interscript-maps 3.0.0 → 3.1.0

data/maps/alalc-rue-Cyrl-Latn-2013.isc

@@ -0,0 +1,196 @@
+system "ALA-LC:rue-Cyrl:Latn:2013" {
+
+metadata {
+  authority_id alalc
+  id 2013
+  language iso-639-3:rue
+  source_script Cyrl
+  destination_script Latn
+  name Romanization Table -- Rusyn (2013)
+  url https://www.loc.gov/catdir/cpso/romanization/rusyn.pdf
+  creation_date 2013
+  description {
+    ALA-LC romanization table for Rusyn / Carpatho-Rusyn (2013 version,
+    no earlier versions). Reflects written variants of Rusyn from
+    several regions. Transcribed from the digitized table (pages 1-2).
+  }
+
+  notes {
+    note "Source prose: this romanization table reflects written variants of the Rusyn / Carpatho-Rusyn language from several regions. Diacritics and characters that are referenced occasionally but used inconsistently (such as Cyrillic ӱ, л̆, г̆) are not included. Use the Church Slavic ALA-LC romanization table for Church Slavic and pre-revolutionary Russian characters."
+    note "Note 1: the ligature (tie, U+0361) is necessary to distinguish ж from the combination зг; hence ж = z͡h. Note 3: the ligature is necessary to distinguish х from the combination кг; hence х = k͡h. Note 4: the ligature is necessary to distinguish ц from the combination тс; hence ц = t͡s."
+    note "Note 2: romanize the letter и as i for Rusyn materials published in the Serbian Vojvodina, historic Bačka, and Srem regions, with places of publication including Belgrade, Djurdjevo, Kucura, Novi Sad, Pančevo, Ruski Krstur, Sremska Mitrovica, Subotica; romanize и as y for all other Rusyn materials. This map encodes the general rule (и = y); the Vojvodinian i variant depends on publication provenance and cannot be resolved from the text alone."
+    note "The iotated vowels є, ю and я are romanized Ī plus tie plus the vowel (Ī͡e, Ī͡u, Ī͡a), exactly as printed in the source."
+    note "Source errata, flagged in the pull request: the table's vernacular cells for the yo row print Latin Ë (U+00CB) rather than Cyrillic Ё, so this map keys the Cyrillic inputs Ё/ё (U+0401/U+0451); the o-circumflex row prints Latin Ô (U+00D4), so this map keys Cyrillic О plus combining circumflex (U+0302); the lower-case row for ф prints romanization F, encoded as f; the hard-sign row prints two primes (ʹʹ), encoded as the double prime ʺ (U+02BA) matching the Church Slavic table; the upper-case romanization cell for Я shows only ī, encoded as Ī͡A per the lower-case cell and the pattern of the other iotated rows."
