interscript-maps 2.0.5

data/maps/din-pra-Deva-Latn-33904-2018.imp

@@ -0,0 +1,66 @@
+metadata {
+  authority_id: din
+  id: 33904-2018
+  language: iso-639-2:pra
+  source_script: Deva
+  destination_script: Latn
+  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Prakit"
+  url: https://www.beuth.de/en/standard/din-33904/293049024
+  creation_date: 2018
+  description: |
+    Prakit system.
+
+    This standard specifies the transliteration of all languages of the Devanāgarī characters into Latin letters firmly.
+    It is suitable for any application.
+
+  notes:
+    - |
+      Vowels:
+      The Ardhacandra ॅ is often used to denote English vowels:
+      EXAMPLE
+      बॅट     bêṭa       (bat)
+      डॉक्टर  ḍôkṭara (doctor)
+    - |
+      Consonants:
+
+      Since the Devanāgarī script is a syllabic script, it becomes -a inherent in the consonant.
+      Always written during transliteration, also in the final part
+      EXAMPLE 1
+      पुस्तक   pustaka
+
+      A line under the consonant, the so-called Virāma, means in the Devanāgarī script that that inherent -a not applicable.
+      EXAMPLE 2
+      वाक्   vāk
+
+      The anusvāra is always represented with -ṃ-.
+      EXAMPLE 3
+      संसकरण saṃskaraṇa
+
+      Before k, kh, g, gh, c, ch, j, jh, ṭ, ṭh, ḍ, ḍh, t, th, d, dh, p, ph, b, bh, the anusvāra becomes the class nasal transformed.
+      EXAMPLE 4
+      तंघी   kaṃghī becomes kaṅghī
+      पंजाबी  paṃjābī becomes pañjābī
+      पंडित  paṃḍita becomes paṇḍita
+      संधी   saṃdhī becomes sandhī
+      दिसंबर  disaṃbara becomes disambara
+
+      Anunāsika or Candrabindu signals the nasalization of vowels
+
+      EXAMPLE 5
+      माँ māṁ
+}
+
+tests {
+  test "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि", "sṛṣṭisthitivināśānāṃ śaktibhūte sanātani"
+  test "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते", "guṇāśraye guṇamaye nārāyaṇi namo’stu te"
+  test "तेन समयेन बुद्धो भगवा सावत्थियं विहरति जेतवने अनाथपिण्डिकस्स आरामे", "tena samayena buddho bhagavā sāvatthiyaṃ viharati jetavane anāthapiṇḍikassa ārāme"
+}
+
+dependency "din-san-Deva-Latn-33904-2018", as: devalatn
+
+stage {
+
+  run map.devalatn.stage.main
+
+}
+

data/maps/din-san-Deva-Latn-33904-2018.imp

@@ -0,0 +1,294 @@
+metadata {
+  authority_id: din
+  id: 33904-2018
+  language: iso-639-2:san
+  source_script: Deva
+  destination_script: Latn
+  name: "DIN 33904:2018-10 Information and documentation - Romanization Devanagari, Sanskrit"
+  url: https://www.beuth.de/en/standard/din-33904/293049024
+  creation_date: 2018
+  description: |
+    Sanskrit system.
+
+    This standard specifies the transliteration of all languages of the Devanāgarī characters into Latin letters firmly.
+    It is suitable for any application.
+
+  notes:
+    - |
+      Vowels:
+      The Ardhacandra ॅ is often used to denote English vowels:
+      EXAMPLE
+      बॅट     bêṭa       (bat)
+      डॉक्टर  ḍôkṭara (doctor)
+    - |
+      Consonants:
+
+      Since the Devanāgarī script is a syllabic script, it becomes -a inherent in the consonant.
+      Always written during transliteration, also in the final part
+      EXAMPLE 1
+      पुस्तक   pustaka
+
+      A line under the consonant, the so-called Virāma, means in the Devanāgarī script that that inherent -a not applicable.
