interscript-maps 2.5.2 → 3.0.0

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

@@ -0,0 +1,76 @@
+system "DIN:mns-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-35
+  language iso-639-3:mns
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 35: Mansisch (Uralic)"
+  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 35
+    (Mansisch). 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 "ў" "ŭ"
+    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-mrj-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,79 @@
+system "DIN:mrj-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-45
+  language iso-639-3:mrj
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 45: Berg-Mari (Uralic)"
+  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 45
+    (Berg-Mari). 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 "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 "ҥ" "n"
+    sub "о" "o"
+    sub "ӧ" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ӱ" "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 "ӹ" "ÿ"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

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

@@ -0,0 +1,74 @@
+system "DIN:myv-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-13
+  language iso-639-3:myv
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 13: Ersa-Mordwinisch (Uralic)"
+  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 13
+    (Ersa-Mordwinisch). 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 "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-niv-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,80 @@
+system "DIN:niv-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-43
+  language iso-639-3:niv
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 43: Niwchisch (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 43
+    (Niwchisch). 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 "ҕ" "ġ"
+    sub "ɦ̢" "ǵ"
+    sub "h" "h"
+    sub "h̢" "ḩ"
+    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 "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-nog-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,74 @@
+system "DIN:nog-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-44
+  language iso-639-3:nog
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 44: Nogaisch (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 44
+    (Nogaisch). 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 "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-os-Cyrl-Latn-1460-2-2011.isc

@@ -0,0 +1,89 @@
+system "DIN:os-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-46
+  language iso-639-3:os
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 46: Ossetisch (Indo-European)"
+  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 46
+    (Ossetisch). 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"
+   "æ" ->  "ä"
+   "б" ->  "b"
+   "в" ->  "v"
+}
+
+stage main {
+  parallel {
+    sub "a" "a"
+    sub "æ" "ä"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ҕ" "ġ"
+    sub "h" "h"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "д +с" "ǧ"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "j" "j́"
+    sub "к" "k"
+    sub "к̢" ""
+    sub "q" "q"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "п" "p"
+    sub "ҧ" "р́"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "Ђ" ""
+    sub "у" "u"
+    sub "у̅" "ū"
+    sub "ў" "ŭ"
+    sub "ѵ" "у̇"
+    sub "w" "w"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ҵ" "ç"
+    sub "ч" "č"
+    sub "ӌ" "ǵ"
+    sub "ш" "š"
+    sub "щ" "śč"
+    sub "ъ" "q"
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

data/maps/din-ro-Cyrl-Latn-1460-2-2011-s38.isc

@@ -0,0 +1,72 @@
+system "DIN:ro-Cyrl:Latn:1460-2-2011-s38" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-38
+  language iso-639-3:ro
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 38: Moldauisch (Moldavian (Cyrillic)) (Indo-European)"
+  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 38
+    (Moldauisch (Moldavian (Cyrillic))). 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: Moldavian (Cyrillic); 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 "д" "d"
+    sub "е" "e"
+    sub "ж" "ž"
+    sub "ӂ" "dž"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "к" "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 "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}

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

@@ -0,0 +1,89 @@
+system "DIN:sah-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-19
+  language iso-639-3:sah
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 19: Jakutisch (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 19
+    (Jakutisch). 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 "ҕ" "ġ"
+    sub "h" "h"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ё"
+    sub "ж" "ž"
+    sub "д +с" "ǧ"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "j"
+    sub "i" "í"
+    sub "j" "j́"
+    sub "j̶̶̶ ̶" "j̄"
+    sub "к" "k"
+    sub "л" "l"
+    sub "l" ""
+    sub "м" "m"
+    sub "н" "n"
+    sub "ң" ""
+    sub "ҥ" "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 "џ" "ḑž"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "щ" "šč"
+    sub "ъ" "\""
+    sub "ы" "y"
+    sub "ь" "'"
+    sub "э" "ė"
+  }
+}
+}