interscript 0.1.3 → 0.1.9

data/maps/{bgnpcgn-bel-cyrl-latn-1979.yaml → bgnpcgn-bel-Cyrl-Latn-1979.yaml}

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1979
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: United States Board on Geographic Names Foreign Names Committee Staff, 1994. Romanization Systems and Roman-Script Spelling Conventions, p. 23.
+alias:
+  ogc11122:
+    code: bel_Cyrl2Latn_BGN_1979
+    description: Byelorussian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1979 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811510/ROMANIZATION_OF_BELARUSIAN.pdf
 creation_date: 1979
 description: |

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1952
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: ROMANIZATION SYSTEM FOR BULGARIAN BGN/PCGN of 1952
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_1952
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Bulgarian 1952 System
 url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
 creation_date: 1945
 confirmation_date: 1952
@@ -51,7 +55,7 @@ map:
     '\u0413': 'G'
     '\u0414': 'D'
     '\u0415': 'E'
-    '\u0416': 'ZH'
+    '\u0416': 'Zh'
     '\u0417': 'Z'
     '\u0418': 'I'
     '\u0419': 'Y'
@@ -66,15 +70,15 @@ map:
     '\u0422': 'T'
     '\u0423': 'U'
     '\u0424': 'F'
-    '\u0425': 'KH'
-    '\u0426': 'TS'
-    '\u0427': 'CH'
-    '\u0428': 'SH'
-    '\u0429': 'SHT'
+    '\u0425': 'Kh'
+    '\u0426': 'Ts'
+    '\u0427': 'Ch'
+    '\u0428': 'Sh'
+    '\u0429': 'Sht'
     '\u042a': "U\u0306"
     '\u042c': "\\'"
-    '\u042e': 'YU'
-    '\u042f': 'YA'
+    '\u042e': 'Yu'
+    '\u042f': 'Ya'
     '\u0430': 'a'
     '\u0431': 'b'
     '\u0432': 'v'
@@ -111,5 +115,5 @@ map:
     '\u046B': "u\u0306" # ѫ
 
     # note[3]
-    '\u0462': "YE" # Ѣ
+    '\u0462': "Ye" # Ѣ
     '\u0463': "ye" # ѣ

data/maps/bgnpcgn-bul-Cyrl-Latn-2013.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 2013
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: BGN/PCGN 2013 Agreement
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_BGN_2013
+    description: Bulgarian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names(PCGN) Bulgarian 2013 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
 creation_date: 2013
 confirmation date: 2019-06

