interscript-maps 2.5.2 → 3.0.0

data/maps/din-urd-Arab-Latn-31635-2011.isc

@@ -0,0 +1,300 @@
+system "DIN:urd-Arab:Latn:31635-2011" {
+
+metadata {
+  authority_id din
+  id 31635-2011-10
+  language iso-639-2:urd
+  source_script Arab
+  destination_script Latn
+  name "DIN 31635:2011-07 section 10: Transliteration von Urdu"
+  url https://www.din.de
+  creation_date 2011
+  confirmation_date 2011-07
+  description {    DIN 31635:2011-07, section 10: transliteration of Urdu. Tabelle 7
+    (the 37-row letter table, including the four retroflex letters,
+    the nasal letter and the badi ye) plus the transliteration hints
+    10.1 a-d: the vowel system (short a i u; long a-macron e i-macron
+    o u-macron; diphthongs ai au), the dropped word-initial alif
+    short-vowel carrier, nasal vowels marked by the following nasal
+    letter, and aspiration written as in the original script.
+  }
+
+  notes {
+    note "Waw (row 34) renders v as consonant by default — the norm's
+    consonantal value is v, not w — and u-macron over vocalized input;
+    the o reading is a pronunciation fact of the vowel system and is
+    recorded here. Yeh (row 36, given as 064A/0649) renders y by
+    default and i-macron over vocalized input; Urdu texts commonly
+    write the yeh with the Persian codepoint (06CC), which this map
+    accepts as the same letter. The badi ye (row 37) renders e.
+    Remark d: aspiration is written as in the original script (bh and
+    the like), which follows mechanically from the heh's constant h —
+    the aspirate digraphs need no separate rules. Remark b: the
+    word-initial alif as a short-vowel carrier is not transliterated;
+    remark c: nasal vowels are marked by the following nasal letter,
+    whose own value is n-with-below-descender (row 33). The alif's
+    long-vowel a-macron and the hamza rules follow section 6 as in the
+    Persian and Kurdish columns."
+  }
+}
+
+tests {
+  # every table row (Tabelle 7)
+   "ء" ->  ""  # word-initial hamza is not rendered (remark b)
+   "ب" ->  "b"
+   "پ" ->  "p"
+   "ت" ->  "t"
+   "ٹ" ->  "ṭ"
+   "ث" ->  "s̱"
+   "ج" ->  "j"
+   "چ" ->  "c"
+   "ح" ->  "ḥ"
+   "خ" ->  "ẖ"
+   "د" ->  "d"
+   "ڈ" ->  "ḍ"
+   "ذ" ->  "ẕ"
+   "ر" ->  "r"
+   "ڑ" ->  "ṛ"
+   "ز" ->  "z"
+   "ژ" ->  "ž"
+   "س" ->  "s"
+   "ش" ->  "š"
+   "ص" ->  "ṣ"
+   "ض" ->  "z̤"
+   "ط" ->  "t̤"
+   "ظ" ->  "ẓ"
+   "ع" ->  "ʿ"
+   "غ" ->  "ġ"
+   "ف" ->  "f"
+   "ق" ->  "q"
+   "ک" ->  "k"
+   "گ" ->  "g"
+   "ل" ->  "l"
+   "م" ->  "m"
+   "ن" ->  "n"
+   "ں" ->  "ṉ"
+   "و" ->  "v"
+   "ه" ->  "h"
+   "ھ" ->  "h"
+   "ی" ->  "y"
+   "ي" ->  "y"
+   "ى" ->  "y"
+   "ے" ->  "e"
+  # vocalized readings and merges
+   "بَ" ->  "ba"
+   "بِ" ->  "bi"
+   "بُ" ->  "bu"
+   "وُ" ->  "ū"
+   "یِ" ->  "ī"
+   "بَاب" ->  "bāb"
+  # remark d: aspiration as in the original script
+   "بھ" ->  "bh"
+   "پھ" ->  "ph"
+  # remark c: nasal vowel marking
+   "وُں" ->  "ūṉ"
+  # madda and initial omission
+   "آ" ->  "ā"
+   "آب" ->  "āb"
