diffs: don't use highlite on the new ops lines

rhodecode/lib/codeblocks.py

@@ -1,754 +1,762 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2011-2018 RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # 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 Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 import logging
 import difflib
-import string
 from itertools import groupby
 
 from pygments import lex
 from pygments.formatters.html import _get_ttype_class as pygment_token_class
 from pygments.lexers.special import TextLexer, Token
+from pygments.lexers import get_lexer_by_name
 
 from rhodecode.lib.helpers import (
     get_lexer_for_filenode, html_escape, get_custom_lexer)
 from rhodecode.lib.utils2 import AttributeDict, StrictAttributeDict, safe_unicode
 from rhodecode.lib.vcs.nodes import FileNode
 from rhodecode.lib.vcs.exceptions import VCSError, NodeDoesNotExistError
 from rhodecode.lib.diff_match_patch import diff_match_patch
 from rhodecode.lib.diffs import LimitedDiffContainer, DEL_FILENODE, BIN_FILENODE
-from pygments.lexers import get_lexer_by_name
+
 
 plain_text_lexer = get_lexer_by_name(
     'text', stripall=False, stripnl=False, ensurenl=False)
 
 
 log = logging.getLogger(__name__)
 
 
 def filenode_as_lines_tokens(filenode, lexer=None):
     org_lexer = lexer
     lexer = lexer or get_lexer_for_filenode(filenode)
     log.debug('Generating file node pygment tokens for %s, %s, org_lexer:%s',
               lexer, filenode, org_lexer)
     tokens = tokenize_string(filenode.content, lexer)
     lines = split_token_stream(tokens)
     rv = list(lines)
     return rv
 
 
 def tokenize_string(content, lexer):
     """
     Use pygments to tokenize some content based on a lexer
     ensuring all original new lines and whitespace is preserved
     """
 
     lexer.stripall = False
     lexer.stripnl = False
     lexer.ensurenl = False
 
     if isinstance(lexer, TextLexer):
         lexed = [(Token.Text, content)]
     else:
         lexed = lex(content, lexer)
 
     for token_type, token_text in lexed:
         yield pygment_token_class(token_type), token_text
 
 
 def split_token_stream(tokens):
     """
     Take a list of (TokenType, text) tuples and split them by a string
 
     split_token_stream([(TEXT, 'some\ntext'), (TEXT, 'more\n')])
     [(TEXT, 'some'), (TEXT, 'text'),
      (TEXT, 'more'), (TEXT, 'text')]
     """
 
     buffer = []
     for token_class, token_text in tokens:
         parts = token_text.split('\n')
         for part in parts[:-1]:
             buffer.append((token_class, part))
             yield buffer
             buffer = []
 
         buffer.append((token_class, parts[-1]))
 
     if buffer:
         yield buffer
 
 
 def filenode_as_annotated_lines_tokens(filenode):
     """
     Take a file node and return a list of annotations => lines, if no annotation
     is found, it will be None.
 
     eg:
 
     [
         (annotation1, [
             (1, line1_tokens_list),
             (2, line2_tokens_list),
         ]),
         (annotation2, [
             (3, line1_tokens_list),
         ]),
         (None, [
             (4, line1_tokens_list),
         ]),
         (annotation1, [
             (5, line1_tokens_list),
             (6, line2_tokens_list),
         ])
     ]
     """
 
     commit_cache = {}  # cache commit_getter lookups
 
     def _get_annotation(commit_id, commit_getter):
         if commit_id not in commit_cache:
             commit_cache[commit_id] = commit_getter()
         return commit_cache[commit_id]
 
     annotation_lookup = {
         line_no: _get_annotation(commit_id, commit_getter)
         for line_no, commit_id, commit_getter, line_content
         in filenode.annotate
     }
 
     annotations_lines = ((annotation_lookup.get(line_no), line_no, tokens)
                           for line_no, tokens
                           in enumerate(filenode_as_lines_tokens(filenode), 1))
 
     grouped_annotations_lines = groupby(annotations_lines, lambda x: x[0])
 
     for annotation, group in grouped_annotations_lines:
         yield (
             annotation, [(line_no, tokens)
                           for (_, line_no, tokens) in group]
         )
 
 
 def render_tokenstream(tokenstream):
     result = []
     for token_class, token_ops_texts in rollup_tokenstream(tokenstream):
 
         if token_class:
             result.append(u'<span class="%s">' % token_class)
         else:
             result.append(u'<span>')
 
         for op_tag, token_text in token_ops_texts:
 
             if op_tag:
                 result.append(u'<%s>' % op_tag)
 
             escaped_text = html_escape(token_text)
 
             # TODO: dan: investigate showing hidden characters like space/nl/tab
             # escaped_text = escaped_text.replace(' ', '<sp> </sp>')
             # escaped_text = escaped_text.replace('\n', '<nl>\n</nl>')
             # escaped_text = escaped_text.replace('\t', '<tab>\t</tab>')
 
             result.append(escaped_text)
 
             if op_tag:
                 result.append(u'</%s>' % op_tag)
 
         result.append(u'</span>')
 
     html = ''.join(result)
     return html
 
 
 def rollup_tokenstream(tokenstream):
     """
     Group a token stream of the format:
 
         ('class', 'op', 'text')
     or
         ('class', 'text')
 
     into
 
         [('class1',
             [('op1', 'text'),
              ('op2', 'text')]),
          ('class2',
             [('op3', 'text')])]
 
     This is used to get the minimal tags necessary when
     rendering to html eg for a token stream ie.
 
     <span class="A"><ins>he</ins>llo</span>
     vs
     <span class="A"><ins>he</ins></span><span class="A">llo</span>
 
     If a 2 tuple is passed in, the output op will be an empty string.
 
     eg:
 
     >>> rollup_tokenstream([('classA', '',      'h'),
                             ('classA', 'del',   'ell'),
                             ('classA', '',      'o'),
                             ('classB', '',      ' '),
                             ('classA', '',      'the'),
                             ('classA', '',      're'),
                             ])
 
     [('classA', [('', 'h'), ('del', 'ell'), ('', 'o')],
      ('classB', [('', ' ')],
      ('classA', [('', 'there')]]
 
     """
     if tokenstream and len(tokenstream[0]) == 2:
         tokenstream = ((t[0], '', t[1]) for t in tokenstream)
 
     result = []
     for token_class, op_list in groupby(tokenstream, lambda t: t[0]):
         ops = []
         for token_op, token_text_list in groupby(op_list, lambda o: o[1]):
             text_buffer = []
             for t_class, t_op, t_text in token_text_list:
                 text_buffer.append(t_text)
             ops.append((token_op, ''.join(text_buffer)))
         result.append((token_class, ops))
     return result
 
 
 def tokens_diff(old_tokens, new_tokens, use_diff_match_patch=True):
     """
     Converts a list of (token_class, token_text) tuples to a list of
     (token_class, token_op, token_text) tuples where token_op is one of
     ('ins', 'del', '')
 