+      EXAMPLE 2
+      वाक्   vāk
+
+      The anusvāra is always represented with -ṃ-.
+      EXAMPLE 3
+      संसकरण saṃskaraṇa
+
+      Before k, kh, g, gh, c, ch, j, jh, ṭ, ṭh, ḍ, ḍh, t, th, d, dh, p, ph, b, bh, the anusvāra becomes the class nasal transformed.
+      EXAMPLE 4
+      तंघी   kaṃghī becomes kaṅghī
+      पंजाबी  paṃjābī becomes pañjābī
+      पंडित  paṃḍita becomes paṇḍita
+      संधी   saṃdhī becomes sandhī
+      दिसंबर  disaṃbara becomes disambara
+
+      Anunāsika or Candrabindu signals the nasalization of vowels
+
+      EXAMPLE 5
+      माँ māṁ
+}
+
+tests {
+  test "पुस्तक", "pustaka"
+  test "बॅट", "bêṭa"
+  test "वाक्", "vāk"
+  test "पंजाबी", "pañjābī"
+  test "डॉक्टर", "ḍôkṭara"
+  test "पंडित", "paṇḍita"
+  test "संधी", "sandhī"
+  test "दिसंबर", "disambara"
+  test "संसकरण", "saṃsakaraṇa"
+  test "माँ", "māṁ"
+  test "शुभाशुभपरित्यागी भक्तिमान्यः स मे प्रियः", "śubhāśubhaparityāgī bhaktimānyaḥ sa me priyaḥ"
+  test "सत्य -सत्यमेवेश्वरो लोके सत्ये धर्मः सदाश्रितः", "satya -satyameveśvaro loke satye dharmaḥ sadāśritaḥ"
+  test "सत्यमूलनि सर्वाणि सत्यान्नास्ति परं पदम्", "satyamūlani sarvāṇi satyānnāsti paraṃ padam"
+  test "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ", "pitā mātāgnirātmā ca guruśca bharatarṣabha"
+  test "०१२३४५६७८९", "0123456789"
+}
+
+aliases {
+  def_alias deva_chars_1, any("\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C")
+}
+
+stage {
+
+  # RULES
+  sub "\u0902", "ṅ", after: any("कक़खख़गग़घङ")
+  sub "\u0902", "ñ", after: any("चछजज़झञ")
+  sub "\u0902", "ṇ", after: any("टट़ठडड़ढढ़ण")
+  sub "\u0902", "n", after: any("तथदधन")
+  sub "\u0902", "m", after: any("पफबभम")
+
+  sub "\u0902", "ñ", after: any("कखगघचछजझतथदधपफबभटठडढ")
+
+  sub "क", "k", after: deva_chars_1
+  sub "ख", "kh", after: deva_chars_1
+  sub "ग", "g", after: deva_chars_1
+  sub "घ", "gh", after: deva_chars_1
+  sub "ङ", "ṅ", after: deva_chars_1
+  sub "च", "c", after: deva_chars_1
+  sub "छ", "ch", after: deva_chars_1
+  sub "ज", "j", after: deva_chars_1
+  sub "झ", "jh", after: deva_chars_1
+  sub "ञ", "ñ", after: deva_chars_1
+  sub "ट", "ṭ", after: deva_chars_1
+  sub "ठ", "ṭh", after: deva_chars_1
+  sub "ड", "ḍ", after: deva_chars_1
+  sub "ढ", "ḍh", after: deva_chars_1
+  sub "ण", "ṇ", after: deva_chars_1
+  sub "त", "t", after: deva_chars_1
+  sub "थ", "th", after: deva_chars_1
+  sub "द", "d", after: deva_chars_1
+  sub "ध", "dh", after: deva_chars_1
+  sub "न", "n", after: deva_chars_1
+  sub "प", "p", after: deva_chars_1
+  sub "फ", "ph", after: deva_chars_1
+  sub "ब", "b", after: deva_chars_1
+  sub "भ", "bh", after: deva_chars_1
+  sub "म", "m", after: deva_chars_1
+  sub "य", "y", after: deva_chars_1
+  sub "र", "r", after: deva_chars_1
+  sub "ल", "l", after: deva_chars_1
+  sub "ळ", "ḷ", after: deva_chars_1
+  sub "व", "v", after: deva_chars_1
+  sub "श", "ś", after: deva_chars_1
+  sub "ष", "ṣ", after: deva_chars_1
+  sub "स", "s", after: deva_chars_1
+  sub "ह", "h", after: deva_chars_1
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    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", "ḷ"
