interscript 0.1.2 → 0.1.7

data/maps/bgnpcgn-tat-Cyrl-Latn-2007.yaml

@@ -0,0 +1,220 @@
+---
+authority_id: bgnpcgn
+id: 2007
+language: iso-639-2:tat
+source_script: Cyrl
+destination_script: Latn
+name: TATAR TABLE OF CORRESPONDENCES CYRILLIC - ROMAN BGN/PCGN 2007 Agreement
+alias:
+  ogc11122:
+    code: tat_Cyrl2Latn_BGN_2005
+    description: Tatar is an official language within Respublika Tatarstan, one of the republics of the Russian Federation.
+url: https://geonames.nga.mil/gns/html/Romanization/TABLE%20OF%20CORRESPONDENCES%20FOR%20TATAR.pdf
+creation_date: 2007
+confirmation_date: 2017-11
+description: |
+  Tatar is an official language within Respublika Tatarstan, one of the republics of the Russian
+  Federation. It will normally be encountered in Cyrillic script, in which case it should be romanized by means
+  of the Cyrillic-Roman table of correspondences given below.
+
+notes:
+  - |
+    The alphabet portrayed in the above table is referred to as yaꞑalif-2. 
+    A set of simpler characters is also encountered; this is known as zamanalif. 
+    In this latter set, the alternative characters ä, ñ and ö are used for letters
+    2, 17 and 19 respectively where the user has difficulty reproducing ə, ꞑ, and ө.
+    Please note that all three alternatives must be used as a set, and the letters should not be intermingled.
+  - Used only in borrowed words.
+  - The first option is used in words with back vowels, the second in words with front vowels (though this does not apply to borrowed words).
+  - yı/ye is used after a vowel (except и, ю), ъ and ь, also word-initially.
+  - w is used after a vowel.
+  - After ğ or q, ый is represented i
+  - Э is represented ’ after a vowel in words of Arabic origin.
+  - Ю and Я are represented ü and a/ä respectively after и.
+  - |
+    An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters
+    of the basic Roman script is:
+        Ə (U+018F) ə (U+0259)
+        Ğ (U+011E) ğ (U+011F)
+        İ (U+0130) ı (U+0131)
+        Ü (U+00DC) ü (U+00FC)
+        Ꞑ (U+A790) ꞑ (U+A791)
+        Ɵ (U+019F) ɵ (U+0275)
+        Ç (U+00C7) ç (U+00E7)
+        Ş (U+015E) ş (U+015F)
+        Ä (U+00C4) ä (U+00E4)
+        ’ (U+2019)
+  - |
+    The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase
+    Roman letters as appropriate should be used.
+
+tests:
+  - source: Гыйльмиев # 
+    expected: Ğil’miew # note[6] in the note it's Ğilmiev which incorrect according to the rules
+  # https://en.wikipedia.org/wiki/Tatar_alphabet
+  - source: баеды
+    expected: bayıdı # note[4]
+  - source: кардәш 
+    expected: qardəş
+  - source: калынлык һәм аеру билгесе
+    expected: qalınlıq həm ayıru bilgese # note[4]
+  - source: |
+      Барлык кешеләр дә азат һәм үз абруйлары һәм хокуклары ягыннан тиң булып туалар.
+      Аларга акыл һәм вөҗдан бирелгән һәм бер-берсенә карата туганнарча мөнасәбәттә булырга тиешләр.
+    expected: |
+      Barlıq keşelər də azat həm üz abruyları həm xoquqları yağınnan tiꞑ bulıp tualar.
+      Alarğa aqıl həm wocdan birelgən həm ber-bersenə qarata tuğannarça monasəbəttə bulırğa tieşlər.
