interscript 0.1.3 → 0.1.9

data/maps/alalc-asm-Deva-Latn-1997.yaml

@@ -0,0 +1,259 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:asm
+source_script: Deva
+destination_script: Latn
+name: Assamese Romanization, 1997
+alias:
+  ogc11122:
+    code: asm_Deva2Latn_ALA_1997
+    description: Assamese ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/assamese.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Assamese
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the subscript sign ( ◌् ) called halanta or
+       birāma.
+
+  - Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "অসমীয়া কবিতা"
+    expected: "asamīẏā kabitā"
+  - source: "কবিৰ আজি জন্মদিন"
+    expected: "kabira āji janmadina"
+  - source: "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড"
+    expected: "beruṭata emāhara pāchate punara bhayaṃkara agnikāṇḍa"
+  - source: "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ"
+    expected: "bhaṅāra biruddhe āwedana dākhila kaṃganāra"
+  - source: "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি"
+    expected: "āpuni paṛhi bhāla pāba parā bātari"
+  - source: "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক"
+    expected: "śrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
+  - source: "কেনে আছে প্ৰাক্তন"
+    expected: "kene āche prāktana"
+  - source: "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ"
+    expected: "kamumbāira meẏarara dehata kobhiḍa pajiṭibha"
+  - source: "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা"
+    expected: "ṭuiṭāraẏoge khoda sadarī kare ei kathā"
+  - source: "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়"
+    expected: "lakhimapura jilāra nārāẏaṇapurara barapathārata āji praśānti dhāma nāmere ekhana bṛddhāśramara śubhārambha karā haẏa"
+
+
+map:
+
+  rules:
+    # note[2]
+    - pattern: (ক=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'k'
+    - pattern: (খ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'kh'
+    - pattern: (গ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'g'
+    - pattern: (ঘ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'gh'
+    - pattern: (ঙ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṅ'
+    - pattern: (চ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'c'
+    - pattern: (ছ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ch'
+    - pattern: (জ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'j'
+    - pattern: (ঝ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'jh'
+    - pattern: (ঞ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ñ'
+    - pattern: (ট=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṭ'
+    - pattern: (ঠ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṭh'
+    - pattern: (ড=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ḍ'
+    - pattern: (ড়=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṛ'
+    - pattern: (ঢ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ḍh'
+    - pattern: (ঢ়=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṛh'
+    - pattern: (ণ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṇ'
+    - pattern: (ত=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  't'
+    - pattern: (ৎ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ṭ'
+    - pattern: (থ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'th'
+    - pattern: (দ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'd'
+    - pattern: (ধ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'dh'
+    - pattern: (ন=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'n'
