interscript 0.1.3 → 0.1.9

data/maps/iso-pli-Thai-Latn-15919-2001.yaml

@@ -0,0 +1,55 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pli
+source_script: Thai
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+
+
+tests:
+  - source: "โย กปฺปโกฏีหิปิ อปฺปเมยฺยํ;"
+    expected: "oy kp–̥pokṭīh̄ipi xp–̥pemy–̥ẙ;"
+  - source: "ตตฺถ ตํ วณฺณยิสฺสํ วินยนฺติ วุตฺตตฺตา วินโย ตาว ววตฺถเปตพฺโพฯ เตเนตํ วุจฺจติ"
+    expected: "tt–̥t̄h t̊ wṇ–̥ṇyis̄–̥s̄̊ winyn–̥ti wut–̥tt–̥tā winoy tāw wwt–̥t̄heptph–̥ophǂ etent̊ wuc–̥cti"
+  - source: "วุตฺตํ เยน ยทา ยสฺมา, ธาริตํ เยน จาภตํ; ยตฺถปฺปติฏฺฐิตเจตเมตํ วตฺวา วิธิํ ตโตฯ"
+    expected: "wut–̥t̊ eyn ythā ys̄–̥mā, ṭhārit̊ eyn cāp̣ht̊; yt–̥t̄hp–̥ptiṭ–̥ṭ̄hitectemt̊ wt–̥wā wiṭhi̊ totǂ"
+  - source: "เตนาติอาทิปาฐสฺส, อตฺถํ นานปฺปการโต; ทสฺสยนฺโต กริสฺสามิ, วินยสฺสตฺถวณฺณนนฺติฯ"
+    expected: "etnātixāthipāṭ̄hs̄–̥s̄, xt–̥t̄h̊ nānp–̥pkārot; ths̄–̥s̄yn–̥ot kris̄–̥s̄āmi, winys̄–̥s̄t–̥t̄hwṇ–̥ṇnn–̥tiǂ"
+  - source: "ยํนูนาหํ ธมฺมญฺจ วินยญฺจ สงฺคาเยยฺยํ, ยถยิทํ สาสนํ อทฺธนิยํ อสฺส จิรฏฺฐิติกํฯ"
+    expected: "ẙnūnāh̄̊ ṭhm–̥mỵ–̥c winyỵ–̥c s̄ng–̥khāeyy–̥ẙ, yt̄hyith̊ s̄ās̄n̊ xth–̥ṭhniẙ xs̄–̥s̄ cirṭ–̥ṭ̄hitik̊ǂ"
+  - source: "ธาเรสฺสสิ ปน เม ตฺวํ, กสฺสป, สาณานิ ปํสุกูลานิ นิพฺพสนานี’ติ วตฺวา จีวเร สาธารณปริโภเคน เจว"
+    expected: "ṭhāers̄–̥s̄s̄i pn em t–̥ẘ, ks̄–̥s̄p, s̄āṇāni p̊s̄ukūlāni niph–̥phs̄nānī’ti wt–̥wā cīwer s̄āṭhārṇpriop̣hekhn ecw"
+  - source: "อถ โข อายสฺมา มหากสฺสโป ภิกฺขู อามนฺเตสิ"
+    expected: "xt̄h ok̄h xāys̄–̥mā mh̄āks̄–̥s̄op p̣hik–̥k̄hū xāmn–̥ets̄i"
+  - source: "อกาโล โข, มาณวก, อตฺถิ เม อชฺช เภสชฺชมตฺตา ปีตา, อปฺเปว นาม สฺเวปิ อุปสงฺกเมยฺยามา"
+    expected: "xkāol ok̄h, māṇwk, xt–̥t̄hi em xch–̥ch ep̣hs̄ch–̥chmt–̥tā pītā, xp–̥epw nām s̄–̥ewpi xups̄ng–̥kemy–̥yāmā"
+  - source: "สฺเว สนฺนิปาโต, น โข ปน เมตํ ปติรูปํ ยฺวาหํ เสกฺโข สมาโน สนฺนิปาตํ คจฺเฉยฺย"
+    expected: "s̄–̥ew s̄n–̥nipāot, n ok̄h pn emt̊ ptirūp̊ y–̥wāh̄̊ es̄k–̥ok̄h s̄māon s̄n–̥nipāt̊ khc–̥ec̄hy–̥y"
+  - source: "สุณาตุ เม, ภนฺเต, สงฺโฆฯ ยทิ สงฺฆสฺส ปตฺตกลฺลํ, อหํ อายสฺมตา มหากสฺสเปน วินยํ ปุฏฺโฐ วิสฺสชฺเชยฺย"
+    expected: "s̄uṇātu em, p̣hn–̥et, s̄ng–̥oḳhǂ ythi s̄ng–̥ḳhs̄–̥s̄ pt–̥tkl–̥l̊, xh̄̊ xāys̄–̥mtā mh̄āks̄–̥s̄epn winẙ puṭ–̥oṭ̄h wis̄–̥s̄ch–̥echy–̥y"
+  - source: "สุณาตุ เม, อาวุโส, สงฺโฆฯ ยทิ สงฺฆสฺส ปตฺตกลฺลํ, อหํ อานนฺทํ ธมฺมํ ปุจฺเฉยฺย"
+    expected: "s̄uṇātu em, xāwuos̄, s̄ng–̥oḳhǂ ythi s̄ng–̥ḳhs̄–̥s̄ pt–̥tkl–̥l̊, xh̄̊ xānn–̥th̊ ṭhm–̥m̊ puc–̥ec̄hy–̥y"
+
+map:
+
+    inherit: 'iso-tha-Thai-Latn-11940-1998'

data/maps/iso-pra-Deva-Latn-15919-2001.yaml

@@ -0,0 +1,59 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pra
+source_script: Deva
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+tests:
+  - source: "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि"
+    expected: "saṛṣaṭaisathaitaivainaāśaānaāṁ śakataibhaūtae sanaātanai"
+  - source: "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते"
+    expected: "gauṇaāśarayae gauṇamayae naāraāyaṇai namao:’satau tae"
+  - source: "तेन समयेन बुद्धो भगवा सावत्थियं विहरति जेतवने अनाथपिण्डिकस्स आरामे"
