interscript 0.1.5 → 0.1.6

data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml

@@ -5,7 +5,7 @@ language: ell
 source_script: Grek
 destination_script: Latn
 name: ISO 843:1997
-url: 
+url:
 creation_date: 1997
 description: |
   ISO Transliteration table for Greek
@@ -25,7 +25,7 @@ tests:
 
     expected: |
         Éna práma mónon me parakínīse ki eména na grápsō óti toútīn tīn patrída tīn échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai ftōchoí kai politikoí kai stratiōtikoí kai oi pléon mikróteroi ánthrōpoi; ósoi agōnistī́kamen, analógōs o katheís, échomen na zī́somen edṓ. To loipón doulépsamen óloi mazí, na tīn fylámen ki óloi mazí kai na mīn légei oúte o dynatós «egṓ» oúte o adýnatos. Xérete póte na légei o katheís «egṓ»? Ótan agōnisteí mónos tou kai fkiásei ī́ chalásei, na légei «egṓ»; ótan ómōs agōnízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egṓ». Kai eis to exī́s na máthomen gnṓsī, an thélomen na fkiásomen chōrión, na zī́somen óloi mazí.
-       
+
         Giánnīs Makrygiánnīs.
 
 
@@ -73,7 +73,7 @@ tests:
     expected: Taÿ́getos
   - source: σπρέυ
     expected: spréy
-    
+
   - source: Αθήνα
     expected: Athī́na
   - source: Άγιον Όρος
@@ -521,7 +521,7 @@ map:
     - pattern: (?<=[ΑαΕεΟο])\u03C5    # υ (after Α, Ε, Η)
       result: u
     - pattern: (?<=[ΑαΕεΟο])\u03CD    # ύ (after Ο)
-      result: ú      
+      result: ú
     - pattern: \u037E   # ;
       result: "?"
     - pattern: \u003B   # ;
@@ -607,4 +607,3 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
-

data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml

@@ -5,7 +5,7 @@ language: ell
 source_script: Grek
 destination_script: Latn
 name: ISO 843:1997
-url: 
+url:
 creation_date: 1997
 description: |
   ISO Transcription table for Greek
@@ -38,4 +38,3 @@ map:
     "\u03F9": "S"   # Ϲ
     "\u03F3": "j"
     "\u037F": "j"
-

data/maps/iso-rus-Cyrl-Latn-9-1995.yaml

@@ -269,4 +269,3 @@ map:
     "\u04c0": "\u2021"                         # Ӏ	=> ‡
     "\u02bc": "\u0060"                         # ʼ	=> `
     "\u02ee": "\u00a8"                         # ˮ => ¨
-

data/maps/iso-tha-Thai-Latn-11940-1998.yaml

@@ -7,7 +7,7 @@ destination_script: Latn
 name: ISO 11940:1998 Information and documentation -- Transliteration of Thai
 url: https://www.iso.org/standard/20574.html
 creation_date: 1998
-adoption_date: 
+adoption_date:
 description:
 
 notes:

data/maps/kp-kor-Hang-Latn-2002.yaml

@@ -12,7 +12,7 @@ description:
 
 notes:
 
-  - Here is a list of features that are listed in the guideline but 
+  - Here is a list of features that are listed in the guideline but
     not unimplemented in this map.
 
   - Note 3.2
@@ -30,15 +30,15 @@ notes:
     Except for the n-g combination, this has not been implemented.
 
   - Note 4.4
-    Geographical names "may be transliterated or translated". In this map, 
-    all names will be transliterated, not translated. Numerals will not be 
+    Geographical names "may be transliterated or translated". In this map,
+    all names will be transliterated, not translated. Numerals will not be
     transliterated.
 
   - Note 4.5
     Spacing rule for personal names has not been implemented.
 
   - Note 4.7
-    Optional omission of diacritics and optional simplification of 
+    Optional omission of diacritics and optional simplification of
     KK, TT, PP, SS, JJ to single letter have not been implemented.
 
 tests:

data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml

@@ -4,7 +4,7 @@ id: jyutping
 language: yue
 source_script: Hani
 destination_script: Latn
-name: LSHK Jyutping 
+name: LSHK Jyutping
 url: https://lshk.org/jyutping
 creation_date: 1993-12
 description:
@@ -39,7 +39,7 @@ map:
   #  - pattern: \u044c(?=[ЕеЁёИиОоЭэ]) # ь (before Е, Ё, И, O, Э)
   #    result: y
 
