interscript-maps 2.0.5

data/maps/icao-bel-Cyrl-Latn-9303.imp

@@ -0,0 +1,136 @@
+metadata {
+  authority_id: icao
+  id: 9303
+  language: iso-639-2:bel
+  source_script: Cyrl
+  destination_script: Latn
+  name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Belorussian Cyrillic to Latin
+  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  creation_date: 2015
+  description: |
+    Part 3 defines specifications that are common to TD1, TD2 and TD3
+    size machine readable travel documents (MRTDs) including those
+    necessary for global interoperability using visual inspection and
+    machine readable (optical character recognition) means.
+  
+    Since only Latin-alphabet characters are allowed in the VIZ, if
+    mandatory data elements are in a national language that does not use
+    the Latin alphabet, a transcription or transliteration shall also be
+    provided.
+  
+    This document defines the transliteration mappings used to produce
+    this transcription or transliteration.
+}
+
+tests {
+  test "Бабрыковіч Аляксандр", "Babrykovich Aliaksandr"
+  test "Міховіч Марыя", "Mikhovich Maryia"
+  test "Максім", "Maksim"
+  test "Іван", "Ivan"
+  test "СВЯТЛАНА", "SVIATLANA"
+  test "Ігар", "Ihar"
+  test "Палто Алена", "Palto Alena"
+  test "Мікалай", "Mikalai"
+}
+
+# https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "'", "" # '
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "Д", "D" # Д
+    sub "Ё", "IO" # Ё
+    sub "Е", "E" # Е
+    sub "Э", "E" # Э
+    sub "Ф", "F" # Ф
+    sub "Г", "H" # Г
+    sub "И", "I" # И
+    sub "Й", "I" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "В", "V" # В
+    sub "Ы", "Y" # Ы
+    sub "З", "Z" # З
+    sub "Ч", "CH" # Ч
+    sub "Я", "IA" # Я
+    sub "Ю", "IU" # Ю
+    sub "Х", "KH" # Х
+    sub "Ш", "SH" # Ш
+    sub "Щ", "SHCH" # Щ
+    sub "Ц", "TS" # Ц
+    sub "Ж", "ZH" # Ж
+    sub "Ґ", "G" # Ґ
+    sub "Ў", "U" # Ў
+    sub "Ѫ", "U" # Ѫ
+    sub "Ђ", "D" # Ђ
+    sub "Ѕ", "DZ" # Ѕ
+    sub "Ј", "J" # Ј
+    sub "Љ", "LJ" # Љ
+    sub "Њ", "NJ" # Њ
+    sub "Һ", "C" # Һ
+    sub "Џ", "DZ" # Џ
+    sub "Є", "IE" # Є
+    sub "Ї", "I" # Ї
+    sub "Ѓ", "G" # Ѓ
+    sub "І", "I" # І
+    
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "д", "d" # д
+    sub "ё", "io" # ё
+    sub "е", "e" # e
+    sub "э", "e" # э
+    sub "ф", "f" # ф
+    sub "г", "h" # г
+    sub "и", "i" # и
+    sub "й", "i" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "" # у
+    sub "в", "v" # в
+    sub "ы", "y" # ы
+    sub "з", "z" # з
+    sub "ч", "ch" # ч
+    sub "я", "ia" # я
+    sub "ю", "i" # ю
+    sub "х", "kh" # х
+    sub "ш", "sh" # ш
+    sub "щ", "shch" # щ
+    sub "ц", "ts" # ц
+    sub "ж", "zh" # ж
+    sub "ґ", "g" # ґ
+    sub "ў", "" # ў
+    sub "ѫ", "" # ѫ
+    sub "ђ", "d" # ђ
+    sub "ѕ", "dz" # ѕ
+    sub "ј", "j" # ј
+    sub "љ", "lj" # љ
+    sub "њ", "nj" # њ
+    sub "һ", "c" # һ
+    sub "џ", "dz" # џ
+    sub "є", "ie" # є
+    sub "ї", "i" # ї
+    sub "ѓ", "g" # ѓ
+    sub "і", "i" # і
+  }
+
+}
+