data/maps/bgnpcgn-che-Cyrl-Latn-2008.yaml

@@ -0,0 +1,184 @@
+---
+authority_id: bgnpcgn
+id: 2008
+language: iso-639-2:che
+source_script: Cyrl
+destination_script: Latn
+name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+creation_date: 2008
+confirmation_date: 2019-07
+description: |
+  Chechen is an official language within Chechnya, 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 letter ə is used to represent short a; a is used for long a.
+  - Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources.
+  - This character occurs only in loan words.
+  - q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇)
+  - ŋ when preceding vowel is nasalized.
+  - This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources.
+  - Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ.
+  - |
+    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
+
+        Ə (U+018F)       ə (U+0259)
+        Ä (U+00C4)       ä (U+00E4)
+        Ġ (U+0047+0307)  ġ (U+0067+0307)
+        Z̵ (U+005A+0335)  z̵ (U+007A+0335)
+        Q̇ (U+0051+0307)  q̇ (U+0071+0307)
+        Ŋ (U+014A)       ŋ (U+014B)
+        Ö (U+00D6)       ö (U+00F6)
+        Ü (U+00DC)       ü (U+00FC)
+        Ẋ (U+0058+0307)  ẋ (U+0078+0307)
+        Ċ (U+0043+0307)  ċ (U0063+0307)
+        Ç (U+00C7)       ç (U+00E7)
+        Ç̇ (U+00C7+0307)  ç̇ (U+00E7+0307)
+        Ş (U+015E)       ş (U+015F)
+
+  - 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: кӏант
+    expected: khant
+  - source: зуда
+    expected: zuda
+  - source: пхьагал
+    expected: pẋagal
+  - source: наж
+    expected: naz̵
+  - source: мангал
+    expected: mangal
+  - source: Ӏаж
+    expected: Jaz̵
+  - source: Нохчийн Википеди
+    expected: Noxçiyn Vikipedi
+  - source: сагӏадаккхар
+    expected: saġadaqqar
+  - source: йеза
+    expected: yeza
+  - source: еара
+    expected: yeara
+  - source: елха
+    expected: yelxa
+
+map:
+  rules:
+    # note[2]
+    - pattern: (?<!\b\u2019)\b\u0415 # Е in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0435 # е in initial position -> ye
+      result: ye
+    # note[4]
+    - pattern: \u043A\u043A\u0445
+      result: qq
+    - pattern: \u043A\u043A\u042A
+      result: q̇q̇
+    - pattern: \u041A\u041A\u0445
+      result: QQ
+    - pattern: \u041A\u041A\u042A
+      result: Q̇Q̇
+
+  characters:
+    '\u0410'        : ['A', 'Ə']        # А note[1]
+    '\u0410\u044C'  : "A\u0308"         # Аь -> Ä
+    '\u0411'        : 'B'               # Б
+    '\u0412'        : 'V'               # В
+    '\u0413'        : 'G'               # Г
+    '\u0413\u04C0'  : "G\u0307"         # ГӀ -> Ġ
+    '\u0414'        : 'D'               # Д
+    '\u0415'        : 'E'               # Е note[2]
+    '\u0401'        : 'Yo'              # Ё note[3]
+    '\u0416'        : "Z\u0335"         # Ж -> Ƶ
+    '\u0417'        : 'Z'               # З
+    '\u0418'        : 'I'               # И
+    '\u042B'        : 'Y'               # Й
+    '\u041A'        : 'K'               # К note[4]
+    '\u041A\u0445'  : 'Q'               # Кх note[4]
+    '\u041A\u044A'  : "Q\u0307"         # Къ -> Q̇ note[4]
+    '\u041A\u04C0'  : 'Kh'              # КӀ note[4]
+    '\u041B'        : 'L'               # Л
+    '\u041C'        : 'M'               # М
+    '\u041D'        : ['N', 'Ŋ']        # Н note[5]
+    '\u041E'        : 'O'               # О note[6]
+    '\u041E\u044C'  : "O\u0308"         # Оь -> Ö
+    '\u041F'        : 'P'               # П
+    '\u041F\u04C0'  : 'Ph'              # ПӀ
+    '\u0420'        : 'R'               # Р
