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.
38
from .iterablefile import IterableFile
43
# XXX: some redundancy is allowing to write stanzas in isolation as well as
44
# through a writer object.
46
class RioWriter(object):
48
def __init__(self, to_file):
50
self._to_file = to_file
52
def write_stanza(self, stanza):
54
self._to_file.write(b'\n')
55
stanza.write(self._to_file)
59
class RioReader(object):
60
"""Read stanzas from a file as a sequence
62
to_file can be anything that can be enumerated as a sequence of
63
lines (with newlines.)
65
def __init__(self, from_file):
66
self._from_file = from_file
70
s = read_stanza(self._from_file)
77
def rio_file(stanzas, header=None):
78
"""Produce a rio IterableFile from an iterable of stanzas"""
80
if header is not None:
84
if first_stanza is not True:
86
for line in s.to_lines():
89
return IterableFile(str_iter())
92
def read_stanzas(from_file):
95
s = read_stanza(from_file)
101
def read_stanzas_unicode(from_file):
104
s = read_stanza_unicode(from_file)
110
class Stanza(object):
111
"""One stanza for rio.
113
Each stanza contains a set of named fields.
115
Names must be non-empty ascii alphanumeric plus _. Names can be repeated
116
within a stanza. Names are case-sensitive. The ordering of fields is
119
Each field value must be either an int or a string.
122
__slots__ = ['items']
124
def __init__(self, **kwargs):
125
"""Construct a new Stanza.
127
The keyword arguments, if any, are added in sorted order to the stanza.
131
for tag, value in sorted(kwargs.items()):
134
def add(self, tag, value):
135
"""Append a name and value to the stanza."""
136
if not valid_tag(tag):
137
raise ValueError("invalid tag %r" % (tag,))
138
if isinstance(value, bytes):
139
value = value.decode('ascii')
140
elif isinstance(value, text_type):
143
raise TypeError("invalid type for rio value: %r of type %s"
144
% (value, type(value)))
145
self.items.append((tag, value))
148
def from_pairs(cls, pairs):
153
def __contains__(self, find_tag):
154
"""True if there is any field in this stanza with the given tag."""
155
for tag, value in self.items:
161
"""Return number of pairs in the stanza."""
162
return len(self.items)
164
def __eq__(self, other):
165
if not isinstance(other, Stanza):
167
return self.items == other.items
169
def __ne__(self, other):
170
return not self.__eq__(other)
173
return "Stanza(%r)" % self.items
175
def iter_pairs(self):
176
"""Return iterator of tag, value pairs."""
177
return iter(self.items)
180
"""Generate sequence of lines for external version of this file.
182
The lines are always utf-8 encoded strings.
185
# max() complains if sequence is empty
188
for text_tag, text_value in self.items:
189
tag = text_tag.encode('ascii')
190
value = text_value.encode('utf-8')
192
result.append(tag + b': \n')
194
# don't want splitlines behaviour on empty lines
195
val_lines = value.split(b'\n')
196
result.append(tag + b': ' + val_lines[0] + b'\n')
197
for line in val_lines[1:]:
198
result.append(b'\t' + line + b'\n')
200
result.append(tag + b': ' + value + b'\n')
204
"""Return stanza as a single string"""
205
return b''.join(self.to_lines())
207
def to_unicode(self):
208
"""Return stanza as a single Unicode string.
210
This is most useful when adding a Stanza to a parent Stanza
216
for tag, value in self.items:
218
result.append(tag + u': \n')
220
# don't want splitlines behaviour on empty lines
221
val_lines = value.split(u'\n')
222
result.append(tag + u': ' + val_lines[0] + u'\n')
223
for line in val_lines[1:]:
224
result.append(u'\t' + line + u'\n')
226
result.append(tag + u': ' + value + u'\n')
227
return u''.join(result)
229
def write(self, to_file):
230
"""Write stanza to a file"""
231
to_file.writelines(self.to_lines())
234
"""Return the value for a field wih given tag.
