interscript-maps 2.5.2 → 3.0.0

data/maps/bgnpcgn-udm-Cyrl-Latn-2011.isc

@@ -0,0 +1,225 @@
+system "BGN-PCGN:udm-Cyrl:Latn:2011" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2011
+  language iso-639-2:udm
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Udmurt (2011)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2011
+  confirmation_date 2017-11
+  description {
+    The BGN/PCGN system for Udmurt is designed for use in romanizing names written in the
+    Udmurt Cyrillic alphabet. Udmurt (sometimes known as Votyak) is a member of the Permian
+    branch of the Finno-Ugric languages and is an official language alongside Russian in the
+    Russian Federation's republic of Udmurtiya; it has existed in written form since the late
+    18th century, and first appeared in its present Cyrillic orthography in 1905.
+  }
+
+  notes {
+    note "Е should be romanized ye word-initially, after a vowel, after Й, Ъ, Ь, and after the palatalizing consonants Д, З, Л, Н, С and Т. It should be romanized e elsewhere."
+    note "In order to retain reversibility, where two consonant characters appear together and the resulting romanization is equivalent to a Roman-script digraph occurring in the system (i.e. gh, zh, tl, sh or ts), a medial dot may be employed between the Roman-script consonants in order to distinguish these from the Roman-script digraphs."
+    note "The character ё is always romanized yo, independently of position."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:"
+    note "All apostrophes appearing in romanization are U+2019"
+    note "Ï (U+00CF)  ï (U+00EF)  Ö (U+00D6)  ö (U+00F6)"
+    note "The Romanization columns show only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+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"
+   "Е" ->  "Ye"
+   "е" ->  "ye"
+   "Ё" ->  "Yo"
+   "ё" ->  "yo"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "Ӝ" ->  "Dzh"
+   "ӝ" ->  "dzh"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "Ӟ" ->  "J"
+   "ӟ" ->  "j"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Ӥ" ->  "Ï"
+   "ӥ" ->  "ï"
+   "Й" ->  "Y"
+   "й" ->  "y"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "Ӧ" ->  "Ö"
+   "ӧ" ->  "ö"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "У" ->  "U"
+   "у" ->  "u"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ц" ->  "Ts"
+   "ц" ->  "ts"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ӵ" ->  "Tsh"
+   "ӵ" ->  "tsh"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Shch"
+   "щ" ->  "shch"
+   "Ъ" ->  "”"
+   "ъ" ->  "”"
+   "Ы" ->  "Y"
+   "ы" ->  "y"
+   "Ь" ->  "’"
+   "ь" ->  "’"
+   "Э" ->  "E"
+   "э" ->  "e"
+   "Ю" ->  "Yu"
+   "ю" ->  "yu"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+  # note 1: ye after vowels, й ъ ь, and д з л н с т; e elsewhere
+   "бе" ->  "be"
+   "де" ->  "dye"
+   "йе" ->  "yye"
+   "ъе" ->  "”ye"
+   "ӧе" ->  "öye"
+   "ое" ->  "oye"
+}
+
+stage main {
+
+  # RULES
+  # note 1: Е word-initially, after a vowel, after й ъ ь, and after д з л н с т
+  sub {
+    from boundary + "Е"
+    to "Ye"
+  }
+  sub {
+    from boundary + "е"
+    to "ye"
+  }
+  sub {
+    from "Е"
+    to "Ye"
+    before any("АаЕеЁёИиОоУуЫыЭэЮюЯяӦӧЙйЪъЬьДдЗзЛлНнСсТт")
+  }
+  sub {
+    from "е"
+    to "ye"
+    before any("АаЕеЁёИиОоУуЫыЭэЮюЯяӦӧЙйЪъЬьДдЗзЛлНнСсТт")
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "Ӝ" "Dzh"
+    sub "Ӵ" "Tsh"
+    sub "Ӟ" "J"
+    sub "Ӧ" "Ö"
+    sub "Ӥ" "Ï"
+    sub "Щ" "Shch"
+    sub "Ъ" "”"
+    sub "Ы" "Y"
+    sub "Ь" "’"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ё" "Yo"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Й" "Y"
+    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 "Э" "E"
+
+    sub "ӝ" "dzh"
+    sub "ӵ" "tsh"
+    sub "ӟ" "j"
+    sub "ӧ" "ö"
+    sub "ӥ" "ï"
+    sub "щ" "shch"
+    sub "ъ" "”"
+    sub "ы" "y"
+    sub "ь" "’"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "yo"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "y"
+    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 "э" "e"
+  }
+
+}
+
+}

