interscript-maps 2.5.1 → 3.0.0

data/maps/bsi-srp-Cyrl-Latn-1958.isc

@@ -0,0 +1,134 @@
+system "BSI:srp-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:srp
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Serbian column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Serbian column: the "British" system for (modern) Cyrillic.
+    Table A is a five-column family table (East Slavonic: Russian, Ukrainian,
+    Byelorussian; South Slavonic: Bulgarian, Serbian and Macedonian).
+    This map is the Serbian rows of the column; the Macedonian-specific letters
+    (ѓ, ѕ, ќ) are a separate map.
+  }
+
+  notes {
+    note "NOTE 1 of Section 1: for extreme simplicity, when avoidance of ambiguity in back transliteration is not a paramount consideration, all accents, diacritics, etc., may be omitted in the English rendering; the document's own examples apply this (the document's own examples apply it). This map applies the table as printed, with the diacritics."
+    note "NOTE 2 of Section 1: Cyrillic characters for which the transliteration is given in parentheses, though no longer in official use, are sometimes found in the literature of the relevant language; this map renders them as given in the parentheses."
+    note "Rows 45 to 47 of Table A (the little yus, fita, izhitsa) are not rendered: their parenthesized cells are not legible beyond doubt in the scan and this map does not guess them. Table B (back transliteration) is out of scope; Table C is ISO/R9 and is cited against the existing iso corpus maps."
+    note "Row 38/40 choices: this map renders the hard sign with the right double quotation mark (U+201D) and the soft sign with the right single quotation mark (U+2019), the first option of each cell. The Serbian alphabet has no hard or soft sign."
+    note "The Serbian and Macedonian column gives the latinica, the existing Latin alphabet of Serbo-Croat, to avoid the confusion of an English transliteration. The footnote to Table A: in latinica, dj and gj are still sometimes found as alternatives to d with caron, but the practice is disappearing."
+  }
+}
+
+tests {
+   "Заштита биља" ->  "Zaštita bilja"
+   "Скопље" ->  "Skoplje"
+   "Српски Архив" ->  "Srpski Arhiv"
+   "Ђ" ->  "Đ"
+   "ђ" ->  "đ"
+   "Ћ" ->  "Ć"
+   "ћ" ->  "ć"
+   "Џ" ->  "Dž"
+   "џ" ->  "dž"
+   "Љ" ->  "Lj"
+   "љ" ->  "lj"
+   "Њ" ->  "Nj"
+   "њ" ->  "nj"
+   "а" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "g"
+   "д" ->  "d"
+   "е" ->  "e"
+   "ж" ->  "ž"
+   "з" ->  "z"
+   "и" ->  "i"
+   "ј" ->  "j"
+   "к" ->  "k"
+   "л" ->  "l"
+   "м" ->  "m"
+   "н" ->  "n"
+   "о" ->  "o"
+   "п" ->  "p"
+   "р" ->  "r"
+   "с" ->  "s"
+   "т" ->  "t"
+   "ц" ->  "c"
+   "ч" ->  "č"
+   "ш" ->  "š"
+   "х" ->  "h"
+
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Ђ" "Đ"
+    sub "Е" "E"
+    sub "Ж" "Ž"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Ј" "J"
+    sub "К" "K"
+    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 "Ц" "C"
+    sub "Ч" "Č"
+    sub "Џ" "Dž"
+    sub "Ш" "Š"
+    sub "Х" "H"
+
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "ђ" "đ"
+    sub "е" "e"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "и" "i"
+    sub "ј" "j"
+    sub "к" "k"
+    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 "ц" "c"
+    sub "ч" "č"
+    sub "џ" "dž"
+    sub "ш" "š"
+    sub "х" "h"
+  }
+
+}
+
+}

