interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-arm-Armn-Latn-1981.isc

@@ -0,0 +1,132 @@
+system "BGN-PCGN:arm-Armn:Latn:1981" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1981
+  language iso-639-2:arm
+  source_script Armn
+  destination_script Latn
+  name Romanization of Armenian (1981)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/810208/ROMANIZATION_OF_ARMENIAN.pdf
+  creation_date 1981
+  confirmation_date 2019-06
+  description {    The BGN/PCGN system for Armenian was designed for use in romanizing
+    names written in the Armenian alphabet. The Roman letters and letter
+    combinations shown as equivalents to the Armenian characters reflect
+    the eastern variety of Armenian, i.e. the language spoken in the
+    Republic of Armenia.
+  }
+
+  notes {
+    note "The character ե should be romanized ye initially and after the vowel characters ա, ե, է, ը, ի, ո, ու and օ. In all other instances, it should be romanized e."
+    note "The character ո should be romanized vo initially except in the word ով, which should be roman- ized ov. In all other instances, it should be romanized o."
+    note "In Soviet-era sources this upper-case digraph character is found as Եի (Unicode encoding 0535+056B)."
+    note "This lower-case character may be seen either in digraph form as եւ (Unicode encoding 0565+0582) or in single character form as եւ (Unicode encoding 0587)."
+    note "The characters ԵՎ , եւ and եւ should be romanized yev initially, in isolation, and after the vowel characters ա, ե, է, ը, ի, ո, ու, and օ. In all other instances these characters should be romanized ev."
+    note "All apostrophes appearing in Armenian romanization are encoded Unicode 2019."
+    note "The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+  # UN card tests
+   "Հայաստան" ->  "Hayastan"
+   "Երևան" ->  "Yerevan"
+}
+
+# This map has been partially converted by the bin/maps_v1_to_v2 script
+# The section below requires human attention. Remember to remove this
+# comment and move the converted map to 'maps/' directory. Please also
+# take note that the maps-staging directory will be cleaned up whenever
+# you run the bin/maps_v1_to_v2 script. You should particularly be
+# concerned about any regular expressions found in this file and about
+# advanced expressions in parallel {} parts, and also about the order
+# of particular parts of the stage.
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0531" "A"
+    sub "\u0532" "B"
+    sub "\u0533" "G"
+    sub "\u0534" "D"
+    sub "\u0535" "Ye"
+    sub "\u0536" "Z"
+    sub "\u0537" "E"
+    sub "\u0538" "Y"
+    sub "\u0539" "T\u2019"
+    sub "\u053a" "Zh"
+    sub "\u053b" "I"
+    sub "\u053c" "L"
+    sub "\u053d" "Kh"
+    sub "\u053e" "Ts"
+    sub "\u053f" "K"
+    sub "\u0540" "H"
+    sub "\u0541" "Dz"
+    sub "\u0542" "Gh"
+    sub "\u0543" "Ch"
+    sub "\u0544" "M"
+    sub "\u0545" "Y"
+    sub "\u0546" "N"
+    sub "\u0547" "Sh"
+    sub "\u0548" "O"
+    sub "\u0549" "u'Ch\u2019'"
+    sub "\u054a" "P"
+    sub "\u054b" "J"
+    sub "\u054c" "Rr"
+    sub "\u054d" "S"
+    sub "\u054e" "V"
+    sub "\u054f" "T"
+    sub "\u0550" "R"
+    sub "\u0551" "Ts\u2019"
+    sub "\u0548\u0552" "U"
+    sub "\u0548\u0582" "U"
+    sub "\u0553" "P\u2019"
+    sub "\u0554" "K\u2019"
+    sub "\u0555" "O"
+    sub "\u0556" "F"
+    sub "\u0561" "a"
+    sub "\u0562" "b"
+    sub "\u0563" "g"
+    sub "\u0564" "d"
+    sub "\u0565" "e"
+    sub "\u0566" "z"
+    sub "\u0567" "e"
+    sub "\u0568" "y"
+    sub "\u0569" "u't\u2019'"
+    sub "\u056a" "zh"
+    sub "\u056b" "i"
+    sub "\u056c" "l"
+    sub "\u056d" "kh"
+    sub "\u056e" "ts"
+    sub "\u056f" "k"
+    sub "\u0570" "h"
+    sub "\u0571" "dz"
+    sub "\u0572" "gh"
+    sub "\u0573" "ch"
+    sub "\u0574" "m"
+    sub "\u0575" "y"
+    sub "\u0576" "n"
+    sub "\u0577" "sh"
+    sub "\u0578" "o"
+    sub "\u0579" "ch\u2019"
+    sub "\u057a" "p"
+    sub "\u057b" "j"
+    sub "\u057c" "rr"
+    sub "\u057d" "s"
+    sub "\u057e" "v"
+    sub "\u057f" "t"
+    sub "\u0580" "r"
+    sub "\u0581" "ts\u2019"
+    sub "\u0578\u0582" "u"
+    sub "\u0583" "p\u2019"
+    sub "\u0584" "k\u2019"
+    sub "\u0585" "o"
+    sub "\u0586" "f"
+    sub "\u0587" "ev"
+  }
+
+}
+
+}