236
If there is more than one value, only the first is returned. If the
237
tag is not present, KeyError is raised.
239
for t, v in self.items:
247
def get_all(self, tag):
249
for t, v in self.items:
255
"""Return a dict containing the unique values of the stanza.
258
for tag, value in self.items:
264
return _valid_tag(tag)
267
def read_stanza(line_iter):
268
"""Return new Stanza read from list of lines or a file
270
Returns one Stanza that was read, or returns None at end of file. If a
271
blank line follows the stanza, it is consumed. It's not an error for
272
there to be no blank at end of file. If there is a blank file at the
273
start of the input this is really an empty stanza and that is returned.
275
Only the stanza lines and the trailing blank (if any) are consumed
278
The raw lines must be in utf-8 encoding.
280
return _read_stanza_utf8(line_iter)
283
def read_stanza_unicode(unicode_iter):
284
"""Read a Stanza from a list of lines or a file.
286
The lines should already be in unicode form. This returns a single
287
stanza that was read. If there is a blank line at the end of the Stanza,
288
it is consumed. It is not an error for there to be no blank line at
289
the end of the iterable. If there is a blank line at the beginning,
290
this is treated as an empty Stanza and None is returned.
292
Only the stanza lines and the trailing blank (if any) are consumed
293
from the unicode_iter
295
:param unicode_iter: A iterable, yeilding Unicode strings. See read_stanza
296
if you have a utf-8 encoded string.
297
:return: A Stanza object if there are any lines in the file.
300
return _read_stanza_unicode(unicode_iter)
303
def to_patch_lines(stanza, max_width=72):
304
"""Convert a stanza into RIO-Patch format lines.
306
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
307
It resists common forms of damage such as newline conversion or the removal
308
of trailing whitespace, yet is also reasonably easy to read.
310
:param max_width: The maximum number of characters per physical line.
311
:return: a list of lines
314
raise ValueError(max_width)
315
max_rio_width = max_width - 4
317
for pline in stanza.to_lines():
318
for line in pline.split(b'\n')[:-1]:
319
line = re.sub(b'\\\\', b'\\\\\\\\', line)
321
partline = line[:max_rio_width]
322
line = line[max_rio_width:]
323
if len(line) > 0 and line[:1] != [b' ']:
325
break_index = partline.rfind(b' ', -20)
327
break_index = partline.rfind(b'-', -20)
330
break_index = partline.rfind(b'/', -20)
332
line = partline[break_index:] + line
333
partline = partline[:break_index]
336
partline = re.sub(b'\r', b'\\\\r', partline)
340
elif re.search(b' $', partline):
343
lines.append(b'# ' + partline + b'\n')
345
lines.append(b'# \n')
349
def _patch_stanza_iter(line_iter):
350
map = {b'\\\\': b'\\',
354
return map[match.group(0)]
357
for line in line_iter:
358
if line.startswith(b'# '):
360
elif line.startswith(b'#'):
363
raise ValueError("bad line %r" % (line,))
364
if last_line is not None and len(line) > 2:
366
line = re.sub(b'\r', b'', line)
367
line = re.sub(b'\\\\(.|\n)', mapget, line)
368
if last_line is None:
372
if last_line[-1:] == b'\n':
375
if last_line is not None:
379
def read_patch_stanza(line_iter):
380
"""Convert an iterable of RIO-Patch format lines into a Stanza.
382
RIO-Patch is a RIO variant designed to be e-mailed as part of a patch.
383
It resists common forms of damage such as newline conversion or the removal
384
of trailing whitespace, yet is also reasonably easy to read.
388
return read_stanza(_patch_stanza_iter(line_iter))
392
from ._rio_pyx import (
394
_read_stanza_unicode,
397
except ImportError as e:
398
osutils.failed_to_load_extension(e)
399
from ._rio_py import (
401
_read_stanza_unicode,