interscript-maps 2.0.5

data/maps/iso-prs-Arab-Latn-233-3-1999.imp

@@ -0,0 +1,352 @@
+metadata {
+  authority_id: iso
+  id: 233-3
+  language: iso-233-3:prs
+  source_script: Arab
+  destination_script: Latn
+  name: Persian language — Simplified transliteration
+  url: https://web.archive.org/web/20200920064754/http://www.freeprotocols.org/content/republished/doc.public/standards/communication/iso/iso-233/iso-233-3.pdf
+  creation_date: 1999
+  confirmation_date: 1999-01-15
+  description: |
+    This part of ISO 233 is one of a series of International
+    Standards, dealing with the conversion of systems of
+    writing. The aim of this part of ISO 233 and others in the
+    series is to provide a means for international
+    communication of written messages in a form which permits
+    the automatic transmission and reconstitution of these, by
+    men or machines. The system of conversion, in this case,
+    must be univocal and entirely reversible. This means that
+    no consideration should be given to phonetic and aesthetic
+    matters or to certain national customs: all these
+    considerations are, indeed, ignored by the machine
+    performing the function. The adoption of this part of ISO
+    233 for international communication leaves every country
+    free to adopt for its own use a national standard which may
+    be different, on condition that it is compatible with this
+    part of ISO 233. The system proposed herein should make
+    this possible and be acceptable to international use if the
+    graphisms it creates are such that they may be converted
+    automatically into the graphisms used in any strict
+    national systems. This part of ISO 233 may be used by
+    anyone who has a clear understanding of the system and is
+    certain that it can be applied without ambiguity. The
+    result obtained will not give a correct pronunciation of
+    the original text in a person’s own language, but it will
+    serve as a means of finding automatically the original
+    graphism and thus allow anyone who has knowledge of the
+    original language to pronounce it correctly. Similarly, one
+    can only pronounce correctly a text written in, for
+    example, English or Polish, if one has a knowledge of
+    English or Polish. The adoption of national standards
+    compatible with this part of ISO 233 will permit the
+    representation, in an international publication, of the
+    morphemes of each language according to the customs of the
+    country where it is spoken. It will be possible to simplify
+    this representation in order to take into account the
+    number of the character sets available on different kinds
+    of machines.
+    1-Scope:
+    This part of ISO 233 establishes a simplified
+    system for the transliteration of Persian characters into
+    Latin characters. This simplification of the stringent
+    rules established by ISO 233:1984 is especially intended to
+    facilitate the processing of bibliographic information (
+    e.g. catalogues, indices, citations, etc.)
+    2-Normative references:
+    The following normative documents contain
+    provisions which, though reference in this text, constitute
+    provisions of this part of ISO 233. For dated references,
+    subsequent amendments to, or revisions of, any of these
+    publications do not apply. However, parties to agreements
+    based on this part of ISO 233 are encouraged to investigate
+    the possibility of applying the most recent editions of the
+    normative documents indicated below. For undated
+    references, the latest edition of the normative document
+    referred to applies. Members of ISO and IEC maintain
+    registers of currently valid International StandardsISO 233-
+    2, Information and documentation — Transliteration of
+    Arabic characters into Latin characters — Part 2: Arabic
+    language — Simplified transliteration. ISO/IEC 10646-1,
+    Information Technology — Universal Multiple-Octet Coded
+    Character Set (UCS) — Part 1: Architecture and Basic
+    Multilingual Plane.
+
+  notes: |
+    TODO
+}
+
+tests {
+  test "آذَر", "âẕar"
+  test "سَم", "sam"
+  test "پُر", "por"
+  test "پِدَر", "pedar"
+  test "مَثَلاً", "mas̱alâ´´"
+  test "جزء", "jz’"
+  test "رأس", "râ’s"
+  test "سؤال", "sv’âl"
+  test "مسئلة", "msy’lh"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # word-medial or word-final form where so appearing in a word.
