interscript 0.1.3 → 0.1.9

data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: bgnpcgn
 id: 1965
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: BGN/PCGN 1965 System
+alias:
+  ogc11122:
+    code: ukr_Cyrl2Latn_BGN_1965
+    description: Ukrainian Board on Geographic Names/Permanent Committee on Geographical Names for British Official Use(PCGN) 1965 System
 url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816788/ROMANIZATION_OF_UKRAINIAN.pdf
 creation_date: 1947
 confirmation_date: 2019-06
@@ -160,4 +164,3 @@ map:
     "\u042e": 'Yu'
     "\u042f": 'Ya'
     "\u0490": 'G'
-

data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 2019
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: BGN/PCGN 2019 Agreement
@@ -113,96 +113,7 @@ tests:
     expected: Znamianka
 
 map:
-  rules:
-    - pattern: (?<=З|з)(Г|г)
-      result: gh
-    - 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\u0407 # Ї in initial position -> Yi
-      result: Yi
-    - pattern: (?<!\b\u2019)\b\u0457 # ї in initial position -> yi
-      result: yi
-    - 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
-    - pattern: \b\u2019\b # remove ’
-      result: ""
+  inherit: un-ukr-Cyrl-Latn-2012
 
   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"        # 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
-    "\u0427": "Ch"       # Ч
-    "\u0428": "Sh"       # Ш
-    "\u0429": "Shch"     # Щ
-    "\u042e": "Iu"       # Ю
-    "\u042f": "Ia"       # 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": "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
-    "\u0447": "ch"       # ч
-    "\u0448": "sh"       # ш
-    "\u0449": "shch"     # щ
-    "\u044e": "iu"       # ю
-    "\u044f": "ia"       # я
-    "\u044c": ""         # Ь
+    "\u0027": ''     # ' ->

data/maps/bgnpcgn-urd-Arab-Latn-2007.yaml

@@ -0,0 +1,459 @@
+---
+authority_id: bgnpcgn
+id: 2007
+language: iso-639-2:urd
+source_script: Arab
+destination_script: Latn
+name: BGN/PCGN Romanization System -- Urdu (2007)
+alias:
+  ogc11122:
+    code: uas_Arab2Latn_BGN_2007
+    description: Unified Afghan Romanization System US Board on Geographic Names (BGN)/The Permanent Committee on Geographical Names (PCGN) 2007
+url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693788/ROMANIZATION_OF_URDU.pdf
+creation_date: 2007
+confirmation_date: 2017-11
+description: |
+  The following is the approved romanization system for
+  deriving standard spellings of Urdu geographical names for
+  Pakistan. It was jointly adopted by BGN and PCGN at the
+  23rd BGN/PCGN Conference in Washington, DC, in 2007 and it
+  is based on the Hunterian romanization system for Urdu,
+  which has been used by the Surveys of India and Pakistan
+  for romanizing Urdu geographical names for more than one
+  hundred years. The BGN/PCGN system laid out below includes
+  diacritical marks in order that the original script can be
+  derived from the romanized form (i.e. it is reversible).
+  For desk users requiring a diacritic-free form, these
+  diacritics can simply be removed. In every case the same
+  basic Roman-script characters are kept as are used in the
+  Hunterian system. The BGN/PCGN forms have further been
+  designed to harmonize with the BGN/PCGN Persian
+  romanization system.
+notes:
+  - 1. When the vowel sign zīr ( ِ) occurs word-finally in the
+    first element of a compound, it is assumed to mark the
+    Persian izafat
+    morpheme, and is romanized -e, not i.
+  - 2. The source of almost all example names is the 1951
+    Census of Pakistan, Village List, Northwest Frontier
+    Province, Chitral
+    State. Office of the Provincial Superintendant of Census,
+    North-West Frontier Province, Peshawar.
+  - 3. No examples of aspirated dental r (rh, رھ ( were found,
+    though this phoneme is assumed to be part of the phonology
+    of
+    Urdu, and was therefore left out of Table 2.
+  - 4. Note that the short vowels in the Urdu examples are not
+    pointed.
+  - 5. Occasionally, sequences of /z/ or /s/ plus /h/ may be
+    encountered, i.e. z·h, s·h. These may be romanized with the
+    Unicode
+    'center dot' (U+00B7) separating the two letters, to
+    distinguish them from the digraphs /zh/ and /sh/.
