interscript 0.1.3 → 0.1.9

data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml

@@ -0,0 +1,230 @@
+---
+authority_id: bgnpcgn
+id: 2020
+language: iso-639-2:nep
+source_script: Deva
+destination_script: Latn
+name: Nepali Romanization, 2020
+url: https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20NEPALI.pdf
+creation_date: 1964
+description: |
+  BGN/PCGN 2011 Agreement Romanization of Nepali
+  The BGN and the PCGN have adopted the Nepal Survey Department (NSD) system for the
+  romanization of Nepali names.  This system, below, should be applied to Nepali names for which Roman‐
+  script spellings in materials produced by the government of Nepal are not available.
+
+notes:
+
+  - Only the isolated forms of the characters are given in the consonant table.  See any grammar of Nepali
+    (or other language using the Devanagari alphabet) for variant forms used in conjunct characters.
+  - These two consonant characters appear sometimes to represent ṛ (cerebral r), e.g., पहाड  →  pahāṛ
+    instead of pahāḍ.  At one time they were written with dots below, i.e., as ड़ and ढ़, though this is no
+    longer normal practice in Nepali.    The romanizations ṛ and ṛh, respectively, are optional for
+    documentary purposes if such dots appear in Nepali writing.
+  -  व , can be romanized as either v or w.    This character is primarily
+    romanized as v in consonant initial, medial, and final position; however, initial, medial, and final w
+    romanizations can occur. The w romanization is a special case which is believed to be dependent on
+    dialect, pronunciation, or stress.
+  - |
+    An inventory of letter‐diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:
+      Ṅ(U+1E44)  ṅ (U+1E45)
+      Ñ (U+00D1) ñ (U+00F1)
+      Ṭ (1E6C)   ṭ (1E6D)
+      Ḍ (1E0C)   ḍ (1E0D)
+      Ṇ (1E46)   ṇ (1E47)
+      Ṣ (1E62)   ṣ (1E63)
+      Ā (U+0100) ā (U+0101)
+      Ī (U+012A) ī (U+012B)
+      Ū (U+016A) ū (U+016B)
+      Ṛ (1E5A)   ṛ (1E5B)
+
+  - The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase
+    Roman letters as appropriate should be used.
+
+  - |
+    ं (anusvara) is rendered by
+    ṅ before क, ख, ग, and घ
+    ñ before च, छ, ज, and झ
+    ṇ before ट, ठ, ड, and ढ
+    n before त, थ, द, and ध
+    ṁ before य, र, ल, व, श, ष, स and ह
+
+tests:
+  - source: "लेखन"
+    expected: "lekhn"
+  - source: "मुद्रा"
+    expected: "mudarā"
+  - source: "प्रशंसा"
+    expected: "parshṃsā" # note 5 rule checking
+  - source: "अंक"
+    expected: "aṅk" # note 5 rule checking
+  - source: "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको"
+    expected: "nekpāle sathgit sathāyī kmiṭīko baiṭhk bhdau gte bolāune bheko"
+  - source: "न घर रह्यो, न परिवार"
+    expected: "n ghr rhayo, n privār"
+  - source: "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली"
+    expected: "ḍhorpāṭnmā bhujīkholā bāḍhīphirole abhibhāvk gumāekā bālbālikāko bichlalī"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+  - source: "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो"
+    expected: "sṃvidhān jārī bhes~gai sāravjnik parshāsnmā nyā~ utasāh āune apekṣā thiyo"
+  - source: "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ"
+    expected: "deshmā koronā sṅkarmit r mṛitkko sṅkhayā hrek din bḍhado chh"
+  - source: "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए"
+    expected: "gāu~pālikākā adhaykṣ ṭikā guruṅkā anusār viṣaṇudāslāī rājule sutankā lāgi belukā sāthī lgekā thie"
+  - source: "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ"