+    - pattern: (প=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'p'
+    - pattern: (ফ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ph'
+    - pattern: (ব=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'b'
+    - pattern: (ভ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'bh'
+    - pattern: (ম=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'm'
+    - pattern: (য়=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'y'
+    - pattern: (য=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ẏ'
+    - pattern: (য়=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ẏ'
+    - pattern: (ৰ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'r'
+    - pattern: (ল=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'l'
+    - pattern: (ৱ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'w'
+    - pattern: (শ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'ś'
+    - pattern: (ষ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'sh'
+    - pattern: (স=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  's'
+    - pattern: (হ=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd])
+      result:  'h'
+    # note[3]
+    - pattern: \u0981(?=[কখগঘঙচছজঝঞটঠডড়ঢঢ়ণতৎথদধন])    # ঁ before guttural, palatal, cerebral, and dental
+      result: ṅ
+
+  characters:
+
+    #Vowels and Diphthongs (see Note 1)
+
+    'অ': 'a'
+    'আ': 'ā'
+    'ই': 'i'
+    'ঈ': 'ī'
+    'উ': 'u'
+    'ঊ': 'ū'
+    'ঋ': 'ṛ'
+    'ৠ': 'ṝ'
+    'ঌ': 'ḹ'
+    'এ': 'e'
+    'ঐ': 'ai'
+    'ও': 'o'
+    'ঔ': 'au'
+
+   # Consonant characters
+
+    #Gutturals
+    'ক': 'ka'
+    'খ': 'kha'
+    'গ': 'ga'
+    'ঘ': 'gha'
+    'ঙ': 'ṅa'
+
+    #Palatals
+    'চ': 'ca'
+    'ছ': 'cha'
+    'জ': 'ja'
+    'ঝ': 'jha'
+    'ঞ': 'ña'
+
+    #Cerebrals
+    'ট': 'ṭa'
+    'ঠ': 'ṭha'
+    'ড': 'ḍa'
+    'ড়': 'ṛa'
+    'ঢ': 'ḍha'
+    'ঢ়': 'ṛha'
+    'ণ': 'ṇa'
+
+    #Dentals
+    'ত': 'ta'
+    'ৎ': 'ṭ'
+    'থ': 'tha'
+    'দ': 'da'
+    'ধ': 'dha'
+    'ন': 'na'
+
+    #Labials
+    'প': 'pa'
+    'ফ': 'pha'
+    'ব': 'ba'
+    'ভ': 'bha'
+    'ম': 'ma'
+
+    #Semivowels
+    'য়': 'ya'
+    'য': 'ẏa'
+    'য়': 'ẏa'
+    'ৰ': 'ra'
+    'ল': 'la'
+    'ৱ': 'wa'
+
+    #Sibilants
+    'শ': 'śa'
+    'ষ': 'sha'
+    'স': 'sa'
+
+    #Aspirate
+    'হ': 'ha'
+
+
+    # Anusvāra
+    'ং': 'ṃ'
+
+    # Bisarga
+    'ঃ': 'ḥ'
+
+    # Candrabindu (see Note 3)
+    'ঁ': 'm̐'
+
+    # Abagraha  (see Note 4)
+    'ऽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    '\u09be': 'ā'
+    '\u09bf': 'i'
+    '\u09c0': 'ī'
+    '\u09c1': 'u'
+    '\u09c2': 'ū'
+    '\u09c3': 'ṛ'
+    '\u09c7': 'e'
+    '\u09c8': 'ai'
+    '\u09cb': 'o'
+    '\u09cc': 'au'
+    '।': '.'
+    '्': ''
+    '\u09CD': '' # Used for joining
+
+    # Digits
+
+    '১': '1'
+    '২': '2'
+    '৩': '3'
+    '৪': '4'
+    '৫': '5'
+    '৬': '6'
+    '৭': '7'
+    '৮': '8'
+    '৯': '9'
+    '০': '0'
+
+
+

data/maps/alalc-asm-Deva-Latn-2012.yaml

@@ -0,0 +1,55 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:asm
+source_script: Deva
+destination_script: Latn
+name: Assamese Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/assamese.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Assamese
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the subscript sign ( ◌् ) called halanta or
+       birāma.
+
+  - Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "ৰাজ্যিক স্বাস্থ্য মন্ত্ৰী পীয়ুষ হাজৰিকাৰ বিৰুদ্ধে দাখিল কৰা হৈছে এজাহাৰ।"
+    expected: "rājẏika sbāsthẏa mantrī pīyusha hājarikāra biruddhe dākhila karā haiche ejāhāra."