+    expected: "taena samayaena baudadhao bhagavaā saāvatathaiyaṁ vaiharatai jaetavanae anaāthapaiṇaḍaikasasa āraāmae"
+map:
+
+  inherit: iso-san-Deva-Latn-15919-2001

data/maps/iso-prs-Arab-Latn-233-3-1999.yaml

@@ -0,0 +1,366 @@
+---
+authority_id: iso
+id: 233-3
+language: iso-233-3:prs
+source_script: Arab
+destination_script: Latn
+name: Persian language — Simplified transliteration
+url: https://web.archive.org/web/20200920064754/http://www.freeprotocols.org/content/republished/doc.public/standards/communication/iso/iso-233/iso-233-3.pdf
+creation_date: 1999
+confirmation_date: 1999-01-15
+description: |
+  This part of ISO 233 is one of a series of International
+  Standards, dealing with the conversion of systems of
+  writing. The aim of this part of ISO 233 and others in the
+  series is to provide a means for international
+  communication of written messages in a form which permits
+  the automatic transmission and reconstitution of these, by
+  men or machines. The system of conversion, in this case,
+  must be univocal and entirely reversible. This means that
+  no consideration should be given to phonetic and aesthetic
+  matters or to certain national customs: all these
+  considerations are, indeed, ignored by the machine
+  performing the function. The adoption of this part of ISO
+  233 for international communication leaves every country
+  free to adopt for its own use a national standard which may
+  be different, on condition that it is compatible with this
+  part of ISO 233. The system proposed herein should make
+  this possible and be acceptable to international use if the
+  graphisms it creates are such that they may be converted
+  automatically into the graphisms used in any strict
+  national systems. This part of ISO 233 may be used by
+  anyone who has a clear understanding of the system and is
+  certain that it can be applied without ambiguity. The
+  result obtained will not give a correct pronunciation of
+  the original text in a person’s own language, but it will
+  serve as a means of finding automatically the original
+  graphism and thus allow anyone who has knowledge of the
+  original language to pronounce it correctly. Similarly, one
+  can only pronounce correctly a text written in, for
+  example, English or Polish, if one has a knowledge of
+  English or Polish. The adoption of national standards
+  compatible with this part of ISO 233 will permit the
+  representation, in an international publication, of the
+  morphemes of each language according to the customs of the
+  country where it is spoken. It will be possible to simplify
+  this representation in order to take into account the
+  number of the character sets available on different kinds
+  of machines.
+  1-Scope:
+  This part of ISO 233 establishes a simplified
+  system for the transliteration of Persian characters into
+  Latin characters. This simplification of the stringent
+  rules established by ISO 233:1984 is especially intended to
+  facilitate the processing of bibliographic information (
+  e.g. catalogues, indices, citations, etc.)