     :param old_tokens: list of (token_class, token_text) tuples of old line
     :param new_tokens: list of (token_class, token_text) tuples of new line
     :param use_diff_match_patch: boolean, will use google's diff match patch
         library which has options to 'smooth' out the character by character
         differences making nicer ins/del blocks
     """
 
     old_tokens_result = []
     new_tokens_result = []
 
     similarity = difflib.SequenceMatcher(None,
         ''.join(token_text for token_class, token_text in old_tokens),
         ''.join(token_text for token_class, token_text in new_tokens)
     ).ratio()
 
     if similarity < 0.6: # return, the blocks are too different
         for token_class, token_text in old_tokens:
             old_tokens_result.append((token_class, '', token_text))
         for token_class, token_text in new_tokens:
             new_tokens_result.append((token_class, '', token_text))
         return old_tokens_result, new_tokens_result, similarity
 
     token_sequence_matcher = difflib.SequenceMatcher(None,
         [x[1] for x in old_tokens],
         [x[1] for x in new_tokens])
 
     for tag, o1, o2, n1, n2 in token_sequence_matcher.get_opcodes():
         # check the differences by token block types first to give a more
         # nicer "block" level replacement vs character diffs
 
         if tag == 'equal':
             for token_class, token_text in old_tokens[o1:o2]:
                 old_tokens_result.append((token_class, '', token_text))
             for token_class, token_text in new_tokens[n1:n2]:
                 new_tokens_result.append((token_class, '', token_text))
         elif tag == 'delete':
             for token_class, token_text in old_tokens[o1:o2]:
                 old_tokens_result.append((token_class, 'del', token_text))
         elif tag == 'insert':
             for token_class, token_text in new_tokens[n1:n2]:
                 new_tokens_result.append((token_class, 'ins', token_text))
         elif tag == 'replace':
             # if same type token blocks must be replaced, do a diff on the
             # characters in the token blocks to show individual changes
 
             old_char_tokens = []
             new_char_tokens = []
             for token_class, token_text in old_tokens[o1:o2]:
                 for char in token_text:
                     old_char_tokens.append((token_class, char))
 
             for token_class, token_text in new_tokens[n1:n2]:
                 for char in token_text:
                     new_char_tokens.append((token_class, char))
 
             old_string = ''.join([token_text for
                 token_class, token_text in old_char_tokens])
             new_string = ''.join([token_text for
                 token_class, token_text in new_char_tokens])
 
             char_sequence = difflib.SequenceMatcher(
                 None, old_string, new_string)
             copcodes = char_sequence.get_opcodes()
             obuffer, nbuffer = [], []
 
             if use_diff_match_patch:
                 dmp = diff_match_patch()
-                dmp.Diff_EditCost = 11 # TODO: dan: extract this to a setting
+                dmp.Diff_EditCost = 11  # TODO: dan: extract this to a setting
                 reps = dmp.diff_main(old_string, new_string)
                 dmp.diff_cleanupEfficiency(reps)
 
                 a, b = 0, 0
                 for op, rep in reps:
                     l = len(rep)
                     if op == 0:
                         for i, c in enumerate(rep):
                             obuffer.append((old_char_tokens[a+i][0], '', c))
                             nbuffer.append((new_char_tokens[b+i][0], '', c))
                         a += l
                         b += l
                     elif op == -1:
                         for i, c in enumerate(rep):
                             obuffer.append((old_char_tokens[a+i][0], 'del', c))
                         a += l
                     elif op == 1:
                         for i, c in enumerate(rep):
                             nbuffer.append((new_char_tokens[b+i][0], 'ins', c))
                         b += l
             else:
                 for ctag, co1, co2, cn1, cn2 in copcodes:
                     if ctag == 'equal':
                         for token_class, token_text in old_char_tokens[co1:co2]:
                             obuffer.append((token_class, '', token_text))
                         for token_class, token_text in new_char_tokens[cn1:cn2]:
                             nbuffer.append((token_class, '', token_text))
                     elif ctag == 'delete':
                         for token_class, token_text in old_char_tokens[co1:co2]:
                             obuffer.append((token_class, 'del', token_text))
                     elif ctag == 'insert':
                         for token_class, token_text in new_char_tokens[cn1:cn2]:
                             nbuffer.append((token_class, 'ins', token_text))
                     elif ctag == 'replace':
                         for token_class, token_text in old_char_tokens[co1:co2]:
                             obuffer.append((token_class, 'del', token_text))
                         for token_class, token_text in new_char_tokens[cn1:cn2]:
                             nbuffer.append((token_class, 'ins', token_text))
 
             old_tokens_result.extend(obuffer)
             new_tokens_result.extend(nbuffer)
 
     return old_tokens_result, new_tokens_result, similarity
 
 
 def diffset_node_getter(commit):
     def get_node(fname):
         try:
             return commit.get_node(fname)
         except NodeDoesNotExistError:
             return None
 
     return get_node
 
 
 class DiffSet(object):
     """
     An object for parsing the diff result from diffs.DiffProcessor and
     adding highlighting, side by side/unified renderings and line diffs
     """
 
     HL_REAL = 'REAL'  # highlights using original file, slow
     HL_FAST = 'FAST'  # highlights using just the line, fast but not correct
                       # in the case of multiline code
     HL_NONE = 'NONE'  # no highlighting, fastest
 
     def __init__(self, highlight_mode=HL_REAL, repo_name=None,
                  source_repo_name=None,
                  source_node_getter=lambda filename: None,
                  target_node_getter=lambda filename: None,
                  source_nodes=None, target_nodes=None,
                  # files over this size will use fast highlighting
                  max_file_size_limit=150 * 1024,
                  ):
 
         self.highlight_mode = highlight_mode
         self.highlighted_filenodes = {}
         self.source_node_getter = source_node_getter
         self.target_node_getter = target_node_getter
         self.source_nodes = source_nodes or {}
         self.target_nodes = target_nodes or {}
         self.repo_name = repo_name
         self.source_repo_name = source_repo_name or repo_name
         self.max_file_size_limit = max_file_size_limit
 
     def render_patchset(self, patchset, source_ref=None, target_ref=None):
         diffset = AttributeDict(dict(
             lines_added=0,
             lines_deleted=0,
             changed_files=0,
             files=[],
             file_stats={},
             limited_diff=isinstance(patchset, LimitedDiffContainer),
             repo_name=self.repo_name,
             source_repo_name=self.source_repo_name,
             source_ref=source_ref,
             target_ref=target_ref,
         ))
         for patch in patchset:
             diffset.file_stats[patch['filename']] = patch['stats']
             filediff = self.render_patch(patch)
             filediff.diffset = StrictAttributeDict(dict(
                 source_ref=diffset.source_ref,
                 target_ref=diffset.target_ref,
                 repo_name=diffset.repo_name,
                 source_repo_name=diffset.source_repo_name,
             ))
             diffset.files.append(filediff)
             diffset.changed_files += 1
             if not patch['stats']['binary']:
                 diffset.lines_added += patch['stats']['added']
                 diffset.lines_deleted += patch['stats']['deleted']
 
         return diffset
 
     _lexer_cache = {}
 
     def _get_lexer_for_filename(self, filename, filenode=None):
         # cached because we might need to call it twice for source/target
         if filename not in self._lexer_cache:
             if filenode:
                 lexer = filenode.lexer
                 extension = filenode.extension
             else:
                 lexer = FileNode.get_lexer(filename=filename)
                 extension = filename.split('.')[-1]
 
