interscript 0.1.6 → 0.1.7

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: aze
+language: iso-639-2:aze
 source_script: Cyrl
 destination_script: Latn
 name: Standards for the transliteration of azeri personal names in written reports and products

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: Office of the Director Of National Intelligence Belarusian Personal Names 2015, ICS 630-01 Annex B

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

@@ -1,7 +1,7 @@
 ---
 authority_id: odni
 id: 2015
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: Office of the Director Of National Intelligence Bulgarian Personal Names 2015, ICS-630-01 Annex O
@@ -61,7 +61,7 @@ tests:
     expected: balgarski ezik
   - source: българска азбука
     expected: balgarska azbuka
-  - source: градъ
+  - source: град
     expected: grad
   - source: аз държа
     expected: az darzha

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

@@ -0,0 +1,169 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:che
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence -- ICS 630-01 -- Chechen Cyrillic 2015
+url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20C%20-%20Chechen_Personal_Names_FLTS%20(U).pdf
+source: ICS-630-01 Annex C
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of Chechen 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 Chechen 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 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: Ilyas
+  Akhmadkant (also seen as Ilyas Axmadkhant, Ильяс Ахмадкӏант). 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 Chechen-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 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:
+  - Add a preceding 'y' if the vowel is preceded by the sound of a 'y' consonant.
+  - |
+    This is a single apostrophe as found on regular US keyboards (ASCII character 39),
+    though software may render the apostrophe with differing appearances (e.g. curved left or right).
+    Note that the same apostrophe is used for 'ъ', '|', 'ӏ', and '1'.
+  - A word-initial hard sign 'ъ' is not represented, but instead is left out of the transliteration.
+  - The romanization follows the dialect spoken in Chechnya rather than other local pronunciations.
+  - Long and short vowels are not distinguished in this system.
+  - In the Roman, no distinction is made between digraphs such as 'sh' and single contiguous letters (e.g. 's' followed by 'h').
+  - The Cyrillic soft sign ('ь') by itself (not part of a digraph) is not represented, but instead is left out of the transliteration.
+  - Interpretation of Cyrillic digraphs in Table 1 takes precedence over interpretation of the individual characters. Thus, 'кх' -> 'q', and not to 'k' followed by 'kh'.
+  - Transliteration of Cyrillic digraphs for diphthongs will follow the combination of the transliteration of the individual characters. Thus, 'aй' -> 'ay', 'oй' -> 'oy', and both 'эй' and 'eй' -> 'ey'.
+
+tests:
+  - source: Ильяс Ахмадкӏант
+    expected: Ilyas Akhmadkant
+  - source: Ильяс Ахмадк1ант
+    expected: Ilyas Akhmadkant
+
+map:
+  rules:
+    # note[1]
+    - pattern: (?<!\b\u2019)\b\u0415 # Е in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0435 # е in initial position -> ye
+      result: ye
+    # note[2]
+    - pattern: (\W+)1(\W+)
+      result: "\\1ӏ\\2"
+    - pattern: (\W+)1
+      result: "\\1ӏ"
+    - pattern: 1(\W+)
+      result: "ӏ\\1"
+
+  characters:
+    '\u0410'        : 'A'               # А
+    '\u0411'        : 'B'               # Б
+    '\u0412'        : 'V'               # В
+    '\u0413'        : 'G'               # Г
+    '\u0413\u04C0'  : 'Gh'              # ГӀ
+    '\u0414'        : 'D'               # Д
+    '\u0415'        : 'E'               # Е note[1]
+    '\u0416'        : 'J'               # Ж
+    '\u0417'        : 'Z'               # З
+    '\u0418'        : 'I'               # И
+    '\u0418\u042B'  : 'I'               # ИЙ
+    '\u042B'        : 'Y'               # Й
+    '\u041A'        : 'K'               # К
+    '\u041A\u04C0'  : 'K'               # КӀ
+    '\u041A\u0445'  : 'Q'               # Кх note[8]
+    '\u041A\u044A'  : 'Q'               # Къ
+    '\u041B'        : 'L'               # Л
+    '\u041C'        : 'M'               # М
+    '\u041D'        : 'N'               # Н
+    '\u041E'        : 'O'               # О
+    '\u041F'        : 'P'               # П
+    '\u041F\u04C0'  : 'Ph'              # ПӀ
+    '\u0420'        : 'R'               # Р
+    '\u0421'        : 'S'               # С
+    '\u0422'        : 'T'               # Т
+    '\u0422\u04C0'  : 'T'               # TӀ
+    '\u0423'        : 'U'               # У
+    '\u0424'        : 'F'               # Ф
+    '\u0425'        : 'Kh'              # Х
+    '\u0425\u044C'  : 'H'               # Хь
+    '\u0425\u04C0'  : 'H'               # ХӀ
+    '\u04B8'        : 'Ts'              # Ц
+    '\u04B8\u04C0'  : 'Ts'              # ЦӀ
+    '\u0427'        : 'Ch'              # Ч
+    '\u0427\u04C0'  : 'Ch'              # ЧӀ
+    '\u0428'        : 'Sh'              # Ш
+    '\u042A'        : "'"               # Ъ note[2] note[3]
+    '\u042B'        : 'Е'               # Ы
+    '\u042D'        : 'E'               # Э
+    '\u042E'        : 'Yu'              # Ю
+    '\u042F'        : 'Ya'              # Я
+    '\u04C0'        : "'"               # Ӏ note[2]
+    '\u042C'        : ''                # Ь note[7]
+
+    '\u0430'        : 'a'               # а
+    '\u0431'        : 'b'               # б
+    '\u0432'        : 'v'               # в
+    '\u0433'        : 'g'               # г
+    '\u0433\u04CF'  : 'gh'              # гӏ
+    '\u0434'        : 'd'               # д
+    '\u0435'        : 'e'               # е note[1]
+    '\u0436'        : 'j'               # ж
+    '\u0437'        : 'z'               # з
+    '\u0438'        : 'i'               # и
+    '\u0438\u0439'  : 'i'               # ий
+    '\u0439'        : 'y'               # й
+    '\u043A'        : 'k'               # к
+    '\u043A\u04CF'  : 'k'               # кӏ
+    '\u043A\u0445'  : 'q'               # кх note[8]
+    '\u043A\u044A'  : 'q'               # къ
+    '\u043B'        : 'l'               # л
+    '\u043C'        : 'm'               # м
+    '\u043D'        : 'n'               # н
+    '\u043E'        : 'o'               # о
+    '\u043F'        : 'p'               # п
+    '\u0440'        : 'r'               # р
+    '\u0441'        : 's'               # с
+    '\u0442'        : 't'               # т
+    '\u0442\u04CF'  : 't'               # тӏ
+    '\u0443'        : 'u'               # у
+    '\u0444'        : 'f'               # ф
+    '\u0445'        : 'kh'              # х
+    '\u0445\u044C'  : 'h'               # хь
+    '\u0445\u04CF'  : 'h'               # хӏ
+    '\u04B9'        : 'ts'              # ц
+    '\u04B9\u04CF'  : 'ts'              # цӏ
+    '\u0447'        : 'ch'              # ч
+    '\u0447\u04CF'  : 'ch'              # чӏ
+    '\u0448'        : 'sh'              # ш
+    '\u044A'        : "'"               # ъ note[2] note[3]
+    '\u044B'        : 'e'               # ы
+    '\u044D'        : 'e'               # э
+    '\u044E'        : 'yu'              # ю
+    '\u044F'        : 'ya'              # я
+    '\u04CF'        : "'"               # ӏ note[2]
+    '\u044C'        : ''                # ь note[7]

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

@@ -0,0 +1,406 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:fas
+source_script: Arab
+destination_script: Latn
+name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
+url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+creation_date: 2015
+confirmation_date: 2015-11
+description: |
+  This system is the Intelligence Community (IC) standard for
+  the transliteration of Persian (Farsi)
+  and Dari names that is 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 Persian (Farsi) and Dari 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 Perso-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 while maintaining consistency.
+
+  For names of individuals who are not part of the Persian-(
+  Farsi) or Dari-speaking community,
+  but whose names are encountered in Farsi or Dari, use the
+  relevant IC transliteration standard for
+  names from that language (e.g., Mikhail, Yitzhak, Abu-
+  Murtada). 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
+  online CIA World Factbook and the
+  online directory of Chiefs of State and Cabinet Members of
+  Foreign Governments, the spellings
+  given in these online reference works should be used in
+  place of the IC Standard, with the IC
+  Standard included as a variant in parentheses at the first
+  usage. 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 (e.g., former president Mahmud
+  Ahmadinezhad (Ahmadi-Nejad).
+
+  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 plus the apostrophe and hyphen.
+  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 online tools,
+  name dictionaries, and lists containing
+  conventional spellings of names of well-known individuals.
+
+notes:
+  - |
+    Alef maqsura (final yeh pronounced as a long “a”) should
+    be written “a” as in “Musa.”
+
+  - |
+    Digraphs: No distinction is drawn between digraphs such
+    as sh and single contiguous letters
+    (e.g., s followed by h).
