interscript-maps 2.2.0 → 2.2.1

data/maps/odni-kat-Geor-Latn-2015.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:kat
   source_script: Geor
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Georgian Personal Names 2015, ICS 630-01 Annex E
-  
+  name: Romanization of Georgian Personal Names (2015), ICS 630-01 Annex E
   # url:
   source: ICS 630-01, Annex E
   creation_date: 2015
@@ -16,7 +15,7 @@ metadata {
     eliminate variations of a name that can contribute forensic information. Rather, it is to provide an
     IC standard Romanized (English) transliteration from Georgian that can then be linked to forensic
     information in ways that will help identify the referent of the name.
-  
+
   notes:
 }
 

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

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

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

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

data/maps/odni-kor-Hang-Latn-2015.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kor
   source_script: Hang
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Korean 2015 System, ICS-630-01 Annex W
+  name: Romanization of Korean Personal Names (2015), ICS-630-01 Annex W
   url:
   creation_date: 2015
   adoption_date:

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mkd
   source_script: Cyrl
   destination_script: Latn
-  name: Standards for the transliteration of macedonian personal names in written reports and products
+  name: Intelligence Community (IC) Standard for the Transliteration of Macedonian Personal Names (2005)
   creation_date: 2005
   confirmation_date: 2005
   description: |

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

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

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-3:prs
   source_script: Arab
   destination_script: Latn
-  name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
+  name: Romanization of Persian Farsi Dari Personal Names (2015), 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
   creation_date: 2015
   confirmation_date: 2015-11

data/maps/odni-pus-Arab-Latn-2011.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-3:prs
   source_script: Arab
   destination_script: Latn
-  name: ODNI Pashto Personal Names 2011 System
+  name: Romanization of Pashto Personal Names (2011)
   url: https://github.com/interscript/interscript-private-references/blob/master/odni/Pashto%20June%202011.pdf
   creation_date: 2011
   confirmation_date: 2011-06

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

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

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

@@ -4,12 +4,12 @@ metadata {
   language: iso-639-2:srp
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Serbian Personal Names 2004 System
+  name: Intelligence Community (IC) Standard for the Transliteration of Serbian Personal Names (2004)
   creation_date: 2005
   confirmation_date: 2005
   description: |
     Office of the Director Of National Intelligence Serbian Personal Names 2004 System
-  
+
   notes:
 }
 

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

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-2:srp
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Serbian Personal Names 2015, ICS-630-01 Annex L
-  
+  name: Romanization of Serbian Personal Names (2015), ICS-630-01 Annex L
+
   # url:
   source: ICS-630-01 Annex L
   creation_date: 2015
@@ -16,27 +16,27 @@ metadata {
     is not intended to eliminate variations of a name that can contribute forensic information. Rather,
     it is to provide an IC standard Romanized (English) transliteration from Serbian that can then be
     linked to forensic information in ways that will help identify the referent of the name.
-  
+
     In cases where an individual’s name has already been transliterated in a variant spelling, the IC
     Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
     usage. In addition, if the original Cyrillic spelling is known, that spelling should also appear in
     parentheses following the name, if possible, following best practices of the issuing organization
     and taking into consideration information system capabilities. This convention is designed to
     ensure that vital forensic information is not lost.
-  
+
     For names of persons who are known to not be part of the Serbian-speaking community, use the
     relevant IC transliteration standard for names from that language (e.g., Mikhail, Yitzhak). A
     translator’s note may be used to clarify the known origin of the person. Spell names of
     individuals from languages that are written in Roman letters as they are spelled in those
     languages (e.g., George Clooney, Jorge Garcia, Georges Pompidou).
-  
+
     In the case of active senior government officials in the on-line CIA World Factbook and the online directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
     given in these on-line reference works should be used in place of the IC Standard. For any
     individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
     longer appears in those resources (i.e. is no longer a government official), the IC Standard
     spelling should appear first, with the spelling, if known, as it previously appeared in those
     resources listed within parentheses at the first usage.
-  
+
     The primary goal is to produce a consistent Romanized transcription of names that is specifically
     readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
     (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
@@ -44,7 +44,7 @@ metadata {
     individual is provided, the referent will be clearly identified. This system will be used in
     conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
     names of well-known individuals.
-  
+
   notes:
 }
 
@@ -93,7 +93,7 @@ stage {
     sub "\u0427", "C" # Ч
     sub "\u040F", "Dz" # Џ
     sub "\u0428", "S" # Ш
-    
+
     sub "\u0430", "a" # а
     sub "\u0431", "b" # б
     sub "\u0432", "v" # в

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

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

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

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

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:tuk
   source_script: Cyrl
   destination_script: Latn
-  name: Standards for the transliteration of Turkmen personal names in written reports and products
+  name: Romanization of Turkmen Personal Names (2015)
   url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20T%20-%20Turkmen_Personal_Names_FLTS%20(U).pdf
   source: ICS-630-01 Annex T
   creation_date: 2015

