interscript-maps 2.1.0 → 2.3.1a

data/maps/acadsin-zho-Hani-Latn-2002.imp

@@ -4,9 +4,9 @@ metadata {
   language: iso-639-2:zho
   source_script: Hani
   destination_script: Latn
-  name: Chinese Tongyong Pinyin Academica Sinica 2002 System
+  name: Tongyong Pinyin System (2002)
   url:
-  description: Chinese Tongyong Pinyin Academica Sinica 2002 System
+  description: Academia Sinica Tongyong Pinyin System (2002)
 }
 
 tests {

data/maps/alalc-amh-Ethi-Latn-1997.imp

@@ -4,14 +4,18 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Amharic (1997)
+  name: Romanization Table -- Amharic (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/amharic.pdf
   creation_date: 1997
   description: |
-    ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts. Randal K. Berry (ed.). Library of Congress, 1997.
-  
+    ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts.
+    Randal K. Berry (ed.). Library of Congress, 1997.
+
   notes:
-    - The Ethiopic script used for Amharic is also used for other languages, including Ge’ez, Argobba, Gurage, and Tigre. Ge’ez, which is chiefly a liturgical language, uses only 26 basic letter forms from this table.
+    - |
+      The Ethiopic script used for Amharic is also used for other languages,
+      including Ge’ez, Argobba, Gurage, and Tigre. Ge’ez, which is chiefly a
+      liturgical language, uses only 26 basic letter forms from this table.
 }
 
 tests {
@@ -319,17 +323,17 @@ stage {
     sub "ቬ", "vé"
     sub "ቭ", any(["ve", "v"])
     sub "ቮ", "vo"
-    
+
     sub "ቈ", "qwa"
     sub "ቊ", "qwi"
     sub "ቋ", "qwā"
     sub "ቌ", "qwé"
     sub "ቍ", "qwe"
-    sub "ኈ", "hwa"
-    sub "ኊ", "hwi"
-    sub "ኋ", "hwā"
-    sub "ኌ", "hwé"
-    sub "ኍ", "hwe"
+    sub "ኈ", "ẖwa"
+    sub "ኊ", "ẖwi"
+    sub "ኋ", "ẖwā"
+    sub "ኌ", "ẖwé"
+    sub "ኍ", "ẖwe"
     sub "ኰ", "kwa"
     sub "ኲ", "kwi"
     sub "ኳ", "kwā"
@@ -340,7 +344,7 @@ stage {
     sub "ጓ", "gwā"
     sub "ጔ", "gwé"
     sub "ጕ", "gwe"
-    
+
     sub "ሏ", "lwa"
     sub "ቧ", "bwa"
     sub "ዟ", "zwa"
@@ -361,12 +365,12 @@ stage {
     sub "ሿ", "šwa"
     sub "ኟ", "ñwa"
     sub "ጇ", "ǧwa"
-    
+
     sub "ፙ", "mya"
     sub "ፚ", "fya"
-    
+
     sub "ኧ", "ă"
-    
+
     sub "፩", "1"
     sub "፪", "2"
     sub "፫", "3"

data/maps/alalc-amh-Ethi-Latn-2011.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Amharic (2011)
+  name: Romanization Table -- Amharic (2011)
   url: https://www.loc.gov/catdir/cpso/romanization/amharic.pdf
   creation_date: 2011
   description: ''

data/maps/alalc-ara-Arab-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Arabic (1997)
+  name: Romanization Table -- Arabic (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/arabic.pdf
   creation_date: 1997
   description: |

data/maps/alalc-asm-Deva-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:asm
   source_script: Deva
   destination_script: Latn
-  name: Assamese Romanization, 1997
+  name: Romanization Table -- Assamese (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/assamese.pdf
   creation_date: 1997
   description: |

data/maps/alalc-asm-Deva-Latn-2012.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:asm
   source_script: Deva
   destination_script: Latn
-  name: Assamese Romanization, 2012
+  name: Romanization Table -- Assamese (2012)
   url: https://www.loc.gov/catdir/cpso/romanization/assamese.pdf
   creation_date: 1997
   description: |

data/maps/alalc-aze-Arab-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:aze
   source_script: Arab
   destination_script: Latn
-  name: ALA-LC Romanization Table -- azerbaij (1997)
+  name: Romanization Table -- azerbaij (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/azerbaij.pdf
   creation_date: 1997
   description: |

data/maps/alalc-aze-Cyrl-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:aze
   source_script: Cyrl
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Azerbaijani (1997)
+  name: Romanization Table -- Azerbaijani (1997)
   url: https://transliteration.eki.ee/pdf/Azerbaijani.pdf
   creation_date: 1997
   description: |

data/maps/alalc-bel-Cyrl-Latn-1997.imp

@@ -4,10 +4,10 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Byelorussian (1997)
+  name: Romanization Table -- Byelorussian (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/beloruss.pdf
   creation_date: 1997
-  
+
   notes:
     - Ґ letter found in Old Belarusian and in modern publications in Tarashkevitsa orthography.
     - Do not confuse with the digraph кг (also romanized as “kh”). Manual review may be needed when transcribing data in vernacular characters in order to distinguish х from кг.
@@ -43,7 +43,7 @@ stage {
     sub "\u00B4", "" # official english Apostrophe
     sub "\u02BC", ""
     sub "\u0027", "" # from belarussian keyboard
-    
+
     # Characters
     sub "\u0410", "A" # A
     sub "\u0411", "B" # Б
@@ -78,7 +78,7 @@ stage {
     sub "\u042D", "Ė" # Э : Ė
     sub "\u042E", "I͡U" # Ю : I͡U
     sub "\u042F", "I͡A" # Я : I͡A
-    
+
     sub "\u0430", "a" # а
     sub "\u0431", "b" # б
     sub "\u0432", "v" # в

