interscript-maps 2.2.1 → 2.3.0

data/maps/odni-bul-Cyrl-Latn-2015.imp

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Bulgarian Personal Names (2015), ICS-630-01 Annex O
-
-  # url:
+  name: ICS-630-01 Romanization of Bulgarian Personal Names (2015)
   source: ICS-630-01 Annex O
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-che-Cyrl-Latn-2015.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:che
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Chechen Cyrillic Personal Names (2015)
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20C%20-%20Chechen_Personal_Names_FLTS%20(U).pdf
+  name: ICS-630-01 Romanization of Chechen Cyrillic Personal Names (2015)
   source: ICS-630-01 Annex C
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-fas-Arab-Latn-2004.imp

@@ -5,7 +5,6 @@ metadata {
   source_script: Arab
   destination_script: Latn
   name: Intelligence Community (IC) Standard for the Transliteration of Farsi (Persian) Personal Names (2004)
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Farsi_(Persian)_%26_Dari_IC_Standards.doc
   creation_date: 2004
   confirmation_date: 2004-11
   description: |

data/maps/odni-fas-Arab-Latn-2015.imp

@@ -4,10 +4,10 @@ metadata {
   language: iso-639-2:fas
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Persian Farsi Dari Personal Names (2015), ICS-630-01 Annex J
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+  name: ICS-630-01 Romanization of Persian Farsi Dari Personal Names (2015)
+  source: ICS-630-01 Annex J
   creation_date: 2015
-  confirmation_date: 2015-11
+  confirmation_date: 2018-11
   description: |
     This system is the Intelligence Community (IC) standard for
     the transliteration of Persian (Farsi)

data/maps/odni-hin-Deva-Latn-2004.imp

@@ -5,7 +5,6 @@ metadata {
   source_script: Deva
   destination_script: Latn
   name: Intelligence Community (IC) Standard for the Transliteration of Hindi and Urdu Personal Names (2004)
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Hindi_and_Urdu_IC_Standard.doc
   creation_date: 2004
   description: |
     IC STANDARDS FOR TRANSLITERATION OF HINDI AND URDU PERSONAL NAMES

data/maps/odni-hin-Deva-Latn-2015.imp

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: Romanization of Hindi Urdu Personal Names (2015), ICS-630-01 Annex F
-  #url:
+  name: ICS-630-01 Romanization of Hindi Urdu Personal Names (2015)
+  source: ICS-630-01 Annex F
   creation_date: 2015
   confirmation_date: 2015
   description: |

data/maps/odni-kat-Geor-Latn-2015.imp

@@ -4,9 +4,8 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: Romanization of Georgian Personal Names (2015), ICS 630-01 Annex E
-  # url:
-  source: ICS 630-01, Annex E
+  name: ICS-630-01 Romanization of Georgian Personal Names (2015)
+  source: ICS-630-01 Annex E
   creation_date: 2015
   confirmation_date: 2015
   description: |

data/maps/odni-kaz-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kaz
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Kazakh Personal Names (2015)
+  name: ICS-630-01 Romanization of Kazakh Personal Names (2015)
   source: ICS-630-01 Annex Q
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-kir-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kir
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Kyrgyz Personal Names (2015)
+  name: ICS-630-01 Romanization of Kyrgyz Personal Names (2015)
   source: ICS-630-01 Annex R
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-kor-Hang-Latn-2015.imp

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Romanization of Korean Personal Names (2015), ICS-630-01 Annex W
-  url:
+  name: ICS-630-01 Romanization of Korean Personal Names (2015)
+  source: ICS-630-01 Annex W
   creation_date: 2015
   adoption_date:
   description:

data/maps/odni-mkd-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mkd
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of macedonian Personal Names (2015)
+  name: ICS-630-01 Romanization of Macedonian Personal Names (2015)
   source: ICS-630-01 Annex H
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-prs-Arab-Latn-2004.imp

@@ -5,7 +5,6 @@ metadata {
   source_script: Arab
   destination_script: Latn
   name: Intelligence Community (IC) Standard for the Transliteration of Dari Personal Names (2004)
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Farsi_(Persian)_%26_Dari_IC_Standards.doc
   creation_date: 2004
   confirmation_date: 2004-11
   description: |

data/maps/odni-prs-Arab-Latn-2015.imp

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-3:prs
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Persian Farsi Dari Personal Names (2015), ICS-630-01 Annex J
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+  name: ICS-630-01 Romanization of Persian Farsi Dari Personal Names (2015)
+  source: ICS-630-01 Annex J
   creation_date: 2015
   confirmation_date: 2015-11
   description: |

data/maps/odni-pus-Arab-Latn-2011.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-3:prs
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Pashto Personal Names (2011)
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Pashto%20June%202011.pdf
+  name: Pashto Standardized Transliteration System for Personal Names (2011)
   creation_date: 2011
   confirmation_date: 2011-06
   description: |

data/maps/odni-rus-Cyrl-Latn-2015.imp

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Russian Personal Names (2015), ICS-630-01 Annex K
-
-  # url:
+  name: ICS-630-01 Romanization of Russian Personal Names (2015)
   source: ICS-630-01 Annex K
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-srp-Cyrl-Latn-2005.imp

