Python源码示例：unicodedata.east_asian_width()
示例1
def strdisplaywidth(self, s):
def get_char_display_width(unicode_str):
r = unicodedata.east_asian_width(unicode_str)
if r == "F": # Fullwidth
return 1
elif r == "H": # Half-width
return 1
elif r == "W": # Wide
return 2
elif r == "Na": # Narrow
return 1
elif r == "A": # Ambiguous, go with 2
return 1
elif r == "N": # Neutral
return 1
else:
return 1
s = unicodedata.normalize('NFC', s)
w = 0
for c in s:
w += get_char_display_width(c)
return w
示例2
def cursor_left(self, n=1):
"""ESCnD CUB (Cursor Back)"""
# Commented out to save CPU (and the others below too)
#logging.debug('cursor_left(%s)' % n)
n = int(n)
# This logic takes care of double-width unicode characters
if self.double_width_left:
self.double_width_left = False
return
self.cursorX = max(0, self.cursorX - n) # Ensures positive value
try:
char = self.screen[self.cursorY][self.cursorX]
except IndexError: # Cursor is past the right-edge of the screen; ignore
char = u' ' # This is a safe default/fallback
if unicodedata.east_asian_width(char) == 'W':
# This lets us skip the next call (get called 2x for 2x width)
self.double_width_left = True
try:
for callback in self.callbacks[CALLBACK_CURSOR_POS].values():
callback()
except TypeError:
pass
示例3
def cursor_right(self, n=1):
"""ESCnC CUF (Cursor Forward)"""
#logging.debug('cursor_right(%s)' % n)
if not n:
n = 1
n = int(n)
# This logic takes care of double-width unicode characters
if self.double_width_right:
self.double_width_right = False
return
self.cursorX += n
try:
char = self.screen[self.cursorY][self.cursorX]
except IndexError: # Cursor is past the right-edge of the screen; ignore
char = u' ' # This is a safe default/fallback
if unicodedata.east_asian_width(char) == 'W':
# This lets us skip the next call (get called 2x for 2x width)
self.double_width_right = True
try:
for callback in self.callbacks[CALLBACK_CURSOR_POS].values():
callback()
except TypeError:
pass
示例4
def get_east_asian_width(unicode_str):
r = unicodedata.east_asian_width(unicode_str)
if r == "F": # Fullwidth
return 1
elif r == "H": # Half-width
return 1
elif r == "W": # Wide
return 2
elif r == "Na": # Narrow
return 1
elif r == "A": # Ambiguous, go with 2
return 1
elif r == "N": # Neutral
return 1
else:
return 1
示例5
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'), '')
示例6
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例7
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, unicode):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例8
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)
示例9
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例10
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)
示例11
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例12
def cursor_left(self, n=1):
"""ESCnD CUB (Cursor Back)"""
# Commented out to save CPU (and the others below too)
#logging.debug('cursor_left(%s)' % n)
n = int(n)
# This logic takes care of double-width unicode characters
if self.double_width_left:
self.double_width_left = False
return
self.cursorX = max(0, self.cursorX - n) # Ensures positive value
try:
char = self.screen[self.cursorY][self.cursorX]
except IndexError: # Cursor is past the right-edge of the screen; ignore
char = u' ' # This is a safe default/fallback
if unicodedata.east_asian_width(char) == 'W':
# This lets us skip the next call (get called 2x for 2x width)
self.double_width_left = True
try:
for callback in self.callbacks[CALLBACK_CURSOR_POS].values():
callback()
except TypeError:
pass
示例13
def cursor_right(self, n=1):
"""ESCnC CUF (Cursor Forward)"""
#logging.debug('cursor_right(%s)' % n)
if not n:
n = 1
n = int(n)
# This logic takes care of double-width unicode characters
if self.double_width_right:
self.double_width_right = False
return
self.cursorX += n
try:
char = self.screen[self.cursorY][self.cursorX]
except IndexError: # Cursor is past the right-edge of the screen; ignore
char = u' ' # This is a safe default/fallback
if unicodedata.east_asian_width(char) == 'W':
# This lets us skip the next call (get called 2x for 2x width)
self.double_width_right = True
try:
for callback in self.callbacks[CALLBACK_CURSOR_POS].values():
callback()
except TypeError:
pass
示例14
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'), '')
示例15
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, unicode):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例16
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例17
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例18
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, str):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例19
def pad_double_width(self, pad_char):
"""
Pad all double-width characters in self by appending `pad_char` to each.
For East Asian language support.
