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

"""

    rhodecode.controllers.compare

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

    compare controller for pylons showing differences between two

    repos, branches, bookmarks or tips

    :created_on: May 6, 2012

    :author: marcink

    :copyright: (C) 2010-2012 Marcin Kuzminski <marcin@python-works.com>

    :license: GPLv3, see COPYING for more details.

"""

# 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/>.

import logging

import traceback

from webob.exc import HTTPNotFound

from pylons import request, response, session, tmpl_context as c, url

from pylons.controllers.util import abort, redirect

from pylons.i18n.translation import _

from rhodecode.lib.vcs.exceptions import EmptyRepositoryError, RepositoryError

from rhodecode.lib import helpers as h

from rhodecode.lib.base import BaseRepoController, render

from rhodecode.lib.auth import LoginRequired, HasRepoPermissionAnyDecorator

from rhodecode.lib import diffs

from rhodecode.model.db import Repository

from rhodecode.model.pull_request import PullRequestModel

from webob.exc import HTTPBadRequest

from rhodecode.lib.utils2 import str2bool

from rhodecode.lib.diffs import LimitedDiffContainer

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

log = logging.getLogger(__name__)

class CompareController(BaseRepoController):

    @LoginRequired()

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

                                   'repository.admin')

    def __before__(self):

        super(CompareController, self).__before__()

    def __get_cs_or_redirect(self, rev, repo, redirect_after=True,

                             partial=False):

        """

        Safe way to get changeset if error occur it redirects to changeset with

        proper message. If partial is set then don't do redirect raise Exception

        instead

        :param rev: revision to fetch

        :param repo: repo instance

        """

        try:

            type_, rev = rev

            return repo.scm_instance.get_changeset(rev)

        except EmptyRepositoryError, e:

            if not redirect_after:

                return None

            h.flash(h.literal(_('There are no changesets yet')),

                    category='warning')

            redirect(url('summary_home', repo_name=repo.repo_name))

        except RepositoryError, e:

            log.error(traceback.format_exc())

            h.flash(str(e), category='warning')

            if not partial:

                redirect(h.url('summary_home', repo_name=repo.repo_name))

            raise HTTPBadRequest()

    def index(self, org_ref_type, org_ref, other_ref_type, other_ref):

        org_repo = c.rhodecode_db_repo.repo_name

        org_ref = (org_ref_type, org_ref)

        other_ref = (other_ref_type, other_ref)

        other_repo = request.GET.get('other_repo', org_repo)

        c.fulldiff = fulldiff = request.GET.get('fulldiff')

        rev_start = request.GET.get('rev_start')

        rev_end = request.GET.get('rev_end')

        c.swap_url = h.url('compare_url', as_form=request.GET.get('as_form'),

            repo_name=other_repo,

            org_ref_type=other_ref[0], org_ref=other_ref[1],

            other_repo=org_repo,

            other_ref_type=org_ref[0], other_ref=org_ref[1])

        c.org_repo = org_repo = Repository.get_by_repo_name(org_repo)

        c.other_repo = other_repo = Repository.get_by_repo_name(other_repo)

        if c.org_repo is None:

            log.error('Could not find org repo %s' % org_repo)

            raise HTTPNotFound

        if c.other_repo is None:

            log.error('Could not find other repo %s' % other_repo)

            raise HTTPNotFound

        if c.org_repo != c.other_repo and h.is_git(c.rhodecode_repo):

            log.error('compare of two remote repos not available for GIT REPOS')

            raise HTTPNotFound

        if c.org_repo.scm_instance.alias != c.other_repo.scm_instance.alias:

            log.error('compare of two different kind of remote repos not available')

            raise HTTPNotFound

        partial = request.environ.get('HTTP_X_PARTIAL_XHR')

        self.__get_cs_or_redirect(rev=org_ref, repo=org_repo, partial=partial)

        self.__get_cs_or_redirect(rev=other_ref, repo=other_repo, partial=partial)

        if rev_start and rev_end:

            #replace our org_ref with given CS

            org_ref = ('rev', rev_start)

            other_ref = ('rev', rev_end)

        c.statuses = c.rhodecode_db_repo.statuses([x.raw_id for x in

                                                   c.cs_ranges])

        c.target_repo = c.other_repo.repo_name

        # defines that we need hidden inputs with changesets

        c.as_form = request.GET.get('as_form', False)

        if partial:

            return render('compare/compare_cs.html')

        c.org_ref = org_ref[1]

        c.other_ref = other_ref[1]