+    # '\u0627': '-'
+
+    # # Vowel, Diphthong and Diacritical Characters
+
+    # '\u064E': 'a'
+
+    # # Both e and i are available to romanize this short vowel,
+    # # depending on local usage and/or root language. In cases where the sound
+    # # is uncertain, i is the default romanization in BGN/PCGN standardization
+    # # procedures.
+    # '\u0650':
+    #   - 'e'
+    #   - 'i'
+
+    # # Both o and u are available to romanize this short vowel,
+    # # depending on local usage and/or root language. In cases where the sound
+    # # is uncertain, u is the default romanization in BGN/PCGN standardization
+    # # procedures.
+    # '\u064F':
+    #   - 'o'
+    #   - 'u'
+    # '\u0659': 'ê'
+
+    # # An alif with mad ( آ ) is written only in the initial position by
+    # # BGN/PCGN standardization procedures, in keeping with Persian language
+    # # family standards of use of the Arabic alphabet. The same letter written
+    # # in a medial or final position is written . . .
+    # '\u0622': 'ā'
+
+    # pending issue #442
+    # '\u0648': 'ō'
+    # '\u0648': 'ū'
+    # '\u0648': 'ow'
+    # '\u06CC': 'ī'
+
+    # # Or 'ē'. The character ی should be romanized ay or ē according to
+    # # its root language or local pronunciation. In case of uncertainty a
+    # # reference source (such as the Fairchild Aerial Surveys map series, or a
+    # # BGN/PCGN approved policy document/list of recommended spellings) should
+    # # be consulted.
+    # '\u06CC': 'ay'
+    # '\u06D0': 'ē'
+
+    # # Or 'aī'. Both the combination ay and aī are available to romanize
+    # # this character according to its root language or local pronunciation.
+    # # In cases where the sound is uncertain ay is the default romanization in
+    # # BGN/PCGN standardization procedures
+    # '\u06CC':
+    #   - 'ay'
+    #   - 'á'
+    # '\u06CD': 'êy'
+    # '\u0621': '’'
+    # '\u0674':
+    #   - '-e'
+    #   - '-ye'
+
+    # # Other Diacritical Marks and Language Conventions
+
+    # '\u0627': 'āy'
+
+    # '\u0648': 'w'
+    # '\u0626': '’'
+    # '\u06C0': ''
+    # '\u0651': ''
+
+
+    # special rules
+
+    sub space, "", after: "\u0622\u0628\u064E\u0627\u062F" # space followed by abad is removed
+    sub "\ufdf2", "Allāh" # See note 5
+
+    # pointing
+    sub "\u064e", "a" # َ fatha
+
+    sub "\u0650", any(["e", "i"])
+    sub "\u0650" + boundary, "-e" # ِ kasra
+
+    sub "\u064f", any(["o", "u"]) # ُ damma
+
+    sub "\u0652", "" # ْ sokoon
+    sub "\u0659", "ê"
+
+    # special pointed letters
+    sub "\u0639\u064e", "‘a" # عَ
+    sub "\u0639\u0650", "‘i" # عِ
+    sub "\u0639\u064f", "‘ū" # عُ
+    # handle MacOS regex difference
