interscript-maps 2.1.0 → 2.3.1a

data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: BGN/PCGN 1965 System
+  name: Romanization of Ukrainian (1965)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816788/ROMANIZATION_OF_UKRAINIAN.pdf
   creation_date: 1947
   confirmation_date: 2019-06

data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: BGN/PCGN 2019 Agreement
+  name: Romanization of Ukrainian (2019 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/864314/ROMANIZATION_OF_UKRAINIAN.pdf
   creation_date: 2019
   confirmation_date: 2020-01

data/maps/bgnpcgn-urd-Arab-Latn-2007.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:urd
   source_script: Arab
   destination_script: Latn
-  name: BGN/PCGN Romanization System -- Urdu (2007)
+  name: Romanization of Urdu (2007)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693788/ROMANIZATION_OF_URDU.pdf
   creation_date: 2007
   confirmation_date: 2017-11
@@ -251,20 +251,20 @@ stage {
     # '\uFE8E' : ''  # ﺎ
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "at t" # الت
-    sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
-    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
-    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
-    sub boundary + "\u0627\u0644\u0632", "az z" # الز
-    sub boundary + "\u0627\u0644\u0633", "as s" # الس
-    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
-    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
-    sub boundary + "\u0627\u0644\u0636", "aẕ ẕ" # الض
-    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
-    sub boundary + "\u0627\u0644\u0638", "az̧ z̧" # الظ
-    sub boundary + "\u0627\u0644\u0644", "al l" # الل
-    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "as̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
 
 
     # consonant characters

data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:uzb
   source_script: Cyrl
   destination_script: Latn
-  name: BGN/PCGN Romanization System -- Uzbek Cyrillic (1979)
+  name: Romanization of Uzbek Cyrillic (1979)
   url: http://transliteration.eki.ee/pdf/Uzbek.pdf
   creation_date: 1979
 
@@ -30,7 +30,7 @@ tests {
 }
 
 aliases {
-  
+
 def_alias uzbek_upper, any("\u0410\u0411\u0412\u0413\u0492\u0414\u0415\u0401\u0416\u0417\u0418\u0419\u041A\u049A\u041B\u041C\u041D\u041E\u041F\u0420\u0421\u0422\u0423\u040E\u0424\u04B2\u0426\u0427\u0428\u042a\u042c\u042D\u042E\u042F")
 
 }
@@ -55,7 +55,7 @@ stage {
     sub "\u0401", "Yo" # Ё
     sub "\u0401", "YO", after: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ё
     sub "\u0401", "YO", before: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ё
-    
+
     sub "\u0416", "Zh" # Ж
     sub "\u0416", "ZH", after: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ж
     sub "\u0416", "ZH", before: any("АБВГҒДЕЁЖЗИЙКҚЛМНОПРСТУЎФҲЦЧШЪЬЭЮЯ") # Ж

data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:uzb
   source_script: Cyrl
   destination_script: Latn
-  name: TABLE OF CORRESPONDENCES CYRILLIC - ROMAN BGN/PCGN 2000 Agreement
+  name: Table of Correspondences for Uzbek (Cyrillic-Roman) (2000 Agreement)
   description: |
     In 1995, the Uzbek government adopted the Roman alphabet to replace the existing Cyrillic alphabet.
     The presentation below provides a table of correspondences between the former Cyrillic alphabet and the

data/maps/bgnpcgn-zho-Hans-Latn-1979.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:zho
   source_script: Hans
   destination_script: Latn
-  name: ROMANIZATION OF CHINESE -- BGN/PCGN 1979 AGREEMENT
+  name: Romanization of Chinese (1979 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693689/ROMANIZATION_OF_CHINESE.pdf
   creation_date: 1979
   confirmation_date: 2017-12