            # revision that is common ancestor

            _org_ref = org_ref

            org_repo = other_repo

        diff_limit = self.cut_off_limit if not fulldiff else None

        _diff = diffs.differ(org_repo, org_ref, other_repo, other_ref)

        diff_processor = diffs.DiffProcessor(_diff or '', format='gitdiff',

                                             diff_limit=diff_limit)

        _parsed = diff_processor.prepare()

        c.limited_diff = False

        if isinstance(_parsed, LimitedDiffContainer):

            c.limited_diff = True

        c.files = []

        c.changes = {}

        c.lines_added = 0

        c.lines_deleted = 0

        for f in _parsed:

            st = f['stats']

            if st[0] != 'b':

                c.lines_added += st[0]

                c.lines_deleted += st[1]

            fid = h.FID('', f['filename'])

            c.files.append([fid, f['operation'], f['filename'], f['stats']])

            diff = diff_processor.as_html(enable_comments=False, parsed_lines=[f])

            c.changes[fid] = [f['operation'], f['filename'], diff]

        return render('compare/compare_diff.html')

        """

        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:]:

            binary = False

            binary_msg = 'unknown binary'

            head, diff = self._get_header(raw_diff)

            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:

                #probably we're dealing with a binary file 1

                binary = True

                if head['deleted_file_mode']:

                    op = 'D'

                    stats = ['b', DEL_FILENODE]

                    binary_msg = 'deleted binary file'

                elif head['new_file_mode']:

                    op = 'A'

                    stats = ['b', NEW_FILENODE]

                    binary_msg = 'new binary file %s' % head['new_file_mode']

                else:

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

                        stats = ['b', CHMOD_FILENODE]

                        op = 'M'

                        binary_msg = ('modified binary file chmod %s => %s'

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

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

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

                        stats = ['b', RENAMED_FILENODE]

                        op = 'M'

                        binary_msg = ('file renamed from %s to %s'

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

                    else:

                        stats = ['b', MOD_FILENODE]

                        op = 'M'

                        binary_msg = 'modified binary file'

            if not binary:

                try:

                    chunks, stats = self._parse_lines(diff)

                except DiffLimitExceeded:

                    diff_container = lambda _diff: LimitedDiffContainer(

                                                self.diff_limit,

                                                self.cur_diff_size,

                                                _diff)

                    break

            else:

                chunks = []

                chunks.append([{

                    'old_lineno': '',

                    'new_lineno': '',

                    'action':     'binary',

                    'line':       binary_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 inline_diff is False:

            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 = []

        _html.append('''<table class="%(table_class)s">\n''' % {

            'table_class': table_class

        })

        for diff in diff_lines:

            for line in diff['chunks']:

                _html_empty = False

                for change in line:

                    _html.append('''<tr class="%(lc)s %(action)s">\n''' % {

                        'lc': line_class,

                        'action': change['action']

                    })

                    anchor_old_id = ''

                    anchor_new_id = ''

                    anchor_old = "%(filename)s_o%(oldline_no)s" % {

                        'filename': self._safe_id(diff['filename']),

                        'oldline_no': change['old_lineno']

                    }

                    anchor_new = "%(filename)s_n%(oldline_no)s" % {

                        'filename': self._safe_id(diff['filename']),

                        'oldline_no': change['new_lineno']

                    }

                    cond_old = (change['old_lineno'] != '...' and

                                change['old_lineno'])

                    cond_new = (change['new_lineno'] != '...' and

                                change['new_lineno'])

                    if cond_old:

                        anchor_old_id = 'id="%s"' % anchor_old

                    if cond_new:

                        anchor_new_id = 'id="%s"' % anchor_new

                    ###########################################################

                    # OLD LINE NUMBER

                    ###########################################################

                    _html.append('''\t<td %(a_id)s class="%(olc)s">''' % {

                        'a_id': anchor_old_id,

                        'olc': old_lineno_class

                    })

                    _html.append('''%(link)s''' % {

                        'link': _link_to_if(True, change['old_lineno'],

                                            '#%s' % anchor_old)

                    })

                    _html.append('''</td>\n''')

                    ###########################################################

                    # NEW LINE NUMBER

                    ###########################################################

                    _html.append('''\t<td %(a_id)s class="%(nlc)s">''' % {

                        'a_id': anchor_new_id,

                        'nlc': new_lineno_class

                    })

                    _html.append('''%(link)s''' % {

                        'link': _link_to_if(True, change['new_lineno'],

                                            '#%s' % anchor_new)