+    sub "\u0639\u064f\u0648", "‘ū" # عُو damma followed by و
+
+    sub "\u0650\u064a", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u06cc", "ī" # ـِي kasra followed by ي
+    sub "\u0650\u064a\u0651\u064e", "īy" # ـِيَّ
+    sub "\u0650\u064a", "iy", after: any(["\u064e", "u064f"]) # ـِي kasra followed by ي
+    sub "\u064f\u0648", "ō" # ـُو damma followed by و
+    sub "\u064e\u0627", "ā" # ـَا fatha followed by ا
+    sub "\u064e\u0649", "ay" # ـَى fatha followed by ى which is ا not ي
+    sub "\u064e\u0648\u0652", "aw" # ـَوْ
+    sub "\u064e\u0648", "ow" # ـَو
+    sub "\u064e\u064a\u0652", "ay" # ـَيْ
+    sub "\u0650\u06cc\u0651\u064e", "īy" # ـِيَّ
+    sub "\u064e\u064a", "aī" # ـَي
+    sub "\u064e\u06cc", "aī" # ـَي
+    sub "\u0649\u0670", "á" # ىٰ
+    sub "\u0674", "-e" # ٴ
+    sub "\u0654", "-e" #  ٔ
+    # - '-ye'
+
+    sub "\u0622", "â" # آ
+
+    # ta' marboota
+    sub "\u0629", "t" # ة in the middle of the sentence
+    sub "\u0629" + line_end, "h"
+    # TODO: simplify this
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "h", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+    # Tanvin
+    sub "\u064b", "´´" #  ً
+    sub "\u064c", "" #  ٌ
+    sub "\u064d", "" #  ٍ
+
+    # hamzeh
+    sub "\u0621", "’" # ء
+    sub "\u0623", "â’" # أ
+    sub "\u0624", "v’" # ؤ
+    sub "\u0626", "y’" # ئ
+
+    # punctuation
+
+    sub "\u060c", "," # vavak comma
+    sub "\u061b", ";" # nogteh vavak semi column
+    sub "\u061f", "?" # neshane-ye porsesh question mark
+
+    sub "\u0625", "" # إ
+    sub "\u0627", "â" # ا
+
+    # See note B
+    sub boundary + "\u0627\u0644", "al " # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    sub boundary + "\u0627\u0644\u062a", "at t" # الت
+    sub boundary + "\u0627\u0644\u062b", "as̄ s̄" # الث
+    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630", "az̄ z̄" # الذ
+    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632", "az z" # الز
+    sub boundary + "\u0627\u0644\u0633", "as s" # الس
+    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636", "aẕ ẕ" # الض
+    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0638", "az̧ z̧" # الظ
+    sub boundary + "\u0627\u0644\u0644", "al l" # الل
+    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+
+    # consonant characters
+
+    sub "\u0628", "b" # ب
+    sub "\u067E", "p" # پ
+    sub "\u062a", "t" # ت
+    # '\u067C': 'ṯ'  # ټ
+    sub "\u062B", "s̱" # ث
+    sub "\u062c", "j" # ج
+    sub "\u0686", "c" # ‫چ‬
+
+    # # The variant form ج is seen infrequently and does not have a
+    # # single Unicode encoding.
+    # '\u0681': 'dz' # Note 2 # ‫ځ‬
+
+    # '\u0685': 'ts' # Note 2 # ‫څ
+
+    sub "\u062d", "ḥ" # ح
