interscript-maps 2.1.0 → 2.3.1a

data/maps/bgnpcgn-ell-Grek-Latn-1962.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: BGN/PCGN 1962 System
+  name: Romanization of Greek (1962)
   url: https://github.com/riboseinc/interscript/files/4225556/BGN_Romanization_Guide_1962_greek.pdf
   creation_date: 1962
   description: |

data/maps/bgnpcgn-ell-Grek-Latn-1996.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: BGN/PCGN 1996 System
+  name: Romanization of Greek (1996)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693694/ROMANIZATION_OF_GREEK.pdf
   creation_date: 1996
   description: |

data/maps/bgnpcgn-fao-Latn-Latn-1964.imp

@@ -4,12 +4,13 @@ metadata {
   language: iso-639-2:far
   source_script: Latn
   destination_script: Latn
-  name: https://github.com/interscript/interscript/files/5180777/BGN_Romanization_Guide_1964_faeroese.pdf
+  name: Romanization of Faeroese (1964)
+  url: https://github.com/interscript/interscript/files/5180777/BGN_Romanization_Guide_1964_faeroese.pdf
   creation_date: 1964
   description: |
-    The Faeroese language is a dialect of Icelandic and, like Icelandic, employes the letter eth (Ð ð).
+    The Faeroese language is a dialect of Icelandic and, like Icelandic, employs the letter eth (Ð ð).
     Unlike Icelandic, however, the Faeroese ð has the sound of y (as in "yes") before i, v before u, and is silent in all other cases.
-    The Icelandic letter thorn (Þ þ) does not occur in the writting of Faeroese.
+    The Icelandic letter thorn (Þ þ) does not occur in the writing of Faeroese.
 
     To avoid the use of the unfamiliar symbol ð, the Board transliterates it as dh, as in Icelandic,
     even though its pronunciation in the two languages is not the same.

data/maps/bgnpcgn-fao-Latn-Latn-1968.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:fao
   source_script: Latn
   destination_script: Latn
-  name: BGN/PCGN Faroese 1968 Roman-Script Spelling Convention Agreement
+  name: Roman-Script Spelling Convention of Faroese (1968 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
   creation_date: 1968
 

data/maps/bgnpcgn-fas-Arab-Latn-1956.imp

@@ -8,7 +8,7 @@ metadata {
   language: iso-639-2:fas
   source_script: Arab
   destination_script: Latn
-  name: BGN/PCGN 1956 System
+  name: Romanization of Arabic (1956)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/320079/Arabic_Romanization.pdf
   creation_date: 1947
   confirmation_date: 2019-06

data/maps/bgnpcgn-isl-Latn-Latn-1964.imp

@@ -4,14 +4,14 @@ metadata {
   language: iso-639-2:isl
   source_script: Latn
   destination_script: Latn
-  name: TRANSLITERATION OF ICELANDIC BGN/PCGN 1947 System
+  name: Transliteration of Icelandic (1947)
   url: https://github.com/interscript/interscript/files/5180785/BGN_Romanization_Guide_1964_icelandic_1947.pdf
   creation_date: 1964
   description: |
     The BGN and the PCGn in 1947 jointly agreed to the transliteration of two letters of the Icelandic alphabet which,
     although used in writing Old English, have disappeared from the modern English alphabet.
 
-    The transliterated letters are the edh (Ð ð) and the thorn (Þ þ), pronounved as th in "thus" and th in "think," respectively.
+    The transliterated letters are the edh (Ð ð) and the thorn (Þ þ), pronounced as th in "thus" and th in "think," respectively.
 
     It was felt that it was better to transliterate these letters into familiar symbols than preserve such unfamiliar letters in the nomenclature.
 

data/maps/bgnpcgn-isl-Latn-Latn-1968.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:isl
   source_script: Latn
   destination_script: Latn
-  name: BGN/PCGN Icelandic 1968 Roman-Script Spelling Convention Agreement
+  name: Roman-Script Spelling Convention of Icelandic (1968 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
   creation_date: 1968
 

data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: Japanese Kana Modified Hepburn 1930 System
+  name: Romanization of Japanese -- Kana Modified Hepburn (1930)
   url:
   creation_date:
   adoption_date:

data/maps/bgnpcgn-kat-Geor-Latn-1981.imp

@@ -4,13 +4,13 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: ROMANIZATION OF GEORGIAN; BGN/PCGN 1981 System
+  name: Romanization of Georgian (1981)
   url: https://transliteration.eki.ee/pdf/Georgian.pdf
   creation_date: 1981
   confirmation_date: 1981
   description: |
     BGN/PCGN system of 1981.
-  
+
   notes:
 }
 
