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., 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'
16
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
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
240
def iter_hunks(iter_lines):
226
242
for line in iter_lines:
232
248
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.
250
hunk = hunk_from_header(line)
245
253
while orig_size < hunk.orig_range or mod_size < hunk.mod_range:
256
class BinaryPatch(object):
257
265
def __init__(self, oldname, newname):
258
266
self.oldname = oldname
259
267
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
270
def __str__(self):
272
ret = self.get_header()
271
ret = self.get_header()
273
272
ret += "".join([str(h) for h in self.hunks])
276
275
def get_header(self):
277
276
return "--- %s\n+++ %s\n" % (self.oldname, self.newname)
279
def stats_values(self):
280
"""Calculate the number of inserts and removes."""
279
"""Return a string of patch statistics"""
283
282
for hunk in self.hunks:
287
286
elif isinstance(line, RemoveLine):
289
return (inserts, removes, len(self.hunks))
292
"""Return a string of patch statistics"""
293
288
return "%i inserts, %i removes in %i hunks" % \
289
(inserts, removes, len(self.hunks))
296
291
def pos_in_mod(self, position):
297
292
newpos = position
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):
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)
316
def parse_patch(iter_lines):
317
(orig_name, mod_name) = get_patch_names(iter_lines)
318
patch = Patch(orig_name, mod_name)
319
for hunk in iter_hunks(iter_lines):
320
patch.hunks.append(hunk)
324
def iter_file_patch(iter_lines):
357
327
for line in iter_lines:
358
328
if line.startswith('=== ') or line.startswith('*** '):
362
332
elif orig_range > 0:
363
333
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:
335
elif line.startswith('--- '):
336
if len(saved_lines) > 0:
372
337
yield saved_lines
374
339
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)]
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)]
414
373
def difference_index(atext, btext):