interscript-maps 2.0.5

data/maps/bgnpcgn-prs-Arab-Latn-2007.imp

@@ -0,0 +1,552 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2007
+  language: iso-639-3:prs
+  # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
+  source_script: Arab
+  destination_script: Latn
+  name: BGN/PCGN NATIONAL ROMANIZATION SYSTEM FOR AFGHANISTAN -- BGN/PCGN 2007 System
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693661/ROMANIZATION_FOR_AFGHANISTAN.pdf
+  creation_date: 2007
+  confirmation_date: 2017-11
+  description: |
+    This romanization system agreed by BGN and PCGN in November 2007,
+    accommodates the linguistic complexity of Afghanistan as manifest in
+    its geographical names.
+
+    The following tabulation shows the original Perso-Arabic script with
+    accompanying Unicode value (columns 1a and b), the Yaghoubi
+    romanization (column 2), the BGN/PCGN romanization with accompanying
+    Unicode value (columns 3a and b), an English phonetic example (column
+    4), and an example toponym (columns 5b and c).
+
+    [The Yaghoubi romanization system was developed in 1959 by
+    Muzaffarud Din Yaqubi (commonly seen as Yaghoubi). It is a native
+    official system designed to reflect Afghan names, both Dari and Pashto,
+    and both pronunciation and genuine linguistic truth.]
+
+    The tables function as both a romanization system for Afghanistan (i.e.
+    with access to the original script, these tables can be applied to get
+    a standardized Roman result - moving from columns 1 to 3) and as a
+    means of converting the available Yaghoubi Roman-script spellings, as
+    appear on the Fairchild Aerial Surveys map series, to standard BGN/PCGN
+    spellings (moving from columns 2 to 3).
+
+    The points used in Arabic to mark short vowels and certain other
+    diacritical marks are infrequently written in Afghanistan.
+    Consequently, a reference source may sometimes be required to aid
+    correct identification of the standard spellings and proper vowels and
+    elimination of dialectal and idiosyncratic variations. In the interests
+    of clarity, the example columns show script with vowel pointing from
+    Arabic to indicate the short vowels that are included alongside the
+    unpointed form that will usually be encountered. However it should be
+    noted that the pronunciation of short vowels will vary.
+
+    Note: it is recommended that a font such as Scheherazade, available
+    from www.sil.org, which includes the Unicode extended Arabic sub-range,
+    be used to view this system. [Please note that the identification of a
+    particular font does not represent an endorsement of any specific
+    product or manufacturer.]
+
+  notes:
+    - |
+      Alif (ا) should be romanized as follows:
+
+      a. Initially, it indicates that the word begins with a vowel or
+        diphthong; the alif itself is not romanized, but rather the short vowel
+        it “carries” is romanized; e.g., ميړ أَسَلم ژرَندَه → Mī Aslam Zhrandah
+      b. When it carries a maddah (آ) (see vowel table, row 6), it represents ā; e.g., آب بَند → Āb Band.
+      c. Medially and finally it represents ā (see vowel table, row 5); e.g., ماڼۍ → Māṉêy
+      d. Medially and finally in words of Arabic origin, alif may serve as the bearer of hamzah, e.g. رأس → ra’s.
+
+    - Occasionally the letter sequences سه ,زه ,که, and گه occur without
+      intervening vowels. They may be romanized k·h, z·h, s·h, and g·h in
+      order to differentiate these romanizations from the digraphs kh, zh,
+      sh, and gh, which are used to represent the letters ش ,ژ ,خ, and غ.
+      Additionally, the Pashto letters څ and ځ, routinely romanized ts and
+      dz, may be alternatively romanized s and z تس when for special reasons
+      it is desired that confusion be avoided with the character sequences
+      (ts) and دز (dz), respectively.
+
+    - "The vagaries of written Afghan languages, as pertains to spacing
+      and word division, are addressed as follows:
+      Spaces may be added to or subtracted from Afghan words written in
+      Arabic script, for the purposes of standardization. This is
+      particularly relevant when the words are hand-written, are rendered
+      “art st cally”, or express other s ch non-standard flourishes, as long
+      as the sense of the toponym, word, or phrase is not compromised.
