interscript 0.1.2 → 0.1.3

data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml

@@ -0,0 +1,253 @@
+---
+authority_id: bgnpcgn
+id: kn-1945
+language: kor
+source_script: Hang
+destination_script: Latn
+name: BGN/PCGN 1945 Agreement
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693725/ROMANIZATION_OF_KOREAN-_MR_for_DPRK.pdf
+creation_date: 1945
+adoption_date:
+description:
+
+notes: "
+
+  1. At the end of a syllable, the character ᄋ should be romanized ng, 
+     as in the following example: 
+
+     평양 → P’yŏngyang
+
+     At the beginning of a syllable, the character ᄋ is silent and 
+     should not be romanized. An example follows: 
+
+     용화 → Yonghwa 
+
+  2. Syllable boundaries within words are not reflected in romanization.
+     In the different types of syllables shown in the table below, C 
+     represents any consonant character, V represents any vowel character
+     and / represents a syllable boundary.
+
+       Han’gŭl              개성      남포      안양 
+       Syllable boundaries  CV/CVC   CVC/CV   VC/VC
+       Romanization         Kaesŏng  Namp’o   Anyang
+
+  3. Euphonic changes occurring within a word, including between the 
+     specific and generic of a geographical name, should be reflected in 
+     romanization. Generic terms are usually seen separated from the name 
+     by a hyphen and with a lower case initial letter rather than as a 
+     separate word: 
+
+       영진리 → Yŏngjil-li
+       덕흥리 → Tŏkhŭng-ni
+       압록강 → Amnok-kang
+       대동강 → Taedong-gang
+
+  4. As a result of 조선말규범집 (‘Standard Korean Language’ guidelines 
+     published in North Korea in 1966), unlike the Korean spoken in the 
+     Republic of Korea, the language spoken in the Democratic People’s 
+     Republic of Korea maintains and pronounces the word-initial ᆯ (‘r’).
+     The use of the word-initial ᄅ ('r') can be seen in official news 
+     reports as well as native mapping. Since such examples exist, the 
+     word initial ᄅ ('r') is reflected as an option in the tables given above.
+
+  5. The Romanization column shows only lowercase forms but, when romanizing,
+     uppercase and lowercase Roman letters as appropriate should be used.
+  "
+
+tests:
+  - source: "평양"
+    expected: "P’yŏngyang"
+  - source: "용화"
+    expected: "Yonghwa"
+  - source: "개성"
+    expected: "Kaesŏng"
+  - source: "남포"
+    expected: "Namp’o"
+  - source: "안양"
+    expected: "Anyang"
+  - source: "영진-리"
+    expected: "Yŏngjil-li"
+  - source: "덕흥-리"
+    expected: "Tŏkhŭng-ni"
+  - source: "압록-강"
+    expected: "Amnok-kang"
+  - source: "대동-강"
+    expected: "Taedong-gang"
+  - source: "라선특별시"
+    expected: "Rasŏnt’ŭkpyŏlsi"
+  - source: 은하-리
+    expected: "Ŭnha-ri"
+  - source: 은중-리
+    expected: "Ŭnjung-ni"
+  - source: 은장-령
+    expected: "Ŭnjang-nyŏng"
+  - source: 은혜-동
+    expected: "Ŭnhye-dong"
+  - source: 은호-리
+    expected: "Ŭnho-ri"
+  - source: 은행정
+    expected: "Ŭnhaengjŏng"
+  - source: 은행-동
+    expected: "Ŭnhaeng-dong"
+  - source: 은행-촌
+    expected: "Ŭnhaeng-ch’on"
+  - source: 원수
+    expected: "Wŏnsu"
+  - source: 원소리-고개
+    expected: "Wŏnsori-gogae"
+  - source: 원소참
+    expected: "Wŏnsoch’am"
+  - source: 원소-리
+    expected: "Wŏnso-ri"
+  - source: 원신-리
+    expected: "Wŏnsil-li"
+  - source: 난곡
+    expected: "Nan’gok"
+  - source: 난산-리
+    expected: "Nansal-li"
+  - source: 난직
+    expected: "Nanjik"
+  - source: 영곡
+    expected: "Yŏnggok"
+  - source: 윗두밀
+    expected: "Wittumil"
+  - source: 윗도심이
+    expected: "Wittosimi"
+  - source: 둔지
+    expected: "Tunji"
+  - source: 서승
+    expected: "Sŏsŭng"
+  - source: 신촌
+    expected: "Sinch’on"
+  - source: 비암덕
+    expected: "Piamdŏk"
+  - source: 바위안
+    expected: "Pawian"
+  - source: 오송평
+    expected: "Osongp’yŏng"
+  - source: 그물목
