interscript 0.1.1 → 0.1.6

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

@@ -0,0 +1,144 @@
+---
+authority_id: odni
+id: 2015
+language: aze
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of azeri personal names in written reports and products
+source: ICS-630-01 Annex P
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Azeri person 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 Azeri 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-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. For example:
+  Rashad Sadykhov (also seen as Rashad Sadigov, Рашад Садыхов). 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 Azeri-speaking community, use the
+  relevant IC transliteration standard for names from that language (e.g., 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 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 of
+  diacritics. However, within the context of a report, where additional information about the
+  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:
+  - Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,
+    (e.g. 's' followed by 'h').
+  - The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration.
+
+tests:
+  - source: Рашад Садыхов
+    expected: Rashad Sadykhov
+
+map:
+  rules:
+    # note[1]
+    - pattern: "(?i)(\u0492|\u0401|\u0416|\u0425|\u0427|\u0428|\u0429|\u042E|\u042F)\\1(?-i)"
+      result: "\\1"
+    # note[3]
+    - pattern: \u044A|\u044C
+      result: ""
+
+  characters:
+    '\u0410': 'A'      # А
+    '\u0411': 'B'      # Б
+    '\u0412': 'V'      # В
+    '\u0413': 'G'      # Г
+    '\u049C': 'G'      # Ҝ
+    '\u0492': 'Gh'     # Ғ
+    '\u0414': 'D'      # Д
+    '\u0415': 'E'      # Е
+    '\u0401': 'Yo'     # Ё
+    '\u04D8': 'A'      # Ә
+    '\u0416': 'Zh'     # Ж
+    '\u0417': 'Z'      # З
+    '\u0418': 'I'      # И
+    '\u0419': 'Y'      # Й
+    '\u0408': 'Y'      # Ј
+    '\u041A': 'K'      # К
+    '\u041B': 'L'      # Л
+    '\u041C': 'M'      # М
+    '\u041D': 'N'      # Н
+    '\u041E': 'O'      # О
+    '\u04E8': 'O'      # Ө
+    '\u041F': 'P'      # П
+    '\u0420': 'R'      # Р
+    '\u0421': 'S'      # С
+    '\u0422': 'T'      # Т
+    '\u0423': 'U'      # У
+    '\u04AE': 'U'      # Ү
+    '\u0424': 'F'      # Ф
+    '\u0425': 'Kh'     # Х
+    '\u04BA': 'H'      # Һ
+    '\u0427': 'Ch'     # Ч
+    '\u04B8': 'J'      # Ҹ
+    '\u0428': 'Sh'     # Ш
+    '\u0429': 'Shch'   # Щ
+    '\u042B': 'Y'      # Ы
+    '\u042D': 'E'      # Э
+    '\u042E': 'Yu'     # Ю
+    '\u042F': 'Ya'     # Я
+
+    '\u0430': 'a'      # а
+    '\u0431': 'b'      # б
+    '\u0432': 'v'      # в
+    '\u0433': 'g'      # г
+    '\u049D': 'g'      # ҝ
+    '\u0493': 'gh'     # ғ
+    '\u0434': 'd'      # д
+    '\u0435': 'e'      # e
+    '\u0451': 'yo'     # ё
+    '\u04D9': 'a'      # ә
+    '\u0436': 'zh'     # ж
+    '\u0437': 'z'      # з
+    '\u0438': 'i'      # и
+    '\u0439': 'y'      # й
+    '\u0458': 'y'      # ј
+    '\u043A': 'k'      # к
+    '\u043B': 'l'      # л
+    '\u043C': 'm'      # м
+    '\u043D': 'n'      # н
+    '\u043E': 'o'      # о
+    '\u04E9': 'o'      # ө
+    '\u043F': 'p'      # п
+    '\u0440': 'r'      # р
+    '\u0441': 's'      # с
+    '\u0442': 't'      # т
+    '\u0443': 'u'      # у
+    '\u04AF': 'u'      # ү
+    '\u0444': 'f'      # ф
+    '\u0445': 'kh'     # х
+    '\u04BB': 'h'      # һ
+    '\u0447': 'ch'     # ч
+    '\u04B9': 'j'      # ҹ
+    '\u0448': 'sh'     # ш
+    '\u0449': 'shch'   # щ
+    '\u044B': 'y'      # ы
+    '\u044D': 'e'      # э
+    '\u044E': 'yu'     # ю
+    '\u044F': 'ya'     # я

