interscript-maps 2.4.3 → 2.5.0

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

@@ -0,0 +1,404 @@
+system "ALA-LC:sin-Sinh:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:sin
+  source_script Sinh
+  destination_script Latn
+  name Romanization Table -- Sinhalese (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/sinhales.pdf
+  creation_date 1997
+  description {    ALA-LC Romanization table for Sinhalese
+  }
+
+  notes {
+
+    note "Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n vowels following a consonant can be found in grammars; no distinction between the two is\n made in transliteration."
+
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the sign ් called virāma."
+
+    note "      Exceptions: Anusvāra is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials."
+
+    note "      Exceptions:\n      a) when saññaka represents a nasal, it is romanized according to the rule for anusvāra.\n      b) when saññaka is combined with an aspirated consonant, the combination is romanized as a non-aspirated, followed by an aspirated consonant."
+  }
+}
+
+tests {
+   "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා" ->  "śīra laṃkāvē kīraḍāva itihāsayē ihaḷama tănakaṭa gēnanna kaṭayutu karanavā"
+   "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"
+   "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා" ->  "lōka ḷamā dinayadā sisun pirisak kasippu bīlā"
+   "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ" ->  "kōṭi 16ka heroyin samaga danaṅkoṭuvēdī 7k dălē"
+   "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි" ->  "minuvanaṅgoḍa pīsīār dedahasak sidukarayi"
+   "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"
+   "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි" ->  "ṭarampaṅgē saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
+   "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති" ->  "pāsaṅku dā parahāraya piḷibanda parīkṣaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa denannē nâ - agamăti"
+   "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි" ->  "dilli kăpiṭals saha kōligē băṃgalōr tevăni jaya labayi"
+   "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා" ->  "śarī lāṃkika sambhavayak sahita paraṃśayē pavulaka 5 k ghātanaya karalā"
+   "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර" ->  "pătikudaya ikmanin suva karana paratikāra"
+}
+
+aliases {
+  sinh_chars_1 = any("\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca")
+}
+
+stage main {
+
+  # RULES
+  # note[3]
+    sub {
+    from "\u0DCA"
+    to "ṅ"
+    after any("කඛගඝඞ")
+  }
+    sub {
+    from "\u0DCA"
+    to "ñ"
+    after any("චඡජඣඤ")
+  }
+    sub {
+    from "\u0DCA"
+    to "ṇ"
+    after any("ටඨඩඪණ")
+  }
+    sub {
+    from "\u0DCA"
+    to "n"
+    after any("තථදධන")
+  }
+
+  # note[2(a,b)]
+    sub {
+    from "ක"
+    to "k"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඛ"
+    to "kh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ග"
+    to "g"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඝ"
+    to "gh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඞ"
+    to "ṅ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ච"
+    to "c"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඡ"
+    to "ch"
+    after sinh_chars_1
+  }
+    sub {
+    from "ජ"
+    to "j"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඣ"
+    to "jh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඤ"
+    to "ñ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ට"
+    to "ṭ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඨ"
+    to "ṭh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඩ"
+    to "ḍ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඪ"
+    to "ḍh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ණ"
+    to "ṇ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ත"
+    to "t"
+    after sinh_chars_1
+  }
+    sub {
+    from "ථ"
+    to "th"
+    after sinh_chars_1
+  }
+    sub {
+    from "ද"
+    to "d"
+    after sinh_chars_1
+  }
+    sub {
+    from "ධ"
+    to "dh"
+    after sinh_chars_1
+  }
+    sub {
+    from "න"
+    to "n"
+    after sinh_chars_1
+  }
+    sub {
+    from "ප"
+    to "p"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඵ"
+    to "ph"
+    after sinh_chars_1
+  }
+    sub {
+    from "බ"
+    to "b"
+    after sinh_chars_1
+  }
+    sub {
+    from "භ"
+    to "bh"
+    after sinh_chars_1
+  }
+    sub {
+    from "ම"
+    to "m"
+    after sinh_chars_1
+  }
+    sub {
+    from "ය"
+    to "y"
+    after sinh_chars_1
+  }
+    sub {
+    from "ර"
+    to "r"
+    after sinh_chars_1
+  }
+    sub {
+    from "ල"
+    to "l"
+    after sinh_chars_1
+  }
+    sub {
+    from "ළ"
+    to "ḷ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ව"
+    to "v"
+    after sinh_chars_1
+  }
+    sub {
+    from "ශ"
+    to "ś"
+    after sinh_chars_1
+  }
+    sub {
+    from "ෂ"
+    to "ṣ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ස"
+    to "s"
+    after sinh_chars_1
+  }
+    sub {
+    from "හ"
+    to "h"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඟ"
+    to "ṅg"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඦ"
+    to "ñj"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඬ"
+    to "ṇḍ"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඳ"
+    to "nd"
+    after sinh_chars_1
+  }
+    sub {
+    from "ඹ"
+    to "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 "‍" ""
+    sub "‌" ""
+    sub "්" ""
+
+    # Rule no 4
+    sub "ඟ" "ṅga"
+    sub "ඦ" "ñja"
+    sub "ඬ" "ṇḍa"
+    sub "ඳ" "nda"
+    sub "ඹ" "ṃba"
+  }
+
+  compose
+}
+
+}

