(?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))?

        (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\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>\S+)\n

           ^rename[ ]to[ ](?P<rename_to>\S+)(?:\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|$))?

        (?:^---[ ](a/(?P<a_file>.+)|/dev/null)(?:\n|$))?

        (?:^\+\+\+[ ](b/(?P<b_file>.+)|/dev/null)(?:\n|$))?

    """, re.VERBOSE | re.MULTILINE)

    #used for inline highlighter word split

    _token_re = re.compile(r'()(>|<|&|\W+?)')

    def __init__(self, diff, vcs='hg', format='gitdiff', diff_limit=None):

        """

        :param diff:   a text in diff format

        :param vcs: type of version controll hg or git

        :param format: format of diff passed, `udiff` or `gitdiff`

        :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._format = format

        self.adds = 0

        self.removes = 0

        # calculate diff size

        self.diff_size = len(diff)

        self.diff_limit = diff_limit

        self.cur_diff_size = 0

        self.parsed = False

        self.parsed_diff = []

        self.vcs = vcs

        if format == 'gitdiff':

            self.differ = self._highlight_line_difflib

            self._parser = self._parse_gitdiff

        else:

            self.differ = self._highlight_line_udiff

            self._parser = self._parse_udiff

    def _copy_iterator(self):

        """

        make a fresh copy of generator, we should not iterate thru

        an original as it's needed for repeating operations on

        this instance of DiffProcessor

        """

        self.__udiff, iterator_copy = tee(self.__udiff)

        return iterator_copy

    def _escaper(self, string):

        """

        Escaper for diff escapes special chars and checks the diff limit

        :param string:

        :type string:

        """

        self.cur_diff_size += len(string)

        # escaper get's iterated on each .next() call and it checks if each

        # parsed line doesn't exceed the diff limit

        if self.diff_limit is not None and self.cur_diff_size > self.diff_limit:

            raise DiffLimitExceeded('Diff Limit Exceeded')

        return safe_unicode(string).replace('&', '&')\

                .replace('<', '&lt;')\

                .replace('>', '>')

    def _line_counter(self, l):

        """

        Checks each line and bumps total adds/removes for this diff

        :param l:

        """

        if l.startswith('+') and not l.startswith('+++'):

            self.adds += 1

        elif l.startswith('-') and not l.startswith('---'):

            self.removes += 1

        return safe_unicode(l)

    def _highlight_line_difflib(self, line, next_):

        """

        Highlight inline changes in both lines.

        """

        if line['action'] == 'del':

            old, new = line, next_

        else:

            old, new = next_, line

        oldwords = self._token_re.split(old['line'])

        newwords = self._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:

                    newfrag = '<ins>%s</ins>' % newfrag

            oldfragments.append(oldfrag)

            newfragments.append(newfrag)

        old['line'] = "".join(oldfragments)

        new['line'] = "".join(newfragments)

    def _highlight_line_udiff(self, line, next_):

        """

        Highlight inline changes in both lines.

        """

        start = 0

        limit = min(len(line['line']), len(next_['line']))

        while start < limit and line['line'][start] == next_['line'][start]:

            start += 1

        end = -1

        limit -= start

        while -end <= limit and line['line'][end] == next_['line'][end]:

            end -= 1

        end += 1

        if start or end:

            def do(l):

                last = end + len(l['line'])

                if l['action'] == 'add':

                    tag = 'ins'

                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:]:

            head, diff = self._get_header(raw_diff)

            op = None

            stats = 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:

                if head['deleted_file_mode']:

                    op = 'D'

                    stats = ['b', DEL_FILENODE]

                elif head['new_file_mode']:

                    op = 'A'

                    stats = ['b', NEW_FILENODE]

                else:

                    if head['new_mode'] and head['old_mode']:

                        stats = ['b', CHMOD_FILENODE]

                                      % (head['old_mode'], head['new_mode']))

                          and head['rename_from'] != head['rename_to']):

                        op = 'M'

                                      % (head['rename_from'], head['rename_to']))