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

@@ -0,0 +1,148 @@
+---
+authority_id: odni
+id: 2015
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Belarusian Personal Names 2015, ICS 630-01 Annex B
+# url:
+source: ICS 630-01, Annex B
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of Belarusian
+  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 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
+  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 Belarusian-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
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name
+
+notes:
+
+tests:
+  - source: Міхаіл
+    expected: Mikhail
+  - source: Беларусь
+    expected: Byelarus
+  - source: Кастусь Каліноўскі
+    expected: Kastus Kalinowski
+  - source: Васіль Быкау
+    expected: Vasil Bykau
+  - source: Янка Купала
+    expected: Yanka Kupala
+  - source: Маланка
+    expected: Malanka
+  - source: Пакаранне
+    expected: Pakarannye
+  - source: Бэз
+    expected: Bez
+  - source: Чабор
+    expected: Chabor
+  - source: |
+      Дзяўчына, дзяўчыначка пасярод гісторыі
+      З прастадушнай шчырасьцю глядзіць на тэрыторыю.
+      У вакне заўсёды звыклая выява:
+      Шэры двор, шэры слуп, на слупе аб'явы.
+    expected: |
+      Dzyawchyna, dzyawchynachka pasyarod historyi
+      Z prastadushnay shchyrastsyu hlyadzits na terytoryyu.
+      U vaknye zawsyody zvyklaya vyyava:
+      Shery dvor, shery slup, na slupye abyavy.
+
+map:
+  characters:
+    '\u0027' : ''   # '
+
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'H'  # Г
+    '\u0490' : 'G'  # Ґ
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'Ye' # Е
+    '\u0401' : 'Yo' # Ё
+    '\u0416' : 'Zh' # Ж
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : 'Y'  # Й
+    '\u041A' : 'K'  # К
+    '\u041B' : 'L'  # Л
+    '\u041C' : 'M'  # М
+    '\u041D' : 'N'  # Н
+    '\u041E' : 'O'  # О
+    '\u041F' : 'P'  # П
+    '\u0420' : 'R'  # Р
+    '\u0421' : 'S'  # С
+    '\u0422' : 'T'  # Т
+    '\u0423' : 'U'  # У
+    '\U040E' : 'W'  # Ў
+    '\u0424' : 'F'  # Ф
+    '\u0425' : 'Kh' # Х
+    '\u0426' : 'Ts' # Ц
+    '\u0427' : 'Ch' # Ч
+    '\u0428' : 'Sh' # Ш
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : ''   # Ь
+    '\u042D' : 'E'  # Э
+    '\u042E' : 'Yu' # Ю
+    '\u042F' : 'Ya' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'h'  # г
+    '\u0491' : 'g'  # ґ
+    '\u0434' : 'd'  # д
+    '\u0435' : 'ye' # е
+    '\u0451' : 'yo' # ё
+    '\u0436' : 'zh' # ж
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : 'y'  # й
+    '\u043A' : 'k'  # к
+    '\u043B' : 'l'  # л
+    '\u043C' : 'm'  # м
+    '\u043D' : 'n'  # н
+    '\u043E' : 'o'  # о
+    '\u043F' : 'p'  # п
+    '\u0440' : 'r'  # р
+    '\u0441' : 's'  # с
+    '\u0442' : 't'  # т
+    '\u0443' : 'u'  # у
+    '\u045E' : 'w'  # ў
+    '\u0444' : 'f'  # ф
+    '\u0445' : 'kh' # х
+    '\u0446' : 'ts' # ц
+    '\u0447' : 'ch' # ч
+    '\u0448' : 'sh' # ш
+    '\u044B' : 'y'  # ы
+    '\u044c' : ''   # Ь
+    '\u044D' : 'e'  # э
+    '\u044E' : 'yu' # ю
+    '\u044F' : 'ya' # я

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

@@ -0,0 +1,96 @@
+---
+authority_id: odni
+id: 2015
+language: bul
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Bulgarian Personal Names 2015, ICS-630-01 Annex O
+# url:
+source: ICS-630-01 Annex O
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community standard for the transliteration of Bulgarian person
+  names that will be applied to all final written reports and products for IC consumers. This
+  standard matches both the Bulgarian national standard adopted in 2009 and the Board of
+  Geographic Names / Permanent Committee on Geographic Names standard adopted in 2013. 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 Bulgarian 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-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. For example: Dobri
+  Hristov (also seen as Dobri Khristov, Добри Христов). 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 Bulgarian-speaking community, use
+  the relevant IC transliteration standard for names from that language (e.g., 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
+  of diacritics. However, within the context of a report, where additional information about the
+  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:
+  - Transliterate double digraphs as a single digraph i.e. шш -> sh, not shsh
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters (e.g. 's' followed by 'h').
+
+tests:
+
+  - source: Добри Христов
+    expected: Dobri Khristov
+  - source: болгарица
+    expected: bolgaritsa
+  - source: български език
+    expected: balgarski ezik
+  - source: българска азбука
+    expected: balgarska azbuka
+  - source: градъ
+    expected: grad
+  - source: аз държа
+    expected: az darzha
+  - source: Ядеш хляба с чубрица
+    expected: Yadesh khlyaba s chubritsa
+
+
+  # note[1]
+  - source: шш
+    expected: sh
+  - source: ччччч
+    expected: ch
+
+map:
+  inherit: bgnpcgn-bul-Cyrl-Latn-2013
+
+  rules:
+    # note[1]
+    - pattern: "(.)\\1{1,}"
+      result: "\\1"
+
+    - pattern: \u042C# # Ь
+      result: "Y"
+
+    - pattern: \u042A # Ъ
+      result: "A"
+
+    - pattern: \u044C # ь
+      result: "y"
+
+    - pattern: \u044A # ъ
+      result: "a"

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"