             lexer = get_custom_lexer(extension) or lexer
             self._lexer_cache[filename] = lexer
         return self._lexer_cache[filename]
 
     def render_patch(self, patch):
         log.debug('rendering diff for %r', patch['filename'])
 
         source_filename = patch['original_filename']
         target_filename = patch['filename']
 
         source_lexer = plain_text_lexer
         target_lexer = plain_text_lexer
 
         if not patch['stats']['binary']:
-            if self.highlight_mode == self.HL_REAL:
+            node_hl_mode = self.HL_NONE if patch['chunks'] == [] else None
+            hl_mode = node_hl_mode or self.highlight_mode
+
+            if hl_mode == self.HL_REAL:
                 if (source_filename and patch['operation'] in ('D', 'M')
                     and source_filename not in self.source_nodes):
                         self.source_nodes[source_filename] = (
                             self.source_node_getter(source_filename))
 
                 if (target_filename and patch['operation'] in ('A', 'M')
                     and target_filename not in self.target_nodes):
                         self.target_nodes[target_filename] = (
                             self.target_node_getter(target_filename))
 
-            elif self.highlight_mode == self.HL_FAST:
+            elif hl_mode == self.HL_FAST:
                 source_lexer = self._get_lexer_for_filename(source_filename)
                 target_lexer = self._get_lexer_for_filename(target_filename)
 
         source_file = self.source_nodes.get(source_filename, source_filename)
         target_file = self.target_nodes.get(target_filename, target_filename)
 
         source_filenode, target_filenode = None, None
 
         # TODO: dan: FileNode.lexer works on the content of the file - which
         # can be slow - issue #4289 explains a lexer clean up - which once
         # done can allow caching a lexer for a filenode to avoid the file lookup
         if isinstance(source_file, FileNode):
             source_filenode = source_file
             #source_lexer = source_file.lexer
             source_lexer = self._get_lexer_for_filename(source_filename)
             source_file.lexer = source_lexer
 
         if isinstance(target_file, FileNode):
             target_filenode = target_file
             #target_lexer = target_file.lexer
             target_lexer = self._get_lexer_for_filename(target_filename)
             target_file.lexer = target_lexer
 
         source_file_path, target_file_path = None, None
 
         if source_filename != '/dev/null':
             source_file_path = source_filename
         if target_filename != '/dev/null':
             target_file_path = target_filename
 
         source_file_type = source_lexer.name
         target_file_type = target_lexer.name
 
         filediff = AttributeDict({
             'source_file_path': source_file_path,
             'target_file_path': target_file_path,
             'source_filenode': source_filenode,
             'target_filenode': target_filenode,
             'source_file_type': target_file_type,
             'target_file_type': source_file_type,
             'patch': {'filename': patch['filename'], 'stats': patch['stats']},
             'operation': patch['operation'],
             'source_mode': patch['stats']['old_mode'],
             'target_mode': patch['stats']['new_mode'],
             'limited_diff': isinstance(patch, LimitedDiffContainer),
             'hunks': [],
             'hunk_ops': None,
             'diffset': self,
         })
-
-        for hunk in patch['chunks'][1:]:
+        file_chunks = patch['chunks'][1:]
+        for hunk in file_chunks:
             hunkbit = self.parse_hunk(hunk, source_file, target_file)
             hunkbit.source_file_path = source_file_path
             hunkbit.target_file_path = target_file_path
             filediff.hunks.append(hunkbit)
 
         # Simulate hunk on OPS type line which doesn't really contain any diff
         # this allows commenting on those
-        actions = []
-        for op_id, op_text in filediff.patch['stats']['ops'].items():
-            if op_id == DEL_FILENODE:
-                actions.append(u'file was deleted')
-            elif op_id == BIN_FILENODE:
-                actions.append(u'binary diff hidden')
-            else:
-                actions.append(safe_unicode(op_text))
-        action_line = u'FILE WITHOUT CONTENT: ' + \
-                      u', '.join(map(string.upper, actions)) or u'UNDEFINED_ACTION'
+        if not file_chunks:
+            actions = []
+            for op_id, op_text in filediff.patch['stats']['ops'].items():
+                if op_id == DEL_FILENODE:
+                    actions.append(u'file was deleted')
+                elif op_id == BIN_FILENODE:
+                    actions.append(u'binary diff hidden')
+                else:
+                    actions.append(safe_unicode(op_text))
+            action_line = u'NO CONTENT: ' + \
+                          u', '.join(actions) or u'UNDEFINED_ACTION'
 
-        hunk_ops = {'source_length': 0, 'source_start': 0,
-                    'lines': [
-                        {'new_lineno': 0, 'old_lineno': 1,
-                         'action': 'unmod', 'line': action_line}
-                    ],
-                    'section_header': u'', 'target_start': 1, 'target_length': 1}
+            hunk_ops = {'source_length': 0, 'source_start': 0,
+                        'lines': [
+                            {'new_lineno': 0, 'old_lineno': 1,
+                             'action': 'unmod-no-hl', 'line': action_line}
+                        ],
+                        'section_header': u'', 'target_start': 1, 'target_length': 1}
 
-        hunkbit = self.parse_hunk(hunk_ops, source_file, target_file)
-        hunkbit.source_file_path = source_file_path
-        hunkbit.target_file_path = target_file_path
-        filediff.hunk_ops = hunkbit
+            hunkbit = self.parse_hunk(hunk_ops, source_file, target_file)
+            hunkbit.source_file_path = source_file_path
+            hunkbit.target_file_path = target_file_path
+            filediff.hunk_ops = hunkbit
         return filediff
 
     def parse_hunk(self, hunk, source_file, target_file):
         result = AttributeDict(dict(
             source_start=hunk['source_start'],
             source_length=hunk['source_length'],
             target_start=hunk['target_start'],
             target_length=hunk['target_length'],
             section_header=hunk['section_header'],
             lines=[],
         ))
         before, after = [], []
 
         for line in hunk['lines']:
-
-            if line['action'] == 'unmod':
+            if line['action'] in ['unmod', 'unmod-no-hl']:
+                no_hl = line['action'] == 'unmod-no-hl'
                 result.lines.extend(
-                    self.parse_lines(before, after, source_file, target_file))
+                    self.parse_lines(before, after, source_file, target_file, no_hl=no_hl))
                 after.append(line)
                 before.append(line)
             elif line['action'] == 'add':
                 after.append(line)
             elif line['action'] == 'del':
                 before.append(line)
             elif line['action'] == 'old-no-nl':
                 before.append(line)
             elif line['action'] == 'new-no-nl':
                 after.append(line)
 
