interscript-maps 2.0.5

data/maps/bis-asm-Beng-Latn-13194-1991.imp

@@ -0,0 +1,154 @@
+metadata {
+  authority_id: bis
+  id: 1991
+  language: iso-639-2:asm
+  source_script: Beng
+  destination_script: Latn
+  name: Indian script code for information interchange - ISCII - Assamese Romanization
+
+  #url:
+  creation_date: 1991
+  description: |
+    IS 13194 (1991): Indian script code for information
+    interchange - ISCII [LITD 20: Indian Language Technologies
+    and Products]
+
+  notes:
+    - |
+      Exception: Anusvāra is transliterated by:
+
+      a) ṅ before gutturals,
+      b) ñ before palatals,
+      c) ṇ before cerebrals,
+      d) n before dentals, and
+      e) m before labials.
+}
+
+tests {
+  test "অসমীয়া কবিতা", "asmīẏā kbitā"
+  test "কবিৰ আজি জন্মদিন", "kbir āji jnmdin"
+  test "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড", "bēruṭt ēmāhr pāchtē punr bhẏṅkr agnikāṇḍ"
+  test "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ", "bhṅār biruddhē āvēdn dākhil kṅgnār"
+  test "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি", "āpuni pd̂hi bhāl pāb prā bātri"
+  test "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক", "śrīrāmpurt grubhrti ṭrāk jbd, dujnk āṭk"
+  test "কেনে আছে প্ৰাক্তন", "kēnē āchē prāktn"
+  test "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ", "kmumbāir mēẏrr dēht kŏbhiḍ pjiṭibh"
+  test "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা", "ṭuiṭāryŏgē khŏd sdrī krē ēi kthā"
+  test "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়", "lkhimpur jilār nārāẏṇpurr brpthārt āji prśānti dhām nāmērē ēkhn bṛddhāśrmr śubhārmbh krā hẏ"
+}
+
+stage {
+
+  # RULES
+  # note
+    sub "\u0982", "ṅ", after: any("কখগঘঙ")
+    sub "\u0982", "ñ", after: any("চছজঝঞ")
+    sub "\u0982", "ṇ", after: any("টঠডড়ঢঢ়ণ")
+    sub "\u0982", "n", after: any("তৎথদধন")
+    sub "\u0982", "m", after: any("পফবভম")
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "অ", "a"
+    sub "আ", "ā"
+    sub "ই", "i"
+    sub "ঈ", "ī"
+    sub "উ", "u"
+    sub "ঊ", "ū"
+    sub "ৠ", "ṛ"
+    sub "ঌ", "ḻ"
+    sub "এ", "ē"
+    sub "ঐ", "ai"
+    sub "ও", "ŏ"
+    sub "ঔ", "au"
+
+    # Consonants
+    # Gutturals
+    sub "ক", "k"
+    sub "খ", "kh"
+    sub "গ", "g"
+    sub "ঘ", "gh"
+    sub "ঙ", "ṅ"
+
+    # Palatals
+    sub "চ", "c"
+    sub "ছ", "ch"
+    sub "জ", "j"
+    sub "ঝ", "jh"
+    sub "ঞ", "ñ"
+
+    # Cerebrals
+    sub "ট", "ṭ"
+    sub "ঠ", "ṭh"
+    sub "ড", "ḍ"
+    sub "ড়", "d̂"
+    sub "ঢ", "ḍh"
+    sub "ঢ়", "d̂h"
+    sub "ণ", "ṇ"
+
+    # Dentals
+    sub "ত", "t"
+    sub "ৎ", "t"
+    sub "থ", "th"
+    sub "দ", "d"
+    sub "ধ", "dh"
+    sub "ন", "n"
+
+    # Labials
+    sub "প", "p"
+    sub "ফ", "ph"
+    sub "ব", "b"
+    sub "ভ", "bh"
+    sub "ম", "m"
+
+    # Semivowels
+    sub "য", "y"
+    sub "য়", "ẏ"
+    sub "য়", "ẏ"
+    sub "ৰ", "r"
+    sub "ল", "l"
+    sub "ৱ", "v"
+
+
+    # Sibilants
+    sub "শ", "ś"
+    sub "ষ", "ṣ"
+    sub "স", "s"
+
+
+    # Aspirate
+    sub "হ", "h"
+
+    # Chandrabindu
+    sub "ঁ", "m"
+
+    # Bisarga
+    sub "ঃ ", "ḥ"
+
+    # Anusvāra
+    sub "ং", "ṃ"
+
+    # 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", "ē"
+    sub "\u09c8", "ai"
+    sub "\u09cb", "ŏ"
+    sub "\u09cc", "au"
+    sub "\u09CD", "" # Used for joining
+    sub "्", ""
+    sub "़", ""
+    sub "।", "."