+
+  - |
+    Long/short vowels: There is no distinction made between
+    long and short a. E.g., Farzad (the
+    first a is short, the second long).
+
+  - |
+    Diphthongs: The diphthong such as in the name Hosein is
+    written ei. Following the
+    predominant lack of pronunciation of the ow diphthong in
+    Farsi, this diphthong will not be
+    represented (Khosro, not Khosrow).
+
+  - |
+    Apostrophe: The apostrophe is used in three cases: 1) to
+    represent a name-internal or terminal
+    hamzeh or ein (Mo’men, Ghane’), 2) to represent the first
+    yeh (ی (in a double yeh (یی (
+    construction (since رضایی is simply an orthographic variant
+    of رضائی – both are rendered
+    Reza’i), and 3) to represent the alef (ا (in the special
+    case of a name ending in ای ه) e.g.,
+    Badreh’i, Ganjeh’i). Name-initially, however, neither
+    hamzeh nor ein are indicated in
+    transliteration (Abdorrahman, not 'Abdorrahman).
+
+  - |
+    Double consonants: Double consonants represented by the
+    tashdid are shown by doubling the
+    Roman letter: Mo'azzami, Tavakkoli, Sajjad. Exceptions: Ein
+    and consonants represented by
+    Roman digraphs (e.g., sh, ch) are not doubled (Mobasher,
+    not Mobashsher). Double letters
+    are only used for tashdid (Hosein, not Hossein) or to
+    reflect “sun-letter” assimilation (see
+    below). Special care should be taken when possible to
+    discriminate between doubled and
+    non-doubled letters in names that are otherwise
+    indistinguishable in their transliterated forms:
+    Hasan (حسن (vs. Hassan (حسان(
+
+  - |
+    Hyphens: A hyphen will be used for compound
+    last names to connect major name elements (e.g., Raja’i-
+    Khorasani, Tabataba’i-Shirazi, Soleimani-Meimandi). No
+    spaces are to be used for last names to reduce ambiguity (
+    with the exception of certain Arabic-origin constructions
+    as specified below). Hyphens are not used to attach minor
+    elements and suffixes/prefixes, or to show ezafeh
+    constructions in or between names (Shahrbabak, not Shahr-e
+    Babak). It should be understood that when a full compound
+    last name is available, the second major element is
+    typically omitted for normal use, while the first major
+    element of the last name is preferred. It is thus
+    recommended as a best practice for reporting that both of
+    these names, if known, be included at the first instance,
+    and only the family name be used thereafter in the report (
+    unless it is known that a specific individual is commonly
+    known otherwise). E.g., “Mohammad Mahmudi-Tehrani (
+    hereafter Mahmudi).”
+
+  - |
+    Compound first names will be written as distinct words:
+    Ali Reza (not Alireza or Ali-Reza);
+    Mohammad Hosein (not Mohammadhosein or Mohammad-Hosein),
+    with the exception of cases identified below.
+
+  - |
+    Arabic-origin names that incorporate the word “Allah” are
+    transliterated as one word, with the letter ‘o’ replacing the
+    alef in Allah (Azizollah, Rahimollah).
+
+  - |
+    Name-internal Arabic definite article "al" (‫)ال‬: Common
+    in many names borrowed
+    from Arabic, the transliteration should follow the Arabic
+    rules for “sun letter” assimilation in spoken form and
+    reflect the nominative case. That is: Abdorrahman, not Abd-
+    al-Rahman. (The Arabic sun letters are: ‫ت‬،‫ث‬،‫د‬،‫ذ‬،
+    ‫ر‬، ‫ز‬،‫س‬،‫ش‬،‫ص‬،‫ض‬،‫ط‬،‫ظ‬،‫ل‬،‫ن‬ . These correspond with
+    d, l, n, r, s, sh, t, and z.) Note that the moon letters (
+    i.e., all other Arabic letters) are not assimilated (e.g.,
+    Abdolhasan, Abolfazl). Note also that the “Abdollah” and
+    “Abdol + attribute of Allah” names are written as a single
+    word, as are other names that contain the definite article:
+    Shamsoddin (not Shams-al-Din), Nezamoddin, etc.
+
+  - |
+    Name-initial Arabic definite article "al" (‫)ال‬: For
+    Arabic-origin names starting with the definite article “al” (‫)
+    ال‬, follow the Arabic standard of al-Sisi (‫)الصیصی‬ (not
+    Alsisi or Assisi) and forego sun-letter assimilation.
+
+  - |
+    Arabic "family marker" of Al (‫)آل‬: For Arabic-origin
+    names starting with the "family marker" of Al (‫)آل‬,
+    follow the Arabic standard of Al Davud (‫داود‬ ‫)آل‬ (not
+    Aldavud or Aledavud).