+        all_actions = [x['action'] for x in after] + [x['action'] for x in before]
+        no_hl = {x for x in all_actions} == {'unmod-no-hl'}
         result.lines.extend(
-            self.parse_lines(before, after, source_file, target_file))
+            self.parse_lines(before, after, source_file, target_file, no_hl=no_hl))
+        # NOTE(marcink): we must keep list() call here so we can cache the result...
         result.unified = list(self.as_unified(result.lines))
         result.sideside = result.lines
 
         return result
 
-    def parse_lines(self, before_lines, after_lines, source_file, target_file):
+    def parse_lines(self, before_lines, after_lines, source_file, target_file,
+                    no_hl=False):
         # TODO: dan: investigate doing the diff comparison and fast highlighting
         # on the entire before and after buffered block lines rather than by
         # line, this means we can get better 'fast' highlighting if the context
         # allows it - eg.
         # line 4: """
         # line 5: this gets highlighted as a string
         # line 6: """
 
         lines = []
 
         before_newline = AttributeDict()
         after_newline = AttributeDict()
         if before_lines and before_lines[-1]['action'] == 'old-no-nl':
             before_newline_line = before_lines.pop(-1)
             before_newline.content = '\n {}'.format(
                 render_tokenstream(
                     [(x[0], '', x[1])
                      for x in [('nonl', before_newline_line['line'])]]))
 
         if after_lines and after_lines[-1]['action'] == 'new-no-nl':
             after_newline_line = after_lines.pop(-1)
             after_newline.content = '\n {}'.format(
                 render_tokenstream(
                     [(x[0], '', x[1])
                      for x in [('nonl', after_newline_line['line'])]]))
 
         while before_lines or after_lines:
             before, after = None, None
             before_tokens, after_tokens = None, None
 
             if before_lines:
                 before = before_lines.pop(0)
             if after_lines:
                 after = after_lines.pop(0)
 
             original = AttributeDict()
             modified = AttributeDict()
 
             if before:
                 if before['action'] == 'old-no-nl':
                     before_tokens = [('nonl', before['line'])]
                 else:
                     before_tokens = self.get_line_tokens(
-                        line_text=before['line'],
-                        line_number=before['old_lineno'],
-                        file=source_file)
+                        line_text=before['line'], line_number=before['old_lineno'],
+                        input_file=source_file, no_hl=no_hl)
                 original.lineno = before['old_lineno']
                 original.content = before['line']
                 original.action = self.action_to_op(before['action'])
 
                 original.get_comment_args = (
                     source_file, 'o', before['old_lineno'])
 
             if after:
                 if after['action'] == 'new-no-nl':
                     after_tokens = [('nonl', after['line'])]
                 else:
                     after_tokens = self.get_line_tokens(
                         line_text=after['line'], line_number=after['new_lineno'],
-                        file=target_file)
+                        input_file=target_file, no_hl=no_hl)
                 modified.lineno = after['new_lineno']
                 modified.content = after['line']
                 modified.action = self.action_to_op(after['action'])
 
-                modified.get_comment_args = (
-                    target_file, 'n', after['new_lineno'])
+                modified.get_comment_args = (target_file, 'n', after['new_lineno'])
 
             # diff the lines
             if before_tokens and after_tokens:
                 o_tokens, m_tokens, similarity = tokens_diff(
                     before_tokens, after_tokens)
                 original.content = render_tokenstream(o_tokens)
                 modified.content = render_tokenstream(m_tokens)
             elif before_tokens:
                 original.content = render_tokenstream(
                     [(x[0], '', x[1]) for x in before_tokens])
             elif after_tokens:
                 modified.content = render_tokenstream(
                     [(x[0], '', x[1]) for x in after_tokens])
 
             if not before_lines and before_newline:
                 original.content += before_newline.content
                 before_newline = None
             if not after_lines and after_newline:
                 modified.content += after_newline.content
                 after_newline = None
 
             lines.append(AttributeDict({
                 'original': original,
                 'modified': modified,
             }))
 
         return lines
 
-    def get_line_tokens(self, line_text, line_number, file=None):
+    def get_line_tokens(self, line_text, line_number, input_file=None, no_hl=False):
         filenode = None
         filename = None
 
-        if isinstance(file, basestring):
-            filename = file
-        elif isinstance(file, FileNode):
-            filenode = file
-            filename = file.unicode_path
+        if isinstance(input_file, basestring):
+            filename = input_file
+        elif isinstance(input_file, FileNode):
+            filenode = input_file
+            filename = input_file.unicode_path
 
-        if self.highlight_mode == self.HL_REAL and filenode:
+        hl_mode = self.HL_NONE if no_hl else self.highlight_mode
+        if hl_mode == self.HL_REAL and filenode:
             lexer = self._get_lexer_for_filename(filename)
-            file_size_allowed = file.size < self.max_file_size_limit
+            file_size_allowed = input_file.size < self.max_file_size_limit
             if line_number and file_size_allowed:
                 return self.get_tokenized_filenode_line(
-                    file, line_number, lexer)
+                    input_file, line_number, lexer)
 
-        if self.highlight_mode in (self.HL_REAL, self.HL_FAST) and filename:
+        if hl_mode in (self.HL_REAL, self.HL_FAST) and filename:
             lexer = self._get_lexer_for_filename(filename)
             return list(tokenize_string(line_text, lexer))
 
         return list(tokenize_string(line_text, plain_text_lexer))
 
     def get_tokenized_filenode_line(self, filenode, line_number, lexer=None):
 
         if filenode not in self.highlighted_filenodes:
             tokenized_lines = filenode_as_lines_tokens(filenode, lexer)
             self.highlighted_filenodes[filenode] = tokenized_lines
         return self.highlighted_filenodes[filenode][line_number - 1]
 
     def action_to_op(self, action):
         return {
             'add': '+',
             'del': '-',
             'unmod': ' ',
+            'unmod-no-hl': ' ',
             'old-no-nl': ' ',
             'new-no-nl': ' ',
         }.get(action, action)
 
     def as_unified(self, lines):
         """
         Return a generator that yields the lines of a diff in unified order
         """
         def generator():
             buf = []
             for line in lines:
 
                 if buf and not line.original or line.original.action == ' ':
                     for b in buf:
                         yield b
                     buf = []
 
                 if line.original:
                     if line.original.action == ' ':
                         yield (line.original.lineno, line.modified.lineno,
                                line.original.action, line.original.content,
                                line.original.get_comment_args)
                         continue
 
                     if line.original.action == '-':
                         yield (line.original.lineno, None,
                                line.original.action, line.original.content,
                                line.original.get_comment_args)
 
                     if line.modified.action == '+':
                         buf.append((
                             None, line.modified.lineno,
                             line.modified.action, line.modified.content,
                             line.modified.get_comment_args))
                         continue
 
                 if line.modified:
                     yield (None, line.modified.lineno,
                            line.modified.action, line.modified.content,
                            line.modified.get_comment_args)
 
             for b in buf:
                 yield b
 
         return generator()

rhodecode/lib/diffs.py

@@ -1,1228 +1,1228 b''
 # -*- coding: utf-8 -*-
 
 # Copyright (C) 2011-2018 RhodeCode GmbH
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License, version 3
 # (only), as published by the Free Software Foundation.
 #
 # 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 Affero General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #
 # This program is dual-licensed. If you wish to learn more about the
 # RhodeCode Enterprise Edition, including its added features, Support services,
 # and proprietary license terms, please see https://rhodecode.com/licenses/
 