+  - source: "কোৰোনা মহামাৰীৰ এই সময়ত সভাখনত হাজাৰ হাজাৰ লোকে মাস্ক পৰিধান নকৰাৰ লগতে সামাজিক দূৰত্ব নমনাৰ অভিযোগ উত্থাপন কৰা হৈছে"
+    expected: "koronā mahāmārīra ei samayata sabhākhanata hājāra hājāra loke māska paridhāna nakarāra lagate sāmājika dūratba namanāra abhiẏoga utthāpana karā haiche"
+  - source: "হাওৰাঘাটৰ গ্ৰামীণ বিকাশ বেংক হিতাধিকাৰীৰ পৰা উৎকোচ লৈ গ্ৰেপ্তাৰ বিজেপি কৰ্মী যীচু কেম্পাই"
+    expected: "hāorāghāṭara grāmīṇa bikāśa beṃka hitādhikārīra parā uṭkoca lai greptāra bijepi karmī ẏīcu kempāi"
+  - source: "জ্যেষ্ঠ সাংবাদিক পৰাগ ভূঞাৰ মৃত্যুক লৈ তদন্ত আৰম্ভ চিআইডিৰ"
+    expected: "jẏeshṭha sāṃbādika parāga bhūñāra mṛtẏuka lai tadanta ārambha ciāiḍira"
+  - source: "সাংবাদিক পৰাগ ভূঞাৰ মৃত্যুৰ উচিত তদন্তৰ দাবীত নলবাৰীত অৱস্থান ধৰ্মঘট"
+    expected: "sāṃbādika parāga bhūñāra mṛtẏura ucita tadantara dābīta nalabārīta awasthāna dharmaghaṭa"
+  - source: "দৰঙৰ বিভিন্ন অঞ্চলত মানসিক ৰোগৰ সজাগতামূলক বাটৰ নাট প্ৰদৰ্শন"
+    expected: "daraṅara bibhinna añcalata mānasika rogara sajāgatāmūlaka bāṭara nāṭa pradarśana"
+  - source: "অযোধ্যাত দীপাৱলীঃ ৫.৮৬ লাখ মাটি চাকি জ্বলাই গঢ়িলে গিনিজ ৱ’ৰ্ল্ড ৰেকৰ্ড"
+    expected: "aẏodhẏāta dīpāwalīḥ 5.86 lākha māṭi cāki jbalāi gaḍha়ile ginija wa’rlḍa rekarḍa"
+  - source: "ৰাজ্যত আকৌ ২৩৩ জন কোভিড পজিটিভ, সুস্থ হৈছে ৬৪২ জন"
+    expected: "rājẏata ākau 233 jana kobhiḍa pajiṭibha, sustha haiche 642 jana"
+  - source: "এতিয়ালৈকে ৰাজ্যত এই ভাইৰাছত আক্ৰান্ত লোকৰ সংখ্যা ২১০০৬৮জনলৈ পাইছে বৃদ্ধি।"
+    expected: "etiyālaike rājẏata ei bhāirāchata ākrānta lokara saṃkhẏā 210068janalai pāiche bṛddhi."
+  - source: "এতিয়ালৈকে ৰাজ্যত কোৰোনাত আক্ৰান্ত হৈ ৯৫৮জন লোক হেৰুৱাইছে প্ৰাণ।"
+    expected: "etiyālaike rājẏata koronāta ākrānta hai 958jana loka heruwāiche prāṇa."
+map:
+
+  inherit: "alalc-asm-Deva-Latn-1997"

data/maps/alalc-aze-Arab-Latn-1997.yaml

@@ -0,0 +1,376 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:aze
+source_script: Arab
+destination_script: Latn
+name: ALA-LC Romanization Table -- azerbaij (1997)
+alias:
+  ogc11122:
+    code: aze_Arab2Latn_ALA_1997
+    description: Arabic ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/azerbaij.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Arabic
+
+notes:
+  - 1. As seen in the examples above, vowel harmony, which is
+    found in Modern Turkish, applies to Azerbaijani as well.
+
+  - 2. The letter ى in final position may represent the long
+    vowel romanized á, in addition to the
+    vowels romanized i and 1. This occurs in Arabic names, such
+    as Mustafá
+    al-Musanná
+
+  - 3. Vowel points are used sparingly in Azerbaijani
+    publications. For romanization, they must be
+    supplied from a dictionary.
+
+  - Rule 1 ء hamza
+    (a) When initial, ء is not represented in romanization
+        üzdah  أوزدة
+
+    (b) When medial or final in words of Perso-Arabic origin, 9 is
+    romanized as ’ (alit), except when it accompanies the
+    phonetic sound e (as in men), in which case it is romanized
+    by e.
+      mas’alah مَسئَلة
+      gecah كئجة
+      necah نئجة
+
+  - Rule 2 ˜ (maddah)
+
+    (a) Initial آ is romanized ā.
+
+    ādām				        آدام
+
+    (b) Medial آ, when it represents the phonetic combination ’ā, is so romanized.