+  - Commented tests are blocked by this issue https://github.com/interscript/interscript/issues/572
+    depends on the different ways of handling ي to y or e AND و to u or o
+
+
+tests:
+  # - source: بوغدِی
+  #   expected: Boghdī
+
+  - source: پَالِير
+    expected: Pālīr
+
+  # - source: بیزوت كَلے
+  #   expected: Bezot Kale
+
+  # - source: عَمَل كوٹ
+  #   expected: ‘Amal Koṭ
+
+  - source: ثَابِر
+    expected: S̄ābir
+
+  - source: شَاه نَثَار ميلة
+    expected: Shāh Nas̄ār Mylah
+
+  # - source: بَرجُو ميلَه
+  #   expected: Barjū Melah
+
+  - source: چَپرِی
+    expected: Chaprī
+
+  - source: أَحمَد خَان كَلے
+    expected: Aḩmad Khān Kale
+
+  # - source: آكَا خيل
+  #   expected: Ākā Khel
+
+  - source: دُرَانِي
+    expected: Durānī
+
+  - source: ڈَنگِیلا
+    expected: Ḍangīlā
+
+  - source: ذَرَانِی
+    expected: Z̄arānī
+
+  - source: بُركِي
+    expected: Burkī
+
+  - source: گِیدَڑَه
+    expected: Gīdaṛah
+
+  - source: عَلِي زَائِي
+    expected: ‘Alī Zā’ī
+
+  # - source: ژوب
+  #   expected: Zhob
+
+  - source: بِسَاتُو
+    expected: Bisātū
+
+  - source: أَحمَدِي شَامَا
+    expected: Aḩmadī Shāmā
+
+  - source: اَصَالَت كَلے
+    expected: Aşālat Kale
+
+  - source: خَضَر خَان
+    expected: Khaẕar Khān
+
+  - source: سُلْطَان
+    expected: Sulţān
+
+  - source: عَزَم سَيِّد نُور كَلے
+    expected: ‘Azam Sayyid Nūr Kale
+
+  # - source: عَلَم شير
+  #   expected: ‘Alam Sher
+
+  - source: بغَاكِي
+    expected: Bghākī
+
+  # - source: مُظَفَر كوٹ
+  #   expected: Muz̧afar Koṭ
+
+  - source: حَقدَرَه
+    expected: Ḩaqdarah
+
+  - source: کَچکِینَہ
+    expected: Kachkīnah
+
+  - source: بَاگَن
+    expected: Bāgan
+
+  - source: بُلبَلَک
+    expected: Bulbalak
+
+  - source: بِلیَامِین
+    expected: Bilyāmīn
+
+  - source: نَہر
+    expected: Nahr
+
+  # - source: جوکَالِیَاں
+  #   expected: Jokālīāñ
+
+  - source: اَرَوْالِی
+    expected: Arawālī
+
+  # - source: هیروشاه
+  #   expected: Heroshāh
+
+  - source: مَہردِی
+    expected: Mahrdī
+
+  - source: بَڑھ
+    expected: Baṛh
+
+  # - source: شِیوَاؤ
+  #   expected: Shīwā’o
+
+  - source:  یَاردَا کَلے
+    expected: Yārdā Kale
+
+  - source: بهَائِي خَان
+    expected: Bhā’ī Khān
+
+  - source: پھاشک
+    expected: Phāshk
+
+  - source: تھَلّ
+    expected: Thall
+
+  - source: پَٹھان ريَا
+    expected: Paṭhān Ryā
+
+  - source: جھِیل
+    expected: Jhīl
+
+  - source:  غَزْنِي سْپِين
+    expected: Ghaznī Spīn
+
+  - source: بَادشَاه چھُم
+    expected: Bādshāh Chhum
+
+  - source:  سِندھ
+    expected: Sindh
+
+  - source: ڈھَنڈ
+    expected: Ḍhanḍ
+
+  # - source: غوزگَڑھِی
+  #   expected: Ghozgaṛhī
+
+  # - source: دوغَل گاکھَر
+  #   expected: Doghal Gākhar
+
+  - source: خَان گھَڑِی
+    expected: Khān Ghaṛī
+
+  - source: غُلَامَک كَلے
+    expected: Ghulāmak Kale
+
+  # - source: کاراخیل
+  #   expected: Kārākhel
+
+  - source: خَپیَنگا
+    expected: Khapyangā
+
+  - source: گَندَه كَلے
+    expected: Gandah Kale
+
+  # - source: گُلونَا ڈھيرِي
+  #   expected: Gulonā Ḍherī
+
+  # - source: خيرَه دِين
+  #   expected: Kherah Dīn
+
+  - source: مَورپِتھِی
+    expected: Maurpithī
+
+  - source: درے پلارِی
