######################################################################## # BGN/PCGN Agreement # # The modified Hepburn system for the romanization of Japanese has been # in use by the U.S. Board on Geographic Names since about 1930 and has # been used extensively in the romanization of Japanese geographic names. # The system is well adapted to the general needs of speakers of English # and is the most widely used system for the romanization of Japanese. # # Prepared by Michael Everson <everson@evertype.com> ######################################################################## # # MINIMAL FILTER: Japanese-Latin # :: [あいうえおかがきぎくぐけげこごさざしじすずせぜそぞただちぢっつづてでとどなにぬねのはばぱひびぴふぶぷへべぺほぼぽまみむめもゃやゅゆょよらりるれろわゐゑをんゔアイウエオカガキギクグケゲコゴサザシジスズセゼソゾタダチヂッツヅテデトドナニヌネノハバパヒビピフブプヘベペホボポマミムメモャヤュユョヨラリルレロワヰヱヲンヴ] ; :: NFD (NFC) ; # ######################################################################## ######################################################################## # # Define All Transformation Variables # ######################################################################## $apostrophe = ’; # Use this $wordBoundary until bug 2034 is fixed in ICU: # http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest # $wordBoundary = [^[:L:][:M:][:N:]] ; ######################################################################## # # Rules moved to front to avoid masking # ######################################################################## ######################################################################## # # BGN Page 45 Rule 2: # # A small-script tsu form (ッ or っ) is inserted between kana symbols # to indicate a double consonant and is romanized as k before k; # as s before s or sh; as t before t, ts, or ch; and as p before p. # ######################################################################## # ッ}[カキクケコ] → k ; # KATAKANA LETTER SMALL TU っ}[かきくけこ] → k ; # HIRAGANA LETTER SMALL TU ッ}[サシスセソ] → s ; # KATAKANA LETTER SMALL TU っ}[さしすせそ] → s ; # HIRAGANA LETTER SMALL TU ッ}[タチツテト] → t ; # KATAKANA LETTER SMALL TU っ}[たちつてと] → t ; # HIRAGANA LETTER SMALL TU ッ}[パピプペポ] → p ; # KATAKANA LETTER SMALL TU っ}[ぱぴぷぺぽ] → p ; # HIRAGANA LETTER SMALL TU # ######################################################################## # # End of Rule 2 # ######################################################################## ######################################################################## # # Start of Syllabic Transformations # ######################################################################## # ア → a ; # KATAKANA LETTER A イ → i ; # KATAKANA LETTER I ウ → u ; # KATAKANA LETTER U エ → e ; # KATAKANA LETTER E オウ → ō ; # KATAKANA LETTER O + U オ → o ; # KATAKANA LETTER O カ → ka ; # KATAKANA LETTER KA キョウ → kyō ; # KATAKANA LETTER