interscript-maps 2.1.0b6 → 2.2.1

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

@@ -4,7 +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
+  name: Intelligence Community (IC) Standard for the Transliteration of Arabic Personal Names (2004)
   url: https://github.com/interscript/interscript-private-references/blob/master/odni/Arabic_IC_Standard.doc
   creation_date: 2004
   confirmation_date: 2004-06

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

@@ -4,7 +4,7 @@ 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
+  name: Romanization of Arabic Personal Names (2015), ICS 630-01 Annex A
   url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20A%20-%20Arabic_Personal_Names_FLTS%20(U).pdf
   creation_date: 2017
   confirmation_date: 2018-06

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: Romanization of Azeri Personal Names (2015), ICS 630-01 Annex P
   source: ICS-630-01 Annex P
   creation_date: 2015
   confirmation_date: 2015

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

@@ -4,7 +4,7 @@ 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
+  name: Romanization of Belarusian Personal Names (2015), ICS 630-01 Annex B
 
   # url:
   source: ICS 630-01, Annex B

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

@@ -4,7 +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
+  name: Romanization of Bulgarian Personal Names (2015), ICS-630-01 Annex O
 
   # url:
   source: ICS-630-01 Annex O

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

@@ -4,7 +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
+  name: Romanization of Chechen Cyrillic Personal Names (2015)
   url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20C%20-%20Chechen_Personal_Names_FLTS%20(U).pdf
   source: ICS-630-01 Annex C
   creation_date: 2015

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

@@ -140,20 +140,20 @@ 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

@@ -4,7 +4,7 @@ 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
+  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
@@ -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 +4,12 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: IC STANDARDS FOR TRANSLITERATION OF HINDI AND URDU PERSONAL NAMES
+  name: Intelligence Community (IC) Standard for the Transliteration of Hindi and Urdu Personal Names (2004)
   url: https://github.com/interscript/interscript-private-references/blob/master/odni/Hindi_and_Urdu_IC_Standard.doc
   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 +69,7 @@ stage {
 
   # CHARACTERS
   parallel {
-    
+
     #Independent vowel characters
     sub "अ", "a"
     sub "आ", "a"
@@ -84,7 +84,7 @@ stage {
     sub "ओ", "o"
     sub "ऑ", "au"
     sub "औ", "au"
-    
+
     #Dependent Vowels
     sub "ा", "a"
     sub "ि", "i"
@@ -98,10 +98,10 @@ stage {
     sub "ो", "o"
     sub "ौ", "au"
     sub "ॉ", "au"
-    
-    
+
+
     # Consonants
-    
+
     # Gutturals
     sub "क", "k"
     sub "क्ष", "ksha"
@@ -112,7 +112,7 @@ stage {
     sub "ग़", "gh"
     sub "घ", "gh"
     sub "ङ", "n"
-    
+
     # Palatals
     sub "च", "ch"
     sub "छ", "ch"
@@ -121,7 +121,7 @@ stage {
     sub "झ", "gya"
     sub "झ", "jh"
     sub "ञ", "n"
-    
+
     # Cerebrals
     sub "ट", "t"
     sub "ठ", "th"
@@ -130,14 +130,14 @@ 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 +145,34 @@ 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 "़", ""
   }
 

data/maps/odni-hin-Deva-Latn-2015.imp

@@ -4,8 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   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 Urdu Personal Names (2015), ICS-630-01 Annex F
   #url:
   creation_date: 2015
   confirmation_date: 2015
@@ -16,7 +15,7 @@ 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 +30,7 @@ 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 +39,7 @@ 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 +47,14 @@ 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 +63,7 @@ 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 +71,16 @@ 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/.
@@ -151,9 +150,9 @@ stage {
 
   # CHARACTERS
   parallel {
-    
+
     # I. Vowels and Diphthongs (see Note 1)
-    
+
     sub "अ", "a"
     sub "आ", "a"
     sub "इ", "i"
@@ -165,7 +164,7 @@ stage {
     sub "ऐ", "ai"
     sub "ऑ", "o"
     sub "ओ", "au"
-    
+
     # II. Consonants (see Note 2)
     # Gutturals
     sub "क", "k"
@@ -177,7 +176,7 @@ stage {
     sub "घ", "gh"
     sub "ग़", "gh"
     sub "ङ", "n"
-    
+
     # Palatals
     sub "च", "ch"
     sub "छ", "ch"
@@ -185,7 +184,7 @@ stage {
     sub "झ", "jh"
     sub "ज़", "z"
     sub "ञ", "n"
-    
+
     # Cerebrals
     sub "ट", "t"
     sub "ठ", "th"
@@ -194,14 +193,14 @@ stage {
     sub "ढ", "dh"
     sub "ढ़", "rh"
     sub "ण", "n"
-    
+
     # Dentals
     sub "त", "t"
     sub "थ", "th"
     sub "द", "d"
     sub "ध", "dh"
     sub "न", "n"
-    
+
     # Labials
     sub "प", "p"
     sub "फ", "ph"
@@ -209,33 +208,33 @@ 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"
-    
+
     # Bisarga
     sub "ः ", "h"
-    
+
     # Anunāsika
     sub "ँ", "n"
-    
+
     sub "़", ""
     sub "्", ""
-    
+
     # Medials # Needed for connecting constants
     sub "ा", "a"
     sub "ि", "i"