                    })

                    _html.append('''</td>\n''')

                    ###########################################################

                    # CODE

                    ###########################################################

                    comments = '' if enable_comments else 'no-comment'

                    _html.append('''\t<td class="%(cc)s %(inc)s">''' % {

                        'cc': code_class,

                        'inc': comments

                    })

                    _html.append('''\n\t\t<pre>%(code)s</pre>\n''' % {

                        'code': change['line']

                    })

                    _html.append('''\t</td>''')

                    _html.append('''\n</tr>\n''')

        _html.append('''</table>''')

        if _html_empty:

            return None

        return ''.join(_html)

    def stat(self):

        """

        Returns tuple of added, and removed lines for this instance

        """

        return self.adds, self.removes

def differ(org_repo, org_ref, other_repo, other_ref,

           context=3, ignore_whitespace=False):

    """

    General differ between branches, bookmarks, revisions of two remote or

    local but related repositories

    :param org_repo:

    :param org_ref:

    :param other_repo:

    :type other_repo:

    :type other_ref:

    """

    org_repo_scm = org_repo.scm_instance

    other_repo_scm = other_repo.scm_instance

    org_repo = org_repo_scm._repo

    other_repo = other_repo_scm._repo

    org_ref = org_ref[1]

    other_ref = other_ref[1]

    if org_repo_scm == other_repo_scm:

        log.debug('running diff between %s@%s and %s@%s'

                  % (org_repo.path, org_ref, other_repo.path, other_ref))

        _diff = org_repo_scm.get_diff(rev1=org_ref, rev2=other_ref,

            ignore_whitespace=ignore_whitespace, context=context)

        return _diff

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

"""

    rhodecode.model.pull_request

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

    pull request model for RhodeCode

    :created_on: Jun 6, 2012

    :author: marcink

    :copyright: (C) 2012-2012 Marcin Kuzminski <marcin@python-works.com>

    :license: GPLv3, see COPYING for more details.

"""

# 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/>.

import logging

import datetime

import re

from pylons.i18n.translation import _

from rhodecode.model.meta import Session

from rhodecode.lib import helpers as h, unionrepo

from rhodecode.model import BaseModel

from rhodecode.model.db import PullRequest, PullRequestReviewers, Notification,\

    ChangesetStatus

from rhodecode.model.notification import NotificationModel

from rhodecode.lib.utils2 import safe_unicode

from rhodecode.lib.vcs.utils.hgcompat import scmutil

from rhodecode.lib.vcs.utils import safe_str

log = logging.getLogger(__name__)

class PullRequestModel(BaseModel):

    cls = PullRequest

    def __get_pull_request(self, pull_request):

        return self._get_instance(PullRequest, pull_request)

    def get_all(self, repo):

        repo = self._get_repo(repo)

        return PullRequest.query()\

                .filter(PullRequest.other_repo == repo)\

                .order_by(PullRequest.created_on)\

                .all()

    def create(self, created_by, org_repo, org_ref, other_repo, other_ref,

               revisions, reviewers, title, description=None):

        from rhodecode.model.changeset_status import ChangesetStatusModel

        created_by_user = self._get_user(created_by)

        org_repo = self._get_repo(org_repo)

        other_repo = self._get_repo(other_repo)

        new = PullRequest()

        new.org_repo = org_repo

        new.org_ref = org_ref

        new.other_repo = other_repo

        new.other_ref = other_ref

        new.revisions = revisions

        new.title = title

        new.description = description

        new.author = created_by_user

        self.sa.add(new)

        Session().flush()

        #members

        for member in reviewers:

            _usr = self._get_user(member)

            reviewer = PullRequestReviewers(_usr, new)

            self.sa.add(reviewer)

        #reset state to under-review

        ChangesetStatusModel().set_status(

            repo=org_repo,

            status=ChangesetStatus.STATUS_UNDER_REVIEW,

            user=created_by_user,

            pull_request=new

        )

        #notification to reviewers

        notif = NotificationModel()

        pr_url = h.url('pullrequest_show', repo_name=other_repo.repo_name,

                       pull_request_id=new.pull_request_id,

                       qualified=True,

        )

        subject = safe_unicode(

            h.link_to(

              _('%(user)s wants you to review pull request #%(pr_id)s: %(pr_title)s') % \

                {'user': created_by_user.username,

                 'pr_title': new.title,

                 'pr_id': new.pull_request_id},

                pr_url

            )