"""
if hasattr(unicodedata, 'east_asian_width'):
east_asian_width = unicodedata.east_asian_width
else:
return # new in Python 2.4
for i in range(len(self.data)):
line = self.data[i]
if isinstance(line, unicode):
new = []
for char in line:
new.append(char)
if east_asian_width(char) in 'WF': # 'W'ide & 'F'ull-width
new.append(pad_char)
self.data[i] = ''.join(new)
示例20
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)
示例21
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 six.PY2:
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
return len(line)
示例22
def width(ch):
"""
Compute the display width of the given character.
Useful for cursor-repositioning tasks, however this is not entirely
reliable since different terminal emulators have different behavior in
this area.
@see: U{http://unicode.org/reports/tr11/}
@return: The width in 1/2 ems of the given single-length unicode string.
@rtype: C{int}
"""
widthSpecifier = unicodedata.east_asian_width(ch)
try:
return _widths[widthSpecifier]
except KeyError:
raise KeyError("%r has a width that is not supported: %s"
% (ch, widthSpecifier))
示例23
def strpad(self, s, width):
if width < 1:
return str()
if '\n' in s:
s = s.replace('\n', '\\n')
# take into account double-width characters
buf = str()
buf_width = 0
for c in s:
w = 2 if unicodedata.east_asian_width(c) == 'W' else 1
if buf_width + w > width:
break
buf_width += w
buf += c
if len(buf) < len(s):
# truncation occurred
while buf_width + len(self.trunc_char) > width:
c = buf[-1]
w = 2 if unicodedata.east_asian_width(c) == 'W' else 1
buf = buf[0:-1]
buf_width -= w
buf += ' ' * (width - buf_width - len(self.trunc_char))
buf += self.trunc_char
elif buf_width < width:
# padding required
buf += ' ' * (width - buf_width)
return buf
示例24
def __cell_len_dw(s):
"""Return the number of character cells a string will take
(double-width aware). Defined as self._cell_len in __init__
"""
len = 0
for c in s:
w = 2 if unicodedata.east_asian_width(c) == 'W' else 1
len += w
return len
示例25
def get_line_width(text):
text = unicodedata.normalize('NFC', text)
return sum(char_width.get(unicodedata.east_asian_width(c), 1) for c in text)
# XXX unify with _escaped func below
示例26
def east_asian_len(data, encoding=None, ambiguous_width=1):
"""
Calculate display width considering unicode East Asian Width
"""
if isinstance(data, text_type):
return sum(_EAW_MAP.get(east_asian_width(c), ambiguous_width) for c in data)
else:
return len(data)
示例27
def east_asian_len(data, encoding=None, ambiguous_width=1):
"""
Calculate display width considering unicode East Asian Width
"""
if isinstance(data, text_type):
try:
data = data.decode(encoding)
except UnicodeError:
pass
return sum(_EAW_MAP.get(east_asian_width(c), ambiguous_width) for c in data)
else:
return len(data)
示例28
def _string_width(string, *, _IS_ASCII=_IS_ASCII):
"""Returns string's width."""
match = _IS_ASCII.match(string)
if match:
return match.endpos
UNICODE_WIDE_CHAR_TYPE = 'WFA'
width = 0
func = unicodedata.east_asian_width
for char in string:
width += 2 if func(char) in UNICODE_WIDE_CHAR_TYPE else 1
return width
示例29
def make_character_presentable(c, rp):
if len(c) == 0:
return c, 0 # The result of an ignored failed decode from an invalid character.
# A character at this point should be a list of integers.
for b in c:
assert(type(b) == int)
if rp.pretty_output:
if len(c) == 1 and ((c[0] > 31 and c[0] < 127) or c[0] == ord('\t')):
# Standard ascii character
if c[0] == ord('\t'):
return [ord(u" "),ord(u" "),ord(u" "),ord(u" ")], 4
else:
return [c[0]], 1
else:
# Extended ASCII characer or multi-byte character.
rtn = []
for byte in c:
rtn += [py23_ord(b) for b in (b"\\x" + as_byte_string(format(byte, '02X'), rp.output_encoding, "internal"))]
return rtn, len(rtn)
else:
# This is not precise at all, but it is the best that can be done
char_as_unicode = e_decode(int_array_as_byte_string(c), rp.output_encoding, "internal")
if len(char_as_unicode) == 0:
return [], 0 # Happens sometimes due to decode failure on invalid characters.
east_asian_width = get_east_asian_width(char_as_unicode)
replacement_chars = get_replacement_char(char_as_unicode)
if replacement_chars is None:
return c, east_asian_width
else:
ls = [get_east_asian_width(c) for c in replacement_chars]
return [py23_ord(b) for b in as_byte_string(replacement_chars, rp.output_encoding, "internal")], sum(ls)
示例30
def get_line_width(text):
text = unicodedata.normalize('NFC', text)
return sum(char_width.get(unicodedata.east_asian_width(c), 1) for c in text)
# XXX unify with _escaped func below
