interscript-maps 2.4.2 → 2.5.0

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

@@ -0,0 +1,425 @@
+system "DIN:san-Deva:Latn:33904-2018" {
+
+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 {
+    note "      Vowels:\n      The Ardhacandra ॅ is often used to denote English vowels:\n      EXAMPLE\n      बॅट     bêṭa       (bat)\n      डॉक्टर  ḍôkṭara (doctor)"
+    note "      Consonants:\n\n      Since the Devanāgarī script is a syllabic script, it becomes -a inherent in the consonant.\n      Always written during transliteration, also in the final part\n      EXAMPLE 1\n      पुस्तक   pustaka\n\n      A line under the consonant, the so-called Virāma, means in the Devanāgarī script that that inherent -a not applicable.\n      EXAMPLE 2\n      वाक्   vāk\n\n      The anusvāra is always represented with -ṃ-.\n      EXAMPLE 3\n      संसकरण saṃskaraṇa\n\n      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.\n      EXAMPLE 4\n      तंघी   kaṃghī becomes kaṅghī\n      पंजाबी  paṃjābī becomes pañjābī\n      पंडित  paṃḍita becomes paṇḍita\n      संधी   saṃdhī becomes sandhī\n      दिसंबर  disaṃbara becomes disambara\n\n      Anunāsika or Candrabindu signals the nasalization of vowels\n\n      EXAMPLE 5\n      माँ māṁ"
+  }
+}
+
+tests {
+   "पुस्तक" ->  "pustaka"
+   "बॅट" ->  "bêṭa"
+   "वाक्" ->  "vāk"
+   "पंजाबी" ->  "pañjābī"
+   "डॉक्टर" ->  "ḍôkṭara"
+   "पंडित" ->  "paṇḍita"
+   "संधी" ->  "sandhī"
+   "दिसंबर" ->  "disambara"
+   "संसकरण" ->  "saṃsakaraṇa"
+   "माँ" ->  "māṁ"
+   "शुभाशुभपरित्यागी भक्तिमान्यः स मे प्रियः" ->  "śubhāśubhaparityāgī bhaktimānyaḥ sa me priyaḥ"
+   "सत्य -सत्यमेवेश्वरो लोके सत्ये धर्मः सदाश्रितः" ->  "satya -satyameveśvaro loke satye dharmaḥ sadāśritaḥ"
+   "सत्यमूलनि सर्वाणि सत्यान्नास्ति परं पदम्" ->  "satyamūlani sarvāṇi satyānnāsti paraṃ padam"
+   "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ" ->  "pitā mātāgnirātmā ca guruśca bharatarṣabha"
+   "०१२३४५६७८९" ->  "0123456789"
+}
+
+aliases {
+  deva_chars_1 = any("\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C")
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from "\u0902"
+    to "ṅ"
+    after any("कक़खख़गग़घङ")
+  }
+  sub {
+    from "\u0902"
+    to "ñ"
+    after any("चछजज़झञ")
+  }
+  sub {
+    from "\u0902"
+    to "ṇ"
+    after any("टट़ठडड़ढढ़ण")
+  }
+  sub {
+    from "\u0902"
+    to "n"
+    after any("तथदधन")
+  }
+  sub {
+    from "\u0902"
+    to "m"
+    after any("पफबभम")
+  }
+
+  sub {
+    from "\u0902"
+    to "ñ"
+    after any("कखगघचछजझतथदधपफबभटठडढ")
+  }
+
+  sub {
+    from "क"
+    to "k"
+    after deva_chars_1
+  }
+  sub {
+    from "ख"
+    to "kh"
+    after deva_chars_1
+  }
+  sub {
+    from "ग"
+    to "g"
+    after deva_chars_1
+  }
+  sub {
+    from "घ"
+    to "gh"
+    after deva_chars_1
+  }
+  sub {
+    from "ङ"
+    to "ṅ"
+    after deva_chars_1
+  }
+  sub {
+    from "च"
+    to "c"
+    after deva_chars_1
+  }
+  sub {
+    from "छ"
+    to "ch"
+    after deva_chars_1
+  }
+  sub {
+    from "ज"
+    to "j"
+    after deva_chars_1
+  }
+  sub {
+    from "झ"
+    to "jh"
+    after deva_chars_1
+  }
+  sub {
+    from "ञ"
+    to "ñ"
+    after deva_chars_1
+  }
+  sub {
+    from "ट"
+    to "ṭ"
+    after deva_chars_1
+  }
+  sub {
+    from "ठ"
+    to "ṭh"
+    after deva_chars_1
+  }
+  sub {
+    from "ड"
+    to "ḍ"
+    after deva_chars_1
+  }
+  sub {
+    from "ढ"
+    to "ḍh"
+    after deva_chars_1
+  }
+  sub {
+    from "ण"
+    to "ṇ"
+    after deva_chars_1
+  }
+  sub {
+    from "त"
+    to "t"
+    after deva_chars_1
+  }
+  sub {
+    from "थ"
+    to "th"
+    after deva_chars_1
+  }
+  sub {
+    from "द"
+    to "d"
+    after deva_chars_1
+  }
+  sub {
+    from "ध"
+    to "dh"
+    after deva_chars_1
+  }
+  sub {
+    from "न"
+    to "n"
+    after deva_chars_1
+  }
+  sub {
+    from "प"
+    to "p"
+    after deva_chars_1
+  }
+  sub {
+    from "फ"
+    to "ph"
+    after deva_chars_1
+  }
+  sub {
+    from "ब"
+    to "b"
+    after deva_chars_1
+  }
+  sub {
+    from "भ"
+    to "bh"
+    after deva_chars_1
+  }
+  sub {
+    from "म"
+    to "m"
+    after deva_chars_1
+  }
+  sub {
+    from "य"
+    to "y"
+    after deva_chars_1
+  }
+  sub {
+    from "र"
+    to "r"
+    after deva_chars_1
+  }
+  sub {
+    from "ल"
+    to "l"
+    after deva_chars_1
+  }
+  sub {
+    from "ळ"
+    to "ḷ"
+    after deva_chars_1
+  }
+  sub {
+    from "व"
+    to "v"
+    after deva_chars_1
+  }
+  sub {
+    from "श"
+    to "ś"
+    after deva_chars_1
+  }
+  sub {
+    from "ष"
+    to "ṣ"
+    after deva_chars_1
+  }
+  sub {
+    from "स"
+    to "s"
+    after deva_chars_1
+  }
+  sub {
+    from "ह"
+    to "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" "’"
+
+    # Medials # Needed for connecting constants
+    sub "ा" "ā"
+    sub "ि" "i"
+    sub "ी" "ī"
+    sub "ु" "u"
+    sub "ू" "ū"
+    sub "ृ" "ṛ"
+    sub "ॄ" "ṝ"
+    sub "ॢ" "ḷ"
+    sub "ॣ" "ḹ"
+    sub "े" "e"
+    sub "ै" "ai"
+    sub "ो" "o"
+    sub "ौ" "au"
+    sub "ॉ" "ô"
+    sub "ॅ" "ê"
+    sub "‍" ""
+
+
+
+    # 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.isc

