interscript-maps 2.4.3 → 2.5.0

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

@@ -0,0 +1,165 @@
+system "ODNI:tuk-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:tuk
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Turkmen Personal Names (2015)
+  source ICS-630-01 Annex T
+  creation_date 2015
+  confirmation_date 2015
+  description {    This system is the Intelligence Community standard for the transliteration of Turkmen 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 Turkmen 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:
+    Azat Muhadov (also seen as Azat Muhadow, Азат Мухадов). 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 Turkmen-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 {
+    note "Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh"
+    note "In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters, (e.g. 's' followed by 'h')."
+    note "The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration."
+  }
+}
+
+tests {
+   "Акгюль" ->  "Akgyul"
+   "Акгыз" ->  "Akgyz"
+   "Арсланбек" ->  "Arslanbek"
+   "Берди" ->  "Berdi"
+   "Дидар" ->  "Didar"
+   "Гөзел" ->  "Gozel"
+   "Гуля" ->  "Gulya"
+   "Гюля" ->  "Gyulya"
+   "Мәхри" ->  "Mahri"
+   "Майса" ->  "Maysa"
+   "Мырат" ->  "Myrat"
+   "Өвез" ->  "Ovez"
+   "Рашит" ->  "Rashit"
+   "Сапармырат" ->  "Saparmyrat"
+}
+
+stage main {
+
+  # RULES
+  sub "шш" "sh"
+  sub "Шш" "Sh"
+  sub "ШШ" "SH"
+  sub "шШ" "sH"
+  sub {
+    from any("Ьь")
+    to none
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0496" "J"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u04A2" "Ng"
+    sub "\u041E" "O"
+    sub "\u04E8" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "H"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u0429" "Shch"
+    sub "\u042B" "Y"
+    sub "\u042D" "E"
+    sub "\u04D8" "A"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0497" "j"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u04A3" "ng"
+    sub "\u043E" "o"
+    sub "\u04E9" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04AF" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "h"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u0449" "shch"
+    sub "\u044B" "y"
+    sub "\u044D" "e"
+    sub "\u04D9" "a"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

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

@@ -0,0 +1,181 @@
+system "ODNI:uig-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:uig
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Uyghur Personal Names (2015)
+  source ICS-630-01 Annex U
+  creation_date 2015
+  confirmation_date 2015
+  description {    This system is the Intelligence Community standard for the transliteration of Uyghur 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 Uyghur 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 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.
+    For example: Zordun Sabir (also seen as Zordun Sabeer, Зордун Сабир ,زوردون سابیر). 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 Uyghur-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 {
+    note "Transliterate double digraphs as a single digraph, i.e. шш -> sh, not shsh"
+    note "In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters,\n (e.g. 's' followed by 'h')."
+    note "The Cyrillic ъ and ь are not transliterated, but instead are left out of the transliteration."
+  }
+}
+
+tests {
+   "Зордун Сабир" ->  "Zordun Sabir"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  # generated with: "ҒЁҖҢЧШЮЯ".split("").each { |i| puts %{sub capture(any("#{i}#{i.downcase}"))+any("#{i}#{i.downcase}"), ref(1)} }
+  sub {
+    from capture(any("Ғғ")) + any("Ғғ")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Ёё")) + any("Ёё")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Җҗ")) + any("Җҗ")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Ңң")) + any("Ңң")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Чч")) + any("Чч")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Шш")) + any("Шш")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Юю")) + any("Юю")
+    to ref(1)
+  }
+  sub {
+    from capture(any("Яя")) + any("Яя")
+    to ref(1)
+  }
+  # note[3]
+  sub {
+    from any("\u044A\u044C")
+    to none
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u04D8" "E"
+    sub "\u0411" "B"
+    sub "\u0412" "W"
+    sub "\u0413" "G"
+    sub "\u0492" "Gh"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "J"
+    sub "\u0496" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u049A" "Q"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u04A2" "Ng"
+    sub "\u041E" "O"
+    sub "\u04E8" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "U"
+    sub "\u0424" "F"
+    sub "\u0425" "X"
+    sub "\u04BA" "H"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u04D9" "e"
+    sub "\u0431" "b"
+    sub "\u0432" "w"
+    sub "\u0433" "g"
+    sub "\u0493" "gh"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "j"
+    sub "\u0497" "zh"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u049B" "q"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u04A3" "ng"
+    sub "\u043E" "o"
+    sub "\u04E9" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04AF" "u"
+    sub "\u0444" "f"
+    sub "\u0445" "x"
+    sub "\u04BB" "h"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