data/maps/alalc-sin-Sinh-Latn-2011.isc

@@ -0,0 +1,49 @@
+system "ALA-LC:sin-Sinh:Latn:2011" {
+
+metadata {
+  authority_id alalc
+  id 2011
+  language iso-639-2:sin
+  source_script Sinh
+  destination_script Latn
+  name Romanization Table -- Sinhalese (2011)
+  url https://www.loc.gov/catdir/cpso/romanization/sinhales.pdf
+  creation_date 2011
+  description {    ALA-LC Romanization table for Sinhalese
+  }
+
+  notes {
+
+    note "Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n vowels following a consonant can be found in grammars; no distinction between the two is\n made in transliteration."
+
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the sign ් called virāma."
+
+    note "      Exceptions: Anusvāra is transliterated by:\n\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials."
+
+    note "      Exceptions:\n      a) when saññaka represents a nasal, it is romanized according to the rule for anusvāra.\n      b) when saññaka is combined with an aspirated consonant, the combination is romanized as a non-aspirated, followed by an aspirated consonant."
+  }
+}
+
+tests {
+   "හිටපු අග්‍රාමාත්‍ය රනිල් වික්‍රමසිංහ අප්‍රේල් 21 ප්‍රහාරය සම්බන්ධයෙන් විමර්ශනය කරන ජනාධිපති පරීක්ෂණ කොමිසම හමුවේ දෙවෙනි දිනටත් සාක්ෂි ලබාදීමට පැමිණෙයි" ->  "hiṭapu agrāmātya ranil vikramasiṃha aprēl 21 prahāraya sambanandhayen vimarśanaya karana janādhipati parīkṣaṇa komisama hamuvē deveni dinaṭat sākṣi labādīmaṭa pămiṇeyi"
+   "පෑලියගොඩ මත්ස්‍ය තොග වෙළෙදපොළට පිවිසෙන පිවිසුම් මාර්ගය පුළුල් කර සංවර්ධනයට පියවර - මහාමාර්ග අමාත්‍ය ජොන්ස්ටන් ප්‍රනාන්දු" ->  "pâliyagoḍa matsya toga veḷedapoḷaṭa pivisena pivisum māraṅgaya puḷul kara saṃvarandhanayaṭa piyavara - mahāmāraṅga amātya jonsaṇṭan pranānandu"
+   "මව්බිමටත් රට වැසියන්ටත් ආශිර්වාද කරමින් වි⁣ශේෂ ආගමික වැඩසටහන් මාලාවක්" ->  "mavbimaṭat raṭa văsiyanaṇṭat āśirvāda karamin vi⁣śēṣa āgamika văḍasaṭahan mālāvak"
+   "මිනුවන්ගොඩ කොරෝනා පොකුරින් තවත් ආසාදිතයින් 49 දෙනකු හඳුනා ගෙන" ->  "minuvanaṅgoḍa korōnā pokurin tavat āsāditayin 49 denaku handunā gena"
+   "ඉරණවිල වෙරළේ නාඳුනන ධීවර යාත‍්‍රා දෙකක්" ->  "iraṇavila veraḷē nāndunana dhīvara yātarā dekak"
+   "මඩකලපුව මංගලාරාමේ හාමුදුරුවන්ට මරණ තර්ජන - ආරක්ෂාවත් අඩුකරලා" ->  "maḍakalapuva maṃgalārāmē hāmuduruvanaṇṭa maraṇa tarañjana - ārakṣāvat aḍukaralā"
+   "හොරට කහ කුඩු හැදූ දෙදෙනෙක් බඩුත් එක්ක දැලේ" ->  "horaṭa kaha kuḍu hădū dedenek baḍut ekaṅka dălē"
+   "ඉංගිරියේ ජලභීතිකාව වැළඳුනු නරියෙකු තෙදිනක මෙහෙයුමකින් අල්ලා ගනී" ->  "iṃgiriyē jalabhītikāva văḷandunu nariyeku tedinaka meheyumakin allā ganī"
+   "බෞද්ධ දර්ශනයට අනුව අපි උපයන ධනය බුද්ධිමත් ලෙස විසර්ජනය කරන්නේ කෙසේ ද?" ->  "baudandha darśanayaṭa anuva api upayana dhanaya budandhimat lesa visarañjanaya karanannē kesē da?"
+   "ඉන්දීය ජාතිකයන් සමග එක්වන මන්නාරමේ ධීවරයන්ට අනතුරු අගවයි" ->  "inandīya jātikayan samaga ekvana manannāramē dhīvarayanaṇṭa anaturu agavayi"
+   "තේ නැවත වගාවට පෙර පස පුනරුත්ථාපනයට කෙටි මග" ->  "tē năvata vagāvaṭa pera pasa punarutanthāpanayaṭa keṭi maga"
+}
+
+dependency "alalc-sin-Sinh-Latn-1997" as sinhlatn
+
+stage main {
+
+  run  map.sinhlatn.stage.main
+
+}
+
+}