+    '\u0421'        : 'S'               # С
+    '\u0422'        : 'T'               # Т
+    '\u0422\u04C0'  : 'Th'              # TӀ
+    '\u0423'        : 'U'               # У
+    '\u0423\u044C'  : "U\u0308"         # Уь -> Ü
+    '\u0424'        : 'F'               # Ф
+    '\u0425'        : 'X'               # Х
+    '\u0425\u044C'  : "X\u0307"         # Хь -> Ẋ
+    '\u0425\u04C0'  : "H"               # ХӀ
+    '\u04B8'        : 'C'               # Ц
+    '\u04B8\u04C0'  : "C\u0307"         # ЦӀ -> Ċ
+    '\u0427'        : "C\u0327"         # Ч -> Ç
+    '\u0427\u04C0'  : "\u00C7\u0307"    # ЧӀ -> Ç̇
+    '\u0428'        : "S\u0327"         # Ш -> Ş
+    '\u0429'        : "S\u0327C\u0327"  # Щ -> ŞÇ note[3]
+    '\u042A'        : "’"               # Ъ note[3]
+    '\u042B'        : "Y"               # Ы
+    '\u042C'        : ""                # Ь note[3]
+    '\u042D'        : "E"               # Э
+    '\u042E'        : "Yu"              # Ю
+    '\u042E\u044C'  : "Yu\u0308"        # Юь -> Yü
+    '\u042F'        : "Ya"              # Я
+    '\u042F\u044C'  : "Ya\u0308"        # Яь -> Yä
+    '\u04C0'        : "J"               # Ӏ note[7]
+
+    '\u0430'        : ['a', 'ə']        # а note[1]
+    '\u0430\u044C'  : "a\u0308"         # аь -> ä
+    '\u0431'        : 'b'               # б
+    '\u0432'        : 'v'               # в
+    '\u0433'        : 'g'               # г
+    '\u0433\u04CF'  : "g\u0307"         # гӏ -> ġ
+    '\u0434'        : 'd'               # д
+    '\u0435'        : 'e'               # е note[2]
+    '\u0451'        : 'yo'              # ё note[3]
+    '\u0436'        : "z\u0335"         # ж -> ƶ
+    '\u0437'        : 'z'               # з
+    '\u0438'        : 'i'               # и
+    '\u0439'        : 'y'               # й
+    '\u043A'        : 'k'               # к note[4]
+    '\u043A\u0445'  : 'q'               # кх note[4]
+    '\u043A\u044A'  : "q\u0307"         # къ -> q̇ note[4]
+    '\u043A\u04CF'  : 'kh'              # кӏ note[4]
+    '\u043B'        : 'l'               # л
+    '\u043C'        : 'm'               # м
+    '\u043D'        : ['n', 'ŋ']        # н note[5]
+    '\u043E'        : 'o'               # о note[6]
+    '\u043E\u044C'  : "o\u0308"         # оь -> ö
+    '\u043F'        : 'p'               # п
+    '\u0440'        : 'r'               # р
+    '\u0441'        : 's'               # с
+    '\u0442'        : 't'               # т
+    '\u0442\u04CF'  : 'th'              # тӏ
+    '\u0443'        : 'u'               # у
+    '\u0443\u044C'  : "u\u0308"         # Уь -> ü
+    '\u0444'        : 'f'               # ф
+    '\u0445'        : 'x'               # х
+    '\u0445\u044C'  : "x\u0307"         # хь -> ẋ
+    '\u0445\u04CF'  : "h"               # хӏ
+    '\u04B9'        : 'c'               # ц
+    '\u04B9\u04CF'  : "с\u0307"         # цӏ -> ċ
+    '\u0447'        : "c\u0327"         # ч -> ç
+    '\u0447\u04CF'  : "c\u00E7\u0307"   # чӏ -> ç̇
+    '\u0448'        : "s\u0327"         # ш -> ş
+    '\u0449'        : "s\u0327c\u0327"  # щ -> şç note[3]
+    '\u044A'        : "’"               # ъ note[3]
+    '\u044B'        : "y"               # ы
+    '\u044C'        : ''                # ь note[3]
+    '\u044D'        : "e"               # э
+    '\u044E'        : "yu"              # ю
+    '\u044E'        : "yu\u0308"        # юь -> yü
+    '\u044F'        : "ya"              # я
+    '\u044F'        : "ya\u0308"        # яь -> yä
+    '\u04CF'        : "j"               # ӏ note[7]