+      Romanized toponyms are typically divided into constituent words
+      (spaces and other grammatical rules applied) when those words can stand
+      independently, for purposes of standardization and minimization of
+      confusion, particularly in situations where Afghan writers are
+      inconsistent in their application of spacing and word breaks. When the
+      Afghan word or suffix is only used in combination with other nouns or
+      adjectives, then it should be appended to the preceding word in its
+      romanization. This includes (but is not limited to) - ābā , -zaī, -zā
+      ah, - ū, -wand, -gaī, -kaī, -pūr, - ēsh, -lar, -lī, -lū and ullāh, as,
+      for example, seen in Raḩmatābād (رحمت آباد) and Raḩmatullāh (رحمت االله),
+      but Raḩmat Khēl (رحمتخيل) and Raḩmat Shahr (رحمتشهر)."
+
+    - The one-letter words د (Pashto) and و (Dari) are romanized dê and
+      wa, respectively.
+
+    - The word الله, meaning God, should always be romanized Allāh,
+      except as specified in note 3. Note that the Unicode value FDF2 spells
+      Allāh, but omits the alif in some common fonts, including Times New
+      Roman. If in doubt, try in Arial Unicode MS to verify. Also note that
+      the “dagger al f” ( ) above the second ل (lām) n the ord الله, is not
+      written but should be romanized ā, like a full-size alif.
+
+    - In names of Arabic origin, the l of the definite article al s ass m
+      lated before the ‘s n letters’ , , , , r, z, s, sh, ş, ẕ, , z, l and n.
+      In its romanization, the article should be separated from the name it
+      precedes and should not be capitalized except at the beginning of a
+      name, e.g. جبل السراج→ Jabal
+      as Sarāj
+
+    - In Arabic names, a shaddah, ّ is used to denote the doubling of a
+      particular consonant character, e.g. ُم َح َمد → Muḩammad. Ho ever, n
+      Pashto th s ‘do bl ng’ s freq ently om tted n both Perso- Arabic script
+      and the resulting romanization. Guidance on doubling may be taken from
+      an authoritative names source, such as an Afghan government source or
+      Pashto dictionary; for example, it is usual to see Ḩājī without and
+      ‘Abbās with the doubled consonant. The doubled y consonant is almost
+      always retained, as in Sayyid or Qayyūm.
+
+    - In Afghan names which contain an iẕāfah, it should be romanized as
+      -e or –ye according to
+      common pronunciation, but generally, -e is used if the preceding word
+      ends with a consonant other
+      than silent heh, and -ye if the preceding word ends with a vowel
+      sound e.g. غر ِحصار → Ghar-e ِ
+      Ḩ şār; َقل َع ٔه َنو → Qal‘ah-ye Now. Scholarly sources indicate that
+      heh is silent in darah and qal‘ah (thus darah-ye, qal‘ah-ye), but
+      lightly spoken in kōh and chāh (thus kōh-e, chāh-e).
+
+    - The character sequence خو, where followed by ا or ی should be
+      romanized khwā or khwī, although the w is either not pronounced, or
+      only weakly so, as in خواجه → khwājah.
+
+    - Plural nouns ending in -hā or -ān should always be romanized as a
+      single word, regardless of whether a space appears in a Perso-Arabic
+      script source.
+
+    - Unicode values listed in the tables above are required to ensure
+      standardization and to minimize confusion from competing
+      representations of a given character. It should be noted that the
+      Persian Unicode value 0643 or FEDA( ك Unicode value 06A9) is
+      recommended rather than the Arabic( ک or FED9), the Persian گ (Unicode
+      value 06AF) is recommended rather than ګ (Unicode value 06AB) or ڰ
+      (Unicode value 06B0) or ك (Unicode value 0643 or FEDA or FED9), and the
+      Pashto character ځ (Unicode value 0681) is recommended rather than the
+      heh with a dot above and a dot below (no Unicode value). For the letter ی
+      in its many variations, care must be exercised to follow this romanization
+      guide's recommendations to eliminate confusion for search engines
+      and software. BGN/PCGN does not use the Unicode encoding FEEF for the
+      character ی in any Afghan word.
