interscript 0.1.0 → 0.1.5

data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml

@@ -0,0 +1,20 @@
+---
+authority_id: bgnpcgn
+id: 1996
+language: ell
+source_script: Grek
+destination_script: Latn
+name: BGN/PCGN 1996 System
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693694/ROMANIZATION_OF_GREEK.pdf
+creation_date: 1996
+description: |
+  BGN/PCGN Romanization table for Greek
+
+note:
+  - Identical to ELOT 743:1982, which is also adopted as ISO 843:1997 and by UNGEGN
+
+map:
+  character_separator: ""
+  word_separator: " "
+  inherit: "elot-ell-Grek-Latn-743-1982-ts"
+

data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.yaml

@@ -0,0 +1,257 @@
+---
+authority_id: bgnpcgn
+id: 1930
+language: jpn
+source_script: Hrkt
+destination_script: Latn
+name: Japanese Kana Modified Hepburn 1930 System
+url:
+creation_date:
+adoption_date:
+description:
+
+notes:
+  - Segmentation needs to be done before using this map
+  - Note 5 in the specification states that when identical repeating vowels
+    belong to different kanji characters, they shall be romanized
+    individually and an apostrophe (’) shall be placed between the vowels.
+    However since this is a map from Kana to Hepburn, there is no way to
+    implement this feature.
+  - The documentation did not specify how the hyphen should be used.
+
+tests:
+
+  - source: てがた-からみでん
+    expected: "Tegata-karamiden"
+  - source: てがた-すみよしちょう
+    expected: "Tegata-sumiyoshichō"
+  - source: さいのはま
+    expected: "Sainohama"
+  - source: てがた-たなか
+    expected: "Tegata-tanaka"
+  - source: ほりおでん
+    expected: "Horioden"
+  - source: そえがわ
+    expected: "Soegawa"
+  - source: ふねがさわ
+    expected: "Funegasawa"
+  - source: とくまんだて
+    expected: "Tokumandate"
+  - source: たてない
+    expected: "Tatenai"
+  - source: つるがさき
+    expected: "Tsurugasaki"
+  - source: しもやつせ
+    expected: "Shimoyatsuse"
+  - source: かみやつせ
+    expected: "Kamiyatsuse"
+  - source: しんとうだ
+    expected: "Shintōda"
+  - source: かじのめ
+    expected: "Kajinome"
+  - source: まえぎ
+    expected: "Maegi"
+  - source: くろさわ やま
+    expected: "Kurosawa Yama"
+  - source: いちのさわ がわ
+    expected: "Ichinosawa Gawa"
+  - source: はちやまえ
+    expected: "Hachiyamae"
+  - source: やち
+    expected: "Yachi"
+  - source: たてぬま
+    expected: "Tatenuma"
+  - source: しらはま
+    expected: "Shirahama"
+  - source: けせんまち
+    expected: "Kesenmachi"
+  - source: けいだい-かわら
+    expected: "Keidai-kawara"
+  - source: いしやました
+    expected: "Ishiyamashita"
+  - source: なえひら-やち
+    expected: "Naehira-yachi"
+  - source: とみの
+    expected: "Tomino"
+  - source: あらや-たかみまち
+    expected: "Araya-takamimachi"
+  - source: ながた
+    expected: "Nagata"
+  - source: とどろき おんせん
+    expected: "Todoroki Onsen"
+  - source: かしわぎはら
+    expected: "Kashiwagihara"
+  - source: とやけもり やま
+    expected: "Toyakemori Yama"
+  - source: なかさい
+    expected: "Nakasai"
+  - source: たけした
+    expected: "Takeshita"
+  - source: みと
+    expected: "Mito"
+  - source: みなみなかさと
+    expected: "Minaminakasato"
+  - source: みずおし
+    expected: "Mizuoshi"
