interscript-maps 2.1.0rc4 → 2.1.0

data/maps/apcbg-bul-Cyrl-Latn-1995.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Toponymic Guidelines for Antarctica (1995)
+  name: Toponymic Guidelines for Antarctica, Lyubomir Ivanov. Antarctic Place-names Commission of Bulgaria, Sofia, 1995.
   url: http://www.apcbg.org/Toponymic-Guidelines.htm
   creation_date: 1995
   description: |
@@ -13,9 +13,6 @@ metadata {
     international scientific research.  They facilitate information exchange in the field, in scientific publications and in
     administrative measures under the Antarctic Treaty System. Geographical names also reflect the history of Antarctic
     exploration.
-
-    Toponymic Guidelines for Antarctica, Lyubomir Ivanov. Antarctic Place-names
-    Commission of Bulgaria, Sofia, 1995.
 }
 
 tests {
@@ -152,7 +149,7 @@ stage {
     sub "\u042c", "Y"
     sub "\u042e", "Yu"
     sub "\u042f", "Ya"
-
+    
     sub "\u0430", "a"
     sub "\u0431", "b"
     sub "\u0432", "v"
@@ -183,11 +180,11 @@ stage {
     sub "\u044c", "y"
     sub "\u044e", "yu"
     sub "\u044f", "ya"
-
+    
     # note 2
     sub "\u046A", "Ŭ" # Ѫ
     sub "\u046B", "ŭ" # ѫ
-
+    
     # note[3]
     sub "\u0462", "YE" # Ѣ
     sub "\u0463", "ye" # ѣ

data/maps/az-aze-Cyrl-Latn-1939.imp

@@ -6,7 +6,6 @@ metadata {
   destination_script: Latn
   url: https://omniglot.com/writing/azeri.htm
   creation_date: 1939
-  name: Azeri Romanization (1939)
   description: |
     In 1939 Joseph Stalin ordered the Cyrillic alphabet to be used by Azeri speakers in the Soviet Union.
 

data/maps/az-aze-Cyrl-Latn-1958.imp

@@ -6,7 +6,6 @@ metadata {
   destination_script: Latn
   url: https://omniglot.com/writing/azeri.htm
   creation_date: 1958
-  name: Azeri Romanization (1958)
   description: |
     In 1939 Joseph Stalin ordered the Cyrillic alphabet to be used by Azeri speakers in the Soviet Union.
 

data/maps/bas-rus-Cyrl-Latn-2017-bss.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Streamlined Romanization of Russian Cyrillic (Basic Streamlined System)
+  name: Streamlined Romanization of Russian Cyrillic -- Basic Streamlined System
   url: https://www.researchgate.net/publication/318402098
   creation_date: 2017-07
   description: |

data/maps/bas-rus-Cyrl-Latn-2017-oss.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Streamlined Romanization of Russian Cyrillic (Optimized Streamlined System)
+  name: Streamlined Romanization of Russian Cyrillic -- Optimized Streamlined System
   url: https://www.researchgate.net/publication/318402098
   creation_date: 2017-07
   description: |

data/maps/bgn-jpn-Hrkt-Latn-1962.imp

@@ -4,22 +4,22 @@ metadata {
   language: iso-639-2:jpn
   source_script: Hrkt
   destination_script: Latn
-  name: Japanese Modified Hepburn (1962)
+  name: BGN (Modified Hepburn) System
   url:
   creation_date: 1930
   adoption_date: 1962
   description: |
     The BGN (Modified Hepburn) System for the transliteration of Japanese
     has been in use by the Board on Geographic Names since about 1930 and
-    has been extensively employed in the systematic standardization of
-    thousands of geographic names of Japan in Romanized form.
+    has been extensively employed in the systematic standardsization of
+    thousands of geographic names of Japan in romanized form.
 
   notes: |
 
     1. The "tsu" forms (ツ/つ) are also used to indicate a double consonant and
-    are generally (but not always) written in smaller script or type
+    are generally (but not alwyas) written in smaller script or type
     slightly to the right of or below the regular line. These characters
-    are transliterated as k before k; s before s or sh; t before t, ts, or
+    are trasnliterated as k before k; s before s or sh; t before t, ts, or
     ch; and p before p. Occasionally, when a "ku" (ク/く) or "ki" (キ/き) form
     precedes k, the u in ku or the i in ki is dropped.
 

