1
# Copyright (C) 2005-2010 Aaron Bentley, Canonical Ltd
1
# Copyright (C) 2004 - 2006, 2008 Aaron Bentley, Canonical Ltd
2
2
# <aaron.bentley@utoronto.ca>
4
4
# This program is free software; you can redistribute it and/or modify
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 (
32
binary_files_re = 'Binary files (.*) and (.*) differ\n'
19
class PatchSyntax(Exception):
20
def __init__(self, msg):
21
Exception.__init__(self, msg)
24
class MalformedPatchHeader(PatchSyntax):
25
def __init__(self, desc, line):
28
msg = "Malformed patch header. %s\n%r" % (self.desc, self.line)
29
PatchSyntax.__init__(self, msg)
32
class MalformedHunkHeader(PatchSyntax):
33
def __init__(self, desc, line):
36
msg = "Malformed hunk header. %s\n%r" % (self.desc, self.line)
37
PatchSyntax.__init__(self, msg)
40
class MalformedLine(PatchSyntax):
41
def __init__(self, desc, line):
44
msg = "Malformed line. %s\n%s" % (self.desc, self.line)
45
PatchSyntax.__init__(self, msg)
48
class PatchConflict(Exception):
49
def __init__(self, line_no, orig_line, patch_line):
50
orig = orig_line.rstrip('\n')
51
patch = str(patch_line).rstrip('\n')
52
msg = 'Text contents mismatch at line %d. Original has "%s",'\
53
' but patch says it should be "%s"' % (line_no, orig, patch)
54
Exception.__init__(self, msg)
34
57
def get_patch_names(iter_lines):
36
59
line = iter_lines.next()
37
match = re.match(binary_files_re, line)
39
raise BinaryFiles(match.group(1), match.group(2))
40
60
if not line.startswith("--- "):
41
61
raise MalformedPatchHeader("No orig name", line)
218
def iter_hunks(iter_lines, allow_dirty=False):
220
:arg iter_lines: iterable of lines to parse for hunks
221
:kwarg allow_dirty: If True, when we encounter something that is not
222
a hunk header when we're looking for one, assume the rest of the lines
223
are not part of the patch (comments or other junk). Default False
238
def iter_hunks(iter_lines):
226
240
for line in iter_lines:
232
246
if hunk is not None:
235
hunk = hunk_from_header(line)
236
except MalformedHunkHeader:
238
# If the line isn't a hunk header, then we've reached the end
239
# of this patch and there's "junk" at the end. Ignore the
240
# rest of this patch.
248
hunk = hunk_from_header(line)
245
251
while orig_size < hunk.orig_range or mod_size < hunk.mod_range:
256
class BinaryPatch(object):
257
263
def __init__(self, oldname, newname):
258
264
self.oldname = oldname
259
265
self.newname = newname
262
return 'Binary files %s and %s differ\n' % (self.oldname, self.newname)
265
class Patch(BinaryPatch):
267
def __init__(self, oldname, newname):
268
BinaryPatch.__init__(self, oldname, newname)
271
268
def __str__(self):
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.
318
def parse_patch(iter_lines):
327
319
iter_lines = iter_lines_handle_nl(iter_lines)
329
(orig_name, mod_name) = get_patch_names(iter_lines)
330
except BinaryFiles, e:
331
return BinaryPatch(e.orig_name, e.mod_name)
333
patch = Patch(orig_name, mod_name)
334
for hunk in iter_hunks(iter_lines, allow_dirty):
335
patch.hunks.append(hunk)
339
def iter_file_patch(iter_lines, allow_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).
353
regex = re.compile(binary_files_re)
320
(orig_name, mod_name) = get_patch_names(iter_lines)
321
patch = Patch(orig_name, mod_name)
322
for hunk in iter_hunks(iter_lines):
323
patch.hunks.append(hunk)
327
def iter_file_patch(iter_lines):
357
330
for line in iter_lines:
358
331
if line.startswith('=== ') or line.startswith('*** '):
362
335
elif orig_range > 0:
363
336
if line.startswith('-') or line.startswith(' '):
365
elif line.startswith('--- ') or regex.match(line):
366
if allow_dirty and beginning:
367
# Patches can have "junk" at the beginning
368
# Stripping junk from the end of patches is handled when we
371
elif len(saved_lines) > 0:
338
elif line.startswith('--- '):
339
if len(saved_lines) > 0:
372
340
yield saved_lines
374
342
elif line.startswith('@@'):
403
def parse_patches(iter_lines, allow_dirty=False):
405
:arg iter_lines: iterable of lines to parse for patches
406
:kwarg allow_dirty: If True, allow text that's not part of the patch at
407
selected places. This includes comments before and after a patch
408
for instance. Default False.
410
return [parse_patch(f.__iter__(), allow_dirty) for f in
411
iter_file_patch(iter_lines, allow_dirty)]
371
def parse_patches(iter_lines):
372
return [parse_patch(f.__iter__()) for f in iter_file_patch(iter_lines)]
414
375
def difference_index(atext, btext):