+    expected: Dre Plārī
+
+  - source: آگرَہ
+    expected: Āgrah
+
+  - source: ڈَنڈَر
+    expected: Ḍanḍar
+
+  # - source: گِیدو
+  #   expected: Gīdo
+
+  - source: گُبازانَہ
+    expected: Gubāzānah
+
+  # - source: اُوشو
+  #   expected: Ūsho
+
+  - source: حَےدَر عَلِی كَلے
+    expected: Ḩaidar ‘Alī Kale
+
+  - source: تَودَہ چِینَہ
+    expected: Taudah Chīnah
+
+  - source: مُوسى خَان كَلے
+    expected: Mūsá Khān Kale
+
+  - source: مُلَّا بَاغ
+    expected: Mullā Bāgh
+
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'|-])[\u0061-\uFFFF]
+      result: "upcase"
+    # don't capitalize defined article in the middle of a sentence
+    - pattern : ' At T'  # الت
+      result: ' at T'
+    - pattern : ' As̄ S̄'  # الث
+      result: ' as̄ S̄'
+    - pattern : ' Ad D' # الد
+      result: ' ad D'
+    - pattern : ' Az̄ Z̄'  # الذ
+      result: ' az̄ Z̄'
+    - pattern : ' Ar R' # الر
+      result: ' ar R'
+    - pattern : ' Az Z'  # الز
+      result: ' az Z'
+    - pattern : ' As S' # الس
+      result: ' as S'
+    - pattern : ' Ash Sh' # الش
+      result: ' ash Sh'
+    - pattern : ' Aş Ş'  # الص
+      result: ' aş Ş'
+    - pattern : ' Aẕ Ẕ'  # الض
+      result: ' aẕ Ẕ'
+    - pattern : ' Aţ Ţ'  # الط
+      result: ' aţ Ţ'
+    - pattern : ' Az̧ Z̧' # الظ
+      result: ' az̧ Z̧'
+    - pattern : ' Al L'  # الل
+      result: ' al L'
+    - pattern : ' An N'  # الن
+      result: ' an N'
+    - pattern: " Al " # ال
+      result: " al "
+  characters:
+    # special rules
+
+    '\s(?=\u0622\u0628\u064E\u0627\u062F)': '' # space followed by abad is removed
+    '\ufdf2': 'Allāh' # See note 5
+
+    # Vowels, Diphthongs, and Diacritical Marks
+    '\u064e' : 'a' # َ fatha
+    '\u064e(?=\u0629)' : '' # َ fatha followed by ta' marboota
+    '\u064e(?=a[h|t])' : '' # َ fatha followed by ta' marboota, handling different order of conversion
+
+    '\u0652' : ''  # ْ sokoon
+    '\u0659': 'ê'
+
+    '\u0650[\u064a|\u06cc]' : 'ī' # ـِي kasra followed by ي
+    '\u0650' : 'i' # karsra
+    '\u06d2' : 'e' # ـے
+
+    '\u0622' : 'ā'  # آ
+    '\u064e\u0627' : 'ā'  # ـَا fatha followed by ا
+    '\u0627' : 'ā'  # ا
+    '\b\u0627' : ''  # ا
+
+    '\u0648' : 'o'  # و # suspect
+    '\u064f' : 'u' # ُ damma
+    '\u064f\u0648' : 'ū'  # ـُو damma followed by و
+
+    '\u064e\u06d2' : 'ai' # ـے
+    '\u064e\u0648' : 'au'  # ـَو
+    '\u0670': 'á' # ىٰ
+    '\u0649': 'á' # ىٰ
+
+    # shadda
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 'thth'  # ث
+    '\u062c\u0651' : 'jj'  # ج
+    '\u062d\u0651' : 'ẖẖ' # ح
+    '\u062e\u0651' : 'khkh'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'z̄z̄'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'sh'  # ش
+    '\u0635\u0651' : 'şş'  # ص
+    '\u0636\u0651' : 'ḏḏ'  # ض
+    '\u0637\u0651' : 'ţţ'  # ط
+    '\u0638\u0651' : 'z̧z̧'  # ظ
+    '\u063a\u0651' : 'ghgh'  # غ
+    '\u0641\u0651' : 'ff'  # ف
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0643\u0651' : 'kk'  # ك
+    '\u0644\u0651' : 'll'  # ل
+    '\u0645\u0651' : 'mm'  # م
+    '\u0646\u0651' : 'nn'  # ن
+    '\u0647\u0651' : 'hh'  # ه
+    '\u0648\u0651' : 'ww'  # و
