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
17
from __future__ import absolute_import
19
# \subsection{\emph{rio} - simple text metaformat}
21
# \emph{r} stands for `restricted', `reproducible', or `rfc822-like'.
23
# The stored data consists of a series of \emph{stanzas}, each of which contains
24
# \emph{fields} identified by an ascii name, with Unicode or string contents.
25
# The field tag is constrained to alphanumeric characters.
26
# There may be more than one field in a stanza with the same name.
28
# The format itself does not deal with character encoding issues, though
29
# the result will normally be written in Unicode.
31
# The format is intended to be simple enough that there is exactly one character
32
# stream representation of an object and vice versa, and that this relation
33
# will continue to hold for future versions of bzr.
37
from bzrlib import osutils
38
from bzrlib.iterablefile import IterableFile
40
# XXX: some redundancy is allowing to write stanzas in isolation as well as
41
# through a writer object.
43
class RioWriter(object):
44
def __init__(self, to_file):
46
self._to_file = to_file
48
def write_stanza(self, stanza):
50
self._to_file.write('\n')
51
stanza.write(self._to_file)
55
class RioReader(object):
56
"""Read stanzas from a file as a sequence
58
to_file can be anything that can be enumerated as a sequence of
59
lines (with newlines.)
61
def __init__(self, from_file):
62
self._from_file = from_file
66
s = read_stanza(self._from_file)
73
def rio_file(stanzas, header=None):
74
"""Produce a rio IterableFile from an iterable of stanzas"""
76
if header is not None:
80
if first_stanza is not True:
82
for line in s.to_lines():
85
return IterableFile(str_iter())
88
def read_stanzas(from_file):
90
s = read_stanza(from_file)
97
"""One stanza for rio.
99
Each stanza contains a set of named fields.
101
Names must be non-empty ascii alphanumeric plus _. Names can be repeated
102
within a stanza. Names are case-sensitive. The ordering of fields is
105
Each field value must be either an int or a string.
108
__slots__ = ['items']
110
def __init__(self, **kwargs):
111
"""Construct a new Stanza.
113
The keyword arguments, if any, are added in sorted order to the stanza.
117
for tag, value in sorted(kwargs.items()):
120
def add(self, tag, value):
121
"""Append a name and value to the stanza."""
122
if not valid_tag(tag):
123
raise ValueError("invalid tag %r" % (tag,))
124
if isinstance(value, str):
125
value = unicode(value)
126
elif isinstance(value, unicode):
128
## elif isinstance(value, (int, long)):
129
## value = str(value) # XXX: python2.4 without L-suffix
131
raise TypeError("invalid type for rio value: %r of type %s"
132
% (value, type(value)))
133
self.items.append((tag, value))
136
def from_pairs(cls, pairs):
141
def __contains__(self, find_tag):
142
"""True if there is any field in this stanza with the given tag."""
143
for tag, value in self.items:
149
"""Return number of pairs in the stanza."""
150
return len(self.items)
152
def __eq__(self, other):
153
if not isinstance(other, Stanza):
155
return self.items == other.items
157
def __ne__(self, other):
158
return not self.__eq__(other)
161
return "Stanza(%r)" % self.items
163
def iter_pairs(self):
164
"""Return iterator of tag, value pairs."""
165
return iter(self.items)
168
"""Generate sequence of lines for external version of this file.
170
The lines are always utf-8 encoded strings.
173
# max() complains if sequence is empty
176
for tag, value in self.items:
178
result.append(tag + ': \n')
180
# don't want splitlines behaviour on empty lines
181
val_lines = value.split('\n')
182
result.append(tag + ': ' + val_lines[0].encode('utf-8') + '\n')
183
for line in val_lines[1:]:
184
result.append('\t' + line.encode('utf-8') + '\n')
186
result.append(tag + ': ' + value.encode('utf-8') + '\n')
190
"""Return stanza as a single string"""
191
return ''.join(self.to_lines())
193
def to_unicode(self):
194
"""Return stanza as a single Unicode string.