+    sub "\u062e", "ḵ" # خ
+    sub "\u062f", "d" # د
+    sub "\u0689", "ḏ" # ‫ډ‬
+    sub "\u0630", "ẕ" # ذ
+    sub "\u0631", "r" # ر
+    # '\u0693' : 'ṟ'   # ړ
+    sub "\u0632", "z" # ز
+    sub "\u0698", "z" # ‫ژ‬
+    # '\u0696' : 'z͟h'  # ږ
+    sub "\u0633", "s" # س
+    # '\u069A' : 's͟h'  # ښ
+    sub "\u0634", "š" # ش
+    sub "\u0635", "ṣ" # ص
+    sub "\u0636", "ż" # ض
+    sub "\u0637", "ṭ" # ط
+    sub "\u0638", "z" # ظ
+    sub "\u0639", "‘" # ع
+    sub "\u063a", "gh" # غ
+    sub "\u0641", "f" # ف
+    sub "\u0642", "q" # ق
+    # '\u0643' : 'k'  # ك
+    sub "\u06A9", "k" # ک
+    sub "\u06AF", "g" # ‫گ‬
+    sub "\u0644", "l" # ل
+    sub "\u0645", "m" # م
+    sub "\u0646", "n" # ن
+    # '\u06BC' : 'ṉ' # ڼ
+    sub "\u0648", "v" # و
+    sub "\u0647", "h" # ه
+    sub "\u064a", "y" # ي
+    sub "\u0649", "y" # ي
+    sub "\u06D0", "ē" # ې
+    sub "\u06CD", "êy" # ‫ۍ‬
+
+    # shadda
+    sub "\u0628", "bb" # ب
+    sub "\u067E", "pp" # پ
+    sub "\u062a", "tt" # ت
+    sub "\u062B", "s̱s̱" # ث
+    sub "\u062c", "jj" # ج
+    sub "\u0686", "č̱č̱" # ‫چ‬‬
+    sub "\u062d", "ḥḥ" # ح
+    sub "\u062e", "ḵḵ" # خ
+    sub "\u062f", "dd" # د
+    sub "\u0689", "ḏḏ" # ‫ډ‬
+    sub "\u0630", "ẕẕ" # ذ
+    sub "\u0631", "rr" # ر
+    sub "\u0632", "zz" # ز
+    sub "\u0698", "zz" # ‫ژ‬
+    sub "\u0633", "ss" # س
+    sub "\u0634", "šš" # ش
+    sub "\u0635", "ṣṣ" # ص
+    sub "\u0636", "żż" # ض
+    sub "\u0637", "ṭṭ" # ط
+    sub "\u0638", "zz" # ظ
+    sub "\u0639", "‘" # ع
+    sub "\u063a", "gh" # غ
+    sub "\u0641", "ff" # ف
+    sub "\u0642", "qq" # ق
+    sub "\u06A9", "kk" # ک
+    sub "\u06AF", "gg" # ‫گ‬
+    sub "\u0644", "ll" # ل
+    sub "\u0645", "mm" # م
+    sub "\u0646", "nn" # ن
+    sub "\u0648", "vv" # و
+    sub "\u0647", "hh" # ه
+    sub "\u064a", "yy" # ي
+    sub "\u0649", "yy" # ي
+    sub "\u06D0", "ēē" # ې
+    sub "\u06CD", "êy" # ‫ۍ
+  }
+
+}

data/maps/iso-rus-Cyrl-Latn-9-1995.imp

@@ -0,0 +1,279 @@
+metadata {
+  authority_id: iso
+  id: 9-1995
+  language: iso-639-2:rus
+  source_script: Cyrl
+  destination_script: Latn
+  name: "ISO 9:1995 Information and documentation — Transliteration of Cyrillic characters into Latin characters — Slavic and non-Slavic languages"
+  url: https://www.iso.org/standard/3589.html
+  creation_date: 1995
+  description: |
+    Establishes a system for the transliteration into Latin characters of
+    Cyrillic characters constituting the alphabets of Slavic and non-Slavic
+    languages. Table 3 includes in a single sequence, listed in the
+    Cyrillic alphabetic order, the 118 single or diacritic-carrying
+    characters that appear in one or another of the considered alphabets.