 
 """
 Set of diffing helpers, previously part of vcs
 """
 
 import os
 import re
 import bz2
 
 import collections
 import difflib
 import logging
 import cPickle as pickle
 from itertools import tee, imap
 
 from rhodecode.lib.vcs.exceptions import VCSError
 from rhodecode.lib.vcs.nodes import FileNode, SubModuleNode
 from rhodecode.lib.utils2 import safe_unicode, safe_str
 
 log = logging.getLogger(__name__)
 
 # define max context, a file with more than this numbers of lines is unusable
 # in browser anyway
 MAX_CONTEXT = 1024 * 1014
 
 
 class OPS(object):
     ADD = 'A'
     MOD = 'M'
     DEL = 'D'
 
 
 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
     # protect against IntOverflow when passing HUGE context
     if context > MAX_CONTEXT:
         context = MAX_CONTEXT
 
     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.commit.repository
     old_commit = filenode_old.commit or repo.EMPTY_COMMIT
     new_commit = filenode_new.commit
 
     vcs_gitdiff = repo.get_diff(
         old_commit, new_commit, filenode_new.path,
         ignore_whitespace, context, path1=filenode_old.path)
     return vcs_gitdiff
 
 NEW_FILENODE = 1
 DEL_FILENODE = 2
 MOD_FILENODE = 3
 RENAMED_FILENODE = 4
 COPIED_FILENODE = 5
 CHMOD_FILENODE = 6
 BIN_FILENODE = 7
 
 
 class 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 __getitem__(self, key):
         return self.diff.__getitem__(key)
 
     def __iter__(self):
         for l in self.diff:
             yield l
 
 
 class Action(object):
     """
     Contains constants for the action value of the lines in a parsed diff.
     """
 
     ADD = 'add'
     DELETE = 'del'
     UNMODIFIED = 'unmod'
 
     CONTEXT = 'context'
     OLD_NO_NL = 'old-no-nl'
     NEW_NO_NL = 'new-no-nl'
 
 
 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.
 
     .. note:: Unicode handling
 
        The original diffs are a byte sequence and can contain filenames
        in mixed encodings. This class generally returns `unicode` objects
        since the result is intended for presentation to the user.
 
     """
     _chunk_re = re.compile(r'^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@(.*)')
     _newline_marker = re.compile(r'^\\ No newline at end of file')
 
     # used for inline highlighter word split
     _token_re = re.compile(r'()(&gt;|&lt;|&amp;|\W+?)')
 
     # collapse ranges of commits over given number
     _collapse_commits_over = 5
 
     def __init__(self, diff, format='gitdiff', diff_limit=None,
                  file_limit=None, show_full_diff=True):
         """
         :param diff: A `Diff` object representing a diff from a vcs backend
         :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
         """
         self._diff = diff
         self._format = format
         self.adds = 0
         self.removes = 0
         # calculate diff size
         self.diff_limit = diff_limit
         self.file_limit = file_limit
         self.show_full_diff = show_full_diff
         self.cur_diff_size = 0
         self.parsed = False
         self.parsed_diff = []
 
         log.debug('Initialized DiffProcessor with %s mode', format)
         if format == 'gitdiff':
             self.differ = self._highlight_line_difflib
             self._parser = self._parse_gitdiff
         else:
             self.differ = self._highlight_line_udiff
             self._parser = self._new_parse_gitdiff
 
     def _copy_iterator(self):
         """
         make a fresh copy of generator, we should not iterate thru
         an original as it's needed for repeating operations on
         this instance of DiffProcessor
         """
         self.__udiff, iterator_copy = tee(self.__udiff)
         return iterator_copy
 
     def _escaper(self, string):
         """
         Escaper for diff escapes special chars and checks the diff limit
 
         :param string:
         """
         self.cur_diff_size += len(string)
 
         if not self.show_full_diff and (self.cur_diff_size > self.diff_limit):
             raise DiffLimitExceeded('Diff Limit Exceeded')
 
         return 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'] == Action.DELETE:
             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'] == 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 _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
 
         for chunk in self._diff.chunks():
             head = chunk.header
 
             diff = imap(self._escaper, self.diff_splitter(chunk.diff))
             raw_diff = chunk.raw
             limited_diff = False
             exceeds_limit = False
 
             op = None
             stats = {
                 'added': 0,
                 'deleted': 0,
                 'binary': False,
                 'ops': {},
             }
 
             if head['deleted_file_mode']:
                 op = OPS.DEL
                 stats['binary'] = True
                 stats['ops'][DEL_FILENODE] = 'deleted file'
 
             elif head['new_file_mode']:
                 op = OPS.ADD
                 stats['binary'] = True
                 stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']
             else:  # modify operation, can be copy, rename or chmod
 
                 # CHMOD
                 if head['new_mode'] and head['old_mode']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][CHMOD_FILENODE] = (
                         'modified file chmod %s => %s' % (
                             head['old_mode'], head['new_mode']))
                 # RENAME
                 if head['rename_from'] != head['rename_to']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][RENAMED_FILENODE] = (
                         'file renamed from %s to %s' % (
                             head['rename_from'], head['rename_to']))
                 # COPY
                 if head.get('copy_from') and head.get('copy_to'):
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][COPIED_FILENODE] = (
                         'file copied from %s to %s' % (
                             head['copy_from'], head['copy_to']))
 
                 # If our new parsed headers didn't match anything fallback to
                 # old style detection
                 if op is None:
                     if not head['a_file'] and head['b_file']:
                         op = OPS.ADD
                         stats['binary'] = True
                         stats['ops'][NEW_FILENODE] = 'new file'
 
                     elif head['a_file'] and not head['b_file']:
                         op = OPS.DEL
                         stats['binary'] = True
                         stats['ops'][DEL_FILENODE] = 'deleted file'
 
                 # it's not ADD not DELETE
                 if op is None:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][MOD_FILENODE] = 'modified file'
 
             # a real non-binary diff
             if head['a_file'] or head['b_file']:
                 try:
                     raw_diff, chunks, _stats = self._parse_lines(diff)
                     stats['binary'] = False
                     stats['added'] = _stats[0]
                     stats['deleted'] = _stats[1]
                     # explicit mark that it's a modified file
                     if op == OPS.MOD:
                         stats['ops'][MOD_FILENODE] = 'modified file'
                     exceeds_limit = len(raw_diff) > self.file_limit
 
                     # changed from _escaper function so we validate size of
                     # each file instead of the whole diff
                     # diff will hide big files but still show small ones
                     # from my tests, big files are fairly safe to be parsed
                     # but the browser is the bottleneck
                     if not self.show_full_diff and exceeds_limit:
                         raise DiffLimitExceeded('File Limit Exceeded')
 
                 except DiffLimitExceeded:
                     diff_container = lambda _diff: \
                         LimitedDiffContainer(
                             self.diff_limit, self.cur_diff_size, _diff)
 
                     exceeds_limit = len(raw_diff) > self.file_limit
                     limited_diff = True
                     chunks = []
 
             else:  # GIT format binary patch, or possibly empty diff
                 if head['bin_patch']:
                     # we have operation already extracted, but we mark simply
                     # it's a diff we wont show for binary files
                     stats['ops'][BIN_FILENODE] = 'binary diff hidden'
                 chunks = []
 
             if chunks and not self.show_full_diff and op == OPS.DEL:
                 # if not full diff mode show deleted file contents
                 # TODO: anderson: if the view is not too big, there is no way
                 # to see the content of the file
                 chunks = []
 
             chunks.insert(0, [{
                                   'old_lineno': '',
                                   'new_lineno': '',
                                   'action': Action.CONTEXT,
                                   'line': msg,
                               } for _op, msg in stats['ops'].iteritems()
                               if _op not in [MOD_FILENODE]])
 