+
+    - |
+      An inventory of letter-diacritic combinations in addition to the
+      unmodified letters of the basic Roman script is:
+
+      ‘ (U+2018)
+      Ā (U+0100)
+      Á (U+00C1)
+      Ḏ (U+0044+0031)
+      Ē (U+9112)
+      Ê (U+00CA)
+      Ḩ (U+1E28)
+      Ī (U+012A)
+      N-bar-top (U+004E+0304)
+      Ō (U+014C)
+      R-bar-bottom (U+0052+0031)
+      Ş (U+015E)
+      S-bar-top (U+0053+0304)
+      Ṯ (U+0054+0031)
+      Ţ (U+0162)
+      Ū (U+918A)
+      Z-comma-bottom (U+005A+0327)
+      Z-bar-top (U+005A+0304)
+      Ẕ (U+005A+0331)
+      ẔH (U+005A+0048+035F)
+
+
+      ʼ (U+2019)
+      ā (U+0101)
+      á (U+00E1)
+      ḏ (U+0064+00031)
+      ē (U+0113)
+      ê (U+00EA)
+      ḩ (U+1E29)
+      ī (U+912B)
+      n-bar-top (U+004E+0304)
+      ō (U+014D)
+      r-bar-bottom (U+0072+0031)
+      ş (U+015F)
+      s-bar-top (U+0073+0304)
+      ṯ (U+0074+0031)
+      ţ (U+0163)
+      ū (U+918B)
+      z-comma-bottom (U+007A+0327)
+      z-bar-top (U+007A+0304)
+      ẕ (U+007A+0331)
+      zh-under-bar (U+007A+0068+035F)
+
+
+    - The Romanization columns show only lowercase forms but, when
+      romanizing, uppercase and lowercase Roman letters as appropriate should
+      be used.
+}
+
+tests {
+  test "بَغْلان", "Baghlān"
+  test "پُوټَكَى", "Pōṯakay"
+  test "شِيرِين تَگَاب", "Shīrīn Tagāb"
+  test "کُوْټ", "Kōṯ"
+  test "ثَابِر", "S̄ābir"
+  test "جَلال آبَاد", "Jalālābād"
+  test "چَارِيكَار", "Chārīkār"
+  test "ځَدْرَاڼ", "Dzadrāṉ"
+  test "څَوکۍ", "Tsowkêy"
+  test "حَضْرَتِ إِمَام", "Ḩaẕrat-e Imām"
+  test "خُوْسْت", "Khōst"
+  test "سْپِين بُوْلْدَک", "Spīn Bōldak"
+  test "ډَنْډ وَ پَتَان", "Ḏanḏ Wa Patān"
+  # - source: گُذَرْگَاهٔ نور
+  #   expected: Guz̄argāh-e nūr
+  test "كَنْدَهَار", "Kandahār"
+  test "أَنْدَړ", "Andaṟ"
+  test "كُنْدُز", "Kunduz"
+  test "مِير أَسْلَم ژْرَنْدَه", "Mīr Aslam Zhrandah"
+  test "ږِيرَه", "Z͟hīrah"
+  test "سَمَنْگَان", "Samangān"
+  # - source: مَزَارِ شَريف
+  #   expected: Mazār-e sharīf
+  test "كښٙتَه كَلا", "Ks͟hêtah Kalā"
+  test "قَيْصَار", "Qayşār"
+  test "فَيض آبَاد", "Faīẕābād"
+  test "حَضْرَتِ سُلْطَان", "Ḩaẕrat-e Sulţān"
+  test "ظَاهِر كَلا", "Z̧āhir Kalā"
+  test "پُلِ عَلَم", "Pul-e ‘Alam"
+  test "غَزْنِي", "Ghaznī"
+  test "مَزَارِ شَرِيف", "Mazār-e Sharīf"
+  test "قَيْصَار", "Qayşār"
+  test "كَنْدَهَار", "Kandahār"
+  test "گَرْدېز", "Gardēz"
+  test "کَابُل", "Kābul"
+  test "مَيمَنَه", "Maīmanah"
+  test "خَان آبَاد", "Khānābād"
+  test "مَاڼۍ", "Māṉêy"
+  test "وَاخَان", "Wākhān"
+  # - source: هِرَات
+  #   expected: Herāt
+  test "يَنْگِي قَلعَه", "Yangī Qal‘ah"
+  test "جَلال آبَاد", "Jalālābād"
+  # - source: هِرات پُلِ حِصَار
