Changeset - ab75def5c15d
[Not reviewed]
beta
0 2 0
Marcin Kuzminski - 13 years ago 2012-09-16 20:04:23
marcin@python-works.com
fixes #567 diff non-unicode encoding missmatch
- now uses safe_unicode ass all other parts of the system
2 files changed with 4 insertions and 2 deletions:
0 comments (0 inline, 0 general)
rhodecode/lib/diffs.py
Show inline comments
 
# -*- 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 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
 

	
 

	
 
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]))
 
@@ -169,97 +170,97 @@ class DiffProcessor(object):
 
    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')
 
            return safe_unicode(l)
 

	
 
        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_):
 
        """
rhodecode/lib/vcs/utils/diffs.py
Show inline comments
 
# -*- coding: utf-8 -*-
 
# original copyright: 2007-2008 by Armin Ronacher
 
# licensed under the BSD license.
 

	
 
import re
 
import difflib
 
import logging
 

	
 
from difflib import unified_diff
 
from itertools import tee, imap
 

	
 
from mercurial.match import match
 

	
 
from rhodecode.lib.vcs.exceptions import VCSError
 
from rhodecode.lib.vcs.nodes import FileNode, NodeError
 
from rhodecode.lib.vcs.utils import safe_unicode
 

	
 

	
 
def get_udiff(filenode_old, filenode_new, show_whitespace=True):
 
    """
 
    Returns unified diff between given ``filenode_old`` and ``filenode_new``.
 
    """
 
    try:
 
        filenode_old_date = filenode_old.changeset.date
 
    except NodeError:
 
        filenode_old_date = None
 

	
 
    try:
 
        filenode_new_date = filenode_new.changeset.date
 
    except NodeError:
 
        filenode_new_date = None
 

	
 
    for filenode in (filenode_old, filenode_new):
 
        if not isinstance(filenode, FileNode):
 
            raise VCSError("Given object should be FileNode object, not %s"
 
                % filenode.__class__)
 

	
 
    if filenode_old_date and filenode_new_date:
 
        if not filenode_old_date < filenode_new_date:
 
            logging.debug("Generating udiff for filenodes with not increasing "
 
                "dates")
 

	
 
    vcs_udiff = unified_diff(filenode_old.content.splitlines(True),
 
                               filenode_new.content.splitlines(True),
 
                               filenode_old.name,
 
                               filenode_new.name,
 
                               filenode_old_date,
 
                               filenode_old_date)
 
    return vcs_udiff
 

	
 

	
 
def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True):
 
    """
 
    Returns git style diff between given ``filenode_old`` and ``filenode_new``.
 

	
 
    :param ignore_whitespace: ignore whitespaces in diff
 
    """
 

	
 
    for filenode in (filenode_old, filenode_new):
 
        if not isinstance(filenode, FileNode):
 
            raise VCSError("Given object should be FileNode object, not %s"
 
                % filenode.__class__)
 

	
 
    old_raw_id = getattr(filenode_old.changeset, 'raw_id', '0' * 40)
 
@@ -104,97 +105,97 @@ class DiffProcessor(object):
 
        # Select a differ.
 
        if differ == 'difflib':
 
            self.differ = self._highlight_line_difflib
 
        else:
 
            self.differ = self._highlight_line_udiff
 

	
 
    def escaper(self, string):
 
        return string.replace('<', '&lt;').replace('>', '&gt;')
 

	
 
    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 filename and revision hint from a line.
 
        """
 

	
 
        try:
 
            if line1.startswith('--- ') and line2.startswith('+++ '):
 
                l1 = line1[4:].split(None, 1)
 
                old_filename = l1[0].lstrip('a/') 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].lstrip('b/') 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
 

	
 
                return filename, new_rev, old_rev
 
        except (ValueError, IndexError):
 
            pass
 

	
 
        return 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')
 
            return safe_unicode(l)
 

	
 
        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):
 
        """
0 comments (0 inline, 0 general)