+    expected: "yo āyojnā gāu~pālikāko kenadar telalokmā prachh"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "susamitākā kākā hembhādur r kākīlāī pni phirole bgāyo"
+  - source: "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए"
+    expected: "chait philo sātā ghr āekā unī lkḍāun bhepchhi ytai rokie"
+  - source: "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ"
+    expected: "kām gran jāneko hkmā rojgārdātā kmapnīko ptrs~gai vḍā r jilalā parshāsnko siphāris anivāray grieko chh"
+  - source: "दुःख"
+    expected: "duḥkh"
+  - source: "निकुञ्जको स्थानीय पोस्टका कर्मचारी पनि त्यहीँ थिए"
+    expected: "nikuñajko sathānīy posaṭkā kramchārī pni tayhī~ thie"
+  - source: "युद्धकालको मनोविज्ञान"
+    expected: "yudadhkālko mnovijñān"
+  - source: "जर्मन वायुसेवाको आक्रमणमा दुई लाख पचास हजार मानिसको ज्यान जानसक्ने र करिब ३० देखि ४० लाख मान्छे विस्थापित हुने अनुमान बेलायत सरकारको थियो"
+    expected: "jramn vāyusevāko ākarmṇmā duī lākh pchās hjār mānisko jayān jānskane r krib 30 dekhi 40 lākh mānachhe visathāpit hune anumān belāyt srkārko thiyo"
+  - source: "युद्ध"
+    expected: "yudadh"
+  - source: "कोरोनासँग जम्काभेट"
+    expected: "koronās~g jmakābheṭ"
+  - source: "संक्रमित"
+    expected: "sṅkarmit"
+  - source: "स्वयम्"
+    expected: "savyma"
+  - source: "संख्या"
+    expected: "sṅkhayā"
+  - source: "गौरीटारस्थित रंगशाला"
+    expected: "gaurīṭārsathit rṅgshālā"
+
+map:
+
+  rules:
+    # note[5]
+    - pattern: \u0902(?=[कखगघ])    # ं  before क, ख, ग, and घ
+      result: ṅ
+    - pattern: \u0902(?=[चछजझ])    # ं  before च, छ, ज, and झ
+      result: ñ
+    - pattern: \u0902(?=[टठडढ])    # ं  before ट, ठ, ड, and ढ
+      result: ṇ
+    - pattern: \u0902(?=[तथदध])    # ं  before त, थ, द, and ध
+      result: n
+
+  characters:
+
+    # Vowels and Diphthongs
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛi'
+    'ॠ': 'rī'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # Medials # Needed for connecting constants
+
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛi"
+    'ॄ': "rī"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+
+
+    # Consonants (see Note 1)
+
+    # Gutturals
+    'क': 'k'
+    'ख': 'kh'
+    'ग': 'g'
+    'घ': 'gh'
+    'ङ': 'ṅ'
+
+    # Palatals
+    'च': 'ch'
+    'छ': 'chh'
+    'ज': 'j'
+    'झ': 'jh'
+    'ञ': 'ñ'
+
+    # Cerebrals
+    'ट': 'ṭ'
+    'ठ': 'ṭh'
+    'ड': 'ḍ'
+    'ढ': 'ḍh'
+    'ण': 'ṇ'
+
+    # Dentals
+    'त': 't'
+    'थ': 'th'
+    'द': 'd'
+    'ध': 'dh'
+    'न': 'n'
+
+    # Labials
+    'प': 'p'
+    'फ': 'ph'
+    'ब': 'b'
+    'भ': 'bh'
+    'म': 'm'
+
+    # Semivowels
+    'य': 'y'
+    'र': 'r'
+    'ल': 'l'
+    'व': 'v' # or wa [Note#3]
+
+    # Sibilants
+    'श': 'sh'
+    'ष': 'ṣ'
+    'स': 's'
+    'क्ष': 'kṣ'
+    'त्र': 'tr'
+    'ज्ञ' : 'jñ'
+
+    # Aspirate
+    'ह': 'h'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Bisarga
+    'ः': 'ḥ'
+
+    # Anunāsika
+    'ँ': '~'
+
+    'ॅ': 'r'
+
+    # halanta
+    '्': 'a'
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Numerals / सङ्ख्या
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'

data/maps/bgnpcgn-per-Arab-Latn-1958.yaml

@@ -0,0 +1,338 @@
+---
+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: TRANSLITERATION SYSTEM FOR PERSIAN BGN/PCGN 1958 System
+url: https://github.com/interscript/interscript/files/5180821/BGN_Romanization_Guide_1964_persian_1958.pdf
+creation_date: 1958
+confirmation_date: 2017-11
+description: |
+  The BGN/PCGN 1958 System for the Persian alphabet was
+  adopted by the BGN in 1946 and by the PCGN In 1958. It Is
+  used for the romanization of standard geographic names in
+  Iran.