+  }
+}
+
+tests {
+  # every table row, upper and lower (the document has no example words
+  # beyond the table itself)
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "H"
+   "г" ->  "h"
+   "Ґ" ->  "G"
+   "ґ" ->  "g"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Е" ->  "E"
+   "е" ->  "e"
+   "Є" ->  "Ī͡E"
+   "є" ->  "ī͡e"
+   "Ё" ->  "Ë"
+   "ё" ->  "ë"
+   "Ж" ->  "Z͡H"
+   "ж" ->  "z͡h"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "І" ->  "I"
+   "і" ->  "i"
+   "Ї" ->  "Ï"
+   "ї" ->  "ï"
+   "И" ->  "Y"
+   "и" ->  "y"
+   "Ы" ->  "Ŷ"
+   "ы" ->  "ŷ"
+   "Й" ->  "Ĭ"
+   "й" ->  "ĭ"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "О̂" ->  "Ô"
+   "о̂" ->  "ô"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "У" ->  "U"
+   "у" ->  "u"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "K͡H"
+   "х" ->  "k͡h"
+   "Ц" ->  "T͡S"
+   "ц" ->  "t͡s"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Shch"
+   "щ" ->  "shch"
+   "Э" ->  "Ė"
+   "э" ->  "ė"
+   "Ю" ->  "Ī͡U"
+   "ю" ->  "ī͡u"
+   "Я" ->  "Ī͡A"
+   "я" ->  "ī͡a"
+   "Ь" ->  "ʹ"
+   "ь" ->  "ʹ"
+   "Ъ" ->  "ʺ"
+   "ъ" ->  "ʺ"
+   "Ѣ" ->  "Î"
+   "ѣ" ->  "î"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "а" "a"
+    sub "Б" "B"
+    sub "б" "b"
+    sub "В" "V"
+    sub "в" "v"
+    sub "Г" "H"
+    sub "г" "h"
+    sub "Ґ" "G"
+    sub "ґ" "g"
+    sub "Д" "D"
+    sub "д" "d"
+    sub "Е" "E"
+    sub "е" "e"
+    sub "Є" "Ī͡E"
+    sub "є" "ī͡e"
+    sub "Ё" "Ë"
+    sub "ё" "ë"
+    sub "Ж" "Z͡H"
+    sub "ж" "z͡h"
+    sub "З" "Z"
+    sub "з" "z"
+    sub "І" "I"
+    sub "і" "i"
+    sub "Ї" "Ï"
+    sub "ї" "ï"
+    sub "И" "Y"
+    sub "и" "y"
+    sub "Ы" "Ŷ"
+    sub "ы" "ŷ"
+    sub "Й" "Ĭ"
+    sub "й" "ĭ"
+    sub "К" "K"
+    sub "к" "k"
+    sub "Л" "L"
+    sub "л" "l"
+    sub "М" "M"
+    sub "м" "m"
+    sub "Н" "N"
+    sub "н" "n"
+    sub "О̂" "Ô"
+    sub "о̂" "ô"
+    sub "О" "O"
+    sub "о" "o"
+    sub "П" "P"
+    sub "п" "p"
+    sub "Р" "R"
+    sub "р" "r"
+    sub "С" "S"
+    sub "с" "s"
+    sub "Т" "T"
+    sub "т" "t"
+    sub "У" "U"
+    sub "у" "u"
+    sub "Ф" "F"
+    sub "ф" "f"
+    sub "Х" "K͡H"
+    sub "х" "k͡h"
+    sub "Ц" "T͡S"
+    sub "ц" "t͡s"
+    sub "Ч" "Ch"
+    sub "ч" "ch"
+    sub "Ш" "Sh"
+    sub "ш" "sh"
+    sub "Щ" "Shch"
+    sub "щ" "shch"
+    sub "Э" "Ė"
+    sub "э" "ė"
+    sub "Ю" "Ī͡U"
+    sub "ю" "ī͡u"
+    sub "Я" "Ī͡A"
+    sub "я" "ī͡a"
+    sub "Ь" "ʹ"
+    sub "ь" "ʹ"
+    sub "Ъ" "ʺ"
+    sub "ъ" "ʺ"
+    sub "Ѣ" "Î"
+    sub "ѣ" "î"
+  }
+
+}
+
+}

data/maps/alalc-snd-Arab-Latn-2024.isc

@@ -0,0 +1,332 @@
+system "ALA-LC:snd-Arab:Latn:2024" {
+
+metadata {
+  authority_id alalc
+  id 2024
+  language iso-639-2:snd
+  source_script Arab
+  destination_script Latn
+  name "Romanization Table -- Sindhi (2024)"
+  url http://catdir.loc.gov/catdir/cpso/romanization/sindhi.pdf
+  creation_date 2024
+  confirmation_date 2024
+  description {    ALA-LC Romanization table for Sindhi (in Arabic script), 2024 version (earlier versions: 2013, 2012, 1997)
+  }
+
+  notes {
+    note "Letters of the Alphabet: alif ا (omit); ب b; ٻ b̤; ڀ bh; ت t; ٿ th; ٽ ṭ; ٺ ṭh; ث s; پ p; ج j; ڄ j̈; جھ jh; ڃ ñ; چ c; ڇ ch; ح ḥ; خ kh; د d; ڌ dh; ڏ d̤; ڊ ḍ; ڍ ḍh; ذ z; ر r; ڙ ṛ; ز z; س s; ش sh; ص ṣ; ض ẓ; ط ṭ; ظ z̤; ع ‘ (ayn); غ gh; ف f; ڦ ph; ق q; ڪ k; ک kh; گ g; ڳ g̈; گھ gh; ڱ ṅ; ل l; م m; ن n; ڻ ṇ; و v; ه ہ ة h; ء (omit); ي ي y. The aspirate digraphs bh ڀ, jh جھ, ch ڇ, dh ڌ, ḍh ڍ, ph ڦ, and gh گھ are single letters except جھ and گھ, which render mechanically as their consonant plus h."