+  # https://www.azatliq.org/a/30820571.html
+  - source: Әлдермештән Әлмәндәр
+    expected: Əldermeştən Əlməndər
+  - source: Әссәламү галәйкүм
+    expected: Əssəlamü ğaləyküm
+  - source: Танымаган кешегә
+    expected: Tanımağan keşegə # note[3]
+  - source: Иң әүвәл кул бирешеп күрешик
+    expected: İꞑ əwwəl qul bireşep küreşiq # note[5]
+  - source: Ялгышмыйсың
+    expected: Yalğışmıysıꞑ
+  - source: Нәкъ үзе
+    expected: Nəq üze
+  - source: Кирәгеннән артыгын
+    expected: Kirəgennən artığın # note[3]
+  - source: мәңгелеккә килмәгән
+    expected: məꞑgeleqkə kilməgən
+  - source: кулыңны куй
+    expected: qulıꞑnı quy
+  - source: Өммия # note[8]
+    expected: Ommiä
+  - source: Җиһангир # note[3]
+    expected: Cihangir
+
+map:
+  rules:
+    # note[3] http://www.hintfox.com/article/sistema-glasnih-zvykov-na-tatarskom-i-anglijskom-jazikah.html
+    # back vowels: у, а, ы, о, 
+    # front vowels: е, ә, и, ө, ү, э
+    - pattern: Г(?=[ЕеƏәИиӨөҮүЭэ])
+      result: G
+    - pattern: г(?=[ЕеƏәИиӨөҮүЭэ])
+      result: g
+    - pattern: К(?=[ЕеƏәИиӨөҮүЭэ])
+      result: K
+    - pattern: к(?=[ЕеƏәИиӨөҮүЭэ])
+      result: k
+    - pattern: Ю(?=[ЕеƏәИиӨөҮүЭэ])
+      result: "Y\u00FC"
+    - pattern: ю(?=[ЕеƏәИиӨөҮүЭэ])
+      result: "y\u00FC"
+    - pattern: Я(?=[ЕеƏәИиӨөҮүЭэ])
+      result: "Y\u00E4"
+    - pattern: я(?=[ЕеƏәИиӨөҮүЭэ])
+      result: "y\u00E4"
+
+    # note[4]
+    - pattern: (?<=[АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь])\u0415
+      result: "Y\u0131"
+    - pattern: (?<=[АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь])\u0435
+      result: "y\u0131"
+
+    # note[5]
+    - pattern: (?<=[АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь])\u0423
+      result: "W"
+    - pattern: (?<=[АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь])\u0443
+      result: "w"
+    - pattern: (?<=[АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь])\u04AE
+      result: "W"
+    - pattern: (?<=[АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь])\u04AF
+      result: "w"
+
+    # note[6]
+    - pattern: (?<=[Гг])ый
+      result: i
+
+    # note[8]
+    - pattern: (?<=[Ии])\u042E
+      result: "\u00DC"
+    - pattern: (?<=[Ии])\u044E
+      result: "\u00FC"
+    - pattern: (?<=[Ии])\u042F
+      result: "\u00C4"
+    - pattern: (?<=[Ии])\u044F
+      result: "\u00E4"
+
+  characters:
+    "\u0410": 'A'                       # А
+    "\u04D8": ["\u018F", "\u00C4"]      # Ә => [Ə, Ä] note[1]
+    "\u0411": 'B'                       # Б
+    "\u0412": ['W', 'V']                # В note[2]
+    "\u0413": "\u011E"                  # Г => Ğ note[3]
+    "\u0414": 'D'                       # Д
+    "\u0415": 'E'                       # Е note[3] note[4]
+    "\u0416": 'J'                       # Ж
+    "\u0496": 'C'                       # Җ
+    "\u0417": 'Z'                       # З
+    "\u0418": "\u0130"                  # И => İ
+    "\u0419": 'Y'                       # Й
+    "\u041A": 'Q'                       # К note[3]
+    "\u041B": 'L'                       # Л
+    "\u041C": 'M'                       # М
+    "\u041D": 'N'                       # Н
+    "\u04A2": ["\uA790", "\u00D1"]      # Ң => [Ꞑ, Ñ] note[1]
+    "\u041E": 'O'                       # О
+    "\u04E8": ['O', "\u00D6"]           # Ө => [O, Ö] note[1]
+    "\u041F": 'P'                       # П
+    "\u0420": 'R'                       # Р
+    "\u0421": 'S'                       # С
+    "\u0422": 'T'                       # Т
+    "\u0423": 'U'                       # У note[5]
+    "\u04AE": "\u00DC"                  # Ү => Ü note[5]
+    "\u0424": 'F'                       # Ф
+    "\u0425": 'Х'                       # Х
+    "\u04BA": 'H'                       # Һ
+    "\u0426": 'Ts'                      # Ц
+    "\u0427": "\u00C7"                  # Ч => Ç