+    sub "ए", "e"
+    sub "ऎ", "ĕ"
+    sub "ऐ", "ai"
+    sub "ओ", "o"
+    sub "ऒ", "ŏ"
+    sub "औ", "au"
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "ka"
+    sub "ख", "kha"
+    sub "ग", "ga"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "ca"
+    sub "छ", "cha"
+    sub "ज", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    sub "ढ", "ḍha"
+    sub "ण", "ṇa"
+
+    # Dentals
+    sub "त", "ta"
+    sub "थ", "tha"
+    sub "द", "da"
+    sub "ध", "dha"
+    sub "न", "na"
+
+    # Labials
+    sub "प", "pa"
+    sub "फ", "pha"
+    sub "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "ळ", "ḷa"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "śa"
+    sub "ष", "ṣa"
+    sub "स", "sa"
+
+    # Aspirate
+    sub "ह", "ha"
+
+    # Anusvāra
+    sub "ं", "ṃ"
+
+    # Bisarga
+    sub "ः", "ḥ"
+
+    # Anunāsika
+    sub "ँ", "ṁ"
+
+    # Abagraha
+    sub "ऽ", "’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ृ", "ṛ"
+    sub "ॄ", "ṝ"
+    sub "◌", "ṝ"
+    sub "ॢ", "ḷ"
+    sub "ॣ", "ḹ"
+    sub "े", "e"
+    sub "ै", "ai"
+    sub "ो", "o"
+    sub "ौ", "au"
+    sub "ॉ", "ô"
+    sub "ॅ", "ê"
+    sub "‍", "" # Used for joining
+
+
+
+    # For consonant Virāma
+    # Gutturals
+    sub "क्", "k"
+    sub "ख्", "kh"
+    sub "ग्", "g"
+    sub "घ्", "gh"
+    sub "ङ्", "ṅ"
+
+    # Palatals
+    sub "च्", "c"
+    sub "छ्", "ch"
+    sub "ज्", "j"
+    sub "झ्", "jh"
+    sub "ञ्", "ñ"
+
+    # Cerebrals
+    sub "ट्", "ṭ"
+    sub "ठ्", "ṭh"
+    sub "ड्", "ḍ"
+    sub "ढ्", "ḍh"
+    sub "ण्", "ṇ"
+
+    # Dentals
+    sub "त्", "t"
+    sub "थ्", "th"
+    sub "द्", "d"
+    sub "ध्", "dh"
+    sub "न्", "n"
+
+    # Labials
+    sub "प्", "p"
+    sub "फ्", "ph"
+    sub "ब्", "b"
+    sub "भ्", "bh"
+    sub "म्", "m"
+
+    # Semivowels
+    sub "य्", "y"
+    sub "र्", "r"
+    sub "ल्", "l"
+    sub "ळ्", "ḷ"
+    sub "व्", "v"
+
+    # Sibilants
+    sub "श्", "ś"
+    sub "ष्", "ṣ"
+    sub "स्", "s"
+
+    # Aspirate
+    sub "ह्", "h"
+
+    # digits
+
+    sub "०", "0"
+    sub "१", "1"
+    sub "२", "2"
+    sub "३", "3"
+    sub "४", "4"
+    sub "५", "5"
+    sub "६", "6"
+    sub "७", "7"
+    sub "८", "8"
+    sub "९", "9"
+  }
+
+  compose
+}

data/maps/din-tam-Taml-Latn-33903-2016.imp

@@ -0,0 +1,187 @@
+metadata {
+  authority_id: din
+  id: 33903-2016
+  language: iso-639-2:tam
+  source_script: Taml
+  destination_script: Latn
+  name: "DIN 33903:2016-02: Information und Dokumentation - Umschrift Tamil"
+  url: https://www.beuth.de/de/norm/din-33903/247150527
+  creation_date: 2018
+  description: |
+    This standard specifies the transcription of the letters of the
+    Tamil alphabet in Latin letters. It is based on international
+    standards as well as on the preprint of the alphabetical tables,
+    which were published in 1976 with the introduction of the rules for
+    alphabetical cataloging. It can be used in all areas, but in
+    particular the aim is to standardize the library and publication
+    area.