+
+    note "Note 1. When Sindhi is written in the Devanagari script, it is romanized according to the Hindi table. The letters ब़, ज़, द़, and ग़ are romanized b̤, j̈, d̤, and g̈ respectively."
+
+    note "Note 2. The rules of application for Urdu are to be used for Sindhi. Vocalization is that used for entries in Mewaram's A Sindhi English Dictionary (1st ed., Hyderabad, 1910), Sindhī Ūrdū Lughāt (Haidarābād, 1959), and Jāmiʻ-i Sindhī Lughāt (Karācī, 1931). This map therefore carries the Urdu rules-of-application machinery (marked vowels, hamzah, maddah, the article al with its sun-letter assimilation, tanvīn, shaddah doubling, bare-letter defaults), with the Sindhi letter values; over unvocalized text the readings of bare و and ی and unwritten short vowels remain lexical."
+
+    note "Vowels and Diphthongs: fatha a; damma u; kasra i; yad with kasra یِ ī; waw و o; bari yad ے, yad ی e; waw with sukun and fatha وَْ au; yad with sukun and fatha یَْ, bari yad ے ai; alif with fatha اَ, yad with fatha یَ, alif maqsura with superscript alif ىٰ ā; waw with damma وُ ū."
+  }
+}
+
+tests {
+  # Letters of the Alphabet
+   "ب" ->  "b"
+   "ٻ" ->  "b̤"
+   "ڀ" ->  "bh"
+   "ت" ->  "t"
+   "ٿ" ->  "th"
+   "ٽ" ->  "ṭ"
+   "ٺ" ->  "ṭh"
+   "ث" ->  "s"
+   "پ" ->  "p"
+   "ج" ->  "j"
+   "ڄ" ->  "j̈"
+   "ڃ" ->  "ñ"
+   "چ" ->  "c"
+   "ڇ" ->  "ch"
+   "ح" ->  "ḥ"
+   "خ" ->  "kh"
+   "د" ->  "d"
+   "ڌ" ->  "dh"
+   "ڏ" ->  "d̤"
+   "ڊ" ->  "ḍ"
+   "ڍ" ->  "ḍh"
+   "ذ" ->  "z"
+   "ر" ->  "r"
+   "ڙ" ->  "ṛ"
+   "ز" ->  "z"
+   "س" ->  "s"
+   "ش" ->  "sh"
+   "ص" ->  "ṣ"
+   "ض" ->  "ẓ"
+   "ط" ->  "ṭ"
+   "ظ" ->  "z̤"
+   "ع" ->  "ʻ"
+   "غ" ->  "gh"
+   "ف" ->  "f"
+   "ڦ" ->  "ph"
+   "ق" ->  "q"
+   "ڪ" ->  "k"
+   "ک" ->  "kh"
+   "گ" ->  "g"
+   "ڳ" ->  "g̈"
+   "ڱ" ->  "ṅ"
+   "ل" ->  "l"
+   "م" ->  "m"
+   "ن" ->  "n"
+   "ڻ" ->  "ṇ"
+   "و" ->  "v"
+   "ه" ->  "h"
+   "ہ" ->  "h"
+   "ة" ->  "h"
+   "ي" ->  "y"
+   "ی" ->  "y"
+   "ے" ->  "e"
+  # Vowels and Diphthongs
+   "اَ" ->  "ā"
+   "یَ" ->  "ā"
+   "ىٰ" ->  "ā"
+   "وُ" ->  "ū"
+   "یِ" ->  "ī"
