interscript-maps 2.1.0 → 2.3.1

data/maps/iso-tel-Telu-Latn-15919-2001.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tel
   source_script: Telu
   destination_script: Latn
-  name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+  name: "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Telugu)"
   url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
   creation_date: 2001
   adoption_date: 2001

data/maps/lshk-yue-Hani-Latn-jyutping-1993.imp

@@ -4,11 +4,11 @@ metadata {
   language: iso-639-3:yue
   source_script: Hani
   destination_script: Latn
-  name: LSHK Jyutping
+  name: Jyutping Cantonese Romanisation Scheme
   url: https://lshk.org/jyutping
   creation_date: 1993-12
   description:
-    - The Linguistic Society of Hong Kong Cantonese Romanization Scheme, or
+    - The Linguistic Society of Hong Kong Cantonese Romanisation Scheme, or
       known as Jyutping, was designed and proposed by the Linguistic Society of
       Hong Kong in 1993. Jyutping is a new Cantonese romanization system which
       has many advantages. It is multifunctional, systematic, user-friendly,
@@ -16,12 +16,12 @@ metadata {
       alphanumeric characters without any diacritics and strange symbols.
       Jyutping can also be used as a Chinese computer input method. Its basic
       principles are simple, easy to learn, and professional.
-  
+
   notes:
     - One may need to parse the text in order to generate accurate
       transliteration.
-  
-  
+
+
   #A longer test list will be generated from GeoNames database
 }
 

data/maps/mext-jpn-Hrkt-Latn-1954.imp

@@ -4,7 +4,8 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: 内閣告示第一号 -- ローマ字のつづり方
+  name: Japanese Cabinet Romanisation of Japanese
+  # name: 内閣告示第一号 -- ローマ字のつづり方
   url: http://www.mext.go.jp/b_menu/hakusho/nc/k19541209001/k19541209001.html
   creation_date: 1954
   adoption_date: 1954-12-09

data/maps/moct-kor-Hang-Latn-2000.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Korean Ministry of Culture and Tourism 2000 System
+  name: Ministry of Culture and Tourism Korean Romanization System (2000)
   url: https://www.korean.go.kr/front_eng/roman/roman_01.do
   creation_date: 2000
   adoption_date: 2002

data/maps/mofa-jpn-Hrkt-Latn-1989.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: Hepburn Romanization, Ministry of Foreign Affairs of Japan
+  name: Ministry of Foreign Affairs of Japan Hepburn Romanization
   url: https://www.ezairyu.mofa.go.jp/passport/hebon.html
   creation_date:
   adoption_date:

data/maps/mv-div-Thaa-Latn-1987.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:div
   source_script: Thaa
   destination_script: Latn
-  name: Maldivian (Divehi) Maldivian Government 1987 system
+  name: Maldivian (Divehi) Romanization system (1987)
   url: https://www.eki.ee/wgrs/rom2_dv.htm
   creation_date: 1887
   description: |

data/maps/mvd-bel-Cyrl-Latn-2008.imp

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: About approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
-  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  name: Transliteration system for Belarusian names in the population register (2008)
+  url:
   creation_date: 2008
 
   description: |
@@ -127,9 +127,9 @@ stage {
     sub "\u0412", "V" # B
     sub "\u0413", "G" # Г
     sub "\u0414", "D" # Д
-    sub "\u0415", "Ie" # Е or JE TODO add rule   
-    sub "\u0415", "IE", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule 
-    sub "\u0415", "IE", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule 
+    sub "\u0415", "Ie" # Е or JE TODO add rule
+    sub "\u0415", "IE", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
+    sub "\u0415", "IE", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Е or JE TODO add rule
     sub "\u0401", "Io" # Ё or JO TODO add rule
     sub "\u0401", "IO", after: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Ё or JO TODO add rule
     sub "\u0401", "IO", before: any("АБВГДЕЁЖЗІЙКЛМНОПРСТУU040EФХЦЧШЩЫЭЮЯ") # Ё or JO TODO add rule

data/maps/mvd-bel-Cyrl-Latn-2010.imp

@@ -4,17 +4,14 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: |
-    8/22721 About approval of the Instructions on the organization of work of units of citizenship
-    and migration of internal affairs bodies on the issuance, registration, exchange,
-    invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+  name: Transliteration system for Belarusian names (2010)
   url: https://pravo.by/document/?guid=3871&p0=W21022721
   creation_date: 2010
 
   description: |
     RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
     June 28, 2010 No. 200
-    On approval of the Instructions on the organization of work of units of citizenship
+    8/22721 About approval of the Instructions on the organization of work of units of citizenship
     and migration of internal affairs bodies on the issuance, registration, exchange,
     invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 

