interscript-maps 2.0.5

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

@@ -0,0 +1,207 @@
+metadata {
+  authority_id: alalc
+  id: 2012
+  language: iso-639-2:san
+  source_script: Deva
+  destination_script: Latn
+  name: Sanskrit Romanization, 2012
+  url: https://www.loc.gov/catdir/cpso/romanization/sanskrit.pdf
+  creation_date: 2012
+  description: |
+    ALA-LC Romanization table for Sanskrit
+
+  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
+         virāma.
+
+    - |
+      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.
+      In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+    - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+}
+
+tests {
+  test "पूर्णमदः पूर्णमिदं पूर्णात् पूर्ण्मुदच्यते", "pūrṇamadaḥ pūrṇamidaṃ pūrṇāt pūrṇmudacyate"
+  test "पूर्णस्य पूर्णमादाय पूर्णमेवावशिष्यते", "pūrṇasya pūrṇamādāya pūrṇamevāvaśiṣyate"
+  test "यथा चतुर्भिः कनकं परीक्ष्यते निर्घषणच्छेदन तापताडनैः", "yathā caturbhiḥ kanakaṃ parīkṣyate nirghaṣaṇacchedana tāpatāḍanaiḥ"
+  test "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा", "tathā caturbhiḥ puruṣaḥ parīkṣyate tyāgena śīlena guṇena karmaṇā"
+  test "यो न हृष्यति न द्वेष्टि न शोचति न काङ्‍क्षति", "yo na hṛṣyati na dveṣṭi na śocati na kāṅkṣati"
+  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"
+}
+
+aliases {
+  def_alias deva_chars_1, any("\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d")
+}
+
+stage {
+
+  # RULES
+  # note [2]
+    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", "ḻ", 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
+  # note[3]
+    sub "\u0902", "ṅ", after: any("कखगघङ")
+    sub "\u0902", "ñ", after: any("चछजझञ")
+    sub "\u0902", "ṇ", after: any("टठडढण")
+    sub "\u0902", "n", after: any("तथदधन")
+
+
+  # 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 "ऐ", "ai"
+    sub "ओ", "o"
+    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", "ḻa"
+    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 "ँ", "m̐"
+
+    # Abagraha
+    sub "ऽ", "’" # (apostrophe)
+
+    #Jihvāmūlīya
+    sub "\u0CF1", "ẖ"
+
+    #Upadhmānīya
+    sub "\u0CF2", "ḫ"
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ृ", "ṛ"
+    sub "ॄ", "ṝ"
+    sub "े", "e"
+    sub "ै", "ai"
+    sub "ो", "o"
+    sub "ौ", "au"
+    sub "्", ""
+    sub "‍", "" # Used for joining
+  }
+
+  compose
+}
+

data/maps/alalc-sin-Sinh-Latn-1997.imp

@@ -0,0 +1,246 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:sin
+  source_script: Sinh
+  destination_script: Latn
+  name: Sinhalese Romanization, 1997
+  url: http://catdir.loc.gov/catdir/cpso/romanization/sinhales.pdf
+  creation_date: 1997
+  description: |
+    ALA-LC Romanization table for Sinhalese
+
+
+  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 sign ් called virāma.
+
+    - |
+      Exceptions: 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.
+
+    - |
+      Exceptions:
+      a) when saññaka represents a nasal, it is romanized according to the rule for anusvāra.
+      b) when saññaka is combined with an aspirated consonant, the combination is romanized as a non-aspirated, followed by an aspirated consonant.