data/maps/bgnpcgn-div-Thaa-Latn-1988.yaml

@@ -0,0 +1,75 @@
+---
+authority_id: bgnpcgn
+id: 1988
+language: iso-639-2:div
+source_script: Thaa
+destination_script: Latn
+name: ROMANIZATION OF MALDIVIAN BGN/PCGN 1988 Agreement, with modifications 2009
+alias:
+  ogc11122:
+    code: div_Thaa2Latn_GMV_1988
+    description: Maldivian (Divehi) 1988 system
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816778/ROMANIZATION_OF_MALDIVIAN.pdf
+creation_date: 1988
+confirmation_date: 2019
+description: |
+  This romanization system supersedes the one that was approved by BGN and PCGN in 1972. An
+  official system was submitted to PCGN by the Maldivian government in 1987 and approved by BGN and
+  PCGN in 1988. The system presented here reflects the 1988 Agreement with minor modifications introduced by the government of the Maldives in 2009
+
+notes:
+  - Maldivian is read from right to left.
+  - The symbol ◌ appearing in the Vowel Characters table represents any Maldivian consonant character.
+  - The character އ is not romanized. If it bears a vowel character, that vowel character alone is romanized (e.g. އެނބޫދޫ En’boodhoo).
+  - |
+    When characters ށ and އ appear in combination with a supercircle (the ‘sukun’, which usually marks
+    the absence of a vowel, see the Diacritical Mark table): ށ ; އ , these characters are not romanized
+    but the following consonant is doubled (e.g. ކަޅުހުރާ Kalhehuttaa), unless the following consonant is a digraph in the
+    romanized form, in which case they are romanized h (e.g. ކެރެށްދޫ Kerehdhoo). ށ and އ appearing at the end of a word are romanized h (e.g. ވޭވައް Veyvah).
+  - Noonu (ނ) is romanized n’ when appearing without any vowel or auxiliary sign (e.g. ކަނޑުފުށި Kan’dufushi)
+  - Thaa (ތ) is romanized iy when appearing in combination with a supercircle (ތ) ,( e.g. ޒިޔާރަތްފުށި  Ziyaaraiyfushi).
+  - 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: "އިރުގައި"
+    expected: "irugai"
+  - source: "ޒިޔާރަތްފުށި"
+    expected: "ziyaaraiyfushi"
+  - source: "ރައްކާތެރިކުރުމާއި"
+    expected: "rakkaatherikurumaai"
+  - source: "ޝަހީދުންގެ ދުވަސް"
+    expected: "sh’aheedhun’ge dhuvas"
+  - source: "މަރުޙަބާ"
+    expected: "maruh’abaa"
+  - source: "ކިހިނެހް"
+    expected: "kihin’eh"
+  - source: "ކޮން ނަމެއް ކިޔަނީ"
+    expected: "kon’ n’ameh kiyan’ee"
+  - source: "ބައްއަޖޖެވުރި ހެނދުނެހް"
+    expected: "baajjevuri hen’dhun’eh"
+  - source: "މެނދުރެހް"
+    expected: "men’dhureh"
+  - source: "ހަވީރެހް"
+    expected: "haveereh"
+
+map:
+  inherit: mv-div-Thaa-Latn-1987
+  characters:
+    #Consonants with diacritical marks (used mainly in words of Arabic origin, corresponding
+    # Arabic characters and their romanizations are shown in parentheses)
+    "ޘ": "th’"
+    "ޙ": "h’"
+    "ޚ": "kh"
+    "ޛ": "dh’"
+    "ޜ": "x"
+    "ޝ": "sh’"
+    "ޞ": "s’"
+    "ޟ": "l’"
+    "ޠ": "t’"
+    "ޡ": "z’"
+    "ޢ": "’"
+    "ޣ": "gh"
+    "ޤ": "q"
+    "ޥ": "w"

data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1962
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: BGN/PCGN 1962 System
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_BGN_1962
+    description: US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) Greek 1962 System (out of date)
 url: https://github.com/riboseinc/interscript/files/4225556/BGN_Romanization_Guide_1962_greek.pdf
 creation_date: 1962
 description: |
@@ -26,7 +30,7 @@ tests:
 