+    sub "‍", "" # Used for joining
+  }
+
+  compose
+}
+

data/maps/bis-ben-Beng-Latn-13194-1991.imp

@@ -0,0 +1,151 @@
+metadata {
+  authority_id: bis
+  id: 1991
+  language: iso-639-2:ben
+  source_script: Beng
+  destination_script: Latn
+  name: Indian script code for information interchange - ISCII - Bengali Romanization
+
+  #url:
+  creation_date: 1991
+  description: |
+    IS 13194 (1991): Indian script code for information
+    interchange - ISCII [LITD 20: Indian Language Technologies
+    and Products]
+
+  notes:
+    - |
+      Exception: Anusvāra is transliterated by:
+
+      a) ṅ before gutturals,
+      b) ñ before palatals,
+      c) ṇ before cerebrals,
+      d) n before dentals, and
+      e) m before labials.
+}
+
+tests {
+  test "টিকা", "ṭikā"
+  test "শুরু", "śuru"
+  test "করোনাভাইরাসের উপসর্গ রয়েছে এমন ভ্রমণকারীদের শনাক্ত করতেই এ ব্যবস্থা নেওয়া হয়", "krŏnābhāirāsēr upsrg rẏēchē ēmn bhrmṇkārīdēr śnākt krtēi ē bybsthā nēŏẏā hẏ"
+  test "চীন এ ভাইরাসের সংক্রমণ ছড়িয়ে পড়ার বিষয়টি নিশ্চিত করার পর এ অঞ্চলের দেশগুলো নিজেদের বন্দরগুলোতে নজরদারি শুরু করে", "cīn ē bhāirāsēr sṅkrmṇ chd̂iẏē pd̂ār biṣẏṭi niścit krār pr ē añclēr dēśgulŏ nijēdēr bndrgulŏtē njrdāri śuru krē"
+  test "আপনার কি মনে হয়, দক্ষিণ এশিয়ার দেশগুলো সফলভাবে এ সুযোগের সদ্ব্যবহার করতে পেরেছে?", "āpnār ki mnē hẏ, dkṣiṇ ēśiẏār dēśgulŏ sphlbhābē ē suyŏgēr sdbybhār krtē pērēchē?"
+  test "এরপর এ ভাইরাসের সংক্রমণ দক্ষিণ এশিয়ায় ছড়িয়ে পড়ার আগে এ অঞ্চলের দেশগুলো চলতি বছরের শুরুর দিকে মহামারি মোকাবিলায় কয়েক মাস সময় পেয়েছিল", "ērpr ē bhāirāsēr sṅkrmṇ dkṣiṇ ēśiẏāẏ chd̂iẏē pd̂ār āgē ē añclēr dēśgulŏ clti bchrēr śurur dikē mhāmāri mŏkābilāẏ kẏēk mās smẏ pēẏēchil"
+  test "ন্যূনতম শেয়ার না থাকলে ছাড়তেই হবে পরিচালক পদ", "nyūntm śēẏār nā thāklē chād̂tēi hbē pricālk pd"
+  test "বিজন কুমার শীলের ‘ওয়ার্ক পারমিট’ পেতে অনিশ্চয়তা", "bijn kumār śīlēr ‘ŏẏārk pārmiṭ’ pētē aniścẏtā"
+  test "বাংলাদেশে হার্ড ইমিউনিটি তৈরি হওয়ার তথ্য–প্রমাণ মেলেনি", "bāṃlādēśē hārḍ imiuniṭi tairi hŏẏār tthy–prmāṇ mēlēni"
+  test "চীনে গত বছর করোনাভাইরাসের মহামারির সূত্রপাত হয়", "cīnē gt bchr krŏnābhāirāsēr mhāmārir sūtrpāt hẏ"
+}
+
+stage {
+
+  # RULES
+  # note
+  sub "\u0982", "ṅ", after: any("কখগঘঙ")
+  sub "\u0982", "ñ", after: any("চছজঝঞ")
+  sub "\u0982", "ṇ", after: any("টঠডড়ঢঢ়ণ")