+}
+
+tests {
+  test "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා", "śīra laṃkāvē kīraḍāva itihāsayē ihaḷama tănakaṭa gēnanna kaṭayutu karanavā"
+  test "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්", "kocañcikaṇḍē mōyakaṭa asala nâmaṭa giya taruṇayō 3k maruṭa - miturāgē upan dinaya sămarīmaṭa ăvit"
+  test "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා", "lōka ḷamā dinayadā sisun pirisak kasippu bīlā"
+  test "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ", "kōṭi 16ka heroyin samaga danaṅkoṭuvēdī 7k dălē"
+  test "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි", "minuvanaṅgoḍa pīsīār dedahasak sidukarayi"
+  test "පාස්කු ප‍්‍රහාරය වගේම පාස්කු ප්‍රෝඩාව ගැනත් සොයන්න කොමිසමක් පත්කළ යුතුයි - විපක්‍ෂ නායක සජිත් පේ‍්‍රමදාස", "pāsaṅku parahāraya vagēma pāsaṅku prōḍāva gănat soyananna komisamak pataṅkaḷa yutuyi - vipakṣa nāyaka sajit pēramadāsa"
+  test "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි", "ṭarampaṅgē saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
+  test "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති", "pāsaṅku dā parahāraya piḷibanda parīkṣaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa denannē nâ - agamăti"
+  test "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි", "dilli kăpiṭals saha kōligē băṃgalōr tevăni jaya labayi"
+  test "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා", "śarī lāṃkika sambhavayak sahita paraṃśayē pavulaka 5 k ghātanaya karalā"
+  test "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර", "pătikudaya ikmanin suva karana paratikāra"
+}
+
+aliases {
+  def_alias sinh_chars_1, any("\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca")
+}
+
+stage {
+
+  # RULES
+  # note[3]
+    sub "\u0DCA", "ṅ", after: any("කඛගඝඞ")
+    sub "\u0DCA", "ñ", after: any("චඡජඣඤ")
+    sub "\u0DCA", "ṇ", after: any("ටඨඩඪණ")
+    sub "\u0DCA", "n", after: any("තථදධන")
+
+  # note[2(a,b)]
+    sub "ක", "k", after: sinh_chars_1
+    sub "ඛ", "kh", after: sinh_chars_1
+    sub "ග", "g", after: sinh_chars_1
+    sub "ඝ", "gh", after: sinh_chars_1
+    sub "ඞ", "ṅ", after: sinh_chars_1
+    sub "ච", "c", after: sinh_chars_1
+    sub "ඡ", "ch", after: sinh_chars_1
+    sub "ජ", "j", after: sinh_chars_1
+    sub "ඣ", "jh", after: sinh_chars_1
+    sub "ඤ", "ñ", after: sinh_chars_1
+    sub "ට", "ṭ", after: sinh_chars_1
+    sub "ඨ", "ṭh", after: sinh_chars_1
+    sub "ඩ", "ḍ", after: sinh_chars_1
+    sub "ඪ", "ḍh", after: sinh_chars_1
+    sub "ණ", "ṇ", after: sinh_chars_1
+    sub "ත", "t", after: sinh_chars_1
+    sub "ථ", "th", after: sinh_chars_1
+    sub "ද", "d", after: sinh_chars_1
+    sub "ධ", "dh", after: sinh_chars_1
+    sub "න", "n", after: sinh_chars_1
+    sub "ප", "p", after: sinh_chars_1
+    sub "ඵ", "ph", after: sinh_chars_1
