interscript-maps 2.3.0 → 2.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 73ee7bd0f92302a8534da56409afcea9e0c08f1645b9f40b7a100b02448c1ae6
-  data.tar.gz: 789d6049ad59dc694d2d4051339e3500be11b9d1af9327b130c96d29f3d8b625
+  metadata.gz: 12c3cef2ef226d7d08f66729623e3fba1b91573299a119610cb3c9112d7a9c2a
+  data.tar.gz: 2c0ec0ae787c4b6781b2a40553c4e1e06027a94a57c3b7175084b773333fb2c1
 SHA512:
-  metadata.gz: ff801e6bf560173c2ec9be62bb548afc14c46f9402c66443fd93ba1c1e63637c8d1afccf82acf0c9d22912a65d5e3b872a091de9d574b87f925bb3da8362dfd1
-  data.tar.gz: 71dcaa6597cca6848d370a216e40b301e91105d15895c90bc29332a2ce5f6090c56e04164e17083be79f143645b836f0342537e482af2e61af733db9f119c0fd
+  metadata.gz: d3ad87ac486640460c6768597341aa71ff606e7f19dbc9ada0d3ff2ebd52e1bbb48eda77f51339efbb6d689e028757ed4f5a12e78be88f7c2bf500194065cecd
+  data.tar.gz: 631068845f59ea3e76be07476e0426f3b7fe60e236c2197b62c13b9afcbdb783da0c0ebdae0964b87246a4a253ed6c9c13cf265bb54d63f0cc1e837e55bbdce9

data/interscript-maps.gemspec

@@ -1,4 +1,4 @@
-INTERSCRIPT_MAPS_VERSION="2.3.0"
+INTERSCRIPT_MAPS_VERSION="2.3.1"
 
 Gem::Specification.new do |spec|
   spec.name          = "interscript-maps"

data/interscript-maps.yaml

@@ -32,6 +32,10 @@ rababa-configs:
 skip:
   Interscript::Compiler::Javascript:
     - var-ara-Arab-Arab-rababa
+  # It works for detection, but takes too much time and doesn't make sense for
+  # the main usecase of Detector
+  Interscript::Detector:
+    - var-ara-Arab-Arab-rababa
   # Windows currently fails tests for rababa
   mswin64:
     - var-ara-Arab-Arab-rababa

data/maps/alalc-div-Thaa-Latn-2012.imp

@@ -0,0 +1,74 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:div
+  source_script: Thaa
+  destination_script: Latn
+  name: Romanization Table -- Divehi (2012)
+  url: https://www.loc.gov/catdir/cpso/romanization/divehi.pdf
+  creation_date: 2012
+  description: |
+    ALA-Library of Congress Divehi Romanization 2012 System
+
+  notes:
+
+    - |
+      Romanize ށް as ḫ when it doubles the following consonant or is used as a glottal stop.
+        aḫvana	އަށްވަނަ
+        maśaḫ	މަށަށް
+    - |
+      When used in medial position without ް (sukūn), romanize ނ as ṁ.
+        aṁga	އަނގަ
+        haṁdu	ހަނދު
+    - |
+      Romanization of އ.
+      (a) When used in the initial position with any vowel sign, do not romanize.
+        ata	އަތަ
+        idu	އިދު
+        umuru	އުމުރު
+        egahugi	އެގަހުގި
+      (b) When used in the medial position with any vowel sign, romanize as ’.
+        ha’hūnu	ހައިހޫނު
+        fa’isa	ފައިސަ
+        k’īn	ކްއީން
+      (c) When a consonant follows އް in medial position, double it in romanization.
+        cappalu	ޗައްޕަލު
+        appacci	އައްޕައްޗި
+      (d) When used in final position with ް (sukūn), romanize as h.
+        boh	ބޮއް
+        biheh	ބިހެއް
+    - |
+      Romanize ތް followed by another ތ as  t̤ .
+       at̤teri   އަތްތެރި
+    - |
+      Only the vowel forms that appear at the beginning of a syllable are listed.
+      When the vowels follow a consonant, އ is not used and the vowel signs are added to the consonant forms.
+      Do not distinguish between the two in romanization.
+    - |
+      ް (called sukūn) generally indicates omission of an inherent vowel associated with a consonant.
+      For its other uses, see Notes 1, 3, and 4.
+}
+
+tests {
+  test "މަށަށް", "maśaḫ"
+  test "އަނގަ", "aṁga"
+  test "ހަނދު", "haṁdu"
+  test "އަތަ", "ata"
+  test "އިދު", "idu"
+  test "އުމުރު", "umuru"
+  test "އެގަހުގި", "egahugi"
+  test "ފައިސަ", "faʼisa"
+  test "ބޮއް", "boh"
+  test "ބިހެއް", "biheh"
+  test "އަތްތެރި", "at̤teri"
+  test "ޗައްޕަލު", "cappalu"
+  test "އައްޕައްޗި", "appacci"
+}
+
+dependency "alalc-div-Thaa-Latn-1997", as: thaalatn
+
+stage {
+
+  run map.thaalatn.stage.main
+
+}

