interscript-maps 2.2.1 → 2.3.2

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 "ක්", "k"
+    sub "ඥ", "jña"
+    sub "න්", "n"
+
     # numbers
     sub "\u0DE6", "0"
     sub "\u0DE7", "1"

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

@@ -1,5 +1,5 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2017
   language: iso-639-2:ara
   source_script: Arab

data/maps/var-ara-Arab-Arab-rababa.imp

@@ -0,0 +1,25 @@
+metadata {
+  authority_id: var
+  id: rababa
+  language: iso-639-2:ara
+  source_script: Arab
+  destination_script: Latn
+  name: RABABA the Arabic Diacritization Library
+  url: https://github.com/interscript/rababa/
+  description: |
+    Arabic diacritization is useful for several practical business cases
+    like text to speech or Romanization of Arabic texts or scripts.
+
+    This map in particular uses the RABABA library to automatically detect
+    and add diacritics using machine learning.
+}
+
+tests {
+  test 'قطر' ,'قِطْرَ'
+  test 'abc', 'abc'
+  test '‘Iz. Ibrāhīm as-Sa‘danī', '‘Iz. Ibrāhīm as-Sa‘danī'
+}
+
+stage {
+  rababa config: "200"
+}

data/maps/var-jpn-Hrkt-Latn-hepburn-1886.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: Traditional Hepburn
+  name: Traditional Hepburn System
   url: http://www.ab.cyberhome.ne.jp/~kaizu/roomazi/doc/hep3.html
   creation_date: 1886
   adoption_date:

data/maps/var-jpn-Hrkt-Latn-hepburn-1954.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: Modified Hepburn
+  name: Modified Hepburn System
   url:
   creation_date: 1954
   adoption_date:

data/maps/var-kor-Hang-Latn-mr-1939.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: McCune-Reischauer System
+  name: McCune-Reischauer System (Hangul-Latin)
   url:
   creation_date: 1939
   adoption_date:

data/maps/var-kor-Kore-Latn-mr-1939.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: McCune-Reischauer System
+  name: McCune-Reischauer System (Korean-Latin)
   url:
   creation_date: 1939
   adoption_date:

data/maps/var-mar-Deva-Latn-hunterian-1872.imp

@@ -11,7 +11,6 @@ metadata {
     The Hunterian system is the national system of romanization in India.
 
   notes:
-
     -  a, i and u are used in word-final position. The a in gaon and the u in pur are not accented.
     -  ज्ञ is transliterated gy.
     -  v is used before i.

data/maps/var-mon-Mong-Latn-1930.imp

@@ -48,7 +48,7 @@ metadata {
       'the state' etc. Multi-letter suffixes most often start with an initial- (consonants),
       medial- (vowels), or variant-shaped form.
 
-    # Note: Provedid sample of "Latin 1931-1939" in https://en.m.wikipedia.org/wiki/Mongolian_Latin_alphabet is not actual transliteration.
+    # Note: Provided sample of "Latin 1931-1939" in https://en.m.wikipedia.org/wiki/Mongolian_Latin_alphabet is not actual transliteration.
     # It's kind of buggy transliteration that mixes Cyrillic and Traditional Mongolian script into Latin based on phonetic sound.
     # There is no expected transliteration sources found for the tests.
 

data/maps/var-mon-Mong-Latn-lessing.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mon
   source_script: Mong
   destination_script: Latn
-  name: Transliteration Systems for Uyghur-Mongolian or Vertical or Old Script
+  name: Lessing transliteration system for Uyghur-Mongolian script
   url: https://collab.its.virginia.edu/wiki/tibetan-script/Transliteration%20Schemes%20for%20Mongolian%20Vertical%20Script.html
   creation_date:
   description: |
@@ -18,7 +18,7 @@ metadata {
 
   notes:
     - A separated final form of vowels a or e is common, and can appear at the end
-      of a word, word stem, or suffix. This form rexuires a final-shaped preceding
+      of a word, word stem, or suffix. This form requires a final-shaped preceding
       consonant and an inter-word gap in between. The vowels themselves appear as ᠎ᠠ,
       and with consonants as ‍ᠬ᠎ᠠ q‑a, ‍ᠷ᠎ᠠ r‑a/r‑e, etc. This gap can be transliterated
       with a hyphen. In digital typesetting, these forms are triggered by inserting

data/maps/var-mon-Mong-Latn-vpmc.imp

@@ -1,10 +1,10 @@
 metadata {
   authority_id: var
-  id: VPMC
+  id: vpmc
   language: iso-639-2:mon
   source_script: Mong
   destination_script: Latn
-  name: Transliteration Systems for Uyghur-Mongolian or Vertical or Old Script
+  name: VPMC transliteration system for Uyghur-Mongolian script
   url: https://collab.its.virginia.edu/wiki/tibetan-script/Transliteration%20Schemes%20for%20Mongolian%20Vertical%20Script.html
   creation_date:
   description: |

data/maps/var-pra-Deva-Latn-iast-1912.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pra
   source_script: Deva
   destination_script: Latn
-  name: IAST Sanskrit Devanagari System
+  name: IAST Sanskrit Devanagari System (Prakrit)
   url: https://www.ashtangayoga.info/philosophy/sanskrit-and-devanagari/transliteration/pronunciation-transliterations/
   creation_date: 1912
   description:

data/maps/var-san-Deva-Latn-iast-1912.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:san
   source_script: Deva
   destination_script: Latn
-  name: IAST Sanskrit Devanagari System
+  name: IAST Sanskrit Devanagari System (Sanskrit)
   url: https://www.ashtangayoga.info/philosophy/sanskrit-and-devanagari/transliteration/pronunciation-transliterations/
   creation_date: 1912
   description:

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: interscript-maps
 version: !ruby/object:Gem::Version
-  version: 2.2.1
+  version: 2.3.2
 platform: ruby
 authors:
 - Ribose Inc.
@@ -44,6 +44,7 @@ files:
 - maps/alalc-ben-Beng-Latn-2017.imp
 - maps/alalc-bul-Cyrl-Latn-1997.imp
 - maps/alalc-div-Thaa-Latn-1997.imp
+- maps/alalc-div-Thaa-Latn-2012.imp
 - maps/alalc-ell-Grek-Latn-1997.imp
 - maps/alalc-ell-Grek-Latn-2010.imp
 - maps/alalc-guj-Gujr-Latn-1997.imp
@@ -53,7 +54,9 @@ files:
 - maps/alalc-kan-Kana-Latn-1997.imp
 - maps/alalc-kan-Kana-Latn-2011.imp
 - maps/alalc-kat-Geok-Latn-1997.imp
+- maps/alalc-kat-Geok-Latn-2011.imp
 - maps/alalc-kat-Geor-Latn-1997.imp
+- maps/alalc-kat-Geor-Latn-2011.imp
 - maps/alalc-kor-Hang-Latn-1997.imp
 - maps/alalc-mal-Mlym-Latn-1997.imp
 - maps/alalc-mal-Mlym-Latn-2012.imp
@@ -299,6 +302,7 @@ files:
 - maps/un-ukr-Cyrl-Latn-2012.imp
 - maps/un-urd-Arab-Latn-1972.imp
 - maps/var-amh-Ethi-Latn-eae-2003.imp
+- maps/var-ara-Arab-Arab-rababa.imp
 - maps/var-gez-Ethi-Latn-eae-2003.imp
 - maps/var-hin-Deva-Latn-hunterian-1872.imp
 - maps/var-jpn-Hrkt-Latn-hepburn-1886.imp