+    sub "බ", "b", after: sinh_chars_1
+    sub "භ", "bh", after: sinh_chars_1
+    sub "ම", "m", after: sinh_chars_1
+    sub "ය", "y", after: sinh_chars_1
+    sub "ර", "r", after: sinh_chars_1
+    sub "ල", "l", after: sinh_chars_1
+    sub "ළ", "ḷ", after: sinh_chars_1
+    sub "ව", "v", after: sinh_chars_1
+    sub "ශ", "ś", after: sinh_chars_1
+    sub "ෂ", "ṣ", after: sinh_chars_1
+    sub "ස", "s", after: sinh_chars_1
+    sub "හ", "h", after: sinh_chars_1
+    sub "ඟ", "ṅg", after: sinh_chars_1
+    sub "ඦ", "ñj", after: sinh_chars_1
+    sub "ඬ", "ṇḍ", after: sinh_chars_1
+    sub "ඳ", "nd", after: sinh_chars_1
+    sub "ඹ", "ṃb", after: sinh_chars_1
+
+
+
+  # CHARACTERS
+  parallel {
+
+    #Vowels and Diphthongs (see Note 1)
+
+    sub "අ", "a"
+    sub "ආ", "ā"
+    sub "ඇ", "ă"
+    sub "ඈ", "â"
+    sub "ඉ", "i"
+    sub "ඊ", "ī"
+    sub "උ", "u"
+    sub "ඌ", "ū"
+    sub "ඍ", "ṛ"
+    sub "ඎ", "ṝ"
+    sub "ඏ", "ḷ"
+    sub "ඐ", "ḹ"
+    sub "එ", "e"
+    sub "ඒ", "ē"
+    sub "ඓ", "ai"
+    sub "ඔ", "o"
+    sub "ඕ", "ō"
+    sub "ඖ", "au"
+
+    sub "ා", "ā"
+    sub "ැ", "ă"
+    sub "ෑ", "â"
+    sub "ි", "i"
+    sub "ී", "ī"
+    sub "ු", "u"
+    sub "ූ", "ū"
+    sub "ෘ", "ṛ"
+    sub "ෲ", "ṝ"
+    sub "ෟ", "ḷ"
+    sub "ෳ", "ḹ"
+    sub "ෙ", "e"
+    sub "ේ", "ē"
+    sub "ෛ", "ai"
+    sub "ො", "o"
+    sub "ෝ", "ō"
+    sub "ෞ", "au"
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "ක", "ka"
+    sub "ඛ", "kha"
+    sub "ග", "ga"
+    sub "ඝ", "gha"
+    sub "ඞ", "ṅa"
+
+
+    # Palatals
+    sub "ච", "ca"
+    sub "ඡ", "cha"
+    sub "ජ", "ja"
+    sub "ඣ", "jha"
+    sub "ඤ", "ña"
+
+
+    # Cerebrals
+    sub "ට", "ṭa"
+    sub "ඨ", "ṭha"
+    sub "ඩ", "ḍa"
+    sub "ඪ", "ḍha"
+    sub "ණ", "ṇa"
+
+
+    # Dentals
+    sub "ත", "ta"
+    sub "ථ", "tha"
+    sub "ද", "da"
+    sub "ධ", "dha"
+    sub "න", "na"
+
+
+    # Labials
+    sub "ප", "pa"
+    sub "ඵ", "pha"
+    sub "බ", "ba"
+    sub "භ", "bha"
+    sub "ම", "ma"
+
+
+    # Semivowels
+    sub "ය", "ya"
+    sub "ර", "ra"
+    sub "ල", "la"
+    sub "ළ", "ḷa"
+    sub "ව", "va"
+
+    # Sibilants
+    sub "ශ", "śa"
+    sub "ෂ", "ṣa"
+    sub "ස", "sa"
+
+    # Aspirate
+    sub "හ", "ha"
+
+
+    # Visarga
+    sub "ඃ", "ḥ"
+
+    # Anusvāra (see Note 3)
+    sub "ං", "ṃ"
+
+
+    # numbers
+    sub "\u0DE6", "0"
+    sub "\u0DE7", "1"
+    sub "\u0DE8", "2"
+    sub "\u0DE9", "3"
+    sub "\u0DEA", "4"
+    sub "\u0DEB", "5"
+    sub "\u0DEC", "6"
+    sub "\u0DED", "7"
+    sub "\u0DEE", "8"
+    sub "\u0DEF", "9"
+
+
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+    sub "්", ""
+
+    # Rule no 4
+    sub "ඟ", "ṅga"
+    sub "ඦ", "ñja"
+    sub "ඬ", "ṇḍa"
+    sub "ඳ", "nda"
+    sub "ඹ", "ṃba"
+  }
+
+  compose
+}
+