Mercurial > kallithea
view rhodecode/lib/diffs.py @ 2640:5f21a9dcb09d beta
create an index for commit messages and the ability to search them and see results
author | Indra Talip <indra.talip@gmail.com> |
---|---|
date | Fri, 20 Jul 2012 12:50:56 +0200 |
parents | 5fe0f744bec0 |
children | 2b6939a77052 |
line wrap: on
line source
# -*- 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 <marcin@python-works.com> :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 markupsafe from itertools import tee, imap from mercurial import patch from mercurial.mdiff import diffopts from mercurial.bundlerepo import bundlerepository from mercurial import localrepo from pylons.i18n.translation import _ from rhodecode.lib.compat import BytesIO from rhodecode.lib.vcs.exceptions import VCSError from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode from rhodecode.lib.helpers import escape from rhodecode.lib.utils import EmptyChangeset, make_ui 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 class DiffProcessor(object): """ Give it a unified 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 = '\\ No newline at end of file\n' def __init__(self, diff, differ='diff', format='gitdiff'): """ :param diff: a text in diff format or generator :param format: format of diff passed, `udiff` or `gitdiff` """ if isinstance(diff, basestring): diff = [diff] self.__udiff = diff self.__format = format self.adds = 0 self.removes = 0 if isinstance(self.__udiff, basestring): self.lines = iter(self.__udiff.splitlines(1)) elif self.__format == 'gitdiff': udiff_copy = self.copy_iterator() self.lines = imap(self.escaper, self._parse_gitdiff(udiff_copy)) else: udiff_copy = self.copy_iterator() self.lines = imap(self.escaper, udiff_copy) # Select a differ. if differ == 'difflib': self.differ = self._highlight_line_difflib else: self.differ = self._highlight_line_udiff def escaper(self, string): return markupsafe.escape(string) 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 _extract_rev(self, line1, line2): """ Extract the operation (A/M/D), filename and revision hint from a line. """ try: if line1.startswith('--- ') and line2.startswith('+++ '): l1 = line1[4:].split(None, 1) old_filename = (l1[0].replace('a/', '', 1) if len(l1) >= 1 else None) old_rev = l1[1] if len(l1) == 2 else 'old' l2 = line2[4:].split(None, 1) new_filename = (l2[0].replace('b/', '', 1) if len(l1) >= 1 else None) new_rev = l2[1] if len(l2) == 2 else 'new' filename = (old_filename if old_filename != '/dev/null' else new_filename) operation = 'D' if new_filename == '/dev/null' else None if not operation: operation = 'M' if old_filename != '/dev/null' else 'A' return operation, filename, new_rev, old_rev except (ValueError, IndexError): pass return None, None, None, None def _parse_gitdiff(self, diffiterator): def line_decoder(l): if l.startswith('+') and not l.startswith('+++'): self.adds += 1 elif l.startswith('-') and not l.startswith('---'): self.removes += 1 return l.decode('utf8', 'replace') output = list(diffiterator) size = len(output) if size == 2: l = [] l.extend([output[0]]) l.extend(output[1].splitlines(1)) return map(line_decoder, l) elif size == 1: return map(line_decoder, output[0].splitlines(1)) elif size == 0: return [] raise Exception('wrong size of diff %s' % size) 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 = re.split(r'(\W)', old['line']) newwords = re.split(r'(\W)', 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 _parse_udiff(self, inline_diff=True): """ Parse the diff an return data for the template. """ lineiter = self.lines files = [] try: line = lineiter.next() while 1: # continue until we found the old file if not line.startswith('--- '): line = lineiter.next() continue chunks = [] stats = [0, 0] operation, filename, old_rev, new_rev = \ self._extract_rev(line, lineiter.next()) files.append({ 'filename': filename, 'old_revision': old_rev, 'new_revision': new_rev, 'chunks': chunks, 'operation': operation, 'stats': stats, }) line = lineiter.next() while line: match = self._chunk_re.match(line) if not match: break lines = [] chunks.append(lines) old_line, old_end, new_line, new_end = \ [int(x or 1) for x in match.groups()[:-1]] old_line -= 1 new_line -= 1 gr = match.groups() 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: if line: command = line[0] if command in ['+', '-', ' ']: #only modify the line if it's actually a diff # thing line = line[1:] else: command = ' ' 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 line != self._newline_marker: 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': line }) line = lineiter.next() if line == self._newline_marker: # 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': line }) except StopIteration: pass sorter = lambda info: {'A': 0, 'M': 1, 'D': 2}.get(info['operation']) if inline_diff is False: return 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 sorted(files, key=sorter) def prepare(self, inline_diff=True): """ Prepare the passed udiff for HTML rendering. It'l return a list of dicts """ return self._parse_udiff(inline_diff=inline_diff) 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 raw_diff(self): """ Returns raw string as udiff """ udiff_copy = self.copy_iterator() if self.__format == 'gitdiff': udiff_copy = self._parse_gitdiff(udiff_copy) return u''.join(udiff_copy) def as_html(self, table_class='code-difftable', line_class='line', new_lineno_class='lineno old', old_lineno_class='lineno new', code_class='code', enable_comments=False, diff_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 diff_lines is None: diff_lines = self.prepare() _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): """ General differ between branches, bookmarks or separate but releated 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: """ bundlerepo = None ignore_whitespace = False context = 3 org_repo = org_repo.scm_instance._repo other_repo = other_repo.scm_instance._repo opts = diffopts(git=True, ignorews=ignore_whitespace, context=context) org_ref = org_ref[1] other_ref = other_ref[1] if org_repo != other_repo: common, incoming, rheads = discovery_data # create a bundle (uncompressed if other repo is not local) if other_repo.capable('getbundle') and incoming: # 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 other_repo.ui.configitems('hooks'): other_repo.ui.setconfig('hooks', k, None) unbundle = other_repo.getbundle('incoming', common=common, heads=rheads) 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 or org_repo, node1=org_repo[org_ref].node(), node2=other_repo[other_ref].node(), opts=opts)) else: return ''.join(patch.diff(org_repo, node1=org_ref, node2=other_ref, opts=opts))