data/maps/bgn-kor-Hang-Latn-1943.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Korean McCune-Reischauer (Hangul to Latin) (1943 Agreement)
+  name: BGN Agreement -- Korean McCune-Reischauer System (1943)
   url:
   creation_date: 1943
   adoption_date:

data/maps/bgn-kor-Kore-Latn-1943.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Kore
   destination_script: Latn
-  name: Korean McCune-Reischauer (Korean to Latin) (1943 Agreement)
+  name: BGN Agreement -- Korean McCune-Reischauer System (1943)
   url:
   creation_date: 1943
   adoption_date:

data/maps/bgnpcgn-amh-Ethi-Latn-1967.imp

@@ -4,32 +4,32 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: Romanization of Amharic (1967)
+  name: BGN/PCGN Romanization System -- Amharic (1967)
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693663/ROMANIZATION_OF_AMHARIC.pdf
   creation_date: 1967
   description: |
     Amharic is the principal and official language of Ethiopia. The BGN/PCGN system for Amharic was designed for use in romanizing names written in the Amharic alphabet. The Roman letters and letter combinations shown as equivalents to the Amharic characters reflect modern Amharic pronunciation.
-
+  
   notes:
     - 1. The 6th-order characters should be romanized either with or without the letter i, depending on pronunciation.
-
+  
     - 2. For documentation purposes, the characters romanized with h in rows 1, 3, 13, and 18 may, instead, be romanized with h, ḥ, ḫ, and ẖ, respectively; the characters both romanized with s in rows 5 and 7 may, instead, be romanized with š and s, respectively; and the characters both romanized with ts’ in rows 30 and 31 may, instead, be romanized with ts’ and ts’, respectively.
-
+  
     - 3. When the character ና in row 14 is known to represent the Amharic word meaning ‘and’, its romanization (na) should always be separated from the preceding and following words by spaces and should never be capitalized, e.g., Raya na K’obo.
-
+  
     - 4. The vowel characters in row 16 should be romanized ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o in all other positions.
-
+  
     - 5. When the character የ in row 23 is known to represent the Amharic preposition, its romanization (Ye) should begin with an upper-case letter and written together with the following word, which should also begin with an upper-case letter, e.g., YeWiha Shet’.
-
+  
     - |
       6. An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:
-
+  
       All apostrophes appearing in romanization are U+2019, except as they appear in row 20, which are U+2018.
-
+  
       Ā (U+0100) ā (U+0101)
       Ī (U+012A) ī (U+012B)
       Ē (U+0112) ē (U+0113)
-
+  
     - 7.The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used.
 }
 
@@ -365,7 +365,7 @@ stage {
     sub "ቬ", "vē" # ቬ
     sub "ቭ", any(["v", "vi"]) # ቭ
     sub "ቮ", "vo" # ቮ
-
+    
     sub "፩", "1" # ፩
     sub "፪", "2" # ፪
     sub "፫", "3" # ፫

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: Romanization of Arabic (1956)
+  name: ROMANIZATION OF ARABIC -- BGN/PCGN 1956 System
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/858000/ROMANIZATION_OF_ARABIC.pdf
   creation_date: 1956
   confirmation_date: 2019-12

data/maps/bgnpcgn-arm-Armn-Latn-1981.imp

@@ -4,9 +4,9 @@ metadata {
   language: iso-639-2:arm
   source_script: Armn
   destination_script: Latn
-  name: Romanization of Armenian (1981)
+  name: BGN/PCGN 1981 System
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/810208/ROMANIZATION_OF_ARMENIAN.pdf
-  creation_date: 1981
+  creation_date: 2013
   confirmation_date: 2019-06
   description: |
     The BGN/PCGN system for Armenian was designed for use in romanizing

data/maps/bgnpcgn-aze-Cyrl-Latn-1993.imp

@@ -4,12 +4,12 @@ metadata {
   language: iso-639-2:aze
   source_script: Cyrl
   destination_script: Latn
-  name: Table of Correspondences for Azerbaijani (Cyrillic-Roman) (1993 Agreement)
+  name: AZERBAIJANI TABLE OF CORRESPONDENCES CYRILLIC-ROMAN -- BGN/PCGN 1993 Agreement
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816656/TABLE_OF_CORRESPONDENCES_FOR_AZERBAIJANI.pdf
   creation_date: 1993
   confirmation_date: 2019-06
   description: |
-      , also known as Azeri, is the official language of the Republic of Azerbaijan. In 1991, the Azerbaijani 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 current Roman alphabet. When Azerbaijani Roman-alphabet spellings are not available, this table can be used to convert Azerbaijani Cyrillic spellings.
+      Azerbaijani, also known as Azeri, is the official language of the Republic of Azerbaijan. In 1991, the Azerbaijani 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 current Roman alphabet. When Azerbaijani Roman-alphabet spellings are not available, this table can be used to convert Azerbaijani Cyrillic spellings.
 