+    "\u0428": "\u015E"                  # Ш => Ş
+    "\u0429": "\u015E\u00C7"            # Щ
+    "\u042A": ''                        # Ъ
+    "\u042B": 'I'                       # Ы => I note[2] note[6]
+    "\u042C": "\u2019"                  # Ь => ’
+    "\u042D": 'E'                       # Э note[7]
+    "\u042E": 'Yu'                      # Ю note[3] note[8]
+    "\u042F": 'Ya'                      # Я note[3] note[8]
+
+    '\u0430': 'a'                       # а
+    '\u04D9': ["\u0259", "\u00E4"]      # ә => [ə, ä] note[1]
+    '\u0431': 'b'                       # б
+    '\u0432': ['w', 'v']                # в note[2]
+    '\u0433': "\u011F"                  # г => ğ note[3]
+    '\u0434': 'd'                       # д
+    '\u0435': 'e'                       # e note[3] note[4]
+    '\u0436': 'j'                       # ж
+    '\u0497': 'c'                       # җ
+    '\u0437': 'z'                       # з
+    '\u0438': 'i'                       # и
+    '\u0439': 'y'                       # й
+    '\u043A': 'q'                       # к note[3]
+    '\u043B': 'l'                       # л
+    '\u043C': 'm'                       # м
+    '\u043D': 'n'                       # н
+    '\u04A3': ["\uA791", "\u00F1"]      # ң => [ꞑ, ñ] note[1]
+    '\u043E': 'o'                       # о
+    '\u04E9': ['o', "\u00F6"]           # ө => [o, ö] note[1]
+    '\u043F': 'p'                       # п
+    '\u0440': 'r'                       # р
+    '\u0441': 's'                       # с
+    '\u0442': 't'                       # т
+    '\u0443': 'u'                       # у note[5]
+    '\u04AF': "\u00FC"                  # ү => ü note[5]
+    '\u0444': 'f'                       # ф
+    '\u0445': 'x'                       # х
+    '\u04BB': 'h'                       # һ
+    '\u0446': 'ts'                      # ц
+    '\u0447': "\u00E7"                  # ч => ç
+    '\u0448': "\u015F"                  # ш => ş
+    '\u0449': "\u015F\u00E7"            # щ => şç
+    "\u044a": ''                        # ъ
+    '\u044B': "\u0131"                  # ы => ı note[2] note[6]
+    "\u044C": "\u2019"                  # ь => ’
+    '\u044D': 'e'                       # э note[7]
+    '\u044E': 'yu'                      # ю note[3] note[8]
+    '\u044F': 'ya'                      # я note[3] note[8]

data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.yaml

@@ -0,0 +1,240 @@
+---
+authority_id: bgnpcgn
+id: 1994
+language: iso-639-2:tgk
+source_script: Cyrl
+destination_script: Latn
+name: BGN/PCGN Romanization System -- Tajik (1994)
+alias:
+  ogc11122:
+    code: tgk_Cyrl2Latn_BGN_1994
+    description: The BGN/PCGN system for Tajik was designed for use in romanizing names written in the Tajik Cyrillic alphabet.
+url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20TAJIK.pdf
+creation_date: 1994
+confirmation_date: 2017-11
+description: |
+  The BGN/PCGN system for Tajik was designed for use in romanizing names written in the Tajik Cyrillic alphabet.
+  The Tajik Cyrillic alphabet contains six characters not present in the Russian alphabet: ғ, ӣ, қ, ӯ, ҳ and ҷ. An
+  orthographic reform of the Tajik Cyrillic alphabet was implemented under the auspices of the Academy of Sciences of
+  Tajikistan. This reform was promulgated in a decree of 3 September 1998 by the government of the Republic of
+  Tajikistan. The reform abolished the characters ц, щ, ь and ы (see notes 2 through 5).
+
+notes:
+  - |
+    The character sequences гҳ , зҳ , кҳ , and сҳ may be romanized g·h, z·h, k·h, and s·h in order
+    to differentiate those romanizations from the digraphs gh, zh, kh, and sh which are used to
+    render the characters ғ, ж, x, and ш.
+  - |
+    The obsolete character ц, abolished in 1998, should be romanized s (before a vowel and/or
+    after a consonant within a word) or ts intervocalically.