+  2-Normative references:
+  The following normative documents contain
+  provisions which, though reference in this text, constitute
+  provisions of this part of ISO 233. For dated references,
+  subsequent amendments to, or revisions of, any of these
+  publications do not apply. However, parties to agreements
+  based on this part of ISO 233 are encouraged to investigate
+  the possibility of applying the most recent editions of the
+  normative documents indicated below. For undated
+  references, the latest edition of the normative document
+  referred to applies. Members of ISO and IEC maintain
+  registers of currently valid International StandardsISO 233-
+  2, Information and documentation — Transliteration of
+  Arabic characters into Latin characters — Part 2: Arabic
+  language — Simplified transliteration. ISO/IEC 10646-1,
+  Information Technology — Universal Multiple-Octet Coded
+  Character Set (UCS) — Part 1: Architecture and Basic
+  Multilingual Plane.
+
+notes: |
+  TODO
+
+tests:
+  - source: آذَر
+    expected: âẕar
+
+  - source: سَم
+    expected: sam
+
+  - source: پُر
+    expected: por
+
+  - source: پِدَر
+    expected: pedar
+
+  - source: مَثَلاً
+    expected: mas̱alâ´´
+
+  - source: جزء
+    expected: jz’
+
+  - source: رأس
+    expected: râ’s
+
+  - source: سؤال
+    expected: sv’âl
+
+  - source: مسئلة
+    expected: msy’lh
+
+
+map:
+  characters:
+
+    # 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
+
+    '\s(?=\u0622\u0628\u064E\u0627\u062F)': '' # space followed by abad is removed
+    '\ufdf2': 'Allāh' # See note 5
+
+    # pointing
+    '\u064e' : 'a' # َ fatha
+
+    '\u0650':
+      - 'e'
+      - 'i'
+    '\u0650\b' : '-e' # ِ kasra
+
+    '\u064f':  # ُ damma
+      - 'o'
+      - 'u'
+
+    '\u0652' : ''  # ْ sokoon
+    '\u0659': 'ê'
+
+    # special pointed letters
+    '\u0639\u064e' : '‘a'  # عَ
+    '\u0639\u0650' : '‘i'  # عِ
+    '\u0639\u064f' : '‘ū'  # عُ
+    # handle MacOS regex difference
+    '\u0639\u064f\u0648' : '‘ū'  # عُو damma followed by و
+
+    '\u0650\u064a' : 'ī' # ـِي kasra followed by ي
+    '\u0650\u06cc' : 'ī' # ـِي kasra followed by ي
+    '\u0650\u064a\u0651\u064e' : 'īy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    '\u064f\u0648' : 'ō'  # ـُو damma followed by و
+    '\u064e\u0627' : 'ā'  # ـَا fatha followed by ا
+    '\u064e\u0649' : 'ay'  # ـَى fatha followed by ى which is ا not ي
+    '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+    '\u064e\u0648' : 'ow'  # ـَو
+    '\u064e\u064a\u0652' : 'ay'  # ـَيْ
+    '\u0650\u06cc\u0651\u064e' : 'īy' # ـِيَّ
+    '\u064e\u064a' : 'aī'  # ـَي
+    '\u064e\u06cc' : 'aī'  # ـَي
+    '\u0649\u0670': 'á' # ىٰ
+    '\u0674': '-e' # ٴ
+    '\u0654': '-e' #  ٔ
+      # - '-ye'
+
+    '\u0622' : 'â'  # آ
+
+    # ta' marboota
+    '\u0629' : 't' # ة in the middle of the sentence
+    '\u0629$' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{4})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{5})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{6})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{7})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{8})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{9})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{10})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{11})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{12})\u0629' : 'h'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{13})\u0629' : 'h'