KI + SMALL YO + U キュウ → kyū ; # KATAKANA LETTER KI + SMALL YU + U キャ → kya ; # KATAKANA LETTER KI + SMALL YA キョ → kyo ; # KATAKANA LETTER KI + SMALL YO キュ → kyu ; # KATAKANA LETTER KI + SMALL YU キ → ki ; # KATAKANA LETTER KI ク → ku ; # KATAKANA LETTER KU ケ → ke ; # KATAKANA LETTER KE コウ → kō ; # KATAKANA LETTER KO + U コ → ko ; # KATAKANA LETTER KO サ → sa ; # KATAKANA LETTER SA ショウ → shō ; # KATAKANA LETTER SI + SMALL YO + U シュウ → shū ; # KATAKANA LETTER SI + SMALL YU + U シャ → sha ; # KATAKANA LETTER SI + SMALL YA ショ → sho ; # KATAKANA LETTER SI + SMALL YO シュ → shu ; # KATAKANA LETTER SI + SMALL YU シ → shi ; # KATAKANA LETTER SI ス → su ; # KATAKANA LETTER SU セ → se ; # KATAKANA LETTER SE ソウ → sō ; # KATAKANA LETTER SO + U ソ → so ; # KATAKANA LETTER SO タ → ta ; # KATAKANA LETTER TA チョウ → chō ; # KATAKANA LETTER TI + SMALL YO + U チュウ → chū ; # KATAKANA LETTER TI + SMALL YU + U チャ → cha ; # KATAKANA LETTER TI + SMALL YA チョ → cho ; # KATAKANA LETTER TI + SMALL YO チュ → chu ; # KATAKANA LETTER TI + SMALL YU チ → chi ; # KATAKANA LETTER TI ツ → tsu ; # KATAKANA LETTER TU テ → te ; # KATAKANA LETTER TE トウ → tō ; # KATAKANA LETTER TO + U ト → to ; # KATAKANA LETTER TO ナ → na ; # KATAKANA LETTER NA ニョウ → nyō ; # KATAKANA LETTER NI + SMALL YO + U ニュウ → nyū ; # KATAKANA LETTER NI + SMALL YU + U ニャ → nya ; # KATAKANA LETTER NI + SMALL YA ニョ → nyo ; # KATAKANA LETTER NI + SMALL YO ニュ → nyu ; # KATAKANA LETTER NI + SMALL YU ニ → ni ; # KATAKANA LETTER NI ヌ → nu ; # KATAKANA LETTER NU ネ → ne ; # KATAKANA LETTER NE ノウ → nō ; # KATAKANA LETTER NO + U ノ → no ; # KATAKANA LETTER NO ハ → ha ; # KATAKANA LETTER HA ヒョウ → hyō ; # KATAKANA LETTER HI + SMALL YO + U ヒュウ → hyū ; # KATAKANA LETTER HI + SMALL YU + U ヒャ → hya ; # KATAKANA LETTER HI + SMALL YA ヒョ → hyo ; # KATAKANA LETTER HI + SMALL YO ヒュ → hyu ; # KATAKANA LETTER HI + SMALL YU ヒ → hi ; # KATAKANA LETTER HI フ → fu ; # KATAKANA LETTER HU ヘ → he ; # KATAKANA LETTER HE ホウ → hō ; # KATAKANA LETTER HO + U ホ → ho ; # KATAKANA LETTER HO マ → ma ; # KATAKANA LETTER MA ミョウ → hyō ; # KATAKANA LETTER MI + SMALL YO + U ミュウ → hyū ; # KATAKANA LETTER MI + SMALL YU + U ミャ → hya ; # KATAKANA LETTER MI + SMALL YA ミョ → hyo ; # KATAKANA LETTER MI + SMALL YO ミュ → hyu ; # KATAKANA LETTER MI + SMALL YU ミ → mi ; # KATAKANA LETTER MI ム → mu ; # KATAKANA LETTER MU メ → me ; # KATAKANA LETTER ME モウ → mō ; # KATAKANA LETTER MO + U モ → mo ; # KATAKANA LETTER MO ヤ → ya ; # KATAKANA LETTER YA ユ → yu ; # KATAKANA LETTER YU ヨウ → yō ; # KATAKANA LETTER YO + U ヨ → yo ; # KATAKANA LETTER YO ラ → ra ; # KATAKANA LETTER RA リョウ → ryō ; # KATAKANA LETTER RI + SMALL YO + U リュウ → ryū ; # KATAKANA LETTER RI + SMALL YU + U リャ → rya ; # KATAKANA LETTER RI + SMALL YA リョ → ryo ; # KATAKANA LETTER RI + SMALL YO リュ → ryu ; # KATAKANA LETTER RI + SMALL YU リ → ri ; # KATAKANA LETTER RI ル → ru ; # KATAKANA LETTER RU レ → re ; # KATAKANA LETTER RE ロウ → rō ; # KATAKANA LETTER RO + U ロ → ro ; # KATAKANA LETTER RO ワ → wa ; # KATAKANA LETTER WA ヰ → i ; # KATAKANA LETTER WI ヱ → e ; # KATAKANA LETTER WE ヲ → o ; # KATAKANA LETTER WO # ######################################################################## # # BGN Page 45 Rule 3: # # The character ン should be romanized m before b, p, or m. # The character ん should be romanized m before b, p, or m. # The character ン should be romanized n’ before y or a vowel letter. # The character ん should be romanized n’ before y or a vowel letter. # ######################################################################## # ン}[バビブベボパピプペポマミムメモ] → m ; # KATAKANA LETTER N ん}[ばびぶべぼぱぴぷぺぽまみむめも] → m ; # HIRAGANA LETTER N ン}[ヤユヨアイウエオ] → n $apostrophe ; # KATAKANA LETTER N ん}[やゆよあいうえお] → n $apostrophe ; # HIRAGANA LETTER N # ######################################################################## # # End of Rule 3 # ######################################################################## # ン → n ; # KATAKANA LETTER N ガ → ga ; # KATAKANA LETTER GA ギョウ → gyō ; # KATAKANA LETTER GI + SMALL YO + U ギュウ → gyū ; # KATAKANA LETTER GI + SMALL YU + U ギャ → gya ; # KATAKANA LETTER GI + SMALL YA ギョ → gyo ; # KATAKANA LETTER GI + SMALL YO ギュ → gyu ; # KATAKANA LETTER GI + SMALL YU ギ → gi ; # KATAKANA LETTER GI グ → gu ; # KATAKANA LETTER GU ゲ → ge ; # KATAKANA LETTER GE ゴウ → gō ; # KATAKANA LETTER GO + U ゴ → go ; # KATAKANA LETTER GO ザ → za ; # KATAKANA LETTER ZA ジョウ → jō ; # KATAKANA LETTER ZI + SMALL YO + U ジュウ → jū ; # KATAKANA LETTER ZI + SMALL YU + U ジャ → ja ; # KATAKANA LETTER ZI + SMALL YA ジョ → jo ; # KATAKANA LETTER ZI + SMALL YO ジュ → ju ; # KATAKANA LETTER ZI + SMALL YU ジ → ji ; # KATAKANA LETTER ZI ズ → zu ; # KATAKANA LETTER ZU ゼ → ze ; # KATAKANA LETTER ZE ゾウ → zō ; # KATAKANA LETTER ZO + U ゾ → zo ; # KATAKANA LETTER ZO ダ → da ; # KATAKANA LETTER DA ヂ → ji ; # KATAKANA LETTER DI ヅ → zu ; # KATAKANA LETTER DU デ → de ; # KATAKANA LETTER DE ドウ → dō ; # KATAKANA LETTER DO + U ド → do ; # KATAKANA LETTER DO バ → ba ; # KATAKANA LETTER BA ビョウ → byō ; # KATAKANA LETTER BI + SMALL YO + U ビュウ → byū ; # KATAKANA LETTER BI + SMALL YU + U ビャ → bya ; # KATAKANA LETTER BI + SMALL YA ビョ → byo ; # KATAKANA LETTER BI + SMALL YO ビュ → byu ; # KATAKANA LETTER BI + SMALL YU ビ → bi ; # KATAKANA LETTER BI ブ → bu ; # KATAKANA LETTER BU ベ → be ; # KATAKANA LETTER BE ボウ → bō ; # KATAKANA LETTER BO + U ボ → bo ; # KATAKANA LETTER BO パ → pa ; # KATAKANA LETTER PA ピョウ → pyō ; # KATAKANA LETTER PI + SMALL YO + U ピュウ → pyū ; # KATAKANA LETTER PI + SMALL YU + U ピャ → pya ; # KATAKANA LETTER PI + SMALL YA ピョ → pyo ; # KATAKANA