+  - source: なかさと
+    expected: "Nakasato"
+  - source: しんかりば
+    expected: "Shinkariba"
+  - source: しんかみぬま
+    expected: "Shinkaminuma"
+  - source: しんばし
+    expected: "Shinbashi"
+  - source: りくぜんやました えき
+    expected: "Rikuzen’yamashita Eki"
+  - source: うしじまにし
+    expected: "Ushijimanishi"
+  - source: はまえば
+    expected: "Hamaeba"
+  - source: ぬまむかい
+    expected: "Numamukai"
+  - source: さんげんやち
+    expected: "Sangen’yachi"
+  - source: にけんやち
+    expected: "Niken’yachi"
+  - source: やちなか
+    expected: "Yachinaka"
+  - source: なす がわ
+    expected: "Nasu Gawa"
+  - source: おおはらはま
+    expected: "Ōharahama"
+  - source: うるご がわ
+    expected: "Urugo Gawa"
+  - source: なかばせ
+    expected: "Nakabase"
+  - source: うと えき
+    expected: "Uto Eki"
+  - source: みずまち
+    expected: "Mizumachi"
+  - source: ごんげんどう
+    expected: "Gongendō"
+  - source: いとひさ
+    expected: "Itohisa"
+  - source: あらおい
+    expected: "Araoi"
+  - source: わんめ
+    expected: "Wanme"
+  - source: かじろ
+    expected: "Kajiro"
+  - source: みやばら
+    expected: "Miyabara"
+  - source: いまどみ
+    expected: "Imadomi"
+  - source: かいほ
+    expected: "Kaiho"
+  - source: かいほ ぼえん
+    expected: "Kaiho Boen"
+  - source: ひきだ
+    expected: "Hikida"
+  - source: あさい-こむかい
+    expected: "Asai-komukai"
+  - source: こうざか
+    expected: "Kōzaka"
+  - source: こうふうだい
+    expected: "Kōfūdai"
+  - source: たての
+    expected: "Tateno"
+  - source: センター
+    expected: "Sentā"
+  - source: フィリピン
+    expected: "Firipin"
+  - source: ヴィオリン
+    expected: "Viorin"
+  - source: クォーター
+    expected: "Kwōtā"
+  - source: パッチリ
+    expected: "Patchiri"
+  - source: ぽっぽっや
+    expected: "Poppoyya"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: var-jpn-Hrkt-Latn-hepburn-1954
+
+  characters:
+    # Rare sounds, Table 2 & 4
+
+    "くぁ": "kwa"
+    "クァ": "kwa"
+    "ぐぁ": "gwa"
+    "グァ": "gwa"
+    "くぃ": "kwi"
+    "クィ": "kwi"
+    "ぐぃ": "gwa"
+    "グィ": "gwa"
+    "きぇ": "kye"
+    "キェ": "kye"
+    "ぎぇ": "gye"
+    "ギェ": "gye"
+    "くぇ": "kwe"
+    "クェ": "kwe"
+    "ぐぇ": "gwe"
+    "グェ": "gwe"
+    "くぉ": "kwo"
+    "クォ": "kwo"
+    "ぐぉ": "gwo"
+    "グォ": "gwo"
+    "しぇ": "she"
+    "シェ": "she"
+    "じぇ": "je"
+    "ジェ": "je"
+    "つぁ": "tsa"
+    "ツァ": "tsa"
+    "てぃ": "ti"
+    "ティ": "ti"
+    "でぃ": "di"
+    "ディ": "di"
+    "てゅ": "tyu"
+    "テュ": "tyu"
+    "でゅ": "dyu"
+    "デュ": "dyu"
+    "とゅ": "tu"
+    "トュ": "tu"
+    "どゅ": "du"
+    "ドュ": "du"
+    "ちぇ": "che"
+    "チェ": "che"
+    "ぢぇ": "je"
+    "ヂェ": "je"
+    "つぇ": "tse"
+    "ツェ": "tse"
+    "つぉ": "tso"
+    "ツォ": "tso"
+    "にぇ": "nye"
+    "ニェ": "nye"
+    "ふぁ": "fa"
+    "ファ": "fa"
+    "ふぃ": "fi"
+    "フィ": "fi"
+    "ふぇ": "fe"
+    "フェ": "fe"
+    "ふぉ": "fo"
+    "フォ": "fo"
+    "みぇ": "mye"
+    "ミェ": "mye"
+    "ぃぇ": "ye"
+    "ィェ": "ye"
+    "りぇ": "rye"
+    "リェ": "rye"
+    "ゔぁ": "va"
+    "ヴァ": "va"
+    "うぃ": "wi"
+    "ウィ": "wi"
+    "ゔぃ": "vi"
+    "ヴィ": "vi"
+    "うぇ": "we"
+    "ウェ": "we"
+    "ゔぇ": "ve"
+    "ヴェ": "ve"
+    "うぉ": "wo"
+    "ウォ": "wo"
+    "ゔぉ": "vo"
+    "ヴォ": "vo"
+    "ゔ": "vu"
+    "ヴ": "vu"