@@ -9,7 +9,6 @@ metadata {
   confirmation_date: 2005
   description: |
     Office of the Director Of National Intelligence Serbian Personal Names 2004 System
-
   notes:
 }
 

data/maps/odni-srp-Cyrl-Latn-2015.imp

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:srp
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Serbian Personal Names (2015), ICS-630-01 Annex L
-
-  # url:
+  name: ICS-630-01 Romanization of Serbian Personal Names (2015)
   source: ICS-630-01 Annex L
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-tat-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tat
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Tatar Personal Names (2015)
+  name: ICS-630-01 Romanization of Tatar Personal Names (2015)
   source: ICS-630-01 Annex S
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-tgk-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tgk
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Tajik Personal Names (2015)
+  name: ICS-630-01 Romanization of Tajik Personal Names (2015)
   source: ICS-630-01 Annex N
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-tuk-Cyrl-Latn-2015.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:tuk
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Turkmen Personal Names (2015)
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20T%20-%20Turkmen_Personal_Names_FLTS%20(U).pdf
+  name: ICS-630-01 Romanization of Turkmen Personal Names (2015)
   source: ICS-630-01 Annex T
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-uig-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:uig
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Uyghur Personal Names (2015)
+  name: ICS-630-01 Romanization of Uyghur Personal Names (2015)
   source: ICS-630-01 Annex U
   creation_date: 2015
   confirmation_date: 2015

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

@@ -4,10 +4,8 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Ukrainian Personal Names (2015), ICS 630-01 Annex M
-
-  # url:
-  source: ICS 630-01, Annex M
+  name: ICS-630-01 Romanization of Ukrainian Personal Names (2015)
+  source: ICS-630-01 Annex M
   creation_date: 2015
   confirmation_date: 2015
   description: |

data/maps/odni-urd-Arab-Latn-2015.imp

@@ -4,9 +4,8 @@ metadata {
   language: iso-639-2:urd
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Hindi and Urdu Personal Names (2015), ICS-630-01 Annex F
-
-  #url:
+  name: ICS-630-01 Romanization of Hindi and Urdu Personal Names (2015)
+  source: ICS-630-01 Annex F
   creation_date: 2015
   confirmation_date: 2015
   description: |

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

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:uzb
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Uzbek Personal Names (2015), ICS-630-01 Annex V
-
-  # url:
+  name: ICS-630-01 Romanization of Uzbek Personal Names (2015)
   source: ICS-630-01 Annex V
   creation_date: 2015
   confirmation_date: 2015

data/maps/ses-ara-Arab-Latn-1930.imp

@@ -1,58 +1,15 @@
 metadata {
-  authority_id: ungegn
+  authority_id: ses
   id: 1930
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  name: Survey of Egypt Romanization
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 1930
   confirmation_date: 2018-06
   description: |
-    The current United Nations recommended romanization
-    system was approved in 2017 (resolution XI/3), based on
-    the system adopted by Arabic experts at the conference
-    held in Beirut in 2007, the Unified Arabic
-    Transliteration System, taking into account the
-    practical amendments and corrections carried out and
-    agreed upon by the representatives of the Arabic-
-    speaking countries at the Fourth Arab Conference on
-    Geographical Names, held in Beirut in 2008, and some
-    clarifications and amendments agreed in Riyadh in 20171.
-    Previously, the United Nations had approved a
-    romanization system in 1972 (resolution II/8), based on the
-    system adopted by Arabic experts at the conference
-    held at Beirut in 1971 with the practical amendments carried out
-    and agreed upon by the representatives of the Arabic-speaking
-    countries at their conference. The table was published in volume
-    II of the conference report.
-    In UN resolution XI/3 it is specifically stated that the
-    system was recommended for the “romanization of the
-    geographical names within those Arabic-speaking countries
-    where this system is officially adopted”. There is
-    evidence of its partial implementation in Jordan, Oman and
-    Saudi Arabia. The UNGEGN Working Group on Romanization
-    Systems intends to continue monitoring the UN system’s
-    implementation across Arabic-speaking countries.
-    In some countries there exist local romanization schemes
-    or practices. The geographical names of Algeria, Djibouti,
-    Mauritania, Morocco and Tunisia are generally rendered in
-    the traditional manner which conforms to the principles of
-    the French orthography.
-    The previous UN-approved system is still found in
-    considerable international usage.
-    Arabic is written from right to left. The Arabic script
-    usually omits vowel points and diacritical marks from
-    writing which makes it difficult to obtain uniform results
-    in the romanization of Arabic. It is essential to identify
-    correctly the words which appear in any particular name
-    and to know the standard Arabic-script spelling including
-    the relevant vowels. One must also take into account
-    dialectal and idiosyncratic deviations. The romanization
-    is generally reversible though there may be some ambiguous
-    letter sequences (dh, kh, sh, th) which may also point to
-    combinations of Arabic characters in addition to the
-    respective single characters.
+    The Survey of Egypt System (SES) of Romanization.
   notes:
     - |
       The Survey of Egypt System (SES) of romanization has the following correspondences with