@@ -75,18 +75,18 @@ stage {
     sub "\u10d4", "e" # ე
     sub "\u10d5", "v" # ვ
     sub "\u10d6", "z" # ზ
-    
+
     sub "\u10f1", "ey" # ჱ
-    
+
     sub "\u10d7", "t’" # თ
     sub "\u10d8", "i" # ი
     sub "\u10d9", "k’" # კ
     sub "\u10da", "l" # ლ
     sub "\u10db", "m" # მ
     sub "\u10dc", "n" # ნ
-    
+
     sub "\u10f2", "j" # ჲ
-    
+
     sub "\u10dd", "o" # ო
     sub "\u10de", "p" # პ
     sub "\u10df", "zh" # ჟ
@@ -105,9 +105,9 @@ stage {
     sub "\u10ec", "ts" # წ
     sub "\u10ed", "ch" # ჭ
     sub "\u10ee", "kh" # ხ
-    
+
     sub "\u10f4", "q’" # ჴ
-    
+
     sub "\u10ef", "j" # ჯ
     sub "\u10f0", "h" # ჰ
   }

data/maps/bgnpcgn-kat-Geor-Latn-2009.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: ROMANIZATION OF GEORGIAN; Georgia 2011 national system; BGN/PCGN 2009 Agreement
+  name: Romanization of Georgian (2009 Agreement, Georgia 2011 national system)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/810202/ROMANIZATION_OF_GEORGIAN.pdf
   creation_date: 2009
   confirmation_date: 2011
@@ -16,7 +16,7 @@ metadata {
     the Mkhedruli alphabet, as presently used in Georgia. This system was
     adopted by BGN and PCGN in 2009, superseding the BGN/PCGN system of
     1981.
-  
+
   notes:
     - This system denotes ejective (glottalised) consonants by means of
       an apostrophe. The BGN/PCGN 1981 system instead used the apostrophe to

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

@@ -1,18 +1,18 @@
 metadata {
-  
+
   authority_id: bgnpcgn
   id: 1979
   language: iso-639-2:kaz
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Kazakh
+  name: Romanization of Kazakh (1979)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811511/ROMANIZATION_OF_KAZAKH.pdf
   creation_date: 1979
   confirmation_date: 2019
   description: |
     The BGN/PCGN system for Kazakh was designed for use in romanizing names written in the Kazakh Cyrillic alphabet.
     The Kazakh Cyrillic alphabet contains nine characters not present in the Russian alphabet: ә, ғ, қ, ң, ө, ұ, ү, һ and і.
-  
+
   notes:
     - The character sequences гһ, зһ, кһ, нг, сһ and цһ may be romanized g·h, z·h, k·h, n·g, s·h
       and ts·h in order to differentiate those romanizations from from the digraphs gh, zh, kh, ng, sh,
@@ -144,7 +144,7 @@ stage {
     sub "\u042D", "Ė" # Э
     sub "\u042E", "Yu" # Ю
     sub "\u042F", "Ya" # Я
-    
+
     sub "\u0430", "a" # а
     sub "\u04D9", "ä" # ә
     sub "\u0431", "b" # б

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kir
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Kyrgyz
+  name: Romanization of Kyrgyz (1979)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816663/ROMANIZATION_OF_KYRGYZ.pdf
   creation_date: 1979
   confirmation_date: 2019
@@ -12,7 +12,7 @@ metadata {
     The BGN/PCGN system for Kyrgyz Cyrillic was designed for use in romanizing names written
     in the Kyrgyz Cyrillic alphabet. The Kyrgyz Cyrillic alphabet contains three characters not present in
     the Russian alphabet: Ң , Ө, and Y.
-  
+
   notes:
     - Both Kyrgyz and Kirghiz may frequently be seen as the language name; both these spellings are used in the
       ISO 639 Standard on the representation of names for languages.
@@ -127,7 +127,7 @@ stage {
     sub "\u042D", "E" # Э
     sub "\u042E", "Yu" # Ю
     sub "\u042F", "Ya" # Я
-    
+
     sub "\u0430", "a" # а
     sub "\u0431", "b" # б
     sub "\u0432", "v" # в

data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: BGN/PCGN 1945 Agreement
+  name: Romanization of Korean for DPRK (Hangul-Latin) (1945 Agreement)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693725/ROMANIZATION_OF_KOREAN-_MR_for_DPRK.pdf
   creation_date: 1945
   adoption_date:

data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.imp

@@ -4,14 +4,14 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
-  url:
-  creation_date:
-  adoption_date:
+  name: Romanization of Korean for ROK (Hangul-Latin) (2011 Agreement, MOCT System 2000)
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693724/ROMANIZATION_OF_KOREAN-__MOCT_for_ROK.pdf
+  creation_date: 2011
+  adoption_date: 2011
   description:
 
   notes:
-    BGN/PCGN 2011 Agreement
+  - BGN/PCGN 2011 Agreement
 }
 
 tests {

data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.imp

@@ -4,16 +4,16 @@ metadata {
   language: iso-639-2:kor
   source_script: Kore
   destination_script: Latn
-  name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
-  url: ""
-  creation_date: ""
-  adoption_date: ""
+  name: Romanization of Korean for ROK (Korean-Latin) (2011 Agreement, MOCT System 2000)
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693724/ROMANIZATION_OF_KOREAN-__MOCT_for_ROK.pdf
+  creation_date: 2011
+  adoption_date: 2011
   description: |
     Establishes a system for the transliteration of the characters of Korean script into Latin characters.
     Intended to provide a means for international communication of written documents.
 