+  The Persian alphabet is the same as the Arabic alphabet
+  except for the addition of four consonant symbols for
+  sounds which do not occur in Arabic. Therefore, the same
+  conversion values are used for the Persian alphabet as for
+  the Arabic alphabet wherever phonetically valid. Where
+  letters common to the two alphabets have different
+  pronunciation in the two languages, conversion values
+  reflecting the Persian pronunciation are provided in the
+  Persian system.
+  It may be noted that neither the system of pointing nor the
+  conversion values for vowels and diphthongs are the same
+  for Persian as for Arabic.
+  Persian presents the same problems of vowel pointing as
+  Arabic in that the short vowel symbols necessary for the
+  proper rendering of short vowels, long vowels, and
+  diphthongs are almost always omitted from written Persian.
+  It follows that, in order to produce transliter- tions in
+  terms of standard written Persian, the transliterator must
+  be able to identify the words used in names and must know
+  their standard written Persian spelling, their proper vowel
+  pointing, and how to eliminate pecularities due to
+  dialectical variation.
+  The notes and special rules explain details of
+  transliteration not stated in the tables.
+
+notes:
+  - |
+    1)The Persian writing system, in its generally used form,
+    employs only the symbols found in Table I, and the alef maddeh
+    (آ) of Table II. The symbols in column 1 of Table II are
+    traditional auxiliary symbols used by Persians only
+    sporadically to indicate the exact reading of a given word.
+    In the case of i, ū, ey and ow, a choice of symbology
+    exists, one system adhering to the Arabic tradition, the
+    other being a modification of it. Likewise, there are two
+    ways of writing alef maq§ureh. The BGN/PCGN transliteration
+    system presupposes forms fully pointed with the Persian
+    symbols represented in Table II, though these are omitted
+    from the examples given below.
+
+  - 2) Alef ( أ ) occurs with the following uses
+    a. Initially, it indicates that the word begins with a vowel or
+    diphthong, and the alef itself is not transliterated, e.g.,
+    انجيرة Anjīreh, ايواني Eyvānī
+    b. Initially with maddeh ( آ ),it indicates ā, e.g., آبادان Ābādān.
+    c. Medially and finally. it represents ā, e.g., e.g., آبادان Ābādān,
+     توكا Tūkā.
+    d.	With hamzeh. See Note 5.
+
+
+  - 3) Where special considerations are paramount, the sub-dot
+    may be used in place of the cedilla
+
+  - 4) The two-letter symbols kh, zh, sh, and gh are convenient
+    for use and easily comprehensible. The infrequent sequences
+    of kāf, ze, sīn, and gāf followed by he can be unequivocally
+    transliterated for bibliographical purposes by the use of a
+    slant line (“shilling,” “solidus") to separate true h from
+    a preceding k, z, s, or	g; that is,	kh represents khe, but
+    k/h stands for kāf followed by he.
+
+  - 5) Hamzeh (ء)	is	not regarded as a letter of the Persian
+    alphabet, but as a diacritic mark, and as such is not
+    always expressed in actual writing. In fully pointed words,
+    however, it appears in several graphic forms, standing
+    alone or written in conjunction with alef, vav, or ye (the
+    ye in this instance being undotted). All these forms are
+    transliterated simply with the apostrophe in the form
+    resembling a small raised figure 9 (’)	,e.g., جزء Joz’
+    صفراء şafrā’, مأخذ ma’khaz̄, مؤتمن mu’taman, پائين pā’īn Occasionally a word may
+    appear pointed according to the strict Arabic tradition so
+    as to indicate an initial hamzeh. This initial hamzeh is
+    never transliterated, but only the vowel which it carries,
+    e.g., •Jfi , whether pointed	or	0	.	is "transliterated
+    simply Anjireh.	' Hamzeh is also sometimes written over
+    final he or ye to represent the -ye form of the eg&feh, cf.
+    Note 8.
