interscript-maps 2.4.3 → 2.5.0

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

@@ -0,0 +1,469 @@
+system "ISO:prs-Arab:Latn:233-3-1999" {
+
+metadata {
+  authority_id iso
+  id 233-3-1999
+  language iso-639-3:prs
+  source_script Arab
+  destination_script Latn
+  name "ISO 223-3:1999 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 {
+    note "    TODO"
+  }
+}
+
+tests {
+   "آذَر" ->  "âẕar"
+   "سَم" ->  "sam"
+   "پُر" ->  "por"
+   "پِدَر" ->  "pedar"
+   "مَثَلاً" ->  "mas̱alâ´´"
+   "جزء" ->  "jz’"
+   "رأس" ->  "râ’s"
+   "سؤال" ->  "sv’âl"
+   "مسئلة" ->  "msy’lh"
+}
+
+stage main {
+
+  # 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 {
+    from space
+    to ""
+    after "\u0622\u0628\u064E\u0627\u062F"
+  }
+    sub "\ufdf2" "Allāh"
+
+    # pointing
+    sub "\u064e" "a"
+
+    sub {
+    from "\u0650"
+    to any(["e", "i"])
+  }
+    sub {
+    from "\u0650" + boundary
+    to "-e"
+  }
+
+    sub {
+    from "\u064f"
+    to any(["o", "u"])
+  }
+
+    sub "\u0652" ""
+    sub "\u0659" "ê"
+
+    # special pointed letters
+    sub "\u0639\u064e" "‘a"
+    sub "\u0639\u0650" "‘i"
+    sub "\u0639\u064f" "‘ū"
+    # handle MacOS regex difference
+    sub "\u0639\u064f\u0648" "‘ū"
+
+    sub "\u0650\u064a" "ī"
+    sub "\u0650\u06cc" "ī"
+    sub "\u0650\u064a\u0651\u064e" "īy"
+    sub {
+    from "\u0650\u064a"
+    to "iy"
+    after any(["\u064e", "u064f"])
+  }
+    sub "\u064f\u0648" "ō"
+    sub "\u064e\u0627" "ā"
+    sub "\u064e\u0649" "ay"
+    sub "\u064e\u0648\u0652" "aw"
+    sub "\u064e\u0648" "ow"
+    sub "\u064e\u064a\u0652" "ay"
+    sub "\u0650\u06cc\u0651\u064e" "īy"
+    sub "\u064e\u064a" "aī"
+    sub "\u064e\u06cc" "aī"
+    sub "\u0649\u0670" "á"
+    sub "\u0674" "-e"
+    sub "\u0654" "-e"
+    # - '-ye'
+
+    sub "\u0622" "â"
+
+    # ta' marboota
+    sub "\u0629" "t"
+    sub {
+    from "\u0629" + line_end
+    to "h"
+  }
+    # TODO: simplify this
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "h"
+    before boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+  }
+    sub {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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 {
+    from "\u0629"
+    to "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" "’"
+    sub "\u0623" "â’"
+    sub "\u0624" "v’"
+    sub "\u0626" "y’"
+
+    # punctuation
+
+    sub "\u060c" ","
+    sub "\u061b" ";"
+    sub "\u061f" "?"
+
+    sub "\u0625" ""
+    sub "\u0627" "â"
+
+    # See note B
+    sub {
+    from boundary + "\u0627\u0644"
+    to "al "
+  }
+    # '\uFE8E' : ''  # ﺎ
+
+    # Sun letters
+    sub {
+    from boundary + "\u0627\u0644\u062a" + maybe("\u0651")
+    to "at t"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u062b" + maybe("\u0651")
+    to "as̄ s̄"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u062f" + maybe("\u0651")
+    to "ad d"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0630" + maybe("\u0651")
+    to "az̄ z̄"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0631" + maybe("\u0651")
+    to "ar r"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0632" + maybe("\u0651")
+    to "az z"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0633" + maybe("\u0651")
+    to "as s"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0634" + maybe("\u0651")
+    to "ash sh"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0635" + maybe("\u0651")
+    to "aş ş"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0636" + maybe("\u0651")
+    to "aẕ ẕ"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0637" + maybe("\u0651")
+    to "aţ ţ"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0638" + maybe("\u0651")
+    to "az̧ z̧"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0644" + maybe("\u0651")
+    to "al l"
+  }
+    sub {
+    from boundary + "\u0627\u0644\u0646" + maybe("\u0651")
+    to "an n"
+  }
+
+    # consonant characters
+
+    sub "\u0628" "b"
+    sub "\u067E" "p"
+    sub "\u062a" "t"
+    # '\u067C': 'ṯ'  # ټ
+    sub "\u062B" "s̱"
+    sub "\u062c" "j"
+    sub "\u0686" "c"
+
+    # # 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"
+    sub "\u062e" "ḵ"
+    sub "\u062f" "d"
+    sub "\u0689" "ḏ"
+    sub "\u0630" "ẕ"
+    sub "\u0631" "r"
+    # '\u0693' : 'ṟ'   # ړ
+    sub "\u0632" "z"
+    sub "\u0698" "z"
+    # '\u0696' : 'z͟h'  # ږ
+    sub "\u0633" "s"
+    # '\u069A' : 's͟h'  # ښ
+    sub "\u0634" "š"
+    sub "\u0635" "ṣ"
+    sub "\u0636" "ż"
+    sub "\u0637" "ṭ"
+    sub "\u0638" "z"
+    sub "\u0639" "‘"
+    sub "\u063a" "gh"
+    sub "\u0641" "f"
+    sub "\u0642" "q"
+    # '\u0643' : 'k'  # ك
+    sub "\u06A9" "k"
+    sub "\u06AF" "g"
+    sub "\u0644" "l"
+    sub "\u0645" "m"
+    sub "\u0646" "n"
+    # '\u06BC' : 'ṉ' # ڼ
+    sub "\u0648" "v"
+    sub "\u0647" "h"
+    sub "\u064a" "y"
+    sub "\u0649" "y"
+    sub "\u06D0" "ē"
+    sub "\u06CD" "êy"
+
+    # shadda
+    sub "\u0628" "bb"
+    sub "\u067E" "pp"
+    sub "\u062a" "tt"
+    sub "\u062B" "s̱s̱"
+    sub "\u062c" "jj"
+    sub "\u0686" "č̱č̱"
+    sub "\u062d" "ḥḥ"
+    sub "\u062e" "ḵḵ"
+    sub "\u062f" "dd"
+    sub "\u0689" "ḏḏ"
+    sub "\u0630" "ẕẕ"
+    sub "\u0631" "rr"
+    sub "\u0632" "zz"
+    sub "\u0698" "zz"
+    sub "\u0633" "ss"
+    sub "\u0634" "šš"
+    sub "\u0635" "ṣṣ"
+    sub "\u0636" "żż"
+    sub "\u0637" "ṭṭ"
+    sub "\u0638" "zz"
+    sub "\u0639" "‘"
+    sub "\u063a" "gh"
+    sub "\u0641" "ff"
+    sub "\u0642" "qq"
+    sub "\u06A9" "kk"
+    sub "\u06AF" "gg"
+    sub "\u0644" "ll"
+    sub "\u0645" "mm"
+    sub "\u0646" "nn"
+    sub "\u0648" "vv"
+    sub "\u0647" "hh"
+    sub "\u064a" "yy"
+    sub "\u0649" "yy"
+    sub "\u06D0" "ēē"
+    sub "\u06CD" "êy"
+  }
+
+}
+}