+
+  - |
+    Kunyas: In the rather rare case where
+    a Persian uses a kunya (a name for an adult normally
+    derived from his or her eldest child, and sometimes
+    employed as a nom de guerre), this name will be rendered
+    with a space separating the two elements (Abu Hosein, Abu
+    Ghasem). Note that this does not apply when the person's
+    given or family name was derived from a predecessor's
+    kunya. In these cases, the leading element should be
+    treated as a prefix as indicated below (Abuhosein[i],
+    Abughasem[i]).
+
+  - |
+    Persian names of non-Persian origin that are
+    no longer considered foreign by Farsi speakers (commonly of
+    Arabic or Hebrew origin) follow this IC transliteration
+    standard for Persian. E.g., Yusef (not Joseph), Davud (not
+    David), Reza (not Rida), Abutorab (not Abu-Turab),
+    Abolfazl (not Abu-al-Fadl). However, in the uncommon event
+    the name of an Iranian with a non-Persian name appears in
+    Farsi (possibly as a result of mixed parentage), it is
+    spelled according to the standard Western tradition or the
+    appropriate IC standard: James, Georges, Pedro, Jiang.
+
+tests:
+  - source: مُوسَى
+    expected: musa
+
+  - source: مُؤمِن
+    expected: mo’men
+
+  - source: رِضايي
+    expected: reza’i
+
+  - source: مُبَشِّر
+    expected: mobasher
+
+  - source: حَسَّان
+    expected: hassan
+
+  - source: حَسَن
+    expected: hasan
+
+  - source: صَفَّار
+    expected: saffar
+
+  - source: صَفَر
+    expected: safar
+
+map:
+  characters:
+
+
+
+    # special rules
+
+    '\s(?=\u0622\u0628\u064E\u0627\u062F)': '' # space followed by abad is removed
+    '\ufdf2': 'Allah' # See note 5
+    '\s\u0627\u0644\u0644\u0651\u064e\u0647': 'ollah' # NOTE 9
+
+    '\u0652' : ''  # ْ sokoon
+    '\u0659': 'ê'
+
+    '\u064e\u064a\u0652' : 'ay'  # ـَيْ
+    '\u0649\u0670': 'á' # ىٰ
+    '\u0674': '-e' # ٴ
+    '\u0654': '-e' #  ٔ
+      # - '-ye'
+
+
+    # ta' marboota
+    '\u0629' : 'eh'
+
+
+
+    '\u0626' : '’' # ئ
+    '\u0624' : '’' # ؤ
+    '\u0623' : ''  # أ
+    '\u0625': ''    # إ
+
+    # See note B
+    '\b\u0627\u0644' : 'al '  # ال
+    '\b\u0622\\u0644' : 'Al ' # ‫آل‬
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    '\b\u0627\u0644\u062a' : 'at t'  # الت
+    '\b\u0627\u0644\u062b' : 'as s'  # الث
+    '\b\u0627\u0644\u062f' : 'ad d' # الد
+    '\b\u0627\u0644\u0630' : 'az z'  # الذ
+    '\b\u0627\u0644\u0631' : 'ar r' # الر
+    '\b\u0627\u0644\u0632' : 'az z'  # الز
+    '\b\u0627\u0644\u0633' : 'as s' # الس
+    '\b\u0627\u0644\u0634' : 'ash sh' # الش
+    '\b\u0627\u0644\u0635' : 'as s'  # الص
+    '\b\u0627\u0644\u0636' : 'az z'  # الض
+    '\b\u0627\u0644\u0637' : 'at t'  # الط
+    '\b\u0627\u0644\u0638' : 'az z' # الظ
+    '\b\u0627\u0644\u0644' : 'al l'  # الل
+    '\b\u0627\u0644\u0646' : 'an n'  # الن
+
+    # Farsi Vowel (Pointing)
+    '\u0622' : 'a'  # آ alef maddeh
+    '\u064e' : 'a' # َ fatha
+    '(?<=\u064e)\u0627' : ''  # ا
+    '(?<!\b)\u0627' : 'a'  # ا
+    '\b\u0627\u064e' : 'a' # ا initial followed by fatha
+    '\b\u0627\u064f' : 'o' # ا initial followed by damma