+  #   expected: Herāt Pul-e Ḩişār
+  test "مُرْغَاب کَابُل", "Murghāb Kābul"
+  test "گٙردُون", "Gêrdōn"
+  test "آب بَنْد", "Āb Band"
+  test "سْپِين بُوْلْدَک", "Spīn Bōldak"
+  # - source: بَالا بُلُوک
+  #   expected: Bālā Bulūk
+  test "جَوزجَان", "Jowzjān"
+  # - source:  غَزْنِى سْپِين
+  #   expected: Ghaznī spīn
+  # - source: ريگ مَيوَنْد
+  #   expected: Maywand, Rēg
+  test "گَرْدېز", "Gardēz"
+  test "مَیدان شَهْر", "Maīdān Shahr"
+  test "ډَنْډِ سُفْلىٰ", "Ḏanḏ-e Suflá"
+  # - source: څَوْکۍ
+  #   expected: Tsowkêy
+  # - source: هَوائِي ډَگَر
+  #   expected: Hawā’ī ḏagar
+  # - source: مَزارِ شَريف
+  #   expected: Mazār-e sharīf
+  # - source: دايکندی
+  #   expected: Dāykundī
+  # - source: زيارت
+  #   expected: Zīārat
+  # - source: غوريان
+  #   expected: Ghōriyān
+  # - source: ميا
+  #   expected: Myā
+  test "جَبَل السَرَاج", "Jabal as Sarāj"
+}
+
+stage {
+  # CHARACTERS
+  parallel {
+
+    # word-medial or word-final form where so appearing in a word.
+    # '\u0627': '-'
+
+    # # Vowel, Diphthong and Diacritical Characters
+
+    # '\u064E': 'a'
+
+    # # Both e and i are available to romanize this short vowel,
+    # # depending on local usage and/or root language. In cases where the sound
+    # # is uncertain, i is the default romanization in BGN/PCGN standardization
+    # # procedures.
+    # '\u0650':
+    #   - 'e'
+    #   - 'i'
+
+    # # Both o and u are available to romanize this short vowel,
+    # # depending on local usage and/or root language. In cases where the sound
+    # # is uncertain, u is the default romanization in BGN/PCGN standardization
+    # # procedures.
+    # '\u064F':
+    #   - 'o'
+    #   - 'u'
+    # '\u0659': 'ê'
+
+    # # An alif with mad ( آ ) is written only in the initial position by
+    # # BGN/PCGN standardization procedures, in keeping with Persian language
+    # # family standards of use of the Arabic alphabet. The same letter written
+    # # in a medial or final position is written . . .
+    # '\u0622': 'ā'
+
+    # pending issue #442
+    # '\u0648': 'ō'
+    # '\u0648': 'ū'
+    # '\u0648': 'ow'
+    # '\u06CC': 'ī'
+
+    # # Or 'ē'. The character ی should be romanized ay or ē according to
+    # # its root language or local pronunciation. In case of uncertainty a
+    # # reference source (such as the Fairchild Aerial Surveys map series, or a
+    # # BGN/PCGN approved policy document/list of recommended spellings) should
+    # # be consulted.
+    # '\u06CC': 'ay'
+    # '\u06D0': 'ē'
+
+    # # Or 'aī'. Both the combination ay and aī are available to romanize
+    # # this character according to its root language or local pronunciation.
