14
14
# You should have received a copy of the GNU General Public License
15
15
# along with this program; if not, write to the Free Software
16
16
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
18
from __future__ import absolute_import
20
from bzrlib.errors import (
20
32
binary_files_re = 'Binary files (.*) and (.*) differ\n'
23
class BinaryFiles(Exception):
25
def __init__(self, orig_name, mod_name):
26
self.orig_name = orig_name
27
self.mod_name = mod_name
28
Exception.__init__(self, 'Binary files section encountered.')
31
class PatchSyntax(Exception):
32
def __init__(self, msg):
33
Exception.__init__(self, msg)
36
class MalformedPatchHeader(PatchSyntax):
37
def __init__(self, desc, line):
40
msg = "Malformed patch header. %s\n%r" % (self.desc, self.line)
41
PatchSyntax.__init__(self, msg)
44
class MalformedHunkHeader(PatchSyntax):
45
def __init__(self, desc, line):
48
msg = "Malformed hunk header. %s\n%r" % (self.desc, self.line)
49
PatchSyntax.__init__(self, msg)
52
class MalformedLine(PatchSyntax):
53
def __init__(self, desc, line):
56
msg = "Malformed line. %s\n%s" % (self.desc, self.line)
57
PatchSyntax.__init__(self, msg)
60
class PatchConflict(Exception):
61
def __init__(self, line_no, orig_line, patch_line):
62
orig = orig_line.rstrip('\n')
63
patch = str(patch_line).rstrip('\n')
64
msg = 'Text contents mismatch at line %d. Original has "%s",'\
65
' but patch says it should be "%s"' % (line_no, orig, patch)
66
Exception.__init__(self, msg)
69
35
def get_patch_names(iter_lines):
36
line = iter_lines.next()
71
line = iter_lines.next()
72
38
match = re.match(binary_files_re, line)
73
39
if match is not None:
74
40
raise BinaryFiles(match.group(1), match.group(2))
253
def iter_hunks(iter_lines):
219
def iter_hunks(iter_lines, allow_dirty=False):
221
:arg iter_lines: iterable of lines to parse for hunks
222
:kwarg allow_dirty: If True, when we encounter something that is not
223
a hunk header when we're looking for one, assume the rest of the lines
224
are not part of the patch (comments or other junk). Default False
255
227
for line in iter_lines:
261
233
if hunk is not None:
263
hunk = hunk_from_header(line)
236
hunk = hunk_from_header(line)
237
except MalformedHunkHeader:
239
# If the line isn't a hunk header, then we've reached the end
240
# of this patch and there's "junk" at the end. Ignore the
241
# rest of this patch.
266
246
while orig_size < hunk.orig_range or mod_size < hunk.mod_range:
338
318
if isinstance(line, ContextLine):
342
def parse_patch(iter_lines):
321
def parse_patch(iter_lines, allow_dirty=False):
323
:arg iter_lines: iterable of lines to parse
324
:kwarg allow_dirty: If True, allow the patch to have trailing junk.
343
327
iter_lines = iter_lines_handle_nl(iter_lines)
345
329
(orig_name, mod_name) = get_patch_names(iter_lines)
347
331
return BinaryPatch(e.orig_name, e.mod_name)
349
333
patch = Patch(orig_name, mod_name)
350
for hunk in iter_hunks(iter_lines):
334
for hunk in iter_hunks(iter_lines, allow_dirty):
351
335
patch.hunks.append(hunk)
355
def iter_file_patch(iter_lines):
339
def iter_file_patch(iter_lines, allow_dirty=False, keep_dirty=False):
341
:arg iter_lines: iterable of lines to parse for patches
342
:kwarg allow_dirty: If True, allow comments and other non-patch text
343
before the first patch. Note that the algorithm here can only find
344
such text before any patches have been found. Comments after the
345
first patch are stripped away in iter_hunks() if it is also passed
346
allow_dirty=True. Default False.
348
### FIXME: Docstring is not quite true. We allow certain comments no
349
# matter what, If they startwith '===', '***', or '#' Someone should
350
# reexamine this logic and decide if we should include those in
351
# allow_dirty or restrict those to only being before the patch is found
352
# (as allow_dirty does).
356
353
regex = re.compile(binary_files_re)
359
359
for line in iter_lines:
360
if line.startswith('=== ') or line.startswith('*** '):
360
if line.startswith('=== '):
361
dirty_head.append(line)
363
if line.startswith('*** '):
362
365
if line.startswith('#'):
365
368
if line.startswith('-') or line.startswith(' '):
367
370
elif line.startswith('--- ') or regex.match(line):
368
if len(saved_lines) > 0:
371
if allow_dirty and beginning:
372
# Patches can have "junk" at the beginning
373
# Stripping junk from the end of patches is handled when we
376
elif len(saved_lines) > 0:
377
if keep_dirty and len(dirty_head) > 0:
378
yield {'saved_lines': saved_lines,
379
'dirty_head': dirty_head}
371
384
elif line.startswith('@@'):
372
385
hunk = hunk_from_header(line)
373
386
orig_range = hunk.orig_range
374
387
saved_lines.append(line)
375
388
if len(saved_lines) > 0:
389
if keep_dirty and len(dirty_head) > 0:
390
yield {'saved_lines': saved_lines,
391
'dirty_head': dirty_head}
379
396
def iter_lines_handle_nl(iter_lines):
400
def parse_patches(iter_lines):
401
return [parse_patch(f.__iter__()) for f in iter_file_patch(iter_lines)]
417
def parse_patches(iter_lines, allow_dirty=False, keep_dirty=False):
419
:arg iter_lines: iterable of lines to parse for patches
420
:kwarg allow_dirty: If True, allow text that's not part of the patch at
421
selected places. This includes comments before and after a patch
422
for instance. Default False.
423
:kwarg keep_dirty: If True, returns a dict of patches with dirty headers.
427
for patch_lines in iter_file_patch(iter_lines, allow_dirty, keep_dirty):
428
if 'dirty_head' in patch_lines:
429
patches.append({'patch': parse_patch(
430
patch_lines['saved_lines'], allow_dirty),
431
'dirty_head': patch_lines['dirty_head']})
433
patches.append(parse_patch(patch_lines, allow_dirty))
404
437
def difference_index(atext, btext):
added
removed
bzrlib/patches.py