data/maps/alalc-kat-Geok-Latn-1997.imp

@@ -5,12 +5,11 @@ metadata {
   source_script: Geok
   destination_script: Latn
   name: Romanization Table -- Georgian Khutsuri (1997)
-  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  url: http://catdir.loc.gov/catdir/cpso/romanization/georgian.pdf
   creation_date: 1997
   confirmation_date: 1997
   description: |
     Values are shown for the Khutsuri alphabet.
-
   notes:
 }
 

data/maps/alalc-kat-Geok-Latn-2011.imp

@@ -0,0 +1,31 @@
+metadata {
+  authority_id: alalc
+  id: 2011
+  language: iso-639-2:kat
+  source_script: Geok
+  destination_script: Latn
+  name: Romanization Table -- Georgian Khutsuri (2011)
+  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  creation_date: 2011
+  confirmation_date: 2011
+  description: |
+    Values are shown for the Khutsuri alphabet.
+  notes:
+}
+
+tests {
+  test "ႼႨႢႬႨ", "CIGNI"
+  test "ⴜⴈⴂⴌⴈ", "cigni"
+  test "ႱႭႪႭႫႭႬ", "SOLOMON"
+  test "ⴑⴍⴊⴍⴋⴍⴌ", "solomon"
+  test "ႠႡႰႠჀႠႫ", "ABRAHAM"
+}
+
+
+dependency "alalc-kat-Geok-Latn-1997", as: geoklatn
+
+stage {
+
+  run map.geoklatn.stage.main
+
+}

data/maps/alalc-kat-Geor-Latn-1997.imp

@@ -5,13 +5,12 @@ metadata {
   source_script: Geor
   destination_script: Latn
   name: Romanization Table -- Georgian Mkhedruli (1997)
-  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  url: http://catdir.loc.gov/catdir/cpso/romanization/georgian.pdf
   creation_date: 1997
   confirmation_date: 1997
   description: |
     Values are shown for the older Khutsuri and the modern Mkhedruli alphabets.
     There are no upper case letters in Mkhedruli.
-
   notes:
 }
 

data/maps/alalc-kat-Geor-Latn-2011.imp

@@ -0,0 +1,52 @@
+metadata {
+  authority_id: alalc
+  id: 2011
+  language: iso-639-2:kat
+  source_script: Geor
+  destination_script: Latn
+  name: Romanization Table -- Georgian Mkhedruli (2011)
+  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  creation_date: 2011
+  confirmation_date: 2011
+  description: |
+    Values are shown for the older Khutsuri and the modern Mkhedruli alphabets.
+    There are no upper case letters in Mkhedruli.
+  notes:
+}
+
+tests {
+  test "ხაოფსე", "xaopʻse"
+  test "ჭლოუ", "člou"
+  test "ჩოხულდი", "čʻoxuldi"
+  test "ქვემო ლინდა", "kʻvemo linda"
+  test "ტამკვაჩ იგვავერა", "tamkvačʻ igvavera"
+  test "სვანეთი", "svanetʻi"
+  test "საცხვარისი", "sacʻxvarisi"
+  test "მუხრან-თელეთი", "muxran-tʻeletʻi"
+  test "მუცდი", "mucʻdi"
+  test "ლეჩხუმი", "lečʻxumi"
+  test "ვერხნაია მწარა", "verxnaia mcara"
+  test "ეგრისის ქედი", "egrisis kʻedi"
+  test "დოჩარიფშა", "dočʻaripʻša"
+  test "ბოლოკო", "boloko"
+  test "აჭანდარა", "ačandara"
+  test "აუალიცა", "aualicʻa"
+  test "აკალამრა", "akalamra"
+  test "ლასილი", "lasili"
+  test "გუბაზეული", "gubazeuli"
+  test "ბაყაყი", "baqaqi"
+  test "ძროხა", "żroxa"
+  test "ჰაერი", "haeri"
+  test "ჟოლო", "žolo"
+  test "ჯართი", "jartʻi"
+  test "ღრმაღელე", "ġrmaġele"
+}
+
+dependency "alalc-kat-Geor-Latn-1997", as: georlatn
+
+stage {
+
+  run map.georlatn.stage.main
+
+}
+

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

@@ -179,9 +179,9 @@ stage {
     sub "ඹ", "mba"
 
     # Other ligatures
-    sub "ක්‍ෂ", "kṣha"
+    sub "ක්", "k"
     sub "ඥ", "jña"
-    sub "න්‍ද", "nda"
+    sub "න්", "n"
 
     # numbers
     sub "\u0DE6", "0"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: interscript-maps
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.3.1
 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