Python unicodedata.name() Examples

def _equivalent(self, char, prev, next, implicitA):
        """ Transliterate a Devanagari character to Latin.
        
        Add implicit As unless overridden by VIRAMA.
        
        """
        implicitA = False  # Force it!
        result = []
        if char.chr != DevanagariCharacter._VIRAMA:
            result.append(char.equivalents[self.name])
        """ Append implicit A to consonants if the next character isn't a vowel. """
        if implicitA and char.isConsonant \
        and ((next is not None \
        and next.chr != DevanagariCharacter._VIRAMA \
        and not next.isVowel) \
        or next is None):
            result.append(characterBlocks['DEVANAGARI']\
                   [DevanagariCharacter._LETTER_A].equivalents[self.name])
        return result 

def test_hangul_syllables(self):
        self.checkletter("HANGUL SYLLABLE GA", u"\uac00")
        self.checkletter("HANGUL SYLLABLE GGWEOSS", u"\uafe8")
        self.checkletter("HANGUL SYLLABLE DOLS", u"\ub3d0")
        self.checkletter("HANGUL SYLLABLE RYAN", u"\ub7b8")
        self.checkletter("HANGUL SYLLABLE MWIK", u"\ubba0")
        self.checkletter("HANGUL SYLLABLE BBWAEM", u"\ubf88")
        self.checkletter("HANGUL SYLLABLE SSEOL", u"\uc370")
        self.checkletter("HANGUL SYLLABLE YI", u"\uc758")
        self.checkletter("HANGUL SYLLABLE JJYOSS", u"\ucb40")
        self.checkletter("HANGUL SYLLABLE KYEOLS", u"\ucf28")
        self.checkletter("HANGUL SYLLABLE PAN", u"\ud310")
        self.checkletter("HANGUL SYLLABLE HWEOK", u"\ud6f8")
        self.checkletter("HANGUL SYLLABLE HIH", u"\ud7a3")

        import unicodedata
        self.assertRaises(ValueError, unicodedata.name, u"\ud7a4") 

def main(argv):
  if len(argv) < 2:
    sys.exit('Must specify one or more font files.')

  cps = set()
  for filename in argv[1:]:
    if not os.path.isfile(filename):
      sys.exit('%s is not a file' % filename)
    cps |= fonts.CodepointsInFont(filename)

  for cp in sorted(cps):
    show_char = ''
    if FLAGS.show_char:
      show_char = (' ' + unichr(cp).strip() + ' ' +
                   unicodedata.name(unichr(cp), ''))
    show_subset = ''
    if FLAGS.show_subsets:
      show_subset = ' subset:%s' % ','.join(fonts.SubsetsForCodepoint(cp))

    print(u'0x%04X%s%s' % (cp, show_char, show_subset)) 

def main(global_delay, local_delay, concurrency):
    global global_sleep, local_sleep, semaphore, index
    global_sleep = global_delay
    local_sleep = local_delay
    semaphore = asyncio.Semaphore(concurrency)
    print('Global delay =', global_delay)
    print('Local delay =', local_delay)
    print('Max. concurrency =', concurrency)
    print('Building inverted index...')
    index = build_index()

    app = web.Application()
    app.router.add_get('/', usage)
    app.router.add_get('/index/{word}', index_for)
    app.router.add_get('/name/{char}', char_name)

    print('Listening on port', PORT)
    web.run_app(app, port=PORT) 

def test_longstrings(self):
        # test long strings to check for memory overflow problems
        errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
                   "backslashreplace"]
        # register the handlers under different names,
        # to prevent the codec from recognizing the name
        for err in errors:
            codecs.register_error("test." + err, codecs.lookup_error(err))
        l = 1000
        errors += [ "test." + err for err in errors ]
        for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
            for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
                        "utf-8", "utf-7", "utf-16", "utf-32"):
                for err in errors:
                    try:
                        uni.encode(enc, err)
                    except UnicodeError:
                        pass 

def test_strict_eror_handling(self):
        # bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{blah}", 'unicode-escape', 'strict'
        )
        # long bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{%s}" % ("x" * 100000), 'unicode-escape', 'strict'
        )
        # missing closing brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{SPACE", 'unicode-escape', 'strict'
        )
        # missing opening brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\NSPACE", 'unicode-escape', 'strict'
        ) 