+
+  - 6) Alef maddeh is used initially to indicate ā, e.g., آبادان Ābādān
+    Noninitially it indicates ’ā in words of Arabic origin,
+    and must be so transliterated, e.g., قرآن Qor’ān, مآب ma’āb
+
+  - 7) Tashdid ( ّ) indicates doubling of the consonant over which
+    it is written and is represented in transliteration by writing
+    the consonant twice, e.g محمّد Mohammad The sequence kasreh ye ye
+    is transliterated īy.In names of Arabic origin containing the
+    definite article, the vowel of the article is transliterated according
+    to its Persian pronunciation and the lam, when followed by a “sun letter”
+    (t, s̄, d, z̄, r, s, sh, ẕ, ţ, z̧, ţ, z̧, l, n) is assimilated. The article
+    is written in lower case and separate from the preceding and following word,
+    e.g., Zeyn od Din, but *£4 . Zeyn ed Dīn. Cf. Special Rule 1.
+
+  - 8) The relational (ezafeh) suffix	is	transliterated -e after final consonants
+    (except for silent h). After silent h and after vowels, it is transliterated
+    -ye. It is usually not expressed in Persian writing after a consonant
+    (kasreh being understood), e.g., كوهِ مَرغٌوب Kuh-e Marghūb. After final alef or vav
+    it is written with ye (ي), e.g., بايِ آب	Pa-ye Ab,	جويِ آس Jū-ye Ās.	After	ye (ي)
+    and silent he it is written as hamzeh over the letter, e.g., دَهَانهٴ مَمبَر Dahāneh-ye Mambar,
+    سَلَيٴ بُذٌرگ Salasi-ye Bozorrg.
+
+
+
+  -  1.	In Persian names of Arabic origin, the word division
+    used for transliterating Arabic will obtain, except that
+    names ending in the word Allah will be written solid and
+    the a of Allah will be replaced by o, e.g.,	The Arabic
+    definite article when not subject to assimilation will be
+    written al in name-initial position but usually, ol
+    elsewhere, e.g., Al JJal but 2u ol Faqar. Cf. Note 7 above.
+
+  - 2. In Persian names in general, in sequences of name
+    elements pronounced as a single unit, division into
+    separate words will be made after Persian letters written
+    in the word final form. (But see the Rule immediately
+    below.)
+
+  - 3. The word abad which occurs very frequently at
+    the end of place names will be written solid with the
+    preceding word; e.g., Allahabad, not Allah Abad.
+
+  - 4. Persian derivational endings such as vand and Turkish and other
+    endings such as lar, li and lu will be written solid with
+    the preceding word, whether so written in Persian script or
+    not.
+
+  - 5. The letter he, when used in Turkish fashion for
+    word internal e, will be transliterated eh as usual but
+    will be written solid with the remainder of the word.
+
+  - 6. Kheplus vdv followed by long vowel or khe plus vdv followed
+    by gammeh will be rendered khv although the v is not
+    pronounced.
+
+tests:
+
+  - source: اَنجِيرة
+    expected: Anjīreh
+
+  - source: اِيْوَانِي
+    expected: Eyvānī
+
+  - source: آبادان
+    expected: Ābādān
+
+  - source: تُوكا
+    expected: Tūkā
+
+  - source: آبادان
+    expected: Ābādān
+
+  - source: قُرآن
+    expected: Qor’ān
+
+  - source: مَآب
+    expected: Ma’āb
+
+  - source: مُحَمَّد
+    expected: Moḩammad
+
+  - source: كُوهِ مَرغُوب
+    expected: Kūh-e Marghūb
+
+  - source: پَايِ آب
+    expected: Pā-ye Āb
+
+  - source: جُويِ آس
+    expected: Jū-ye Ās
+
+  - source: دَهَانِهٴ مَمبَر
+    expected: Dahāneh-ye Mambar
+
+  - source: سَلَسِيٴ بُذُرگ
+    expected: Salasī-ye Boz̄org
+
+  - source: عَبداللَّه
+    expected: ‘Abdollāh
+
+  - source: ذُو الفَقَار
+    expected: Z̄ū ol Faqār
+
+  - source: اللَّه آبَاد
+    expected: Allāhābād
+
+  - source: اِيران
+    expected: Īrān
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'|-])[\u0061-\uFFFF]
+      result: "upcase"
+
+    - pattern: " Ol"
+      result: " ol"
+
+  characters:
+
+    '\s\u0622\u0628\u064E\u0627\u062F' : 'ābād' # Special Rule 3
+
+    '\u064e(?=\u0629)' : '' # َ fatha followed by ta' marboota
+    '\u064e(?=a[h|t])' : '' # َ fatha followed by ta' marboota, handling different order of conversion
+
+    # pointing
+    '\u064e' : 'a' # َ fatha
+    '\u0650' : 'e' # ِ kasra
+    '\u064f' : 'o' # ُ damma
+    '\u064e\u0627' : 'ā'  # ـَا fatha followed by ا
+    '\u0649\u0670' : 'á' # ىٰ
+    '\u0622' : '’ā'  # آ
+    '\b\u0622' : 'ā'  # آ
+    '\u0650[\u064a|\u06cc]' : 'ī' # ـِي kasra followed by ي
+    # '\u0650\u06cc' : 'ī' # ـِي kasra followed by ي
+    '\u064f\u0648' : 'ū'  # ـُو damma followed by و
+    '\u064e[\u064a|\u06cc]\u0652' : 'ey'  # ـَيْ
+    '\u0650[\u064a|\u06cc]\u0652' : 'ey'  # ـِيْ
+    '\u064e\u0648' : 'ow'  # ـَو
+    '\u0652' : ''  # ْ sokoon
+    '\u0650\u064a\u0651' : 'īy'  # ـِيّ
+    '[\u0654|\u0674]' : '-e' # ٴ ezafeh
+    '(?<=[\u064a|\u0647])[\u0654|\u0674]' : '-ye' # ٴ ezafeh
+    '\u0650\b' : '-e' # ِ kasra
+    '[\u064a|\u06cc]\u0650\b' : '-ye' # ِ kasra
+    # shadda
+
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 's̄s̄'  # ث
+    '\u062c\u0651' : 'jj'  # ج
+    '\u062d\u0651' : 'ḩḩ' # ح
+    '\u062e\u0651' : 'kh'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'z̄z̄'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'sh'  # ش
+    '\u0635\u0651' : 'şş'  # ص
+    '\u0636\u0651' : 'ẕẕ'  # ض
+    '\u0637\u0651' : 'ţţ'  # ط
+    '\u0638\u0651' : 'z̧z̧'  # 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' : 'vv'  # و
+    '\u064a\u0651' : 'yy'  # ي
+
+    '\u0659': 'ê'
+
+    # ta' marboota
+    '\u0629' : 'eh'
+
+    '\b\u0627\u0644' : 'al '  # ال
+    '\s\b\u0627\u0644' : ' ol '  # ال #special Rule 1
+    '\ufdf2': 'Allāh' # See note 5
+    '\u0627\u0644\u0644\u0651\u064e\u0647' : "Allāh"
+    '(?<!\b)\u0627\u0644\u0644\u0651\u064e\u0647' : "ollāh" # Special Rule 1
+    # '\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
+
+
+    '\u0621': '’' # ء
+    '\u0626': '’' # ئ
+
+    '\u0623' : ''  # أ
+    '\u0625' : ''    # إ
+    '\u0627' : 'ā'  # ا
+    '\b\u0627' : ''  # ا
+
+    # consonant characters
+
+    '\u0628' : 'b'  # ب
+    '\u067E' : 'p' # پ
+    '\u062a' : 't'  # ت
+    '\u062B' : 's̄'   # ث
+    '\u062c' : 'j'  # ج
+    '\u0686' : 'ch'  # ‫چ‬
+    '\u062d' : 'ḩ' # ح
+    '\u062e' : 'kh'  # خ
+    '\u062f' : 'd'  # د
+    '\u0630' : 'z̄'  # ذ
+    '\u0631' : 'r'  # ر
+    '\u0632' : 'z'  # ز
+    '\u0698' : 'zh'  # ‫ژ‬
+    '\u0633' : 's'  # س
+    '\u0634' : 'sh'  # ش
+    '\u0635' : 'ş'  # ص
+    '\u0636' : 'ẕ'  # ض
+    '\u0637' : 'ţ'  # ط
+    '\u0638' : 'z̧'  # 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
+    '\u0647' : 'h'  # ه
+    '\u0648' : 'v'  # و
+    '\u064a' : 'y'  # ي
+    '\u0649' : 'y'  # ي
+    '\u06D0' : 'ē'   # ې
+    '\u06CD' : 'êy'  # ‫ۍ‬