+}
+
+tests {
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А => A
+    sub "Ӓ", "Ä" # Ӓ => Ä (a diaeresis)
+    sub "Ӓ̄", "Ạ̈" # Ӓ̄ => Ạ̈ (a diaeresis and dot below)
+    sub "Ӑ", "Ă" # Ӑ => Ă (a breve)
+    sub "А̄", "Ā" # А̄ => Ā (a macron)
+    sub "Ӕ", "Æ" # Ӕ => Æ (ae ligature)
+    sub "А́", "Á" # А́ => Á (a acute)
+    sub "А̊", "Å" # А̊ => Å (a ring)
+    sub "Б", "B" # Б => B
+    sub "В", "V" # В => V
+    sub "Г", "G" # Г => G
+    sub "Ѓ", "Ǵ" # Ѓ => Ǵ (g acute)
+    sub "Ғ", "Ġ" # Ғ => Ġ (g dot)
+    sub "Ҕ", "Ğ" # Ҕ => Ğ (g breve)
+    sub "Һ", "Ḥ" # Һ => Ḥ (h dot)
+    sub "Д", "D" # Д => D
+    sub "Ђ", "Đ" # Ђ => Đ (d macron)
+    sub "Е", "E" # Е => E
+    sub "Ӗ", "Ĕ" # Ӗ => Ĕ (e breve)
+    sub "Ё", "Ë" # Ё => Ë (e diaeresis)
+    sub "Є", "Ê" # Є => Ê (e circumflex)
+    sub "Ж", "Ž" # Ж => Ž (z caron)
+    sub "Җ", "Ž̧" # Җ => Ž̧ (z caron and cedilla[4])
+    sub "Ӝ", "Z̄" # Ӝ => Z̄ (z macron)
+    sub "Ӂ", "Z̆" # Ӂ => Z̆ (z breve)
+    sub "З", "Z" # З => Z
+    sub "Ӟ", "Z̈" # Ӟ => Z̈ (z diaeresis)
+    sub "Ӡ", "Ź" # Ӡ => Ź (z acute)
+    sub "Ѕ", "Ẑ" # Ѕ => Ẑ (z circumflex)
+    sub "И", "I" # И => I
+    sub "Ӣ", "Ī" # Ӣ => Ī (i macron)
+    sub "И́", "Í" # И́ => Í (i acute)
+    sub "Ӥ", "Î" # Ӥ => Î (i circumflex)
+    sub "Й", "J" # Й => J
+    sub "І", "Ì" # І => Ì (i grave)
+    sub "Ї", "Ï" # Ї => Ï (i diaeresis)
+    sub "І̄", "Ǐ" # І̄ => Ǐ (i caron (or breve))
+    sub "Ј", "J̌" # Ј => J̌ (j caron)
+    sub "Ј̵", "J́" # Ј̵ => J́ (j acute)
+    sub "К", "K" # К => K
+    sub "Ќ", "Ḱ" # Ќ => Ḱ (k acute)
+    sub "Ӄ", "Ḳ" # Ӄ => Ḳ (k dot below)
+    sub "Ҝ", "K̂" # Ҝ => K̂ (k circumflex)
+    sub "Ҡ", "Ǩ" # Ҡ => Ǩ (k caron)
+    sub "Ҟ", "K̄" # Ҟ => K̄ (k macron)
+    sub "Қ", "Ķ" # Қ => Ķ (k cedilla[4])
+    sub "К̨", "K̀" # К̨ => K̀ (k grave)
+    sub "Ԛ", "Q" # Ԛ => Q
+    sub "Л", "L" # Л => L
+    sub "Љ", "L̂" # Љ => L̂ (l circumflex)
+    sub "Ԡ", "Ļ" # Ԡ => Ļ (l cedilla[4])
+    sub "М", "M" # М => M
+    sub "Н", "N" # Н => N
+    sub "Њ", "N̂" # Њ => N̂ (n circumflex)
+    sub "Ң", "Ņ" # Ң => Ņ (n cedilla[4])
