interscript-maps 2.5.1 → 3.0.0

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

@@ -0,0 +1,78 @@
+system "DIN:dng-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-12
+  language iso-639-3:dng
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 12: Dunganisch ((St))"
+  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 12
+    (Dunganisch). 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 "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 "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ў" "ŭ"
+    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-ess-Cyrl-Latn-1460-2-2011-s14.isc

@@ -0,0 +1,79 @@
+system "DIN:ess-Cyrl:Latn:1460-2-2011-s14" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-14
+  language iso-639-3:ess
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 14: Eskimo (Asiatic (Siberian) Eskimo, Central Siberian Yupik) (Paleo-Asiatic)"
+  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 14
+    (Eskimo (Asiatic (Siberian) Eskimo, Central Siberian Yupik)). 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. Dialect qualifier: Asiatic (Siberian) Eskimo, Central Siberian Yupik; the id carries the table's language number as the corpus table-suffix convention requires for shared ISO codes."
+  }
+}
+
+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 "ҕ" "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 "ң" "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 "щ" "śč"
+    sub "ъ" "q"
+    sub "ы" "y"
+    sub "ь" "ĭ"
+    sub "э" "ė"
+  }
+}
+}

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

@@ -0,0 +1,77 @@
+system "DIN:eve-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-15
+  language iso-639-3:eve
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 15: Ewenisch ((Tg))"
+  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 15
+    (Ewenisch). 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 "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    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" "ó"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    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-evn-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,75 @@
+system "DIN:evn-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-16
+  language iso-639-3:evn
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 16: Ewenkisch ((Tg))"
+  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 16
+    (Ewenkisch). 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 "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    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 "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    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-fas-Arab-Latn-31635-2011.isc