data/maps/bis-asm-Beng-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:asm
   source_script: Beng
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Assamese Romanization
+  name: Indian script code for information interchange (ISCII) -- Assamese Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-ben-Beng-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Bengali Romanization
+  name: Indian script code for information interchange (ISCII) -- Bengali Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-dev-Deva-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:dev
   source_script: Deva
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Devanagri Romanization
+  name: Indian script code for information interchange (ISCII) -- Devanagri Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-guj-Gujr-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Gujrati Romanization
+  name: Indian script code for information interchange (ISCII) -- Gujrati Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-kan-Kana-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Kannada Romanization
+  name: Indian script code for information interchange (ISCII) -- Kannada Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-mlm-Mlym-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mlm
   source_script: Mlym
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Malayalam Romanization
+  name: Indian script code for information interchange (ISCII) -- Malayalam Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-ori-Orya-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ori
   source_script: Orya
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Oriya Romanization
+  name: Indian script code for information interchange (ISCII) -- Oriya Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-pnj-Guru-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pnj
   source_script: Guru
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Panjabi(Gurmukhi) Romanization
+  name: Indian script code for information interchange (ISCII) -- Panjabi(Gurmukhi) Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-tel-Telu-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tel
   source_script: Telu
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Telegu Romanization
+  name: Indian script code for information interchange (ISCII) -- Telegu Romanization
 
   #url:
   creation_date: 1991

data/maps/bis-tml-Taml-Latn-13194-1991.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tml
   source_script: Taml
   destination_script: Latn
-  name: Indian script code for information interchange - ISCII - Tamil Romanization
+  name: Indian script code for information interchange (ISCII) -- Tamil Romanization
 
   #url:
   creation_date: 1991

data/maps/by-bel-Cyrl-Latn-2007.imp

@@ -4,19 +4,21 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: REGULATORY LEGAL ACTS OF THE NATIONAL BANK, NATIONAL ACADEMY OF SCIENCES OF BELARUS, MINISTRIES, OTHER REPUBLICAN GOVERNMENT BODIES 8/16668
+  name: Transliteration of geographical names of the Republic of Belarus in letters of the Latin alphabet (2007)
   url: http://www.pravo.by/pdf/2007-159/2007-159(027-028).pdf
   creation_date: 2007
   description: |
     RESOLUTION OF THE STATE COMMITTEE
     ON PROPERTY OF THE REPUBLIC OF BELARUS June 11, 2007 No. 38
 
-    8/16668 (06/18/2007) On amendments and additions to the Instructions
-    for the transliteration of geographical names of the
-    Republic of Belarus in letters of the Latin alphabet
+    Regulatory Legal Acts Of The National Bank, National Academy Of Sciences Of
+    Belarus, Ministries, Other Republican Government Bodies 8/16668 (06/18/2007)
+    On amendments and additions to the Instructions for the transliteration of
+    geographical names of the Republic of Belarus in letters of the Latin
+    alphabet
 
     Based on the Regulation on the State Property Committee of the Republic of Belarus,
-    approved by the Decree of the Council of Ministers of the Republic of Belarusdated July 29, 2006
+    approved by the Decree of the Council of Ministers of the Republic of Belarus dated July 29, 2006
     No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
 }
 

data/maps/din-hin-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Hindi"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Hindi"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-kat-Geor-Latn-32707-2010.imp

@@ -9,8 +9,8 @@ metadata {
   creation_date: 2010
   confirmation_date: 2010
   description: |
-    Information and documentation - Romanization of the Georgian alphabet.
-  
+    Information and documentation -- Romanization of the Georgian alphabet.
+
   notes:
 }
 