+   "وَ" ->  "o"
+   "وَْ" ->  "au"
+   "یَْ" ->  "ai"
+   "ےَ" ->  "ai"
+}
+
+stage main {
+  sequence {
+    # Marked vowels and diphthongs (Vowels and Diphthongs table)
+    sub "وَْ" "au"
+    sub "یَْ" "ai"
+    sub "وَ" "o"
+    sub "وُ" "ū"
+    sub "یَ" "ā"
+    sub "یِ" "ī"
+    sub "اَ" "ā"
+    sub "ےَ" "ai"
+    sub "ىٰ" "ā"
+
+    # Rule 12 of the Urdu rules - hamzah
+    sub "ئے" "yi"
+    sub "ۀ" "h-yi"
+    sub {
+    from boundary + "ء"
+    to ""
+  }
+    sub {
+    from boundary + "أ"
+    to ""
+  }
+    sub "ء" "ʼ"
+    sub "أ" "ʼ"
+    sub "ؤ" "ʼ"
+    sub "ئ" "ʼ"
+
+    # Rule 13 - maddah
+    sub {
+    from boundary + "آ"
+    to "ā"
+  }
+    sub "آ" "ʼā"
+
+    # Rule 18 - the Arabic article al (moon letters) and its assimilation
+    # (sun letters)
+    sub {
+    from boundary + "الت"
+    to "at-"
+  }
+    sub {
+    from boundary + "الث"
+    to "as-"
+  }
+    sub {
+    from boundary + "الد"
+    to "ad-"
+  }
+    sub {
+    from boundary + "الذ"
+    to "az-"
+  }
+    sub {
+    from boundary + "الر"
+    to "ar-"
+  }
+    sub {
+    from boundary + "الز"
+    to "az-"
+  }
+    sub {
+    from boundary + "الس"
+    to "as-"
+  }
+    sub {
+    from boundary + "الش"
+    to "ash-"
+  }
+    sub {
+    from boundary + "الص"
+    to "aṣ-"
+  }
+    sub {
+    from boundary + "الض"
+    to "aẓ-"
+  }
+    sub {
+    from boundary + "الط"
+    to "aṭ-"
+  }
+    sub {
+    from boundary + "الظ"
+    to "az̤-"
+  }
+    sub {
+    from boundary + "الل"
+    to "al-"
+  }
+    sub {
+    from boundary + "الن"
+    to "an-"
+  }
+    sub {
+    from boundary + "ال"
+    to "al-"
+  }
+
+    # Rule 16 - tanvin
+    sub "اً" "an"
+    sub "ً" "an"
+    sub "ٌ" "un"
+    sub "ٍ" "in"
+
+    # Rule 14 - shaddah doubling
+    sub "بّ" "bb"
+    sub "ٻّ" "b̤b̤"
+    sub "ڀّ" "bhbh"
+    sub "تّ" "tt"
+    sub "ٿّ" "thth"
+    sub "ٽّ" "ṭṭ"
+    sub "ٺّ" "ṭhṭh"
+    sub "ثّ" "ss"
+    sub "پّ" "pp"
+    sub "جّ" "jj"
+    sub "ڄّ" "j̈j̈"
+    sub "ڃّ" "ññ"
+    sub "چّ" "cc"
+    sub "ڇّ" "chch"
+    sub "حّ" "ḥḥ"
+    sub "خّ" "khkh"
