interscript 0.1.0 → 0.1.5

data/maps/odni-ukr-Cyrl-Latn-2015.yaml

@@ -0,0 +1,157 @@
+---
+authority_id: odni
+id: 2015
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Ukrainian Personal Names 2004 System, ICS 630-01 Annex M
+# url:
+source: ICS 630-01, Annex M
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the
+  transliteration of Ukrainian names that will be applied to all final
+  written reports and products for IC consumers. It is not intended to
+  eliminate variations of a name that can contribute forensic
+  information. Rather, it is to provide an IC standard Romanized
+  (English) transliteration from Ukrainian that can then be linked to
+  forensic information in ways that will help identify the referent of
+  the name.
+
+tests:
+  - source: Андрій
+    expected: Andriy
+  - source: Борисенко
+    expected: Borysenko
+  - source: Володимир
+    expected: Volodymyr
+  - source: Богдан
+    expected: Bohdan
+  - source: Згурський
+    expected: Zhurskyy
+  - source: Дмитро
+    expected: Dmytro
+  - source: Олег
+    expected: Oleh
+  - source: Гаєвич
+    expected: Hayevych
+  - source: Жанна
+    expected: Zhanna
+  - source: Казимирчук
+    expected: Kazymyrchuk
+  - source: Михайленко
+    expected: Mykhaylenko
+  - source: Іващенко
+    expected: Ivashchenko
+  - source: Олексій
+    expected: Oleksiy
+  - source: Коваленко
+    expected: Kovalenko
+  - source: Леонід
+    expected: Leonid
+  - source: Маринич
+    expected: Marynych
+  - source: Наталія
+    expected: Nataliya
+  - source: Онищенко
+    expected: Onyshchenko
+  - source: Петро
+    expected: Petro
+  - source: Рибчинський
+    expected: Rybchynskyy
+  - source: Соломія
+    expected: Solomiya
+  - source: Троць
+    expected: Trots
+  - source: Уляна
+    expected: Ulyana
+  - source: Філіпчук
+    expected: Filipchuk
+  - source: Христина
+    expected: Khrystyna
+  - source: Стеценко
+    expected: Stetsenko
+  - source: Шевченко
+    expected: Shevchenko
+  - source: Гаращенко
+    expected: Harashchenko
+  - source: Юрій
+    expected: Yuriy
+  - source: Ярошенко
+    expected: Yaroshenko
+  - source: Костянтин
+    expected: Kostyantyn
+
+map:
+  rules:
+    - pattern: \b\u2019\b # remove ’
+      result: ""
+
+  characters:
+    "\u0410": "A"        # А
+    "\u0411": "B"        # Б
+    "\u0412": "V"        # В
+    "\u0413": "H"        # Г
+    "\u0490": "G"        # Ґ
+    "\u0414": "D"        # Д
+    "\u0415": "E"        # Е
+    "\u0404": "Ye"       # Є
+    "\u0416": "Zh"       # Ж
+    "\u0417": "Z"        # З
+    "\u0418": "Y"        # И
+    "\u0406": "I"        # І
+    "\u0407": "Yi"       # Ї
+    "\u0419": "Y"        # 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
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042e": "Yu"       # Ю
+    "\u042f": "Ya"       # Я
+    "\u042c": ""         # Ь
+    "\u0430": "a"        # а
+    "\u0431": "b"        # б
+    "\u0432": "v"        # в
+    "\u0433": "h"        # г
+    "\u0491": "g"        # ґ
+    "\u0434": "d"        # д
+    "\u0435": "e"        # е
+    "\u0454": "ye"       # є
+    "\u0436": "zh"       # ж
+    "\u0437": "z"        # з
+    "\u0438": "y"        # и
+    "\u0456": "i"        # і
+    "\u0457": "yi"       # ї
+    "\u0439": "y"        # 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
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044e": "yu"       # ю
+    "\u044f": "ya"       # я
+    "\u044c": ""         # Ь