   notes:
 

data/maps/bgnpcgn-bak-Cyrl-Latn-2007.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:rus
   source_script: Cyrl
   destination_script: Latn
-  name: Table of Correspondences for Bashkir (Cyrillic-Roman) (2007 Agreement)
+  name: BASHKIR TABLE OF CORRESPONDENCES CYRILLIC-ROMAN BGN/PCGN 2007 Agreement
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/829203/TABLE_OF_CORRESPONDENCES__FOR_BASHKIR.pdf
   creation_date: 2007
   confirmation_date: 2019

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Belarusian (1979)
+  name: United States Board on Geographic Names Foreign Names Committee Staff, 1994. Romanization Systems and Roman-Script Spelling Conventions, p. 23.
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811510/ROMANIZATION_OF_BELARUSIAN.pdf
   creation_date: 1979
   description: |
@@ -12,9 +12,6 @@ metadata {
     romanizing names written in the Belarusian Cyrillic alphabet. The Belarusian alphabet contains three
     characters not present in the Russian alphabet: і, ў, and ’.
 
-    United States Board on Geographic Names Foreign Names Committee Staff, 1994.
-    Romanization Systems and Roman-Script Spelling Conventions, p. 23.
-
   notes:
    - The character sequences зг, кг, сг, тс and цг and may be romanized z·h, k·h, s·h, t·s and ts·h in order to differentiate those romanizations from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render the characters ж, x, ш, ц, and the character sequence тш
    - All apostrophes appearing in romanization are Unicode encoding 2019.

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Bulgarian (1952)
+  name: ROMANIZATION SYSTEM FOR BULGARIAN BGN/PCGN of 1952
   url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
   creation_date: 1945
   confirmation_date: 1952
@@ -16,16 +16,10 @@ metadata {
     are applicable to sources predating the orthographic reform of 1945.
 
   notes:
-    - In modern Bulgarian orthography, the character ъ, does not occur in
-      word-final position. It should be omitted in romanization when found in
-      word-final position on older sources
+    - In modern Bulgarian orthography, the character ъ, does not occcur in word-final position. It should be omitted in romanization when found in word-final position on older sources
     - The obsolete character ѫ, which was replaced by ъ in 1945, should be romanized ŭ
-    - The obsolete character ѣ, replaced in 1945 by е or я according to local
-      pronunciation, should be romanized as e or ya, accordingly, if the
-      pronunciation is known; otherwise, as ye
-    - The character sequence тс may be romanized t·s in order to differentiate
-      that romanization from the regularly occurring digraph ts, which represents
-      the character ц
+    - The obsolete character ѣ, replaced in 1945 by е or я according to local pronunciation, should be romanized as e or ya, accordingly, if the pronunciation is known; otherwise, as ye
+    - The character sequence тс may be romanized t·s in order to differentiate that romanization from the regularly occurring digraph ts, which represents the character ц
 }
 
 tests {

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bul
   source_script: Cyrl
   destination_script: Latn
-  name: Romanization of Bulgarian (2013 Agreement)
+  name: BGN/PCGN 2013 Agreement
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
   creation_date: 2013
   confirmation_date: 2019-06

data/maps/bgnpcgn-che-Cyrl-Latn-2008.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:che
   source_script: Cyrl
   destination_script: Latn
-  name: Table of Correspondences for Chechen (Cyrillic-Roman) (2008 Agreement)
-  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+  name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
   creation_date: 2008
   confirmation_date: 2019-07
   description: |

data/maps/bgnpcgn-deu-Latn-Latn-2000.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:deu
   source_script: Latn
   destination_script: Latn
-  name: Roman-Script Spelling Convention of German (2000 Agreement)
+  name: BGN/PCGN German 2000 Roman-Script Spelling Convention Agreement
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
   creation_date: 2000
 

