interscript-maps 2.0.5

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

@@ -0,0 +1,180 @@
+metadata {
+  authority_id: odni
+  id: 2004
+  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
+  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:
+      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/.
+    - |
+      A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,
+      Hindi qa and ka).
+    - |
+      A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants
+      (e.g., /dh/), with the exception of ch/chh, both represented by /ch/.
+    - |
+      Digraphs: No distinction is made between digraphs such as /sh/ and single
+      contiguous letters such as /s/ followed by /h/.
+    - |
+      Hyphens: Hyphens (-) are NOT used to connect name elements within a name:
+      Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in
+      noun-link-modifier construction of Persian origin), which does show a hypen
+      before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e
+      xx” (‘Army of xx’ construction).
+    - |
+      Names incorporating “din” are written as one unit: Azermuddin, Badruddin,
+      Faizuddin, Salahuddin.
+    - |
+      Names that incorporate Allah as part of the name show the Arabic grammatical
+      marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).
+    - |
+      Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final
+      consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not
+      Rama Lala).
+    - |
+      As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.
+      Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is
+      transcribed as /w/: Wasim, Walid.
+}
+
+tests {
+  test "दिल्ली", "dilli"
+  test "भारत", "bhart"
+  test "विजय", "vijy"
+  test "विशाल", "vishal"
+  test "अब्दुल्ला", "abdulla"
+  test "संख्या", "snkhya"
+  test "संख्या", "snkhya"
+  test "समीर", "smir"
+  test "सरस्वती", "srsvti"
+  test "कृष्णास्वामी", "krishnasvami"
+}
+
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    
+    #Independent vowel characters
+    sub "अ", "a"
+    sub "आ", "a"
+    sub "इ", "i"
+    sub "ई", "i"
+    sub "उ", "u"
+    sub "ऊ", "u"
+    sub "ऋ", "ri"
+    sub "ऌ", "l̤"
+    sub "ए", "e"
+    sub "ऐ", "ai"
+    sub "ओ", "o"
+    sub "ऑ", "au"
+    sub "औ", "au"
+    
+    #Dependent Vowels
+    sub "ा", "a"
+    sub "ि", "i"
+    sub "ी", "i"
+    sub "ु", "u"
+    sub "ू", "u"
+    sub "ृ", "ri"
+    sub "े", "e"
+    sub "ै", "ai"
+    sub "ॅ", "ai"
+    sub "ो", "o"
+    sub "ौ", "au"
+    sub "ॉ", "au"
+    
+    
+    # Consonants
+    
+    # Gutturals
+    sub "क", "k"
+    sub "क्ष", "ksha"
+    sub "क़", "q"
+    sub "ख", "kh"
+    sub "ख़", "kh"
+    sub "ग", "g"
+    sub "ग़", "gh"
+    sub "घ", "gh"
+    sub "ङ", "n"
+    
+    # Palatals
+    sub "च", "ch"
+    sub "छ", "ch"
+    sub "ज", "j"
+    sub "ज़", "z"
+    sub "झ", "gya"
+    sub "झ", "jh"
+    sub "ञ", "n"
+    
+    # Cerebrals
+    sub "ट", "t"
+    sub "ठ", "th"
+    sub "ड", "d"
+    sub "ड़", "r"
+    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"
+    sub "फ", "ph"
+    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

