interscript-maps 2.0.5

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

@@ -0,0 +1,214 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:asm
+  source_script: Deva
+  destination_script: Latn
+  name: Assamese Romanization, 1997
+  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 {
+  test "অসমীয়া কবিতা", "asamīẏā kabitā"
+  test "কবিৰ আজি জন্মদিন", "kabira āji janmadina"
+  test "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড", "beruṭata emāhara pāchate punara bhayaṃkara agnikāṇḍa"
+  test "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ", "bhaṅāra biruddhe āwedana dākhila kaṃganāra"
+  test "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি", "āpuni paṛhi bhāla pāba parā bātari"
+  test "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক", "śrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
+  test "কেনে আছে প্ৰাক্তন", "kene āche prāktana"
+  test "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ", "kamumbāira meẏarara dehata kobhiḍa pajiṭibha"
+  test "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা", "ṭuiṭāraẏoge khoda sadarī kare ei kathā"
+  test "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়", "lakhimapura jilāra nārāẏaṇapurara barapathārata āji praśānti dhāma nāmere ekhana bṛddhāśramara śubhārambha karā haẏa"
+}
+
+aliases {
+  def_alias deva_chars_1, any("\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd")
+}
+
+stage {
+
+  # RULES
+  # note[2]
+  sub "ক", "k", after: deva_chars_1
+  sub "খ", "kh", after: deva_chars_1
+  sub "গ", "g", after: deva_chars_1
+  sub "ঘ", "gh", after: deva_chars_1
+  sub "ঙ", "ṅ", after: deva_chars_1
+  sub "চ", "c", after: deva_chars_1
+  sub "ছ", "ch", after: deva_chars_1
+  sub "জ", "j", after: deva_chars_1
+  sub "ঝ", "jh", after: deva_chars_1
+  sub "ঞ", "ñ", after: deva_chars_1
+  sub "ট", "ṭ", after: deva_chars_1
+  sub "ঠ", "ṭh", after: deva_chars_1
+  sub "ড", "ḍ", after: deva_chars_1
+  sub "ড়", "ṛ", after: deva_chars_1
+  sub "ঢ", "ḍh", after: deva_chars_1
+  sub "ঢ়", "ṛh", after: deva_chars_1
+  sub "ণ", "ṇ", after: deva_chars_1
+  sub "ত", "t", after: deva_chars_1
+  sub "ৎ", "ṭ", after: deva_chars_1
+  sub "থ", "th", after: deva_chars_1
+  sub "দ", "d", after: deva_chars_1
+  sub "ধ", "dh", after: deva_chars_1
+  sub "ন", "n", after: deva_chars_1
+  sub "প", "p", after: deva_chars_1
+  sub "ফ", "ph", after: deva_chars_1
+  sub "ব", "b", after: deva_chars_1
+  sub "ভ", "bh", after: deva_chars_1
+  sub "ম", "m", after: deva_chars_1
+  sub "য়", "y", after: deva_chars_1
+  sub "য", "ẏ", after: deva_chars_1
+  sub "য়", "ẏ", after: deva_chars_1
+  sub "ৰ", "r", after: deva_chars_1