   notes:
-    - BGN/PCGN 2011 Agreement
+  - BGN/PCGN 2011 Agreement
 }
 
 tests {

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

@@ -4,7 +4,7 @@ metadata {
   language: kur
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF KURDISH -- BGN/PCGN 2007
+  name: Romanization of Kurdish (2007)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693727/ROMANIZATION_OF_KURDISH.pdf
   creation_date: 2007
   confirmation_date: 2017-12

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.imp

@@ -4,10 +4,10 @@ metadata {
   language: iso-639-2:mkd
   source_script: Cyrl
   destination_script: Latn
-  name: Makedonian Romanization, BGN/PCGN 1981 System
+  name: Romanization for Macedonian (1981)
   url: https://github.com/riboseinc/interscript/files/4247920/USBGN_romanization_Macedonian_1981.pdf
   creation_date: 1981
-  description: BGN/PCGN Romanization table for Makedonian.
+  description: BGN/PCGN Romanization table for Macedonian.
 
   notes:
     - The character ѓ should be romanized g when it occurs before е and и. In other

data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mkd
   source_script: Cyrl
   destination_script: Latn
-  name: Makedonian Romanization, BGN/PCGN 2013 System
+  name: Romanization for Macedonian (2013)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811514/ROMANIZATION_OF_MACEDONIAN.pdf
   creation_date: 2013
   description: |

data/maps/bgnpcgn-mon-Cyrl-Latn-1964.imp

@@ -4,10 +4,10 @@ metadata {
   language: iso-639-2:mon
   source_script: Cyrl
   destination_script: Latn
-  name: BGN/PCGN 1964 System
+  name: Romanization of Mongolian (1964)
   url: https://github.com/interscript/interscript/files/5180767/BGN_Romanization_Guide_1964_mongolian_1964.pdf
-  creation_date:
-  confirmation_date:
+  creation_date: 1964
+  confirmation_date: 1964
   description: |
     This system was originated by the PCGN in 1957 and adopted as a
     BGN/PCGN System in 1964. It is intended for use in the romanization of

data/maps/bgnpcgn-nep-Deva-Latn-2011.imp

@@ -1,14 +1,14 @@
 metadata {
   authority_id: bgnpcgn
-  id: 2020
+  id: 2011
   language: iso-639-2:nep
   source_script: Deva
   destination_script: Latn
-  name: Nepali Romanization, 2020
+  name: Romanization for Nepali (2011 Agreement)
   url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20NEPALI.pdf
-  creation_date: 1964
+  creation_date: 2011
+  confirmation_date: 2017
   description: |
-    BGN/PCGN 2011 Agreement Romanization of Nepali
     The BGN and the PCGN have adopted the Nepal Survey Department (NSD) system for the
     romanization of Nepali names.  This system, below, should be applied to Nepali names for which Roman‐
     script spellings in materials produced by the government of Nepal are not available.

data/maps/bgnpcgn-per-Arab-Latn-1958.imp

@@ -1,14 +1,14 @@
 metadata {
   authority_id: bgnpcgn
-  id: 2007
+  id: 1958
   language: iso-639-3:prs
   # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
   source_script: Arab
   destination_script: Latn
-  name: TRANSLITERATION SYSTEM FOR PERSIAN BGN/PCGN 1958 System
+  name: Transliteration System for Persian (1958)
   url: https://github.com/interscript/interscript/files/5180821/BGN_Romanization_Guide_1964_persian_1958.pdf
   creation_date: 1958
-  confirmation_date: 2017-11
+  confirmation_date: 1958
   description: |
     The BGN/PCGN 1958 System for the Persian alphabet was
     adopted by the BGN in 1946 and by the PCGN In 1958. It Is
@@ -30,11 +30,11 @@ metadata {
     Arabic in that the short vowel symbols necessary for the
     proper rendering of short vowels, long vowels, and
     diphthongs are almost always omitted from written Persian.
-    It follows that, in order to produce transliter- tions in
+    It follows that, in order to produce transliterations in
     terms of standard written Persian, the transliterator must
     be able to identify the words used in names and must know
     their standard written Persian spelling, their proper vowel
-    pointing, and how to eliminate pecularities due to
+    pointing, and how to eliminate peculiarities due to
     dialectical variation.
     The notes and special rules explain details of
     transliteration not stated in the tables.
@@ -240,20 +240,20 @@ 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
 
 
     sub "\u0621", "’" # ء

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

@@ -5,7 +5,7 @@ metadata {
   # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
   source_script: Arab
   destination_script: Latn
-  name: BGN/PCGN NATIONAL ROMANIZATION SYSTEM FOR AFGHANISTAN -- BGN/PCGN 2007 System
+  name: National Romanization System for Afghanistan (2007)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693661/ROMANIZATION_FOR_AFGHANISTAN.pdf
   creation_date: 2007
   confirmation_date: 2017-11
@@ -461,20 +461,20 @@ 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