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

@@ -0,0 +1,148 @@
+system "BSI:bel-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:bel
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Byelorussian (White R.) column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Byelorussian (White R.) 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 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."
+    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 {
+   "Мінск" ->  "Minsk"
+   "Ў" ->  "W"
+   "ў" ->  "w"
+   "Ё" ->  "Ě"
+   "ё" ->  "ě"
+   "Ы" ->  "Ȳ"
+   "ы" ->  "ȳ"
+   "Ъ" ->  "”"
+   "Ь" ->  "’"
+   "Ѣ" ->  "Ě"
+   "ѣ" ->  "ě"
+   "Ґ" ->  "G"
+   "ґ" ->  "g"
+   "а" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "h"
+   "д" ->  "d"
+   "е" ->  "e"
+   "ж" ->  "zh"
+   "з" ->  "z"
+   "і" ->  "i"
+   "й" ->  "ĭ"
+   "к" ->  "k"
+   "л" ->  "l"
+   "м" ->  "m"
+   "н" ->  "n"
+   "о" ->  "o"
+   "п" ->  "p"
+   "р" ->  "r"
+   "с" ->  "s"
+   "т" ->  "t"
+   "у" ->  "u"
+   "ф" ->  "f"
+   "х" ->  "kh"
+   "ц" ->  "ts"
+   "ч" ->  "ch"
+   "ш" ->  "sh"
+
+}
+
+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 "Ё" "Ě"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "І" "I"
+    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 "Ў" "W"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Ъ" "”"
+    sub "Ы" "Ȳ"
+    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 "ё" "ě"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "і" "i"
+    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 "ў" "w"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+    sub "ъ" "”"
+    sub "ы" "ȳ"
+    sub "ь" "’"
+    sub "ѣ" "ě"
+    sub "ю" "yu"
+    sub "я" "ya"
+  }
+
+}
+
+}

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

@@ -0,0 +1,137 @@
+system "BSI:bul-Cyrl:Latn:1958" {
+
+metadata {
+  authority_id bsi
+  id 1958
+  language iso-639-2:bul
+  source_script Cyrl
+  destination_script Latn
+  name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Bulgarian column (the British system)"
+  url https://www.bsigroup.com
+  creation_date 1958
+  confirmation_date 2000-05
+  description {    BS 2979:1958, Table A, Bulgarian 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 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. In the Bulgarian column the hard sign is a vowel and this map renders it with the breve (u-breve), per row 38."
+  }
+}
+
+tests {
+   "София" ->  "Sofiya"
+   "Съюз" ->  "Sŭyuz"
+   "Български" ->  "Bŭlgarski"
+   "Щ" ->  "Sht"
+   "щ" ->  "sht"
+   "Ъ" ->  "Ŭ"
+   "ъ" ->  "ŭ"
+   "Ѣ" ->  "Ě"
+   "ѣ" ->  "ě"
+   "а" ->  "a"
+   "б" ->  "b"
+   "в" ->  "v"
+   "г" ->  "g"
+   "д" ->  "d"
+   "е" ->  "e"
+   "ж" ->  "zh"
+   "з" ->  "z"
+   "и" ->  "i"
+   "й" ->  "ĭ"
+   "к" ->  "k"
+   "л" ->  "l"
+   "м" ->  "m"
+   "н" ->  "n"
+   "о" ->  "o"
+   "п" ->  "p"
+   "р" ->  "r"
+   "с" ->  "s"
+   "т" ->  "t"
+   "у" ->  "u"
+   "ф" ->  "f"
+   "х" ->  "kh"
+   "ц" ->  "ts"
+   "ч" ->  "ch"
+   "ш" ->  "sh"
+
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "Тс" "T-s"
+    sub "тс" "t-s"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    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" "Sht"
+    sub "Ъ" "Ŭ"
+    sub "Ь" "’"
+    sub "Ѣ" "Ě"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    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" "sht"
+    sub "ъ" "ŭ"
+    sub "ь" "’"
+    sub "ѣ" "ě"
+    sub "ю" "yu"
+    sub "я" "ya"
+  }
+
+}
+
+}