+
+    Heydar'ãbãd     حيدَرآبَاد
+
+  - Rule 3  ّ
+    (shaddah or tashdid) is represented by doubling the letter or digraph concerned.
+    sãqqãl   سَاقَّال
+
+    Note the exceptional case where  ّ is written over و and ي to represent
+    the combination of long vowel plus consonants.
+    madaníyat  مَدَنِيَّت
+
+  - |
+    Rule 4 Tanvīn (written form ٌ, ً (ًا), or ٍ ) which occurs chiefly in Arabic words,
+    is romanized un, in, an, and an, respectively.
+
+    (a)	When it occurs in indefinite nouns derived from defective roots.
+
+      qāḍin				قاضٍ
+      ma‘nan				معنىً
+
+    (b)	When it indicates the adverbial use of a noun or adjective.
+
+      ṭab‘an				  طبعًا
+      faj’atan				فجأةً
+      al-Mushtarik waḍ‘an		المشترك وضعاً
+            wa-al-muftariq ṣuq‘an	والمفترق صقعاً
+
+  - ة in a word in the construct state is romanized t.  See rule 7(b).
+
+  - The consonant letter ö at the end of Arabic words in the
+    genetive construction (izãfah) is romanized by t.
+
+    takmilat al-axbãr    تَكمِلَة الأخبَار
+
+  # Grammatical Structure as It Affects Romanization
+  - Rule 6 izãfah. When two Persian words are used in an Azerbaijani
+    context in a relationship known as izãfah, the first word (
+    the muzãf) is followed by an additional letter or syllable
+    in romanization. This is added according to the following
+    rules
+    (a) When the muzaf bears no special mark of izãfah, it is
+    followed by -i.
+    Sazman-i tabligãti-Islãm   سازمان تبليغات اسلامي
+
+    (b) When the muzãf is marked by the addition of 9, it is followed by -'i.
+    Nãbigah-'i dahr   نابغة دَهر
+
+    (c) When the muzãf is marked by the addition of û, it is followed by -yi.
+    darya-yi nur    دَريَاي نُور
+
+    (d) izãfah is represented in romanization of personal names only when
+    implied in the Persian script.
+    Mucír-i BeylaqãnT   مَجير بيلقاني
+    Maktabí-i Sírãzí    مكتبي شيرازي
+
+  # Affixes and Compounds
+  - Rule 7 Affixes.
+    (a) When the affix and the word with it is connected grammatically are
+    written separately in Azerbaijani, the two are separated in romanization
+    by a single prime(').
+
+    (b) The Arabic article al is separated by a hyphen, in romanization,
+    from the word to which it is prefixed.
+
+  - Rule 8 Compounds.
+    When the elements of a compound (except a compound personal name)
+    are written separately in Azerbaijani, they are separated in
+    romanization by a single prime(').
+  # Orthography of Azerbaijani in Romanization
+
+  - Rule 9 Capitalization
+
+    (a) Rules for the capitalization of English are followed, except that
+    the Arabic article al, is lower cased in all positions.
+
+    (b)	Diacritics are used with both upper and lower case letters in romanization.
+
+  - Rule 10 Foreign words.
+    Foreign words in an Azerbaijani context, including Persian and Arabic words,
+    are romanized according to the rules for Azerbaijani. For short vowels not
+    indicated in the script, the Azerbaijani vowels nearest the original
+    pronunciation of the word are supplied in romanization.