+  - The obsolete character щ, replaced by ш in 1998, should be romanized sh.
+  - The obsolete character ь, abolished in 1998, should not be romanized.
+  - The obsolete character ы, replaced by и in 1998, should be romanized i.
+  - Unicode values are shown with the uppercase Cyrillic character first, followed by the lowercase character.
+  - |
+    An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the
+    unmodified letters of the basic Roman script is:
+      All apostrophes appearing in romanization are U+2019
+        Í (U+00CD) í (U+00ED)
+        Ŭ (U+016C) ŭ (U+016D)
+        Ė (U+0116) ė (U+0117)
+  - |
+    The Romanization column shows only lowercase forms but, when romanizing, uppercase and
+    lowercase Roman letters as appropriate should be used.
+
+tests:
+  # https://ru.wikipedia.org/wiki/Таджикская_письменность#Образцы_записи
+  - source: |
+      Тамоми одамон озод ба дунё меоянд ва аз лиҳози манзилату ҳуқуқ бо ҳам баробаранд.
+      Ҳама соҳиби ақлу виҷдонанд, бояд нисбат ба якдигар бародарвор муносабат намоянд.
+    expected: |
+      Tamomi odamon ozod ba dunyo meoyand va az lihozi manzilatu huquq bo ham barobarand.
+      Hama sohibi aqlu vijdonand, boyad nisbat ba yakdigar barodarvor munosabat namoyand.
+  - source: Баниодам аъзои як пайкаранд, ки дар офариниш зи як гавҳаранд. Чу узве ба дард оварад рӯзгор, дигар узвҳоро намонад қарор.
+    expected: Baniodam a’zoi yak paykarand, ki dar ofarinish zi yak gavharand. Chu uzve ba dard ovarad rŭzgor, digar uzvhoro namonad qaror.
+  - source: Саъдӣ
+    expected: Sa’dí
+  - source: Мурда будам, зинда шудам; гиря будам, xанда шудам. Давлати ишқ омаду ман давлати поянда шудам.
+    expected: Murda budam, zinda shudam; girya budam, xanda shudam. Davlati ishq omadu man davlati poyanda shudam.
+  - source: Мавлавӣ
+    expected: Mavlaví
+  - source: санг
+    expected: sang
+  - source: барг
+    expected: barg
+  - source: номвар
+    expected: nomvar
+  - source: Бағдод
+    expected: Baghdod
+  - source: ғор
+    expected: ghor
+  - source: модар
+    expected: modar
+  - source: меравам
+    expected: meravam
+  - source: дарё
+    expected: daryo
+  - source: осиёб
+    expected: osiyob
+  - source: жола
+    expected: zhola
+  - source: каждум
+    expected: kazhdum
+  - source: баъз
+    expected: ba’z
+  - source: назар
+    expected: nazar
+  - source: заҳоб
+    expected: zahob
+  - source: ихтиёр
+    expected: ikhtiyor
+  - source: зебоӣ
+    expected: zeboí
+  - source: май
+    expected: may
+  - source: кадом
+    expected: kadom
+  - source: қадам
+    expected: qadam
+  - source: лола
+    expected: lola
+  - source: мурдагӣ
+    expected: murdagí
+  - source: нон
+    expected: non
+  - source: орзу
+    expected: orzu
+  - source: панҷ
+    expected: panj
+  - source: ранг
+    expected: rang
+  - source: сар
+    expected: sar
+  - source: субҳ
+    expected: subh
+  - source: сурайё
+    expected: surayyo
+  - source: тоҷик
+    expected: tojik
+  - source: талаб
+    expected: talab
+  - source: дуд
+    expected: dud
+  - source: хӯрдан
+    expected: khŭrdan
+  - source: фурӯғ
+    expected: furŭgh
+  - source: хондан
+    expected: khondan
+  - source: ҳофиз
+    expected: hofiz
+  - source: чӣ
+    expected: chí
+  - source: ҷанг
+    expected: jang
+  - source: шаб
+    expected: shab
+  - source: таъриф
+    expected: ta’rif
+  - source: эй
+    expected: ėy
+  - source: июн
+    expected: iyun
+  - source: ягонагӣ
+    expected: yagonagí
+  - source: РАМЗҲО
+    expected: RAMZ·HO
+
+map:
+  rules:
+    # note[1]
+    - pattern: ([ГгЗзКкСс])\u04B3
+      result: "\\1·h"
+    - pattern: ([ГгЗзКкСс])\u04B2
+      result: "\\1·H"
+    # note[2]