data/maps/bgnpcgn-kat-Geor-Latn-1981.yaml

@@ -0,0 +1,127 @@
+---
+authority_id: bgnpcgn
+id: 1981
+language: kat
+source_script: Geor
+destination_script: Latn
+name: ROMANIZATION OF GEORGIAN; BGN/PCGN 1981 System
+url: https://transliteration.eki.ee/pdf/Georgian.pdf
+creation_date: 1981
+confirmation_date: 1981
+description: |
+  BGN/PCGN system of 1981.
+
+notes:
+
+tests:
+  - source: ჰებუდი
+    expected: hebudi
+
+  - source: ჯვრის წყალსაცავი
+    expected: jvris tsqalsats’avi
+
+  - source: ჯვავიაკვარა
+    expected: jvaviak’vara
+
+  - source: ჯობრია
+    expected: jobria
+
+  - source: ძულუხირა
+    expected: dzulukhira
+
+  - source: ლეკუხონა
+    expected: lek’ukhona
+
+  - source: აბაშა
+    expected: abasha
+
+  - source: ააცი
+    expected: aats’i
+
+  # TODO: This belongs to which system?!
+  # - source: აბააჟახვუ
+  #   expected: abaazhvakhu
+
+  # TODO: These examples from GNDB are clearly using the BGNPCGN 2009 system
+  #
+  # - source: ხობის მუნიციპალიტეტი
+  #   expected: khobis munitsip’alit’et’i
+  #
+  # - source: მყინვარი ჩრდილოეთი ლეადაშატი
+  #   expected: mq’invari chrdiloeti leadashat’i
+  #
+  # - source: ხეწკვარა
+  #   expected: khets’k’vara
+  #
+  # - source: ჯამპალი
+  #   expected: jamp’ali
+  #
+  # - source: ჯავის მუნიციპალიტეტი
+  #   expected: javis munitsip’alit’et’i
+  #
+  # - source: ხოიჯგეთა
+  #   expected: khoijgeta
+  #
+  # - source: ხობის მუნიციპალიტეტი
+  #   expected: khobis munitsip’alit’et’i
+  #
+  # - source: წვიშარხუ
+  #   expected: ts’visharkhu
+  # - source: აღმოსავლეთი გუმისთა
+  #   expected: aghmosavleti gumista
+  #
+  # - source: ქვემო ბირცხა
+  #   expected: kvemo birtskha
+  #
+  # - source: ზემო ბირცხა
+  #   expected: zemo birtskha
+  #
+  # - source: აბჟაყვა
+  #   expected: abzhaq’va
+
+
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+
+    '\u10f1' : 'ey' # ჱ
+
+    '\u10d7' : 't’' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k’' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+
+    '\u10f2' : 'j' # ჲ
+
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p' # პ
+    '\u10df' : 'zh' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't' # ტ
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'p’' # ფ
+    '\u10e5' : 'k’' # ქ
+    '\u10e6' : 'gh' # ღ
+    '\u10e7' : 'q' # ყ
+    '\u10e8' : 'sh' # შ
+    '\u10e9' : 'ch’' # ჩ
+    '\u10ea' : 'ts’' # ც
+    '\u10eb' : 'dz' # ძ
+    '\u10ec' : 'ts' # წ
+    '\u10ed' : 'ch' # ჭ
+    '\u10ee' : 'kh' # ხ
+
+    '\u10f4' : 'q’' # ჴ
+
+    '\u10ef' : 'j' # ჯ
+    '\u10f0' : 'h' # ჰ

data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml

@@ -0,0 +1,43 @@
+---
+authority_id: bgnpcgn
+id: 2009
+language: kat
+source_script: Geor
+destination_script: Latn
+name: ROMANIZATION OF GEORGIAN; Georgia 2011 national system; BGN/PCGN 2009 Agreement
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/810202/ROMANIZATION_OF_GEORGIAN.pdf
+creation_date: 2009
+confirmation_date: 2011
+description: |
+  This romanization system corresponds to that devised in 2002 by the
+  State Department of Geodesy and Cartography of Georgia and the
+  Institute of Linguistics of the Georgian Academy of Sciences, and
+  approved by Presidential Decree 109 of 24 February 2011. It represents
+  the Mkhedruli alphabet, as presently used in Georgia. This system was
+  adopted by BGN and PCGN in 2009, superseding the BGN/PCGN system of
+  1981.
+
+notes:
+  - This system denotes ejective (glottalised) consonants by means of
+    an apostrophe. The BGN/PCGN 1981 system instead used the apostrophe to
+    denote aspirated consonants (letters 8, 21, 22, 26 & 27).
+  - The Romanization columns show only lowercase forms but, when
+    romanizing, uppercase and lowercase Roman letters as appropriate should
+    be used.
+
+tests:
+  - source: თბილისი
+    expected: tbilisi
+
+  - source: მეღვინეთუხუცესი
+    expected: meghvinetukhutsesi
+
+  - source: ჭიანჭველა
+    expected: ch’ianch’vela
+
+  - source: ბაყაყი
+    expected: baq’aq’i
+
+map:
+  inherit: "ggg-kat-Geor-Latn-2002"
+