Python unicodedata.combining方法代码示例

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def preprocess_text(inputs, remove_space=True, lower=False):
    """preprocess data by removing extra space and normalize data."""
    outputs = inputs
    if remove_space:
        outputs = " ".join(inputs.strip().split())

    if six.PY2 and isinstance(outputs, str):
        try:
            outputs = six.ensure_text(outputs, "utf-8")
        except UnicodeDecodeError:
            outputs = six.ensure_text(outputs, "latin-1")

    outputs = unicodedata.normalize("NFKD", outputs)
    outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
    if lower:
        outputs = outputs.lower()

    return outputs 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def chars(self, num, truncate=None, html=False):
        """
        Returns the text truncated to be no longer than the specified number
        of characters.

        Takes an optional argument of what should be used to notify that the
        string has been truncated, defaulting to a translatable string of an
        ellipsis (...).
        """
        length = int(num)
        text = unicodedata.normalize('NFC', self._wrapped)

        # Calculate the length to truncate to (max length - end_text length)
        truncate_len = length
        for char in self.add_truncation_text('', truncate):
            if not unicodedata.combining(char):
                truncate_len -= 1
                if truncate_len == 0:
                    break
        if html:
            return self._truncate_html(length, truncate, text, truncate_len, False)
        return self._text_chars(length, truncate, text, truncate_len) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def _text_chars(self, length, truncate, text, truncate_len):
        """
        Truncates a string after a certain number of chars.
        """
        s_len = 0
        end_index = None
        for i, char in enumerate(text):
            if unicodedata.combining(char):
                # Don't consider combining characters
                # as adding to the string length
                continue
            s_len += 1
            if end_index is None and s_len > truncate_len:
                end_index = i
            if s_len > length:
                # Return the truncated string
                return self.add_truncation_text(text[:end_index or 0],
                                                truncate)

        # Return the original string since no truncation was necessary
        return text 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
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'), '') 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def strip_accents_unicode(s):
    """Transform accentuated unicode symbols into their simple counterpart

    Warning: the python-level loop and join operations make this
    implementation 20 times slower than the strip_accents_ascii basic
    normalization.

    See also
    --------
    strip_accents_ascii
        Remove accentuated char for any unicode symbol that has a direct
        ASCII equivalent.
    """
    normalized = unicodedata.normalize('NFKD', s)
    if normalized == s:
        return s
    else:
        return ''.join([c for c in normalized if not unicodedata.combining(c)]) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def preprocess_text(inputs, lower=False, remove_space=True, keep_accents=False):
  if remove_space:
    outputs = ' '.join(inputs.strip().split())
  else:
    outputs = inputs
  outputs = outputs.replace("``", '"').replace("''", '"')

  if six.PY2 and isinstance(outputs, str):
    outputs = outputs.decode('utf-8')

  if not keep_accents:
    outputs = unicodedata.normalize('NFKD', outputs)
    outputs = ''.join([c for c in outputs if not unicodedata.combining(c)])
  if lower:
    outputs = outputs.lower()

  return outputs 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def chars(self, num, truncate=None, html=False):
        """
        Return the text truncated to be no longer than the specified number
        of characters.

        `truncate` specifies what should be used to notify that the string has
        been truncated, defaulting to a translatable string of an ellipsis
        (...).
        """
        self._setup()
        length = int(num)
        text = unicodedata.normalize('NFC', self._wrapped)

        # Calculate the length to truncate to (max length - end_text length)
        truncate_len = length
        for char in self.add_truncation_text('', truncate):
            if not unicodedata.combining(char):
                truncate_len -= 1
                if truncate_len == 0:
                    break
        if html:
            return self._truncate_html(length, truncate, text, truncate_len, False)
        return self._text_chars(length, truncate, text, truncate_len) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def _text_chars(self, length, truncate, text, truncate_len):
        """Truncate a string after a certain number of chars."""
        s_len = 0
        end_index = None
        for i, char in enumerate(text):
            if unicodedata.combining(char):
                # Don't consider combining characters
                # as adding to the string length
                continue
            s_len += 1
            if end_index is None and s_len > truncate_len:
                end_index = i
            if s_len > length:
                # Return the truncated string
                return self.add_truncation_text(text[:end_index or 0],
                                                truncate)

        # Return the original string since no truncation was necessary
        return text 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def strip_accents_unicode(s):
    """Transform accentuated unicode symbols into their simple counterpart

    Warning: the python-level loop and join operations make this
    implementation 20 times slower than the strip_accents_ascii basic
    normalization.

    Parameters
    ----------
    s : string
        The string to strip

    See also
    --------
    strip_accents_ascii
        Remove accentuated char for any unicode symbol that has a direct
        ASCII equivalent.
    """
    normalized = unicodedata.normalize('NFKD', s)
    if normalized == s:
        return s
    else:
        return ''.join([c for c in normalized if not unicodedata.combining(c)]) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def GetLineWidth(line):
  """Determines the width of the line in column positions.

  Args:
    line: A string, which may be a Unicode string.

  Returns:
    The width of the line in column positions, accounting for Unicode
    combining characters and wide characters.
  """
  if isinstance(line, unicode):
    width = 0
    for uc in unicodedata.normalize('NFC', line):
      if unicodedata.east_asian_width(uc) in ('W', 'F'):
        width += 2
      elif not unicodedata.combining(uc):
        width += 1
    return width
  else:
    return len(line) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
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 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def check_initial_combiner(label):

    if unicodedata.category(label[0])[0] == 'M':
        raise IDNAError('Label begins with an illegal combining character')
    return True 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def _combining_class(cp):
    return unicodedata.combining(unichr(cp)) 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def _char_block_width(char):
    # Basic Latin, which is probably the most common case
    #if char in xrange(0x0021, 0x007e):
    #if char >= 0x0021 and char <= 0x007e:
    if 0x0021 <= char <= 0x007e:
        return 1
    # Chinese, Japanese, Korean (common)
    if 0x4e00 <= char <= 0x9fff:
        return 2
    # Hangul
    if 0xac00 <= char <= 0xd7af:
        return 2
    # Combining?
    if unicodedata.combining(uni_chr(char)):
        return 0
    # Hiragana and Katakana
    if 0x3040 <= char <= 0x309f or 0x30a0 <= char <= 0x30ff:
        return 2
    # Full-width Latin characters
    if 0xff01 <= char <= 0xff60:
        return 2
    # CJK punctuation
    if 0x3000 <= char <= 0x303e:
        return 2
    # Backspace and delete
    if char in (0x0008, 0x007f):
        return -1
    # Other control characters
    elif char in (0x0000, 0x001f):
        return 0
    # Take a guess
    return 1 

# 需要导入模块: import unicodedata [as 别名]
# 或者: from unicodedata import combining [as 别名]
def preprocess_text(self, inputs):
        if self.remove_space:
            outputs = " ".join(inputs.strip().split())
        else:
            outputs = inputs
        outputs = outputs.replace("``", '"').replace("''", '"')

        if not self.keep_accents:
            outputs = unicodedata.normalize("NFKD", outputs)
            outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
        if self.do_lower_case:
            outputs = outputs.lower()

        return outputs