+    expected: "Kŭmulmok"
+  - source: 구원정
+    expected: "Kuwŏnjŏng"
+  - source: 일하
+    expected: "Irha"
+  - source: 황우
+    expected: "Hwangu"
+  - source: 자작보
+    expected: "Chajakpo"
+  - source: 비파1-동
+    expected: "Pip’a Il-tong"
+  - source: 문암 오-동
+    expected: "Munam O-dong"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: [var-kor-Hang-Latn-mr-1939]
+
+  rules:
+    # Add Zero-width White-space U+200B after spaces (i.e. before word boundaries)
+    # So that the word-initial conversion rules will be blocked.
+    - pattern: "^"
+      result: "\u200B"
+    - pattern: "(?<= )"
+      result: "\u200B"
+
+    # convert numbers to space + Hangul
+    - pattern: "([^0-9 ])(?=[0-9])"
+      result: "\\1 "
+    - pattern: "1"
+      result: "일"
+    - pattern: "2"
+      result: "이"
+    - pattern: "3"
+      result: "삼"
+    - pattern: "4"
+      result: "사"
+    - pattern: "5"
+      result: "오"
+    - pattern: "6"
+      result: "육"
+    - pattern: "7"
+      result: "칠"
+    - pattern: "8"
+      result: "팔"
+    - pattern: "9"
+      result: "구"
+
+    # This is a logic to add hyphen in front of generics
+    # - pattern: "(?<=.)(구역|동|리|도|고개|골|로동자구|사무소|초등학교|중학교|고등학교|강|포|령|역|봉|사|천|교|제|저수지|소류지|재|못|말|면|암|교회|촌|병원|바위|공원|섬|우체국|대학교|보건소|굴|치|대교|지구|폭포|해수욕장|휴게소|중고교|읍|보건진료소|마을|톨게이트|대학|시장|경찰서|학교)$" #to be expanded
+    #   result: "-\\1"
+
+  postrules:
+
+    # Add space to the two ends of the string for easier word boundary handling
+    - pattern: "^"
+      result: " "
+    - pattern: "$"
+      result: " "
+
+    # Initial rules in the inherited map were blocked, so that
+    # this set of updated rules (with the onset rules removed) will be used instead.
+    - pattern: "\u200B"
+      result: ""
+
+    - pattern: "(?<= )ᄀ"
+      result: "k" # HANGUL CHOSEONG KIYEOK
+    - pattern: "(?<= )ᄂ"
+      result: "n" # HANGUL CHOSEONG NIEUN
+    - pattern: "(?<= )ᄃ(?=[ᅵᅣᅤᅧᅨᅭᅲ])"
+      result: "ch" # HANGUL CHOSEONG TIEUT # T -> Ch before yotized vowels
+    - pattern: "(?<= )ᄃ"
+      result: "t" # HANGUL CHOSEONG TIEUT
+    - pattern: "(?<= )ᄅ"
+      result: "r" # HANGUL CHOSEONG RIEUL
+    - pattern: "(?<= )ᄆ"
+      result: "m" # HANGUL CHOSEONG MIEUM
+    - pattern: "(?<= )ᄇ"
+      result: "p" # HANGUL CHOSEONG PIEUP
+    - pattern: "(?<= )ᄉ(?=ᅱ)"
+      result: "sh" # HANGUL CHOSEONG SIOS
+    - pattern: "(?<= )ᄉ"
+      result: "s" # HANGUL CHOSEONG SIOS
+    - pattern: "(?<= )ᄋ"
+      result: "" # HANGUL CHOSEONG IEUNG
+    - pattern: "(?<= )ᄌ"
+      result: "ch" # HANGUL CHOSEONG CIEUC
+    - pattern: "(?<= )ᄎ"
+      result: "ch’" # HANGUL CHOSEONG CHIEUCH
+    - pattern: "(?<= )ᄏ"
+      result: "k’" # HANGUL CHOSEONG KHIEUKH
+    - pattern: "(?<= )ᄐ(?=[ᅵᅣᅤᅧᅨᅭᅲ])"
+      result: "ch’" # HANGUL CHOSEONG THIEUTH + YOTIZED VOWELS
+    - pattern: "(?<= )ᄐ"
+      result: "t’" # HANGUL CHOSEONG THIEUTH
+    - pattern: "(?<= )ᄑ"
+      result: "p’" # HANGUL CHOSEONG PHIEUPH
+    - pattern: "(?<= )ᄒ"
+      result: "h" # HANGUL CHOSEONG HIEUH
+    - pattern: "(?<= )ᄁ"
+      result: "kk" # HANGUL CHOSEONG SSANGKIYEOK
+    - pattern: "(?<= )ᄭ"
+      result: "kk" # HANGUL CHOSEONG SIOS-KIYEOK
+    - pattern: "(?<= )ᄄ"
+      result: "tt" # HANGUL CHOSEONG SSANGTIEUT
+    - pattern: "(?<= )ᄯ"
+      result: "tt" # HANGUL CHOSEONG SIOS-TIEUT
+    - pattern: "(?<= )ᄈ"
+      result: "pp" # HANGUL CHOSEONG SSANGPIEUP
+    - pattern: "(?<= )ᄲ"
+      result: "pp" # HANGUL CHOSEONG SIOS-PIEUP
+    - pattern: "(?<= )ᄊ"
+      result: "ss" # HANGUL CHOSEONG SSANGSIOS
+    - pattern: "(?<= )ᄍ"
+      result: "tch" # HANGUL CHOSEONG SSANGCIEUC
+    - pattern: "(?<= )ᄶ"
+      result: "tch" # HANGUL CHOSEONG SIOS-CIEUC
+
+    # Remove space added
+    - pattern: "^ "
+      result: ""
+    - pattern: " $"
+      result: ""

