« back to all changes in this revision
Viewing changes to bzrlib/_rio_pyx.pyx
- browse files at revision 4368
- compare with another revision
- compare with revision 5449
- download diff
- download tarball
- view history from revision 4368
- Committer: Canonical.com Patch Queue Manager
- Date: 2009-05-15 01:21:40 UTC
- mfrom: (4354.3.18 rio-c)
- Revision ID: pqm@pqm.ubuntu.com-20090515012140-stwx16f974x0zogp
(Jelmer) Add Pyrex RIO implementation.
- files added:
- bzrlib/_rio_py.py
- files modified:
- .bzrignore
added
removed
bzrlib/_rio_pyx.pyx
1
# Copyright (C) 2009 Canonical Ltd
2
#
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
7
#
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
12
#
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
16
17
"""Pyrex implementation of _read_stanza_*."""
18
19
#python2.4 support
20
cdef extern from "python-compat.h":
21
pass
22
23
cdef extern from "malloc.h":
24
void *malloc(int)
25
void *realloc(void *, int)
26
void free(void *)
27
28
cdef extern from "Python.h":
29
ctypedef int Py_ssize_t # Required for older pyrex versions
30
ctypedef int Py_UNICODE
31
char *PyString_AS_STRING(object s)
32
Py_ssize_t PyString_GET_SIZE(object t) except -1
33
object PyUnicode_DecodeUTF8(char *string, Py_ssize_t length, char *errors)
34
object PyString_FromStringAndSize(char *s, Py_ssize_t len)
35
int PyString_CheckExact(object)
36
int PyUnicode_CheckExact(object)
37
object PyUnicode_Join(object, object)
38
object PyUnicode_EncodeASCII(Py_UNICODE *, int, char *)
39
Py_UNICODE *PyUnicode_AS_UNICODE(object)
40
Py_UNICODE *PyUnicode_AsUnicode(object)
41
Py_ssize_t PyUnicode_GET_SIZE(object) except -1
42
int PyList_Append(object, object) except -1
43
int Py_UNICODE_ISLINEBREAK(Py_UNICODE)
44
object PyUnicode_FromUnicode(Py_UNICODE *, int)
45
void *Py_UNICODE_COPY(Py_UNICODE *, Py_UNICODE *, int)
46
47
cdef extern from "string.h":
48
void *memcpy(void *, void *, int)
49
50
from bzrlib.rio import Stanza
51
52
cdef int _valid_tag_char(char c):
53
return (c == c'_' or c == c'-' or
54
(c >= c'a' and c <= c'z') or
55
(c >= c'A' and c <= c'Z') or
56
(c >= c'0' and c <= c'9'))
57
58
59
def _valid_tag(tag):
60
cdef char *c_tag
61
cdef Py_ssize_t c_len
62
cdef int i
63
if not PyString_CheckExact(tag):
64
raise TypeError(tag)
65
c_tag = PyString_AS_STRING(tag)
66
c_len = PyString_GET_SIZE(tag)
67
if c_len < 1:
68
return False
69
for i from 0 <= i < c_len:
70
if not _valid_tag_char(c_tag[i]):
71
return False
72
return True
73
74
75
cdef object _split_first_line_utf8(char *line, int len,
76
char *value, Py_ssize_t *value_len):
77
cdef int i
78
for i from 0 <= i < len:
79
if line[i] == c':':
80
if line[i+1] != c' ':
81
raise ValueError("invalid tag in line %r" % line)
82
memcpy(value, line+i+2, len-i-2)
83
value_len[0] = len-i-2
84
return PyString_FromStringAndSize(line, i)
85
raise ValueError('tag/value separator not found in line %r' % line)
86
87
88
cdef object _split_first_line_unicode(Py_UNICODE *line, int len,
89
Py_UNICODE *value, Py_ssize_t *value_len):
90
cdef int i
91
for i from 0 <= i < len:
92
if line[i] == c':':
93
if line[i+1] != c' ':
94
raise ValueError("invalid tag in line %r" %
95
PyUnicode_FromUnicode(line, len))
96
memcpy(value, &line[i+2], (len-i-2) * sizeof(Py_UNICODE))
97
value_len[0] = len-i-2
98
return PyUnicode_EncodeASCII(line, i, "strict")
99
raise ValueError("tag/value separator not found in line %r" %
100
PyUnicode_FromUnicode(line, len))
101
102
103
def _read_stanza_utf8(line_iter):
104
cdef char *c_line
105
cdef Py_ssize_t c_len