+    - pattern: \u0426(?=[АаЕеЁёИиОоУуЫыЭэЮюЯя])
+      result: S
+    - pattern: \u0446(?=[АаЕеЁёИиОоУуЫыЭэЮюЯя])
+      result: s
+
+  characters:
+    "\u0410": 'A'                       # А
+    "\u0411": 'B'                       # Б
+    "\u0412": 'V'                       # В
+    "\u0413": 'G'                       # Г
+    "\u0492": 'Gh'                      # Ғ
+    "\u0414": 'D'                       # Д
+    "\u0415": 'E'                       # Е
+    "\u0401": 'Yo'                      # Ё
+    "\u0416": 'Zh'                      # Ж
+    "\u0417": 'Z'                       # З
+    "\u0418": 'I'                       # И
+    "\u04E2": "\u00CD"                  # Ӣ => Í
+    "\u0419": 'Y'                       # Й
+    "\u041A": 'K'                       # К
+    "\u049A": 'Q'                       # Қ
+    "\u041B": 'L'                       # Л
+    "\u041C": 'M'                       # М
+    "\u041D": 'N'                       # Н
+    "\u041E": 'O'                       # О
+    "\u041F": 'P'                       # П
+    "\u0420": 'R'                       # Р
+    "\u0421": 'S'                       # С
+    "\u0422": 'T'                       # Т
+    "\u0423": 'U'                       # У
+    "\u04EE": "\u016C"                  # Ӯ => Ŭ
+    "\u0424": 'F'                       # Ф
+    "\u0425": 'Kh'                      # Х
+    "\u04B2": 'H'                       # Ҳ
+    "\u0427": 'Ch'                      # Ч
+    "\u04B6": 'J'                       # Ҷ
+    "\u0426": 'Ts'                      # Ц note[2]
+    "\u0428": 'Sh'                      # Ш
+    "\u0429": 'Sh'                      # Щ note[3]
+    "\u042A": "\u2019"                  # Ъ
+    "\u042B": 'I'                       # Ы note[5]
+    "\u042C": ''                        # Ь note[4]
+    "\u042D": "\u0116"                  # Э => Ė
+    "\u042E": 'Yu'                      # Ю
+    "\u042F": 'Ya'                      # Я
+
+    "\u0430": 'a'                       # а
+    "\u0431": 'b'                       # б
+    "\u0432": 'v'                       # в
+    "\u0433": 'g'                       # г
+    "\u0493": 'gh'                      # ғ
+    "\u0434": 'd'                       # д
+    "\u0435": 'e'                       # e
+    "\u0451": 'yo'                      # ё
+    "\u0436": 'zh'                      # ж
+    "\u0437": 'z'                       # з
+    "\u0438": 'i'                       # и
+    "\u04E3": "\u00ED"                  # ӣ => í
+    "\u0439": 'y'                       # й
+    "\u043A": 'k'                       # к
+    "\u049B": 'q'                       # қ
+    "\u043B": 'l'                       # л
+    "\u043C": 'm'                       # м
+    "\u043D": 'n'                       # н
+    "\u043E": 'o'                       # о
+    "\u043F": 'p'                       # п
+    "\u0440": 'r'                       # р
+    "\u0441": 's'                       # с
+    "\u0442": 't'                       # т
+    "\u0443": 'u'                       # у
+    "\u04EF": "\u016D"                  # ӯ => ŭ
+    "\u0444": 'f'                       # ф
+    "\u0445": 'kh'                      # х
+    "\u04B3": 'h'                       # ҳ
+    "\u0447": 'ch'                      # ч
+    "\u04B7": 'j'                       # ҷ
+    "\u0446": 'ts'                      # ц note[2]
+    "\u0448": 'sh'                      # ш
+    "\u0449": 'sh'                      # щ note[3]
+    "\u044a": "\u2019"                  # ъ
+    "\u044B": 'i'                       # ы note[5]
+    "\u044C": ''                        # ь note[4]
+    "\u044D": "\u0117"                  # э => ė
+    "\u044E": 'yu'                      # ю
+    "\u044F": 'ya'                      # я