1
# Copyright (C) 2005 by Canonical Ltd
3
# Distributed under the GNU General Public Licence v2
1
# Copyright (C) 2005 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
5
17
# \subsection{\emph{rio} - simple text metaformat}
7
19
# \emph{r} stands for `restricted', `reproducible', or `rfc822-like'.
9
21
# The stored data consists of a series of \emph{stanzas}, each of which contains
10
22
# \emph{fields} identified by an ascii name, with Unicode or string contents.
11
# The field tag is constrained to alphanumeric characters.
23
# The field tag is constrained to alphanumeric characters.
12
24
# There may be more than one field in a stanza with the same name.
14
26
# The format itself does not deal with character encoding issues, though
15
27
# the result will normally be written in Unicode.
17
29
# The format is intended to be simple enough that there is exactly one character
18
30
# stream representation of an object and vice versa, and that this relation
19
31
# will continue to hold for future versions of bzr.
171
187
"""Return stanza as a single string"""
172
188
return ''.join(self.to_lines())
190
def to_unicode(self):
191
"""Return stanza as a single Unicode string.
193
This is most useful when adding a Stanza to a parent Stanza
199
for tag, value in self.items:
201
result.append(tag + u': \n')
203
# don't want splitlines behaviour on empty lines
204
val_lines = value.split(u'\n')
205
result.append(tag + u': ' + val_lines[0] + u'\n')
206
for line in val_lines[1:]:
207
result.append(u'\t' + line + u'\n')
209
result.append(tag + u': ' + value + u'\n')
210
return u''.join(result)
174
212
def write(self, to_file):
175
213
"""Write stanza to a file"""
176
214
to_file.writelines(self.to_lines())
203
241
for tag, value in self.items:
208
_tag_re = re.compile(r'^[-a-zA-Z0-9_]+$')
209
246
def valid_tag(tag):
210
return bool(_tag_re.match(tag))
247
return _valid_tag(tag)
213
250
def read_stanza(line_iter):
214
251
"""Return new Stanza read from list of lines or a file
216
253
Returns one Stanza that was read, or returns None at end of file. If a
217
254
blank line follows the stanza, it is consumed. It's not an error for
218
255
there to be no blank at end of file. If there is a blank file at the
219
start of the input this is really an empty stanza and that is returned.
256
start of the input this is really an empty stanza and that is returned.
221
258
Only the stanza lines and the trailing blank (if any) are consumed
222
259
from the line_iter.
224
261
The raw lines must be in utf-8 encoding.
263
return _read_stanza_utf8(line_iter)
266
def read_stanza_unicode(unicode_iter):
267
"""Read a Stanza from a list of lines or a file.
269
The lines should already be in unicode form. This returns a single
270
stanza that was read. If there is a blank line at the end of the Stanza,
271
it is consumed. It is not an error for there to be no blank line at
272
the end of the iterable. If there is a blank line at the beginning,
273
this is treated as an empty Stanza and None is returned.
275
Only the stanza lines and the trailing blank (if any) are consumed
276
from the unicode_iter
278
:param unicode_iter: A iterable, yeilding Unicode strings. See read_stanza
279
if you have a utf-8 encoded string.
280
:return: A Stanza object if there are any lines in the file.
283
return _read_stanza_unicode(unicode_iter)
286
def to_patch_lines(stanza, max_width=72):
287
"""Convert a stanza into RIO-Patch format lines.
289
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
290
It resists common forms of damage such as newline conversion or the removal
291
of trailing whitespace, yet is also reasonably easy to read.
293
:param max_width: The maximum number of characters per physical line.
294
:return: a list of lines
297
raise ValueError(max_width)
298
max_rio_width = max_width - 4
300
for pline in stanza.to_lines():
301
for line in pline.split('\n')[:-1]:
302
line = re.sub('\\\\', '\\\\\\\\', line)
304
partline = line[:max_rio_width]
305
line = line[max_rio_width:]
306
if len(line) > 0 and line[0] != [' ']:
308
break_index = partline.rfind(' ', -20)
310
break_index = partline.rfind('-', -20)
313
break_index = partline.rfind('/', -20)
315
line = partline[break_index:] + line
316
partline = partline[:break_index]
319
partline = re.sub('\r', '\\\\r', partline)
323
elif re.search(' $', partline):
326
lines.append('# ' + partline + '\n')
332
def _patch_stanza_iter(line_iter):
337
return map[match.group(0)]
230
340
for line in line_iter:
231
if line == None or line == '':
234
break # end of stanza
235
line = line.decode('utf-8')
236
assert line[-1] == '\n'
238
if line[0] == '\t': # continues previous value
240
raise ValueError('invalid continuation line %r' % real_l)
241
accum_value += '\n' + line[1:-1]
242
else: # new tag:value line
244
stanza.add(tag, accum_value)
246
colon_index = line.index(': ')
248
raise ValueError('tag/value separator not found in line %r' % real_l)
249
tag = str(line[:colon_index])
250
assert valid_tag(tag), \
251
"invalid rio tag %r" % tag
252
accum_value = line[colon_index+2:-1]
253
if tag is not None: # add last tag-value
254
stanza.add(tag, accum_value)
256
else: # didn't see any content
341
if line.startswith('# '):
343
elif line.startswith('#'):
346
raise ValueError("bad line %r" % (line,))
347
if last_line is not None and len(line) > 2:
349
line = re.sub('\r', '', line)
350
line = re.sub('\\\\(.|\n)', mapget, line)
351
if last_line is None:
355
if last_line[-1] == '\n':
358
if last_line is not None:
362
def read_patch_stanza(line_iter):
363
"""Convert an iterable of RIO-Patch format lines into a Stanza.
365
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
366
It resists common forms of damage such as newline conversion or the removal
367
of trailing whitespace, yet is also reasonably easy to read.
371
return read_stanza(_patch_stanza_iter(line_iter))
375
from bzrlib._rio_pyx import (
377
_read_stanza_unicode,
381
from bzrlib._rio_py import (
383
_read_stanza_unicode,