interscript 0.1.2 → 0.1.3

data/maps/royin-tha-Thai-Latn-1999-chained.yaml

@@ -0,0 +1,180 @@
+---
+authority_id: royin
+id: 1999-chained
+language: tha
+source_script: Thai
+destination_script: Latn
+name: Royal Thai General System of Transcription (1999)
+url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
+creation_date: 1999
+adoption_date: 
+description: |
+  This map loads two external maps to convert Thai text first into phonemic Thai,
+  and then into IPA transcription.
+  
+  The IPA transcription will then be handled by this map, and converted into
+  Royal Thai General System of Transcription (1999)
+
+  The first two parts are done via two external maps.
+
+notes: |
+  The conversion from Thai to Phonemic Thai is still work-in-progress.
+
+tests:
+  - source: "สะพาน"
+    expected: "saphan"
+  - source: "ลานตา"
+    expected: "lanta"
+  - source: "บาง"
+    expected: "bang"
+  - source: "สมุทร"
+    expected: "samut"
+  - source: "ลำ"
+    expected: "lam"
+  - source: "สิงห์"
+    expected: "sing"
+  - source: "บุรี"
+    expected: "buri"
+  - source: "สตึก"
+    expected: "satuek"
+  - source: "พืช"
+    expected: "phuet"
+  - source: "บรบือ"
+    expected: "borabue"
+  - source: "ภู"
+    expected: "phu"
+  - source: "ปะนาเระ"
+    expected: "panare"
+  - source: "เพ็ญ"
+    expected: "phen"
+  # - source: "เขน"
+  #   expected: "khen"
+  - source: "แซะ"
+    expected: "sae"
+  # - source: "สะแก"
+  #   expected: "sakae"
+  - source: "พะโต๊ะ"
+    expected: "phato"
+  - source: "ลพ"
+    expected: "lop"
+  # - source: "สามโก้"
+  #   expected: "samko"
+  - source: "เกาะ"
+    expected: "ko"
+  - source: "บ่อ"
+    expected: "bo"
+  - source: "เซอะ"
+    expected: "soe"
+  - source: "อำเภอ"
+    expected: "amphoe"
+  - source: "เนิน"
+    expected: "noen"
+  # - source: "เพียะ"
+  #   expected: "phia"
+  - source: "เทียน"
+    expected: "thian"
+  # - source: "เกือะ"
+  #   expected: "kuea"
+  - source: "เมือง"
+    expected: "mueang"
+  # - source: "ผัวะ"
+  #   expected: "phua"
+  - source: "บัว"
+    expected: "bua"
+  # - source: "ควน"
+  #   expected: "khuan"
+  - source: "ใหญ่"
+    expected: "yai"
+  # - source: "ไผ่"
+  #   expected: "phai"
+  - source: "ชัย"
+    expected: "chai"
+  - source: "ไทย"
+    expected: "thai"
+  # - source: "ปาย"
+  #   expected: "pai"
+  - source: "เจ้า"
+    expected: "chao"
+  - source: "ข้าว"
+    expected: "khao"
+  # - source: "กุย"
+  #   expected: "kui"
+  - source: "โดย"
+    expected: "doi"
+  # - source: "ดอย"
+  #   expected: "doi"
+  # - source: "งิ้ว"
+  #   expected: "ngio"
+  - source: "เร็ว"
+    expected: "reo"
+  # - source: "เลว"
+  #   expected: "leo"
+  # - source: "เลย"
+  #   expected: "loei"
+  # - source: "เดือย"
+  #   expected: "dueai"
+  # - source: "ห้วย"
+  #   expected: "huai"
+  - source: "แมว"
+    expected: "maeo"
+  - source: "เขียว"
+    expected: "khiao"
+
+
+chain: ["var-tha-Thai-Thai-phonemic" ,"var-tha-Thai-Zsym-ipa"]
+
+map:
+  title-case: false
+  word_separator: " "  
+
+  rules:
+    - pattern: '[˩˨˧˦˥]'
+      result : ''
+    - pattern: '^'
+      result: '.'
+
+  postrules:
+    - pattern: '\.'
+      result:  ''
+
+  characters:
+
+  dictionary:
+
+    '̯': ''
+    '̚': ''
+
+    'ʔ': ''
+    'ː': ''
+
+    't͡ɕʰ': 'ch'
+    't͡ɕ': 'ch'
+    'ŋ': 'ng'
+    'j': 'y'
+    'ɔ': 'o'
+    'ɤ': 'oe' 
+    'ɛ': 'ae'
+    'ɯ': 'ue' # New spelling, was u in 1968
+    'ʰ': 'h'
+
+    'aːw': 'ao'
+    'aw': 'ao'
+    'a̯w': 'ao' # New spelling, was eu in 1968
+    'eːw': 'eo'
+    'ew': 'eo'
+    'ɛːw': 'aeo'
+    'ɛw': 'aeo'
+    'iːw': 'io' # New spelling, was iu in 1968
+    'iw': 'io' # New spelling, was iu in 1968
+
+    'aːj': 'ai'
+    'aj': 'ai'
+    'a̯j': 'ai'
+    'ɔːj': 'oi'
+    'ɔj': 'oi'
+    'oːj': 'oi'
+    'oj': 'oi'
+    'ɤːj': 'oei'
+    'ɤj': 'oei'
+    'uːj': 'ui'
+    'uj': 'ui'

