interscript 0.1.3 → 0.1.9

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

@@ -0,0 +1,63 @@
+---
+authority_id: mvd
+id: 2010
+language: iso-639-2:bel
+source_script: Cyrl
+destination_script: Latn
+name: |
+  8/22721 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
+
+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,
+  invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+
+notes:
+  - |
+    It is not allowed to use in the spelling of the surname, own name superscripts, punctuation, except
+    for the use of the apostrophe in Belarusian and Latin spelling.
+  - The Belarusian letter "Г" is written as the Latin "H"
+
+tests:
+  - source: Бабрыковіч Аляксандр
+    expected: Babrykovich Aliaksandr
+  - source: Міховіч Марыя
+    expected: Mikhovich Maryia
+  - source: Максім
+    expected: Maksim
+  - source: Іван
+    expected: Ivan
+  - source: СВЯТЛАНА
+    expected: SVIATLANA
+  - source: Ігар
+    expected: Ihar
+  - source: МІХАІЛ
+    expected: MIKHAIL
+
+map:
+  inherit: "mvd-bel-Cyrl-Latn-2008"
+
+  rules:
+    # note[5]
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u044C # ь after consonants
+      result: "\\1"
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u02B9 # Ь after consonants
+      result: "\\1"
+    # Й at end
+    - pattern: (?<=[ЕеЁёЫыЮюЯя])\u0419$ # Я after vowels
+      result: ""
+    - pattern: (?<=[ЕеЁёЫыЮюЯя])\u0439$ # я after vowels
+      result: ""
+
+  characters:
+    '\u0413' : 'H'  # Г
+    '\u0433' : 'h'  # г
+
+    '\u042C' : ''  # Ь
+    '\u044C' : ''  # ь

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

@@ -0,0 +1,109 @@
+---
+authority_id: mvd
+id: 2008
+language: iso-639-2:rus
+source_script: Cyrl
+destination_script: Latn
+name: 8/19678 On approval of the Instructions for transliteration of surnames and proper names of citizens of the Republic of Belarus when their personal data is included in the population register
+url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+creation_date: 2008
+
+notes:
+  - check notes from mvd-bel-Cyrl-Latn-2008
+
+tests:
+  - source: Ева
+    expected: Eva
+  - source: Васiльева
+    expected: Vasiĺeva
+  - source: Адъютантов
+    expected: Adjutantov
+
+map:
+  rules:
+    # note[5]
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u044C # ь after consonants
+      result: "\\1\u0301"
+    - pattern: (?<=[ЗзЛлНнСсЦц])\u02B9 # Ь after consonants
+      result: "\\1\u0301"
+    - pattern: ([’Ъъ]\u042E)
+      result: Ju
+    - pattern: ([’Ъъ]\u044E)
+      result: ju
+    - pattern: ([’Ъъ]\u042F)
+      result: Ja
+    - pattern: ([’Ъъ]\u044F)
+      result: ja
+
+  characters:
+    '’' : 'j'
+
+    '\u0410' : 'A'  # А
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'G'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'E'  # Е
+    '\u0401' : 'E'  # Ё
+    '\u0416' : 'Zh' # Ж
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : "J"  # 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
+    '\u0429' : 'Shch' # Щ
+    '\u042A' : 'J'  # Ъ
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : ''   # Ь
+    '\u042D' : 'E'  # Э
+    '\u042E' : 'Iu' # Ю
+    '\u042F' : 'Ia' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'g'  # г
+    '\u0434' : 'd'  # д
+    '\u0435' : 'e'  # е
+    '\u0451' : 'e'  # ё
+    '\u0436' : 'zh' # ж
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : 'j'  # 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
+    '\u0449' : 'shch' # щ
+    '\u044A' : 'j'  # ъ
+    '\u044B' : 'y'  # ы
+    '\u044C' : ''   # ь
+    '\u044D' : 'e'  # э
+    '\u044E' : 'iu' # ю
+    '\u044F' : 'ia' # я

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

@@ -0,0 +1,37 @@
+---
+authority_id: mvd
+id: 2010
+language: iso-639-2: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,
+  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
+
+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,
+  invalidation, seizure, storage and destruction of a passport of a citizen of the Republic of Belarus
+
+notes:
+  - check notes from mvd-rus-Cyrl-Latn-2008
+
+tests:
+  - source: Ева
+    expected: Eva
+  - source: Васiльева
+    expected: Vasileva
+  - source: Адъютантов
+    expected: Adjutantov
+
+map:
+  inherit: "mvd-rus-Cyrl-Latn-2008"
+
+  postrules:
+    - pattern: \u0301 # remove diacritics
+      result: ""

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

@@ -0,0 +1,137 @@
+---
+authority_id: odni
+id: 2004
+language: ics-630-01:ara
+source_script: Arab
+destination_script: Latn
+name: Arabic Personal Names Office of the Director Of National Intelligence 2004 System
+url: https://github.com/interscript/interscript-private-references/blob/master/odni/Arabic_IC_Standard.doc
+creation_date: 2004
+confirmation date: 2004-06
+description:
+notes:
+  - Long/Short Vowels Long and short vowels are not
+    distinguished in this system Samir (could be Saamir or
+    Samiir in Arabic).
+
+  - Double consonants Double consonants represented by the
+    Arabic shaddah are shown in most cases (e.g., Hassan,
+    Muhammad). Exceptions ’ayn and consonants represented by
+    digraphs are not doubled (e.g., al-Qadhafi [not
+    alQadhdhafi], Mubashir [not Mubashshir]).
+
+  - Hamzah (glottal stop) The hamzah is represented by an
+    apostrophe (’). Note that this is the same symbol used to
+    represent another consonant, the ’ayn.
+
+  - Ta’ marbutah (feminine ending marker) On the construct
+    form or when pronounced “t”, it is represented with a roman
+    t. In all other cases, it is represented with an h.
+
+  - Digraphs No distinction is made between digraphs such as
+    sh and single contiguous letters (e.g., s followed by h).
+
+  - Definite article “al” (‘the’) Follows Arabic spelling
+    rather than pronunciation. That is, sun letter assimilation
+    is not shown in the Romanized form (e.g., ’Abd-alRahman,
+    not ’Abd-ar-Rahman).
+
+  - Diphthongs the second element of the diphthong is
+    represented by a y or a w (rather than an i or a u)
+    Haytham, Faysal, Tawfiq, Rawdah.
+
+  - Hyphens Hyphens (-) are used to connect name elements
+    within a name ’Abd- al Rahman, Abu-al-Bashar, Bin-Ladin.
+    Exceptions Names that incorporate “Allah” as part of the
+    name (e.g., ’Abdallah, Nasrallah), names marked by the
+    lineage/family marker “Al” (e.g., Al Thani) are not
+    hyphenated.
+
+  - The definite article, “al”, within name phrases, is
+    Romanized as al and not as ul Nur-al-Din (not Nur-ul-Din).
+    It is not capitalized when name-initial.
+
+  - Names that incorporate Allah as part of the name retain the
+    a of Allah rather than a grammatical marker u ’Abdallah (
+    not ’Abdullah).
+
+  - Foreign names borrowed or appearing in Arabic are spelled
+    according to the standard Western tradition Georges,
+    Michel. However, names of non-Arabic origin no longer
+    considered foreign by Arabic speakers follow the IC
+    conventions Butrus (not Peter).
+
+  - Prefix ‫بن‬ (bin ‘son of’) is Romanized Bin unless written
+    with an alif, in which case it is Romanized as Ibn. The
+    colloquial form Bu (‘father’) should not be standardized as
+    Abu. These prefixes are capitalized.
+
+  - In general, Romanization follows the Modern Standard
+    Arabic (MSA) form rather than local pronunciation
+    standards. For example, the letter ‫ج‬ (jim) is represented
+    as a j even when pronounced as a “g” (e.g., Egyptian Gamal
+    is Romanized as Jamal).
+
+tests:
+
+  - source: مِصر
+    expected: Miṣr
+
+  - source: قَطَر
+    expected: Qaṭar
+
+  - source: المَغرِب
+    expected: Al Maghrib
+
+  - source: الجُمهُورِيَّة العِراقِيَّة
+    expected: Al Jumhuriyah al ’Iraqiyah
+
+  - source: جُمهُورِيَّة العِراق
+    expected: Jumhuriyat al ’Iraq
+
+  - source: جُمهُورِيَّة مِصر العَرَبِيَّة
+    expected: Jumhuriyat Miṣr al ’Arabiyah
+
+  - source: بَغداد
+    expected: Baghdad
+
+  - source: تُونِس
+    expected: Tunis
+
+  - source: حَسّان
+    expected: Hassan
+
+  - source: مُحَمَّد
+    expected: Muhammad
+
+  - source: القَذَّافِي
+    expected: Al Qadhafi
+
+  - source: مُبَشِّر
+    expected: Mubashir
+
+  - source: الجَزائِر
+    expected: Al Jaza’ir
+
+  - source: عَبدالرَحمَن
+    expected: ’Abd al Rahman
+
+  - source: هَيْثَم
+    expected: Haytham
+
+  - source: فَيْصَل
+    expected: Fayṣal
+
+  - source: تَوْفِيق
+    expected: Tawfiq
+
+  - source: رَوْضَة
+    expected: Rawḍah
+
+  - source: نُورُالدِين
+    expected: Nur al Din
+
+  - source: عَبدُاللَّه
+    expected: ’Abdallah
+map:
+  inherit: odni-ara-Arab-Latn-2015