             _files.append({
                 'filename': safe_unicode(head['b_path']),
                 'old_revision': head['a_blob_id'],
                 'new_revision': head['b_blob_id'],
                 'chunks': chunks,
                 'raw_diff': safe_unicode(raw_diff),
                 'operation': op,
                 'stats': stats,
                 'exceeds_limit': exceeds_limit,
                 'is_limited_diff': limited_diff,
             })
 
         sorter = lambda info: {OPS.ADD: 0, OPS.MOD: 1,
                                OPS.DEL: 2}.get(info['operation'])
 
         if not inline_diff:
             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 (
                                 Action.UNMODIFIED, Action.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 _check_large_diff(self):
         log.debug('Diff exceeds current diff_limit of %s', self.diff_limit)
         if not self.show_full_diff and (self.cur_diff_size > self.diff_limit):
             raise DiffLimitExceeded('Diff Limit `%s` Exceeded', self.diff_limit)
 
     # FIXME: NEWDIFFS: dan: this replaces _parse_gitdiff
     def _new_parse_gitdiff(self, inline_diff=True):
         _files = []
 
         # this can be overriden later to a LimitedDiffContainer type
         diff_container = lambda arg: arg
 
         for chunk in self._diff.chunks():
             head = chunk.header
             log.debug('parsing diff %r', head)
 
             raw_diff = chunk.raw
             limited_diff = False
             exceeds_limit = False
 
             op = None
             stats = {
                 'added': 0,
                 'deleted': 0,
                 'binary': False,
                 'old_mode': None,
                 'new_mode': None,
                 'ops': {},
             }
             if head['old_mode']:
                 stats['old_mode'] = head['old_mode']
             if head['new_mode']:
                 stats['new_mode'] = head['new_mode']
             if head['b_mode']:
                 stats['new_mode'] = head['b_mode']
 
             # delete file
             if head['deleted_file_mode']:
                 op = OPS.DEL
                 stats['binary'] = True
                 stats['ops'][DEL_FILENODE] = 'deleted file'
 
             # new file
             elif head['new_file_mode']:
                 op = OPS.ADD
                 stats['binary'] = True
                 stats['old_mode'] = None
                 stats['new_mode'] = head['new_file_mode']
                 stats['ops'][NEW_FILENODE] = 'new file %s' % head['new_file_mode']
 
             # modify operation, can be copy, rename or chmod
             else:
                 # CHMOD
                 if head['new_mode'] and head['old_mode']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][CHMOD_FILENODE] = (
                         'modified file chmod %s => %s' % (
                             head['old_mode'], head['new_mode']))
 
                 # RENAME
                 if head['rename_from'] != head['rename_to']:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['renamed'] = (head['rename_from'], head['rename_to'])
                     stats['ops'][RENAMED_FILENODE] = (
                         'file renamed from %s to %s' % (
                             head['rename_from'], head['rename_to']))
                 # COPY
                 if head.get('copy_from') and head.get('copy_to'):
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['copied'] = (head['copy_from'], head['copy_to'])
                     stats['ops'][COPIED_FILENODE] = (
                         'file copied from %s to %s' % (
                             head['copy_from'], head['copy_to']))
 
                 # If our new parsed headers didn't match anything fallback to
                 # old style detection
                 if op is None:
                     if not head['a_file'] and head['b_file']:
                         op = OPS.ADD
                         stats['binary'] = True
                         stats['new_file'] = True
                         stats['ops'][NEW_FILENODE] = 'new file'
 
                     elif head['a_file'] and not head['b_file']:
                         op = OPS.DEL
                         stats['binary'] = True
                         stats['ops'][DEL_FILENODE] = 'deleted file'
 
                 # it's not ADD not DELETE
                 if op is None:
                     op = OPS.MOD
                     stats['binary'] = True
                     stats['ops'][MOD_FILENODE] = 'modified file'
 
             # a real non-binary diff
             if head['a_file'] or head['b_file']:
                 # simulate splitlines, so we keep the line end part
                 diff = self.diff_splitter(chunk.diff)
 
                 # append each file to the diff size
                 raw_chunk_size = len(raw_diff)
 
                 exceeds_limit = raw_chunk_size > self.file_limit
                 self.cur_diff_size += raw_chunk_size
 
                 try:
                     # Check each file instead of the whole diff.
                     # Diff will hide big files but still show small ones.
                     # From the tests big files are fairly safe to be parsed
                     # but the browser is the bottleneck.
                     if not self.show_full_diff and exceeds_limit:
                         log.debug('File `%s` exceeds current file_limit of %s',
                                   safe_unicode(head['b_path']), self.file_limit)
                         raise DiffLimitExceeded(
                             'File Limit %s Exceeded', self.file_limit)
 
                     self._check_large_diff()
 
                     raw_diff, chunks, _stats = self._new_parse_lines(diff)
                     stats['binary'] = False
                     stats['added'] = _stats[0]
                     stats['deleted'] = _stats[1]
                     # explicit mark that it's a modified file
                     if op == OPS.MOD:
                         stats['ops'][MOD_FILENODE] = 'modified file'
 
                 except DiffLimitExceeded:
                     diff_container = lambda _diff: \
                         LimitedDiffContainer(
                             self.diff_limit, self.cur_diff_size, _diff)
 
                     limited_diff = True
                     chunks = []
 
             else:  # GIT format binary patch, or possibly empty diff
                 if head['bin_patch']:
                     # we have operation already extracted, but we mark simply
                     # it's a diff we wont show for binary files
                     stats['ops'][BIN_FILENODE] = 'binary diff hidden'
                 chunks = []
 
             # Hide content of deleted node by setting empty chunks
             if chunks and not self.show_full_diff and op == OPS.DEL:
                 # if not full diff mode show deleted file contents
                 # TODO: anderson: if the view is not too big, there is no way
                 # to see the content of the file
                 chunks = []
 
             chunks.insert(
                 0, [{'old_lineno': '',
                      'new_lineno': '',
                      'action': Action.CONTEXT,
                      'line': msg,
                      } for _op, msg in stats['ops'].iteritems()
                     if _op not in [MOD_FILENODE]])
 
             original_filename = safe_unicode(head['a_path'])
             _files.append({
                 'original_filename': original_filename,
                 'filename': safe_unicode(head['b_path']),
                 'old_revision': head['a_blob_id'],
                 'new_revision': head['b_blob_id'],
                 'chunks': chunks,
                 'raw_diff': safe_unicode(raw_diff),
                 'operation': op,
                 'stats': stats,
                 'exceeds_limit': exceeds_limit,
                 'is_limited_diff': limited_diff,
             })
 
         sorter = lambda info: {OPS.ADD: 0, OPS.MOD: 1,
                                OPS.DEL: 2}.get(info['operation'])
 
         return diff_container(sorted(_files, key=sorter))
 