data/maps/bgnpcgn-aze-Cyrl-Latn-1993.isc

@@ -0,0 +1,107 @@
+system "BGN-PCGN:aze-Cyrl:Latn:1993" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1993
+  language iso-639-2:aze
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Azerbaijani (Cyrillic-Roman) (1993 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816656/TABLE_OF_CORRESPONDENCES_FOR_AZERBAIJANI.pdf
+  creation_date 1993
+  confirmation_date 2019-06
+  description {      , also known as Azeri, is the official language of the Republic of Azerbaijan. In 1991, the Azerbaijani government adopted the Roman alphabet to replace the existing Cyrillic alphabet. The presentation below provides a table of correspondences between the former Cyrillic alphabet and the current Roman alphabet. When Azerbaijani Roman-alphabet spellings are not available, this table can be used to convert Azerbaijani Cyrillic spellings.
+  }
+
+  notes {
+
+    note "The special letter Ə, ə known as schwa, should be reproduced in that form whenever encountered. The characters Ə (Unicode 04D8) and ə (Unicode 04D9) should be used for schwa when writing in the Cyrillic script, but characters Ə (Unicode 018F) and ə (Unicode 0259) should be used when writing in the Roman alphabet. In those instances when it cannot be reproduced, however, the letter Ä ä may be substituted for it (see below)."
+
+    note "The obsolete characters й, э, ю, and я should be romanized ẏ, ė, yu., and ya."
+
+    note "Unicode values are shown with the uppercase Cyrillic character first, followed by the lowercase character. It is not known whether there exists an uppercase ‘J’ specific to the Cyrillic character set."
+
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n      Ğ (U+011E), ğ (U+011F)\n      Ə (U+018F), ə (U+0259)\n      İ (U+0130), ı (U+0131)\n      Ö (U+00D6), ö (U+00F6)\n      Ü (U+00DC), ü (U+00FC)\n      Ç (U+00C7), ç (U+00E7)\n      Ş (U+015E), ş (U+015F)"
+
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "Азәрбајҹан әлифбасы" ->  "Azərbaycan əlifbası"
+   "Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад бәрабәр доғулурлар.\nОнларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар." ->  "Bütün insanlar ləyaqət və hüquqlarına görə azad bərabər doğulurlar.\nOnların şüurları və vicdanları var və bir-birlərinə münasibətdə qardaşlıq ruhunda davranmalıdırlar."
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "Q"
+    sub "Ғ" "Ğ"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ә" "Ə"
+    sub "Ж" "J"
+    sub "З" "Z"
+    sub "И" "İ"
+    sub "Ы" "I"
+    sub "Ј" "Y"
+    sub "К" "K"
+    sub "Ҝ" "G"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "Ө" "Ö"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ү" "Ü"
+    sub "Ф" "F"
+    sub "Х" "X"
+    sub "Һ" "H"
+    sub "Ч" "Ç"
+    sub "Ҹ" "C"
+    sub "Ш" "Ş"
+
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "q"
+    sub "ғ" "ğ"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ә" "ə"
+    sub "ж" "j"
+    sub "з" "z"
+    sub "и" "i"
+    sub "ы" "ı"
+    sub "ј" "y"
+    sub "к" "k"
+    sub "ҝ" "g"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "ө" "ö"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ү" "ü"
+    sub "ф" "f"
+    sub "х" "x"
+    sub "һ" "h"
+    sub "ч" "ç"
+    sub "ҹ" "c"
+    sub "ш" "ş"
+  }
+
+}
+}

