repo = filenode_new.changeset.repository

    old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET)

    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)

    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 _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.

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][COPIED_FILENODE] = ('file copied from %s to %s'

                                        % (head['copy_from'], head['copy_to']))

                # FALL BACK: detect missed old style add or remove

                if op is None:

                    if not head['a_file'] and head['b_file']:

                        op = 'A'

                        stats['binary'] = True

                        stats['ops'][NEW_FILENODE] = 'new file'

                    elif head['a_file'] and not head['b_file']:

                        op = 'D'

                        stats['binary'] = True

                        stats['ops'][DEL_FILENODE] = 'deleted file'

                # it's not ADD not DELETE

                if op is None:

                    op = 'M'

                    stats['binary'] = True

                    stats['ops'][MOD_FILENODE] = 'modified file'

            # a real non-binary diff

            if head['a_file'] or head['b_file']:

                stats['binary'] = False

                stats['added'] = added

                stats['deleted'] = deleted

                # explicit mark that it's a modified file

                if op == 'M':

                    stats['ops'][MOD_FILENODE] = 'modified file'

            else:  # Git binary patch (or empty diff)

                # Git binary patch

                if head['bin_patch']:

                    stats['ops'][BIN_FILENODE] = 'binary diff not shown'

                chunks = []

            if op == 'D' and chunks:

                # a way of seeing deleted content could perhaps be nice - but

                # not with the current UI

                chunks = []

            chunks.insert(0, [{

                'old_lineno': '',

                'new_lineno': '',

                'action':     'context',

                'line':       msg,

                } for _op, msg in stats['ops'].iteritems()

                  if _op not in [MOD_FILENODE]])

                            peekline = lineiter.next()

                        delline = peekline

                        peekline = lineiter.next()

                        # if not followed by add, eat all following del lines

                        if peekline['action'] != 'add':

                            while peekline['action'] == 'del':

                                peekline = lineiter.next()

                            continue

                        # found an add - make sure it is the only one

                        addline = peekline

                        try:

                            peekline = lineiter.next()

                        except StopIteration:

                            # add was last line - ok

                            _highlight_inline_diff(delline, addline)

                            raise

                        if peekline['action'] != 'add':

                            # there was only one add line - ok

                            _highlight_inline_diff(delline, addline)

                except StopIteration:

                    pass

        return _files

    def stat(self):

        """

        Returns tuple of added, and removed lines for this instance

        """

        return self.adds, self.removes

_escape_re = re.compile(r'(&)|(<)|(>)|(\t)|(\r)|(?<=.)( \n| $)')

def _escaper(string):

    """

    Do HTML escaping/markup

    """

    def substitute(m):

        groups = m.groups()

        if groups[0]:

            return '&'

        if groups[1]:

            return '<'

        if groups[2]:

            return '>'

        if groups[3]:

    1. 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

    2. 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: