interscript-maps 2.5.2 → 3.0.0

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

@@ -0,0 +1,140 @@
+system "BSI:mkd-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:mkd
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Serbian & Macedonian (Macedonian) column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Serbian & Macedonian (Macedonian) 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).
+    The column is shared with Serbian; this map adds the Macedonian-specific
+    letters ѓ, ѕ and ќ to the shared rows.
+  }
+
+  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 "Footnote to Table A: in latinica, dj and gj are still sometimes found as alternatives to d-with-caron (Ђ and Ѓ), but the practice is disappearing; this map renders both ѓ and ђ as d-with-caron."
+    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 {
+   "Македонски Јазик" ->  "Makedonski Jazik"
+   "Ѓ" ->  "Đ"
+   "ѓ" ->  "đ"
+   "Ѕ" ->  "Dz"
+   "ѕ" ->  "dz"
+   "Ќ" ->  "Ć"
+   "ќ" ->  "ć"
+   "а" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "g"
+   "д" ->  "d"
+   "ђ" ->  "đ"
+   "е" ->  "e"
+   "ж" ->  "ž"
+   "з" ->  "z"
+   "и" ->  "i"
+   "ј" ->  "j"
+   "к" ->  "k"
+   "л" ->  "l"
+   "љ" ->  "lj"
+   "м" ->  "m"
+   "н" ->  "n"
+   "њ" ->  "nj"
+   "о" ->  "o"
+   "п" ->  "p"
+   "р" ->  "r"
+   "с" ->  "s"
+   "т" ->  "t"
+   "ћ" ->  "ć"
+   "ц" ->  "c"
+   "ч" ->  "č"
+   "џ" ->  "dž"
+   "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 "Ѓ" "Đ"
+    sub "Ѕ" "Dz"
+    sub "Ќ" "Ć"
+
+    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 "ѓ" "đ"
+    sub "ѕ" "dz"
+    sub "ќ" "ć"
+  }
+
+}
+
+}