+  sub "ল", "l", after: deva_chars_1
+  sub "ৱ", "w", after: deva_chars_1
+  sub "শ", "ś", after: deva_chars_1
+  sub "ষ", "sh", after: deva_chars_1
+  sub "স", "s", after: deva_chars_1
+  sub "হ", "h", after: deva_chars_1
+  # note[3]
+  sub "\u0981", "ṅ", after: any("কখগঘঙচছজঝঞটঠডড়ঢঢ়ণতৎথদধন") # ঁ before guttural, palatal, cerebral, and dental
+
+
+  # CHARACTERS
+  parallel {
+
+    #Vowels and Diphthongs (see Note 1)
+
+    sub "অ", "a"
+    sub "আ", "ā"
+    sub "ই", "i"
+    sub "ঈ", "ī"
+    sub "উ", "u"
+    sub "ঊ", "ū"
+    sub "ঋ", "ṛ"
+    sub "ৠ", "ṝ"
+    sub "ঌ", "ḹ"
+    sub "এ", "e"
+    sub "ঐ", "ai"
+    sub "ও", "o"
+    sub "ঔ", "au"
+
+    # Consonant characters
+
+    #Gutturals
+    sub "ক", "ka"
+    sub "খ", "kha"
+    sub "গ", "ga"
+    sub "ঘ", "gha"
+    sub "ঙ", "ṅa"
+
+    #Palatals
+    sub "চ", "ca"
+    sub "ছ", "cha"
+    sub "জ", "ja"
+    sub "ঝ", "jha"
+    sub "ঞ", "ña"
+
+    #Cerebrals
+    sub "ট", "ṭa"
+    sub "ঠ", "ṭha"
+    sub "ড", "ḍa"
+    sub "ড়", "ṛa"
+    sub "ঢ", "ḍha"
+    sub "ঢ়", "ṛha"
+    sub "ণ", "ṇa"
+
+    #Dentals
+    sub "ত", "ta"
+    sub "ৎ", "ṭ"
+    sub "থ", "tha"
+    sub "দ", "da"
+    sub "ধ", "dha"
+    sub "ন", "na"
+
+    #Labials
+    sub "প", "pa"
+    sub "ফ", "pha"
+    sub "ব", "ba"
+    sub "ভ", "bha"
+    sub "ম", "ma"
+
+    #Semivowels
+    sub "য়", "ya"
+    sub "য", "ẏa"
+    sub "য়", "ẏa"
+    sub "ৰ", "ra"
+    sub "ল", "la"
+    sub "ৱ", "wa"
+
+    #Sibilants
+    sub "শ", "śa"
+    sub "ষ", "sha"
+    sub "স", "sa"
+
+    #Aspirate
+    sub "হ", "ha"
+
+
+    # Anusvāra
+    sub "ং", "ṃ"
+
+    # Bisarga
+    sub "ঃ", "ḥ"
+
+    # Candrabindu (see Note 3)
+    sub "ঁ", "m̐"
+
+    # Abagraha  (see Note 4)
+    sub "ऽ", "’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    sub "\u09be", "ā"
+    sub "\u09bf", "i"
+    sub "\u09c0", "ī"
+    sub "\u09c1", "u"
+    sub "\u09c2", "ū"
+    sub "\u09c3", "ṛ"
+    sub "\u09c7", "e"
+    sub "\u09c8", "ai"
+    sub "\u09cb", "o"
+    sub "\u09cc", "au"
+    sub "।", "."
+    sub "्", ""
+    sub "\u09CD", "" # Used for joining
+
+    # Digits
+
+    sub "১", "1"
+    sub "২", "2"
+    sub "৩", "3"
+    sub "৪", "4"
+    sub "৫", "5"
+    sub "৬", "6"
+    sub "৭", "7"
+    sub "৮", "8"
+    sub "৯", "9"
+    sub "০", "0"
+  }
+
+  compose
+}

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

@@ -0,0 +1,53 @@
+metadata {
+  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 {
+  test "ৰাজ্যিক স্বাস্থ্য মন্ত্ৰী পীয়ুষ হাজৰিকাৰ বিৰুদ্ধে দাখিল কৰা হৈছে এজাহাৰ।", "rājẏika sbāsthẏa mantrī pīyusha hājarikāra biruddhe dākhila karā haiche ejāhāra."