data/maps/icao-bul-Cyrl-Latn-9303.imp

@@ -0,0 +1,127 @@
+metadata {
+  authority_id: icao
+  id: 9303
+  language: iso-639-2:bul
+  source_script: Cyrl
+  destination_script: Latn
+  name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Bulgarian Cyrillic to Latin
+  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  creation_date: 2015
+  description: |
+    Part 3 defines specifications that are common to TD1, TD2 and TD3
+    size machine readable travel documents (MRTDs) including those
+    necessary for global interoperability using visual inspection and
+    machine readable (optical character recognition) means.
+
+    Since only Latin-alphabet characters are allowed in the VIZ, if
+    mandatory data elements are in a national language that does not use
+    the Latin alphabet, a transcription or transliteration shall also be
+    provided.
+
+    This document defines the transliteration mappings used to produce
+    this transcription or transliteration.
+}
+
+tests {
+}
+
+# https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "'", "" # '
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "Д", "D" # Д
+    sub "Ё", "E" # Ё
+    sub "Е", "E" # Е
+    sub "Э", "E" # Э
+    sub "Ф", "F" # Ф
+    sub "Г", "G" # Г
+    sub "И", "I" # И
+    sub "Й", "I" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "В", "V" # В
+    sub "Ы", "Y" # Ы
+    sub "З", "Z" # З
+    sub "Ч", "CH" # Ч
+    sub "Я", "IA" # Я
+    sub "Ю", "IU" # Ю
+    sub "Х", "KH" # Х
+    sub "Ш", "SH" # Ш
+    sub "Щ", "SHT" # Щ
+    sub "Ц", "TS" # Ц
+    sub "Ж", "ZH" # Ж
+    sub "Ґ", "G" # Ґ
+    sub "Ў", "U" # Ў
+    sub "Ѫ", "U" # Ѫ
+    sub "Ђ", "D" # Ђ
+    sub "Ѕ", "DZ" # Ѕ
+    sub "Ј", "J" # Ј
+    sub "Љ", "LJ" # Љ
+    sub "Њ", "NJ" # Њ
+    sub "Һ", "C" # Һ
+    sub "Џ", "DZ" # Џ
+    sub "Є", "IE" # Є
+    sub "Ї", "I" # Ї
+    sub "Ѓ", "G" # Ѓ
+    sub "'", "" # '
+
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "д", "d" # д
+    sub "ё", "e" # ё
+    sub "е", "e" # e
+    sub "э", "e" # э
+    sub "ф", "f" # ф
+    sub "г", "g" # г
+    sub "и", "i" # и
+    sub "й", "i" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "" # у
+    sub "в", "v" # в
+    sub "ы", "y" # ы
+    sub "з", "z" # з
+    sub "ч", "ch" # ч
+    sub "я", "ia" # я
+    sub "ю", "i" # ю
+    sub "х", "kh" # х
+    sub "ш", "sh" # ш
+    sub "щ", "sht" # щ
+    sub "ц", "ts" # ц
+    sub "ж", "zh" # ж
+    sub "ґ", "g" # ґ
+    sub "ў", "" # ў
+    sub "ѫ", "" # ѫ
+    sub "ђ", "d" # ђ
+    sub "ѕ", "dz" # ѕ
+    sub "ј", "j" # ј
+    sub "љ", "lj" # љ
+    sub "њ", "nj" # њ
+    sub "һ", "c" # һ
+    sub "џ", "dz" # џ
+    sub "є", "ie" # є
+    sub "ї", "i" # ї
+    sub "ѓ", "g" # ѓ
+  }
+
+}
+