+   "اُردُو" ->  "urdū"
+}
+
+stage main {
+
+  # sukun is never transliterated (carried over from section 6)
+  sub {
+    from "ْ"
+    to ""
+  }
+  # mark-order normalization: shadda before vowel sign
+  sub {
+    from "َّ"
+    to "َّ"
+  }
+  sub {
+    from "ِّ"
+    to "ِّ"
+  }
+  sub {
+    from "ُّ"
+    to "ُّ"
+  }
+
+  # long vowels: short-vowel sign plus lengthening letter merge
+  sub {
+    from "َا"
+    to "ā"
+  }
+  sub {
+    from "ِی"
+    to "ī"
+  }
+  sub {
+    from "ِي"
+    to "ī"
+  }
+  sub {
+    from "ِى"
+    to "ī"
+  }
+  sub {
+    from "ُو"
+    to "ū"
+  }
+  # diphthongs
+  sub {
+    from "َو"
+    to "au"
+  }
+  sub {
+    from "َی"
+    to "ai"
+  }
+  sub {
+    from "َي"
+    to "ai"
+  }
+
+  # madda: a-macron word-initially, ʾ plus a-macron internally
+  sub {
+    from boundary + "آ"
+    to "ā"
+  }
+  sub {
+    from "آ"
+    to "ʾā"
+  }
+
+  # remark b: alif and hamza word-initially are not rendered
+  sub {
+    from boundary + "ا"
+    to ""
+  }
+  sub {
+    from boundary + "ء"
+    to ""
+  }
+  sub {
+    from boundary + "أ"
+    to ""
+  }
+  sub {
+    from boundary + "إ"
+    to ""
+  }
+  sub {
+    from boundary + "ؤ"
+    to ""
+  }
+  sub {
+    from boundary + "ئ"
+    to ""
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "بّ" "bb"
+    sub "پّ" "pp"
+    sub "تّ" "tt"
+    sub "ٹّ" "ṭṭ"
+    sub "ثّ" "s̱s̱"
+    sub "جّ" "jj"
+    sub "چّ" "cc"
+    sub "حّ" "ḥḥ"
+    sub "خّ" "ẖẖ"
+    sub "دّ" "dd"
+    sub "ڈّ" "ḍḍ"
+    sub "ذّ" "ẕẕ"
+    sub "رّ" "rr"
+    sub "ڑّ" "ṛṛ"
+    sub "زّ" "zz"
+    sub "ژّ" "žž"
+    sub "سّ" "ss"
+    sub "شّ" "šš"
+    sub "صّ" "ṣṣ"
+    sub "ضّ" "z̤z̤"
+    sub "طّ" "t̤t̤"
+    sub "ظّ" "ẓẓ"
+    sub "عّ" "ʿʿ"
+    sub "غّ" "ġġ"
+    sub "فّ" "ff"
+    sub "قّ" "qq"
+    sub "کّ" "kk"
+    sub "گّ" "gg"
+    sub "لّ" "ll"
+    sub "مّ" "mm"
+    sub "نّ" "nn"
+    sub "ںّ" "ṉṉ"
+    sub "وّ" "vv"
+    sub "هّ" "hh"
+    sub "ھّ" "hh"
+    sub "يّ" "yy"
+    sub "یّ" "yy"
+    sub "وُ" "ū"
+    sub "يِ" "ī"
+    sub "یِ" "ī"
+    sub "أَ" "ʾa"
+    sub "إِ" "ʾi"
+    sub "ؤُ" "ʾu"
+    sub "ئِ" "ʾi"
+    sub "ئُ" "ʾu"
+    sub "ئَ" "ʾa"
+    sub "أُ" "ʾu"
+    sub "ء" "ʾ"
+    sub "أ" "ʾ"
+    sub "إ" "ʾ"
+    sub "ؤ" "ʾ"
+    sub "ئ" "ʾ"
+    sub "پ" "p"
+    sub "ٹ" "ṭ"
+    sub "چ" "c"
+    sub "ڈ" "ḍ"
+    sub "ژ" "ž"
+    sub "ڑ" "ṛ"
+    sub "گ" "g"
+    sub "ں" "ṉ"
+    sub "ے" "e"
+    sub "ا" "ā"
+    sub "ب" "b"
+    sub "ت" "t"
+    sub "ث" "s̱"
+    sub "ج" "j"
+    sub "ح" "ḥ"
+    sub "خ" "ẖ"
+    sub "د" "d"
+    sub "ذ" "ẕ"
+    sub "ر" "r"
+    sub "ز" "z"
+    sub "س" "s"
+    sub "ش" "š"
+    sub "ص" "ṣ"
+    sub "ض" "z̤"
+    sub "ط" "t̤"
+    sub "ظ" "ẓ"
+    sub "ع" "ʿ"
+    sub "غ" "ġ"
+    sub "ف" "f"
+    sub "ق" "q"
+    sub "ک" "k"
+    sub "ك" "k"
+    sub "ل" "l"
+    sub "م" "m"
+    sub "ن" "n"
+    sub "و" "v"
+    sub "ه" "h"
+    sub "ھ" "h"
+    sub "ي" "y"
+    sub "ی" "y"
+    sub "ى" "y"
+    sub "َ" "a"
+    sub "ِ" "i"
+    sub "ُ" "u"