+  test "কোৰোনা মহামাৰীৰ এই সময়ত সভাখনত হাজাৰ হাজাৰ লোকে মাস্ক পৰিধান নকৰাৰ লগতে সামাজিক দূৰত্ব নমনাৰ অভিযোগ উত্থাপন কৰা হৈছে", "koronā mahāmārīra ei samayata sabhākhanata hājāra hājāra loke māska paridhāna nakarāra lagate sāmājika dūratba namanāra abhiẏoga utthāpana karā haiche"
+  test "হাওৰাঘাটৰ গ্ৰামীণ বিকাশ বেংক হিতাধিকাৰীৰ পৰা উৎকোচ লৈ গ্ৰেপ্তাৰ বিজেপি কৰ্মী যীচু কেম্পাই", "hāorāghāṭara grāmīṇa bikāśa beṃka hitādhikārīra parā uṭkoca lai greptāra bijepi karmī ẏīcu kempāi"
+  test "জ্যেষ্ঠ সাংবাদিক পৰাগ ভূঞাৰ মৃত্যুক লৈ তদন্ত আৰম্ভ চিআইডিৰ", "jẏeshṭha sāṃbādika parāga bhūñāra mṛtẏuka lai tadanta ārambha ciāiḍira"
+  test "সাংবাদিক পৰাগ ভূঞাৰ মৃত্যুৰ উচিত তদন্তৰ দাবীত নলবাৰীত অৱস্থান ধৰ্মঘট", "sāṃbādika parāga bhūñāra mṛtẏura ucita tadantara dābīta nalabārīta awasthāna dharmaghaṭa"
+  test "দৰঙৰ বিভিন্ন অঞ্চলত মানসিক ৰোগৰ সজাগতামূলক বাটৰ নাট প্ৰদৰ্শন", "daraṅara bibhinna añcalata mānasika rogara sajāgatāmūlaka bāṭara nāṭa pradarśana"
+  test "অযোধ্যাত দীপাৱলীঃ ৫.৮৬ লাখ মাটি চাকি জ্বলাই গঢ়িলে গিনিজ ৱ’ৰ্ল্ড ৰেকৰ্ড", "aẏodhẏāta dīpāwalīḥ 5.86 lākha māṭi cāki jbalāi gaḍha়ile ginija wa’rlḍa rekarḍa"
+  test "ৰাজ্যত আকৌ ২৩৩ জন কোভিড পজিটিভ, সুস্থ হৈছে ৬৪২ জন", "rājẏata ākau 233 jana kobhiḍa pajiṭibha, sustha haiche 642 jana"
+  test "এতিয়ালৈকে ৰাজ্যত এই ভাইৰাছত আক্ৰান্ত লোকৰ সংখ্যা ২১০০৬৮জনলৈ পাইছে বৃদ্ধি।", "etiyālaike rājẏata ei bhāirāchata ākrānta lokara saṃkhẏā 210068janalai pāiche bṛddhi."
+  test "এতিয়ালৈকে ৰাজ্যত কোৰোনাত আক্ৰান্ত হৈ ৯৫৮জন লোক হেৰুৱাইছে প্ৰাণ।", "etiyālaike rājẏata koronāta ākrānta hai 958jana loka heruwāiche prāṇa."