@@ -0,0 +1,278 @@
+system "DIN:tam-Taml:Latn:33903-2016" {
+
+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 {
+    note "      Since the Tamil script is a syllabic script, the consonant -a inherent in the transliteration is always written, even in the final."
+
+    note "      A point above the consonant, the so-called \"pulli\", means in Tamil that the inherent -a is omitted:\n        கார்த்திகேயன் kārttikēyaṉ"
+    note "      Tamil has no anusvara; in contrast to other South Asian scripts, the class nasal is always written."
+    note "      Tamil also has no ligatures."
+  }
+}
+
+tests {
+   "கார்த்திகேயன்" ->  "kārttikēyaṉ"
+   "௲" ->  "1000"
+   "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"
+   "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்" ->  "nāṭāḷumaṉṟattil 4 macōtākkaḷai etirkka kāṅkiras muṭivu - jeyarām ramēṣ"
+   "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி" ->  "karnāṭakāvil mēlum 9,894 pērukku korōṉā toṟṟu uṟuti"
+   "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?" ->  "aitarāpāttukku kaikoṭukkumā atiraṭi?"
+   "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்" ->  "amerikka ōpaṉ ṭeṉṉis: iṟutippōṭṭiyil ṭomiṉik-sverēv"
+   "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்" ->  "ai.pi.el. kirikkeṭṭil kaḷam iṟaṅkum amerikka vīrar"
+   "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்" ->  "amerikka ōpaṉ ṭeṉṉis; navōmi ocākā cāmpiyaṉ paṭṭam veṉṟār"
+   "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்" ->  "putiya kalvikkoḷkaikku etirppu: muṉṉāḷ tuṇaivēntarkaḷ 20 pēr piratamarukku kaṭitam"
+   "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு" ->  "inta āṇṭu ai.pi.el. kōppaiyai enta aṇi vellum? - keviṉ pīṭṭarcaṉ kaṇippu"
+   "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 {
+  taml_chars_1 = any("\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C")
+}
+
+stage main {
+
+  # RULES
+    sub {
+    from "க"
+    to "k"
+    after taml_chars_1
+  }
+    sub {
+    from "ங"
+    to "ṅ"
+    after taml_chars_1
+  }
+    sub {
+    from "ச"
+    to "c"
+    after taml_chars_1
+  }
+    sub {
+    from "ஞ"
+    to "ñ"
+    after taml_chars_1
+  }
+    sub {
+    from "ட"
+    to "ṭ"
+    after taml_chars_1
+  }
+    sub {
+    from "ண"
+    to "ṇ"
+    after taml_chars_1
+  }
+    sub {
+    from "த"
+    to "t"
+    after taml_chars_1
+  }
+    sub {
+    from "ந"
+    to "n"
+    after taml_chars_1
+  }
+    sub {
+    from "ப"
+    to "p"
+    after taml_chars_1
+  }
+    sub {
+    from "ம"
+    to "m"
+    after taml_chars_1
+  }
+    sub {
+    from "ய"
+    to "y"
+    after taml_chars_1
+  }
+    sub {
+    from "ர"
+    to "r"
+    after taml_chars_1
+  }
+    sub {
+    from "ல"
+    to "l"
+    after taml_chars_1
+  }
+    sub {
+    from "ள"
+    to "ḷ"
+    after taml_chars_1
+  }
+    sub {
+    from "ழ"
+    to "ḻ"
+    after taml_chars_1
+  }
+    sub {
+    from "வ"
+    to "v"
+    after taml_chars_1
+  }
+    sub {
+    from "ற"
+    to "ṟ"
+    after taml_chars_1
+  }
+    sub {
+    from "ன"
+    to "ṉ"
+    after taml_chars_1
+  }
+    sub {
+    from "ஜ"
+    to "j"
+    after taml_chars_1
+  }
+    sub {
+    from "ஶ"
+    to "ś"
+    after taml_chars_1
+  }
+    sub {
+    from "ஷ"
+    to "ṣ"
+    after taml_chars_1
+  }
+    sub {
+    from "ஸ"
+    to "s"
+    after taml_chars_1
+  }
+    sub {
+    from "ஹ"
+    to "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 "‍" ""
+    sub "‌" ""
+  }
+
+  compose
+}
+}