kallithea Changeset - 0d22458bd360

Changeset - 0d22458bd360

Parent rev.

Child rev.

[Not reviewed]

beta

0 1 0

Mads Kiilerich - 13 years ago 2013-04-10 02:55:38
madski@unity3d.com

diff parser: more correct detection and reporting of binary git diffs

git mode is not just used for binary diffs.

1 file changed with 17 insertions and 13 deletions:

rhodecode/lib/diffs.py

0 comments (0 inline, 0 general)

rhodecode/lib/diffs.py

➞

Show inline comments

@@ @@ -309,150 +309,154 @@ class DiffProcessor(object): @@
                 else:
                     tag = 'del'
                 l['line'] = '%s<%s>%s</%s>%s' % (
                     l['line'][:start],
                     tag,
                     l['line'][start:last],
                     tag,
                     l['line'][last:]
+                )
             do(line)
             do(next_)
     def _get_header(self, diff_chunk):
         """
         parses the diff header, and returns parts, and leftover diff
         parts consists of 14 elements::
             a_path, b_path, similarity_index, rename_from, rename_to,
             old_mode, new_mode, new_file_mode, deleted_file_mode,
             a_blob_id, b_blob_id, b_mode, a_file, b_file
         :param diff_chunk:
         :type diff_chunk:
         """
         if self.vcs == 'git':
             match = self._git_header_re.match(diff_chunk)
             diff = diff_chunk[match.end():]
             return match.groupdict(), imap(self._escaper, diff.splitlines(1))
         elif self.vcs == 'hg':
             match = self._hg_header_re.match(diff_chunk)
             diff = diff_chunk[match.end():]
             return match.groupdict(), imap(self._escaper, diff.splitlines(1))
         else:
             raise Exception('VCS type %s is not supported' % self.vcs)
     def _clean_line(self, line, command):
         if command in ['+', '-', ' ']:
             #only modify the line if it's actually a diff thing
             line = line[1:]
         return line
     def _parse_gitdiff(self, inline_diff=True):
         _files = []
         diff_container = lambda arg: arg
         ##split the diff in chunks of separate --git a/file b/file chunks
         for raw_diff in ('\n' + self._diff).split('\ndiff --git')[1:]:
             binary = False
             binary_msg = 'unknown binary'
             head, diff = self._get_header(raw_diff)
             op = None
             stats = None
             msg = None
             if not head['a_file'] and head['b_file']:
                 op = 'A'
             elif head['a_file'] and head['b_file']:
                 op = 'M'
             elif head['a_file'] and not head['b_file']:
                 op = 'D'
             else:
                 #probably we're dealing with a binary file 1
                 binary = True
                 if head['deleted_file_mode']:
                     op = 'D'
                     stats = ['b', DEL_FILENODE]
-                    binary_msg = 'deleted binary file'
+                    msg = 'deleted file'
                 elif head['new_file_mode']:
                     op = 'A'
                     stats = ['b', NEW_FILENODE]
-                    binary_msg = 'new binary file %s' % head['new_file_mode']
+                    msg = 'new file %s' % head['new_file_mode']
                 else:
                     if head['new_mode'] and head['old_mode']:
                         stats = ['b', CHMOD_FILENODE]
                         op = 'M'
-                        binary_msg = ('modified binary file chmod %s => %s'
+                        msg = ('modified file chmod %s => %s'
                                       % (head['old_mode'], head['new_mode']))
                     elif (head['rename_from'] and head['rename_to']
                           and head['rename_from'] != head['rename_to']):
                         stats = ['b', RENAMED_FILENODE]
                         op = 'M'
-                        binary_msg = ('file renamed from %s to %s'
+                        msg = ('file renamed from %s to %s'
                                       % (head['rename_from'], head['rename_to']))
                     else:
                         stats = ['b', MOD_FILENODE]
                         op = 'M'
-                        binary_msg = 'modified binary file'
+                        msg = 'modified file'
-            if not binary:
+            if head['a_file'] or head['b_file']: # a real diff
                 try:
                     chunks, stats = self._parse_lines(diff)
                 except DiffLimitExceeded:
                     diff_container = lambda _diff: LimitedDiffContainer(
                                                 self.diff_limit,
                                                 self.cur_diff_size,
                                                 _diff)
                     break
             else:
+            else: # GIT binary patch (or empty diff)
                 chunks = []
                 chunks.append([{
                 if not msg: # don't overwrite more important message
                     msg = 'binary diff not shown'
             if msg:
                 chunks.insert(0, [{
                     'old_lineno': '',
                     'new_lineno': '',
                     'action':     'binary',
-                    'line':       binary_msg,
+                    'line':       msg,
                 }])
             _files.append({
                 'filename':         head['b_path'],
                 'old_revision':     head['a_blob_id'],
                 'new_revision':     head['b_blob_id'],
                 'chunks':           chunks,
                 'operation':        op,
                 'stats':            stats,
             })
         sorter = lambda info: {'A': 0, 'M': 1, 'D': 2}.get(info['operation'])
         if not inline_diff:
             return diff_container(sorted(_files, key=sorter))
         # highlight inline changes
         for diff_data in _files:
             for chunk in diff_data['chunks']:
                 lineiter = iter(chunk)
                 try:
                     while 1:
                         line = lineiter.next()
                         if line['action'] not in ['unmod', 'context']:
                             nextline = lineiter.next()
                             if nextline['action'] in ['unmod', 'context'] or \
                                nextline['action'] == line['action']:
                                 continue
                             self.differ(line, nextline)
                 except StopIteration:
                     pass
         return diff_container(sorted(_files, key=sorter))
     def _parse_udiff(self, inline_diff=True):
         raise NotImplementedError()
     def _parse_lines(self, diff):
         """
         Parse the diff an return data for the template.
         """
         lineiter = iter(diff)
         stats = [0, 0]
         try:
             chunks = []
             line = lineiter.next()

0 comments (0 inline, 0 general)