                        stats = ['b', MOD_FILENODE]

            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: # GIT binary patch (or empty diff)

                chunks = []

                chunks.insert(0, [{

                    'old_lineno': '',

                    'new_lineno': '',

                    'action':     'binary',

                    '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()

            while line:

                lines = []

                chunks.append(lines)

                match = self._chunk_re.match(line)

                if not match:

                    break

                gr = match.groups()

                (old_line, old_end,

                 new_line, new_end) = [int(x or 1) for x in gr[:-1]]

                old_line -= 1

                new_line -= 1

                context = len(gr) == 5

                old_end += old_line

                new_end += new_line

                if context:

                    # skip context only if it's first line

                    if int(gr[0]) > 1:

                        lines.append({

                            'old_lineno': '...',

                            'new_lineno': '...',

                            'action':     'context',

                            'line':       line,

                        })

                line = lineiter.next()

                while old_line < old_end or new_line < new_end:

                    command = ' '

                    if line:

                        command = line[0]

                    affects_old = affects_new = False

                    # ignore those if we don't expect them

                    if command in '#@':

                        continue

                    elif command == '+':

                        affects_new = True

                        action = 'add'

                        stats[0] += 1

                    elif command == '-':

                        affects_old = True

                        action = 'del'

                        stats[1] += 1

                    else:

                        affects_old = affects_new = True

                        action = 'unmod'

                    if not self._newline_marker.match(line):

                        old_line += affects_old

                        new_line += affects_new

                        lines.append({

                            'old_lineno':   affects_old and old_line or '',

                            'new_lineno':   affects_new and new_line or '',

                            'action':       action,

                            'line':         self._clean_line(line, command)

                        })

                    line = lineiter.next()

                    if self._newline_marker.match(line):

                        # we need to append to lines, since this is not

                        # counted in the line specs of diff

                        lines.append({

                            'old_lineno':   '...',

                            'new_lineno':   '...',

                            'action':       'context',

                            'line':         self._clean_line(line, command)

                        })

        except StopIteration:

            pass

        return chunks, stats

    def _safe_id(self, idstring):

        """Make a string safe for including in an id attribute.

        The HTML spec says that id attributes 'must begin with

        a letter ([A-Za-z]) and may be followed by any number

        of letters, digits ([0-9]), hyphens ("-"), underscores

        ("_"), colons (":"), and periods (".")'. These regexps

        are slightly over-zealous, in that they remove colons

        and periods unnecessarily.

        Whitespace is transformed into underscores, and then

        anything which is not a hyphen or a character that

        matches \w (alphanumerics and underscore) is removed.

        """

        # Transform all whitespace to underscore

        idstring = re.sub(r'\s', "_", '%s' % idstring)

        # Remove everything that is not a hyphen or a member of \w

        idstring = re.sub(r'(?!-)\W', "", idstring).lower()

        return idstring

    def prepare(self, inline_diff=True):

        """

        Prepare the passed udiff for HTML rendering. It'l return a list

        of dicts with diff information

        """

        parsed = self._parser(inline_diff=inline_diff)

        self.parsed = True

        self.parsed_diff = parsed

        return parsed

    def as_raw(self, diff_lines=None):

        """

        Returns raw string diff

        """

        return self._diff

        #return u''.join(imap(self._line_counter, self._diff.splitlines(1)))

    def as_html(self, table_class='code-difftable', line_class='line',

                old_lineno_class='lineno old', new_lineno_class='lineno new',

                code_class='code', enable_comments=False, parsed_lines=None):

        """

        Return given diff as html table with customized css classes

        """

        def _link_to_if(condition, label, url):

            """

            Generates a link if condition is meet or just the label if not.

            """

            if condition:

                return '''<a href="%(url)s">%(label)s</a>''' % {

                    'url': url,

                    'label': label

                }

            else:

                return label

        if not self.parsed:

            self.prepare()

        diff_lines = self.parsed_diff

        if parsed_lines:

            diff_lines = parsed_lines

        _html_empty = True

        _html = []