data/maps/icao-fas-Arab-Latn-9303.imp

@@ -0,0 +1,112 @@
+metadata {
+  authority_id: icao
+  id: 9303
+  language: iso-639-2:fas
+  source_script: Arab
+  destination_script: Latn
+  name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Persian Arabic to Latin
+  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  creation_date: 2015
+  description: |
+    Part 3 defines specifications that are common to TD1, TD2 and TD3
+    size machine readable travel documents (MRTDs) including those
+    necessary for global interoperability using visual inspection and
+    machine readable (optical character recognition) means.
+
+    Since only Latin-alphabet characters are allowed in the VIZ, if
+    mandatory data elements are in a national language that does not use
+    the Latin alphabet, a transcription or transliteration shall also be
+    provided.
+
+    This document defines the transliteration mappings used to produce
+    this transcription or transliteration.
+}
+
+tests {
+}
+
+# https://www.icao.int/publications/Documents/9303_p3_cons_en.pdf
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    sub "'", "" # '
+    sub "ء", "XE" # ء
+    sub "آ", "XAA" # آ
+    sub "أ", "XAE" # أ
+    sub "ؤ", "U" # ؤ
+    sub "إ", "I" # إ
+    sub "ئ", "XI" # ئ
+    sub "ا", "A" # ا
+    sub "ب", "B" # ب
+    sub "ة", "P" # ة
+    sub "ت", "T" # ت
+    sub "ث", "XTH" # ث
+    sub "ج", "J" # ج
+    sub "ح", "XH" # ح
+    sub "خ", "XKH" # خ
+    sub "د", "D" # د
+    sub "ذ", "XDH" # ذ
+    sub "ر", "R" # ر
+    sub "ز", "Z" # ز
+    sub "س", "S" # س
+    sub "ش", "XSH" # ش
+    sub "ص", "XSS" # ص
+    sub "ض", "XDZ" # ض
+    sub "ط", "XTT" # ط
+    sub "ظ", "XZZ" # ظ
+    sub "ع", "E" # ع
+    sub "غ", "G" # غ
+    sub "ف", "F" # ف
+    sub "ق", "Q" # ق
+    sub "ك", "K" # ك
+    sub "ل", "L" # ل
+    sub "م", "M" # م
+    sub "ن", "N" # ن
+    sub "ه", "H" # ه
+    sub "و", "W" # و
+    sub "ى", "XAY" # ى
+    sub "ي", "Y" # ي
+    sub "ً", "F" # ً
+    sub "ٌ", "N" # ٌ
+    sub "ٍ", "K" # ٍ
+    sub "َ", "A" # َ
+    sub "ُ", "U" # ُ
+    sub "ِ", "I" # ِ
+    sub "ْ", "O" # ْ
+    sub "ٰ", "" # '
+    sub "ٱ", "XXA" # ٱ
+    sub "ٹ", "XXT" # ٹ
+    sub "ټ", "XRT" # ټ
+    sub "پ", "P" # پ
+    sub "ځ", "XKE" # ځ
+    sub "څ", "XXH" # څ
+    sub "چ", "XC" # چ
+    sub "ڈ", "XXD" # ڈ
+    sub "ډ", "XDR" # ډ
+    sub "ڑ", "XXR" # ڑ
+    sub "ړ", "XRR" # ړ
+    sub "ږ", "XRX" # ږ
+    sub "ژ", "XJ" # ژ
+    sub "ښ", "XXS" # ښ
+    sub "ک", "XKK" # ک
+    sub "ګ", "XXK" # ګ
+    sub "ڭ", "XNG" # ڭ
+    sub "گ", "XGG" # گ
+    sub "ں", "XNN" # ں
+    sub "ڼ", "XXN" # ڼ
+    sub "ھ", "XDO" # ھ
+    sub "ۀ", "XYH" # ۀ
+    sub "ہ", "XXG" # ہ
+    sub "ۂ", "XGE" # ۂ
+    sub "ۃ", "XTG" # ۃ
+    sub "ی", "XYA" # ی
+    sub "ۍ", "XXY" # ۍ
+    sub "ې", "Y" # ې
+    sub "ے", "XYB" # ے
+    sub "ۓ", "XBE" # ۓ
+  }
+
+}
+