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml

@@ -0,0 +1,48 @@
+---
+authority_id: bgnpcgn
+id: 2011
+language: kor
+source_script: Hang
+destination_script: Latn
+name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+url: 
+creation_date: 
+adoption_date:
+description:
+
+notes:
+  BGN/PCGN 2011 Agreement
+
+tests:
+  - source: 불국사
+    expected: "Bulguksa"
+  - source: 묵호
+    expected: "Mukho"
+  - source: 울산
+    expected: "Ulsan"
+  - source: 독립문
+    expected: "Dongnimmun"
+  - source: 강남역
+    expected: "Gangnamyeok"
+  - source: 남산리
+    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
+  - source: 내월리
+    expected: "Naewol-ri"
+  - source: 울릉군
+    expected: "Ulleung-gun"
+  - source: 설악산
+    expected: "Seoraksan"
+  - source: 삼죽면
+    expected: "Samjuk-myeon"
+  - source: 평리1동
+    expected: "Pyeongni Il-dong"
+  - source: 평리2동
+    expected: "Pyeongni I-dong"
+  - source: 탑안이
+    expected: "Tabani"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: moct-kor-Hang-Latn-2000

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml

@@ -0,0 +1,48 @@
+---
+authority_id: bgnpcgn
+id: 2011
+language: kor
+source_script: Kore
+destination_script: Latn
+name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+url: 
+creation_date: 
+adoption_date:
+description:
+
+notes:
+  BGN/PCGN 2011 Agreement
+
+tests:
+  - source: 佛國寺
+    expected: "Bulguksa"
+  - source: 묵호
+    expected: "Mukho"
+  - source: 蔚山
+    expected: "Ulsan"
+  - source: 獨立門
+    expected: "Dongnimmun"
+  - source: 江南驛
+    expected: "Gangnamyeok"
+  - source: 南山里
+    expected: "Namsan-ri" #Note: no assimilation for -ri even after nasals
+  - source: 내월里
+    expected: "Naewol-ri"
+  - source: 鬱陵郡
+    expected: "Ulleung-gun"
+  - source: 雪嶽山
+    expected: "Seoraksan"
+  - source: 三竹面
+    expected: "Samjuk-myeon"
+  - source: 坪里1洞
+    expected: "Pyeongni Il-dong"
+  - source: 坪里2洞
+    expected: "Pyeongni I-dong"
+  - source: 탑안이
+    expected: "Tabani"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: [var-kor-Kore-Hang-2013, moct-kor-Hang-Latn-2000]