+    # # In cases where the sound is uncertain ay is the default romanization in
+    # # BGN/PCGN standardization procedures
+    # '\u06CC':
+    #   - 'ay'
+    #   - 'á'
+    # '\u06CD': 'êy'
+    # '\u0621': '’'
+    # '\u0674':
+    #   - '-e'
+    #   - '-ye'
+
+    # # Other Diacritical Marks and Language Conventions
+
+    # '\u0627': 'āy'
+
+    # '\u0648': 'w'
+    # '\u0626': '’'
+    # '\u06C0': ''
+    # '\u0651': ''
+
+
+    # special rules
+
+    sub space, "", after: "\u0622\u0628\u064E\u0627\u062F" # space followed by abad is removed
+    sub "\ufdf2", "Allāh" # See note 5
+
+    # pointing
+    sub "\u064e", "a" # َ fatha
+    sub "\u064e", "", after: "\u0629" # َ fatha followed by ta' marboota
+    sub "\u064e", "", after: "a" + any("ht") # َ fatha followed by ta' marboota, handling different order of conversion
+
+    # Both e and i are available to romanize this short vowel,
+    # depending on local usage and/or root language. In cases where the sound
+    # is uncertain, i is the default romanization in BGN/PCGN standardization
+    # procedures.
+    sub "\u0650", any("ie")
+    sub "\u0650" + boundary, "-e" # ِ kasra
+
+    # Both o and u are available to romanize this short vowel,
+    # depending on local usage and/or root language. In cases where the sound
+    # is uncertain, u is the default romanization in BGN/PCGN standardization
+    # procedures.
+    sub "\u064f", any("uo") # ُ damma
+
+    sub "\u0652", "" # ْ sokoon
+    sub "\u0659", "ê"
+
+    # special pointed letters
+    sub "\u0639\u064e", "‘a" # عَ
+    sub "\u0639\u0650", "‘i" # عِ
+    sub "\u0639\u064f", "‘ū" # عُ
+    # handle MacOS regex difference
+    sub "\u0639\u064f\u0648", "‘ū" # عُو damma followed by و
+
+    sub "\u0650\u064a", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u06cc", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u064a\u0651\u064e", "īy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any(["\u064e", "u064f"]) # ـِي kasra followed by ي
+    sub "\u064f\u0648", "ō" # ـُو damma followed by و
+    sub "\u064e\u0627", "ā" # ـَا fatha followed by ا
+    sub "\u064e\u0649", "ay" # ـَى fatha followed by ى which is ا not ي
+    sub "\u064e\u0648\u0652", "aw" # ـَوْ
+    sub "\u064e\u0648", "ow" # ـَو
+    sub "\u064e\u064a\u0652", "ay" # ـَيْ
+    sub "\u0650\u06cc\u0651\u064e", "īy" # ـِيَّ
+    sub "\u064e\u064a", "aī" # ـَي
+    sub "\u064e\u06cc", "aī" # ـَي
+    sub "\u0649\u0670", "á" # ىٰ
+    sub "\u0674", "-e" # ٴ
+    sub "\u0654", "-e" #  ٔ
+    # - '-ye'
+
+    # An alif with mad ( آ ) is written only in the initial position by
+    # BGN/PCGN standardization procedures, in keeping with Persian language
+    # family standards of use of the Arabic alphabet. The same letter written
+    # in a medial or final position is written . . .