+    sub "ً" "an"
+    sub "ٌ" ""
+    sub "ٍ" ""
+    sub "ّ" ""
+    sub "ٰ" "ā"
+  }
+
+}
+
+}

data/maps/din-uz-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,76 @@
+system "DIN:uz-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-61
+  language iso-639-3:uz
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 61: Usbekisch (Turkic)"
+  url https://www.beuth.de/de/norm/din-1460-2/134564104
+  creation_date 2011
+  adoption_date
+  description {
+    DIN 1460-2:2011-10, Romanization of Cyrillic alphabets of
+    non-Slavic languages, Tabelle 1, language row 61
+    (Usbekisch). The table assigns each Cyrillic letter of the
+    language's alphabet a Latin letter or letter group; the column
+    order follows DIN 1460:1982 (Slavic). Extracted mechanically from
+    the standard's text layer; the mapping rows below are the table's
+    own cells.
+  }
+
+  notes {
+    note "Extraction provenance: the PDF's text layer carries the full
+    grid; columns were anchored on the per-page position-number row and
+    each cell matched by x-coordinate to its Cyrillic header letter.
+    Position 13's header glyph is PUA (U+E519) in the text layer and
+    was visually identified at 10x as h with comma below (U+0068 + U+0322), the plain-h counterpart of position 12's hooktop-h symbol."
+  }
+}
+
+tests {
+   "a" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "g"
+}
+
+stage main {
+  parallel {
+    sub "a" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ғ" "ġ"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "к" "k"
+    sub "к̢" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ў" "ŭ"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ҳ" "ḩ"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "ъ" "\""
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

data/maps/din-xal-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,82 @@
+system "DIN:xal-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-21
+  language iso-639-3:xal
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 21: Kalmückisch (Mongolic)"
+  url https://www.beuth.de/de/norm/din-1460-2/134564104
+  creation_date 2011
+  adoption_date
+  description {
+    DIN 1460-2:2011-10, Romanization of Cyrillic alphabets of
+    non-Slavic languages, Tabelle 1, language row 21
+    (Kalmückisch). The table assigns each Cyrillic letter of the
+    language's alphabet a Latin letter or letter group; the column
+    order follows DIN 1460:1982 (Slavic). Extracted mechanically from
+    the standard's text layer; the mapping rows below are the table's
+    own cells.
+  }
+
+  notes {
+    note "Extraction provenance: the PDF's text layer carries the full
+    grid; columns were anchored on the per-page position-number row and
+    each cell matched by x-coordinate to its Cyrillic header letter.
+    Position 13's header glyph is PUA (U+E519) in the text layer and
+    was visually identified at 10x as h with comma below (U+0068 + U+0322), the plain-h counterpart of position 12's hooktop-h symbol."