+    '[\u064a|\u06cc]\u0651' : 'yy'  # ي
+
+    # NOTE 1
+    '\u0650\b' : '-e' # ِ kasra
+    '\u0674' : '-e' # ٴ
+    '\u0654' : '-e' #  ٔ
+
+    '\u0650\u064a\u0651\u064e' : 'īy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    '\u064e\u0649' : 'ay'  # ـَى fatha followed by ى which is ا not ي
+    '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+    '\u064e\u064a\u0652' : 'ay'  # ـَيْ
+    '\u0650\u06cc\u0651\u064e' : 'īy' # ـِيَّ
+    '\u064e\u064a' : 'aī'  # ـَي
+    '\u064e\u06cc' : 'aī'  # ـَي
+      # - '-ye'
+
+
+    # ta' marboota
+    '\u0629' : 'at' # ة in the middle of the sentence
+    '\u0629$' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{4})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{5})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{6})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{7})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{8})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{9})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{10})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{11})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{12})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{13})\u0629' : 'ah'
+
+
+
+    '\u0621' : '’' # ء
+    '\u0624' : '’' # ؤ
+    '\u0624\b' : '’o' # ؤ
+    '\u0626' : '’' # ئ
+
+    '\u0623' : ''  # أ
+    '\u0625' : ''    # إ
+    # See note B
+    '\b\u0627\u0644' : 'al '  # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    '\b\u0627\u0644\u062a' : 'at t'  # الت
+    '\b\u0627\u0644\u062b' : 'as̄ s̄'  # الث
+    '\b\u0627\u0644\u062f' : 'ad d' # الد
+    '\b\u0627\u0644\u0630' : 'az̄ z̄'  # الذ
+    '\b\u0627\u0644\u0631' : 'ar r' # الر
+    '\b\u0627\u0644\u0632' : 'az z'  # الز
+    '\b\u0627\u0644\u0633' : 'as s' # الس
+    '\b\u0627\u0644\u0634' : 'ash sh' # الش
+    '\b\u0627\u0644\u0635' : 'aş ş'  # الص
+    '\b\u0627\u0644\u0636' : 'aẕ ẕ'  # الض
+    '\b\u0627\u0644\u0637' : 'aţ ţ'  # الط
+    '\b\u0627\u0644\u0638' : 'az̧ z̧' # الظ
+    '\b\u0627\u0644\u0644' : 'al l'  # الل
+    '\b\u0627\u0644\u0646' : 'an n'  # الن
+
+
+    # consonant characters
+
+    '\u0628' : 'b'  # ب
+    '\u067E' : 'p' # پ
+    '\u062a' : 't'  # ت
+    '\u0679' : 'ṭ'  # ٹ
+    '\u062B' : 's̄'   # ث
+    '\u062c' : 'j'  # ج
+    '\u0686' : 'ch'  # ‫چ‬
+    '\u062d' : 'ḩ' # ح
+    '\u062e' : 'kh'  # خ
+    '\u062f' : 'd'  # د
+    '\u0688' : 'ḍ' # ‫ڈ
+    '\u0630' : 'z̄'  # ذ
+    '\u0631' : 'r'  # ر
+    '\u0691' : 'ṛ'   # ڑ
+    '\u0632' : 'z'  # ز
+    '\u0698' : 'zh'  # ‫ژ‬
+    '\u0633' : 's'  # س
+    '\u0634' : 'sh'  # ش
+    '\u0635' : 'ş'  # ص
+    '\u0636' : 'ẕ'  # ض
+    '\u0637' : 'ţ'  # ط
+    '\u0638' : 'z̧'  # ظ
+    '\u0639' : '‘'  # ع
+    '\u063a' : 'gh'  # غ
+    '\u0641' : 'f'  # ف
+    '\u0642' : 'q'  # ق
+    '\u0643' : 'k'  # ك
+    '\u06A9' : 'k' # ک
+    '\u06AF' : 'g' # ‫گ‬
+    '\u0644' : 'l'  # ل
+    '\u0645' : 'm'  # م
+    '\u0646' : 'n'  # ن
+    '\u06BA' : 'ñ' # ڼ
+    '[\u0647|\u06c1|\u06be]' : 'h'  # ه
+    '\u0648' : 'w'  # و
+    '[\u064a|\u06cc]' : 'y'  # ي
+    # '\u0649' : 'y'  # ي
+    '\u06D0' : 'ē'   # ې
+    '\u06CD' : 'êy'  # ‫ۍ‬