+
+  notes:
+    - |
+      Since the Tamil script is a syllabic script, the consonant -a inherent in the transliteration is always written, even in the final.
+
+    - |
+      A point above the consonant, the so-called "pulli", means in Tamil that the inherent -a is omitted:
+        கார்த்திகேயன் kārttikēyaṉ
+    - |
+      Tamil has no anusvara; in contrast to other South Asian scripts, the class nasal is always written.
+    - |
+      Tamil also has no ligatures.
+}
+
+tests {
+  test "கார்த்திகேயன்", "kārttikēyaṉ"
+  test "௲", "1000"
+  test "இளைஞர்களின் உறுதியான மனநிலையை பிரதிபலிக்கிறது: நீட் தேர்வில் ௮௫-௯௦ சதவீத மாணவர்கள் பங்கேற்பு - ரமேஷ் பொக்ரியால்", "iḷaiñarkaḷiṉ uṟutiyāṉa maṉanilaiyai piratipalikkiṟatu: nīṭ tērvil 85-90 catavīta māṇavarkaḷ paṅkēṟpu - ramēṣ pokriyāl"
+  test "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்", "nāṭāḷumaṉṟattil 4 macōtākkaḷai etirkka kāṅkiras muṭivu - jeyarām ramēṣ"
+  test "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி", "karnāṭakāvil mēlum 9,894 pērukku korōṉā toṟṟu uṟuti"
+  test "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?", "aitarāpāttukku kaikoṭukkumā atiraṭi?"
+  test "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்", "amerikka ōpaṉ ṭeṉṉis: iṟutippōṭṭiyil ṭomiṉik-sverēv"
+  test "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்", "ai.pi.el. kirikkeṭṭil kaḷam iṟaṅkum amerikka vīrar"
+  test "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்", "amerikka ōpaṉ ṭeṉṉis; navōmi ocākā cāmpiyaṉ paṭṭam veṉṟār"
+  test "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்", "putiya kalvikkoḷkaikku etirppu: muṉṉāḷ tuṇaivēntarkaḷ 20 pēr piratamarukku kaṭitam"
+  test "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு", "inta āṇṭu ai.pi.el. kōppaiyai enta aṇi vellum? - keviṉ pīṭṭarcaṉ kaṇippu"
+  test "இந்திய எண்ணெய் கப்பலில் தீ: விபத்து குறித்த எச்சரிக்கையை கப்பல் அதிகாரிகள் புறக்கணித்தனர் - இலங்கை கோர்ட்டு தகவல்", "intiya eṇṇey kappalil tī: vipattu kuṟitta eccarikkaiyai kappal atikārikaḷ puṟakkaṇittaṉar - ilaṅkai kōrṭṭu takaval"
+}
+
+aliases {
+  def_alias taml_chars_1, any("\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C")
+}
+
+stage {
+
+  # RULES
+    sub "க", "k", after: taml_chars_1
+    sub "ங", "ṅ", after: taml_chars_1
+    sub "ச", "c", after: taml_chars_1
+    sub "ஞ", "ñ", after: taml_chars_1
+    sub "ட", "ṭ", after: taml_chars_1