+  }
+}
+
+tests {
+   "a" ->  "a"
+   "ä" ->  "ä"
+   "б" ->  "b"
+   "в" ->  "v"
+}
+
+stage main {
+  parallel {
+    sub "a" "a"
+    sub "ä" "ä"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "h" "h"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "ж̢" "ǧ"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "ң" "n"
+    sub "о" "o"
+    sub "ӧ" "ö"
+    sub "ө" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ӱ" "ü"
+    sub "ү" "ü"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "щ" "šč"
+    sub "ъ" "\""
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

data/maps/din-yid-Hebr-Latn-31636-2018.isc

@@ -0,0 +1,208 @@
+system "DIN:yid-Hebr:Latn:31636-2018" {
+
+metadata {
+  authority_id din
+  id 31636-2018
+  language iso-639-2:yid
+  source_script Hebr
+  destination_script Latn
+  name "DIN 31636:2018-10 Information und Dokumentation - Umschrift des hebraeischen Alphabets (jiddische Spalte)"
+  url https://www.din.de
+  creation_date 2018
+  confirmation_date 2018-10
+  description {    Information and documentation -- Romanization of the Hebrew alphabet, Yiddish
+    column. 2018-10 edition, replacing DIN 31636:2011-01. This map implements the
+    Yiddish column of Table 1 with the Yiddish vowel table (Table 4) and the Yiddish
+    notes (section 9) of the norm. The Hebrew column is a separate map.
+  }
+
+  notes {
+    note "Consonants (Table 1, Yiddish column): alef is rendered with the right half-ring U+02BE or as the vowel a/o via the vowel spellings; bet with dagesh b, bet v; gimel g; dalet d; he h; vav v with dot below (U+1E7F); double vav (U+05F0) is annotated als Konsonant and shares the row's consonantal rendering; zayin z; het h with dot below (U+1E25); tet t with dot below (U+1E6D); yod y; double yod (U+05F2) is annotated als Konsonant when consonantal, and as a vowel per Table 4 (ay or ey); kaf with dagesh k, khaf kh; lamed l; mem m; nun n; samekh s; ayin e; pe p, fe f; tsadi ts; kof k with dot below (k + U+0323); resh r; shin sh, sin s with acute (U+015B); tav s with grave (U+0073+0300) per section 9(c) - the voiceless-s pronunciation of tav."
+    note "Vowels (Table 4): alef with patach (U+FB2A? no - U+05D0+05B7) a; alef with qamats (U+05D0+05B8) a or o - this map renders a, the o-reading is a pronunciation-side determination; ayin e; vav or alef-vav u or o - this map renders u, the norm's own section 9(a) examples use the o-reading (moyre, koyles); vav-yod (U+05F1) or alef-vav-yod oy; yod or alef-yod i; yod-yod (U+05F2) or alef-yod-yod ay or ey, je nach Aussprache - this map renders ay and documents ey as the alternative reading of the same spelling."
+    note "Section 9(a): Hebrew words occurring in a Yiddish context are verified for Yiddish pronunciation in Weinreich and then transliterated with Table 1 (Yiddish) and Table 4; Hebrew proper names in a Yiddish context follow the Yiddish pronunciation. The distinction between tav/tet, kof/khaf and khaf/het is made with the underdots, and word-final he is rendered h."
+    note "Section 9(c): tav pronounced as voiceless s is rendered with the grave (s + U+0300), e.g. bes (beyt-yod-tav)."
+    note "Section 9(d): vowels not written in Old Yiddish may optionally be marked with a stroke above the vowel; this map does not add such marks."
+    note "Words whose vowels are not written in the spelling (loshn-koydesh items such as the norm's own mehaber/moyre examples) are an underspecified skeleton: the unwritten vowels are resolved by a vocalization model, after which this map applies (composition, not duplication)."
+    note "Capitalization and hyphenation follow the rules given for Hebrew (rule 8i/b); this map outputs lower case."