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

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

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ukr
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Ukrainian Personal Names 2004 System, ICS 630-01 Annex M
+  name: Romanization of Ukrainian Personal Names (2015), ICS 630-01 Annex M
 
   # url:
   source: ICS 630-01, Annex M

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

@@ -4,8 +4,8 @@ metadata {
   language: iso-639-2:urd
   source_script: Arab
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Hindi Urdu Personal Names 2015 System, ICS-630-01 Annex F
-  
+  name: Romanization of Hindi and Urdu Personal Names (2015), ICS-630-01 Annex F
+
   #url:
   creation_date: 2015
   confirmation_date: 2015
@@ -16,7 +16,7 @@ metadata {
     forensic information. Rather, it is to provide an IC standard Romanized (English)
     transliteration from standard Hindi and Urdu that can then be linked to forensic
     information in ways that will help identify the referent of the name.
-  
+
     There are typically a number of ways that names can be Romanized from either
     Devanagari (Hindi) or modified Arabic (Urdu) scripts. Ambiguities can result from the
     Romanization of Hindi and Urdu names for several reasons, including the fact that some
@@ -31,7 +31,7 @@ metadata {
     And, as in the Arabic source, names containing the Arabic definite article ‘al’ (‘ul’) show
     anticipatory assimilation in pronunciation (e.g., Shams al Din > Shamsuddin);
     transliterations may either reflect spelling or pronunciation in such cases.
-  
+
     Because Hindi and Urdu overlap so extensively, it is desirable to correlate Hindi and
     Urdu transliterations as much as possible. In the area of names, this can become
     problematic when the Urdu spelling accurately reflects original Arabic spelling while the
@@ -40,7 +40,7 @@ metadata {
     either Urdu or Hindi (e.g., letter sin versus letter sad) while maintaining Arabic/Urdu
     spelling distinctions like Hindi also maintains (e.g., qaf as in Qutubbin versus kaf)).
     However, this is not always possible (see Hindi va versus Urdu wau).
-  
+
     In cases where an individual’s name has already been transliterated, that is to be indicated
     – as found – in parentheses immediately following its rendition in the transliteration
     standard (e.g., Muhammad Khulud (Mohamed Khulood)). In addition, if the original
@@ -48,14 +48,14 @@ metadata {
     parentheses following the name, if possible, following best practices of the issuing
     organization and taking into consideration information system capabilities. This
     convention is designed to ensure that vital forensic information is not lost.
-  
+
     For names of persons who are known to not be part of the Hindi- or Urdu-speaking
     community, use the relevant IC transliteration standard for names from that language
     (e.g., Mikhail, Yitzhak). A translator’s note may be used to clarify the known origin of
     the person. Spell names of individuals from languages that are written in Roman letters as
     they are spelled in those languages (e.g., George Clooney, Jorge Garcia, Georges
     Pompidou).
-  
+
     In the case of active senior government officials in the on-line CIA World Factbook and
     the on-line directory of Chiefs of State and Cabinet Members of Foreign Governments,
     the spellings given in these on-line reference works should be used in place of the IC
@@ -64,7 +64,7 @@ metadata {
     government official), the IC Standard spelling should appear first, with the spelling, if
     known, as it previously appeared in those resources listed within parentheses at the first
     usage.
-  
+
     The primary goal of this system is to produce a consistent Romanized transcription of the
     name that is readable to the non-specialist. The system uses the 26 letters of the standard
     (English) Roman alphabet. Some ambiguities in the Romanized form will occur without
@@ -72,16 +72,16 @@ metadata {
     information about the individual is provided, the referent will be clearly identified.
     Additionally, this system will be used in conjunction with on-line tools, name dictionaries
     and lists containing conventional spellings of names of well-known individuals
-  
+
   notes:
-  
+
     - |
       Long/Short Vowels: Long and short vowels are not distinguished in the system:
       The borrowed Arabic name Samir could represent two distinct names, one with a
       long /a/ (Saamir) and one with a long /i/ (Samiir). One solution would be to use
       /ee/ to stand for the long /i/, as is often done (Sameer). The IC Standard will not
       distinguish between these.
-  
+
     - |
       No distinction is made between: retroflex and non-retroflex consonants; and
       nasalized vowels and vowels followed by /n/.
@@ -150,8 +150,8 @@ stage {
 