data/maps/mvd-rus-Cyrl-Latn-2008.imp

@@ -4,10 +4,11 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: 8/19678 On approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
-  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  name: Transliteration system for Russian names in the population register (2008)
+  url:
   creation_date: 2008
-
+  description: |
+    8/19678 On approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
   notes:
     - check notes from mvd-bel-Cyrl-Latn-2008
 }

data/maps/mvd-rus-Cyrl-Latn-2010.imp

@@ -4,17 +4,14 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: |
-    8/22721 On approval of the Instructions on the organization of work of units of citizenship
-    and migration of internal affairs bodies on the issuance, registration, exchange,
-    invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+  name: Transliteration system for Russian names (2010)
   url: https://pravo.by/document/?guid=3871&p0=W21022721
   creation_date: 2010
 
   description: |
     RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
     June 28, 2010 No. 200
-    On approval of the Instructions on the organization of work of units of citizenship
+    8/22721 On approval of the Instructions on the organization of work of units of citizenship
     and migration of internal affairs bodies on the issuance, registration, exchange,
     invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 

data/maps/odni-ara-Arab-Latn-2004.imp

@@ -4,8 +4,7 @@ metadata {
   language: ics-630-01:ara
   source_script: Arab
   destination_script: Latn
-  name: Arabic Personal Names Office of the Director Of National Intelligence 2004 System
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Arabic_IC_Standard.doc
+  name: Intelligence Community (IC) Standard for the Transliteration of Arabic Personal Names (2004)
   creation_date: 2004
   confirmation_date: 2004-06
   description:

data/maps/odni-ara-Arab-Latn-2015.imp

@@ -4,8 +4,8 @@ metadata {
   language: ics-630-01:ara
   source_script: Arab
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Arabic Personal Names 2015 System
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20A%20-%20Arabic_Personal_Names_FLTS%20(U).pdf
+  name: ICS-630-01 Romanization of Arabic Personal Names (2015)
+  source: ICS-630-01 Annex A
   creation_date: 2017
   confirmation_date: 2018-06
   description: |

data/maps/odni-aze-Cyrl-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:aze
   source_script: Cyrl
   destination_script: Latn
-  name: Standards for the transliteration of azeri personal names in written reports and products
+  name: ICS-630-01 Romanization of Azeri Personal Names (2015)
   source: ICS-630-01 Annex P
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-bel-Cyrl-Latn-2015.imp

@@ -4,10 +4,8 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Belarusian Personal Names 2015, ICS 630-01 Annex B
-
-  # url:
-  source: ICS 630-01, Annex B
+  name: ICS-630-01 Romanization of Belarusian Personal Names (2015)
+  source: ICS 630-01 Annex B
   creation_date: 2015
   confirmation_date: 2015
   description: |

data/maps/odni-bul-Cyrl-Latn-2005.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Intelligence Community (IC) Standard for the Transliteration of Bulgarian Personal Names
+  name: Intelligence Community (IC) Standard for the Transliteration of Bulgarian Personal Names (2005)
   creation_date: 2005
   description:
 }
@@ -53,7 +53,7 @@ stage {
     sub "\u042c", "Y"
     sub "\u042e", "Yu"
     sub "\u042f", "Ya"
-    
+
     sub "\u0430", "a"
     sub "\u0431", "b"
     sub "\u0432", "v"

data/maps/odni-bul-Cyrl-Latn-2015.imp

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Bulgarian Personal Names 2015, ICS-630-01 Annex O
-
-  # url:
+  name: ICS-630-01 Romanization of Bulgarian Personal Names (2015)
   source: ICS-630-01 Annex O
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-che-Cyrl-Latn-2015.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:che
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence -- ICS 630-01 -- Chechen Cyrillic 2015
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20C%20-%20Chechen_Personal_Names_FLTS%20(U).pdf
+  name: ICS-630-01 Romanization of Chechen Cyrillic Personal Names (2015)
   source: ICS-630-01 Annex C
   creation_date: 2015
   confirmation_date: 2015

data/maps/odni-fas-Arab-Latn-2004.imp

@@ -5,7 +5,6 @@ metadata {
   source_script: Arab
   destination_script: Latn
   name: Intelligence Community (IC) Standard for the Transliteration of Farsi (Persian) Personal Names (2004)
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Farsi_(Persian)_%26_Dari_IC_Standards.doc
   creation_date: 2004
   confirmation_date: 2004-11
   description: |
@@ -140,20 +139,20 @@ stage {
     # '\uFE8E' : ''  # ﺎ
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "at t" # الت
-    sub boundary + "\u0627\u0644\u062b", "as s" # الث
-    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630", "az z" # 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", "as s" # الص
-    sub boundary + "\u0627\u0644\u0636", "az z" # الض
-    sub boundary + "\u0627\u0644\u0637", "at t" # الط
-    sub boundary + "\u0627\u0644\u0638", "az z" # 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"), "as s" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az z" # 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"), "as s" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "az z" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "at t" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az z" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
 