+    sub "Ӊ", "Ṇ" # Ӊ => Ṇ (n dot below)
+    sub "Ҥ", "Ṅ" # Ҥ => Ṅ (n dot)
+    sub "Ԋ", "Ǹ" # Ԋ => Ǹ (n grave)
+    sub "Ԣ", "Ń" # Ԣ => Ń (n acute)
+    sub "Ӈ", "Ň" # Ӈ => Ň (n caron)
+    sub "Н̄", "N̄" # Н̄ => N̄ (n macron)
+    sub "О", "O" # О => O
+    sub "Ӧ", "Ö" # Ӧ => Ö (o diaeresis)
+    sub "Ө", "Ô" # Ө => Ô (o circumflex)
+    sub "Ӫ", "Ő" # Ӫ => Ő (o double acute)
+    sub "Ӧ̄", "Ọ̈" # Ӧ̄ => Ọ̈ (o diaeresis and dot below)
+    sub "Ҩ", "Ò" # Ҩ => Ò (o grave)
+    sub "О́", "Ó" # О́ => Ó (o acute)
+    sub "О̄", "Ō" # О̄ => Ō (o macron)
+    sub "Œ", "Œ" # Œ => Œ (oe ligature)
+    sub "П", "P" # П => P
+    sub "Ҧ", "Ṕ" # Ҧ => Ṕ (p acute)
+    sub "Ԥ", "P̀" # Ԥ => P̀ (p grave)
+    sub "Р", "R" # Р => R
+    sub "С", "S" # С => S
+    sub "Ҫ", "Ş" # Ҫ => Ş (s cedilla[4])
+    sub "С̀", "S̀" # С̀ => S̀ (s grave)
+    sub "Т", "T" # Т => T
+    sub "Ћ", "Ć" # Ћ => Ć (c acute)
+    sub "Ԏ", "T̀" # Ԏ => T̀ (t grave)
+    sub "Т̌", "Ť" # Т̌ => Ť (t caron)
+    sub "Ҭ", "Ţ" # Ҭ => Ţ (t cedilla[4])
+    sub "У", "U" # У => U
+    sub "Ӱ", "Ü" # Ӱ => Ü (u diaeresis)
+    sub "Ӯ", "Ū" # Ӯ => Ū (u macron)
+    sub "Ў", "Ŭ" # Ў => Ŭ (u breve)
+    sub "Ӳ", "Ű" # Ӳ => Ű (u double acute)
+    sub "У́", "Ú" # У́ => Ú (u acute)
+    sub "Ӱ̄", "Ụ̈" # Ӱ̄ => Ụ̈ (u diaeresis and dot below)
+    sub "Ү", "Ù" # Ү => Ù (u grave)
+    sub "Ұ", "U̇" # Ұ => U̇ (u dot)
+    sub "Ԝ", "W" # Ԝ => W
+    sub "Ф", "F" # Ф => F
+    sub "Х", "H" # Х => H
+    sub "Ҳ", "Ḩ" # Ҳ => Ḩ (h cedilla[4])
+    sub "Ц", "C" # Ц => C
+    sub "Ҵ", "C̄" # Ҵ => C̄ (c macron)
+    sub "Џ", "D̂" # Џ => D̂ (d circumflex)
+    sub "Ч", "Č" # Ч => Č (c caron)
+    sub "Ҷ", "Ç" # Ҷ => Ç (c cedilla[4])
+    sub "Ӌ", "C̣" # Ӌ => C̣ (c dot below)
+    sub "Ӵ", "C̈" # Ӵ => C̈ (c diaeresis)
+    sub "Ҹ", "Ĉ" # Ҹ => Ĉ (c circumflex)
+    sub "Ч̀", "C̀" # Ч̀ => C̀ (c grave)
+    sub "Ҽ", "C̆" # Ҽ => C̆ (c breve)
+    sub "Ҿ", "C̨̆" # Ҿ => C̨̆ (c ogonek[4] and breve)
+    sub "Ш", "Š" # Ш => Š (s caron)
+    sub "Щ", "Ŝ" # Щ => Ŝ (s circumflex)
+    sub "Ъ", "ʺ" # Ъ => ʺ (modifier letter double prime[5])