data/maps/bgnpcgn-div-Thaa-Latn-1972.imp

@@ -4,14 +4,14 @@ metadata {
   language: iso-639-2:div
   source_script: Thaa
   destination_script: Latn
-  name: Romanization of Maldivian (1972)
-  url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
+  name: ROMANIZATION SYSTEM FOR MALDIVIAN BGN/PCGN 1972 System
+  url: ''
   creation_date: 1972
   description: ROMANIZATION SYSTEM FOR MALDIVIAN BGN/PCGN 1972 System
   notes:
     - Maldivian writing is read from right to left.
-    - In the vowel and Diacritical Mark columns x represents any Maldivian consonant character. A Roman vowel letter follows the Romanized Maldivian consonant
-    - Alifu(އ) is romanized [’], except when brearing a vowel ,marker, in which case it is not represented in Romanization.
+    - In the vowel and Diacritical Mark columns x represents any Maldivian consonant character. A Roman vowel letter follows the romanized Maldivian consonant
+    - Alifu(އ) is romanized [’], except when brearing a vowel ,marker, in which case it is not represented in romanization.
     - Nūnu(ނ) appearing immediately before bā, dālu, d̦aviyani, or gāfu, and not braring a vowel marker or sukunu, is romanised [ň];otherwise [n].
     - Where sīnu is followed by hā, or nūnu by yā, a raised dot or slash may be employed in order to differentiate these form shaviyani and nyaviyani respectively
 }

data/maps/bgnpcgn-div-Thaa-Latn-1988.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:div
   source_script: Thaa
   destination_script: Latn
-  name: Romanization of Maldivian (1988 Agreement, with 2009 modifications)
+  name: ROMANIZATION OF MALDIVIAN BGN/PCGN 1988 Agreement, with modifications 2009
   url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816778/ROMANIZATION_OF_MALDIVIAN.pdf
   creation_date: 1988
   confirmation_date: 2019

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: Romanization of Greek (1962)
+  name: BGN/PCGN 1962 System
   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: Romanization of Greek (1996)
+  name: BGN/PCGN 1996 System
   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

@@ -4,13 +4,12 @@ metadata {
   language: iso-639-2:far
   source_script: Latn
   destination_script: Latn
-  name: Romanization of Faeroese (1964)
-  url: https://github.com/interscript/interscript/files/5180777/BGN_Romanization_Guide_1964_faeroese.pdf
+  name: 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, employs the letter eth (Ð ð).
+    The Faeroese language is a dialect of Icelandic and, like Icelandic, employes 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 writing of Faeroese.
+    The Icelandic letter thorn (Þ þ) does not occur in the writting 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: Roman-Script Spelling Convention of Faroese (1968 Agreement)
+  name: BGN/PCGN Faroese 1968 Roman-Script Spelling Convention 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: Romanization of Arabic (1956)
+  name: BGN/PCGN 1956 System
   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 (1947)
+  name: TRANSLITERATION OF ICELANDIC BGN/PCGN 1947 System
   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), pronounced as th in "thus" and th in "think," respectively.
+    The transliterated letters are the edh (Ð ð) and the thorn (Þ þ), pronounved 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: Roman-Script Spelling Convention of Icelandic (1968 Agreement)
+  name: BGN/PCGN Icelandic 1968 Roman-Script Spelling Convention 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: Romanization of Japanese -- Kana Modified Hepburn (1930)
+  name: Japanese Kana Modified Hepburn 1930 System
   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 (1981)
+  name: ROMANIZATION OF GEORGIAN; BGN/PCGN 1981 System
   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 (2009 Agreement, Georgia 2011 national system)
+  name: ROMANIZATION OF GEORGIAN; Georgia 2011 national system; BGN/PCGN 2009 Agreement
   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 (1979)
+  name: Romanization of Kazakh
   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 (1979)
+  name: Romanization of Kyrgyz
   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: Romanization of Korean for DPRK (Hangul-Latin) (1945 Agreement)
+  name: BGN/PCGN 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: 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
+  name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+  url:
+  creation_date:
+  adoption_date:
   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: 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
+  name: Ministry of Culture and Tourism System (2000) BGN/PCGN 2011 Agreement
+  url: ""
+  creation_date: ""
+  adoption_date: ""
   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 (2007)
+  name: ROMANIZATION OF KURDISH -- BGN/PCGN 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