revision='tip'))

            except (NodeError, NodeAlreadyExistsError) as e:

                h.flash(_(e), category='error')

            except Exception:

                log.error(traceback.format_exc())

                h.flash(_('Error occurred during commit'), category='error')

            raise HTTPFound(location=url('changeset_home',

                                repo_name=c.repo_name, revision='tip'))

        return render('files/files_add.html')

    @LoginRequired()

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

                                   'repository.admin')

    def archivefile(self, repo_name, fname):

        fileformat = None

        revision = None

        ext = None

        subrepos = request.GET.get('subrepos') == 'true'

        for a_type, ext_data in settings.ARCHIVE_SPECS.items():

            archive_spec = fname.split(ext_data[1])

            if len(archive_spec) == 2 and archive_spec[1] == '':

                fileformat = a_type or ext_data[1]

                revision = archive_spec[0]

                ext = ext_data[1]

        try:

            dbrepo = RepoModel().get_by_repo_name(repo_name)

            if not dbrepo.enable_downloads:

                return _('Downloads disabled') # TODO: do something else?

            if c.db_repo_scm_instance.alias == 'hg':

                # patch and reset hooks section of UI config to not run any

                # hooks on fetching archives with subrepos

                for k, v in c.db_repo_scm_instance._repo.ui.configitems('hooks'):

                    c.db_repo_scm_instance._repo.ui.setconfig('hooks', k, None)

            cs = c.db_repo_scm_instance.get_changeset(revision)

            content_type = settings.ARCHIVE_SPECS[fileformat][0]

        except ChangesetDoesNotExistError:

            return _('Unknown revision %s') % revision

        except EmptyRepositoryError:

            return _('Empty repository')

        except (ImproperArchiveTypeError, KeyError):

            return _('Unknown archive type')

        from kallithea import CONFIG

        rev_name = cs.raw_id[:12]

        archive_name = '%s-%s%s' % (safe_str(repo_name.replace('/', '_')),

                                    safe_str(rev_name), ext)

        archive_path = None

        cached_archive_path = None

        archive_cache_dir = CONFIG.get('archive_cache_dir')

        if archive_cache_dir and not subrepos: # TODO: subrepo caching?

            if not os.path.isdir(archive_cache_dir):

                os.makedirs(archive_cache_dir)

            cached_archive_path = os.path.join(archive_cache_dir, archive_name)

            if os.path.isfile(cached_archive_path):

                log.debug('Found cached archive in %s', cached_archive_path)

                archive_path = cached_archive_path

            else:

                log.debug('Archive %s is not yet cached', archive_name)

        if archive_path is None:

            # generate new archive

            fd, archive_path = tempfile.mkstemp()

            log.debug('Creating new temp archive in %s', archive_path)

            with os.fdopen(fd, 'wb') as stream:

                cs.fill_archive(stream=stream, kind=fileformat, subrepos=subrepos)

                # stream (and thus fd) has been closed by cs.fill_archive

            if cached_archive_path is not None:

                # we generated the archive - move it to cache

                log.debug('Storing new archive in %s', cached_archive_path)

                shutil.move(archive_path, cached_archive_path)

                archive_path = cached_archive_path

        def get_chunked_archive(archive_path):

            stream = open(archive_path, 'rb')

            while True:

                data = stream.read(16 * 1024)

                if not data:

                    break

                yield data

            stream.close()

            if archive_path != cached_archive_path:

                log.debug('Destroying temp archive %s', archive_path)

                os.remove(archive_path)

        action_logger(user=c.authuser,

                      action='user_downloaded_archive:%s' % (archive_name),

                      repo=repo_name, ipaddr=self.ip_addr, commit=True)

        response.content_disposition = str('attachment; filename=%s' % (archive_name))

        response.content_type = str(content_type)

        return get_chunked_archive(archive_path)

    @LoginRequired()

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

                                   'repository.admin')

    def diff(self, repo_name, f_path):

        ignore_whitespace = request.GET.get('ignorews') == '1'

        line_context = safe_int(request.GET.get('context'), 3)