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

@@ -0,0 +1,140 @@
+system "ODNI:ukr-Cyrl:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name ICS-630-01 Romanization of Ukrainian Personal Names (2015)
+  source ICS-630-01 Annex M
+  creation_date 2015
+  confirmation_date 2015
+  description {    This system is the Intelligence Community (IC) standard for the
+    transliteration of Ukrainian 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 Ukrainian that can then be linked to
+    forensic information in ways that will help identify the referent of
+    the name.
+  }
+}
+
+tests {
+   "Андрій" ->  "Andriy"
+   "Борисенко" ->  "Borysenko"
+   "Володимир" ->  "Volodymyr"
+   "Богдан" ->  "Bohdan"
+   "Згурський" ->  "Zhurskyy"
+   "Дмитро" ->  "Dmytro"
+   "Олег" ->  "Oleh"
+   "Гаєвич" ->  "Hayevych"
+   "Жанна" ->  "Zhanna"
+   "Казимирчук" ->  "Kazymyrchuk"
+   "Михайленко" ->  "Mykhaylenko"
+   "Іващенко" ->  "Ivashchenko"
+   "Олексій" ->  "Oleksiy"
+   "Коваленко" ->  "Kovalenko"
+   "Леонід" ->  "Leonid"
+   "Маринич" ->  "Marynych"
+   "Наталія" ->  "Nataliya"
+   "Онищенко" ->  "Onyshchenko"
+   "Петро" ->  "Petro"
+   "Рибчинський" ->  "Rybchynskyy"
+   "Соломія" ->  "Solomiya"
+   "Троць" ->  "Trots"
+   "Уляна" ->  "Ulyana"
+   "Філіпчук" ->  "Filipchuk"
+   "Христина" ->  "Khrystyna"
+   "Стеценко" ->  "Stetsenko"
+   "Шевченко" ->  "Shevchenko"
+   "Гаращенко" ->  "Harashchenko"
+   "Юрій" ->  "Yuriy"
+   "Ярошенко" ->  "Yaroshenko"
+   "Костянтин" ->  "Kostyantyn"
+   "Новофедорівка" ->  "Novofedorivka"
+   "Гуляйгородок" ->  "Hulyayhorodok"
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from boundary + "\u2019" + boundary
+    to none
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "H"
+    sub "Ґ" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Є" "Ye"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "Y"
+    sub "І" "I"
+    sub "Ї" "Yi"
+    sub "Й" "Y"
+    sub "К" "K"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Щ" "Shch"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "Ь" ""
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "h"
+    sub "ґ" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "є" "ye"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "y"
+    sub "і" "i"
+    sub "ї" "yi"
+    sub "й" "y"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "щ" "shch"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "ь" ""
+  }
+
+}
+}