data/maps/royin-tha-Thai-Latn-1999.yaml

@@ -0,0 +1,76 @@
+---
+authority_id: royin
+id: 1999
+language: tha
+source_script: Thai
+destination_script: Latn
+name: Royal Thai General System of Transcription (1999)
+url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
+creation_date: 1999
+adoption_date: 
+description:
+
+notes: |
+
+tests:
+  - source: 'ภาษาไทย'
+    expected: 'phasathai'
+  - source: 'ไทย'
+    expected: 'thai'
+  - source: 'เชียงใหม่'
+    expected: 'chiangmai'
+  - source: 'ใหม่'
+    expected: 'mai'
+  - source: 'ใคร'
+    expected: 'khrai'
+  - source: "ที่"
+    expected: "thi"
+  - source: "เป็น"
+    expected: "pen"
+  - source: "ใน"
+    expected: "nai"
+  - source: "การ"
+    expected: "kan"
+  - source: "มี"
+    expected: "mi"
+  - source: "ได้"
+    expected: "dai"
+  - source: "ของ"
+    expected: "khong"
+  - source: "ไม่"
+    expected: "mai"
+  - source: "สถานีปางต้นผึ้ง"
+    expected: "sathanipangtonphueng"
+  - source: "ไพศาลี"
+    expected: "phaisali"
+  - source: "โรงเรียนไม้เรียงประชาสรรค์"
+    expected: "rongrianmairiangprachasan"
+
+map:
+  title-case: false
+  word_separator: " "  
+  transcription: "sequitur.pythainlp_lexicon"
+
+  rules:
+
+  postrules:
+    - pattern: 'chh'
+      result: 'ch'
+
+  characters:
+    '[0-9]': ''
+
+  dictionary:
+    'ʰ': 'h'
+    'c': 'ch'
+    'ː': ''
+    'ŋ': 'ng'
+    'j': 'i'
+    'w': 'o'
+    'ɔ': 'o'
+    'ɤ': 'oe' 
+    'ɛ': 'ae'
+    'ɯ': 'ue'
+    'ʔ' : ''
+    't͡ɕ': 'c'
+    '.' : ''

data/maps/{cn-chn-Hans-Latn-pinyin.yaml → sac-zho-Hans-Latn-1979.yaml}

@@ -1,6 +1,6 @@
 ---
-authority_id: cn
-id: pinyin
+authority_id: sac
+id: 1979
 language: chn
 source_script: Hans
 destination_script: Latn
@@ -11,8 +11,7 @@ description: |
   This table contains the data on how Unicode Hanzi characters
   are pronounced in P.R.China.
 tests:
-  - source:
-    expected:
+
 