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

        diff1 = request.GET.get('diff1', '') or diff2

        c.action = request.GET.get('diff')

        c.no_changes = diff1 == diff2

        c.f_path = f_path

        c.big_diff = False

        c.anchor_url = anchor_url

        c.ignorews_url = _ignorews_url

        c.context_url = _context_url

        c.changes = OrderedDict()

        c.changes[diff2] = []

        #special case if we want a show rev only, it's impl here

        #to reduce JS and callbacks

        if request.GET.get('show_rev'):

            if str2bool(request.GET.get('annotate', 'False')):

                _url = url('files_annotate_home', repo_name=c.repo_name,

                           revision=diff1, f_path=c.f_path)

            else:

                _url = url('files_home', repo_name=c.repo_name,

                           revision=diff1, f_path=c.f_path)

            raise HTTPFound(location=_url)

        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 (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')

            h.flash(msg, category='error')

            raise HTTPNotFound()

        c.node1 = node1

        c.node2 = node2

        c.cs1 = c.changeset_1

        c.cs2 = c.changeset_2

        return render('files/diff_2way.html')

    def _get_node_history(self, cs, f_path, changesets=None):

        """

        get changesets history for given node

        :param cs: changeset to calculate history

        :param f_path: path for node to calculate history for

        :param changesets: if passed don't calculate history and take

            changesets defined in this list

        """

        # calculate history based on tip

        tip_cs = c.db_repo_scm_instance.get_changeset()

        if changesets is None:

            try:

                changesets = tip_cs.get_file_history(f_path)

            except (NodeDoesNotExistError, ChangesetError):

                #this node is not present at tip !

                changesets = cs.get_file_history(f_path)

        hist_l = []

        changesets_group = ([], _("Changesets"))

        branches_group = ([], _("Branches"))

        tags_group = ([], _("Tags"))

        for chs in changesets:

            #_branch = '(%s)' % chs.branch if (cs.repository.alias == 'hg') else ''

            _branch = chs.branch

            n_desc = '%s (%s)' % (h.show_id(chs), _branch)

            changesets_group[0].append((chs.raw_id, n_desc,))

        hist_l.append(changesets_group)

        for name, chs in c.db_repo_scm_instance.branches.items():

            branches_group[0].append((chs, name),)

        hist_l.append(branches_group)

        for name, chs in c.db_repo_scm_instance.tags.items():

            tags_group[0].append((chs, name),)

        hist_l.append(tags_group)

        return hist_l, changesets

    @LoginRequired()

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

                                   'repository.admin')

    @jsonify

    def nodelist(self, repo_name, revision, f_path):

        if request.environ.get('HTTP_X_PARTIAL_XHR'):

            cs = self.__get_cs(revision)

            _d, _f = ScmModel().get_nodes(repo_name, cs.raw_id, f_path,

                                          flat=False)

            return {'nodes': _d + _f}

# -*- coding: utf-8 -*-

# This program is free software: you can redistribute it and/or modify

# it under the terms of the GNU General Public License as published by

# the Free Software Foundation, either version 3 of the License, or

# (at your option) any later version.

#

# This program is distributed in the hope that it will be useful,

# but WITHOUT ANY WARRANTY; without even the implied warranty of

# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

# GNU General Public License for more details.

#

# You should have received a copy of the GNU General Public License

# along with this program.  If not, see <http://www.gnu.org/licenses/>.

"""

kallithea.lib.diffs

~~~~~~~~~~~~~~~~~~~

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)

        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

    def __iter__(self):

        for l in self.diff:

            yield l

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.

    """

    _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"""

        # has already been split on this:

        # ^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"""

        # has already been split on this:

        # ^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', format='gitdiff', diff_limit=None):

        """

        :param diff:   a text in diff format

        :param vcs: type of version control 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:

        """

        self.cur_diff_size += len(string)

        # escaper gets 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')

        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 _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, old, new):

        """

        Highlight inline changes in both lines.

        """