-  # Although the map is called "characters", phrases are added before individual characters 
+  # Although the map is called "characters", phrases are added before individual characters
   # in order to improve transliteration accuracy
 
   characters:

data/maps/mvd-bel-Cyrl-Latn-2008.yaml

@@ -17,7 +17,7 @@ description: |
 
 notes:
   # Original notes
-  # - | 
+  # - |
   #   Инструкция по транслитерации фамилий и собственных имен граждан Республики Беларусь при включении
   #   их персональных данных в регистр населения устанавливает правила передачи с белорусской либо русской формы
   #   написания на латиницу при включении фамилий и собственных имен граждан Республики Беларусь в регистр населения.
@@ -37,8 +37,8 @@ notes:
   # - Сложные и составные фамилии и собственные имена, пишущиеся слитно, раздельно или через дефис,
   #   сохраняют слитное, раздельное или дефисное написание и в латинице.
   - | # 1
-    Instructions for transliterating the names and first names of citizens of the Republic of Belarus 
-    when including their personal data in the population register sets the rules for transferring 
+    Instructions for transliterating the names and first names of citizens of the Republic of Belarus
+    when including their personal data in the population register sets the rules for transferring
     from the Belarusian or Russian form of writing in Latin when including the names and first names
     of citizens of the Republic of Belarus in the population register.
   - | # 2
@@ -165,7 +165,7 @@ map:
     '\u0414' : 'D'  # Д
     '\u0415' : 'Ie' # Е or JE TODO add rule
     '\u0401' : 'Io' # Ё or JO TODO add rule
-    '\u0416' : 'Zh' # Ж 
+    '\u0416' : 'Zh' # Ж
     '\u0417' : 'Z'  # З
     '\u0406' : 'I'  # І
     '\u0419' : "J"  # Й

data/maps/mvd-bel-Cyrl-Latn-2010.yaml

@@ -5,8 +5,8 @@ language: bel
 source_script: Cyrl
 destination_script: Latn
 name: |
-  About approval of the Instructions on the organization of work of units of citizenship 
-  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  About approval of the Instructions on the organization of work of units of citizenship
+  and migration of internal affairs bodies on the issuance, registration, exchange,
   invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 url: https://pravo.by/document/?guid=3871&p0=W21022721
 creation_date: 2010
@@ -14,8 +14,8 @@ creation_date: 2010
 description: |
   RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
   June 28, 2010 No. 200
-  On approval of the Instructions on the organization of work of units of citizenship 
-  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  On approval of the Instructions on the organization of work of units of citizenship
+  and migration of internal affairs bodies on the issuance, registration, exchange,
   invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 
 notes:

data/maps/mvd-rus-Cyrl-Latn-2008.yaml

@@ -45,7 +45,7 @@ map:
     '\u0414' : 'D'  # Д
     '\u0415' : 'E'  # Е
     '\u0401' : 'E'  # Ё
-    '\u0416' : 'Zh' # Ж 
+    '\u0416' : 'Zh' # Ж
     '\u0417' : 'Z'  # З
     '\u0406' : 'I'  # І
     '\u0419' : "J"  # Й
@@ -107,4 +107,3 @@ map:
     '\u044D' : 'e'  # э
     '\u044E' : 'iu' # ю
     '\u044F' : 'ia' # я
-

data/maps/mvd-rus-Cyrl-Latn-2010.yaml

@@ -5,8 +5,8 @@ language: bel
 source_script: Cyrl
 destination_script: Latn
 name: |
-  8/22721 On approval of the Instructions on the organization of work of units of citizenship 
-  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  8/22721 On approval of the Instructions on the organization of work of units of citizenship
+  and migration of internal affairs bodies on the issuance, registration, exchange,
   invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 url: https://pravo.by/document/?guid=3871&p0=W21022721
 creation_date: 2010
@@ -14,8 +14,8 @@ creation_date: 2010
 description: |
   RESOLUTION OF THE MINISTRY OF INTERNAL AFFAIRS OF THE REPUBLIC OF BELARUS
   June 28, 2010 No. 200
-  On approval of the Instructions on the organization of work of units of citizenship 
-  and migration of internal affairs bodies on the issuance, registration, exchange, 
+  On approval of the Instructions on the organization of work of units of citizenship
+  and migration of internal affairs bodies on the issuance, registration, exchange,
   invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
 
 notes:

data/maps/nil-kor-Hang-Hang-jamo.yaml

@@ -5,9 +5,9 @@ language: kor
 source_script: Hang
 destination_script: Hang
 name: Hangul to Jamo decomposition
-url: 
-creation_date: 
-adoption_date: 
+url:
+creation_date:
+adoption_date:
 description:
 
 notes:

data/maps/odni-aze-Cyrl-Latn-2015.yaml

@@ -21,7 +21,7 @@ description: |
   also appear in parentheses following the name, if possible, following best practices of the
   issuing organization and taking into consideration information system capabilities. For example:
   Rashad Sadykhov (also seen as Rashad Sadigov, Рашад Садыхов). This convention is designed to
-  ensure that vital forensic information is not lost.    
+  ensure that vital forensic information is not lost.
 
