Unicode as String without conversion Python
我正试图将Unicode文本逐字转换为字符串，但似乎找不到一种方法来实现这一点。
1 | input= u'/123/123/123' |
转换为字符串：
1 | output="/123/123/123" |
如果我尝试执行str()，它将对其进行编码，如果我尝试循环文本并逐字转换，它将为我提供每个Unicode字符。
编辑：考虑到目标不是转换字符串，而是采用Unicode文本中的字母并创建字符串。如果我遵循注释中提供的链接：
在python中将unicode字符串转换为字符串(包含额外符号)
1 2 | import unicodedata unicodedata.normalize('NFKD', input).encode('ascii','ignore') |
输出="SSS"
可以看出，这不是预期的产出。
编辑：我写了一个unicode u'/123'的例子，但我试图转换汉字，例如：
1 2 3 4 5 | a=u'\u6c34' str(a) UnicodeEncodeError: 'ascii' codec can't encode character u'\u6c34' in position 0: ordinal not in range(128) |
output_expected="u6c34"
我试着用str()来转换它，正如您在问题中提到的，它确实对我有用。您可以使用type()检查编码。
1 2 3 4 5 6 7 8 | >>> input= u'/123/123/123' >>> type(input) <type 'unicode'> >>> output=str(input) >>> print output /123/123/123 >>> type(output) <type 'str'> |
你如何尝试在字母之间迭代？我试过了，但它们仍然是一根绳子。您可以先转换输入，然后在它们是str时执行您想要的任何操作：
letters = [x for x in output]
for letter in letters:
... print type(letter)
...< /块引用>< /块引用>
希望有帮助！
以下是简单的方法：
2
3
4
5
>>> a.encode('unicode_escape')
'\\x83\\u6c34\\U00103abc'
>>> print a.encode('unicode_escape')
\x83\u6c34\U00103abc以下是如何做到这一点的方法。
2
3
4
5
6
7
8
9
10
11
12
13
def convert(ch):
if ch in ascii_printable:
return ch
ix = ord(ch)
if ix < 0x100:
return '\\x%02x' % ix
elif ix < 0x10000:
return '\\u%04x' % ix
return '\\U%08x' % ix
output = ''.join(convert(ch) for ch in input)对于python 3，使用
chr 而不是unichr 。有人为此编写了一个非常完整的代码，非常酷，来源：
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
def fix_bad_unicode(text):
if not isinstance(text, unicode):
raise TypeError("This isn't even decoded into Unicode yet."
"Decode it first.")
if len(text) == 0:
return text
maxord = max(ord(char) for char in text)
tried_fixing = []
if maxord < 128:
# Hooray! It's ASCII!
return text
else:
attempts = [(text, text_badness(text) + len(text))]
if maxord < 256:
tried_fixing = reinterpret_latin1_as_utf8(text)
tried_fixing2 = reinterpret_latin1_as_windows1252(text)
attempts.append((tried_fixing, text_cost(tried_fixing)))
attempts.append((tried_fixing2, text_cost(tried_fixing2)))
elif all(ord(char) in WINDOWS_1252_CODEPOINTS for char in text):
tried_fixing = reinterpret_windows1252_as_utf8(text)
attempts.append((tried_fixing, text_cost(tried_fixing)))
else:
# We can't imagine how this would be anything but valid text.
return text
# Sort the results by badness
attempts.sort(key=lambda x: x[1])
#print attempts
goodtext = attempts[0][0]
if goodtext == text:
return goodtext
else:
return fix_bad_unicode(goodtext)
def reinterpret_latin1_as_utf8(wrongtext):
newbytes = wrongtext.encode('latin-1', 'replace')
return newbytes.decode('utf-8', 'replace')
def reinterpret_windows1252_as_utf8(wrongtext):
altered_bytes = []
for char in wrongtext:
if ord(char) in WINDOWS_1252_GREMLINS:
altered_bytes.append(char.encode('WINDOWS_1252'))
else:
altered_bytes.append(char.encode('latin-1', 'replace'))
return ''.join(altered_bytes).decode('utf-8', 'replace')
def reinterpret_latin1_as_windows1252(wrongtext):
return wrongtext.encode('latin-1').decode('WINDOWS_1252', 'replace')
def text_badness(text):
assert isinstance(text, unicode)
errors = 0
very_weird_things = 0
weird_things = 0
prev_letter_script = None
for pos in xrange(len(text)):
char = text[pos]
index = ord(char)
if index < 256:
weird_things += SINGLE_BYTE_WEIRDNESS[index]
if SINGLE_BYTE_LETTERS[index]:
prev_letter_script = 'latin'
else:
prev_letter_script = None
else:
category = unicodedata.category(char)
if category == 'Co':
# Unassigned or private use
errors += 1
elif index == 0xfffd:
# Replacement character
errors += 1
elif index in WINDOWS_1252_GREMLINS:
lowchar = char.encode('WINDOWS_1252').decode('latin-1')
weird_things += SINGLE_BYTE_WEIRDNESS[ord(lowchar)] - 0.5
if category.startswith('L'):
name = unicodedata.name(char)
scriptname = name.split()[0]
freq, script = SCRIPT_TABLE.get(scriptname, (0, 'other'))
if prev_letter_script:
if script != prev_letter_script:
very_weird_things += 1
if freq == 1:
weird_things += 2
elif freq == 0:
very_weird_things += 1
prev_letter_script = script
else:
prev_letter_script = None
return 100 * errors + 10 * very_weird_things + weird_things
def text_cost(text):
"""
Assign a cost function to the length plus weirdness of a text string.
