1
# Copyright (C) 2009, 2010 Canonical Ltd
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.
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.
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
17
"""Pyrex implementation of _read_stanza_*."""
20
cdef extern from "python-compat.h":
23
cdef extern from "stdlib.h":
25
void *realloc(void *, int)
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)
47
cdef extern from "string.h":
48
void *memcpy(void *, void *, int)
50
from bzrlib.rio import Stanza
52
cdef int _valid_tag_char(char c): # cannot_raise
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'))
63
if not PyString_CheckExact(tag):
65
c_tag = PyString_AS_STRING(tag)
66
c_len = PyString_GET_SIZE(tag)
69
for i from 0 <= i < c_len:
70
if not _valid_tag_char(c_tag[i]):
75
cdef object _split_first_line_utf8(char *line, int len,
76
char *value, Py_ssize_t *value_len):
78
for i from 0 <= i < len:
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)
88
cdef object _split_first_line_unicode(Py_UNICODE *line, int len,
89
Py_UNICODE *value, Py_ssize_t *value_len):
91
for i from 0 <= i < len:
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))
103
def _read_stanza_utf8(line_iter):
105
cdef Py_ssize_t c_len
106
cdef char *accum_value, *new_accum_value
107
cdef Py_ssize_t accum_len, accum_size
112
accum_value = <char *>malloc(accum_size)
113
if accum_value == NULL:
116
for line in line_iter:
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)
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:
133
accum_value = new_accum_value
134
if c_line[0] == c'\t': # continues previous value
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
142
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1,
144
tag = _split_first_line_utf8(c_line, c_len, accum_value,
146
if not _valid_tag(tag):
147
raise ValueError("invalid rio tag %r" % (tag,))
148
if tag is not None: # add last tag-value
150
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1, "strict")))
151
return Stanza.from_pairs(pairs)
152
else: # didn't see any content
158
def _read_stanza_unicode(unicode_iter):
159
cdef Py_UNICODE *c_line
161
cdef Py_UNICODE *accum_value, *new_accum_value
162
cdef Py_ssize_t accum_len, accum_size
167
accum_value = <Py_UNICODE *>malloc(accum_size*sizeof(Py_UNICODE))
168
if accum_value == NULL:
171
for line in unicode_iter:
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)
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:
189
accum_value = new_accum_value
190
if c_line[0] == c'\t': # continues previous value,
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
199
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
200
tag = _split_first_line_unicode(c_line, c_len, accum_value,
202
if not _valid_tag(tag):
203
raise ValueError("invalid rio tag %r" % (tag,))
204
if tag is not None: # add last tag-value
206
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
207
return Stanza.from_pairs(pairs)
208
else: # didn't see any content