refactoring: drop unused 'discovery data' in pull request and compare diffs

rhodecode/controllers/compare.py

@@ -1,184 +1,183
 # -*- coding: utf-8 -*-
 """
     rhodecode.controllers.compare
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
     compare controller for pylons showoing differences between two
     repos, branches, bookmarks or tips
 
     :created_on: May 6, 2012
     :author: marcink
     :copyright: (C) 2010-2012 Marcin Kuzminski <[e-mail]>
     :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('repo', org_repo)
         incoming_changesets = str2bool(request.GET.get('bundle', False))
         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', repo_name=other_repo,
               org_ref_type=other_ref[0], org_ref=other_ref[1],
               other_ref_type=org_ref[0], other_ref=org_ref[1],
               repo=org_repo, as_form=request.GET.get('as_form'),
               bundle=incoming_changesets)
 
         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.cs_ranges, discovery_data = PullRequestModel().get_compare_data(
+        c.cs_ranges = PullRequestModel().get_compare_data(
                                     org_repo, org_ref, other_repo, other_ref,
                                     )
 
         c.statuses = c.rhodecode_db_repo.statuses([x.raw_id for x in
                                                    c.cs_ranges])
         c.target_repo = c.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]
 
         if not incoming_changesets and c.cs_ranges and c.org_repo != c.other_repo:
             # case we want a simple diff without incoming changesets, just
             # for review purposes. Make the diff on the forked repo, with
             # revision that is common ancestor
             _org_ref = org_ref
             org_ref = ('rev', getattr(c.cs_ranges[0].parents[0]
                                       if c.cs_ranges[0].parents
                                       else EmptyChangeset(), 'raw_id'))
             log.debug('Changed org_ref from %s to %s' % (_org_ref, org_ref))
             other_repo = org_repo
 
         diff_limit = self.cut_off_limit if not fulldiff else None
 
         _diff = diffs.differ(org_repo, org_ref, other_repo, other_ref,
-                             discovery_data,
                              remote_compare=incoming_changesets)
 
         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')

rhodecode/lib/diffs.py

@@ -1,770 +1,769
 # -*- coding: utf-8 -*-
 """
     rhodecode.lib.diffs
     ~~~~~~~~~~~~~~~~~~~
 
     Set of diffing helpers, previously part of vcs
 
 
     :created_on: Dec 4, 2011
     :author: marcink
     :copyright: (C) 2010-2012 Marcin Kuzminski <[e-mail]>
     :original copyright: 2007-2008 by Armin Ronacher
     :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 re
 import difflib
 import logging
 import traceback
 
 from itertools import tee, imap
 
 from mercurial import patch
 from mercurial.mdiff import diffopts
 from mercurial.bundlerepo import bundlerepository
 
 from pylons.i18n.translation import _
 
 from rhodecode.lib.compat import BytesIO
 from rhodecode.lib.vcs.utils.hgcompat import localrepo
 from rhodecode.lib.vcs.exceptions import VCSError
 from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode
 from rhodecode.lib.vcs.backends.base import EmptyChangeset
 from rhodecode.lib.helpers import escape
 from rhodecode.lib.utils import make_ui
 from rhodecode.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)
         size = 0
 
     elif cut_off_limit != -1 and (cut_off_limit is None or
     (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()
         size = len(diff or '')
     else:
         diff = wrap_to_table(_('Changeset was too big and was cut off, use '
                                'diff menu to display this diff'))
         stats = (0, 0)
         size = 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 size, cs1, cs2, diff, stats
 
 
 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
 CHMOD_FILENODE = 5
 
 
 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"""
         #^diff[ ]--git
             [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
         (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%\n
            ^rename[ ]from[ ](?P<rename_from>\S+)\n
            ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))?
         (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
            ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
         (?:^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|$))?
     """, re.VERBOSE | re.MULTILINE)
     _hg_header_re = re.compile(r"""
         #^diff[ ]--git
             [ ]a/(?P<a_path>.+?)[ ]b/(?P<b_path>.+?)\n
         (?:^similarity[ ]index[ ](?P<similarity_index>\d+)%(?:\n|$))?
         (?:^rename[ ]from[ ](?P<rename_from>\S+)\n
            ^rename[ ]to[ ](?P<rename_to>\S+)(?:\n|$))?
         (?:^old[ ]mode[ ](?P<old_mode>\d+)\n
            ^new[ ]mode[ ](?P<new_mode>\d+)(?:\n|$))?
         (?:^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'()(&gt;|&lt;|&amp;|\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('&', '&amp;')\
                 .replace('<', '&lt;')\
                 .replace('>', '&gt;')
 
     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:]:
             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
 
 
 class InMemoryBundleRepo(bundlerepository):
     def __init__(self, ui, path, bundlestream):
         self._tempparent = None
         localrepo.localrepository.__init__(self, ui, path)
         self.ui.setconfig('phases', 'publish', False)
 
         self.bundle = bundlestream
 
         # dict with the mapping 'filename' -> position in the bundle
         self.bundlefilespos = {}
 
 
-def differ(org_repo, org_ref, other_repo, other_ref, discovery_data=None,
+def differ(org_repo, org_ref, other_repo, other_ref,
            remote_compare=False, 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
 
     elif remote_compare:
         opts = diffopts(git=True, ignorews=ignore_whitespace, context=context)
-        common, incoming, rheads = discovery_data
         org_repo_peer = localrepo.locallegacypeer(org_repo.local())
         # create a bundle (uncompressed if other repo is not local)
         if org_repo_peer.capable('getbundle'):
             # disable repo hooks here since it's just bundle !
             # patch and reset hooks section of UI config to not run any
             # hooks on fetching archives with subrepos
             for k, _ in org_repo.ui.configitems('hooks'):
                 org_repo.ui.setconfig('hooks', k, None)
             unbundle = org_repo.getbundle('incoming', common=None,
                                           heads=None)
 
