1
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
|
#
# Cython -- encoding related tools
#
import re
import sys
if sys.version_info[0] >= 3:
_str, _bytes = str, bytes
else:
_str, _bytes = unicode, str
empty_bytes = _bytes()
empty_str = _str()
join_bytes = empty_bytes.join
class UnicodeLiteralBuilder(object):
"""Assemble a unicode string.
"""
def __init__(self):
self.chars = []
def append(self, characters):
if isinstance(characters, _bytes):
# this came from a Py2 string literal in the parser code
characters = characters.decode("ASCII")
assert isinstance(characters, _str), str(type(characters))
self.chars.append(characters)
def append_charval(self, char_number):
self.chars.append( unichr(char_number) )
def getstring(self):
return EncodedString(u''.join(self.chars))
class BytesLiteralBuilder(object):
"""Assemble a byte string or char value.
"""
def __init__(self, target_encoding):
self.chars = []
self.target_encoding = target_encoding
def append(self, characters):
if isinstance(characters, _str):
characters = characters.encode(self.target_encoding)
assert isinstance(characters, _bytes), str(type(characters))
self.chars.append(characters)
def append_charval(self, char_number):
self.chars.append( chr(char_number).encode('ISO-8859-1') )
def getstring(self):
# this *must* return a byte string! => fix it in Py3k!!
s = BytesLiteral(join_bytes(self.chars))
s.encoding = self.target_encoding
return s
def getchar(self):
# this *must* return a byte string! => fix it in Py3k!!
return self.getstring()
class EncodedString(_str):
# unicode string subclass to keep track of the original encoding.
# 'encoding' is None for unicode strings and the source encoding
# otherwise
encoding = None
def byteencode(self):
assert self.encoding is not None
return self.encode(self.encoding)
def utf8encode(self):
assert self.encoding is None
return self.encode("UTF-8")
def is_unicode(self):
return self.encoding is None
is_unicode = property(is_unicode)
class BytesLiteral(_bytes):
# str subclass that is compatible with EncodedString
encoding = None
def byteencode(self):
return _bytes(self)
def utf8encode(self):
assert False, "this is not a unicode string: %r" % self
def __str__(self):
"""Fake-decode the byte string to unicode to support %
formatting of unicode strings.
"""
return self.decode('ISO-8859-1')
is_unicode = False
char_from_escape_sequence = {
r'\a' : u'\a',
r'\b' : u'\b',
r'\f' : u'\f',
r'\n' : u'\n',
r'\r' : u'\r',
r'\t' : u'\t',
r'\v' : u'\v',
}.get
def _to_escape_sequence(s):
if s in '\n\r\t':
return repr(s)[1:-1]
elif s == '"':
return r'\"'
elif s == '\\':
return r'\\'
else:
# within a character sequence, oct passes much better than hex
return ''.join(['\\%03o' % ord(c) for c in s])
_c_special = ('\\', '\0', '\n', '\r', '\t', '??', '"')
_c_special_replacements = [(orig.encode('ASCII'),
_to_escape_sequence(orig).encode('ASCII'))
for orig in _c_special ]
def _build_specials_test():
subexps = []
for special in _c_special:
regexp = ''.join(['[%s]' % c.replace('\\', '\\\\') for c in special])
subexps.append(regexp)
return re.compile('|'.join(subexps).encode('ASCII')).search
_has_specials = _build_specials_test()
def escape_char(c):
c = c.decode('ISO-8859-1')
if c in '\n\r\t\\':
return repr(c)[1:-1]
elif c == "'":
return "\\'"
n = ord(c)
if n < 32 or n > 127:
# hex works well for characters
return "\\x%02X" % n
else:
return c
def escape_byte_string(s):
"""Escape a byte string so that it can be written into C code.
Note that this returns a Unicode string instead which, when
encoded as ISO-8859-1, will result in the correct byte sequence
being written.
"""
if _has_specials(s):
for special, replacement in _c_special_replacements:
s = s.replace(special, replacement)
try:
return s.decode("ASCII") # trial decoding: plain ASCII => done
except UnicodeDecodeError:
pass
if sys.version_info[0] >= 3:
s_new = bytearray()
append, extend = s_new.append, s_new.extend
for b in s:
if b >= 128:
extend(('\\%3o' % b).encode('ASCII'))
else:
append(b)
return s_new.decode('ISO-8859-1')
else:
l = []
append = l.append
for c in s:
o = ord(c)
if o >= 128:
append('\\%3o' % o)
else:
append(c)
return join_bytes(l).decode('ISO-8859-1')
def split_docstring(s):
if len(s) < 2047:
return s
return '\\n\"\"'.join(s.split(r'\n'))
|