def test_ipy2_gh357(self):
        """https://github.com/IronLanguages/ironpython2/issues/357"""

        import unicodedata

        if is_cli:
            self.assertEqual(unicodedata.name(u'\u4e2d'), '<CJK IDEOGRAPH, FIRST>..<CJK IDEOGRAPH, LAST>')
        else:
            self.assertEqual(unicodedata.name(u'\u4e2d'), 'CJK UNIFIED IDEOGRAPH-4E2D')

        self.assertRaises(ValueError, unicodedata.decimal, u'\u4e2d')
        self.assertEqual(unicodedata.decimal(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.digit, u'\u4e2d')
        self.assertEqual(unicodedata.digit(u'\u4e2d', 0), 0)
        self.assertRaises(ValueError, unicodedata.numeric, u'\u4e2d')
        self.assertEqual(unicodedata.numeric(u'\u4e2d', 0), 0)
        self.assertEqual(unicodedata.category(u'\u4e2d'), 'Lo')
        self.assertEqual(unicodedata.bidirectional(u'\u4e2d'), 'L')
        self.assertEqual(unicodedata.combining(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.east_asian_width(u'\u4e2d'), 'W')
        self.assertEqual(unicodedata.mirrored(u'\u4e2d'), 0)
        self.assertEqual(unicodedata.decomposition(u'\u4e2d'), '') 

def test_longstrings(self):
        # test long strings to check for memory overflow problems
        errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
                   "backslashreplace"]
        # register the handlers under different names,
        # to prevent the codec from recognizing the name
        for err in errors:
            codecs.register_error("test." + err, codecs.lookup_error(err))
        l = 1000
        errors += [ "test." + err for err in errors ]
        for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
            for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
                        "utf-8", "utf-7", "utf-16", "utf-32"):
                for err in errors:
                    try:
                        uni.encode(enc, err)
                    except UnicodeError:
                        pass 

def test_hangul_syllables(self):
        self.checkletter("HANGUL SYLLABLE GA", u"\uac00")
        self.checkletter("HANGUL SYLLABLE GGWEOSS", u"\uafe8")
        self.checkletter("HANGUL SYLLABLE DOLS", u"\ub3d0")
        self.checkletter("HANGUL SYLLABLE RYAN", u"\ub7b8")
        self.checkletter("HANGUL SYLLABLE MWIK", u"\ubba0")
        self.checkletter("HANGUL SYLLABLE BBWAEM", u"\ubf88")
        self.checkletter("HANGUL SYLLABLE SSEOL", u"\uc370")
        self.checkletter("HANGUL SYLLABLE YI", u"\uc758")
        self.checkletter("HANGUL SYLLABLE JJYOSS", u"\ucb40")
        self.checkletter("HANGUL SYLLABLE KYEOLS", u"\ucf28")
        self.checkletter("HANGUL SYLLABLE PAN", u"\ud310")
        self.checkletter("HANGUL SYLLABLE HWEOK", u"\ud6f8")
        self.checkletter("HANGUL SYLLABLE HIH", u"\ud7a3")

        import unicodedata
        self.assertRaises(ValueError, unicodedata.name, u"\ud7a4") 

def test_strict_eror_handling(self):
        # bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{blah}", 'unicode-escape', 'strict'
        )
        # long bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{%s}" % ("x" * 100000), 'unicode-escape', 'strict'
        )
        # missing closing brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{SPACE", 'unicode-escape', 'strict'
        )
        # missing opening brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\NSPACE", 'unicode-escape', 'strict'
        ) 