data/maps/bsi-ukr-Cyrl-Latn-1958.isc

@@ -0,0 +1,129 @@
+system "BSI:ukr-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Ukrainian column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Ukrainian column: the "British" system for (modern) Cyrillic.
+    Table A is a five-column family table (East Slavonic: Russian, Ukrainian,
+    Byelorussian; South Slavonic: Bulgarian, Serbian and Macedonian).
+  }
+
+  notes {
+    note "NOTE 1 of Section 1: for extreme simplicity, when avoidance of ambiguity in back transliteration is not a paramount consideration, all accents, diacritics, etc., may be omitted in the English rendering; the document's own examples apply this (the document's own example Kyyiv applies it to the table's Kȳyiv). This map applies the table as printed, with the diacritics."
+    note "NOTE 2 of Section 1: Cyrillic characters for which the transliteration is given in parentheses, though no longer in official use, are sometimes found in the literature of the relevant language; this map renders them as given in the parentheses."
+    note "Rows 45 to 47 of Table A (the little yus, fita, izhitsa) are not rendered: their parenthesized cells are not legible beyond doubt in the scan and this map does not guess them. Table B (back transliteration) is out of scope; Table C is ISO/R9 and is cited against the existing iso corpus maps."
+    note "Row 38/40 choices: this map renders the hard sign with the right double quotation mark (U+201D) and the soft sign with the right single quotation mark (U+2019), the first option of each cell."
+    note "The Serbian and Macedonian column gives the latinica, the existing Latin alphabet of Serbo-Croat, to avoid the confusion of an English transliteration. The footnote to Table A: in latinica, dj and gj are still sometimes found as alternatives to d with caron, but the practice is disappearing."
+  }
+}
+
+tests {
+   "Української" ->  "Ukrayins’koyi"
+   "Харкова" ->  "Kharkova"
+   "Київ" ->  "Kȳyiv"
+   "Вісник" ->  "Visnȳk"
+   "Ґ" ->  "G"
+   "ґ" ->  "g"
+   "Є" ->  "Ye"
+   "є" ->  "ye"
+   "Ї" ->  "Yi"
+   "ї" ->  "yi"
+   "Ъ" ->  "”"
+   "Ь" ->  "’"
+   "Ѣ" ->  "Ě"
+   "ѣ" ->  "ě"
+   "Тс" ->  "T-s"
+   "тс" ->  "t-s"
+   "ѣ" ->  "ě"
+
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "Тс" "T-s"
+    sub "тс" "t-s"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "H"
+    sub "Ґ" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Є" "Ye"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "Ȳ"
+    sub "І" "I"
+    sub "Ї" "Yi"
+    sub "Й" "Ĭ"
+    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" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Щ" "Shch"
+    sub "Ъ" "”"
+    sub "Ь" "’"
+    sub "Ѣ" "Ě"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "h"
+    sub "ґ" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "є" "ye"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "ȳ"
+    sub "і" "i"
+    sub "ї" "yi"
+    sub "й" "ĭ"
+    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" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "щ" "shch"
+    sub "ъ" "”"
+    sub "ь" "’"
+    sub "ѣ" "ě"
+    sub "ю" "yu"
+    sub "я" "ya"
+  }
+
+}
+
+}

data/maps/by-bel-Cyrl-Latn-1998.isc

@@ -69,6 +69,7 @@ tests {
 
 dependency "gost-rus-Cyrl-Latn-16876-71-1983" as cyrllatn
 dependency "var-Cyrl"
+dependency "var-kor"
 
 stage main {
   # RULES

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

@@ -0,0 +1,83 @@
+system "DIN:ab-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-2
+  language iso-639-3:ab
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 2: Abchasisch (Caucasus)"
+  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 2
+    (Abchasisch). 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 "д" "d"
+    sub "е" "e"
+    sub "ҽ" "ċ"
+    sub "ҿ" "ć"
+    sub "ж" "ž"
+    sub "з" "z"
+    sub "ӡ" "z̈"
+    sub "и" "i"
+    sub "к" "k"
+    sub "к̢" "k"
+    sub "ҟ" "q"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "ҩ" "w"
+    sub "п" "p"
+    sub "ҧ" "р́"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "Ђ" "ţ"
+    sub "у" "u"
+    sub "ѵ" "у̇"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ҳ" "ḩ"
+    sub "ц" "c"
+    sub "ҵ" "ç"
+    sub "џ" "ḑž"
+    sub "ч" "č"
+    sub "ӌ" "ǵ"
+    sub "ш" "š"
+    sub "ы" "y"
+    sub "ь" "ĭ"
+  }
+}
+}

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

@@ -0,0 +1,66 @@
+system "DIN:abq-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-1
+  language iso-639-3:abq
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 1: Abasinisch (Caucasus)"
+  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 1
+    (Abasinisch). 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 "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 "ч" "č"
+    sub "ш" "š"
+    sub "щ" "śč"
+    sub "ъ" "q"
+    sub "ы" "y"
+    sub "ь" "ĭ"
+    sub "э" "ė"
+  }
+}
+}

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

@@ -0,0 +1,73 @@
+system "DIN:ady-Cyrl:Latn:1460-2-2011" {
+
+metadata {
+  authority_id din
+  id 1460-2-2011-3
+  language iso-639-3:ady
+  source_script Cyrl
+  destination_script Latn
+  name "DIN 1460-2:2011-10, Tabelle 1 row 3: Adygeisch (Caucasus)"
+  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 3
+    (Adygeisch). 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 "у" "u"
+    sub "ф" "f"
+    sub "х" "h"
+    sub "ц" "c"
+    sub "ч" "č"
+    sub "ш" "š"
+    sub "щ" "śč"
+    sub "ъ" "q"
+    sub "ы" "y"
+    sub "ь" "ĭ"
+    sub "э" "ė"
+  }
+}
+}