+}
+
+dependency "alalc-asm-Deva-Latn-1997", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

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

@@ -0,0 +1,321 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:aze
+  source_script: Arab
+  destination_script: Latn
+  name: ALA-LC Romanization Table -- azerbaij (1997)
+  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 {
+  test "بَرَكَت", "Barakat"
+  test "سَاحِل", "Sāḥil"
+  test "بَادِمجَان", "Bādimcān"
+  test "قُدرَت", "Qudrat"
+  test "بُوغَا", "Būğā"
+  test "آرَام", "Ārām"
+  test "اِئنلِي", "Enlī"
+  test "دَلِيل", "Dalīl"
+  test "قَارَانلِيق", "Qārānlīq"
+  test "اِيش", "Īş"
+  test "اِيشِيق", "Īşīq"
+  test "اُون", "On"
+  test "ُاون", "Ūn"
+  test "ُاؤن", "Ön"
+  # - source: ُأوزُوم
+  #   expected: üzūm
+  test "اَيْوَان", "Eyvān"
+  test "اَوحَدِي", "Awḥadī"
+  test "َاوَّل", "Avval"
+  test "طَهي", "Ṭahy"
+  # From Rule 1 - part a
+  test "ُأوزدَة", "Üzdah"
+  # From Rule 1 - part b
+  test "مَسئَلَة", "Mas’alah"
+  test "گِئجَة", "Gecah"
+  test "نِئچَة", "Neçah"
+  # From Rule 2 - part a
+  test "آدَام", "Ādām"
+  # From Rule 2 - part b
+  test "حَيْدَرآبَاد", "Ḥeydar’ābād"
+  # From Rule 3
+  test "سَاقَّال", "Sāqqāl"
+  test "مَدَنِيَّت", "Madanīyat"
+  # From Rule 5
+  test "تَكمِلَة الأَخبَار", "Takmilat al-Axbār"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    sub "\u0628\u0651", "bb" # ب
+    sub "\u067E\u0651", "pp" # پ
+    sub "\u062A\u0651", "tt" # ت
+    sub "\u062b\u0651", "s̱s̱" # ث
+    sub "\u062C\u0651", "cc" # ج
+    sub "\u0686\u0651", "çç" # چ
+    sub "\u062d\u0651", "ḥḥ" # ح
+    sub "\u062E\u0651", "xx" # خ
+    sub "\u062F\u0651", "dd" # د
+    sub "\u0630\u0651", "ẕẕ" # ذ
+    sub "\u0631\u0651", "rr" # ر
+    sub "\u0632\u0651", "zz" # ز
+    sub "\u0698\u0651", "jj" # ژ
+    sub "\u0633\u0651", "ss" # س
+    sub "\u0634\u0651", "şş" # ش
+    sub "\u0635\u0651", "ṣṣ" # ص
+    sub "\u0636\u0651", "z̤z̤" # ض
+    sub "\u0637\u0651", "ṭṭ" # ط
+    sub "\u0638\u0651", "ẓẓ" # ظ
+    sub "\u0639\u0651", "‘‘" # ع
+    sub "\u063A\u0651", "ğğ" # غ
+    sub "\u0341\u0651", "ff" # ف
+    sub "\u0642\u0651", "qq" # ق
+    sub "\u06A9\u0651", "kk" # ك
+    sub "\u0643\u0651", "kk" # ك
+    sub "\u06AF\u0651", "gg" # گ
+    sub "\u0644\u0651", "ll" # ل
+    sub "\u0645\u0651", "mm" # م
+    sub "\u0646\u0651", "nn" # ن
+    sub "\u0648\u0651", "vv" # و
+    sub "\u0647\u0651", "hh" # ه
+    sub "\u064A\u0651", "yy" # ي
+
+    sub "\u060c", "," # ،
+
+    sub "\u0627\u0644\u0644\u0651\u064e\u0647", "Allāh"
+
+    sub boundary + "\u0627\u0644", "al-" # ال
+
+    sub "\u0628", "b" # ب
+    sub "\u067E", "p" # پ
+    sub "\u062A", "t" # ت
+    sub "\u062b", "s̱" # ث
+    sub "\u062C", "c" # ج
+    sub "\u0686", "ç" # چ
+    sub "\u062d", "ḥ" # ح
+    sub "\u062E", "x" # خ
+    sub "\u062F", "d" # د
+    sub "\u0630", "ẕ" # ذ
+    sub "\u0631", "r" # ر
+    sub "\u0632", "z" # ز
+    sub "\u0698", "j" # ژ
+    sub "\u0633", "s" # س
+    sub "\u0634", "ş" # ش
+    sub "\u0635", "ṣ" # ص
+    sub "\u0636", "z̤" # ض
+    sub "\u0637", "ṭ" # ط
+    sub "\u0638", "ẓ" # ظ
+    sub "\u0639", "‘" # ع
+    sub "\u063A", "ğ" # غ
