
  2392. "\uFF07" => "\'"
  2393. # ‐ [HYPHEN]
  2394. "\u2010" => "-"
  2395. # ‑ [NON-BREAKING HYPHEN]
  2396. "\u2011" => "-"
  2397. # ‒ [FIGURE DASH]
  2398. "\u2012" => "-"
  2399. # – [EN DASH]
  2400. "\u2013" => "-"
  2401. # — [EM DASH]
  2402. "\u2014" => "-"
  2403. # ⁻ [SUPERSCRIPT MINUS]
  2404. "\u207B" => "-"
  2405. # ₋ [SUBSCRIPT MINUS]
  2406. "\u208B" => "-"
  2407. # - [FULLWIDTH HYPHEN-MINUS]
  2408. "\uFF0D" => "-"
  2409. # ⁅ [LEFT SQUARE BRACKET WITH QUILL]
  2410. "\u2045" => "["
  2411. # ❲ [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT]
  2412. "\u2772" => "["
  2413. # [ [FULLWIDTH LEFT SQUARE BRACKET]
  2414. "\uFF3B" => "["
  2415. # ⁆ [RIGHT SQUARE BRACKET WITH QUILL]
  2416. "\u2046" => "]"
  2417. # ❳ [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT]
  2418. "\u2773" => "]"
  2419. # ] [FULLWIDTH RIGHT SQUARE BRACKET]
  2420. "\uFF3D" => "]"
  2421. # ⁽ [SUPERSCRIPT LEFT PARENTHESIS]
  2422. "\u207D" => "("
  2423. # ₍ [SUBSCRIPT LEFT PARENTHESIS]
  2424. "\u208D" => "("
  2425. # ❨ [MEDIUM LEFT PARENTHESIS ORNAMENT]
  2426. "\u2768" => "("
  2427. # ❪ [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT]
  2428. "\u276A" => "("
  2429. # ( [FULLWIDTH LEFT PARENTHESIS]
  2430. "\uFF08" => "("
  2431. # ⸨ [LEFT DOUBLE PARENTHESIS]
  2432. "\u2E28" => "(("
  2433. # ⁾ [SUPERSCRIPT RIGHT PARENTHESIS]
  2434. "\u207E" => ")"
  2435. # ₎ [SUBSCRIPT RIGHT PARENTHESIS]
  2436. "\u208E" => ")"
  2437. # ❩ [MEDIUM RIGHT PARENTHESIS ORNAMENT]
  2438. "\u2769" => ")"
  2439. # ❫ [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT]
  2440. "\u276B" => ")"
  2441. # ) [FULLWIDTH RIGHT PARENTHESIS]
  2442. "\uFF09" => ")"
  2443. # ⸩ [RIGHT DOUBLE PARENTHESIS]
  2444. "\u2E29" => "))"
  2445. # ❬ [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT]
  2446. "\u276C" => "<"
  2447. # ❰ [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT]
  2448. "\u2770" => "<"
  2449. # < [FULLWIDTH LESS-THAN SIGN]
  2450. "\uFF1C" => "<"
  2451. # ❭ [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT]
  2452. "\u276D" => ">"
  2453. # ❱ [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT]
  2454. "\u2771" => ">"
  2455. # > [FULLWIDTH GREATER-THAN SIGN]
  2456. "\uFF1E" => ">"
  2457. # ❴ [MEDIUM LEFT CURLY BRACKET ORNAMENT]
  2458. "\u2774" => "{"
  2459. # { [FULLWIDTH LEFT CURLY BRACKET]
  2460. "\uFF5B" => "{"
  2461. # ❵ [MEDIUM RIGHT CURLY BRACKET ORNAMENT]
  2462. "\u2775" => "}"
  2463. # } [FULLWIDTH RIGHT CURLY BRACKET]
  2464. "\uFF5D" => "}"
  2465. # ⁺ [SUPERSCRIPT PLUS SIGN]
  2466. "\u207A" => "+"
  2467. # ₊ [SUBSCRIPT PLUS SIGN]
  2468. "\u208A" => "+"
  2469. # + [FULLWIDTH PLUS SIGN]
  2470. "\uFF0B" => "+"
  2471. # ⁼ [SUPERSCRIPT EQUALS SIGN]
  2472. "\u207C" => "="
  2473. # ₌ [SUBSCRIPT EQUALS SIGN]
  2474. "\u208C" => "="
  2475. # = [FULLWIDTH EQUALS SIGN]
  2476. "\uFF1D" => "="
  2477. # ! [FULLWIDTH EXCLAMATION MARK]
  2478. "\uFF01" => "!"