     # Farsi Vowel (Pointing)
     sub "\u0622", "a" # آ alef maddeh

data/maps/odni-fas-Arab-Latn-2015.imp

@@ -4,10 +4,10 @@ metadata {
   language: iso-639-2:fas
   source_script: Arab
   destination_script: Latn
-  name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
-  url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+  name: ICS-630-01 Romanization of Persian Farsi Dari Personal Names (2015)
+  source: ICS-630-01 Annex J
   creation_date: 2015
-  confirmation_date: 2015-11
+  confirmation_date: 2018-11
   description: |
     This system is the Intelligence Community (IC) standard for
     the transliteration of Persian (Farsi)
@@ -257,20 +257,20 @@ stage {
     # '\uFE8E' : ''  # ﺎ
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "at t" # الت
-    sub boundary + "\u0627\u0644\u062b", "as s" # الث
-    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630", "az z" # 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", "as s" # الص
-    sub boundary + "\u0627\u0644\u0636", "az z" # الض
-    sub boundary + "\u0627\u0644\u0637", "at t" # الط
-    sub boundary + "\u0627\u0644\u0638", "az z" # 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"), "as s" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "az z" # 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"), "as s" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "az z" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "at t" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az z" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
 
     # Farsi Vowel (Pointing)
     sub "\u0622", "a" # آ alef maddeh

data/maps/odni-hin-Deva-Latn-2004.imp

@@ -4,12 +4,11 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: IC STANDARDS FOR TRANSLITERATION OF HINDI AND URDU PERSONAL NAMES
-  url: https://github.com/interscript/interscript-private-references/blob/master/odni/Hindi_and_Urdu_IC_Standard.doc
+  name: Intelligence Community (IC) Standard for the Transliteration of Hindi and Urdu Personal Names (2004)
   creation_date: 2004
   description: |
     IC STANDARDS FOR TRANSLITERATION OF HINDI AND URDU PERSONAL NAMES
-  
+
   notes:
     - |
       Long/Short Vowels: Long and short vowels are not distinguished in the system:
@@ -69,7 +68,7 @@ stage {
 
   # CHARACTERS
   parallel {
-    
+
     #Independent vowel characters
     sub "अ", "a"
     sub "आ", "a"
@@ -84,7 +83,7 @@ stage {
     sub "ओ", "o"
     sub "ऑ", "au"
     sub "औ", "au"
-    
+
     #Dependent Vowels
     sub "ा", "a"
     sub "ि", "i"
@@ -98,10 +97,10 @@ stage {
     sub "ो", "o"
     sub "ौ", "au"
     sub "ॉ", "au"
-    
-    
+
+
     # Consonants
-    
+
     # Gutturals
     sub "क", "k"
     sub "क्ष", "ksha"
@@ -112,7 +111,7 @@ stage {
     sub "ग़", "gh"
     sub "घ", "gh"
     sub "ङ", "n"
-    
+
     # Palatals
     sub "च", "ch"
     sub "छ", "ch"
@@ -121,7 +120,7 @@ stage {
     sub "झ", "gya"
     sub "झ", "jh"
     sub "ञ", "n"
-    
+
     # Cerebrals
     sub "ट", "t"
     sub "ठ", "th"
@@ -130,14 +129,14 @@ stage {
     sub "ढ़", "rh"
     sub "ढ", "dh"
     sub "ण", "n"
-    
+
     # Dentals
     sub "त", "t"
     sub "थ", "th"
     sub "द", "d"
     sub "ध", "dh"
     sub "न", "n"
-    
+
     # Labials
     sub "प", "p"
     sub "फ़", "f"
@@ -145,34 +144,34 @@ stage {
     sub "ब", "b"
     sub "भ", "bh"
     sub "म", "m"
-    
+
     # Semivowels
     sub "य", "y"
     sub "र", "r"
     sub "ल", "l"
     sub "व", "v"
-    
+
     # Sibilants
     sub "श", "sh"
     sub "ष", "sh"
     sub "स", "s"
-    
-    
+
+
     # Aspirate
     sub "ह", "h"
-    
+
     # Anusvāra
     sub "ं", "n"
-    
+
     # Anunāsika
     sub "ँ", "n"
-    
+
     # halanta
     sub "्", ""
-    
+
     # bisharga
     sub "ः", "h"
-    
+
     sub "़", ""
   }