data/maps/alalc-srp-Cyrl-Latn-1997.isc

@@ -0,0 +1,148 @@
+system "ALA-LC:srp-Cyrl:Latn:1997" {
+
+metadata {
+  authority_id alalc
+  id 1997
+  language iso-639-2:srp
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Serbian and Macedonian (1997)
+  url http://catdir.loc.gov/catdir/cpso/romanization/serbian.pdf
+  creation_date 1997
+  description ALA-LC Romanization table for Serbian and Macedonian.
+
+  notes {
+    note "Special characters in romanization\n Đ - D with crossbar (upper case). USMARC hexadecimal code A3.\n đ - d with crossbar (upper case). USMARC hexadecimal code B3."
+
+    note "Character modifiers in romanization\n ´ - acute. USMARC hexadecimal code E2.\n ˇ - hachek. USMARC hexadecimal code E9."
+  }
+}
+
+tests {
+   "Општина Ердут" ->  "Opština Erdut"
+   "Општина Двор" ->  "Opština Dvor"
+   "ЛУЃЕ луѓе" ->  "LUǴE luǵe"
+   "ЅВЕЗДА ѕвезда Ѕвезда" ->  "DZVEZDA dzvezda Dzvezda"
+   "ЌАРУВАЊЕ ќарување" ->  "ḰARUVANJE ḱaruvanje"
+}
+
+dependency "posix"
+
+stage main {
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Ѓ" "Ǵ"
+    sub "Д" "D"
+    sub "Ђ" "Đ"
+    sub "Е" "E"
+    sub "Ж" "Ž"
+    sub "З" "Z"
+    sub "Ѕ" "Dz"
+    sub "И" "I"
+    sub "Ј" "J"
+    sub "К" "K"
+    sub "Ќ" "Ḱ"
+    sub "Л" "L"
+    sub "Љ" "Lj"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "Њ" "Nj"
+    sub "О" "O"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "Ћ" "Ć"
+    sub "У" "U"
+    sub "Ф" "F"
+    sub "Х" "H"
+    sub "Ц" "C"
+    sub "Ч" "Č"
+    sub "Џ" "Dž"
+    sub "Ш" "Š"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ѓ" "ǵ"
+    sub "д" "d"
+    sub "ђ" "đ"
+    sub "е" "e"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "ѕ" "dz"
+    sub "и" "i"
+    sub "ј" "j"
+    sub "к" "k"
+    sub "ќ" "ḱ"
+    sub "л" "l"
+    sub "љ" "lj"
+    sub "м" "m"
+    sub "н" "n"
+    sub "њ" "nj"
+    sub "о" "o"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "ћ" "ć"
+    sub "у" "u"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "џ" "dž"
+    sub "ш" "š"
+  }
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub {
+    from capture(maybe(upper)) + "Dz" + capture(upper)
+    to ref(1) + "DZ" + ref(2)
+  }
+  sub {
+    from capture(upper) + "Dz" + capture(maybe(upper))
+    to ref(1) + "DZ" + ref(2)
+  }
+
+  #LJ
+  sub {
+    from capture(upper) + "Lj" + capture(maybe(upper))
+    to ref(1) + "LJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Lj" + capture(upper)
+    to ref(1) + "LJ" + ref(2)
+  }
+
+  #NJ
+  sub {
+    from capture(upper) + "Nj" + capture(maybe(upper))
+    to ref(1) + "NJ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Nj" + capture(upper)
+    to ref(1) + "NJ" + ref(2)
+  }
+
+  #DŽ
+  sub {
+    from capture(upper) + "Dž" + capture(maybe(upper))
+    to ref(1) + "DŽ" + ref(2)
+  }
+  sub {
+    from capture(maybe(upper)) + "Dž" + capture(upper)
+    to ref(1) + "DŽ" + ref(2)
+  }
+
+  compose
+}
+
+}