  2479. # ‼ [DOUBLE EXCLAMATION MARK]
  2480. "\u203C" => "!!"
  2481. # ⁉ [EXCLAMATION QUESTION MARK]
  2482. "\u2049" => "!?"
  2483. # # [FULLWIDTH NUMBER SIGN]
  2484. "\uFF03" => "#"
  2485. # $ [FULLWIDTH DOLLAR SIGN]
  2486. "\uFF04" => "$"
  2487. # ⁒ [COMMERCIAL MINUS SIGN]
  2488. "\u2052" => "%"
  2489. # % [FULLWIDTH PERCENT SIGN]
  2490. "\uFF05" => "%"
  2491. # & [FULLWIDTH AMPERSAND]
  2492. "\uFF06" => "&"
  2493. # ⁎ [LOW ASTERISK]
  2494. "\u204E" => "*"
  2495. # * [FULLWIDTH ASTERISK]
  2496. "\uFF0A" => "*"
  2497. # , [FULLWIDTH COMMA]
  2498. "\uFF0C" => ","
  2499. # . [FULLWIDTH FULL STOP]
  2500. "\uFF0E" => "."
  2501. # ⁄ [FRACTION SLASH]
  2502. "\u2044" => "/"
  2503. # / [FULLWIDTH SOLIDUS]
  2504. "\uFF0F" => "/"
  2505. # : [FULLWIDTH COLON]
  2506. "\uFF1A" => ":"
  2507. # ⁏ [REVERSED SEMICOLON]
  2508. "\u204F" => ";"
  2509. # ; [FULLWIDTH SEMICOLON]
  2510. "\uFF1B" => ";"
  2511. # ? [FULLWIDTH QUESTION MARK]
  2512. "\uFF1F" => "?"
  2513. # ⁇ [DOUBLE QUESTION MARK]
  2514. "\u2047" => "??"
  2515. # ⁈ [QUESTION EXCLAMATION MARK]
  2516. "\u2048" => "?!"
  2517. # @ [FULLWIDTH COMMERCIAL AT]
  2518. "\uFF20" => "@"
  2519. # \ [FULLWIDTH REVERSE SOLIDUS]
  2520. "\uFF3C" => "\\"
  2521. # ‸ [CARET]
  2522. "\u2038" => "^"
  2523. # ^ [FULLWIDTH CIRCUMFLEX ACCENT]
  2524. "\uFF3E" => "^"
  2525. # _ [FULLWIDTH LOW LINE]
  2526. "\uFF3F" => "_"
  2527. # ⁓ [SWUNG DASH]
  2528. "\u2053" => "~"
  2529. # ~ [FULLWIDTH TILDE]
  2530. "\uFF5E" => "~"
  2531. ################################################################
  2532. # Below is the Perl script used to generate the above mappings #
  2533. # from ASCIIFoldingFilter.java: #
  2534. ################################################################
  2535. #
  2536. # #!/usr/bin/perl
  2537. #
  2538. # use warnings;
  2539. # use strict;
  2540. #
  2541. # my @source_chars = ();
  2542. # my @source_char_descriptions = ();
  2543. # my $target = '';
  2544. #
  2545. # while (<>) {
  2546. # if (/case\s+'(\\u[A-F0-9]+)':\s*\/\/\s*(.*)/i) {
  2547. # push @source_chars, $1;
  2548. # push @source_char_descriptions, $2;
  2549. # next;
  2550. # }
  2551. # if (/output\[[^\]]+\]\s*=\s*'(\\'|\\\\|.)'/) {
  2552. # $target .= $1;
  2553. # next;
  2554. # }
  2555. # if (/break;/) {
  2556. # $target = "\\\"" if ($target eq '"');
  2557. # for my $source_char_num (0..$#source_chars) {
  2558. # print "# $source_char_descriptions[$source_char_num]\n";
  2559. # print "\"$source_chars[$source_char_num]\" => \"$target\"\n\n";
  2560. # }
  2561. # @source_chars = ();
  2562. # @source_char_descriptions = ();
  2563. # $target = '';
  2564. # }
  2565. # }