+
+    # shadda
+    '\u0628' : 'bb'  # ب
+    '\u067E' : 'pp' # پ
+    '\u062a' : 'tt'  # ت
+    '\u062B' : 's̱s̱'   # ث
+    '\u062c' : 'jj'  # ج
+    '\u0686' : 'č̱č̱'  # ‫چ‬‬
+    '\u062d' : 'ḥḥ' # ح
+    '\u062e' : 'ḵḵ'  # خ
+    '\u062f' : 'dd'  # د
+    '\u0689' : 'ḏḏ' # ‫ډ‬
+    '\u0630' : 'ẕẕ'  # ذ
+    '\u0631' : 'rr'  # ر
+    '\u0632' : 'zz'  # ز
+    '\u0698' : 'zz'  # ‫ژ‬
+    '\u0633' : 'ss'  # س
+    '\u0634' : 'šš'  # ش
+    '\u0635' : 'ṣṣ'  # ص
+    '\u0636' : 'żż'  # ض
+    '\u0637' : 'ṭṭ'  # ط
+    '\u0638' : 'zz'  # ظ
+    '\u0639' : '‘'  # ع
+    '\u063a' : 'gh'  # غ
+    '\u0641' : 'ff'  # ف
+    '\u0642' : 'qq'  # ق
+    '\u06A9' : 'kk' # ک
+    '\u06AF' : 'gg' # ‫گ‬
+    '\u0644' : 'll'  # ل
+    '\u0645' : 'mm'  # م
+    '\u0646' : 'nn'  # ن
+    '\u0648' : 'vv'  # و
+    '\u0647' : 'hh'  # ه
+    '\u064a' : 'yy'  # ي
+    '\u0649' : 'yy'  # ي
+    '\u06D0' : 'ēē'   # ې
+    '\u06CD' : 'êy'  # ‫ۍ
+
+    # Tanvin
+    '\u064b': '´´' #  ً
+    '\u064c': '' #  ٌ
+    '\u064d': '' #  ٍ
+
+    # hamzeh
+    '\u0621' : '’' # ء
+    '\u0623' : 'â’'  # أ
+    '\u0624' : 'v’'  # ؤ
+    '\u0626' : 'y’' # ئ
+
+    # punctuation
+
+    '\u060c' : ',' # vavak comma
+    '\u061b' : ';' # nogteh vavak semi column
+    '\u061f' : '?' # neshane-ye porsesh question mark
+
+    '\u0625' : ''    # إ
+    '\u0627' : 'â'  # ا
+
+    # See note B
+    '\b\u0627\u0644' : 'al '  # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    '\b\u0627\u0644\u062a' : 'at t'  # الت
+    '\b\u0627\u0644\u062b' : 'as̄ s̄'  # الث
+    '\b\u0627\u0644\u062f' : 'ad d' # الد
+    '\b\u0627\u0644\u0630' : 'az̄ z̄'  # 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' : 'aş ş'  # الص
+    '\b\u0627\u0644\u0636' : 'aẕ ẕ'  # الض
+    '\b\u0627\u0644\u0637' : 'aţ ţ'  # الط
+    '\b\u0627\u0644\u0638' : 'az̧ z̧' # الظ
+    '\b\u0627\u0644\u0644' : 'al l'  # الل
+    '\b\u0627\u0644\u0646' : 'an n'  # الن
+
+    # consonant characters
+
+    '\u0628' : 'b'  # ب
+    '\u067E': 'p' # پ
+    '\u062a' : 't'  # ت
+    # '\u067C': 'ṯ'  # ټ
+    '\u062B': 's̱'   # ث
+    '\u062c' : 'j'  # ج
+    '\u0686': 'c'  # ‫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' : 'ḥ' # ح
+    '\u062e' : 'ḵ'  # خ
+    '\u062f' : 'd'  # د
+    '\u0689' : 'ḏ' # ‫ډ‬
+    '\u0630' : 'ẕ'  # ذ
+    '\u0631' : 'r'  # ر
+    # '\u0693' : 'ṟ'   # ړ
+    '\u0632' : 'z'  # ز
+    '\u0698' : 'z'  # ‫ژ‬
+    # '\u0696' : 'z͟h'  # ږ
+    '\u0633' : 's'  # س
+    # '\u069A' : 's͟h'  # ښ
+    '\u0634' : 'š'  # ش
+    '\u0635' : 'ṣ'  # ص
+    '\u0636' : 'ż'  # ض
+    '\u0637' : 'ṭ'  # ط
+    '\u0638' : 'z'  # ظ
+    '\u0639' : '‘'  # ع
+    '\u063a' : 'gh'  # غ
+    '\u0641' : 'f'  # ف
+    '\u0642' : 'q'  # ق
+    # '\u0643' : 'k'  # ك
+    '\u06A9' : 'k' # ک
+    '\u06AF' : 'g' # ‫گ‬
+    '\u0644' : 'l'  # ل
+    '\u0645' : 'm'  # م
+    '\u0646' : 'n'  # ن
+    # '\u06BC' : 'ṉ' # ڼ
+    '\u0648' : 'v'  # و
+    '\u0647' : 'h'  # ه
+    '\u064a' : 'y'  # ي
+    '\u0649' : 'y'  # ي
+    '\u06D0' : 'ē'   # ې
+    '\u06CD' : 'êy'  # ‫ۍ‬