+    sub "دّ" "dd"
+    sub "ڌّ" "dhdh"
+    sub "ڏّ" "d̤d̤"
+    sub "ڊّ" "ḍḍ"
+    sub "ڍّ" "ḍhḍh"
+    sub "ذّ" "zz"
+    sub "رّ" "rr"
+    sub "ڙّ" "ṛṛ"
+    sub "زّ" "zz"
+    sub "سّ" "ss"
+    sub "شّ" "shsh"
+    sub "صّ" "ṣṣ"
+    sub "ضّ" "ẓẓ"
+    sub "طّ" "ṭṭ"
+    sub "ظّ" "z̤z̤"
+    sub "عّ" "ʻʻ"
+    sub "غّ" "ghgh"
+    sub "فّ" "ff"
+    sub "ڦّ" "phph"
+    sub "قّ" "qq"
+    sub "ڪّ" "kk"
+    sub "کّ" "khkh"
+    sub "گّ" "gg"
+    sub "ڳّ" "g̈g̈"
+    sub "ڱّ" "ṅṅ"
+    sub "لّ" "ll"
+    sub "مّ" "mm"
+    sub "نّ" "nn"
+    sub "ڻّ" "ṇṇ"
+    sub "وّ" "vv"
+    sub "یّ" "yy"
+
+    # Letters of the Alphabet
+    sub "ب" "b"
+    sub "ٻ" "b̤"
+    sub "ڀ" "bh"
+    sub "ت" "t"
+    sub "ٿ" "th"
+    sub "ٽ" "ṭ"
+    sub "ٺ" "ṭh"
+    sub "ث" "s"
+    sub "پ" "p"
+    sub "ج" "j"
+    sub "ڄ" "j̈"
+    sub "ڃ" "ñ"
+    sub "چ" "c"
+    sub "ڇ" "ch"
+    sub "ح" "ḥ"
+    sub "خ" "kh"
+    sub "د" "d"
+    sub "ڌ" "dh"
+    sub "ڏ" "d̤"
+    sub "ڊ" "ḍ"
+    sub "ڍ" "ḍh"
+    sub "ذ" "z"
+    sub "ر" "r"
+    sub "ڙ" "ṛ"
+    sub "ز" "z"
+    sub "س" "s"
+    sub "ش" "sh"
+    sub "ص" "ṣ"
+    sub "ض" "ẓ"
+    sub "ط" "ṭ"
+    sub "ظ" "z̤"
+    sub "ع" "ʻ"
+    sub "غ" "gh"
+    sub "ف" "f"
+    sub "ڦ" "ph"
+    sub "ق" "q"
+    sub "ڪ" "k"
+    sub "ک" "kh"
+    sub "گ" "g"
+    sub "ڳ" "g̈"
+    sub "ڱ" "ṅ"
+    sub "ل" "l"
+    sub "م" "m"
+    sub "ن" "n"
+    sub "ڻ" "ṇ"
+    sub "ة" "h"
+    sub "ه" "h"
+    sub "ہ" "h"
+    sub "ھ" "h"
+
+    # Bare alif: word-initial short a, after a consonant ā (Urdu rule 3)
+    sub {
+    from boundary + "ا"
+    to "a"
+  }
+    sub "ا" "ā"
+
+    # Marks not represented, and the short-vowel signs
+    sub "ْ" ""
+    sub "ّ" ""
+    sub "َ" "a"
+    sub "ُ" "u"
+    sub "ِ" "i"
+
+    # Bare yad: word-initial y, other bare yad e; bare bari yad e
+    sub {
+    from boundary + "ی"
+    to "y"
+  }
+    sub {
+    from boundary + "ي"
+    to "y"
+  }
+    sub "ی" "e"
+    sub "ي" "e"
+    sub "ے" "e"
+    sub "ى" "e"
+
+    # Bare waw: the alphabet-row consonant v
+    sub "و" "v"
+  }
+
+}
+
+}