     # FIXME: NEWDIFFS: dan: this gets replaced by _new_parse_lines
     def _parse_lines(self, diff_iter):
         """
         Parse the diff an return data for the template.
         """
 
         stats = [0, 0]
         chunks = []
         raw_diff = []
 
         try:
             line = diff_iter.next()
 
             while line:
                 raw_diff.append(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':     Action.CONTEXT,
                             'line':       line,
                         })
 
                 line = diff_iter.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 = Action.ADD
                         stats[0] += 1
                     elif command == '-':
                         affects_old = True
                         action = Action.DELETE
                         stats[1] += 1
                     else:
                         affects_old = affects_new = True
                         action = Action.UNMODIFIED
 
                     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)
                         })
                         raw_diff.append(line)
 
                     line = diff_iter.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':       Action.CONTEXT,
                             'line':         self._clean_line(line, command)
                         })
 
         except StopIteration:
             pass
         return ''.join(raw_diff), chunks, stats
 
     # FIXME: NEWDIFFS: dan: this replaces _parse_lines
     def _new_parse_lines(self, diff_iter):
         """
         Parse the diff an return data for the template.
         """
 
         stats = [0, 0]
         chunks = []
         raw_diff = []
 
         try:
             line = diff_iter.next()
 
             while line:
                 raw_diff.append(line)
                 # match header e.g @@ -0,0 +1 @@\n'
                 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]]
 
                 lines = []
                 hunk = {
                     'section_header': gr[-1],
                     'source_start': old_line,
                     'source_length': old_end,
                     'target_start': new_line,
                     'target_length': new_end,
                     'lines': lines,
                 }
                 chunks.append(hunk)
 
                 old_line -= 1
                 new_line -= 1
 
                 context = len(gr) == 5
                 old_end += old_line
                 new_end += new_line
 
                 line = diff_iter.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 = Action.ADD
                         stats[0] += 1
                     elif command == '-':
                         affects_old = True
                         action = Action.DELETE
                         stats[1] += 1
                     else:
                         affects_old = affects_new = True
                         action = Action.UNMODIFIED
 
                     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)
                         })
                     raw_diff.append(line)
 
                     line = diff_iter.next()
 
                     if self._newline_marker.match(line):
                         # we need to append to lines, since this is not
                         # counted in the line specs of diff
                         if affects_old:
                             action = Action.OLD_NO_NL
                         elif affects_new:
                             action = Action.NEW_NO_NL
                         else:
                             raise Exception('invalid context for no newline')
 
                         lines.append({
                             'old_lineno':   None,
                             'new_lineno':   None,
                             'action':       action,
                             'line':         self._clean_line(line, command)
                         })
 
         except StopIteration:
             pass
 
         return ''.join(raw_diff), 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
 
     @classmethod
     def diff_splitter(cls, string):
         """
         Diff split that emulates .splitlines() but works only on \n
         """
         if not string:
             return
         elif string == '\n':
             yield u'\n'
         else:
 
             has_newline = string.endswith('\n')
             elements = string.split('\n')
             if has_newline:
                 # skip last element as it's empty string from newlines
                 elements = elements[:-1]
 
             len_elements = len(elements)
 
             for cnt, line in enumerate(elements, start=1):
                 last_line = cnt == len_elements
                 if last_line and not has_newline:
                     yield safe_unicode(line)
                 else:
                     yield safe_unicode(line) + '\n'
 
     def prepare(self, inline_diff=True):
         """
         Prepare the passed udiff for HTML rendering.
 
         :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 diff as a byte string
         """
         return self._diff.raw
 
     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
         """
         # TODO(marcink): not sure how to pass in translator
         # here in an efficient way, leave the _ for proper gettext extraction
         _ = lambda s: s
 
         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" class="tooltip"
                 title="%(title)s">%(label)s</a>''' % {
                     'title': _('Click to select line'),
                     '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
 
                     if change['action'] != Action.CONTEXT:
                         anchor_link = True
                     else:
                         anchor_link = False
 
                     ###########################################################
                     # COMMENT ICONS
                     ###########################################################
                     _html.append('''\t<td class="add-comment-line"><span class="add-comment-content">''')
 
                     if enable_comments and change['action'] != Action.CONTEXT:
                         _html.append('''<a href="#"><span class="icon-comment-add"></span></a>''')
 
                     _html.append('''</span></td><td class="comment-toggle tooltip" title="Toggle Comment Thread"><i class="icon-comment"></i></td>\n''')
 
                     ###########################################################
                     # 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(anchor_link, 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(anchor_link, change['new_lineno'],
                                             '#%s' % anchor_new)
                     })
                     _html.append('''</td>\n''')
                     ###########################################################
                     # CODE
                     ###########################################################
                     code_classes = [code_class]
                     if (not enable_comments or
                             change['action'] == Action.CONTEXT):
                         code_classes.append('no-comment')
                     _html.append('\t<td class="%s">' % ' '.join(code_classes))
                     _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 get_context_of_line(
             self, path, diff_line=None, context_before=3, context_after=3):
         """
         Returns the context lines for the specified diff line.
 
         :type diff_line: :class:`DiffLineNumber`
         """
         assert self.parsed, "DiffProcessor is not initialized."
 
         if None not in diff_line:
             raise ValueError(
                 "Cannot specify both line numbers: {}".format(diff_line))
 
         file_diff = self._get_file_diff(path)
         chunk, idx = self._find_chunk_line_index(file_diff, diff_line)
 
         first_line_to_include = max(idx - context_before, 0)
         first_line_after_context = idx + context_after + 1
         context_lines = chunk[first_line_to_include:first_line_after_context]
 
         line_contents = [
             _context_line(line) for line in context_lines
             if _is_diff_content(line)]
         # TODO: johbo: Interim fixup, the diff chunks drop the final newline.
         # Once they are fixed, we can drop this line here.
         if line_contents:
             line_contents[-1] = (
                 line_contents[-1][0], line_contents[-1][1].rstrip('\n') + '\n')
         return line_contents
 
     def find_context(self, path, context, offset=0):
         """
         Finds the given `context` inside of the diff.
 
         Use the parameter `offset` to specify which offset the target line has
         inside of the given `context`. This way the correct diff line will be
         returned.
 