LETTER PI + SMALL YO ピュ → pyu ; # KATAKANA LETTER PI + SMALL YU ピ → pi ; # KATAKANA LETTER PI プ → pu ; # KATAKANA LETTER PU ペ → pe ; # KATAKANA LETTER PE ポウ → pō ; # KATAKANA LETTER PO + U ポ → po ; # KATAKANA LETTER PO ヴ → v ; # KATAKANA LETTER VU あ → a ; # HIRAGANA LETTER A い → i ; # HIRAGANA LETTER I う → u ; # HIRAGANA LETTER U え → e ; # HIRAGANA LETTER E おう → ō ; # HIRAGANA LETTER O + U お → o ; # HIRAGANA LETTER O か → ka ; # HIRAGANA LETTER KA きょう → kyō ; # HIRAGANA LETTER KI + SMALL YO + U きゅう → kyū ; # HIRAGANA LETTER KI + SMALL YU + U きゃ → kya ; # HIRAGANA LETTER KI + SMALL YA きょ → kyo ; # HIRAGANA LETTER KI + SMALL YO きゅ → kyu ; # HIRAGANA LETTER KI + SMALL YU き → ki ; # HIRAGANA LETTER KI く → ku ; # HIRAGANA LETTER KU け → ke ; # HIRAGANA LETTER KE こう → kō ; # HIRAGANA LETTER KO + U こ → ko ; # HIRAGANA LETTER KO さ → sa ; # HIRAGANA LETTER SA しょう → shō ; # HIRAGANA LETTER SI + SMALL YO + U しゅう → shū ; # HIRAGANA LETTER SI + SMALL YU + U しゃ → sha ; # HIRAGANA LETTER SI + SMALL YA しょ → sho ; # HIRAGANA LETTER SI + SMALL YO しゅ → shu ; # HIRAGANA LETTER SI + SMALL YU し → shi ; # HIRAGANA LETTER SI す → su ; # HIRAGANA LETTER SU せ → se ; # HIRAGANA LETTER SE そう → sō ; # HIRAGANA LETTER SO + U そ → so ; # HIRAGANA LETTER SO た → ta ; # HIRAGANA LETTER TA ちょう → chō ; # HIRAGANA LETTER TI + SMALL YO + U ちゅう → chū ; # HIRAGANA LETTER TI + SMALL YU + U ちゃ → cha ; # HIRAGANA LETTER TI + SMALL YA ちょ → cho ; # HIRAGANA LETTER TI + SMALL YO ちゅ → chu ; # HIRAGANA LETTER TI + SMALL YU ち → chi ; # HIRAGANA LETTER TI つ → tsu ; # HIRAGANA LETTER TU て → te ; # HIRAGANA LETTER TE とう → tō ; # HIRAGANA LETTER TO + U と → to ; # HIRAGANA LETTER TO な → na ; # HIRAGANA LETTER NA にょう → nyō ; # HIRAGANA LETTER NI + SMALL YO + U にゅう → nyū ; # HIRAGANA LETTER NI + SMALL YU + U にゃ → nya ; # HIRAGANA LETTER NI + SMALL YA にょ → nyo ; # HIRAGANA LETTER NI + SMALL YO にゅ → nyu ; # HIRAGANA LETTER NI + SMALL YU に → ni ; # HIRAGANA LETTER NI ぬ → nu ; # HIRAGANA LETTER NU ね → ne ; # HIRAGANA LETTER NE のう → nō ; # HIRAGANA LETTER NO + U の → no ; # HIRAGANA LETTER NO は → ha ; # HIRAGANA LETTER HA ひょう → hyō ; # HIRAGANA LETTER HI + SMALL YO + U ひゅう → hyū ; # HIRAGANA LETTER HI + SMALL YU + U ひゃ → hya ; # HIRAGANA LETTER HI + SMALL YA ひょ → hyo ; # HIRAGANA LETTER HI + SMALL YO ひゅ → hyu ; # HIRAGANA LETTER HI + SMALL YU ひ → hi ; # HIRAGANA LETTER HI ふ → fu ; # HIRAGANA LETTER HU へ → he ; # HIRAGANA LETTER HE ほう → hō ; # HIRAGANA LETTER HO + U ほ → ho ; # HIRAGANA LETTER HO ま → ma ; # HIRAGANA LETTER MA みょう → hyō ; # HIRAGANA LETTER MI + SMALL YO + U みゅう → hyū ; # HIRAGANA LETTER MI + SMALL YU + U みゃ → hya ; # HIRAGANA LETTER MI + SMALL YA みょ → hyo ; # HIRAGANA LETTER MI + SMALL YO みゅ → hyu ; # HIRAGANA LETTER MI + SMALL YU み → mi ; # HIRAGANA