     expected: |
         Éna práma mónon me parakínise ki eména na grápso óti toútin tin patrídha tin ékhomen óloi mazí, kai sofoí ki amathís kai ploúsioi kai ftokhoí kai politikoí kai stratiotikoí kai oi pléon mikróteroi ánthropoi; ósoi agonistíkamen, analógos o kathís, ékhomen na zísomen edhó. To loipón dhoulépsamen óloi mazí, na tin filámen ki óloi mazí kai na min léyi oúte o dhinatós «egó» oúte o adhínatos. Xérete póte na léyi o kathís «egó»? Ótan agonistí mónos tou kai fkiási í khalási, na léyi «egó»; ótan ómos agonízondai polloí kai fkiánoun, tóte na léne «emís». Ímaste is to «emís» ki ókhi is to «egó». Kai is to exís na máthomen gnósi, an thélomen na fkiásomen khorión, na zísomen óloi mazí.
-       
+
         Yiánnis Makriyiánnis.
 
 
@@ -74,7 +78,7 @@ tests:
     expected: Taḯyetos
   - source: σπρέυ
     expected: spréi
-    
+
   - source: Αθήνα
     expected: Athína
   - source: Άγιον Όρος
@@ -526,7 +530,7 @@ map:
     - pattern: (?<=[Οο])\u03C5    # υ (after Ο)
       result: u
     - pattern: (?<=[Οο])\u03CD    # ύ (after Ο)
-      result: ú      
+      result: ú
     - pattern: \u03A5[Ιιί]        # ΥΙ
       result: I
     - pattern: \u03C5[Ιιί]        # υι
@@ -699,4 +703,3 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
-

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

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1996
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: BGN/PCGN 1996 System
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_ELOT743_1996
+    description: Greek ELOT 743 System, US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(PCGN) 1996 agreement
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693694/ROMANIZATION_OF_GREEK.pdf
 creation_date: 1996
 description: |
@@ -17,4 +21,3 @@ map:
   character_separator: ""
   word_separator: " "
   inherit: "elot-ell-Grek-Latn-743-1982-ts"
-

data/maps/bgnpcgn-far-Latn-Latn-1964.yaml

@@ -0,0 +1,28 @@
+---
+authority_id: bgnpcgn
+id: 1964
+language: iso-639-2:far
+source_script: Latn
+destination_script: Latn
+name: https://github.com/interscript/interscript/files/5180777/BGN_Romanization_Guide_1964_faeroese.pdf
+creation_date: 1964
+description: |
+  The Faeroese language is a dialect of Icelandic and, like Icelandic, employes the letter eth (Ð ð).
+  Unlike Icelandic, however, the Faeroese ð has the sound of y (as in "yes") before i, v before u, and is silent in all other cases.
+  The Icelandic letter thorn (Þ þ) does not occur in the writting of Faeroese.
+
+  To avoid the use of the unfamiliar symbol ð, the Board transliterates it as dh, as in Icelandic,
+  even though its pronunciation in the two languages is not the same.
+
+tests:
+  - source: Fyrirgefðu
+    expected: Fyrirgefdhu
+  - source: Þakka
+    expected: Þakka
+
+map:
+  inherit: bgnpcgn-isl-Latn-Latn-1964
+
+  characters:
+    "\u00DE": ~ # Þ translitarion removed
+    "\u00FE": ~ # þ translitarion removed

data/maps/{bgnpcgn-per-Arab-Latn-1956.yaml → bgnpcgn-fas-Arab-Latn-1956.yaml}

@@ -3,10 +3,14 @@
 # TODO: Add tests from PDF
 authority_id: bgnpcgn
 id: 1956
-language: per
+language: iso-639-2:fas
 source_script: Arab
 destination_script: Latn
 name: BGN/PCGN 1956 System
+alias:
+  ogc11122:
+    code: fas_Arab2Latn_BGN_1958
+    description: Persian (Afghan and Iranian) BGN/Permanent Committee on Geographical Names for British Official Use(PCGN) 1958 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/320079/Arabic_Romanization.pdf
 creation_date: 1947
 confirmation_date: 2019-06
@@ -90,4 +94,3 @@ map:
     '\u0647' : 'h'
     '\u0648' : 'v'
     '\u0649' : 'y'
-