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_*."""
19
from __future__ import absolute_import
22
cdef extern from "python-compat.h":
25
cdef extern from "stdlib.h":
27
void *realloc(void *, int)
30
cdef extern from "Python.h":
31
ctypedef int Py_ssize_t # Required for older pyrex versions
32
ctypedef int Py_UNICODE
33
char *PyString_AS_STRING(object s)
34
Py_ssize_t PyString_GET_SIZE(object t) except -1
35
object PyUnicode_DecodeUTF8(char *string, Py_ssize_t length, char *errors)
36
object PyString_FromStringAndSize(char *s, Py_ssize_t len)
37
int PyString_CheckExact(object)
38
int PyUnicode_CheckExact(object)
39
object PyUnicode_Join(object, object)
40
object PyUnicode_EncodeASCII(Py_UNICODE *, int, char *)
41
Py_UNICODE *PyUnicode_AS_UNICODE(object)
42
Py_UNICODE *PyUnicode_AsUnicode(object)
43
Py_ssize_t PyUnicode_GET_SIZE(object) except -1
44
int PyList_Append(object, object) except -1
45
int Py_UNICODE_ISLINEBREAK(Py_UNICODE)
46
object PyUnicode_FromUnicode(Py_UNICODE *, int)
47
void *Py_UNICODE_COPY(Py_UNICODE *, Py_UNICODE *, int)
49
cdef extern from "string.h":
50
void *memcpy(void *, void *, int)
52
from .rio import Stanza
54
cdef int _valid_tag_char(char c): # cannot_raise
55
return (c == c'_' or c == c'-' or
56
(c >= c'a' and c <= c'z') or
57
(c >= c'A' and c <= c'Z') or
58
(c >= c'0' and c <= c'9'))
65
if not PyString_CheckExact(tag):
67
c_tag = PyString_AS_STRING(tag)
68
c_len = PyString_GET_SIZE(tag)
71
for i from 0 <= i < c_len:
72
if not _valid_tag_char(c_tag[i]):
77
cdef object _split_first_line_utf8(char *line, int len,
78
char *value, Py_ssize_t *value_len):
80
for i from 0 <= i < len:
83
raise ValueError("invalid tag in line %r" % line)
84
memcpy(value, line+i+2, len-i-2)
85
value_len[0] = len-i-2
86
return PyString_FromStringAndSize(line, i)
87
raise ValueError('tag/value separator not found in line %r' % line)
90
cdef object _split_first_line_unicode(Py_UNICODE *line, int len,
91
Py_UNICODE *value, Py_ssize_t *value_len):
93
for i from 0 <= i < len:
96
raise ValueError("invalid tag in line %r" %
97
PyUnicode_FromUnicode(line, len))
98
memcpy(value, &line[i+2], (len-i-2) * sizeof(Py_UNICODE))
99
value_len[0] = len-i-2
100
return PyUnicode_EncodeASCII(line, i, "strict")
101
raise ValueError("tag/value separator not found in line %r" %
102
PyUnicode_FromUnicode(line, len))
105
def _read_stanza_utf8(line_iter):
107
cdef Py_ssize_t c_len
108
cdef char *accum_value, *new_accum_value
109
cdef Py_ssize_t accum_len, accum_size
114
accum_value = <char *>malloc(accum_size)
115
if accum_value == NULL:
118
for line in line_iter:
121
if not PyString_CheckExact(line):
122
raise TypeError("%r is not a plain string" % line)
123
c_line = PyString_AS_STRING(line)
124
c_len = PyString_GET_SIZE(line)
127
if c_len == 1 and c_line[0] == c"\n":
128
break # end of stanza
129
if accum_len + c_len > accum_size:
130
accum_size = (accum_len + c_len)
131
new_accum_value = <char *>realloc(accum_value, accum_size)
132
if new_accum_value == NULL:
135
accum_value = new_accum_value
136
if c_line[0] == c'\t': # continues previous value
138
raise ValueError('invalid continuation line %r' % line)
139
memcpy(accum_value+accum_len, c_line+1, c_len-1)
140
accum_len = accum_len + c_len-1
141
else: # new tag:value line
144
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1,
146
tag = _split_first_line_utf8(c_line, c_len, accum_value,
148
if not _valid_tag(tag):
149
raise ValueError("invalid rio tag %r" % (tag,))
150
if tag is not None: # add last tag-value
152
(tag, PyUnicode_DecodeUTF8(accum_value, accum_len-1, "strict")))
153
return Stanza.from_pairs(pairs)
154
else: # didn't see any content
160
def _read_stanza_unicode(unicode_iter):
161
cdef Py_UNICODE *c_line
163
cdef Py_UNICODE *accum_value, *new_accum_value
164
cdef Py_ssize_t accum_len, accum_size
169
accum_value = <Py_UNICODE *>malloc(accum_size*sizeof(Py_UNICODE))
170
if accum_value == NULL:
173
for line in unicode_iter:
176
if not PyUnicode_CheckExact(line):
177
raise TypeError("%r is not a unicode string" % line)
178
c_line = PyUnicode_AS_UNICODE(line)
179
c_len = PyUnicode_GET_SIZE(line)
182
if Py_UNICODE_ISLINEBREAK(c_line[0]):
183
break # end of stanza
184
if accum_len + c_len > accum_size:
185
accum_size = accum_len + c_len
186
new_accum_value = <Py_UNICODE *>realloc(accum_value,
187
accum_size*sizeof(Py_UNICODE))
188
if new_accum_value == NULL:
191
accum_value = new_accum_value
192
if c_line[0] == c'\t': # continues previous value,
194
raise ValueError('invalid continuation line %r' % line)
195
memcpy(&accum_value[accum_len], &c_line[1],
196
(c_len-1)*sizeof(Py_UNICODE))
197
accum_len = accum_len + (c_len-1)
198
else: # new tag:value line
201
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
202
tag = _split_first_line_unicode(c_line, c_len, accum_value,
204
if not _valid_tag(tag):
205
raise ValueError("invalid rio tag %r" % (tag,))
206
if tag is not None: # add last tag-value
208
(tag, PyUnicode_FromUnicode(accum_value, accum_len-1)))
209
return Stanza.from_pairs(pairs)
210
else: # didn't see any content