kallithea Changeset - ef6991dee3b1

Changeset - ef6991dee3b1

Parent rev.

Child rev.

[Not reviewed]

default

0 1 0

Mads Kiilerich - 8 years ago 2017-10-03 00:14:40
mads@kiilerich.com

diffs: extract _get_header as a pure function

1 file changed with 64 insertions and 61 deletions:

kallithea/lib/diffs.py

0 comments (0 inline, 0 general)

kallithea/lib/diffs.py

➞

Show inline comments

@@ @@ -249,144 +249,84 @@ def get_gitdiff(filenode_old, filenode_n @@
     new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET)
     vcs_gitdiff = repo.get_diff(old_raw_id, new_raw_id, filenode_new.path,
                                 ignore_whitespace, context)
     return vcs_gitdiff
 NEW_FILENODE = 1
 DEL_FILENODE = 2
 MOD_FILENODE = 3
 RENAMED_FILENODE = 4
 COPIED_FILENODE = 5
 CHMOD_FILENODE = 6
 BIN_FILENODE = 7
 class DiffProcessor(object):
     """
     Give it a unified or git diff and it returns a list of the files that were
     mentioned in the diff together with a dict of meta information that
     can be used to render it in a HTML template.
     """
     _diff_git_re = re.compile('^diff --git', re.MULTILINE)
     _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')
     _newline_marker = re.compile(r'^\\ No newline at end of file')
     _git_header_re = re.compile(r"""
         ^diff[ ]--git
             [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
         (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
            ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
         (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n
            ^rename[ ]from[ ](?P<rename_from>.+)\n
            ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?
         (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
         (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
         (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
             \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
         (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
         (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?
         (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?
     """, re.VERBOSE | re.MULTILINE)
     _hg_header_re = re.compile(r"""
         ^diff[ ]--git
             [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
         (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
            ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
         (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))?
         (?:^rename[ ]from[ ](?P<rename_from>.+)\n
            ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?
         (?:^copy[ ]from[ ](?P<copy_from>.+)\n
            ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))?
         (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
         (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
         (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
             \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
         (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
         (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?
         (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?
     """, re.VERBOSE | re.MULTILINE)
     def __init__(self, diff, vcs='hg', diff_limit=None, inline_diff=True):
         """
         :param diff:   a text in diff format
         :param vcs: type of version control hg or git
         :param diff_limit: define the size of diff that is considered "big"
             based on that parameter cut off will be triggered, set to None
             to show full diff
         """
         if not isinstance(diff, basestring):
             raise Exception('Diff must be a basestring got %s instead' % type(diff))
         self._diff = diff
         self.adds = 0
         self.removes = 0
         self.diff_limit = diff_limit
         self.limited_diff = False
         self.vcs = vcs
         self.parsed = self._parse_gitdiff(inline_diff=inline_diff)
     def _get_header(self, diff_chunk):
         """
         Parses a Git diff for a single file (header and chunks) and returns a tuple with:
 . A dict with meta info:
             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
 . An iterator yielding lines with simple HTML markup.
         """
         match = None
         if self.vcs == 'git':
             match = self._git_header_re.match(diff_chunk)
         elif self.vcs == 'hg':
             match = self._hg_header_re.match(diff_chunk)
         if match is None:
             raise Exception('diff not recognized as valid %s diff' % self.vcs)
         meta_info = match.groupdict()
         rest = diff_chunk[match.end():]
         if rest and not rest.startswith('@') and not rest.startswith('literal ') and not rest.startswith('delta '):
             raise Exception('cannot parse %s diff header: %r followed by %r' % (self.vcs, diff_chunk[:match.end()], rest[:1000]))
         diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do
         return meta_info, diff_lines
     def _parse_gitdiff(self, inline_diff):
         """Parse self._diff and return a list of dicts with meta info and chunks for each file.
         Might set limited_diff.
         Optionally, do an extra pass and to extra markup of one-liner changes.
         """
         _files = [] # list of dicts with meta info and chunks
         starts = [m.start() for m in self._diff_git_re.finditer(self._diff)]
         starts.append(len(self._diff))
         for start, end in zip(starts, starts[1:]):
