if diff2 not in ['', None, 'None', '0' * 12, '0' * 40]:

                c.changeset_2 = c.db_repo_scm_instance.get_changeset(diff2)

                try:

                    node2 = c.changeset_2.get_node(f_path)

                    if node2.is_dir():

                        raise NodeError('%s path is a %s not a file'

                                        % (node2, type(node2)))

                except NodeDoesNotExistError:

                    c.changeset_2 = EmptyChangeset(cs=diff2,

                                                   revision=c.changeset_2.revision,

                                                   repo=c.db_repo_scm_instance)

                    node2 = FileNode(f_path, '', changeset=c.changeset_2)

            else:

                c.changeset_2 = EmptyChangeset(repo=c.db_repo_scm_instance)

                node2 = FileNode(f_path, '', changeset=c.changeset_2)

        except (RepositoryError, NodeError):

            log.error(traceback.format_exc())

            raise HTTPFound(location=url('files_home', repo_name=c.repo_name,

                                f_path=f_path))

        if c.action == 'download':

            _diff = diffs.get_gitdiff(node1, node2,

                                      ignore_whitespace=ignore_whitespace,

                                      context=line_context)

            diff = diffs.DiffProcessor(_diff, format='gitdiff')

            diff_name = '%s_vs_%s.diff' % (diff1, diff2)

            response.content_type = 'text/plain'

            response.content_disposition = (

                'attachment; filename=%s' % diff_name

            )

            return diff.as_raw()

        elif c.action == 'raw':

            _diff = diffs.get_gitdiff(node1, node2,

                                      ignore_whitespace=ignore_whitespace,

                                      context=line_context)

            diff = diffs.DiffProcessor(_diff, format='gitdiff')

            response.content_type = 'text/plain'

            return diff.as_raw()

        else:

            fid = h.FID(diff2, node2.path)

            line_context_lcl = get_line_ctx(fid, request.GET)

            ign_whitespace_lcl = get_ignore_ws(fid, request.GET)

            lim = request.GET.get('fulldiff') or self.cut_off_limit

                                         filenode_new=node2,

                                         cut_off_limit=lim,

                                         ignore_whitespace=ign_whitespace_lcl,

                                         line_context=line_context_lcl,

                                         enable_comments=False)

            filename = node1.path

            cs_changes = {

                'fid': [cs1, cs2, op, filename, diff, st]

            }

            c.changes = cs_changes

        return render('files/file_diff.html')

    @LoginRequired()

    @HasRepoPermissionAnyDecorator('repository.read', 'repository.write',

                                   'repository.admin')

    def diff_2way(self, repo_name, f_path):

        diff1 = request.GET.get('diff1', '')

        diff2 = request.GET.get('diff2', '')

        try:

            if diff1 not in ['', None, 'None', '0' * 12, '0' * 40]:

                c.changeset_1 = c.db_repo_scm_instance.get_changeset(diff1)

                try:

                    node1 = c.changeset_1.get_node(f_path)

                    if node1.is_dir():

                        raise NodeError('%s path is a %s not a file'

                                        % (node1, type(node1)))

                except NodeDoesNotExistError:

                    c.changeset_1 = EmptyChangeset(cs=diff1,

                                                   revision=c.changeset_1.revision,

                                                   repo=c.db_repo_scm_instance)

                    node1 = FileNode(f_path, '', changeset=c.changeset_1)

            else:

                c.changeset_1 = EmptyChangeset(repo=c.db_repo_scm_instance)

                node1 = FileNode(f_path, '', changeset=c.changeset_1)

            if diff2 not in ['', None, 'None', '0' * 12, '0' * 40]:

                c.changeset_2 = c.db_repo_scm_instance.get_changeset(diff2)

                try:

                    node2 = c.changeset_2.get_node(f_path)

                    if node2.is_dir():

                        raise NodeError('%s path is a %s not a file'

                                        % (node2, type(node2)))

                except NodeDoesNotExistError:

                    c.changeset_2 = EmptyChangeset(cs=diff2,

                                                   revision=c.changeset_2.revision,

                                                   repo=c.db_repo_scm_instance)

                    node2 = FileNode(f_path, '', changeset=c.changeset_2)

            else:

                c.changeset_2 = EmptyChangeset(repo=c.db_repo_scm_instance)

                node2 = FileNode(f_path, '', changeset=c.changeset_2)

        except ChangesetDoesNotExistError as e:

            msg = _('Such revision does not exist for this repository')

Set of diffing helpers, previously part of vcs

This file was forked by the Kallithea project in July 2014.

Original author and date, and relevant copyright and licensing information is below:

:created_on: Dec 4, 2011

:author: marcink

:copyright: (c) 2013 RhodeCode GmbH, and others.

:license: GPLv3, see LICENSE.md for more details.

"""

import re

import difflib

import logging

from itertools import tee, imap

from pylons.i18n.translation import _

from kallithea.lib.vcs.exceptions import VCSError

from kallithea.lib.vcs.nodes import FileNode, SubModuleNode

from kallithea.lib.vcs.backends.base import EmptyChangeset

from kallithea.lib.helpers import escape

from kallithea.lib.utils2 import safe_unicode

log = logging.getLogger(__name__)

def wrap_to_table(str_):

    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>''' % str_

def wrapped_diff(filenode_old, filenode_new, cut_off_limit=None,

                ignore_whitespace=True, line_context=3,

                enable_comments=False):

    """

    returns a wrapped diff into a table, checks for cut_off_limit and presents

    proper message

    """

    if filenode_old is None:

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

    if filenode_old.is_binary or filenode_new.is_binary:

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

        stats = (0, 0)

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

        f_gitdiff = get_gitdiff(filenode_old, filenode_new,

                                ignore_whitespace=ignore_whitespace,

                                context=line_context)

        diff_processor = DiffProcessor(f_gitdiff, format='gitdiff')

        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

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

    """

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

    :param ignore_whitespace: ignore whitespaces in diff

    """

    # 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 DiffLimitExceeded(Exception):

    pass

class LimitedDiffContainer(object):

    def __init__(self, diff_limit, cur_diff_size, diff):

        self.diff = diff

        self.diff_limit = diff_limit

        self.cur_diff_size = cur_diff_size