data/maps/un-ara-Arab-Latn-1971.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1971
   language: iso-639-2:ara
   source_script: Arab

data/maps/un-ara-Arab-Latn-1972.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1972
   language: iso-639-2:ara
   source_script: Arab

data/maps/un-ara-Arab-Latn-2017.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2017
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Arabic -- UNGEGN (2017)
+  name: Romanization of Arabic -- Unified Arabic Transliteration System (2017)
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 2017
   confirmation_date: 2018-06

data/maps/un-hin-Deva-Latn-2016.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2016
   language: iso-639-2:hin
   source_script: Deva

data/maps/un-kan-Kana-Latn-2016.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2016
   language: iso-639-2:kan
   source_script: Kana

data/maps/un-mar-Deva-Latn-2016.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2016
   language: iso-639-2:hin
   source_script: Deva

data/maps/un-nep-Deva-Latn-1972.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1972
   language: iso-639-2:nep
   source_script: Deva

data/maps/un-nep-Deva-Latn-2013.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2013
   language: iso-639-2:nep
   source_script: Deva

data/maps/un-ori-Orya-Latn-1972.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1972
   language: iso-639-2:ori
   source_script: Orya

data/maps/un-rus-Cyrl-Latn-1987.imp

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1987
   language: iso-639-2:rus
   source_script: Cyrl

data/maps/un-sin-Sinh-Latn-1972.imp

@@ -5,6 +5,7 @@ metadata {
   source_script: Sinh
   destination_script: Latn
   name: Romanization of Sinhalese -- UNGEGN 4.0 (1972)
+  source: "Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp. 151–152."
   url: https://www.eki.ee/wgrs/rom1_ml.htm
   creation_date: 1972
   confirmation_date: 2016
@@ -18,7 +19,6 @@ metadata {
     Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially) and in an
     abbreviated form, to denote vowels after consonants.
 
-
   notes:
     - |
       The character ඇ was romanized as a͝i and the character ඈ as ai in Sharma's table, but there was no romanization for the character ඓ which,
@@ -37,13 +37,13 @@ metadata {
 
 tests {
   test "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා", "shīra laṁkāve kīraḍāva itihāsaye ihaḷama tæ̆nakaṭa genna kaṭayutu karanavā"
-  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kŏchchikaඬe moyakaṭa asala næmaṭa giya taruṇayo 3k maruṭa - miturāge upan dinaya sæ̆marīmaṭa æ̆vit"
+  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kŏchchikaṇḍae moyakaṭa asala næmaṭa giya taruṇayo 3k maruṭa - miturāge upan dinaya sæ̆marīmaṭa æ̆vit"
   test "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා", "loka ḷamā dinayadā sisun pirisak kasippu bīlā"
   test "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ", "koṭi 16ka hĕrŏyin samaga dankŏṭuvedī 7k dæ̆le"
   test "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි", "minuvangŏḍa pīsīār dĕdahasak sidukarayi"
   test "පාස්කු ප‍්‍රහාරය වගේම පාස්කු ප්‍රෝඩාව ගැනත් සොයන්න කොමිසමක් පත්කළ යුතුයි - විපක්‍ෂ නායක සජිත් පේ‍්‍රමදාස", "pāsku parahāraya vagema pāsku proḍāva gæ̆nat sŏyanna kŏmisamak patkaḷa yutuyi - vipakṣha nāyaka sajit peramadāsa"
   test "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි", "ṭarampge saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
-  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsku dā parahāraya piḷibaඳ parīkṣhaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa dĕnne næ - agamæ̆ti"
+  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsku dā parahāraya piḷibanda parīkṣhaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa dĕnne næ - agamæ̆ti"
   test "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි", "dilli kæ̆piṭals saha kolige bæ̆ṁgalor tĕvæ̆ni jaya labayi"
   test "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා", "sharī lāṁkika sambhavayak sahita paraṁshaye pavulaka 5 k ghātanaya karalā"
   test "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර", "pæ̆tikudaya ikmanin suva karana paratikāra"
@@ -171,6 +171,18 @@ stage {
     sub "ෆ", "fa"
     sub "ළ", "ḷa"
 
+    # Prenasalized sounds
+    sub "ඟ", "ṅga"
+    sub "ඦ", "ñja"
+    sub "ඬ", "ṇḍa"
+    sub "ඳ", "nda"
+    sub "ඹ", "mba"
+
+    # Other ligatures
+    sub "ක්‍ෂ", "kṣha"
+    sub "ඥ", "jña"
+    sub "න්‍ද", "nda"
+
     # numbers
     sub "\u0DE6", "0"
     sub "\u0DE7", "1"