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

@@ -0,0 +1,244 @@
+system "BSI:ron-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:ron
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table E, Transliteration of Rumanian Cyrillic (Alfabetul Cirilic)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table E: transliteration of Rumanian Cyrillic (Alfabetul Cirilic),
+    the Cyrillic alphabet used for Romanian until 1860. For transliteration of
+    Moldavian in the modern orthography, the table's companion note directs the
+    reader to Table C (ISO/R9) in Section 2.
+  }
+
+  notes {
+    note "The table's footnote marks variant renderings encountered in latinised Rumanian that make for ambiguity in retransliteration and should therefore be avoided in documents for export: No. 6 ie (after vowels); 8 z; 23 ch; 24 o; 29 a-breve alternatives; 30 i and a-circumflex alternatives; 32 e; 36 e and ia; 37 u-breve; 40 t; 41 i. This map applies the primary renderings as printed."
+    note "K is romanized c, and ch before e and i; this map implements the context rule for the letters e, i and i-diaeresis following k, and renders c elsewhere. Dzhe (row 43, shaped like ts with a descender) is romanized g, the table conditioning the rendering on position before e and i."
+    note "Yer is romanized a with breve; yery as a-circumflex plus i; yat as ea; the little yus as e with circumflex and the big yus as a with circumflex. The soft sign is u with breve, omitted when final; this map renders it u with breve in all positions and does not implement the final-omission rule, which requires word-boundary handling the note leaves to the user."
+    note "The semiyus (row 42) is printed with the rendering i-circumflex and the parenthetical n; this map renders the letter as the two-letter reading in."
+    note "The digraph uk (o plus u, with monograph-uk variants) is romanized u with breve, the table also showing the alternative rendering as the two separate letters."
+    note "Fita is romanized th and izhitsa y, the source's own footnote listing t and i among the ambiguous variants to avoid."
+    note "Transcribed visually from the scanned table page of the digitized BS 2979:1958 (BSI 05-2000 reprint); row 43's dzhe and the yus readings were confirmed at 14x-20x magnification."
+  }
+}
+
+tests {
+  # every table row, upper and lower
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "G"
+   "г" ->  "g"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Є" ->  "E"
+   "є" ->  "e"
+   "Ж" ->  "J"
+   "ж" ->  "j"
+   "Ѕ" ->  "Dz"
+   "ѕ" ->  "dz"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Й" ->  "Ĭ"
+   "й" ->  "ĭ"
+   "І" ->  "I"
+   "і" ->  "i"
+   "Ї" ->  "Ï"
+   "ї" ->  "ï"
+  # row 12: k is c, ch before e & i
+   "К" ->  "C"
+   "к" ->  "c"
+   "ке" ->  "che"
+   "Ки" ->  "Chi"
+   "ка" ->  "ca"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "ОУ" ->  "Ŭ"
+   "оу" ->  "ŭ"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "H"
+   "х" ->  "h"
+   "Ѡ" ->  "Ō"
+   "ѡ" ->  "ō"
+   "Ц" ->  "Ţ"
+   "ц" ->  "ţ"
+   "Ч" ->  "C"
+   "ч" ->  "c"
+   "Ш" ->  "Ş"
+   "ш" ->  "ş"
+   "Щ" ->  "Şt"
+   "щ" ->  "şt"
+   "Ъ" ->  "Ă"
+   "ъ" ->  "ă"
+   "Ы" ->  "Âi"
+   "ы" ->  "âi"
+   "Ь" ->  "Ŭ"
+   "ь" ->  "ŭ"
+   "Ѣ" ->  "Ea"
+   "ѣ" ->  "ea"
+   "Ю" ->  "Iu"
+   "ю" ->  "iu"
+   "ІА" ->  "Ia"
+   "іа" ->  "ia"
+   "Ѥ" ->  "Ie"
+   "ѥ" ->  "ie"
+   "Ѧ" ->  "Ê"
+   "ѧ" ->  "ê"
+   "Ѫ" ->  "Â"
+   "ѫ" ->  "â"
+   "Ѯ" ->  "X"
+   "ѯ" ->  "x"
+   "Ѱ" ->  "Ps"
+   "ѱ" ->  "ps"
+   "Ѳ" ->  "Th"
+   "ѳ" ->  "th"
+   "Ѵ" ->  "Y"
+   "ѵ" ->  "y"
+   "Ꙏ" ->  "În"
+   "ꙏ" ->  "în"
+   "Џ" ->  "G"
+   "џ" ->  "g"
+}
+
+stage main {
+
+  # RULES
+  # row 12: k is ch before e & i, c elsewhere
+  sub {
+    from "К"
+    to "Ch"
+    after any("ЕеИиІіЇї")
+  }
+  sub {
+    from "к"
+    to "ch"
+    after any("ЕеИиІіЇї")
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "ІА" "Ia"
+    sub "ОУ" "Ŭ"
+    sub "Ѣ" "Ea"
+    sub "Ѥ" "Ie"
+    sub "Ѧ" "Ê"
+    sub "Ѫ" "Â"
+    sub "Ѯ" "X"
+    sub "Ѱ" "Ps"
+    sub "Ѳ" "Th"
+    sub "Ѕ" "Dz"
+    sub "Щ" "Şt"
+    sub "Ы" "Âi"
+    sub "Ю" "Iu"
+    sub "Ѡ" "Ō"
+    sub "Ц" "Ţ"
+    sub "Ш" "Ş"
+    sub "Ъ" "Ă"
+    sub "Ь" "Ŭ"
+    sub "Ж" "J"
+    sub "И" "I"
+    sub "Й" "Ĭ"
+    sub "Ї" "Ï"
+    sub "Є" "E"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "З" "Z"
+    sub "І" "I"
+    sub "К" "C"
+    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 "Ѵ" "Y"
+    sub "Ч" "C"
+    sub "Ꙏ" "În"
+    sub "Џ" "G"
+
+    sub "іа" "ia"
+    sub "оу" "ŭ"
+    sub "ѣ" "ea"
+    sub "ѥ" "ie"
+    sub "ѧ" "ê"
+    sub "ѫ" "â"
+    sub "ѯ" "x"
+    sub "ѱ" "ps"
+    sub "ѳ" "th"
+    sub "ѕ" "dz"
+    sub "щ" "şt"
+    sub "ы" "âi"
+    sub "ю" "iu"
+    sub "ѡ" "ō"
+    sub "ц" "ţ"
+    sub "ш" "ş"
+    sub "ъ" "ă"
+    sub "ь" "ŭ"
+    sub "ж" "j"
+    sub "и" "i"
+    sub "й" "ĭ"
+    sub "ї" "ï"
+    sub "є" "e"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "з" "z"
+    sub "і" "i"
+    sub "к" "c"
+    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 "ѵ" "y"
+    sub "ч" "c"
+    sub "ꙏ" "în"
+    sub "џ" "g"
+  }
+
+}
+
+}