196
This is most useful when adding a Stanza to a parent Stanza
202
for tag, value in self.items:
204
result.append(tag + u': \n')
206
# don't want splitlines behaviour on empty lines
207
val_lines = value.split(u'\n')
208
result.append(tag + u': ' + val_lines[0] + u'\n')
209
for line in val_lines[1:]:
210
result.append(u'\t' + line + u'\n')
212
result.append(tag + u': ' + value + u'\n')
213
return u''.join(result)
215
def write(self, to_file):
216
"""Write stanza to a file"""
217
to_file.writelines(self.to_lines())
220
"""Return the value for a field wih given tag.
222
If there is more than one value, only the first is returned. If the
223
tag is not present, KeyError is raised.
225
for t, v in self.items:
233
def get_all(self, tag):
235
for t, v in self.items:
241
"""Return a dict containing the unique values of the stanza.
244
for tag, value in self.items:
250
return _valid_tag(tag)
253
def read_stanza(line_iter):
254
"""Return new Stanza read from list of lines or a file
256
Returns one Stanza that was read, or returns None at end of file. If a
257
blank line follows the stanza, it is consumed. It's not an error for
258
there to be no blank at end of file. If there is a blank file at the
259
start of the input this is really an empty stanza and that is returned.
261
Only the stanza lines and the trailing blank (if any) are consumed
264
The raw lines must be in utf-8 encoding.
266
return _read_stanza_utf8(line_iter)
269
def read_stanza_unicode(unicode_iter):
270
"""Read a Stanza from a list of lines or a file.
272
The lines should already be in unicode form. This returns a single
273
stanza that was read. If there is a blank line at the end of the Stanza,
274
it is consumed. It is not an error for there to be no blank line at
275
the end of the iterable. If there is a blank line at the beginning,
276
this is treated as an empty Stanza and None is returned.
278
Only the stanza lines and the trailing blank (if any) are consumed
279
from the unicode_iter
281
:param unicode_iter: A iterable, yeilding Unicode strings. See read_stanza
282
if you have a utf-8 encoded string.
283
:return: A Stanza object if there are any lines in the file.
286
return _read_stanza_unicode(unicode_iter)
289
def to_patch_lines(stanza, max_width=72):
290
"""Convert a stanza into RIO-Patch format lines.
292
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
293
It resists common forms of damage such as newline conversion or the removal
294
of trailing whitespace, yet is also reasonably easy to read.
296
:param max_width: The maximum number of characters per physical line.
297
:return: a list of lines
300
raise ValueError(max_width)
301
max_rio_width = max_width - 4
303
for pline in stanza.to_lines():
304
for line in pline.split('\n')[:-1]:
305
line = re.sub('\\\\', '\\\\\\\\', line)
307
partline = line[:max_rio_width]
308
line = line[max_rio_width:]
309
if len(line) > 0 and line[0] != [' ']:
311
break_index = partline.rfind(' ', -20)
313
break_index = partline.rfind('-', -20)
316
break_index = partline.rfind('/', -20)
318
line = partline[break_index:] + line
319
partline = partline[:break_index]
322
partline = re.sub('\r', '\\\\r', partline)
326
elif re.search(' $', partline):
329
lines.append('# ' + partline + '\n')
335
def _patch_stanza_iter(line_iter):
340
return map[match.group(0)]
343
for line in line_iter:
344
if line.startswith('# '):
346
elif line.startswith('#'):
349
raise ValueError("bad line %r" % (line,))
350
if last_line is not None and len(line) > 2:
352
line = re.sub('\r', '', line)
353
line = re.sub('\\\\(.|\n)', mapget, line)
354
if last_line is None:
358
if last_line[-1] == '\n':
361
if last_line is not None:
365
def read_patch_stanza(line_iter):
366
"""Convert an iterable of RIO-Patch format lines into a Stanza.
368
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
369
It resists common forms of damage such as newline conversion or the removal
370
of trailing whitespace, yet is also reasonably easy to read.
374
return read_stanza(_patch_stanza_iter(line_iter))
378
from bzrlib._rio_pyx import (
380
_read_stanza_unicode,
383
except ImportError, e:
384
osutils.failed_to_load_extension(e)
385
from bzrlib._rio_py import (
387
_read_stanza_unicode,