data/maps/icao-heb-Hebr-Latn-9303.imp

@@ -0,0 +1,160 @@
+metadata {
+  authority_id: icao
+  id: 9303
+  language: iso-639-2:heb
+  source_script: Hebr
+  destination_script: Latn
+  name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Hebrew to Latin
+  url: https://www.icao.int/publications/pages/publication.aspx?docnum=9303
+  creation_date: 2015
+  description: |
+    Part 3 defines specifications that are common to TD1, TD2 and TD3
+    size machine readable travel documents (MRTDs) including those
+    necessary for global interoperability using visual inspection and
+    machine readable (optical character recognition) means.
+
+    Since only Latin-alphabet characters are allowed in the VIZ, if
+    mandatory data elements are in a national language that does not use
+    the Latin alphabet, a transcription or transliteration shall also be
+    provided.
+
+    This document defines the transliteration mappings used to produce
+    this transcription or transliteration.
+}
+
+tests {
+}
+
+# https://en.wikipedia.org/wiki/Romanization_of_Hebrew
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "'", "" # '
+
+    # Consonants
+    sub "א", "" # א
+    sub "ב", "V" # ב
+    sub "בּ", "B" # בּ
+    sub "בּ", "B" # בּ
+    sub "ג", "G" # ג
+    sub "גּ", "G" # גּ
+    sub "גּ", "G" # גּ‬‬
+    sub "ג׳", "J" # ג׳
+    sub "ד", "D" # ד
+    sub "דּ", "D" # דּ
+    sub "דּ", "D" # דּ
+    sub "ד׳", "DH" # ד׳
+    sub "ה", "H" # ה
+    sub "הּ", "H" # הּ
+    sub "הּ", "H" # הּ
+    sub "ו", "V" # ו‬
+    sub "ו‬", "V" # ו‬
+    sub "וּ", "V" # וּ
+    # "\uFB35":             "V"  # וּ  # To vowels "U"
+    sub "ז", "Z" # ז
+    sub "זּ", "Z" # זּ
+    sub "זּ", "Z" # זּ‬
+    sub "ז׳", "ZH" # ז׳
+    sub "ח", "CH" # ח
+    sub "ט", "T" # ט
+    sub "טּ", "T" # טּ
+    sub "טּ", "T" # טּ
+    sub "י", "Y" # י
+    sub "יּ", "Y" # יּ
+    sub "יּ‬", "Y" # יּ‬
+    sub "יּ", "Y" # יּ‬
+    sub "כ", "CH" # כ
+    sub "כּ", "CH" # כּ
+    sub "כּ‬", "CH" # כּ
+    sub "כּ", "C" # כּ
+    sub "ך", "CH" # ך
+    sub "ךּ", "CH" # ךּ
+    sub "ךּ‬", "CH" # ךּ‬
+    sub "ךּ", "CH" # ךּ
+    sub "ל", "L" # ל‬
+    sub "לּ", "L" # לּ
+    sub "לּ", "L" # לּ
+    sub "ם", "M" # ם
+    sub "מ", "M" # מ‬
+    sub "מּ", "M" # מּ
+    sub "מּ", "M" # מּ‬
+    sub "ן", "N" # ן
+    sub "נ", "N" # נ
+    sub "נּ", "N" # נּ
+    sub "נּ", "N" # נּ
+    sub "ס", "S" # ס
+    sub "סּ", "S" # סּ
+    sub "סּ", "S" # סּ
+    sub "ע", "" # ע
+    sub "ף", "F" # ף
+    sub "ףּ", "P" # Possible problem u05BC # ףּ
+    sub "ףּ", "P" # ףּ
+    sub "פ", "F" # פ‬
+    sub "פּ", "P" # פּ
+    sub "פּ", "P" # פּ
+    sub "ץ", "TZ" # ץ
+    sub "ץ׳", "TSH" # Possible problem u05F3  # ץ׳
+    sub "צ", "TZ" # צ‬
+    sub "צּ", "TZ" # צּ
+    sub "צּ", "TZ" # צּ‬
+    sub "צ׳", "TSH" # Possible problem u05F3  # צ׳
+    sub "ק", "Q" # ק
+    sub "קּ", "Q" # קּ
+    sub "קּ", "Q" # קּ‬
+    sub "ר", "R" # ר
+    sub "רּ", "R" # רּ
+    sub "רּ", "R" # רּ
+    sub "ש", "S" # ש
+    sub "שּ", "S" # שּ
+    sub "שּ", "S" # שּ‬
+    sub "שׂ‬", "S" # שׂ
+    sub "שׂ", "S" # שׂ
+    sub "שׁ", "SH" # שׁ
+    sub "שׁ", "SH" # שׁ
+    sub "שּׂ‬", "S" # שּׂ‬
+    sub "שּׂ", "S" # שּׂ
+    sub "ת", "T" # ת
+    sub "תּ", "T" # תּ
+    sub "תּ", "T" # תּ
+    sub "ת׳", "T" # ת׳
+
+    # Niqqud vowels
+    sub "ְ", "E" # ( ְ‬ )
+    sub "ֱ", "E" # ( ֱ )
+    sub "ֲ", "A" # ( ֲ )
+    sub "ֳ", "O" # ( ֲ )
+    sub "ִ", "I" # ( ִ )
+    sub "ֵ", "E" # ( ֵ )
+    sub "ֶ", "E" # ( ֶ )
+    sub "ַ", "A" # ( ַ )
+    sub "ָ", "O" # ( ָ ) # It could be "A" too
+    sub "ֹ", "O" # ( ֹ )
+    sub "ֻ", "U" # ( ֻ )
+    sub "וּ", "U" # ( וּ )
+    sub "וּ", "U" # ( וּ )
+
+    # Diphthongs
+    sub "ֵי", "EI" # ( ֵי )
+    sub "ֶי", "EI" # ( ֶי )
+    sub "ַי", "AI" # ( ַי )
+    sub "ַיְ", "AI" # ( ַיְ )
+    sub "ַיְ‬", "AI" # ( ַיְ‬ )
+    sub "ָי", "AI" # ( ָי )
+    sub "ָי‬", "AI" # ( ָי‬ )
+    sub "ָיְ", "AI" # ( ָיְ )
+    sub "ָיְ‬", "AI" # ( ָיְ‬ )
+    sub "ֹי", "OI" # ( ֹי )
+    sub "ֹיְ", "OI" # ( ֹיְ )
+    sub "ֹיְ‬", "OI" # ( ֹיְ‬ )
+    sub "ֻי", "UI" # ( ֻי )
+    sub "ֻיְ", "UI" # ( ֻיְ )
+    sub "ֻיְ‬", "UI" # ( ֻיְ‬ )
+    sub "וּי", "UI" # ( וּי )
+    sub "וּיְ", "UI" # ( וּיְ )
+    sub "וּיְ‬", "UI" # ( וּיְ‬ )
+  }
+
+}
+