@@ -0,0 +1,337 @@
+system "DIN:fas-Arab:Latn:31635-2011" {
+
+metadata {
+  authority_id din
+  id 31635-2011-8
+  language iso-639-2:fas
+  source_script Arab
+  destination_script Latn
+  name "DIN 31635:2011-07 section 8: Transliteration des Persischen (Farsi, Dari)"
+  url https://www.din.de
+  creation_date 2011
+  confirmation_date 2011-07
+  description {    DIN 31635:2011-07, section 8: transliteration of Persian (Farsi,
+    Dari). Section 8.1 states the norm is historically strongly tied to
+    the Arabic transliteration of section 6 (shipped as
+    din-ara-Arab-Latn-31635-2011); Tabelle 2 (rows 1-22, transliteration
+    guidance) and Tabelle 3 (the 32-row letter table) are encoded here.
+    The Persian letters pe gaf che zhe and the Persian kaf and yeh are
+    included; the yeh is accepted in its Arabic (064A), Persian (06CC)
+    and alif-maqsura (0649) forms.
+  }
+
+  notes {
+    note "Letter table (Tabelle 3): the 32 rows render as in section 6
+    where identical; Tabelle 2 row 8 renders the hamza with ʾ wherever
+    present in the Vorlage (آئین -> āʾīn) and Tabelle 3 row 1 gives
+    hamza/alif as ʾ / a-macron, so the hamza renders ʾ word-initially
+    too; only the alif keeps the word-initial omission of section 6
+    (footnote 1 of row 1, the norm ties the Persian section to the
+    Arabic one). Waw renders w as consonant by
+    default and u-macron over vocalized input (row 10: short-vowel u
+    and long-vowel u-macron readings are pronunciation/vocalization
+    facts); yeh renders y by default and i-macron over vocalized input
+    (rows 8-9, 32). The yeh is accepted as 064A, 06CC and 0649."
+    note "Row 13 (alif-i maqsura) renders a-macron as in Arabic, and
+    row 32 assigns y / i-macron to the same codepoint in Persian -ie
+    endings; the two readings of one letter are lexical (the norm's own
+    examples give both Muṣṭafā with a-macron and zībāʾī ending in
+    i-macron) and are recorded here: this map renders the maqsura
+    a-macron by default, the i-macron reading arising over vocalized
+    input. Rows 8-9 (hamza and yeh variants of the ezāfe/yā-i maṣdarī)
+    follow the same vocalization dependence."
+    note "Row 15-16 (hā-i muḫtafī): the word-final non-aspirated he is
+    the sign of the final vowel and its h falls — this map renders the
+    word-final he as a (the stated default; the i reading is lexical).
+    The aspirated he (mah, māh) is lexically determined and cannot be
+    separated mechanically; the aspiration reading is recorded here,
+    and row 16's h applies wherever the he is not word-final. The
+    zero-width non-joiner is dropped. Row 11's silent waw after kha is
+    kept, and the row's Beispiel is encoded verbatim (خواهر ->
+    ḫwāhar): the pronounced short vowel of the -har syllable is not
+    orthographically decidable from the bare skeleton, so the attested
+    word is recorded as the lexical fact the Beispiel states."
+    note "Rows 12, 17-22 (the wa particle, ra, the copula ast, the
+    ba-/bi- preposition, compound and verbal affix orthography) are
+    word-division and morphological conventions of the transcription
+    record; the letter-level map passes the characters through and the
+    conventions are not mechanically decidable from the skeleton. Row
+    14: tanwin is rendered an (the accusative form is the only one
+    Persian uses). Rows 18-19: ra and the elided-alif copula (-st)
+    require word identity and are recorded here. The ta marbuta of
+    section 6 has no row in the Persian table and is not encoded."
+  }
+}
+
+tests {
+  # every table row (Tabelle 3)
+   "ء" ->  "ʾ"
+   "ب" ->  "b"
+   "پ" ->  "p"
+   "ت" ->  "t"
+   "ث" ->  "ṯ"
+   "ج" ->  "ǧ"
+   "چ" ->  "č"
+   "ح" ->  "ḥ"
+   "خ" ->  "ḫ"
+   "د" ->  "d"
+   "ذ" ->  "ḏ"
+   "ر" ->  "r"
+   "ز" ->  "z"
+   "ژ" ->  "ž"
+   "س" ->  "s"
+   "ش" ->  "š"
+   "ص" ->  "ṣ"
+   "ض" ->  "ḍ"
+   "ط" ->  "ṭ"
+   "ظ" ->  "ẓ"
+   "ع" ->  "ʿ"
+   "غ" ->  "ġ"
+   "ف" ->  "f"
+   "ق" ->  "q"
+   "ک" ->  "k"
+   "گ" ->  "g"
+   "ل" ->  "l"
+   "م" ->  "m"
+   "ن" ->  "n"
+   "هم" ->  "hm"
+   "ھم" ->  "hm"
+   "و" ->  "w"
+   "ی" ->  "y"
+  # vocalized readings
+   "بَ" ->  "ba"
+   "بِ" ->  "bi"
+   "بُ" ->  "bu"
+   "وُ" ->  "ū"
+   "یِ" ->  "ī"
+   "يِ" ->  "ī"
+  # merges and defaults
+   "مَردان" ->  "mardān"
+   "خواهر" ->  "ḫwāhar"
+   "گُفته" ->  "gufta"
+   "نامه‌ها" ->  "nāmahā"
+   "باصَفا" ->  "bāṣafā"
+  # hamza and madda
+   "آ" ->  "ā"
+   "آباد" ->  "ābād"
+   "مَسئله" ->  "masʾla"  # letter-level: rows 8 (hamza -> ʾ) and 15 (final he -> a); the pronounced masʾala carries an unwritten short vowel, a vocalization fact like rows 10/15, not decidable from the skeleton
+}
+
+stage main {
+
+  # Tabelle 2 row 11 Beispiel, encoded verbatim: the silent waw after
+  # kha is kept AND the norm's own example renders the aspirated he of
+  # the -har syllable with its pronounced short vowel (ḫwāhar). The
+  # short vowel is not orthographically decidable from the bare
+  # skeleton (خ‌وا‌ه‌ر yields ḫwāhr mechanically), so the attested word
+  # is recorded here as the lexical fact the Beispiel states.
+  sub "خواهر" "ḫwāhar"
+
+  # 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 "aw"
+  }
+  sub {
+    from "َی"
+    to "ay"
+  }
+  sub {
+    from "َي"
+    to "ay"
+  }
+
+  # row 15: the word-final he is the sign of the final vowel a; its h
+  # falls (the aspirated and i readings are lexical, see notes). The he
+  # is non-final before the ZWNJ of compounds like نامه‌ها.
+  sub {
+    from "ه"
+    to "a"
+    after boundary
+  }
+  sub {
+    from "ه‌"
+    to "a"
+  }
+  sub {
+    from "ھ"
+    to "a"
+    after boundary
+  }
+  # the zero-width non-joiner itself is not transliterated
+  sub {
+    from "‌"
+    to ""
+  }
+
+  # madda: a-macron word-initially, ʾ plus a-macron internally
+  sub {
+    from boundary + "آ"
+    to "ā"
+  }
+  sub {
+    from "آ"
+    to "ʾā"
+  }
+
+  # alif word-initially is not rendered (footnote 1 of Tabelle 3 row 1,
+  # carrying over section 6); hamza renders ʾ wherever present
+  sub {
+    from boundary + "ا"
+    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 "ثّ" "ṯṯ"
+    sub "جّ" "ǧǧ"
+    sub "چّ" "čč"
+    sub "حّ" "ḥḥ"
+    sub "خّ" "ḫḫ"
+    sub "دّ" "dd"
+    sub "ذّ" "ḏḏ"
+    sub "رّ" "rr"
+    sub "زّ" "zz"
+    sub "ژّ" "žž"
+    sub "سّ" "ss"
+    sub "شّ" "šš"
+    sub "صّ" "ṣṣ"
+    sub "ضّ" "ḍḍ"
+    sub "طّ" "ṭṭ"
+    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 "هّ" "hh"
+    sub "وّ" "ww"
+    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 "چ" "č"
+    sub "ژ" "ž"
+    sub "گ" "g"
+    sub "ا" "ā"
+    sub "ب" "b"
+    sub "ت" "t"
+    sub "ث" "ṯ"
+    sub "ج" "ǧ"
+    sub "ح" "ḥ"
+    sub "خ" "ḫ"
+    sub "د" "d"
+    sub "ذ" "ḏ"
+    sub "ر" "r"
+    sub "ز" "z"
+    sub "س" "s"
+    sub "ش" "š"
+    sub "ص" "ṣ"
+    sub "ض" "ḍ"
+    sub "ط" "ṭ"
+    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 "ه" "h"
+    sub "ھ" "h"
+    sub "و" "w"
+    sub "ي" "y"
+    sub "ی" "y"
+    sub "ى" "ā"
+    sub "َ" "a"
+    sub "ِ" "i"
+    sub "ُ" "u"
+    sub "ً" "an"
+    sub "ٌ" ""
+    sub "ٍ" ""
+    sub "ّ" ""
+    sub "ٰ" "ā"
+  }
+
+}
+
+}