+
+tests:
+  - source: بَرَكَت
+    expected: Barakat
+
+  - source: سَاحِل
+    expected: Sāḥil
+
+  - source: بَادِمجَان
+    expected: Bādimcān
+
+  - source: قُدرَت
+    expected: Qudrat
+
+  - source: بُوغَا
+    expected: Būğā
+
+  - source: آرَام
+    expected: Ārām
+
+  - source: اِئنلِي
+    expected: Enlī
+
+  - source: دَلِيل
+    expected: Dalīl
+
+  - source: قَارَانلِيق
+    expected: Qārānlīq
+
+  - source: اِيش
+    expected: Īş
+
+  - source: اِيشِيق
+    expected: Īşīq
+
+  - source: اُون
+    expected: 'On'
+
+  - source:  ُاون
+    expected: Ūn
+
+  - source:  ُاؤن
+    expected: Ön
+
+  # - source: ُأوزُوم
+  #   expected: üzūm
+
+  - source: اَيْوَان
+    expected: Eyvān
+
+  - source: اَوحَدِي
+    expected: Awḥadī
+
+  - source: َاوَّل
+    expected: Avval
+
+  - source: طَهي
+    expected: Ṭahy
+
+  # From Rule 1 - part a
+
+  - source: ُأوزدَة
+    expected: Üzdah
+
+  # From Rule 1 - part b
+
+  - source: مَسئَلَة
+    expected: Mas’alah
+
+  - source: گِئجَة
+    expected: Gecah
+
+  - source: نِئچَة
+    expected: Neçah
+
+  # From Rule 2 - part a
+  - source: آدَام
+    expected: Ādām
+
+  # From Rule 2 - part b
+  - source: حَيْدَرآبَاد
+    expected: Ḥeydar’ābād
+
+  # From Rule 3
+  - source: سَاقَّال
+    expected: Sāqqāl
+
+  - source: مَدَنِيَّت
+    expected: Madanīyat
+
+  # From Rule 5
+
+  - source: تَكمِلَة الأَخبَار
+    expected: Takmilat al-Axbār
+
+
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'])[\u0061-\uFFFF]
+      result: "upcase"
+
+    - pattern : '\bAl'  # الت
+      result: 'al'
+
+  characters:
+
+    '\u0628\u0651': 'bb'  # ب
+    '\u067E\u0651': 'pp'  # پ
+    '\u062A\u0651': 'tt'  # ت
+    '\u062b\u0651': 's̱s̱'  # ث
+    '\u062C\u0651': 'cc'  # ج
+    '\u0686\u0651': 'çç'  # چ
+    '\u062d\u0651': 'ḥḥ'  # ح
+    '\u062E\u0651': 'xx'  # خ
+    '\u062F\u0651': 'dd'  # د
+    '\u0630\u0651': 'ẕẕ'  # ذ
+    '\u0631\u0651': 'rr'  # ر
+    '\u0632\u0651': 'zz'  # ز
+    '\u0698\u0651': 'jj'  # ژ
+    '\u0633\u0651': 'ss'  # س
+    '\u0634\u0651': 'şş'  # ش
+    '\u0635\u0651': 'ṣṣ'  # ص
+    '\u0636\u0651': 'z̤z̤'  # ض
+    '\u0637\u0651': 'ṭṭ'  # ط
+    '\u0638\u0651': 'ẓẓ'  # ظ
+    '\u0639\u0651': '‘‘'  # ع
+    '\u063A\u0651': 'ğğ'  # غ
+    '\u0341\u0651': 'ff'  # ف
+    '\u0642\u0651': 'qq'  # ق
+    '\u06A9\u0651': 'kk'  # ك
+    '\u0643\u0651': 'kk'  # ك
+    '\u06AF\u0651': 'gg'  # گ
+    '\u0644\u0651': 'll'  # ل
+    '\u0645\u0651': 'mm'  # م
+    '\u0646\u0651': 'nn'  # ن
+    '\u0648\u0651': 'vv'  # و
+    '\u0647\u0651': 'hh'  # ه
+    '\u064A\u0651': 'yy'  # ي
+
+    '\u060c': ',' # ،
+
+    '\u0627\u0644\u0644\u0651\u064e\u0647': "Allāh"
+
+    '\b\u0627\u0644' : 'al-'  # ال
+
+    '\u0628': 'b'  # ب