data/maps/odni-uzb-Cyrl-Latn-2015.yaml

@@ -0,0 +1,167 @@
+---
+authority_id: odni
+id: 2015
+language: uzb
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Uzbek Personal Names 2015, ICS-630-01 Annex V
+# url:
+source: ICS-630-01 Annex V
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Uzbek person names
+  that will be applied to all final written reports and products for IC consumers. It is not intended to
+  eliminate variations of a name that can contribute forensic information. Rather, it is to provide an
+  IC standard Romanized (English) transliteration from Uzbek that can then be linked to forensic
+  information in ways that will help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
+  usage. In addition, if the original Cyrillic-script spelling is known, that spelling should also
+  appear in parentheses following the name, if possible, following best practices of the issuing
+  organization and taking into consideration information system capabilities. For example:
+  Farkhod Tojiev (also seen as Farhod Tadjiyev, Фарход Тожиев). This convention is designed to
+  ensure that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Uzbek-speaking community, use the
+  relevant IC transliteration standard for names from that language (e.g., Yitzhak). A translator’s
+  note may be used to clarify the known origin of the person. Spell names of individuals from
+  languages that are written in Roman letters as they are spelled in those languages (e.g., George
+  Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the online directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
+  given in these on-line reference works should be used in place of the IC Standard. For any
+  individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
+  longer appears in those resources (i.e. is no longer a government official), the IC Standard
+  spelling should appear first, with the spelling, if known, as it previously appeared in those
+  resources listed within parentheses at the first usage.
+  
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+  names of well-known individuals.
+
+notes:
+  - Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters, (e.g. 's' followed by 'h').
+  - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+
+tests:
+  - source: Фарход Тожиев
+    expected: Farkhod Tojiev
+  - source: Барча одамлар эркин, қадр-қиммат в ҳуқуқлард тенг бўлиб туғиладилар. Улар ақл в виждон соҳибидирлар в бир-бирлари ила биродарларча муомал қилишларь зарур.
+    expected: Barcha odamlar erkin, qadr-qimat v huquqlard teng bolib tughiladilar. Ular aql v vijdon sohibidirlar v bir-birlari ila birodarlarcha muomal qilishlar zarur.
+  - source: Тутук белгись
+    expected: Tutuk belgis
+  - source: Янги юл
+    expected: Yangi iul
+  - source: Ўзбек ёзуви
+    expected: Ozbek yozuvi
+  - source: Чиғатай гурунги
+    expected: Chighatay gurungi
+  - source: ъ
+    expected: ''
+  - source: шш
+    expected: sh
+  - source: ччччч
+    expected: ch
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(.)\\1{1,}"
+      result: "\\1"
+
+  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': 'J'    # Ж
+    '\u0417': 'Z'    # З
+    '\u0418': 'I'    # И
+    '\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
+    '\u040E': 'O'    # Ў
+    '\u0424': 'F'    # Ф
+    '\u0425': 'Kh'   # Х
+    '\u04B2': 'H'    # Ҳ
+    '\u0426': 'Ts'   # Ц
+    '\u0427': 'Ch'   # Ч
+    '\u0428': 'Sh'   # Ш
+    '\u042D': 'E'    # Э
+    '\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': 'j'    # ж
+    '\u0437': 'z'    # з
+    '\u0438': 'i'    # и
+    '\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
+    '\u045E': 'o'    # ў
+    '\u0444': 'f'    # ф
+    '\u044B': 'y'    # ы
+    '\u0447': 'ch'   # ч
+    '\u044F': 'ia'   # я
+    '\u044E': 'iu'   # ю
+    '\u0445': 'kh'   # х
+    '\u04B3': 'h'    # ҳ
+    '\u0448': 'sh'   # ш
+    '\u044D': 'e'    # э
+    '\u0449': 'shch' # щ
+    '\u0446': 'ts'   # ц
+    '\u0491': 'g'    # ґ
+    '\u046B': 'u'    # ѫ
+    '\u0452': 'd'    # ђ
+    '\u0455': 'dz'   # ѕ
+    '\u0458': 'j'    # ј
+    '\u0459': 'lj'   # љ
+    '\u045A': 'nj'   # њ
+    '\u04BB': 'c'    # һ
+    '\u045F': 'dz'   # џ
+    '\u0454': 'ie'   # є
+    '\u0457': 'i'    # ї
+    '\u0453': 'g'    # ѓ
+
+    # note[3]
+    '\u042a': ''     # Ъ
+    '\u042c': ''     # Ь
+    '\u044a': ''     # ъ
+    '\u044c': ''     # ь
+