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

@@ -0,0 +1,315 @@
+---
+authority_id: odni
+id: 2017
+language: ics-630-01:ara
+source_script: Arab
+destination_script: Latn
+name: Office of the Director Of National Intelligence Arabic Personal Names 2015 System
+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
+description: |
+  This system, adapted from the Board on Geographic Names, is
+  the Intelligence Community (IC) standard for the
+  transliteration of Arabic 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
+  modern standard Arabic that can then be linked to forensic
+  information in ways that will help identify the referent of
+  the name. Ambiguities can result from the Romanization of
+  Arabic names because the Arabic source generally omits
+  short vowel markings, double consonant marks, and other
+  diacritics that would clearly distinguish the name.
+  Linguists use their experience with the language and aids
+  such as on-line tools and name dictionaries to determine
+  the exact Arabic and the appropriate transliteration into
+  the Roman alphabet. 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 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 Arabic-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 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 plus the apostrophe. 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: |
+  - Long/Short Vowels: Long and short vowels are not
+  distinguished in this system Samir (could be Saamir or
+  Samiir in Arabic).
+
+  - Double consonants: Double consonants represented by the
+  Arabic shaddah are shown in most cases (e.g., Hassan,
+  Muhammad). Exceptions: ’ayn and consonants represented by
+  digraphs are not doubled (e.g., al-Qadhafi [not
+  alQadhdhafi], Mubashir [not Mubashshir]).
+
+  - Hamzah (glottal stop): The hamzah is represented by an
+  apostrophe (’). Note that this is the same symbol used to
+  represent another consonant, the ’ayn.
+
+  - Ta’ marbutah (feminine ending marker): On the construct
+  form or when pronounced “t”, it is represented with a roman
+  t. In all other cases, it is represented with an h.
+
+  - Digraphs: No distinction is made between digraphs such as
+  sh and single contiguous letters (e.g., s followed by h).
+
+  - Definite article “al” (‘the’): Follows Arabic spelling
+  rather than pronunciation. That is, sun letter assimilation
+  is not shown in the Romanized form (e.g., ’Abd-alRahman,
+  not ’Abd-ar-Rahman).
+
+  - Diphthongs: the second element of the diphthong is
+    represented by a y or a w (rather than an i or a u):
+    Haytham, Faysal, Tawfiq, Rawdah.
+
+  - Hyphens: Hyphens (-) are used to connect name elements
+    within a name: ’Abd- al Rahman, Abu-al-Bashar, Bin-Ladin.
+    Exceptions: Names that incorporate “Allah” as part of the
+    name (e.g., ’Abdallah, Nasrallah), names marked by the