+    '\u067E': 'p'  # پ
+    '\u062A': 't'  # ت
+    '\u062b': 's̱'  # ث
+    '\u062C': 'c'  # ج
+    '\u0686': 'ç'  # چ
+    '\u062d': 'ḥ'  # ح
+    '\u062E': 'x'  # خ
+    '\u062F': 'd'  # د
+    '\u0630': 'ẕ'  # ذ
+    '\u0631': 'r'  # ر
+    '\u0632': 'z'  # ز
+    '\u0698': 'j'  # ژ
+    '\u0633': 's'  # س
+    '\u0634': 'ş'  # ش
+    '\u0635': 'ṣ'  # ص
+    '\u0636': 'z̤'  # ض
+    '\u0637': 'ṭ'  # ط
+    '\u0638': 'ẓ'  # ظ
+    '\u0639': '‘'  # ع
+    '\u063A': 'ğ'  # غ
+    '\u0341': 'f'  # ف
+    '\u0642': 'q'  # ق
+    '\u06A9': 'k'  # ك
+    '\u0643': 'k'  # ك
+    '\u06AF': 'g'  # گ
+    '\u0644': 'l'  # ل
+    '\u0645': 'm'  # م
+    '\u0646': 'n'  # ن
+    '\u0648': 'v'  # و
+    '\u0647': 'h'  # ه
+    '\u064A': 'y'  # ي
+
+    # Vowels and Diphthongs
+    '\u064e': 'a'
+    '\u0650': 'i'
+    '\u064f': 'u'
+    '\u064f\u0648' : 'ū'  # ـُو damma followed by و
+    '\u064e\u0627' : 'ā'  # ـَا fatha followed by ا
+    '\u0622' : 'ā'  # آ
+    '\u0650[\u0621|\u0623|\u0624|\u0626]' : 'e' # ـِأ kasra followed by hamza
+    '\u0650\u064a' : 'ī' # ـِي kasra followed by ي
+    '\u0650\u0627\u064a' : 'ī' # ـِي kasra followed by ي
+    '[\u064f]?\u0627\u064f\u0648' : 'o'  # ـُاُو
+    '\u064f\u0627\u0648' : 'ū'  # ـُاو
+    '\u064f\u0627\u0624' : 'ö'  # ـُاؤ
+    '\u064f\u0623\u0648' : 'ü'  # ـُأو
+    '\u064e\u064a\u0652' : 'ey'  # ـَيْ
+    '\u064e\u0648\u0652?' : 'aw'  # ـَوْ
+    '\b\u0627' : '' # ا
+    '\b\u064e\u0627': 'a' # ـَا
+    '\b\u0650\u0627': 'i' # ـِا
+
+    # hamzah
+    '\b\u0623' : ''  # أ
+    '\u0623' : '’'  # أ
+    '\u0624': '’' # ؤ
+    '\u0626' : "’" # ئ
+    '\b\u0622' : 'ā'  # آ
+    '(?<!\b\u0627\u0644)(?<!\b)\u0622(?![\b|\u0621])' : '’ā'  # آ in middle, not final, or initial, or after ال
+    '\u064e\u0622' : 'ā'  # ـَآ fatha followed by ا
+    '\u0622' : ''  # آ
+
+    # Rule 3 - shadda
+    '\u0650\u064a\u0651' : 'īy' # ـِيَّ
+    '\u064f\u0648\u0651' : 'ūw'  # ـَوّ damma followed by و with shadda
+    '\u0650\u064a\u0651\b' : 'ī' # ـِيَّ
+    '\u064e\u0648\u0651' : 'aww'  # ـَوّ fatha followed by و with shadda
+    '\u064e\u064a\u0651' : 'ayy'  # ـَيّ fatha followed by و with shadda
+
+    # Rule 4 - tanvin
+    '\u064c': 'un' #  ٌ
+    '\u064b': 'an' #  ً
+    '\u064d': 'in' #  ٍ
+    # tanween should be onb the letter preceeding the end in case of ا, ى
+    # however, it's common that people mistake that, so we're handling both orders
+    '\u064b\u0649': 'an' #  ً
+    '\u064b\u0627': 'an' #  ً
+    '\u0649\u064b': 'an' #  ً
+    '\u0627\u064b': 'an' #  ً
+
+    # Rule 5 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'
+
+
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    '\u064e\u0649' : 'á'  # ـَى fatha followed by ى which is ا not ي