+  }
+}
+
+tests {
+  # table 1 Yiddish column rows
+   "א" ->  "ʾ"
+   "בּ" ->  "b"
+   "בּ" ->  "b"
+   "ב" ->  "v"
+   "ג" ->  "g"
+   "ד" ->  "d"
+   "ה" ->  "h"
+   "ו" ->  "ṿ"
+   "װ" ->  "ṿ"
+   "ז" ->  "z"
+   "ח" ->  "ḥ"
+   "ט" ->  "ṭ"
+   "י" ->  "y"
+   "כּ" ->  "k"
+   "כּ" ->  "k"
+   "כ" ->  "kh"
+   "ך" ->  "kh"
+   "ל" ->  "l"
+   "מ" ->  "m"
+   "ם" ->  "m"
+   "נ" ->  "n"
+   "ן" ->  "n"
+   "ס" ->  "s"
+   "ע" ->  "e"
+   "פּ" ->  "p"
+   "פּ" ->  "p"
+   "פ" ->  "f"
+   "ף" ->  "f"
+   "צ" ->  "ts"
+   "ץ" ->  "ts"
+   "ק" ->  "ḳ"
+   "ר" ->  "r"
+   "שׁ" ->  "sh"
+   "שׁ" ->  "sh"
+   "שׂ" ->  "ś"
+   "שׂ" ->  "ś"
+   "תּ" ->  "t"
+   "תּ" ->  "t"
+   "ת" ->  "s̀"
+  # table 2 rows (geresh-marked, same as Hebrew column)
+   "גʹ" ->  "gʹ"
+   "דʹ" ->  "dʹ"
+   "זʹ" ->  "zʹ"
+   "חʹ" ->  "ḥʹ"
+   "טʹ" ->  "ṭʹ"
+   "עʹ" ->  "ġ"
+   "צʹ" ->  "tsʹ"
+  # table 4 rows
+   "אַ" ->  "a"
+   "אָ" ->  "a"
+   "ע" ->  "e"
+   "ױ" ->  "oy"
+   "אױ" ->  "oy"
+   "ײ" ->  "ay"
+   "אײ" ->  "ay"
+   "אי" ->  "i"
+   "או" ->  "u"
+}
+
+stage main {
+
+  # RULES
+  # table 4: the Yiddish vowel spellings are sequences of letters and
+  # must be matched before their single letters
+  sub {
+    from "אַ"
+    to "a"
+  }
+  sub {
+    from "אָ"
+    to "a"
+  }
+  sub {
+    from "אױ"
+    to "oy"
+  }
+  sub {
+    from "או"
+    to "u"
+  }
+  sub {
+    from "אי"
+    to "i"
+  }
+  sub {
+    from "אײ"
+    to "ay"
+  }
+  sub {
+    from "ױ"
+    to "oy"
+  }
+  sub {
+    from "ײ"
+    to "ay"
+  }
+
+  # sin and shin dots
+  sub {
+    from "שׂ"
+    to "ś"
+  }
+  sub {
+    from "שׁ"
+    to "sh"
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "גʹ" "gʹ"
+    sub "דʹ" "dʹ"
+    sub "זʹ" "zʹ"
+    sub "חʹ" "ḥʹ"
+    sub "טʹ" "ṭʹ"
+    sub "עʹ" "ġ"
+    sub "צʹ" "tsʹ"
+    sub "שׂ" "ś"
+    sub "שׁ" "sh"
+    sub "בּ" "b"
+    sub "כּ" "k"
+    sub "פּ" "p"
+    sub "וּ" "u"
+    sub "בּ" "b"
+    sub "כּ" "k"
+    sub "פּ" "p"
+    sub "וּ" "u"
+    sub "וֹ" "o"
+    sub "שׁ" "sh"
+    sub "שׂ" "ś"
+    sub "תּ" "t"
+    sub "אַ" "a"
+    sub "אָ" "a"
+    sub "װ" "ṿ"
+    sub "ך" "kh"
+    sub "כ" "kh"
+    sub "ם" "m"
+    sub "מ" "m"
+    sub "ן" "n"
+    sub "נ" "n"
+    sub "ף" "f"
+    sub "פ" "f"
+    sub "ץ" "ts"
+    sub "צ" "ts"
+    sub "א" "ʾ"
+    sub "ב" "v"
+    sub "ג" "g"
+    sub "ד" "d"
+    sub "ה" "h"
+    sub "ו" "ṿ"
+    sub "ז" "z"
+    sub "ח" "ḥ"
+    sub "ט" "ṭ"
+    sub "י" "y"
+    sub "ל" "l"
+    sub "ס" "s"
+    sub "ע" "e"
+    sub "ק" "ḳ"
+    sub "ר" "r"
+    sub "ש" "sh"
+    sub "תּ" "t"
+    sub "ת" "s̀"
+    sub "ַ" "a"
+    sub "ָ" "a"
+    sub "ֶ" "e"
+    sub "ֵ" "e"
+    sub "ִ" "i"
+    sub "ֹ" "o"
+    sub "ֻ" "u"
+    sub "ֲ" "a"
+    sub "ֱ" "e"
+    sub "ֳ" "o"
+    sub "ּ" ""
+  }
+
+}
+
+}