data/maps/royin-tha-Thai-Latn-1939-generic.yaml

@@ -0,0 +1,90 @@
+---
+authority_id: royin
+id: 1939-generic
+language: tha
+source_script: Thai
+destination_script: Latn
+name: Royal Thai General System of Transcription (1939) Generic
+url: http://www.siamese-heritage.org/jsspdf/1941/JSS_033_1d_RoyalInstituteTranscriptionOfThaiIntoRomanCharacters.pdf
+creation_date: 1939
+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 (1939)
+
+  The first two parts are done via two external maps.
+
+
+notes: |
+  This is a draft for the map.
+  The conversion from Thai to Phonemic Thai is still work-in-progress.
+
+tests:
+  - source: "กษัตริย์"
+    expected: "kasat"
+  - source: "ประกาศ"
+    expected: "prakat"
+  # - source: "ราชบุรี่"
+  #   expected: "ratburi"
+  # - source: "ปากลัด"
+  #   expected: "pak-lat"
+
+
+chain: ["var-tha-Thai-Thai-phonemic" ,"var-tha-Thai-Zsym-ipa"]
+
+map:
+  title-case: false
+  word_separator: " "  
+
+  rules:
+    - pattern: '[˩˨˧˦˥]'
+      result : ''
+
+  postrules:
+    - pattern: '\.'
+      result:  ''
+
+  characters:
+
+  dictionary:
+
+    '̯': ''
+    '̚': ''
+
+    'ʔ': ''
+    'ː': ''
+
+    't͡ɕʰ': 'ch'
+    't͡ɕ': 'čh'
+    'ŋ': 'ng'
+    'j': 'y'
+    'ɔ': 'o̦'
+    'ɤ': 'œ' 
+    'ɛ': 'æ'
+    'ɯ': 'ư'
+    'ʰ': 'h'
+
+    'aːw': 'ao'
+    'aw': 'ao'
+    'a̯w': 'ao'
+    'eːw': 'eo'
+    'ew': 'eo'
+    'ɛːw': 'aeo'
+    'ɛw': 'æo'
+    'iːw': 'iu'
+    'iw': 'iu'
+
+    'aːj': 'ai'
+    'aj': 'ai'
+    'a̯j': 'ai'
+    'ɔːj': 'o̦i'
+    'ɔj': 'o̦i'
+    'oːj': 'oi'
+    'oj': 'oi'
+    'ɤːj': 'œi'
+    'ɤj': 'œi'
+    'uːj': 'ui'
+    'uj': 'ui'

data/maps/royin-tha-Thai-Latn-1968.yaml

@@ -0,0 +1,179 @@
+---
+authority_id: royin
+id: 1968-chained
+language: tha
+source_script: Thai
+destination_script: Latn
+name: Royal Thai General System of Transcription (1968)
+url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
+creation_date: 1968
+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 (1968).
+
+  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: "satuk"
+  - source: "พืช"
+    expected: "phut"
+  - source: "บรบือ"
+    expected: "borabu"
+  - 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: "kua"
+  - source: "เมือง"
+    expected: "muang"
+  # - 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: "ngiu"
+  - source: "เร็ว"
+    expected: "reo"
+  # - source: "เลว"
+  #   expected: "leo"
+  # - source: "เลย"
+  #   expected: "loei"
+  # - source: "เดือย"
+  #   expected: "duai"
+  # - source: "ห้วย"
+  #   expected: "huai"
+  - source: "แมว"
+    expected: "maeo"
+  - source: "เขียว"
+    expected: "khieu"
+
+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': 'u'
+    'ʰ': 'h'
+
+    'aːw': 'ao'
+    'aw': 'ao'
+    'a̯w': 'eu'
+    'eːw': 'eo'
+    'ew': 'eo'
+    'ɛːw': 'aeo'
+    'ɛw': 'aeo'
+    'iːw': 'iu'
+    'iw': 'iu'
+
+    'aːj': 'ai'
+    'aj': 'ai'
+    'a̯j': 'ai'
+    'ɔːj': 'oi'
+    'ɔj': 'oi'
+    'oːj': 'oi'
+    'oj': 'oi'
+    'ɤːj': 'oei'
+    'ɤj': 'oei'
+    'uːj': 'ui'
+    'uj': 'ui'