+    lineage/family marker “Al” (e.g., Al Thani) are not
+    hyphenated.
+
+  - The definite article, “al”, within name phrases, is
+    Romanized as al and not as ul: Nur-al-Din (not Nur-ul-Din).
+    It is not capitalized when name-initial.
+
+  - Names that incorporate Allah as part of the name retain the
+    a of Allah rather than a grammatical marker u: ’Abdallah (
+    not ’Abdullah).
+
+  - Foreign names borrowed or appearing in Arabic are spelled
+    according to the standard Western tradition: Georges,
+    Michel. However, names of non-Arabic origin no longer
+    considered foreign by Arabic speakers follow the IC
+    conventions: Butrus (not Peter).
+
+  - Prefix ‫بن‬ (bin ‘son of’) is Romanized Bin unless written
+    with an alif, in which case it is Romanized as Ibn. The
+    colloquial form Bu (‘father’) should not be standardized as
+    Abu. These prefixes are capitalized.
+
+  - In general, Romanization follows the Modern Standard
+    Arabic (MSA) form rather than local pronunciation
+    standards. For example, the letter ‫ج‬ (jim) is represented
+    as a j even when pronounced as a “g” (e.g., Egyptian Gamal
+    is Romanized as Jamal).
+
+tests:
+
+  - source: مِصر
+    expected: Miṣr
+
+  - source: قَطَر
+    expected: Qaṭar
+
+  - source: المَغرِب
+    expected: Al Maghrib
+
+  - source: الجُمهُورِيَّة العِراقِيَّة
+    expected: Al Jumhuriyah al ’Iraqiyah
+
+  - source: جُمهُورِيَّة العِراق
+    expected: Jumhuriyat al ’Iraq
+
+  - source: جُمهُورِيَّة مِصر العَرَبِيَّة
+    expected: Jumhuriyat Miṣr al ’Arabiyah
+
+  - source: بَغداد
+    expected: Baghdad
+
+  - source: تُونِس
+    expected: Tunis
+
+  - source: حَسّان
+    expected: Hassan
+
+  - source: مُحَمَّد
+    expected: Muhammad
+
+  - source: القَذَّافِي
+    expected: Al Qadhafi
+
+  - source: مُبَشِّر
+    expected: Mubashir
+
+  - source: الجَزائِر
+    expected: Al Jaza’ir
+
+  - source: عَبدالرَحمَن
+    expected: ’Abd al Rahman
+
+  - source: هَيْثَم
+    expected: Haytham
+
+  - source: فَيْصَل
+    expected: Fayṣal
+
+  - source: تَوْفِيق
+    expected: Tawfiq
+
+  - source: رَوْضَة
+    expected: Rawḍah
+
+  - source: نُورُالدِين
+    expected: Nur al Din
+
+  - source: عَبدُاللَّه
+    expected: ’Abdallah
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'])[\u0061-\uFFFF]
+      result: "upcase"
+    - pattern: " Al " # ال
+      result: " al "
+
+    # don't capitalize defined article in the middle of a sentence
+
+  characters:
+
+    # Tool used for Unicode finding:
+    # https://www.branah.com/unicode-converter
+
+    # pointing
+    '\u064e' : 'a' # َ fatha
+    '\u064e(?=\u0629)' : '' # َ fatha followed by ta' marboota
+    '\u064e(?=a[h|t])' : '' # َ fatha followed by ta' marboota, handling different order of conversion
+    '\u0650' : 'i' # ِ kasra
+    '\u064f' : 'u' # ُ damma
+    '\u0652' : ''  # ْ sokoon, see note A below
+
+
+    '\u0650\u064a' : 'i' # ـِي kasra followed by ي