LETTER MI む → mu ; # HIRAGANA LETTER MU め → me ; # HIRAGANA LETTER ME もう → mō ; # HIRAGANA LETTER MO + U も → mo ; # HIRAGANA LETTER MO や → ya ; # HIRAGANA LETTER YA ゆ → yu ; # HIRAGANA LETTER YU よう → yō ; # HIRAGANA LETTER YO + U よ → yo ; # HIRAGANA LETTER YO ら → ra ; # HIRAGANA LETTER RA りょう → ryō ; # HIRAGANA LETTER RI + SMALL YO + U りゅう → ryū ; # HIRAGANA LETTER RI + SMALL YU + U りゃ → rya ; # HIRAGANA LETTER RI + SMALL YA りょ → ryo ; # HIRAGANA LETTER RI + SMALL YO りゅ → ryu ; # HIRAGANA LETTER RI + SMALL YU り → ri ; # HIRAGANA LETTER RI る → ru ; # HIRAGANA LETTER RU れ → re ; # HIRAGANA LETTER RE ろう → rō ; # HIRAGANA LETTER RO + U ろ → ro ; # HIRAGANA LETTER RO わ → wa ; # HIRAGANA LETTER WA ゐ → i ; # HIRAGANA LETTER WI ゑ → e ; # HIRAGANA LETTER WE を → o ; # HIRAGANA LETTER WO ん → n ; # HIRAGANA LETTER N が → ga ; # HIRAGANA LETTER GA ぎょう → gyō ; # HIRAGANA LETTER GI + SMALL YO + U ぎゅう → gyū ; # HIRAGANA LETTER GI + SMALL YU + U ぎゃ → gya ; # HIRAGANA LETTER GI + SMALL YA ぎょ → gyo ; # HIRAGANA LETTER GI + SMALL YO ぎゅ → gyu ; # HIRAGANA LETTER GI + SMALL YU ぎ → gi ; # HIRAGANA LETTER GI ぐ → gu ; # HIRAGANA LETTER GU げ → ge ; # HIRAGANA LETTER GE ごう → gō ; # HIRAGANA LETTER GO + U ご → go ; # HIRAGANA LETTER GO ざ → za ; # HIRAGANA LETTER ZA じょう → jō ; # HIRAGANA LETTER ZI + SMALL YO + U じゅう → jū ; # HIRAGANA LETTER ZI + SMALL YU + U じゃ → ja ; # HIRAGANA LETTER ZI + SMALL YA じょ → jo ; # HIRAGANA LETTER ZI + SMALL YO じゅ → ju ; # HIRAGANA LETTER ZI + SMALL YU じ → ji ; # HIRAGANA LETTER ZI ず → zu ; # HIRAGANA LETTER ZU ぜ → ze ; # HIRAGANA LETTER ZE ぞう → zō ; # HIRAGANA LETTER ZO + U ぞ → zo ; # HIRAGANA LETTER ZO だ → da ; # HIRAGANA LETTER DA ぢ → ji ; # HIRAGANA LETTER DI づ → zu ; # HIRAGANA LETTER DU で → de ; # HIRAGANA LETTER DE どう → dō ; # HIRAGANA LETTER DO + U ど → do ; # HIRAGANA LETTER DO ば → ba ; # HIRAGANA LETTER BA びょう → byō ; # HIRAGANA LETTER BI + SMALL YO + U びゅう → byū ; # HIRAGANA LETTER BI + SMALL YU + U びゃ → bya ; # HIRAGANA LETTER BI + SMALL YA びょ → byo ; # HIRAGANA LETTER BI + SMALL YO びゅ → byu ; # HIRAGANA LETTER BI + SMALL YU び → bi ; # HIRAGANA LETTER BI ぶ → bu ; # HIRAGANA LETTER BU べ → be ; # HIRAGANA LETTER BE ぼう → bō ; # HIRAGANA LETTER BO + U ぼ → bo ; # HIRAGANA LETTER BO ぱ → pa ; # HIRAGANA LETTER PA ぴょう → pyō ; # HIRAGANA LETTER PI + SMALL YO + U ぴゅう → pyū ; # HIRAGANA LETTER PI + SMALL YU + U ぴゃ → pya ; # HIRAGANA LETTER PI + SMALL YA ぴょ → pyo ; # HIRAGANA LETTER PI + SMALL YO ぴゅ → pyu ; # HIRAGANA LETTER PI + SMALL YU ぴ → pi ; # HIRAGANA LETTER PI ぷ → pu ; # HIRAGANA LETTER PU ぺ → pe ; # HIRAGANA LETTER PE ぽう → pō ; # HIRAGANA LETTER PO + U ぽ → po ; # HIRAGANA LETTER PO ゔ → v ; # HIRAGANA LETTER VU # ########################################################################