def get_unicode_index(symbol):
    """get_unicode_index(symbol) -> integer

Return the integer index (from the Unicode table) of symbol.  *symbol*
can be a single unicode character, a TeX command (i.e. r'\pi'), or a
Type1 symbol name (i.e. 'phi').
"""
    # From UTF #25: U+2212 minus sign is the preferred
    # representation of the unary and binary minus sign rather than
    # the ASCII-derived U+002D hyphen-minus, because minus sign is
    # unambiguous and because it is rendered with a more desirable
    # length, usually longer than a hyphen.
    if symbol == '-':
        return 0x2212
    try:# This will succeed if symbol is a single unicode char
        return ord(symbol)
    except TypeError:
        pass
    try:# Is symbol a TeX symbol (i.e. \alpha)
        return tex2uni[symbol.strip("\\")]
    except KeyError:
        message = """'%(symbol)s' is not a valid Unicode character or
TeX/Type1 symbol"""%locals()
        raise ValueError(message) 

def test_hangul_syllables(self):
        self.checkletter("HANGUL SYLLABLE GA", u"\uac00")
        self.checkletter("HANGUL SYLLABLE GGWEOSS", u"\uafe8")
        self.checkletter("HANGUL SYLLABLE DOLS", u"\ub3d0")
        self.checkletter("HANGUL SYLLABLE RYAN", u"\ub7b8")
        self.checkletter("HANGUL SYLLABLE MWIK", u"\ubba0")
        self.checkletter("HANGUL SYLLABLE BBWAEM", u"\ubf88")
        self.checkletter("HANGUL SYLLABLE SSEOL", u"\uc370")
        self.checkletter("HANGUL SYLLABLE YI", u"\uc758")
        self.checkletter("HANGUL SYLLABLE JJYOSS", u"\ucb40")
        self.checkletter("HANGUL SYLLABLE KYEOLS", u"\ucf28")
        self.checkletter("HANGUL SYLLABLE PAN", u"\ud310")
        self.checkletter("HANGUL SYLLABLE HWEOK", u"\ud6f8")
        self.checkletter("HANGUL SYLLABLE HIH", u"\ud7a3")

        import unicodedata
        self.assertRaises(ValueError, unicodedata.name, u"\ud7a4") 

def test_longstrings(self):
        # test long strings to check for memory overflow problems
        errors = [ "strict", "ignore", "replace", "xmlcharrefreplace",
                   "backslashreplace"]
        # register the handlers under different names,
        # to prevent the codec from recognizing the name
        for err in errors:
            codecs.register_error("test." + err, codecs.lookup_error(err))
        l = 1000
        errors += [ "test." + err for err in errors ]
        for uni in [ s*l for s in (u"x", u"\u3042", u"a\xe4") ]:
            for enc in ("ascii", "latin-1", "iso-8859-1", "iso-8859-15",
                        "utf-8", "utf-7", "utf-16", "utf-32"):
                for err in errors:
                    try:
                        uni.encode(enc, err)
                    except UnicodeError:
                        pass 

def __init__(self, unicodeHexValue, block):
        """ Set up a unicode character.
        
        Arguments:
        unicodeHexValue -- an integer that should correspond to a 
                           Unicode code point.
        block -- the CharacterBlock this character belongs to.
        
        Raises:
        ValueError -- if unicodeHexValue is not a valid code point.
        
        """
        if unicodeHexValue < 0 or unicodeHexValue > 0x10FFFF:
            raise (ValueError, "numeric value outside Unicode range")
        self.unicodeHexValue = unicodeHexValue
        """ Use name check to filter out unused characters.
              unicodedata.name() raises ValueError for these
        """
        self.chr = chr(self.unicodeHexValue)
        self.name = unicodedata.name(self.chr)
        self.equivalents = {}
        self._block = block 

def _equivalent(self, char, prev, next, implicitA):
        """ Transliterate a Devanagari character to Latin.
        
        Add implicit As unless overridden by VIRAMA.
        
        """
        result = []
        if char.unichr != DevanagariCharacter._VIRAMA:
            result.append(char.equivalents[self.name])
        """ Append implicit A to consonants if the next character isn't a vowel. """
        if implicitA and char.isConsonant \
        and ((next is not None \
        and next.unichr != DevanagariCharacter._VIRAMA \
        and not next.isVowel) \
        or next is None):
            result.append(characterBlocks['DEVANAGARI']\
                   [DevanagariCharacter._LETTER_A].equivalents[self.name])
        return result 

def __init__(self, unicodeHexValue, block):
        """ Set up a unicode character.
        