   For names of persons who are known to not be part of the Azeri-speaking community, use the
   relevant IC transliteration standard for names from that language (e.g., Yitzhak). A translator’s

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

@@ -15,7 +15,7 @@ description: |
   intended to eliminate variations of a name that can contribute forensic information. Rather, it is to
   provide an IC standard Romanized (English) transliteration from Belarusian 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

data/maps/odni-bul-Cyrl-Latn-2015.yaml

@@ -68,7 +68,7 @@ tests:
   - source: Ядеш хляба с чубрица
     expected: Yadesh khlyaba s chubritsa
 
-    
+
   # note[1]
   - source: шш
     expected: sh
@@ -85,10 +85,10 @@ map:
 
     - pattern: \u042C# # Ь
       result: "Y"
-      
+
     - pattern: \u042A # Ъ
       result: "A"
-      
+
     - pattern: \u044C # ь
       result: "y"
 

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

@@ -0,0 +1,258 @@
+---
+authority_id: odni
+id: 2015
+language: 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:
+  - source: "हसन मोहम्मद"
+    expected: "hsn mohmmd"
+  - source: "विशाल ठाकुर"
+    expected: "vishal thakur"
+  - source: "अमिताभ जैन"
+    expected: "amitabh jain"
+  - source: "आकाङ्क्षा बच्चन"
+    expected: "akankshaa bchchn"
+  - source: "अनुष्का शर्मा"
+    expected: "anushka shrma"
+  - source: "शाहरुख खान"
+    expected: "shahrukh khan"
+  - source: "इंजमाम उल हक"
+    expected: "injmam ul hk"
+  - source: "शाहिद अफरीदी"
+    expected: "shahid aphridi"
+  - source: "सचिन तेंडुलकर"
+    expected: "schin tendulkr"
+  - source: "वसीम अकरम"
+    expected: "vsim akrm"
+  - source: "हसन अब्दुल्ला"
+    expected: "hsn abdulla"
+
+map:
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'a'
+    'इ': 'i'
+    'ई': 'i'
+    'उ': 'u'
+    'ऊ': 'u'
+    'ऋ': 'ri'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ऑ': 'o'
+    'ओ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'k'
+    'क्ष': 'ksha'
+    'क़': 'q'
+    'ख': 'kh'
+    'ख़': 'kh'
+    'ग': 'g'
+    'घ': 'gh'
+    'ग़': 'gh'
+    'ङ': 'n'
+
+    # Palatals
+    'च': 'ch'
+    'छ': 'ch'
+    'ज': 'j'
+    'झ': 'jh'
+    'ज़': 'z'
+    'ञ': 'n'
+
+    # Cerebrals
+    'ट': 't'
+    'ठ': 'th'
+    'ड': 'd'
+    'ड़': 'r'
+    'ढ': 'dh'
+    'ढ़': 'rh'
+    'ण': 'n'
+
+    # Dentals
+    'त': 't'
+    'थ': 'th'
+    'द': 'd'
+    'ध': 'dh'
+    'न': 'n'
+
+    # Labials
+    'प': 'p'
+    'फ': 'ph'
+    'फ़': 'f'
+    'ब': 'b'
+    'भ': 'bh'
+    'म': 'm'
+
+    # Semivowels
+    'य': 'y'
+    'र': 'r'
+    'ल': 'l'
+    'व': 'v'
+
+    # Sibilants
+    'श': 'sh'
+    'ष': 'sh'
+    'स': 's'
+
+    # Aspirate
+    'ह': 'h'
+
+    # Anusvāra
+    'ं': 'n'
+
+    # Bisarga
+    'ः ': 'h'
+
+    # Anunāsika
+    'ँ': 'n'
+
+    '़': ''
+    '्': ''
+
+    # Medials # Needed for connecting constants
+    'ा': "a"
+    'ि': "i"
+    'ी': "i"
+    'ु': "u"
+    'ू': "u"
+    'ृ': "ri"
+    'े': "e"
+    'ै': "ai"
+    'ॅ': "ai"
+    'ॊ': "o"
+    'ो': "o"
+    'ौ': "au"
+    'ॉ': "au"