+    '\u0650\u064a\u0651\u064e' : 'iy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    '\u064f\u0648' : 'u'  # ـُو damma followed by و
+    '\u064e\u0627' : 'a'  # ـَا fatha followed by ا
+    '\u064e\u0649' : 'á'  # ـَى fatha followed by ى which is ا not ي
+    '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+    '\u064e\u064a\u0652' : 'ay'  # ـَيْ
+    '\u0622' : 'a'  # آ
+
+    # ta' marboota
+    '\u0629' : 'at' # ة in the middle of the sentence
+    '\u0629$' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{4})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{5})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{6})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{7})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{8})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{9})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{10})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{11})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{12})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{13})\u0629' : 'ah'
+
+    # shadda
+
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 'th'  # ث
+    '\u062c\u0651' : 'jj'  # ج
+    '\u062d\u0651' : 'hh' # ح
+    '\u062e\u0651' : 'kh'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'dh'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'sh'  # ش
+    '\u0635\u0651' : 'ṣṣ'  # ص
+    '\u0636\u0651' : 'ḍḍ'  # ض
+    '\u0637\u0651' : 'ṭṭ'  # ط
+    '\u0638\u0651' : 'ẓẓ'  # ظ
+    '\u063a\u0651' : 'gh'  # غ
+    '\u0641\u0651' : 'ff'  # ف
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0643\u0651' : 'kk'  # ك
+    '\u0644\u0651' : 'll'  # ل
+    '\u0645\u0651' : 'mm'  # م
+    '\u0646\u0651' : 'nn'  # ن
+    '\u0647\u0651' : 'hh'  # ه
+    '\u0648\u0651' : 'ww'  # و
+    '\u064a\u0651' : 'yy'  # ي
+
+    '\u0626' : "’" # ئ
+
+    '\b\u0627\u0644\u0644\u0651\u064e\u0647': 'Allah'
+
+    '\B\u064f?\u0627\u0644\u0644\u0651\u064e\u0647': 'allah'
+
+    '\u0621' : # ء
+       - '’'
+       - ''
+
+    '\b\u0627\u0644' : 'al '  # ال
+    '\B\u064f?\u0627\u0644' : ' al '  # ال in middle of composite name
+
+    # '\uFE8E' : ''  # ﺎ
+
+
+    '\u0623' : ''  # أ
+    '\b\u0627' : ''  # ا
+    '\u0627' : 'a'  # ا
+    '\u0628' : 'b'  # ب
+    '\u062a' : 't'  # ت
+    '\u062b' : 'th'  # ث
+    '\u062c' : 'j'  # ج
+    '\u062d' : 'h' # ح
+    '\u062e' : 'kh'  # خ
+    '\u062f' : 'd'  # د
+    '\u0630' : 'dh'  # ذ
+    '\u0631' : 'r'  # ر
+    '\u0632' : 'z'  # ز
+    '\u0633' : 's'  # س
+    '\u0634' : 'sh'  # ش
+    '\u0635' : 'ṣ'  # ص
+    '\u0636' : 'ḍ'  # ض
+    '\u0637' : 'ṭ'  # ط
+    '\u0638' : 'ẓ'  # ظ
+    '\u0639' : '’'  # ع
+    '\u063a' : 'gh'  # غ
+    '\u0641' : 'f'  # ف
+    '\u0642' : 'q'  # ق
+    '\u0643' : 'k'  # ك
+    '\u0644' : 'l'  # ل
+    '\u0645' : 'm'  # م
+    '\u0646' : 'n'  # ن
+    '\u0647' : 'h'  # ه
+    '\u0648' : 'w'  # و
+    '\u064a' : 'y'  # ي