+    sub "Ы", "Y" # Ы => Y
+    sub "Ӹ", "Ÿ" # Ӹ => Ÿ (y diaeresis)
+    sub "Ы̄", "Ȳ" # Ы̄ => Ȳ (y macron)
+    sub "Ь", "ʹ" # Ь => ʹ (modifier letter prime[5])
+    sub "Э", "È" # Э => È (e grave)
+    sub "Ә", "A̋" # Ә => A̋ (a double acute)
+    sub "Ӛ", "À" # Ӛ => À (a grave)
+    sub "Ю", "Û" # Ю => Û (u circumflex)
+    sub "Ю̄", "Û̄" # Ю̄ => Û̄ (u circumflex with macron)
+    sub "Я", "Â" # Я => Â (a circumflex)
+    sub "Ґ", "G̀" # Ґ => G̀ (g grave)
+    sub "Ѣ", "Ě" # Ѣ => Ě (e caron)
+    sub "Ѫ", "Ǎ" # Ѫ => Ǎ (a caron)
+    sub "Ѳ", "F̀" # Ѳ => F̀ (f grave)
+    sub "Ѵ", "Ỳ" # Ѵ => Ỳ (y grave)
+    sub "а", "a" # а => a
+    sub "ӓ", "ä" # ӓ => ä
+    sub "ӓ̄", "ạ̈" # ӓ̄ => ạ̈
+    sub "ӑ", "ă" # ӑ => ă
+    sub "а̄", "ā" # а̄ => ā
+    sub "ӕ", "æ" # ӕ => æ
+    sub "а́", "á" # а́ => á
+    sub "а̊", "å" # а̊ => å
+    sub "б", "b" # б => b
+    sub "в", "v" # в => v
+    sub "г", "g" # г => g
+    sub "ѓ", "ǵ" # ѓ => ǵ
+    sub "ғ", "ġ" # ғ => ġ
+    sub "ҕ", "ğ" # ҕ => ğ
+    sub "һ", "ḥ" # һ => ḥ
+    sub "д", "d" # д => d
+    sub "ђ", "đ" # ђ => đ
+    sub "е", "e" # е => e
+    sub "ӗ", "ĕ" # ӗ => ĕ
+    sub "ё", "ë" # ё => ë
+    sub "є", "ê" # є => ê
+    sub "ж", "ž" # ж => ž
+    sub "җ", "ž̧" # җ => ž̧
+    sub "ӝ", "z̄" # ӝ => z̄
+    sub "ӂ", "z̆" # ӂ => z̆
+    sub "з", "z" # з => z
+    sub "ӟ", "z̈" # ӟ => z̈
+    sub "ӡ", "ź" # ӡ => ź
+    sub "ѕ", "ẑ" # ѕ => ẑ
+    sub "и", "i" # и => i
+    sub "ӣ", "ī" # ӣ => ī
+    sub "и́", "í" # и́ => í
+    sub "ӥ", "î" # ӥ => î
+    sub "й", "j" # й => j
+    sub "і", "ì" # і => ì
+    sub "ї", "ï" # ї => ï
+    sub "і̄", "ǐ" # і̄ => ǐ
+    sub "ј", "ǰ" # ј => ǰ
+    sub "ј̵", "j́" # ј̵ => j́
+    sub "к", "k" # к => k
+    sub "ќ", "ḱ" # ќ => ḱ
+    sub "ӄ", "ḳ" # ӄ => ḳ
+    sub "ҝ", "k̂" # ҝ => k̂
+    sub "ҡ", "ǩ" # ҡ => ǩ
+    sub "ҟ", "k̄" # ҟ => k̄
+    sub "қ", "ķ" # қ => ķ
+    sub "к̨", "k̀" # к̨ => k̀
+    sub "ԛ", "q" # ԛ => q
+    sub "л", "l" # л => l
+    sub "љ", "l̂" # љ => l̂
+    sub "ԡ", "ļ" # ԡ => ļ
+    sub "м", "m" # м => m