+  sub "\u0982", "n", after: any("তৎথদধন")
+  sub "\u0982", "m", after: any("পফবভম")
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "অ", "a"
+    sub "আ", "ā"
+    sub "ই", "i"
+    sub "ঈ", "ī"
+    sub "উ", "u"
+    sub "ঊ", "ū"
+    sub "ৠ", "ṛ"
+    sub "ঌ", "ḻ"
+    sub "এ", "ē"
+    sub "ঐ", "ai"
+    sub "ও", "ŏ"
+    sub "ঔ", "au"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "ক", "k"
+    sub "খ", "kh"
+    sub "গ", "g"
+    sub "ঘ", "gh"
+    sub "ঙ", "ṅ"
+
+    # Palatals
+    sub "চ", "c"
+    sub "ছ", "ch"
+    sub "জ", "j"
+    sub "ঝ", "jh"
+    sub "ঞ", "ñ"
+
+    # Cerebrals
+    sub "ট", "ṭ"
+    sub "ঠ", "ṭh"
+    sub "ড", "ḍ"
+    sub "ড়", "d̂"
+    sub "ঢ", "ḍh"
+    sub "ঢ়", "d̂h"
+    sub "ণ", "ṇ"
+
+    # Dentals
+    sub "ত", "t"
+    sub "ৎ", "t"
+    sub "থ", "th"
+    sub "দ", "d"
+    sub "ধ", "dh"
+    sub "ন", "n"
+
+    # Labials
+    sub "প", "p"
+    sub "ফ", "ph"
+    sub "ব", "b"
+    sub "ভ", "bh"
+    sub "ম", "m"
+
+    # Semivowels
+    sub "য", "y"
+    sub "য়", "ẏ"
+    sub "য়", "ẏ"
+    sub "র", "r"
+    sub "ল", "l"
+
+    # Sibilants
+    sub "শ", "ś"
+    sub "ষ", "ṣ"
+    sub "স", "s"
+
+
+    # Aspirate
+    sub "হ", "h"
+
+    # Chandrabindu
+    sub "ঁ", "m"
+
+    # Bisarga
+    sub "ঃ ", "ḥ"
+
+    # Anusvāra
+    sub "ং", "ṃ"
+
+    # 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", "ē"
+    sub "\u09c8", "ai"
+    sub "\u09cb", "ŏ"
+    sub "\u09cc", "au"
+    sub "\u09CD", "" # Used for joining
+    sub "्", ""
+    sub "़", ""
+    sub "।", "."
+    sub "‍", "" # Used for joining
+  }
+
+  compose
+}

data/maps/bis-dev-Deva-Latn-13194-1991.imp

@@ -0,0 +1,178 @@
+metadata {
+  authority_id: bis
+  id: 1991
+  language: iso-639-2:dev
+  source_script: Deva
+  destination_script: Latn
+  name: Indian script code for information interchange - ISCII - Devanagri Romanization
+
+  #url:
+  creation_date: 1991
+  description: |
+    IS 13194 (1991): Indian script code for information
+    interchange - ISCII [LITD 20: Indian Language Technologies
+    and Products]
+
+  notes:
+    - |
+      Exception: Anusvāra is transliterated by:
+
+      a) ṅ before gutturals,
+      b) ñ before palatals,
+      c) ṇ before cerebrals,
+      d) n before dentals, and
+      e) m before labials.