106
cdef char *accum_value, *new_accum_value
107
cdef Py_ssize_t accum_len, accum_size
108
pairs = []
109
tag = None
110
accum_len = 0
111
accum_size = 4096
112
accum_value = <char *>malloc(accum_size)
113
if accum_value == NULL:
114
raise MemoryError
115
try:
116
for line in line_iter:
117
if line is None:
118
break # end of file
119
if not PyString_CheckExact(line):
120
raise TypeError("%r is not a plain string" % line)
121
c_line = PyString_AS_STRING(line)
122
c_len = PyString_GET_SIZE(line)
123
if c_len < 1:
124
break # end of file
125
if c_len == 1 and c_line[0] == c"\n":
126
break # end of stanza
127
if accum_len + c_len > accum_size:
128
accum_size = (accum_len + c_len)
129
new_accum_value = <char *>realloc(accum_value, accum_size)
130
if new_accum_value == NULL:
131
raise MemoryError
132
else:
133
accum_value = new_accum_value
134
if c_line[0] == c'\t': # continues previous value
135
if tag is None:
136
raise ValueError('invalid continuation line %r' % line)
137
memcpy(accum_value+accum_len, c_line+1, c_len-1)
138
accum_len = accum_len + c_len-1
139
else: # new tag:value line
140
if tag is not None:
141
PyList_Append(pairs,
142
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1,
143
"strict")))
144
tag = _split_first_line_utf8(c_line, c_len, accum_value,
145
&accum_len)
146
if not _valid_tag(tag):
147
raise ValueError("invalid rio tag %r" % (tag,))
148
if tag is not None: # add last tag-value
149
PyList_Append(pairs,
150
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1, "strict")))
151
return Stanza.from_pairs(pairs)
152
else: # didn't see any content
153
return None
154
finally:
155
free(accum_value)
156
157
158
def _read_stanza_unicode(unicode_iter):
159
cdef Py_UNICODE *c_line
160
cdef int c_len
161
cdef Py_UNICODE *accum_value, *new_accum_value
162
cdef Py_ssize_t accum_len, accum_size
163
pairs = []
164
tag = None
165
accum_len = 0
166
accum_size = 4096
167
accum_value = <Py_UNICODE *>malloc(accum_size*sizeof(Py_UNICODE))
168
if accum_value == NULL:
169
raise MemoryError
170
try:
171
for line in unicode_iter:
172
if line is None:
173
break # end of file
174
if not PyUnicode_CheckExact(line):
175
raise TypeError("%r is not a unicode string" % line)
176
c_line = PyUnicode_AS_UNICODE(line)
177
c_len = PyUnicode_GET_SIZE(line)
178
if c_len < 1:
179
break # end of file
180
if Py_UNICODE_ISLINEBREAK(c_line[0]):
181
break # end of stanza
182
if accum_len + c_len > accum_size:
183
accum_size = accum_len + c_len
184
new_accum_value = <Py_UNICODE *>realloc(accum_value,
185
accum_size*sizeof(Py_UNICODE))
186
if new_accum_value == NULL:
187
raise MemoryError
188
else:
189
accum_value = new_accum_value
190
if c_line[0] == c'\t': # continues previous value,
191
if tag is None:
192
raise ValueError('invalid continuation line %r' % line)
193
memcpy(&accum_value[accum_len], &c_line[1],
194
(c_len-1)*sizeof(Py_UNICODE))
195
accum_len = accum_len + (c_len-1)
196
else: # new tag:value line
197
if tag is not None:
198
PyList_Append(pairs,
199
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
200
tag = _split_first_line_unicode(c_line, c_len, accum_value,
201
&accum_len)
202
if not _valid_tag(tag):
203
raise ValueError("invalid rio tag %r" % (tag,))
204
if tag is not None: # add last tag-value
205
PyList_Append(pairs,
206
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
207
return Stanza.from_pairs(pairs)
208
else: # didn't see any content
209
return None
210
finally:
211
free(accum_value)
Loggerhead is a web-based interface for Breezy
Version: 2.0.1