        Arguments:
        unicodeHexValue -- an integer that should correspond to a 
                           Unicode code point.
        block -- the CharacterBlock this character belongs to.
        
        Raises:
        ValueError -- if unicodeHexValue is not a valid code point.
        
        """
        if unicodeHexValue < 0 or unicodeHexValue > 0x10FFFF:
            raise ValueError("numeric value outside Unicode range")
        self.unicodeHexValue = unicodeHexValue
        """ Use name check to filter out unused characters.
              unicodedata.name() raises ValueError for these
        """
        self.unichr = py23char(self.unicodeHexValue)
        self.name = unicodedata.name(self.unichr)
        self.equivalents = {}
        self._block = block 

def remove_diacritics(self):
        """
        :return: str: the input string stripped of its diacritics

        Examples:
            >>> Word('ġelǣd').remove_diacritics()
            'gelæd'

        """

        w = ''
        for c in unicodedata.normalize('NFKD', self.word):
            if 'LATIN' == unicodedata.name(c)[:5]:
                w += c

        return w 

def render_glyph(self, ox, oy, facename, font_class, sym, fontsize, dpi):
        """
        Draw a glyph at

          - *ox*, *oy*: position

          - *facename*: One of the TeX face names

          - *font_class*:

          - *sym*: TeX symbol name or single character

          - *fontsize*: fontsize in points

          - *dpi*: The dpi to draw at.
        """
        info = self._get_info(facename, font_class, sym, fontsize, dpi)
        realpath, stat_key = get_realpath_and_stat(info.font.fname)
        used_characters = self.used_characters.setdefault(
            stat_key, (realpath, set()))
        used_characters[1].add(info.num)
        self.mathtext_backend.render_glyph(ox, oy, info) 

def get_unicode_index(symbol):
    """get_unicode_index(symbol) -> integer

Return the integer index (from the Unicode table) of symbol.  *symbol*
can be a single unicode character, a TeX command (i.e. r'\pi'), or a
Type1 symbol name (i.e. 'phi').
"""
    # From UTF #25: U+2212 minus sign is the preferred
    # representation of the unary and binary minus sign rather than
    # the ASCII-derived U+002D hyphen-minus, because minus sign is
    # unambiguous and because it is rendered with a more desirable
    # length, usually longer than a hyphen.
    if symbol == '-':
        return 0x2212
    try:# This will succeed if symbol is a single unicode char
        return ord(symbol)
    except TypeError:
        pass
    try:# Is symbol a TeX symbol (i.e. \alpha)
        return tex2uni[symbol.strip("\\")]
    except KeyError:
        message = """'%(symbol)s' is not a valid Unicode character or
TeX/Type1 symbol"""%locals()
        raise ValueError(message) 

def unicode(self, irc, msg, args, query):
        """[character]
        Look up unicode character details
        """
        url = "http://unicodelookup.com/lookup?"
        url = url + urlencode({"q": query, "o": 0})
        data = web.getUrl(url)
        try:
            data = json.loads(data)
            responses = []
            for result in data["results"]:
                ucode = result[2].replace("0x", "U+")
                name = unicodedata.name("{0}".format(query))
                responses.append(
                    "%s (%s): %s [HTML: %s / Decimal: %s / Hex: %s]"
                    % (ucode, name, result[4], result[3], result[1], result[2])
                )
            response = "; ".join(responses)
            irc.reply(response)
        except ValueError:
            irc.reply("No unicode characters matching /" + query + "/ found.") 

def test_strict_eror_handling(self):
        # bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{blah}", 'unicode-escape', 'strict'
        )
        # long bogus character name
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{%s}" % ("x" * 100000), 'unicode-escape', 'strict'
        )
        # missing closing brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\N{SPACE", 'unicode-escape', 'strict'
        )
        # missing opening brace
        self.assertRaises(
            UnicodeError,
            unicode, "\\NSPACE", 'unicode-escape', 'strict'
        ) 

def render_glyph(self, ox, oy, facename, font_class, sym, fontsize, dpi):
        """
        Draw a glyph at

          - *ox*, *oy*: position

          - *facename*: One of the TeX face names

          - *font_class*:

          - *sym*: TeX symbol name or single character

          - *fontsize*: fontsize in points

          - *dpi*: The dpi to draw at.
        """
        info = self._get_info(facename, font_class, sym, fontsize, dpi)
        realpath, stat_key = get_realpath_and_stat(info.font.fname)
        used_characters = self.used_characters.setdefault(
            stat_key, (realpath, set()))
        used_characters[1].add(info.num)
        self.mathtext_backend.render_glyph(ox, oy, info) 

def _combining_class(cp):
    v = unicodedata.combining(unichr(cp))
    if v == 0:
        if not unicodedata.name(unichr(cp)):
            raise ValueError("Unknown character in unicodedata")
    return v 

def _ReformatLine(line):
  if line.startswith('0x'):
    codepoint = int(line[2:6], 16)
    out = unichr(codepoint) + ' ' + unicodedata.name(unichr(codepoint), '')
    return '0x%04X  %s' % (codepoint, out)
  else:
    return line 

def charinfo(self, ctx: Context, *, characters: str) -> None:
        """Shows you information on up to 25 unicode characters."""
        match = re.match(r"<(a?):(\w+):(\d+)>", characters)
        if match:
            embed = Embed(
                title="Non-Character Detected",
                description=(
                    "Only unicode characters can be processed, but a custom Discord emoji "
                    "was found. Please remove it and try again."
                )
            )
            embed.colour = Colour.red()
            await ctx.send(embed=embed)
            return

        if len(characters) > 25:
            embed = Embed(title=f"Too many characters ({len(characters)}/25)")
            embed.colour = Colour.red()
            await ctx.send(embed=embed)
            return

        def get_info(char: str) -> Tuple[str, str]:
            digit = f"{ord(char):x}"
            if len(digit) <= 4:
                u_code = f"\\u{digit:>04}"
            else:
                u_code = f"\\U{digit:>08}"
            url = f"https://www.compart.com/en/unicode/U+{digit:>04}"
            name = f"[{unicodedata.name(char, '')}]({url})"
            info = f"`{u_code.ljust(10)}`: {name} - {utils.escape_markdown(char)}"
            return info, u_code

        charlist, rawlist = zip(*(get_info(c) for c in characters))

        embed = Embed(description="\n".join(charlist))
        embed.set_author(name="Character Info")

        if len(characters) > 1:
            embed.add_field(name='Raw', value=f"`{''.join(rawlist)}`", inline=False)

        await ctx.send(embed=embed) 

def send_pep_zero(self, ctx: Context) -> None:
        """Send information about PEP 0."""
        pep_embed = Embed(
            title="**PEP 0 - Index of Python Enhancement Proposals (PEPs)**",
            description="[Link](https://www.python.org/dev/peps/)"
        )
        pep_embed.set_thumbnail(url=ICON_URL)
        pep_embed.add_field(name="Status", value="Active")
        pep_embed.add_field(name="Created", value="13-Jul-2000")
        pep_embed.add_field(name="Type", value="Informational")

        await ctx.send(embed=pep_embed) 

def _combining_class(cp):
    v = unicodedata.combining(unichr(cp))
    if v == 0:
        if not unicodedata.name(unichr(cp)):
            raise ValueError("Unknown character in unicodedata")
    return v 

def _combining_class(cp):
    v = unicodedata.combining(unichr(cp))
    if v == 0:
        if not unicodedata.name(unichr(cp)):
            raise ValueError("Unknown character in unicodedata")
    return v 

def _combining_class(cp):
    v = unicodedata.combining(unichr(cp))
    if v == 0:
        if not unicodedata.name(unichr(cp)):
            raise ValueError("Unknown character in unicodedata")
    return v 

def __init__(self, glue_type, copy=False):
        Node.__init__(self)
        self.glue_subtype   = 'normal'
        if is_string_like(glue_type):
            glue_spec = GlueSpec.factory(glue_type)
        elif isinstance(glue_type, GlueSpec):
            glue_spec = glue_type
        else:
            raise ArgumentError("glue_type must be a glue spec name or instance.")
        if copy:
            glue_spec = glue_spec.copy()
        self.glue_spec      = glue_spec