+}
+
+tests {
+  test "हम", "hm"
+  test "मीन", "mīn"
+  test "औसत", "aust"
+  test "माँ", "mām"
+  test "ट्रंप बोले, चीन को देश बेच देगा बिडेन परिवार, वैक्सीन लाने की कोशिशों में अड़ंगा डालने का लगाया आरोप", "ṭrmp bōlē, cīn kō dēś bēc dēgā biḍēn privār, vaiksīn lānē kī kōśiśōṃ mēṃ aḍṅgā ḍālnē kā lgāyā ārōp"
+  test "चालबाज चीन से तनातनी के बीच पश्चिमी मोर्चे को लगातार मजबूत कर रही वायुसेना", "cālbāj cīn sē tnātnī kē bīc pścimī mōrcē kō lgātār mjbūt kr rhī vāyusēnā"
+  test "चीन ने पांचों भारतीय नागरिकों को रिहा किया, PLA ने किया था अगवा", "cīn nē pāñcōṃ bhārtīy nāgrikōṃ kō rihā kiyā, PLA nē kiyā thā agvā"
+  test "पूर्व नौसेना अधिकारी मदन शर्मा से रक्षा मंत्री राजनाथ सिंह ने की बात, कहा- ऐसे हमले हैं अस्वीकार्य", "pūrv nausēnā adhikārī mdn śrmā sē rkṣā mntrī rājnāth siṃh nē kī bāt, khā- aisē hmlē haiṃ asvīkāry"
+  test "सात दिन बाद ही छोड़ दिया ससुराल", "sāt din bād hī chōd̂ diyā ssurāl"
+  test "राजस्‍थान में फि‍र खींचतान, पायलट ने गहलोत को लिखा पत्र, याद दिलाया घोषणा-पत्र, कहा- नाखुश है गुर्जर समाज", "rājsthān mēṃ phir khīñctān, pāylṭ nē ghlōt kō likhā ptr, yād dilāyā ghōṣṇā-ptr, khā- nākhuś hai gurjr smāj"
+}
+
+stage {
+
+  # RULES
+  # note
+  sub "\u0902", "ṅ", after: any("कखगघङ")
+  sub "\u0902", "ñ", after: any("चछजझञ")
+  sub "\u0902", "ṇ", after: any("टठडढण")
+  sub "\u0902", "n", after: any("तथदधन")
+  sub "\u0902", "m", after: any("पफबभम")
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "अ", "a"
+    sub "आ", "ā"
+    sub "इ", "i"
+    sub "ई", "ī"
+    sub "उ", "u"
+    sub "ऊ", "ū"
+    sub "ऋ", "ṛ"
+    sub "ॠ", "ṝ"
+    sub "ऌ", "ḻ"
+    sub "ॡ", "ḹ"
+
+    sub "ए", "ē"
+    sub "ऐ", "ai"
+    sub "ऍ", "ê"
+
+    sub "ऒ", "o"
+    sub "ओ", "ŏ"
+    sub "औ", "au"
+    sub "ऑ", "ô"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "k"
+    sub "ख", "kh"
+    sub "ग", "g"
+    sub "घ", "gh"
+    sub "ङ", "ṅ"
+
+    # Palatals
+    sub "च", "c"
+    sub "छ", "ch"
+    sub "ज", "j"
+    sub "झ", "jh"
+    sub "ञ", "ñ"
+
+    # Cerebrals
+    sub "ट", "ṭ"
+    sub "ठ", "ṭh"
+    sub "ड", "ḍ"
+    sub "ढ", "ḍh"
+    sub "ण", "ṇ"
+
+    # Dentals
+    sub "त", "t"
+    sub "थ", "th"
+    sub "द", "d"
+    sub "ध", "dh"
+    sub "न", "n"
+    sub "ऩ", "ṉ"
+
+    # Labials
+    sub "प", "p"
+    sub "फ", "ph"
+    sub "ब", "b"
+    sub "भ", "bh"
+    sub "म", "m"
+
+    # Semivowels
+    sub "य", "y"
+    sub "य़", "ẏ"
+    sub "र", "r"
+    sub "ऱ", "ṟ"
+    sub "ल", "l"
+    sub "ळ", "ḷ"
+    sub "ऴ", "ẕ"
+
+
+    sub "व", "v"
+
+    # Sibilants
+    sub "श", "ś"
+    sub "ष", "ṣ"
+    sub "स", "s"
+
+
+    # Aspirate
+    sub "ह", "h"
+
+
+    #Nukta Constants
+
+    sub "क़", "q"
+    sub "ख़", "ḵẖ"
+    sub "ग़", "gẖ"
+    sub "ज़", "z"
+    sub "ड़", "d̂"
+    sub "ढ़", "d̂h"
+    sub "फ़", "f"
+
+    # Chandrabindu
+    sub "ँ", "m"
+
+    # Bisarga
+    sub "ः ", "ḥ"
+
+    # Anusvāra
+    sub "ं", "ṃ"
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ृ", "ṛ"
+
+
+    sub "ॆ", "e"
+    sub "े", "ē"
+    sub "ै", "ai"
+    sub "ॅ", "ê"
+
+
+    sub "ॊ", "o"
+    sub "ो", "ō"
+    sub "ौ", "au"
+    sub "ॉ", "ô"
+    sub "्", ""
+    sub "़", ""
+    sub "।", "."
+    sub "‍", "" # no need for zero with joiner
+  }
+
+  compose
+}