@@ -53,27 +53,27 @@ stage {
     sub "\u10d4", "e" # ე
     sub "\u10d5", "v" # ვ
     sub "\u10d6", "z" # ზ
-    
+
     sub "\u10f1", "ê" # ჱ
-    
+
     sub "\u10d7", "t̕" # 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", "p̕" # ფ
     sub "\u10e5", "k̕" # ქ
@@ -86,14 +86,14 @@ stage {
     sub "\u10ec", "c" # წ
     sub "\u10ed", "č" # ჭ
     sub "\u10ee", "x" # ხ
-    
+
     sub "\u10f4", "q̕" # ჴ
-    
+
     sub "\u10ef", "ǰ" # ჯ
     sub "\u10f0", "h" # ჰ
-    
+
     sub "\u10f5", "ô" # ჵ
-    
+
     sub "\u10f6", "f" # ჶ
     sub "\u10f7", "ẹ" # ჷ
     sub "\u10f8", "ʼ" # ჸ

data/maps/din-mar-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mar
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Marathi"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Marathi"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-nep-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Nepali"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Nepali"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-pli-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pli
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Pali"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Pali"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-pra-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:pra
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Prakit"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Prakit"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/din-san-Deva-Latn-33904-2018.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:san
   source_script: Deva
   destination_script: Latn
-  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Sanskrit"
+  name: "DIN 33904:2018-10 Information and documentation -- Romanization Devanagari, Sanskrit"
   url: https://www.beuth.de/en/standard/din-33904/293049024
   creation_date: 2018
   description: |

data/maps/dos-nep-Deva-Latn-1997.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: bgnpcgn
+  authority_id: dos
   id: 1997
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: Nepali Romanization, 1997
+  name: Survey Department Nepali Romanization System (1997)
   url: http://nationalgeoportal.gov.np/old/pdf/translation2.pdf
   creation_date: 1997
   description: |

data/maps/elot-ell-Grek-Latn-743-1982-tl.imp

@@ -4,12 +4,11 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: ELOT 743:1982 (transliteration)
+  name: ELOT 743:1982 Information and documentation -- Conversion of Greek characters into Latin characters (transliteration system)
   url:
   creation_date: 1982
   description: |
     ELOT 743:1982 transliteration table for Greek
-
   notes:
     - This was the intended system in ELOT 743:1982 for transliteration, as is apparent from un-ell-Grek-Latn-1987-tl and iso-ell-Grek-Latn-843-1997-t2, and ELOT 743:2001, Annex B; but the reversible character diacritics are missing from the currently available document, and the document does not indicate what there was supposed to be.
     - "\"Transliteration\" as used in this specification and its inheritors refers to reversible transliteration, as distinct from \"transcription\", which is a simpler transliteration and which is intended for default use."

data/maps/elot-ell-Grek-Latn-743-1982-ts.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: ELOT 743:1982
+  name: ELOT 743:1982 Information and documentation -- Conversion of Greek characters into Latin characters (transcription system)
   url:
   creation_date: 1982
   description: |

data/maps/elot-ell-Grek-Latn-743-2001-tl.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: ELOT 743:2001
+  name: ELOT 743:2001 Information and documentation -- Conversion of Greek characters into Latin characters (transliteration system)
   url: https://docplayer.gr/docview/18/849832/
   #file=/storage/18/849832/849832.pdf
   creation_date: 2001

data/maps/elot-ell-Grek-Latn-743-2001-ts.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: ELOT 743:2001
+  name: ELOT 743:2001 Information and documentation -- Conversion of Greek characters into Latin characters (transcription system)
   url: https://docplayer.gr/docview/18/849832/
   #file=/storage/18/849832/849832.pdf
   creation_date: 2001

data/maps/ggg-kat-Geor-Latn-2002.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: Georgian State Department of Geodesy and Cartography 2002 System
+  name: Georgian State Department of Geodesy and Cartography Romanization System (2002)
   url: https://transliteration.eki.ee/pdf/Georgian.pdf
   creation_date: 1998
   confirmation_date: 2002
@@ -12,10 +12,10 @@ metadata {
     The national system of romanization adopted in February 2002 by the State
     Department of Geodesy and Cartography of Georgia and the Institute
     of Linguistics, Georgian Academy of Sciences.
-  
+
   notes:
     - Georgian script refers in this document to the Mkhedruli alphabet.
-  
+
     - There is no case in Georgian.
 }