+    sub "\u0341", "f" # ف
+    sub "\u0642", "q" # ق
+    sub "\u06A9", "k" # ك
+    sub "\u0643", "k" # ك
+    sub "\u06AF", "g" # گ
+    sub "\u0644", "l" # ل
+    sub "\u0645", "m" # م
+    sub "\u0646", "n" # ن
+    sub "\u0648", "v" # و
+    sub "\u0647", "h" # ه
+    sub "\u064A", "y" # ي
+
+    # Vowels and Diphthongs
+    sub "\u064e", "a"
+    sub "\u0650", "i"
+    sub "\u064f", "u"
+    sub "\u064f\u0648", "ū" # ـُو damma followed by و
+    sub "\u064e\u0627", "ā" # ـَا fatha followed by ا
+    sub "\u0622", "ā" # آ
+    sub "\u0650" + any("\u0621\u0623\u0624\u0626"), "e" # ـِأ kasra followed by hamza
+    sub "\u0650\u064a", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u0627\u064a", "ī" # ـِي kasra followed by ي
+    sub maybe(any("\u064f")) + "\u0627\u064f\u0648", "o" # ـُاُو
+    sub "\u064f\u0627\u0648", "ū" # ـُاو
+    sub "\u064f\u0627\u0624", "ö" # ـُاؤ
+    sub "\u064f\u0623\u0648", "ü" # ـُأو
+    sub "\u064e\u064a\u0652", "ey" # ـَيْ
+    sub "\u064e\u0648" + maybe("\u0652"), "aw" # ـَوْ
+    sub boundary + "\u0627", "" # ا
+    sub boundary + "\u064e\u0627", "a" # ـَا
+    sub boundary + "\u0650\u0627", "i" # ـِا
+
+    # hamzah
+    sub boundary + "\u0623", "" # أ
+    sub "\u0623", "’", not_before: "\u0644" # أ
+    sub "\u0623", ""# أ
+    sub "\u0624", "’" # ؤ
+    sub "\u0626", "’" # ئ
+    sub boundary + "\u0622", "ā" # آ
+    sub "\u0622", "’ā", not_before: any([boundary + "\u0627\u0644", boundary]), not_after: any([boundary, "\u0621"]) # آ in middle, not final, or initial, or after ال
+    sub "\u064e\u0622", "ā" # ـَآ fatha followed by ا
+    sub "\u0622", "" # آ
+
+    # Rule 3 - shadda
+    sub "\u0650\u064a\u0651", "īy" # ـِيَّ
+    sub "\u064f\u0648\u0651", "ūw" # ـَوّ damma followed by و with shadda
+    sub "\u0650\u064a\u0651" + boundary, "ī" # ـِيَّ
+    sub "\u064e\u0648\u0651", "aww" # ـَوّ fatha followed by و with shadda
+    sub "\u064e\u064a\u0651", "ayy" # ـَيّ fatha followed by و with shadda
+
+    # Rule 4 - tanvin
+    sub "\u064c", "un" #  ٌ
+    sub "\u064b", "an" #  ً
+    sub "\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
+    sub "\u064b\u0649", "an" #  ً
+    sub "\u064b\u0627", "an" #  ً
+    sub "\u0649\u064b", "an" #  ً
+    sub "\u0627\u064b", "an" #  ً
+
+    # Rule 5 ta' marboota
+    sub "\u0629", "t" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "h"
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", 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", "h", 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", "h", 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", "h", 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", "h", 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", "h", 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", "h", 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")
+
+
+    sub "\u0650\u064a", "iy", after: any("\u064e\u064f") # ـِي kasra followed by ي
+    sub "\u064e\u0649", "á" # ـَى fatha followed by ى which is ا not ي
+  }
+
+  # POSTRULES
+  sub any("\u0061".."\uFFFF"), upcase, before: boundary, not_before: boundary + any("‘’'")
+
+  sub boundary + "Al", "al" # الت
+
+  compose
+}