        )

        body = description

        kwargs = {

            'pr_title': title,

            'pr_user_created': h.person(created_by_user.email),

            'pr_repo_url': h.url('summary_home', repo_name=other_repo.repo_name,

                                 qualified=True,),

            'pr_url': pr_url,

            'pr_revisions': revisions

        }

        notif.create(created_by=created_by_user, subject=subject, body=body,

                     recipients=reviewers,

                     type_=Notification.TYPE_PULL_REQUEST, email_kwargs=kwargs)

        return new

    def update_reviewers(self, pull_request, reviewers_ids):

        reviewers_ids = set(reviewers_ids)

        pull_request = self.__get_pull_request(pull_request)

        current_reviewers = PullRequestReviewers.query()\

                            .filter(PullRequestReviewers.pull_request==

                                   pull_request)\

                            .all()

        current_reviewers_ids = set([x.user.user_id for x in current_reviewers])

        to_add = reviewers_ids.difference(current_reviewers_ids)

        to_remove = current_reviewers_ids.difference(reviewers_ids)

        log.debug("Adding %s reviewers" % to_add)

        log.debug("Removing %s reviewers" % to_remove)

        for uid in to_add:

            _usr = self._get_user(uid)

            reviewer = PullRequestReviewers(_usr, pull_request)

            self.sa.add(reviewer)

        for uid in to_remove:

            reviewer = PullRequestReviewers.query()\

                    .filter(PullRequestReviewers.user_id==uid,

                            PullRequestReviewers.pull_request==pull_request)\

                    .scalar()

            if reviewer:

                self.sa.delete(reviewer)

    def delete(self, pull_request):

        pull_request = self.__get_pull_request(pull_request)

        Session().delete(pull_request)

    def close_pull_request(self, pull_request):

        pull_request = self.__get_pull_request(pull_request)

        pull_request.status = PullRequest.STATUS_CLOSED

        pull_request.updated_on = datetime.datetime.now()

        self.sa.add(pull_request)

    def _get_changesets(self, alias, org_repo, org_ref, other_repo, other_ref):

        """

        :param org_repo:

        :param org_ref:

        :param other_repo:

        :param other_ref:

        :param tmp:

        """

        if alias == 'hg':

            # lookup up the exact node id

            _revset_predicates = {

                    'branch': 'branch',

                    'book': 'bookmark',

                    'tag': 'tag',

                    'rev': 'id',

                }

            org_rev_spec = "%s('%s')" % (_revset_predicates[org_ref[0]],

                                         safe_str(org_ref[1]))

            org_rev = scmutil.revsingle(org_repo._repo,

                                         org_rev_spec)

            other_rev_spec = "%s('%s')" % (_revset_predicates[other_ref[0]],

                                           safe_str(other_ref[1]))

            other_rev = scmutil.revsingle(other_repo._repo, other_rev_spec)

            #case two independent repos

            if org_repo != other_repo:

                hgrepo = unionrepo.unionrepository(other_repo.baseui,

                                                   other_repo.path,

                                                   org_repo.path)

                # all the changesets we are looking for will be in other_repo,

                # so rev numbers from hgrepo can be used in other_repo

            #no remote compare do it on the same repository

            else:

                hgrepo = other_repo._repo

            revs = ["ancestors(id('%s')) and not ancestors(id('%s'))" %

                    (other_rev, org_rev)]

        elif alias == 'git':

            assert org_repo == other_repo, (org_repo, other_repo) # no git support for different repos

            so, se = org_repo.run_git_command(

                'log --reverse --pretty="format: %%H" -s -p %s..%s' % (org_ref[1],

                                                                       other_ref[1])

            )

    def get_compare_data(self, org_repo, org_ref, other_repo, other_ref):

        """

        Returns incoming changesets for mercurial repositories

        :param org_repo:

        :type org_repo:

        :param org_ref:

        :type org_ref:

        :param other_repo:

        :type other_repo:

        :param other_ref:

        :type other_ref:

        """

        if len(org_ref) != 2 or not isinstance(org_ref, (list, tuple)):

            raise Exception('org_ref must be a two element list/tuple')

        if len(other_ref) != 2 or not isinstance(org_ref, (list, tuple)):

            raise Exception('other_ref must be a two element list/tuple')

        org_repo_scm = org_repo.scm_instance

        other_repo_scm = other_repo.scm_instance

        alias = org_repo.scm_instance.alias

                                         org_repo_scm, org_ref,

                                         other_repo_scm, other_ref)