@@ -0,0 +1,256 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  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
+  
+  #url:
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community (IC) standard for the transliteration of names
+    from Hindi and Urdu that will be applied to all final written reports and products for IC
+    consumers. It 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 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
+    sounds in South Asian languages (e.g., retroflex consonants, voiced aspirates) have no
+    equivalent in English or other European languages. In the case of Urdu, as in the original
+    Arabic source of many Islamic names, short vowel markings, double consonant marks
+    and other diacritics that would clearly distinguish the name are almost always omitted
+    from standard written texts. And many Islamic names of Arabic or Persian origin reflect
+    spelling distinctions from those languages that are lost in modern Urdu pronunciation
+    (e.g., three distinct Arabic letters all represent the identical sound [s] for Urdu speakers);
+    transliterations might either maintain those spelling distinctions or ignore them entirely.
+    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
+    Hindi spelling was phonetically-based, in essence, already a transliteration. This would
+    argue for ignoring Arabic/Urdu spelling distinctions not reflected in pronunciation in
+    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
+    Devanagari or Arabic-script 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 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
+    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 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
+    the use of diacritics. However, within the context of a report, where additional
+    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/.
+    - |
+      No distinction is made between the several Arabic letters with the same phonetic
+      value in Urdu: e.g., letters sin/svad, zal/ze/zoe.
+    - |
+      A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,
+      Hindi qa and ka).
+    - |
+      A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants
+      (e.g., /dh/), with the exception of ch/chh, both represented by /ch/.
+    - |
+      Double consonants: Double consonants represented by the tashdid (shaddah) are
+      shown in most cases (e.g., Hassan, Muhammad). Exceptions: consonants
+      represented by digraphs are not doubled (e.g., Mubashir [not Mubashshir]).
+    - |
+      Hamzah (glottal stop) and ayn: Unlike in the Arabic IC Standard, these are not
+      represented in the IC standard.
+    - |
+      Digraphs: No distinction is made between digraphs such as /sh/ and single
+      contiguous letters such as /s/ followed by /h/.
+    - |
+      Arabic definite article “al” (‘the’): Shows sun letter assimilation in the
+      Romanized form (e.g., Abdur Rahman rather than Abdal Rahman, rather than
+      Arabic IC standard 'Abd al-Rahman).
+    - |
+      Special Rules
+      - |
+        Hyphens: Hyphens (-) are NOT used to connect name elements within a name:
+        Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in
+        noun-link-modifier construction of Persian origin), which does show a hyphen
+        before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e
+        xx” (‘Army of xx’ construction).
+      - |
+        Names incorporating “din” are written as one unit: Azermuddin, Badruddin,
+      Faizuddin, Salahuddin.
+      - |
+        Names that incorporate Allah as part of the name show the Arabic grammatical
+        marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).
+      - |
+        Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final
+        consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not
+        Rama Lala).
+      - |
+        As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.
+        Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is
+        transcribed as /w/: Wasim, Walid.
+}
+
+tests {
+  test "हसन मोहम्मद", "hsn mohmmd"
+  test "विशाल ठाकुर", "vishal thakur"
+  test "अमिताभ जैन", "amitabh jain"
+  test "आकाङ्क्षा बच्चन", "akankshaa bchchn"
+  test "अनुष्का शर्मा", "anushka shrma"
+  test "शाहरुख खान", "shahrukh khan"
+  test "इंजमाम उल हक", "injmam ul hk"
+  test "शाहिद अफरीदी", "shahid aphridi"
+  test "सचिन तेंडुलकर", "schin tendulkr"
+  test "वसीम अकरम", "vsim akrm"
+  test "हसन अब्दुल्ला", "hsn abdulla"
+}
+
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    
+    # I. Vowels and Diphthongs (see Note 1)
+    
+    sub "अ", "a"
+    sub "आ", "a"
+    sub "इ", "i"
+    sub "ई", "i"
+    sub "उ", "u"
+    sub "ऊ", "u"
+    sub "ऋ", "ri"
+    sub "ए", "e"
+    sub "ऐ", "ai"
+    sub "ऑ", "o"
+    sub "ओ", "au"
+    
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "k"
+    sub "क्ष", "ksha"
+    sub "क़", "q"
+    sub "ख", "kh"
+    sub "ख़", "kh"
+    sub "ग", "g"
+    sub "घ", "gh"
+    sub "ग़", "gh"
+    sub "ङ", "n"
+    
+    # Palatals
+    sub "च", "ch"
+    sub "छ", "ch"
+    sub "ज", "j"
+    sub "झ", "jh"
+    sub "ज़", "z"
+    sub "ञ", "n"
+    
+    # Cerebrals
+    sub "ट", "t"
+    sub "ठ", "th"
+    sub "ड", "d"
+    sub "ड़", "r"
+    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"
+    sub "फ़", "f"
+    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"
+    sub "ी", "i"
+    sub "ु", "u"
+    sub "ू", "u"
+    sub "ृ", "ri"
+    sub "े", "e"
+    sub "ै", "ai"
+    sub "ॅ", "ai"
+    sub "ॊ", "o"
+    sub "ो", "o"
+    sub "ौ", "au"
+    sub "ॉ", "au"
+  }
+
+}
+

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

@@ -0,0 +1,76 @@
+metadata {
+  authority_id: odni
+  id: 2015
+  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
+  
+  # url:
+  source: ICS 630-01, Annex E
+  creation_date: 2015
+  confirmation_date: 2015
+  description: |
+    This system is the Intelligence Community standard for the transliteration of Georgian names that
+    will be applied to all final written reports and products for IC consumers. It 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 Georgian that can then be linked to forensic
+    information in ways that will help identify the referent of the name.
+  
+  notes:
+}
+
+tests {
+  test "ბაყაყი", "baqaqi"
+  test "ძროხა", "dzrokha"
+  test "ჰაერი", "haeri"
+  test "ჟოლო", "zholo"
+  test "ჯართი", "jarti"
+  test "ღრმაღელე", "ghrmaghele"
+  test "ზვიად გამსახურდია", "zviad gamsakhurdia"
+  test "ედუარდ შევარდნაძე", "eduard shevardnadze"
+  test "მიხეილ სააკაშვილი", "mikheil saakashvili"
+  test "გიორგი მარგველაშვილი", "giorgi margvelashvili"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u10d0", "a" # ა
+    sub "\u10d1", "b" # ბ
+    sub "\u10d2", "g" # გ
+    sub "\u10d3", "d" # დ
+    sub "\u10d4", "e" # ე
+    sub "\u10d5", "v" # ვ
+    sub "\u10d6", "z" # ზ
+    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 "\u10dd", "o" # ო
+    sub "\u10de", "p" # პ
+    sub "\u10df", "zh" # ჟ
+    sub "\u10e0", "r" # რ
+    sub "\u10e1", "s" # ს
+    sub "\u10e2", "t" # ტ
+    sub "\u10e3", "u" # უ
+    sub "\u10e4", "p" # ფ
+    sub "\u10e5", "k" # ქ
+    sub "\u10e6", "gh" # ღ
+    sub "\u10e7", "q" # ყ
+    sub "\u10e8", "sh" # შ
+    sub "\u10e9", "ch" # ჩ
+    sub "\u10ea", "ts" # ც
+    sub "\u10eb", "dz" # ძ
+    sub "\u10ec", "ts" # წ
+    sub "\u10ed", "ch" # ჭ
+    sub "\u10ee", "kh" # ხ
+    sub "\u10ef", "j" # ჯ
+    sub "\u10f0", "h" # ჰ
+  }
+
+}
+