+    sub "\u0622", "ā" # آ
+
+    # ta' marboota
+    sub "\u0629", "at" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "ah"
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "ah", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+    # shadda
+
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u062a\u0651", "tt" # ت
+    sub "\u062b\u0651", "thth" # ث
+    sub "\u062c\u0651", "jj" # ج
+    sub "\u062d\u0651", "ẖẖ" # ح
+    sub "\u062e\u0651", "khkh" # خ
+    sub "\u062f\u0651", "dd" # د
+    sub "\u0630\u0651", "z̄z̄" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "sh" # ش
+    sub "\u0635\u0651", "şş" # ص
+    sub "\u0636\u0651", "ḏḏ" # ض
+    sub "\u0637\u0651", "ţţ" # ط
+    sub "\u0638\u0651", "z̧z̧" # ظ
+    sub "\u063a\u0651", "ghgh" # غ
+    sub "\u0641\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u0648\u0651", "ww" # و
+    sub "\u064a\u0651", "yy" # ي
+
+
+    sub "\u0621", "’" # ء
+    sub "\u0626", "’" # ئ
+
+    sub "\u0623", "" # أ
+    sub "\u0625", "" # إ
+    sub "\u0627", "ā" # ا
+
+    # See note B
+    sub boundary + "\u0627\u0644", "al " # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    sub boundary + "\u0627\u0644\u062a", "at t" # الت
+    sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632", "az z" # الز
+    sub boundary + "\u0627\u0644\u0633", "as s" # الس
+    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636", "aẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638", "az̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644", "al l" # الل
+    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+
+
+    # consonant characters
+
+    sub "\u0628", "b" # ب
+    sub "\u067E", "p" # پ
+    sub "\u062a", "t" # ت
+    sub "\u067C", "ṯ" # ټ
+    sub "\u062B", "s̄" # ث
+    sub "\u062c", "j" # ج
+    sub "\u0686", "ch" # ‫چ‬
+
+    # # The variant form ج is seen infrequently and does not have a
+    # # single Unicode encoding.
+    sub "\u0681", "dz" # Note 2 # ‫ځ‬
+
+    sub "\u0685", "ts" # Note 2 # ‫څ
+
+    sub "\u062d", "ḩ" # ح
+    sub "\u062e", "kh" # خ
+    sub "\u062f", "d" # د
+    sub "\u0689", "ḏ" # ‫ډ‬
+    sub "\u0630", "z̄" # ذ
+    sub "\u0631", "r" # ر
+    sub "\u0693", "ṟ" # ړ
+    sub "\u0632", "z" # ز
+    sub "\u0698", "zh" # ‫ژ‬
+    sub "\u0696", "z͟h" # ږ
+    sub "\u0633", "s" # س
+    sub "\u069A", "s͟h" # ښ
+    sub "\u0634", "sh" # ش
+    sub "\u0635", "ş" # ص
+    sub "\u0636", "ẕ" # ض
+    sub "\u0637", "ţ" # ط
+    sub "\u0638", "z̧" # ظ
+    sub "\u0639", "‘" # ع
+    sub "\u063a", "gh" # غ
+    sub "\u0641", "f" # ف
+    sub "\u0642", "q" # ق
+    sub "\u0643", "k" # ك
+    sub "\u06A9", "k" # ک
+    sub "\u06AF", "g" # ‫گ‬
+    sub "\u0644", "l" # ل
+    sub "\u0645", "m" # م
+    sub "\u0646", "n" # ن
+    sub "\u06BC", "ṉ" # ڼ
+    sub "\u0647", "h" # ه
+    sub "\u0648", "w" # و
+    sub "\u064a", "y" # ي
+    sub "\u0649", "y" # ي
+    sub "\u06D0", "ē" # ې
+    sub "\u06CD", "êy" # ‫ۍ‬
+  }
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'-")
+  # don't capitalize defined article in the middle of a sentence
+  sub " At T", " at T" # الت
+  sub " As̄ S̄", " as̄ S̄" # الث
+  sub " Ad D", " ad D" # الد
+  sub " Az̄ Z̄", " az̄ Z̄" # الذ
+  sub " Ar R", " ar R" # الر
+  sub " Az Z", " az Z" # الز
+  sub " As S", " as S" # الس
+  sub " Ash Sh", " ash Sh" # الش
+  sub " Aş Ş", " aş Ş" # الص
+  sub " Aẕ Ẕ", " aẕ Ẕ" # الض
+  sub " Aţ Ţ", " aţ Ţ" # الط
+  sub " Az̧ Z̧", " az̧ Z̧" # الظ
+  sub " Al L", " al L" # الل
+  sub " An N", " an N" # الن
+  sub " Al ", " al " # ال
+
+  compose
+}