interscript-maps 2.2.1 → 2.3.0

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: 2.3.0
 platform: ruby
 authors:
 - Ribose Inc.
@@ -299,6 +299,7 @@ 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