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

@@ -0,0 +1,179 @@
+system "ODNI:urd-Arab:Latn:2015" {
+
+metadata {
+  authority_id odni
+  id 2015
+  language iso-639-2:urd
+  source_script Arab
+  destination_script Latn
+  name ICS-630-01 Romanization of Hindi and Urdu Personal Names (2015)
+  source ICS-630-01 Annex F
+  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 {
+
+    note "      Long/Short Vowels: Long and short vowels are not distinguished in the system:\n      The borrowed Arabic name Samir could represent two distinct names, one with a\n      long /a/ (Saamir) and one with a long /i/ (Samiir). One solution would be to use\n      /ee/ to stand for the long /i/, as is often done (Sameer). The IC Standard will not\n      distinguish between these."
+
+    note "      No distinction is made between: retroflex and non-retroflex consonants; and\n      nasalized vowels and vowels followed by /n/."
+    note "      No distinction is made between the several Arabic letters with the same phonetic\n      value in Urdu: e.g., letters sin/svad, zal/ze/zoe."
+    note "      A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,\n      Hindi qa and ka)."
+    note "      A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants\n      (e.g., /dh/), with the exception of ch/chh, both represented by /ch/."
+    note "      Double consonants: Double consonants represented by the tashdid (shaddah) are\n      shown in most cases (e.g., Hassan, Muhammad). Exceptions: consonants\n      represented by digraphs are not doubled (e.g., Mubashir [not Mubashshir])."
+    note "      Hamzah (glottal stop) and ayn: Unlike in the Arabic IC Standard, these are not\n      represented in the IC standard."
+    note "      Digraphs: No distinction is made between digraphs such as /sh/ and single\n      contiguous letters such as /s/ followed by /h/."
+    note "      Arabic definite article “al” (‘the’): Shows sun letter assimilation in the\n      Romanized form (e.g., Abdur Rahman rather than Abdal Rahman, rather than\n      Arabic IC standard 'Abd al-Rahman)."
+    note "      Special Rules\n      - |\n        Hyphens: Hyphens (-) are NOT used to connect name elements within a name:\n        Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in\n        noun-link-modifier construction of Persian origin), which does show a hyphen\n        before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e\n        xx” (‘Army of xx’ construction).\n      - |\n        Names incorporating “din” are written as one unit: Azermuddin, Badruddin,\n      Faizuddin, Salahuddin.\n      - |\n        Names that incorporate Allah as part of the name show the Arabic grammatical\n        marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).\n      - |\n        Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final\n        consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not\n        Rama Lala).\n      - |\n        As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.\n        Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is\n        transcribed as /w/: Wasim, Walid."
+  }
+}
+
+tests {
+   "وشال ٹھاکر" ->  "ishal tsakr"
+   "حسن محمود" ->  "hasn mhamid"
+   "یوسف خان" ->  "iisf khan"
+   "معین خان" ->  "mein khan"
+   "سعید اجمل" ->  "seid ajml"
+   "انضمام الحق" ->  "anzmam alhaq"
+   "فرہاد رضا" ->  "frahad rza"
+   "وسیم اکرام" ->  "isim akram"
+   "شکیب الحسن" ->  "shkib alhasn"
+   "حسن عبد اللہ" ->  "hasn ebd allah"
+}
+
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+
+
+    sub "\u0622" "a"
+    sub "\u0627" "a"
+    sub "\u06cc" "i"
+    sub "\u0648" "i"
+    sub "\u06d2" "e"
+    sub "\u0650" "e"
+    sub "\u0639" "e"
+    sub "\u06c1" "ah"
+    sub "\u062d" "ha"
+    sub "\u0648\u0670" "a"
+    sub "\u0670" "a"
+    sub "\u0627\u0650" "i"
+    sub "\u0639\u0650" "i"
+    sub "\u064f" "i"
+    sub "\u06d3" "i"
+    sub "\u06c2" "-e"
+    sub "\u06c1\u0650" "o"
+    sub "\u0624" "au"
+
+
+
+    sub "\u06a9" "k"
+    sub "\u0642" "q"
+    sub "\u062e" "kh"
+    sub "\u06af" "g"
+    sub "\u063a" "gh"
+    sub "\u0686" "ch"
+    sub "\u062c" "j"
+
+    sub "\u0632" "z"
+    sub "\u0630" "z"
+    sub "\u0636" "z"
+    sub "\u0638" "z"
+    sub "\u0698" "zh"
+
+
+    sub "\u0679" "t"
+    sub "\u0688" "d"
+    sub "\u062f" "d"
+    sub "\u0691" "r"
+    sub "\u062a" "t"
+    sub "\u0637" "t"
+    sub "\u0646" "n"
+    sub "\u06ba" "n"
+
+
+    sub "\u067e" "p"
+    sub "\u0641" "f"
+    sub "\u0628" "b"
+    sub "\u0645" "m"
+    sub "\u0631" "r"
+    sub "\u0644" "l"
+    sub "\u0634" "sh"
+    sub "\u0633" "s"
+    sub "\u062b" "s"
+    sub "\u0635" "s"
+    sub "\u0621" ""
+    sub "\u06be" "s"
+    sub "\u064b" "n"
+    sub "\u064e" "n"
+    sub "\u0652" ""
+    sub "\u0651" ""
+  }
+
+}
+
+}