 notes:
   - Nine tab-separated columns. Column #1 is the Unicode (in hex), Columns #2 to #6 are Pinyin (tone '5' means Qingsheng)
@@ -13601,8 +13600,8 @@ map:
     "\u7A21": "zui4"
     "\u7A22": "yu4"
     "\u7A23": "su1"
-    "\u7A24": l��4
-    "\u7A25":
+    "\u7A24": "lue4"
+    "\u7A25": "xiang1"
     "\u7A26": "yi1"
     "\u7A27": "xi4"
     "\u7A28": "bian1"
@@ -21054,7 +21053,7 @@ map:
     "\u92DF": "qin2"
     "\u92E0": "shen4"
     "\u92E1": "han2"
-    "\u92E2": l��4
+    "\u92E2": "lue4"
     "\u92E3": "ye2"
     "\u92E4": "chu2"
     "\u92E5": "zeng4"

data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml

@@ -0,0 +1,222 @@
+---
+authority_id: stategeocadastre
+id: 1993
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: PROVISIONAL RULES OF REPRODUCING LETTERS OF THE UKRAINIAN ALPHABET WITH LATIN (ENGLISH) CHARACTERS
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/17th-gegn-docs/17th_gegn_WP73.pdf
+creation_date: 1993
+description: |
+  These Rules are intended for Romanized transliteration of Ukrainian
+  geographic names in international cartographic editions.
+
+  Geographic names of Russia, Byelorussia, Bulgaria and other states
+  using the Cyrillic alphabet are transliterated according to rules
+  accepted in those states.
+
+  These Rules come into effect from the moment of their approval by
+  the Main Administration of Geodesy, Cartography and Cadastre and
+  will be effective until the introduction of a State standard of
+  Ukraine regulating the Romanized transliteration of the Ukrainian
+  alphabet.
+
+notes:
+  - No apostrophe (’) is used in transliteration, the combination "ьо" is transliterated as "io"
+  - Use of capitals in Latin version of Ukrainian geographic names correspond to the Ukrainian spelling
+  - Generics geographical terms standing before or after a name in full or abbreviated form are transliterated
+  - Romanized versions of complex and compound Ukrainian toponyms (one word, hyphenated or separate words) will follow the Ukrainian spelling
+  - In indexes of Romanized geographical names entries must be arranged in the order of the Latin (English) alphabet
+  - Geographic names of Russia, Byelorussia, Bulgaria and other states using the Cyrillic alphabet are transliterated according to rules accepted in those states.
+  - "Ed: There seems to be a mistake in the source document. 'ц' should be replaced with ts instead 'tz'."
+
+tests:
+  - source: Кам’янка # note[1]
+    expected: Kamianka
+  - source: Сьомаки # note[1]
+    expected: Siomaky
+  - source: Усть-Чорна # note[2]
+    expected: Ust’-Chorna
+  - source: Чорне море # note[2]
+    expected: Chorne more
+  - source: оз. Сиваш # note[3]
+    expected: oz. Syvash
+  - source: Кримський канал # note[3]
+    expected: Kryms’kyi kanal # ! Example had typo in original document "Krums’kyi kanal"
+  - source: Гола Пристань
+    expected: Hola Prystan’
+  - source: Корсунь Шевченківський
+    expected: Korsun’ Shevchenkivs’kyi
+  - source: Верхньодніпровськ
+    expected: Verkhniodniprovs’k
+  - source: Варва
+    expected: Varva
+  - source: Броди
+    expected: Brody
+  - source: Верховина
+    expected: Verkhovyna
+  - source: Глухів
+    expected: Hlukhiv
+  - source: Великий
+    expected: Velykyi
+  - source: Ґрунь(гора)
+    expected: Grun’(hora)
+  - source: Димер
+    expected: Dymer
+  - source: Срібне
+    expected: Sribne
+  - source: Євпаторія
+    expected: Yevpatoriia
+  - source: Єнакієве
+    expected: Yenakiieve
+  - source: Жолква
+    expected: Zholkva
+  - source: Затока