data/maps/bgnpcgn-bak-Cyrl-Latn-2007.isc

@@ -0,0 +1,191 @@
+system "BGN-PCGN:bak-Cyrl:Latn:2007" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2007
+  language iso-639-2:bak
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Bashkir (Cyrillic-Roman) (2007 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/829203/TABLE_OF_CORRESPONDENCES__FOR_BASHKIR.pdf
+  creation_date 2007
+  confirmation_date 2019
+  description {    Bashkir is an official language within Respublika Bashkortostan, one of the
+    republics of the Russian Federation. It will normally be encountered in Cyrillic script, in
+    which case it should be romanized by means of the Cyrillic-Roman table of
+    correspondences given below
+  }
+
+  notes {
+    note "The letter w is used word initially and before a vowel."
+    note "The letter sequence ye is used word initially and before a vowel."
+    note "The letter w is used between or after vowels."
+    note "The letter w is used after e, u, ö and ə."
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding,\n      in addition to the unmodified letters of the basic Roman script is:\n        Ğ (U+011E) ğ (U+011F)\n        Ź (U+0179) ź (U+017A)\n        Ë (U+00CB) ë (U+00EB)\n        Ñ (U+00D1) ñ (U+00F1)\n        Ö (U+00D6) ö (U+00F6)\n        Ś (U+015A) ś (U+015B)\n        Ü (U+00DC) ü (U+00FC)\n        Ç (U+00C7) ç (U+00E7)\n        Ş (U+015E) ş (U+015F)\n        Ə (U+018F) ə (U+0259)"
+    note "      The Roman-script columns show only lowercase forms but, when applying the table,\n      uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+  # adopted http://www.eki.ee/knab/lat/kblba.pdf
+   "Васйылға" ->  "Wasyılğa"
+   "Еҙем" ->  "Yeźem"
+   "Раевка" ->  "Raevka"
+   "Сәйетҡол" ->  "Səyetqol"
+   "Ауырғазы" ->  "Awırğazı"
+   "Бурһыҡтау" ->  "Burhıqtaw"
+   "Мәләүез" ->  "Mələwez"
+   "Ҡыҙылъяр" ->  "Qıźılyar"
+  # adopted https://en.wikipedia.org/wiki/Bashkir_language#Grammar
+   "кемдең" ->  "kemdeñ"
+   "кем" ->  "kem"
+   "был" ->  "bıl"
+   "ошо" ->  "oşo"
+   "быларҙың" ->  "bılarźıñ"
+   "һеҙҙән" ->  "heźźən"
+   "һин" ->  "hin"
+   "һеҙҙең" ->  "heźźeñ"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  sub {
+    from boundary + "\u0412"
+    to "W"
+    after any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+  }
+  sub {
+    from boundary + "\u0432"
+    to "w"
+    after any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+  }
+  # note[2]
+  sub {
+    from boundary + "\u0415"
+    to "Ye"
+  }
+  sub {
+    from boundary + "\u0435"
+    to "ye"
+  }
+  sub {
+    from "\u0415"
+    to "Ye"
+    before any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+    after boundary
+  }
+  sub {
+    from "\u0435"
+    to "ye"
+    before any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+    after boundary
+  }
+
+  # note[3] # note[4]
+  sub {
+    from any("\u0423\u04AE")
+    to "W"
+    before any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+  }
+  sub {
+    from any("\u0443\u04AF")
+    to "w"
+    before any("АаЕеЁёИиОоӨөУуҮЫыЭэӘәЮюЯя")
+  }
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0492" "Ğ"
+    sub "\u0414" "D"
+    sub "\u0498" "Ź"
+    sub "\u0415" "E"
+    sub "\u0401" "Ë"
+    sub "\u0416" "J"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u04A0" "Q"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u04A2" "Ñ"
+    sub "\u041E" "O"
+    sub "\u04E8" "Ö"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u04AA" "Ś"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "Ü"
+    sub "\u0424" "F"
+    sub "\u0425" "X"
+    sub "\u04BA" "H"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ç"
+    sub "\u0428" "Ş"
+    sub "\u0429" "ŞÇ"
+    sub "\u042A" ""
+    sub "\u042B" "I"
+    sub "\u042C" ""
+    sub "\u042D" "E"
+    sub "\u04D8" "Ə"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0493" "ğ"
+    sub "\u0434" "d"
+    sub "\u0499" "ź"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "j"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u04A1" "q"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u04A3" "ñ"
+    sub "\u043E" "o"
+    sub "\u04E9" "ö"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u04AB" "ś"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "ү" "ü"
+    sub "\u0444" "f"
+    sub "\u0445" "x"
+    sub "\u04BB" "h"
+    sub "\u0446" "ts"
+    sub "\u0447" "ç"
+    sub "\u0448" "ş"
+    sub "\u0449" "şç"
+    sub "\u044A" ""
+    sub "\u044B" "ı"
+    sub "\u044C" ""
+    sub "\u044D" "e"
+    sub "\u04D9" "ə"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+
+}