             if self.diff_limit and end > self.diff_limit:
                 self.limited_diff = True
                 continue
-            head, diff_lines = self._get_header(buffer(self._diff, start, end - start))
+            head, diff_lines = _get_header(self.vcs, buffer(self._diff, start, end - start))
             op = None
             stats = {
                 'added': 0,
                 'deleted': 0,
                 'binary': False,
                 'ops': {},
+            }
             if head['deleted_file_mode']:
                 op = 'D'
                 stats['binary'] = True
                 stats['ops'][DEL_FILENODE] = 'deleted file'
             elif head['new_file_mode']:
                 op = 'A'
                 stats['binary'] = True
                 stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']
             else:  # modify operation, can be cp, rename, chmod
                 # CHMOD
                 if head['new_mode'] and head['old_mode']:
                     op = 'M'
                     stats['binary'] = True
                     stats['ops'][CHMOD_FILENODE] = ('modified file chmod %s => %s'
@@ @@ -606,48 +546,111 @@ _escape_re = re.compile(r'(&)|(<)|(>)|(\ @@
 def _escaper(string):
     """
     Do HTML escaping/markup
     """
     def substitute(m):
         groups = m.groups()
         if groups[0]:
             return '&amp;'
         if groups[1]:
             return '&lt;'
         if groups[2]:
             return '&gt;'
         if groups[3]:
             return '<u>\t</u>'
         if groups[4]:
             return '<u class="cr"></u>'
         if groups[5]:
             return ' <i></i>'
         assert False
     return _escape_re.sub(substitute, safe_unicode(string))
 _git_header_re = re.compile(r"""
     ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
     (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
        ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
     (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n
        ^rename[ ]from[ ](?P<rename_from>.+)\n
        ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?
     (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
     (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
     (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
         \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
     (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
     (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?
     (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?
 """, re.VERBOSE | re.MULTILINE)
 _hg_header_re = re.compile(r"""
     ^diff[ ]--git[ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
     (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
        ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
     (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))?
     (?:^rename[ ]from[ ](?P<rename_from>.+)\n
        ^rename[ ]to[ ](?P<rename_to>.+)(?:\n|$))?
     (?:^copy[ ]from[ ](?P<copy_from>.+)\n
        ^copy[ ]to[ ](?P<copy_to>.+)(?:\n|$))?
     (?:^new[ ]file[ ]mode[ ](?P<new_file_mode>.+)(?:\n|$))?
     (?:^deleted[ ]file[ ]mode[ ](?P<deleted_file_mode>.+)(?:\n|$))?
     (?:^index[ ](?P<a_blob_id>[0-9A-Fa-f]+)
         \.\.(?P<b_blob_id>[0-9A-Fa-f]+)[ ]?(?P<b_mode>.+)?(?:\n|$))?
     (?:^(?P<bin_patch>GIT[ ]binary[ ]patch)(?:\n|$))?
     (?:^---[ ](a/(?P<a_file>.+?)|/dev/null)\t?(?:\n|$))?
     (?:^\+\+\+[ ](b/(?P<b_file>.+?)|/dev/null)\t?(?:\n|$))?
 """, re.VERBOSE | re.MULTILINE)
 def _get_header(vcs, diff_chunk):
     """
     Parses a Git diff for a single file (header and chunks) and returns a tuple with:
 . A dict with meta info:
         a_path, b_path, similarity_index, rename_from, rename_to,
         old_mode, new_mode, new_file_mode, deleted_file_mode,
         a_blob_id, b_blob_id, b_mode, a_file, b_file
 . An iterator yielding lines with simple HTML markup.
     """
     match = None
     if vcs == 'git':
         match = _git_header_re.match(diff_chunk)
     elif vcs == 'hg':
         match = _hg_header_re.match(diff_chunk)
     if match is None:
         raise Exception('diff not recognized as valid %s diff' % vcs)
     meta_info = match.groupdict()
     rest = diff_chunk[match.end():]
     if rest and not rest.startswith('@') and not rest.startswith('literal ') and not rest.startswith('delta '):
         raise Exception('cannot parse %s diff header: %r followed by %r' % (vcs, diff_chunk[:match.end()], rest[:1000]))
     diff_lines = (_escaper(m.group(0)) for m in re.finditer(r'.*\n|.+$', rest)) # don't split on \r as str.splitlines do
     return meta_info, diff_lines
 # Used for inline highlighter word split, must match the substitutions in _escaper
 _token_re = re.compile(r'()(&amp;|&lt;|&gt;|<u>\t</u>|<u class="cr"></u>| <i></i>|\W+?)')
 def _highlight_inline_diff(old, new):
     """
     Highlight simple add/remove in two lines given as info dicts. They are
     modified in place and given markup with <del>/<ins>.
     """
     assert old['action'] == 'del'
     assert new['action'] == 'add'
     oldwords = _token_re.split(old['line'])
     newwords = _token_re.split(new['line'])
     sequence = difflib.SequenceMatcher(None, oldwords, newwords)
     oldfragments, newfragments = [], []
     for tag, i1, i2, j1, j2 in sequence.get_opcodes():
         oldfrag = ''.join(oldwords[i1:i2])
         newfrag = ''.join(newwords[j1:j2])
         if tag != 'equal':
             if oldfrag:
                 oldfrag = '<del>%s</del>' % oldfrag
             if newfrag:

0 comments (0 inline, 0 general)