+    '\b\u0627\u0650' : 'e' # ِ ا initial followed by kasra
+
+    '\u064f' : 'o' # damma
+    '\u064f\u0648' : 'u'  # ـُو damma followed by و
+    # '\u064e\u0648' : 'ow'  # ـَو
+    # '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+
+
+    '\u0650' : 'e' # kasra
+    '\u0650\u064a' : 'i' # ـِي kasra followed by ي
+    '\u0650\u06cc' : 'i' # ـِي kasra followed by ي
+    '\u0650\u064a\u0651\u064e' : 'iy' # ـِيَّ
+    '\u0650\u06cc\u0651\u064e' : 'iy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    # '\u064e\u064a' : 'aī'  # ـَي
+    # '\u064e\u06cc' : 'aī'  # ـَي
+    # '\u064e\u0649' : 'ay'  # ـَى fatha followed by ى which is ا not ي
+
+    # additional symbols
+
+    # shadda
+
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 'ss'  # ث
+    '\u062c\u0651' : 'jj'  # ج
+    '\u062d\u0651' : 'hh' # ح
+    '\u062e\u0651' : 'kh'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'zz'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'sh'  # ش
+    '\u0635\u0651' : 'ss'  # ص
+    '\u0636\u0651' : 'zz'  # ض
+    '\u0637\u0651' : 'tt'  # ط
+    '\u0638\u0651' : 'zz'  # ظ
+    '\u063a\u0651' : 'gh'  # غ
+    '\u0641\u0651' : 'ff'  # ف
+    '\u0642\u0651' : 'gh'  # ق
+    '\u0643\u0651' : 'kk'  # ك
+    '\u0644\u0651' : 'll'  # ل
+    '\u0645\u0651' : 'mm'  # م
+    '\u0646\u0651' : 'nn'  # ن
+    '\u0647\u0651' : 'hh'  # ه
+    '\u0648\u0651' : 'vv'  # و
+    '\u064a\u0651' : 'yy'  # ي
+
+    '(?<=\b)\u0621': '' # ء
+    '\u0621': '’' # ء
+
+    # FROM NOTES
+
+    '\u064e\u0649' : 'a'  # ـَى fatha followed by ى which is ا not ي
+    '\u0649' : 'a'  # ى alef maqsura NOTE-1
+
+    '\u064a\u064a' : '’i' # NOTE 4 (2)
+    '\u06cc\u06cc' : '’i'
+
+    '\u0627\u064a\b' : '’i' # NOTE 4 (3)
+    '\u0627\u06cc\b' : '’i'
+
+    # Farsi consonant characters
+
+    '\u0628' : 'b'  # ب
+    '\u067E': 'p' # پ
+    '\u062a' : 't'  # ت
+    # '\u067C': 'ṯ'  # ټ
+    '\u062B': 's'   # ث
+    '\u062c' : 'j'  # ج
+    '\u0686': 'ch'  # ‫چ‬
+
+    # # The variant form ج is seen infrequently and does not have a
+    # # single Unicode encoding.
+    # '\u0681': 'dz' # Note 2 # ‫ځ‬
+
+    # '\u0685': 'ts' # Note 2 # ‫څ
+
+    '\u062d' : 'h' # ح
+    '\u062e' : 'kh'  # خ
+    '\u062f' : 'd'  # د
+    # '\u0689' : 'ḏ' # ‫ډ‬
+    '\u0630' : 'z'  # ذ
+    '\u0631' : 'r'  # ر
+    # '\u0693' : 'ṟ'   # ړ
+    '\u0632' : 'z'  # ز
+    '\u0698' : 'zh'  # ‫ژ‬
+    # '\u0696' : 'z͟h'  # ږ
+    '\u0633' : 's'  # س
+    # '\u069A' : 's͟h'  # ښ
+    '\u0634' : 'sh'  # ش
+    '\u0635' : 's'  # ص
+    '\u0636' : 'z'  # ض
+    '\u0637' : 't'  # ط
+    '\u0638' : 'z'  # ظ
+    '\u0639' : '‘'  # ع
+    '(?<=\b)\u0639' : ''  # ع not represented initially
+    '\u063a' : 'gh'  # غ
+    '\u0641' : 'f'  # ف
+    '\u0642' : 'gh'  # ق
+    '\u0643' : 'k'  # ك
+    # '\u06A9' : 'k' # ک
+    '\u06AF' : 'g' # ‫گ‬
+    '\u0644' : 'l'  # ل
+    '\u0645' : 'm'  # م
+    '\u0646' : 'n'  # ن
+    # '\u06BC' : 'ṉ' # ڼ
+    '\u0647' : 'h'  # ه
+    '\u0648' : 'v'  # و
+    '\u064a' : 'y'  # ي
+    '\u0649' : 'y'  # ي
+    '\u06D0' : 'ē'   # ې
+    '\u06CD' : 'êy'  # ‫ۍ‬