             buf = BytesIO()
             while True:
                 chunk = unbundle._stream.read(1024 * 4)
                 if not chunk:
                     break
                 buf.write(chunk)
 
             buf.seek(0)
             # replace chunked _stream with data that can do tell() and seek()
             unbundle._stream = buf
 
             ui = make_ui('db')
             bundlerepo = InMemoryBundleRepo(ui, path=org_repo.root,
                                             bundlestream=unbundle)
 
             return ''.join(patch.diff(bundlerepo,
                                       node1=other_repo[other_ref].node(),
                                       node2=org_repo[org_ref].node(),
                                       opts=opts))
 
     return ''

rhodecode/model/pull_request.py

@@ -1,295 +1,251
 # -*- 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 <[e-mail]>
     :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 binascii
 import datetime
 import re
 
 from pylons.i18n.translation import _
 
 from rhodecode.model.meta import Session
 from rhodecode.lib import helpers as h
 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 discovery, localrepo, scmutil, \
     findcommonoutgoing
 
 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).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') % \
                 {'user': created_by_user.username,
                  '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,
-                        discovery_data):
+    def _get_changesets(self, alias, org_repo, org_ref, other_repo, other_ref):
         """
         Returns a list of changesets that are incoming from org_repo@org_ref
         to other_repo@other_ref
 
         :param org_repo:
         :param org_ref:
         :param other_repo:
         :param other_ref:
         :param tmp:
         """
 
         changesets = []
         #case two independent repos
-        common, incoming, rheads = discovery_data
         if org_repo != other_repo:
             revs = [
                 org_repo._repo.lookup(org_ref[1]),
                 org_repo._repo.lookup(other_ref[1]),
             ]
 
             obj = findcommonoutgoing(org_repo._repo,
                         localrepo.locallegacypeer(other_repo._repo.local()),
                         revs,
                         force=True)
             revs = obj.missing
 
             for cs in map(binascii.hexlify, revs):
                 _cs = org_repo.get_changeset(cs)
                 changesets.append(_cs)
             # in case we have revisions filter out the ones not in given range
             if org_ref[0] == 'rev' and other_ref[0] == 'rev':
                 revs = [x.raw_id for x in changesets]
                 start = org_ref[1]
                 stop = other_ref[1]
                 changesets = changesets[revs.index(start):revs.index(stop) + 1]
         else:
             #no remote compare do it on the same repository
             if alias == 'hg':
                 _revset_predicates = {
                         'branch': 'branch',
                         'book': 'bookmark',
                         'tag': 'tag',
                         'rev': 'id',
                     }
 
                 revs = [
                     "ancestors(%s('%s')) and not ancestors(%s('%s'))" % (
                         _revset_predicates[other_ref[0]], other_ref[1],
                         _revset_predicates[org_ref[0]], org_ref[1],
                    )
                 ]
 
                 out = scmutil.revrange(org_repo._repo, revs)
                 for cs in (out):
                     changesets.append(org_repo.get_changeset(cs))
             elif alias == 'git':
                 so, se = org_repo.run_git_command(
                     'log --reverse --pretty="format: %%H" -s -p %s..%s' % (org_ref[1],
                                                                      other_ref[1])
                 )
                 ids = re.findall(r'[0-9a-fA-F]{40}', so)
                 for cs in (ids):
                     changesets.append(org_repo.get_changeset(cs))
 
         return changesets
 
-    def _get_discovery(self, org_repo, org_ref, other_repo, other_ref):
-        """
-        Get's mercurial discovery data used to calculate difference between
-        repos and refs
-
-        :param org_repo:
-        :type org_repo:
-        :param org_ref:
-        :type org_ref:
-        :param other_repo:
-        :type other_repo:
-        :param other_ref:
-        :type other_ref:
-        """
-
-        _org_repo = org_repo._repo
-        org_rev_type, org_rev = org_ref
-
-        _other_repo = other_repo._repo
-        other_rev_type, other_rev = other_ref
-
-        log.debug('Doing discovery for %s@%s vs %s@%s' % (
-                        org_repo, org_ref, other_repo, other_ref)
-        )
-
-        #log.debug('Filter heads are %s[%s]' % ('', org_ref[1]))
-        org_peer = localrepo.locallegacypeer(_org_repo.local())
-        tmp = discovery.findcommonincoming(
-                  repo=_other_repo,  # other_repo we check for incoming
-                  remote=org_peer,  # org_repo source for incoming
-#                  heads=[_other_repo[other_rev].node(),
-#                         _org_repo[org_rev].node()],
-                  force=True
-        )
-        return tmp
-
     def get_compare_data(self, org_repo, org_ref, other_repo, other_ref):
         """
-        Returns a tuple of incomming changesets, and discoverydata cache for
-        mercurial repositories
+        Returns incomming 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
-        discovery_data = [None, None, None]
-        if alias == 'hg':
-            discovery_data = self._get_discovery(org_repo_scm, org_ref,
-                                               other_repo_scm, other_ref)
         cs_ranges = self._get_changesets(alias,
                                          org_repo_scm, org_ref,
-                                         other_repo_scm, other_ref,
-                                         discovery_data)
-        return cs_ranges, discovery_data
+                                         other_repo_scm, other_ref)
+        return cs_ranges