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

@@ -0,0 +1,199 @@
+system "BSI:rus-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:rus
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Russian column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Russian 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
+    Russian column. The Serbian and Macedonian column gives the latinica, the existing
+    Latin alphabet of Serbo-Croat. British Standard confirmed December 1998; the BSI
+    05-2000 reprint is the digitized edition.
+  }
+
+  notes {
+    note "NOTE 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 (e.g. the example rendering of Khozyaistvo shows й without the breve). This map applies the table as printed, with the diacritics."
+    note "NOTE 2. Cyrillic characters for which the transliteration is given in parentheses (і, ѣ), though no longer in official use, are sometimes found in the literature, e.g. in emigre or the older literature. This map renders them as given in the parentheses."
+    note "NOTE 4. For transliteration of Moldavian, see Table C in Section 2 (ISO/R9)."
+    note "Rows 45 (the little yus), 46 (fita) and 47 (izhitsa) carry parenthesized obsolete romanizations whose exact diacritics the scan does not resolve unambiguously; this map does not render those three characters rather than guess them."
+    note "Row 38: the table gives the choice of right double quotation mark or straight double quotation mark for ъ; this map renders the right double quotation mark (U+201D). Row 40 likewise offers two apostrophe forms for ь; this map renders the right single quotation mark (U+2019)."
+    note "Row 28+27: the character sequence тс is romanized t-s with a hyphen, distinguishing it from ц, romanized ts. Footnote to Table A: final ъ, now obsolete in Russian, is disregarded when encountered (this map deletes it, per the row 38 rendering choice above)."
+    note "Other columns of Table A (Ukrainian, Byelorussian, Bulgarian, Serbian and Macedonian) are separate maps."
+  }
+}
+
+tests {
+  # document examples (Russian items, British column)
+   "Бюллетень" ->  "Byulleten’"
+   "Известия" ->  "Izvestiya"
+   "Академии Наук" ->  "Akademii Nauk"
+   "Ленинград" ->  "Leningrad"
+   # the document's example prints Promyshlennost' (NOTE 1 permits dropping diacritics);
+  # the table specifies ȳ for ы and this map follows the table
+   "Техника Промышленность и Торговля" ->  "Tekhnika Promȳshlennost’ i Torgovlya"
+   "Москва" ->  "Moskva"
+  # table rows, upper and lower
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "G"
+   "г" ->  "g"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Е" ->  "E"
+   "е" ->  "e"
+   "Ё" ->  "Ě"
+   "ё" ->  "ě"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Й" ->  "Ĭ"
+   "й" ->  "ĭ"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "Тс" ->  "T-s"
+   "тс" ->  "t-s"
+   "У" ->  "U"
+   "у" ->  "u"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ц" ->  "Ts"
+   "ц" ->  "ts"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Shch"
+   "щ" ->  "shch"
+   "Ъ" ->  "”"
+   "ъ" ->  "”"
+   "Ы" ->  "Ȳ"
+   "ы" ->  "ȳ"
+   "Ь" ->  "’"
+   "ь" ->  "’"
+   "Э" ->  "É"
+   "э" ->  "é"
+   "Ю" ->  "Yu"
+   "ю" ->  "yu"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+   "І" ->  "I"
+   "і" ->  "i"
+   "Ѣ" ->  "Ě"
+   "ѣ" ->  "ě"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "Тс" "T-s"
+    sub "тс" "t-s"
+    sub "Щ" "Shch"
+    sub "Ё" "Ě"
+    sub "Ж" "Zh"
+    sub "Й" "Ĭ"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Ы" "Ȳ"
+    sub "Э" "É"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "Ѣ" "Ě"
+    sub "Ъ" "”"
+    sub "Ь" "’"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "І" "I"
+    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 "щ" "shch"
+    sub "тс" "t-s"
+    sub "ё" "ě"
+    sub "ж" "zh"
+    sub "й" "ĭ"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "ы" "ȳ"
+    sub "э" "é"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "ѣ" "ě"
+    sub "ъ" "”"
+    sub "ь" "’"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "з" "z"
+    sub "и" "i"
+    sub "і" "i"
+    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"
+  }
+
+}
+
+}