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.yaml

@@ -0,0 +1,159 @@
+---
+authority_id: bgnpcgn
+id: 1981
+language: mkd
+source_script: Cyrl
+destination_script: Latn
+name: Makedonian Romanization, BGN/PCGN 1981 System
+url: https://github.com/riboseinc/interscript/files/4247920/USBGN_romanization_Macedonian_1981.pdf
+creation_date: 1981
+description: BGN/PCGN Romanization table for Makedonian.
+
+tests:
+  - source: Ѓол
+    expected: Đol
+  - source: Јусек Тепеси
+    expected: Jusek Tepesi
+  - source: Љуги Ќарит
+    expected: Ljugi Ćarit
+  - source: Ќафа Сан
+    expected: Ćafa San
+  - source: Агроплод Ресен
+    expected: Agroplod Resen
+  - source: Алта Чука
+    expected: Alta Čuka
+  - source: Баш Тепе
+    expected: Baš Tepe
+  - source: Браќам
+    expected: Braćam
+  - source: Винарска Визба Агропин
+    expected: Vinarska Vizba Agropin
+  - source: Галичица
+    expected: Galičica
+  - source: Дрењево
+    expected: Drenjevo
+  - source: Енешево
+    expected: Eneševo
+  - source: Иберлија
+    expected: Iberlija
+  - source: Крмзи Су
+    expected: Krmzi Su
+  - source: Лесноски Рид
+    expected: Lesnoski Rid
+  - source: Мала Корабска Врата
+    expected: Mala Korabska Vrata
+  - source: Низок Врв
+    expected: Nizok Vrv
+  - source: Охридско Езеро
+    expected: Ohridsko Ezero
+  - source: Прлиќ
+    expected: Prlić
+  - source: Равна Гора
+    expected: Ravna Gora
+  - source: Сеѓавечкиот Рид
+    expected: Seđavečkiot Rid
+  - source: Трновите Њиве
+    expected: Trnovite Njive
+  - source: Фасов Рид
+    expected: Fasov Rid
+  - source: Црни Камен
+    expected: Crni Kamen
+  - source: Чатал Чешми
+    expected: Čatal Češmi
+  - source: Шехово
+    expected: Šehovo
+
+notes:
+  - The character ѓ should be romanized g when it occurs before е and и. In other
+    instances, it should be romanized ǵ (Ǵ).
+  - The character ќ should be romanized k when it occurs before е and и. In other
+    instances, it should be romanized ć.
+
+map:
+  rules:
+    - pattern: "Ѓ(?=[еЕиИ])"
+      result: "G"
+    - pattern: "ѓ(?=[еЕиИ])"
+      result: "g"
+    - pattern: "Ќ(?=[еЕиИ])"
+      result: "K"
+    - pattern: "ќ(?=[еЕиИ])"
+      result: "k"
+
+  postrules:
+    # DZ
+    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
+      result: "DZ"
+    #LJ
+    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
+      result: "LJ"
+    #NJ
+    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
+      result: "NJ"
+    #DŽ
+    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
+      result: "DŽ"
+
+  characters:
+    "\u0410": "A"
+    "\u0411": "B"
+    "\u0412": "V"
+    "\u0413": "G"
+    "\u0414": "D"
+    "\u0403": "\u0110" # Đ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\u0405": "Dz"
+    "\u0418": "I"
+    "\u0408": "J"
+    "\u041A": "K"
+    "\u041B": "L"
+    "\u0409": "Lj"
+    "\u041C": "M"
+    "\u041D": "N"
+    "\u040A": "Nj"
+    "\u041E": "O"
+    "\u041F": "P"
+    "\u0420": "R"
+    "\u0421": "S"
+    "\u0422": "T"
+    "\u040c": "\u0106" # Ć
+    "\u0423": "U"
+    "\u0424": "F"
+    "\u0425": "H"
+    "\u0426": "C"
+    "\u0427": "\u0043\u030c" # Č
+    "\u040F": "D\u007a\u030c" # Dž
+    "\u0428": "\u0053\u030c" # Š
+    "\u0430": "a"
+    "\u0431": "b"
+    "\u0432": "v"
+    "\u0433": "g"
+    "\u0434": "d"
+    "\u0453": "\u0111" # đ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\u0455": "dz"
+    "\u0438": "i"
+    "\u0458": "j"
+    "\u043A": "k"
+    "\u043B": "l"
+    "\u0459": "lj"
+    "\u043C": "m"
+    "\u043D": "n"
+    "\u045A": "nj"
+    "\u043E": "o"
+    "\u043F": "p"
+    "\u0440": "r"
+    "\u0441": "s"
+    "\u0442": "t"
+    "\u045c": "\u0107" # ć
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š