   # CHARACTERS
   parallel {
-    
-    
+
+
     sub "\u0622", "a" # ARABIC ALEF W/MADDA ABOVE
     sub "\u0627", "a" # or u ARABIC ALEF
     sub "\u06cc", "i" # or ai or u ARABIC LETTER WAW
@@ -170,9 +170,9 @@ stage {
     sub "\u06c2", "-e" #  ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
     sub "\u06c1\u0650", "o" #  ARABIC LETTER YEH  WITH HAMZA ABOVE
     sub "\u0624", "au" #  ARABIC LETTER WAW WITH HAMZA ABOVE
-    
-    
-    
+
+
+
     sub "\u06a9", "k" #   ARABIC LETTER KEHEH
     sub "\u0642", "q" #   ARABIC LETTER QAF
     sub "\u062e", "kh" #   ARABIC LETTER KHAH
@@ -180,14 +180,14 @@ stage {
     sub "\u063a", "gh" #   ARABIC LETTER GHAIN
     sub "\u0686", "ch" #   ARABIC LETTER TCHEH
     sub "\u062c", "j" #   Arabic Letter Jeem
-    
+
     sub "\u0632", "z" #   Arabic Letter ZAIN
     sub "\u0630", "z" #   Arabic Letter THAL
     sub "\u0636", "z" #   Arabic Letter DAD
     sub "\u0638", "z" #   Arabic Letter ZAH
     sub "\u0698", "zh" #   Arabic Letter JEH
-    
-    
+
+
     sub "\u0679", "t" #   ARABIC LETTER TTEH
     sub "\u0688", "d" #   Arabic Letter DDAL
     sub "\u062f", "d" #   Arabic Letter DAL
@@ -196,8 +196,8 @@ stage {
     sub "\u0637", "t" #   Arabic Letter TAH
     sub "\u0646", "n" #   Arabic Letter NOON
     sub "\u06ba", "n" #   Arabic Letter NOON GHUNNA
-    
-    
+
+
     sub "\u067e", "p" #   Arabic Letter PE
     sub "\u0641", "f" #   Arabic Letter FEH
     sub "\u0628", "b" #   Arabic Letter BEH

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

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

data/maps/ses-ara-Arab-Latn-1930.imp

@@ -129,20 +129,20 @@ stage {
 
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "el-t" # الت
-    sub boundary + "\u0627\u0644\u062b", any(["el-th", "el-t"]) # الث
-    sub boundary + "\u0627\u0644\u062f", "el-d" # الد
-    sub boundary + "\u0627\u0644\u0630", any(["el-dh", "el-z"]) # الذ
-    sub boundary + "\u0627\u0644\u0631", "el-r" # الر
-    sub boundary + "\u0627\u0644\u0632", "el-z" # الز
-    sub boundary + "\u0627\u0644\u0633", any(["el-s", "el-c"]) # الس
-    sub boundary + "\u0627\u0644\u0634", "el-sh" # الش
-    sub boundary + "\u0627\u0644\u0635", "el-ṣ" # الص
-    sub boundary + "\u0627\u0644\u0636", "el-ḍ" # الض
-    sub boundary + "\u0627\u0644\u0637", "el-ṭ" # الط
-    sub boundary + "\u0627\u0644\u0638", any(["el-ẓ", "el-d"]) # الظ
-    sub boundary + "\u0627\u0644\u0644", "el-l" # الل
-    sub boundary + "\u0627\u0644\u0646", "el-n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "el-t" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), any(["el-th", "el-t"]) # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "el-d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), any(["el-dh", "el-z"]) # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "el-r" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "el-z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), any(["el-s", "el-c"]) # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "el-sh" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "el-ṣ" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "el-ḍ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "el-ṭ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), any(["el-ẓ", "el-d"]) # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "el-l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "el-n" # الن
 
 
     # shadda

data/maps/un-amh-Ethi-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
+  name: Romanization of Amharic -- UNGEGN (2016)
   url: http://www.eki.ee/wgrs/rom1_am.pdf
   creation_date: 1967
   confirmation_date: 2016-03

data/maps/un-ara-Arab-Latn-1971.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: 1971 "Beirut system"
+  name: Romanization of Arabic -- Beirut system (1971)
   url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
   creation_date: 1971
   confirmation_date: 2018-06
@@ -85,10 +85,10 @@ stage {
   parallel {
 
     # sun letters
-    sub boundary + "\u0627\u0644\u062b", "at͟h t͟h" # الث
-    sub boundary + "\u0627\u0644\u0630", "ad͟h d͟h" # الذ
-    sub boundary + "\u0627\u0644\u0634", "as͟h s͟h" # الش
-    sub boundary + "\u0627\u0644\u0638", "az͟h z͟h" # الظ
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "at͟h t͟h" # الث
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "ad͟h d͟h" # الذ
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "as͟h s͟h" # الش
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az͟h z͟h" # الظ
 
     # shadda
     sub "\u062e\u0651", "k͟hk͟h" # خ

data/maps/un-ara-Arab-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 1972 System
+  name: Romanization of Arabic -- UNGEGN (1972)
   url: http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
   creation_date: 1972
   confirmation_date: 2018-06
@@ -107,9 +107,9 @@ stage {
   # CHARACTERS
   parallel {
 
-    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
-    sub boundary + "\u0627\u0644\u0636", "aḑ ḑ" # الض
-    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḑ ḑ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
 
     sub "\u062d\u0651", "ḩḩ" # ح
     sub "\u0635\u0651", "şş" # ص