+    expected: Zatoka
+  - source: Житомир
+    expected: Zhytomyr
+  - source: Інгул
+    expected: Inhul
+  - source: Зміїв
+    expected: Zmiïv
+  - source: Йосипівка
+    expected: Yosypivka
+  - source: Стрий
+    expected: Stryi
+  - source: Калуш
+    expected: Kalush
+  - source: Лубни
+    expected: Lubny
+  - source: Миколаїв
+    expected: Mykolaïv
+  - source: Ніжин
+    expected: Nizhyn
+  - source: Острог
+    expected: Ostroh
+  - source: Печеніги
+    expected: Pechenihy
+  - source: Рівне
+    expected: Rivne
+  - source: Сарата
+    expected: Sarata
+  - source: Тячів
+    expected: Tiachiv
+  - source: Узин
+    expected: Uzyn
+  - source: Форос
+    expected: Foros
+  - source: Харків
+    expected: Kharkiv
+  - source: Цюрупінськ
+    expected: Tsiurupins’k
+  - source: Черемош
+    expected: Cheremosh
+  - source: Шацьк
+    expected: Shats’k
+  - source: Щорс
+    expected: Shchors
+  - source: Хмельницький
+    expected: Khmel’nyts’kyi # ! Example had typo in original document "Khmel’nyts’ky"
+  - source: Юрівка
+    expected: Yurivka
+  - source: Любеч
+    expected: Liubech
+  - source: Ялта
+    expected: Yalta
+  - source: Ясіня
+    expected: Yasinia
+
+
+map:
+  rules:
+    - pattern: (?<!\b\u2019)\b\u0404 # Є in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0454 # є in initial position -> ye
+      result: ye
+    - pattern: (?<!\b\u2019)\b\u0419 # Й in initial position -> Y
+      result: "Y"
+    - pattern: (?<!\b\u2019)\b\u0419 # й in initial position -> y
+      result: "y"
+    - pattern: (?<!\b\u2019)\b\u042e # Ю in initial position -> Yu
+      result: Yu
+    - pattern: (?<!\b\u2019)\b\u044e # ю in initial position -> yu
+      result: yu
+    - pattern: (?<!\b\u2019)\b\u042f # Я in initial position -> Ya
+      result: Ya
+    - pattern: (?<!\b\u2019)\b\u044f # я in initial position -> ya
+      result: ya
+    # note[1]
+    - pattern: \b\u2019\b # remove ’
+      result: ""
+    - pattern: \u042c\u041e
+      result: "IO"
+    - pattern: \u044c\u043e
+      result: "io"
+
+  characters:
+    "\u0410": "A"        # А
+    "\u0411": "B"        # Б
+    "\u0412": "V"        # В
+    "\u0413": "H"        # Г
+    "\u0490": "G"        # Ґ
+    "\u0414": "D"        # Д
+    "\u0415": "E"        # Е
+    "\u0404": "Ie"       # Є
+    "\u0416": "Zh"       # Ж
+    "\u0417": "Z"        # З
+    "\u0418": "Y"        # И
+    "\u0406": "I"        # І
+    "\u0407": "I\u0308"  # Ї
+    "\u0419": "I"        # Й
+    "\u041a": "K"        # К
+    "\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
+    "\u0424": "F"        # Ф
+    "\u0425": "Kh"       # Х
+    "\u0426": "Ts"       # Ц note[7]
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042c": "\u2019"   # Ь
+    "\u042e": "Iu"       # Ю
+    "\u042f": "Ia"       # Я
+    "\u0430": "a"        # а
+    "\u0431": "b"        # б
+    "\u0432": "v"        # в
+    "\u0433": "h"        # г
+    "\u0491": "g"        # ґ
+    "\u0434": "d"        # д
+    "\u0435": "e"        # е
+    "\u0454": "ie"       # є
+    "\u0436": "zh"       # ж
+    "\u0437": "z"        # з
+    "\u0438": "y"        # и
+    "\u0456": "i"        # і
+    "\u0457": "i"        # ї
+    "\u0439": "i"        # й
+    "\u043a": "k"        # к
+    "\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
+    "\u0444": "f"        # ф
+    "\u0445": "kh"       # х
+    "\u0446": "ts"       # ц note[7]
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044e": "iu"       # ю
+    "\u044f": "ia"       # я
+    "\u044c": "\u2019"   # ь