+    sub "ண", "ṇ", after: taml_chars_1
+    sub "த", "t", after: taml_chars_1
+    sub "ந", "n", after: taml_chars_1
+    sub "ப", "p", after: taml_chars_1
+    sub "ம", "m", after: taml_chars_1
+    sub "ய", "y", after: taml_chars_1
+    sub "ர", "r", after: taml_chars_1
+    sub "ல", "l", after: taml_chars_1
+    sub "ள", "ḷ", after: taml_chars_1
+    sub "ழ", "ḻ", after: taml_chars_1
+    sub "வ", "v", after: taml_chars_1
+    sub "ற", "ṟ", after: taml_chars_1
+    sub "ன", "ṉ", after: taml_chars_1
+    sub "ஜ", "j", after: taml_chars_1
+    sub "ஶ", "ś", after: taml_chars_1
+    sub "ஷ", "ṣ", after: taml_chars_1
+    sub "ஸ", "s", after: taml_chars_1
+    sub "ஹ", "h", after: taml_chars_1
+
+
+  # CHARACTERS
+  parallel {
+    sub "அ", "a"
+    sub "ஆ", "ā"
+    sub "ா", "ā"
+
+    sub "இ", "i"
+    sub "ி", "i"
+
+    sub "ஈ", "ī"
+    sub "ீ", "ī"
+
+    sub "உ", "u"
+    sub "ு", "u"
+
+    sub "ஊ", "ū"
+    sub "ூ", "ū"
+
+    sub "ெ", "e"
+    sub "எ", "e"
+
+    sub "ே", "ē"
+    sub "ஏ", "ē"
+
+    sub "ஐ", "ai"
+    sub "ை", "ai"
+
+    sub "ஒ", "o"
+    sub "ொ", "o"
+
+    sub "ோ", "ō"
+    sub "ஓ", "ō"
+
+    sub "ஔ", "au"
+    sub "ௌ", "au"
+
+    sub "க்", "k"
+    sub "ங்", "ṅ"
+    sub "ச்", "c"
+    sub "ஞ்", "ñ"
+    sub "ட்", "ṭ"
+    sub "ண்", "ṇ"
+    sub "த்", "t"
+    sub "ந்", "n"
+    sub "ப்", "p"
+    sub "ம்", "m"
+    sub "ய்", "y"
+    sub "ர்", "r"
+    sub "ல்", "l"
+    sub "ள்", "ḷ"
+    sub "ழ்", "ḻ"
+    sub "வ்", "v"
+    sub "ற்", "ṟ"
+    sub "ன்", "ṉ"
+    sub "ஜ்", "j"
+
+    sub "ஶ்", "ś"
+    sub "ஷ்", "ṣ"
+    sub "ஸ்", "s"
+    sub "ஹ்", "h"
+
+
+    sub "க", "ka"
+    sub "ங", "ṅa"
+    sub "ஃ", "ḵ"
+    sub "ச", "ca"
+    sub "ஞ", "ña"
+    sub "ட", "ṭa"
+    sub "ண", "ṇa"
+    sub "த", "ta"
+    sub "ந", "na"
+    sub "ப", "pa"
+    sub "ம", "ma"
+    sub "ய", "ya"
+    sub "ர", "ra"
+    sub "ல", "la"
+    sub "ள", "ḷa"
+    sub "ழ", "ḻa"
+    sub "வ", "va"
+    sub "ற", "ṟa"
+    sub "ன", "ṉa"
+    sub "ஜ", "ja"
+    sub "ஶ", "śa"
+    sub "ஷ", "ṣa"
+    sub "ஸ", "sa"
+    sub "ஹ", "ha"
+
+    # Digits
+    sub "௧", "1"
+    sub "௨", "2"
+    sub "௩", "3"
+    sub "௪", "4"
+    sub "௫", "5"
+    sub "௬", "6"
+    sub "௭", "7"
+    sub "௮", "8"
+    sub "௯", "9"
+    sub "௦", "0"
+    sub "௰", "10"
+    sub "௱", "100"
+    sub "௲", "1000"
+
+
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+  }
+
+  compose
+}