"""
return text_badness(text) + len(text)
WINDOWS_1252_GREMLINS = [
# adapted from http://effbot.org/zone/unicode-gremlins.htm
0x0152, # LATIN CAPITAL LIGATURE OE
0x0153, # LATIN SMALL LIGATURE OE
0x0160, # LATIN CAPITAL LETTER S WITH CARON
0x0161, # LATIN SMALL LETTER S WITH CARON
0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS
0x017E, # LATIN SMALL LETTER Z WITH CARON
0x017D, # LATIN CAPITAL LETTER Z WITH CARON
0x0192, # LATIN SMALL LETTER F WITH HOOK
0x02C6, # MODIFIER LETTER CIRCUMFLEX ACCENT
0x02DC, # SMALL TILDE
0x2013, # EN DASH
0x2014, # EM DASH
0x201A, # SINGLE LOW-9 QUOTATION MARK
0x201C, # LEFT DOUBLE QUOTATION MARK
0x201D, # RIGHT DOUBLE QUOTATION MARK
0x201E, # DOUBLE LOW-9 QUOTATION MARK
0x2018, # LEFT SINGLE QUOTATION MARK
0x2019, # RIGHT SINGLE QUOTATION MARK
0x2020, # DAGGER
0x2021, # DOUBLE DAGGER
0x2022, # BULLET
0x2026, # HORIZONTAL ELLIPSIS
0x2030, # PER MILLE SIGN
0x2039, # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
0x203A, # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
0x20AC, # EURO SIGN
0x2122, # TRADE MARK SIGN
]
# a list of Unicode characters that might appear in Windows-1252 text
WINDOWS_1252_CODEPOINTS = range(256) + WINDOWS_1252_GREMLINS
# Rank the characters typically represented by a single byte -- that is, in
# Latin-1 or Windows-1252 -- by how weird it would be to see them in running
# text.
#
# 0 = not weird at all
# 1 = rare punctuation or rare letter that someone could certainly
# have a good reason to use. All Windows-1252 gremlins are at least
# weirdness 1.
# 2 = things that probably don't appear next to letters or other
# symbols, such as math or currency symbols
# 3 = obscure symbols that nobody would go out of their way to use
# (includes symbols that were replaced in ISO-8859-15)
# 4 = why would you use this?
# 5 = unprintable control character
#
# The Portuguese letter ? (0xc3) is marked as weird because it would usually
# appear in the middle of a word in actual Portuguese, and meanwhile it
# appears in the mis-encodings of many common characters.
SINGLE_BYTE_WEIRDNESS = (
# 0 1 2 3 4 5 6 7 8 9 a b c d e f
5, 5, 5, 5, 5, 5, 5, 5, 5, 0, 0, 5, 5, 5, 5, 5, # 0x00
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, # 0x10
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0x20
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0x30
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0x40
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0x50
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0x60
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, # 0x70
2, 5, 1, 4, 1, 1, 3, 3, 4, 3, 1, 1, 1, 5, 1, 5, # 0x80
5, 1, 1, 1, 1, 3, 1, 1, 4, 1, 1, 1, 1, 5, 1, 1, # 0x90
1, 0, 2, 2, 3, 2, 4, 2, 4, 2, 2, 0, 3, 1, 1, 4, # 0xa0
2, 2, 3, 3, 4, 3, 3, 2, 4, 4, 4, 0, 3, 3, 3, 0, # 0xb0
0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0xc0
1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, # 0xd0
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 0xe0
1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, # 0xf0
)
# Pre-cache the Unicode data saying which of these first 256 characters are
# letters. We'll need it often.
SINGLE_BYTE_LETTERS = [
unicodedata.category(unichr(i)).startswith('L')
for i in xrange(256)
]
# A table telling us how to interpret the first word of a letter's Unicode
# name. The number indicates how frequently we expect this script to be used
# on computers. Many scripts not included here are assumed to have a frequency
# of"0" -- if you're going to write in Linear B using Unicode, you're
# probably aware enough of encoding issues to get it right.
#
# The lowercase name is a general category -- for example, Han characters and
# Hiragana characters are very frequently adjacent in Japanese, so they all go
# into category 'cjk'. Letters of different categories are assumed not to
# appear next to each other often.
SCRIPT_TABLE = {
'LATIN': (3, 'latin'),
'CJK': (2, 'cjk'),
'ARABIC': (2, 'arabic'),
'CYRILLIC': (2, 'cyrillic'),
'GREEK': (2, 'greek'),
'HEBREW': (2, 'hebrew'),
'KATAKANA': (2, 'cjk'),
'HIRAGANA': (2, 'cjk'),
'HIRAGANA-KATAKANA': (2, 'cjk'),
'HANGUL': (2, 'cjk'),
'DEVANAGARI': (2, 'devanagari'),
'THAI': (2, 'thai'),
'FULLWIDTH': (2, 'cjk'),
'MODIFIER': (2, None),
'HALFWIDTH': (1, 'cjk'),
'BENGALI': (1, 'bengali'),
'LAO': (1, 'lao'),
'KHMER': (1, 'khmer'),
'TELUGU': (1, 'telugu'),
'MALAYALAM': (1, 'malayalam'),
'SINHALA': (1, 'sinhala'),
'TAMIL': (1, 'tamil'),
'GEORGIAN': (1, 'georgian'),
'ARMENIAN': (1, 'armenian'),
'KANNADA': (1, 'kannada'), # mostly used for looks of disapproval
'MASCULINE': (1, 'latin'),
'FEMININE': (1, 'latin')
}Then you just call the method:
2
3
>> u'a\u3042\xe4'