+    sub "н", "n" # н => n
+    sub "њ", "n̂" # њ => n̂
+    sub "ң", "ņ" # ң => ņ
+    sub "ӊ", "ṇ" # ӊ => ṇ
+    sub "ҥ", "ṅ" # ҥ => ṅ
+    sub "ԋ", "ǹ" # ԋ => ǹ
+    sub "ԣ", "ń" # ԣ => ń
+    sub "ӈ", "ň" # ӈ => ň
+    sub "н̄", "n̄" # н̄ => n̄
+    sub "о", "o" # о => o
+    sub "ӧ", "ö" # ӧ => ö
+    sub "ө", "ô" # ө => ô
+    sub "ӫ", "ő" # ӫ => ő
+    sub "о̄̈", "ọ̈" # о̄̈ => ọ̈
+    sub "ҩ", "ò" # ҩ => ò
+    sub "о́", "ó" # о́ => ó
+    sub "о̄", "ō" # о̄ => ō
+    sub "œ", "œ" # œ => œ
+    sub "п", "p" # п => p
+    sub "ҧ", "ṕ" # ҧ => ṕ
+    sub "ԥ", "p̀" # ԥ => p̀
+    sub "р", "r" # р => r
+    sub "с", "s" # с => s
+    sub "ҫ", "ş" # ҫ => ş
+    sub "с̀", "s̀" # с̀ => s̀
+    sub "т", "t" # т => t
+    sub "ћ", "ć" # ћ => ć
+    sub "ԏ", "t̀" # ԏ => t̀
+    sub "т̌", "ť" # т̌ => ť
+    sub "ҭ", "ţ" # ҭ => ţ
+    sub "у", "u" # у => u
+    sub "ӱ", "ü" # ӱ => ü
+    sub "ӯ", "ū" # ӯ => ū
+    sub "ў", "ŭ" # ў => ŭ
+    sub "ӳ", "ű" # ӳ => ű
+    sub "у́", "ú" # у́ => ú
+    sub "ӱ̄", "ụ̈" # ӱ̄ => ụ̈
+    sub "ү", "ù" # ү => ù
+    sub "ұ", "u̇" # ұ => u̇
+    sub "ԝ", "w" # ԝ => w
+    sub "ф", "f" # ф => f
+    sub "х", "h" # х => h
+    sub "ҳ", "ḩ" # ҳ => ḩ
+    sub "ц", "c" # ц => c
+    sub "ҵ", "c̄" # ҵ => c̄
+    sub "џ", "d̂" # џ => d̂
+    sub "ч", "č" # ч => č
+    sub "ҷ", "ç" # ҷ => ç
+    sub "ӌ", "c̣" # ӌ => c̣
+    sub "ӵ", "c̈" # ӵ => c̈
+    sub "ҹ", "ĉ" # ҹ => ĉ
+    sub "ч̀", "c̀" # ч̀ => c̀
+    sub "ҽ", "c̆" # ҽ => c̆
+    sub "ҿ", "c̨̆" # ҿ => c̨̆
+    sub "ш", "š" # ш => š
+    sub "щ", "ŝ" # щ => ŝ
+    sub "ъ", "ʺ" # ъ => ʺ
+    sub "ы", "y" # ы => y
+    sub "ӹ", "ÿ" # ӹ => ÿ
+    sub "ы̄", "ȳ" # ы̄ => ȳ
+    sub "ь", "ʹ" # ь => ʹ
+    sub "э", "è" # э => è
+    sub "ә", "a̋" # ә => a̋
+    sub "ӛ", "à" # ӛ => à
+    sub "ю", "û" # ю => û
+    sub "ю̄", "û̄" # ю̄ => û̄
+    sub "я", "â" # я => â
+    sub "ґ", "g̀" # ґ => g̀
+    sub "ѣ", "ě" # ѣ => ě
+    sub "ѫ", "ǎ" # ѫ => ǎ
+    sub "ѳ", "f̀" # ѳ => f̀
+    sub "ѵ", "ỳ" # ѵ => ỳ
+    sub "Ӏ", "‡" # Ӏ	=> ‡
+    sub "ʼ", "`" # ʼ	=> `
+    sub "ˮ", "¨" # ˮ => ¨
+  }
+
+}
+