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
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
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
class PatchSyntax(Exception):
21
def __init__(self, msg):
22
Exception.__init__(self, msg)
25
class MalformedPatchHeader(PatchSyntax):
26
def __init__(self, desc, line):
29
msg = "Malformed patch header. %s\n%r" % (self.desc, self.line)
30
PatchSyntax.__init__(self, msg)
33
class MalformedHunkHeader(PatchSyntax):
34
def __init__(self, desc, line):
37
msg = "Malformed hunk header. %s\n%r" % (self.desc, self.line)
38
PatchSyntax.__init__(self, msg)
41
class MalformedLine(PatchSyntax):
42
def __init__(self, desc, line):
45
msg = "Malformed line. %s\n%s" % (self.desc, self.line)
46
PatchSyntax.__init__(self, msg)
49
class PatchConflict(Exception):
50
def __init__(self, line_no, orig_line, patch_line):
51
orig = orig_line.rstrip('\n')
52
patch = str(patch_line).rstrip('\n')
53
msg = 'Text contents mismatch at line %d. Original has "%s",'\
54
' but patch says it should be "%s"' % (line_no, orig, patch)
55
Exception.__init__(self, msg)
32
binary_files_re = 'Binary files (.*) and (.*) differ\n'
58
35
def get_patch_names(iter_lines):
36
line = iter_lines.next()
60
line = iter_lines.next()
38
match = re.match(binary_files_re, line)
40
raise BinaryFiles(match.group(1), match.group(2))
61
41
if not line.startswith("--- "):
62
42
raise MalformedPatchHeader("No orig name", line)
257
class BinaryPatch(object):
266
258
def __init__(self, oldname, newname):
267
259
self.oldname = oldname
268
260
self.newname = newname
263
return 'Binary files %s and %s differ\n' % (self.oldname, self.newname)
266
class Patch(BinaryPatch):
268
def __init__(self, oldname, newname):
269
BinaryPatch.__init__(self, oldname, newname)
271
272
def __str__(self):
272
ret = self.get_header()
273
ret = self.get_header()
273
274
ret += "".join([str(h) for h in self.hunks])
276
277
def get_header(self):
277
278
return "--- %s\n+++ %s\n" % (self.oldname, self.newname)
280
"""Return a string of patch statistics"""
280
def stats_values(self):
281
"""Calculate the number of inserts and removes."""
283
284
for hunk in self.hunks:
287
288
elif isinstance(line, RemoveLine):
290
return (inserts, removes, len(self.hunks))
293
"""Return a string of patch statistics"""
289
294
return "%i inserts, %i removes in %i hunks" % \
290
(inserts, removes, len(self.hunks))
292
297
def pos_in_mod(self, position):
293
298
newpos = position
313
318
if isinstance(line, ContextLine):
317
def parse_patch(iter_lines):
318
(orig_name, mod_name) = get_patch_names(iter_lines)
319
patch = Patch(orig_name, mod_name)
320
for hunk in iter_hunks(iter_lines):
321
patch.hunks.append(hunk)
325
def iter_file_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.
327
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, 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).
353
regex = re.compile(binary_files_re)
328
359
for line in iter_lines:
329
if line.startswith('=== ') or line.startswith('*** '):
360
if line.startswith('=== '):
361
if len(saved_lines) > 0:
362
if keep_dirty and len(dirty_head) > 0:
363
yield {'saved_lines': saved_lines,
364
'dirty_head': dirty_head}
369
dirty_head.append(line)
371
if line.startswith('*** '):
331
373
if line.startswith('#'):
333
375
elif orig_range > 0:
334
376
if line.startswith('-') or line.startswith(' '):
336
elif line.startswith('--- '):
337
if len(saved_lines) > 0:
378
elif line.startswith('--- ') or regex.match(line):
379
if allow_dirty and beginning:
380
# Patches can have "junk" at the beginning
381
# Stripping junk from the end of patches is handled when we
384
elif len(saved_lines) > 0:
385
if keep_dirty and len(dirty_head) > 0:
386
yield {'saved_lines': saved_lines,
387
'dirty_head': dirty_head}
340
392
elif line.startswith('@@'):
341
393
hunk = hunk_from_header(line)
342
394
orig_range = hunk.orig_range
343
395
saved_lines.append(line)
344
396
if len(saved_lines) > 0:
397
if keep_dirty and len(dirty_head) > 0:
398
yield {'saved_lines': saved_lines,
399
'dirty_head': dirty_head}
348
404
def iter_lines_handle_nl(iter_lines):
368
def parse_patches(iter_lines):
369
iter_lines = iter_lines_handle_nl(iter_lines)
370
return [parse_patch(f.__iter__()) for f in iter_file_patch(iter_lines)]
425
def parse_patches(iter_lines, allow_dirty=False, keep_dirty=False):
427
:arg iter_lines: iterable of lines to parse for patches
428
:kwarg allow_dirty: If True, allow text that's not part of the patch at
429
selected places. This includes comments before and after a patch
430
for instance. Default False.
431
:kwarg keep_dirty: If True, returns a dict of patches with dirty headers.
435
for patch_lines in iter_file_patch(iter_lines, allow_dirty, keep_dirty):
436
if 'dirty_head' in patch_lines:
437
patches.append({'patch': parse_patch(
438
patch_lines['saved_lines'], allow_dirty),
439
'dirty_head': patch_lines['dirty_head']})
441
patches.append(parse_patch(patch_lines, allow_dirty))
373
445
def difference_index(atext, btext):
393
465
"""Iterate through a series of lines with a patch applied.
394
466
This handles a single file, and does exact, not fuzzy patching.
396
if orig_lines is not None:
397
orig_lines = orig_lines.__iter__()
468
patch_lines = iter_lines_handle_nl(iter(patch_lines))
469
get_patch_names(patch_lines)
470
return iter_patched_from_hunks(orig_lines, iter_hunks(patch_lines))
473
def iter_patched_from_hunks(orig_lines, hunks):
474
"""Iterate through a series of lines with a patch applied.
475
This handles a single file, and does exact, not fuzzy patching.
477
:param orig_lines: The unpatched lines.
478
:param hunks: An iterable of Hunk instances.
399
patch_lines = iter_lines_handle_nl(patch_lines.__iter__())
400
get_patch_names(patch_lines)
402
for hunk in iter_hunks(patch_lines):
482
if orig_lines is not None:
483
orig_lines = iter(orig_lines)
403
485
while line_no < hunk.orig_pos:
404
486
orig_line = orig_lines.next()