data/maps/alalc-ben-Beng-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Bengali Romanization, 1997
+  name: Romanization Table -- Bengali (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/bengali.pdf
   creation_date: 1997
   description: |

data/maps/alalc-ben-Beng-Latn-2017.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Bengali Romanization, 2017
+  name: Romanization Table -- Bengali (2017)
   url: https://www.loc.gov/catdir/cpso/romanization/bengali.pdf
   creation_date: 2017
   description: |

data/maps/alalc-bul-Cyrl-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: ALA-LC Romanization Table -- Bulgarian (1997)
+  name: Romanization Table -- Bulgarian (1997)
   url: http://www.rechtertie.nl/databases/judd/downloads/Bulgarian.pdf
   creation_date: 1997
 

data/maps/alalc-div-Thaa-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:div
   source_script: Thaa
   destination_script: Latn
-  name: ALA-Library of Congress Divehi Romanization 1997 System
+  name: Romanization Table -- Divehi (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/divehi.pdf
   creation_date: 1997
   description: |

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-ell-Grek-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: Greek Romanization, 1997
+  name: Romanization Table -- Greek (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/greek.pdf
   creation_date: 1997
   description: |

data/maps/alalc-ell-Grek-Latn-2010.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: Greek Romanization, 2010
+  name: Romanization Table -- Greek (2010)
   url: http://catdir.loc.gov/catdir/cpso/romanization/greek.pdf
   creation_date: 2010
   description: |

data/maps/alalc-guj-Gujr-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: Gujarati Romanization, 1997
+  name: Romanization Table -- Gujarati (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/gujarati.pdf
   creation_date: 1997
   description: |

data/maps/alalc-guj-Gujr-Latn-2011.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: Gujarati Romanization, 2011
+  name: Romanization Table -- Gujarati (2011)
   url: https://www.loc.gov/catdir/cpso/romanization/gujarati.pdf
   creation_date: 2011
   description: |

data/maps/alalc-hin-Deva-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: Hindi Romanization, 1997
+  name: Romanization Table -- Hindi (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/hindi.pdf
   creation_date: 1997
   description: |

data/maps/alalc-hin-Deva-Latn-2011.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: Hindi Romanization, 2011
+  name: Romanization Table -- Hindi (2011)
   url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
   creation_date: 1997
   description: |

data/maps/alalc-kan-Kana-Latn-1997.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: Kannada Romanization, 1997
+  name: Romanization Table -- Kannada (1997)
   url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
   creation_date: 1997
   description: |

data/maps/alalc-kan-Kana-Latn-2011.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: Kannada Romanization, 2011
+  name: Romanization Table -- Kannada (2011)
   url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
   creation_date: 2011
   description: |

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

@@ -4,13 +4,12 @@ metadata {
   language: iso-639-2:kat
   source_script: Geok
   destination_script: Latn
-  name: ALA-LC Georgian System (1997)
-  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  name: Romanization Table -- Georgian Khutsuri (1997)
+  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:
 }
 
@@ -64,7 +63,7 @@ stage {
     sub "\u10c3", "W" # Ⴣ
     sub "\u10c4", "X̣" # Ⴤ
     sub "\u10c5", "Ō" # Ⴥ
-    
+
     sub "\u2d00", "a" # ⴀ
     sub "\u2d01", "b" # ⴁ
     sub "\u2d02", "g" # ⴂ

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

@@ -4,14 +4,13 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: ALA-LC Georgian System (1997)
-  url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+  name: Romanization Table -- Georgian Mkhedruli (1997)
+  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:
 }
 
@@ -54,27 +53,27 @@ stage {
     sub "\u10d4", "e" # ე
     sub "\u10d5", "v" # ვ
     sub "\u10d6", "z" # ზ
-    
+
     sub "\u10f1", "ē" # ჱ
-    
+
     sub "\u10d7", "tʻ" # თ
     sub "\u10d8", "i" # ი
     sub "\u10d9", "k" # კ
     sub "\u10da", "l" # ლ
     sub "\u10db", "m" # მ
     sub "\u10dc", "n" # ნ
-    
+
     sub "\u10f2", "y" # ჲ
-    
+
     sub "\u10dd", "o" # ო
     sub "\u10de", "p" # პ
     sub "\u10df", "ž" # ჟ
     sub "\u10e0", "r" # რ
     sub "\u10e1", "s" # ს
     sub "\u10e2", "t" # ტ
-    
+
     sub "\u10f3", "w" # ჳ
-    
+
     sub "\u10e3", "u" # უ
     sub "\u10e4", "pʻ" # ფ
     sub "\u10e5", "kʻ" # ქ
@@ -87,14 +86,14 @@ stage {
     sub "\u10ec", "c" # წ
     sub "\u10ed", "č" # ჭ
     sub "\u10ee", "x" # ხ
-    
+
     sub "\u10f4", "x̣" # ჴ
-    
+
     sub "\u10ef", "j" # ჯ
     sub "\u10f0", "h" # ჰ
-    
+
     sub "\u10f5", "ō" # ჵ
-    
+
     sub "\u10f6", "f" # ჶ
     sub "\u10f7", "ĕ" # ჷ
     sub "\u10f8", "ʻ" # ჸ