"""Given a string with html, return it wrapped in a table, similar to what

    DiffProcessor returns."""

    return '''\

              <table class="code-difftable">

                <tr class="line no-comment">

                <td class="lineno new"></td>

                <td class="code no-comment"><pre>%s</pre></td>

                </tr>

              </table>''' % html

def wrapped_diff(filenode_old, filenode_new, diff_limit=None,

                ignore_whitespace=True, line_context=3,

                enable_comments=False):

    """

    Returns a file diff wrapped into a table.

    Checks for diff_limit and presents a message if the diff is too big.

    """

    if filenode_old is None:

        filenode_old = FileNode(filenode_new.path, '', EmptyChangeset())

    op = None

    a_path = filenode_old.path # default, might be overriden by actual rename in diff

    if filenode_old.is_binary or filenode_new.is_binary:

        diff = wrap_to_table(_('Binary file'))

        stats = (0, 0)

    elif diff_limit != -1 and (

            diff_limit is None or

            (filenode_old.size < diff_limit and filenode_new.size < diff_limit)):

        raw_diff = get_gitdiff(filenode_old, filenode_new,

                                ignore_whitespace=ignore_whitespace,

                                context=line_context)

        diff_processor = DiffProcessor(raw_diff)

        if diff_processor.parsed: # there should be exactly one element, for the specified file

            f = diff_processor.parsed[0]

            op = f['operation']

            a_path = f['old_filename']

        diff = diff_processor.as_html(enable_comments=enable_comments)

        stats = diff_processor.stat()

    else:

        diff = wrap_to_table(_('Changeset was too big and was cut off, use '

                               'diff menu to display this diff'))

        stats = (0, 0)

    if not diff:

        submodules = filter(lambda o: isinstance(o, SubModuleNode),

                            [filenode_new, filenode_old])

        if submodules:

            diff = wrap_to_table(escape('Submodule %r' % submodules[0]))

        else:

            diff = wrap_to_table(_('No changes detected'))

    cs1 = filenode_old.changeset.raw_id

    cs2 = filenode_new.changeset.raw_id

    return cs1, cs2, a_path, diff, stats, op

def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3):

    """

    Returns git style diff between given ``filenode_old`` and ``filenode_new``.

    """

    # make sure we pass in default context

    context = context or 3

    submodules = filter(lambda o: isinstance(o, SubModuleNode),

                        [filenode_new, filenode_old])

    if submodules:

        return ''

    for filenode in (filenode_old, filenode_new):

        if not isinstance(filenode, FileNode):

            raise VCSError("Given object should be FileNode object, not %s"

                % filenode.__class__)

    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)

    _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)

    # 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+?)')

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

    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 _escaper(self, string):

        """

        """

        def substitute(m):

            groups = m.groups()

            if groups[0]:

                return '&'

            if groups[1]:

                return '<'

            if groups[2]:

                return '>'

            if groups[3]:

                return '<u>\t</u>'

            if groups[4]:

                return '<u class="cr"></u>'

            if groups[5]:

                return ' <i></i>'

            assert False

        return self._escape_re.sub(substitute, safe_unicode(string))

    def _highlight_inline_diff(self, 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 = 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 _get_header(self, diff_chunk):

        """

        Parses a Git diff for a single file (header and chunks) and returns a tuple with:

        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 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 = (self._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:]):

            head, diff_lines = self._get_header(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'

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

                # RENAME

                if (head['rename_from'] and head['rename_to']

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

                    op = 'R'

                    stats['binary'] = True

                    stats['ops'][RENAMED_FILENODE] = ('file renamed from %s to %s'

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

                # COPY

                if head.get('copy_from') and head.get('copy_to'):

                    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']:

            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]])

            _files.append({

                'old_filename':     head['a_path'],

                'filename':         head['b_path'],

                'old_revision':     head['a_blob_id'],

                'new_revision':     head['b_blob_id'],

                'chunks':           chunks,

                'operation':        op,

                'stats':            stats,

            })

        if not inline_diff:

            return _files

        # highlight inline changes when one del is followed by one add

        for diff_data in _files:

            for chunk in diff_data['chunks']:

                lineiter = iter(chunk)

                try:

                    peekline = lineiter.next()

                    while True:

                        # find a first del line

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

                            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

                            self._highlight_inline_diff(delline, addline)

                            raise

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

                            # there was only one add line - ok

                            self._highlight_inline_diff(delline, addline)

                except StopIteration:

                    pass

        return _files

    def _parse_lines(self, diff_lines):

        """

        Given an iterator of diff body lines, parse them and return a dict per

        line and added/removed totals.

        """

        added = deleted = 0

        old_line = old_end = new_line = new_end = None

        try:

            chunks = []

            line = diff_lines.next()

            while True:

                lines = []

                chunks.append(lines)

                match = self._chunk_re.match(line)

                if not match:

                    raise Exception('error parsing diff @@ line %r' % line)

                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