         :param offset: Shall be used to specify the offset of the main line
             within the given `context`.
         """
         if offset < 0 or offset >= len(context):
             raise ValueError(
                 "Only positive values up to the length of the context "
                 "minus one are allowed.")
 
         matches = []
         file_diff = self._get_file_diff(path)
 
         for chunk in file_diff['chunks']:
             context_iter = iter(context)
             for line_idx, line in enumerate(chunk):
                 try:
                     if _context_line(line) == context_iter.next():
                         continue
                 except StopIteration:
                     matches.append((line_idx, chunk))
                 context_iter = iter(context)
 
         # Increment position and triger StopIteration
         # if we had a match at the end
         line_idx += 1
         try:
             context_iter.next()
         except StopIteration:
             matches.append((line_idx, chunk))
 
         effective_offset = len(context) - offset
         found_at_diff_lines = [
             _line_to_diff_line_number(chunk[idx - effective_offset])
             for idx, chunk in matches]
 
         return found_at_diff_lines
 
     def _get_file_diff(self, path):
         for file_diff in self.parsed_diff:
             if file_diff['filename'] == path:
                 break
         else:
             raise FileNotInDiffException("File {} not in diff".format(path))
         return file_diff
 
     def _find_chunk_line_index(self, file_diff, diff_line):
         for chunk in file_diff['chunks']:
             for idx, line in enumerate(chunk):
                 if line['old_lineno'] == diff_line.old:
                     return chunk, idx
                 if line['new_lineno'] == diff_line.new:
                     return chunk, idx
         raise LineNotInDiffException(
             "The line {} is not part of the diff.".format(diff_line))
 
 
 def _is_diff_content(line):
     return line['action'] in (
         Action.UNMODIFIED, Action.ADD, Action.DELETE)
 
 
 def _context_line(line):
     return (line['action'], line['line'])
 
 
 DiffLineNumber = collections.namedtuple('DiffLineNumber', ['old', 'new'])
 
 
 def _line_to_diff_line_number(line):
     new_line_no = line['new_lineno'] or None
     old_line_no = line['old_lineno'] or None
     return DiffLineNumber(old=old_line_no, new=new_line_no)
 
 
 class FileNotInDiffException(Exception):
     """
     Raised when the context for a missing file is requested.
 
     If you request the context for a line in a file which is not part of the
     given diff, then this exception is raised.
     """
 
 
 class LineNotInDiffException(Exception):
     """
     Raised when the context for a missing line is requested.
 
     If you request the context for a line in a file and this line is not
     part of the given diff, then this exception is raised.
     """
 
 
 class DiffLimitExceeded(Exception):
     pass
 
 
 # NOTE(marcink): if diffs.mako change, probably this
 # needs a bump to next version
-CURRENT_DIFF_VERSION = 'v1'
+CURRENT_DIFF_VERSION = 'v2'
 
 
 def _cleanup_cache_file(cached_diff_file):
     # cleanup file to not store it "damaged"
     try:
         os.remove(cached_diff_file)
     except Exception:
         log.exception('Failed to cleanup path %s', cached_diff_file)
 
 
 def cache_diff(cached_diff_file, diff, commits):
 
     struct = {
         'version': CURRENT_DIFF_VERSION,
         'diff': diff,
         'commits': commits
     }
 
     try:
         with bz2.BZ2File(cached_diff_file, 'wb') as f:
             pickle.dump(struct, f)
         log.debug('Saved diff cache under %s', cached_diff_file)
     except Exception:
         log.warn('Failed to save cache', exc_info=True)
         _cleanup_cache_file(cached_diff_file)
 
 
 def load_cached_diff(cached_diff_file):
 
     default_struct = {
         'version': CURRENT_DIFF_VERSION,
         'diff': None,
         'commits': None
     }
 
     has_cache = os.path.isfile(cached_diff_file)
     if not has_cache:
         return default_struct
 
     data = None
     try:
         with bz2.BZ2File(cached_diff_file, 'rb') as f:
             data = pickle.load(f)
         log.debug('Loaded diff cache from %s', cached_diff_file)
     except Exception:
         log.warn('Failed to read diff cache file', exc_info=True)
 
     if not data:
         data = default_struct
 
     if not isinstance(data, dict):
         # old version of data ?
         data = default_struct
 
     # check version
     if data.get('version') != CURRENT_DIFF_VERSION:
         # purge cache
         _cleanup_cache_file(cached_diff_file)
         return default_struct
 
     return data
 
 
 def generate_diff_cache_key(*args):
     """
     Helper to generate a cache key using arguments
     """
     def arg_mapper(input_param):
         input_param = safe_str(input_param)
         # we cannot allow '/' in arguments since it would allow
         # subdirectory usage
         input_param.replace('/', '_')
         return input_param or None  # prevent empty string arguments
 
     return '_'.join([
         '{}' for i in range(len(args))]).format(*map(arg_mapper, args))
 
 
 def diff_cache_exist(cache_storage, *args):
     """
     Based on all generated arguments check and return a cache path
     """
     cache_key = generate_diff_cache_key(*args)
     cache_file_path = os.path.join(cache_storage, cache_key)
     # prevent path traversal attacks using some param that have e.g '../../'
     if not os.path.abspath(cache_file_path).startswith(cache_storage):
         raise ValueError('Final path must be within {}'.format(cache_storage))
 
     return cache_file_path

rhodecode/templates/codeblocks/diffs.mako

@@ -1,761 +1,761 b''
 <%namespace name="commentblock" file="/changeset/changeset_file_comment.mako"/>
 
 <%def name="diff_line_anchor(filename, line, type)"><%
 return '%s_%s_%i' % (h.safeid(filename), type, line)
 %></%def>
 
 <%def name="action_class(action)">
 <%
     return {
         '-': 'cb-deletion',
         '+': 'cb-addition',
         ' ': 'cb-context',
         }.get(action, 'cb-empty')
 %>
 </%def>
 
 <%def name="op_class(op_id)">
 <%
     return {
         DEL_FILENODE: 'deletion', # file deleted
         BIN_FILENODE: 'warning' # binary diff hidden
     }.get(op_id, 'addition')
 %>
 </%def>
 
 
 
 <%def name="render_diffset(diffset, commit=None,
 
     # collapse all file diff entries when there are more than this amount of files in the diff
     collapse_when_files_over=20,
 
     # collapse lines in the diff when more than this amount of lines changed in the file diff
     lines_changed_limit=500,
 
     # add a ruler at to the output
     ruler_at_chars=0,
 
     # show inline comments
     use_comments=False,
 
     # disable new comments
     disable_new_comments=False,
 
     # special file-comments that were deleted in previous versions
     # it's used for showing outdated comments for deleted files in a PR
     deleted_files_comments=None,
 
     # for cache purpose
     inline_comments=None
 
 )">
 %if use_comments:
 <div id="cb-comments-inline-container-template" class="js-template">
   ${inline_comments_container([], inline_comments)}
 </div>
 <div class="js-template" id="cb-comment-inline-form-template">
     <div class="comment-inline-form ac">
 
     %if c.rhodecode_user.username != h.DEFAULT_USER:
         ## render template for inline comments
         ${commentblock.comment_form(form_type='inline')}
     %else:
         ${h.form('', class_='inline-form comment-form-login', method='get')}
         <div class="pull-left">
             <div class="comment-help pull-right">
               ${_('You need to be logged in to leave comments.')} <a href="${h.route_path('login', _query={'came_from': h.current_route_path(request)})}">${_('Login now')}</a>
             </div>
         </div>
         <div class="comment-button pull-right">
          <button type="button" class="cb-comment-cancel" onclick="return Rhodecode.comments.cancelComment(this);">
           ${_('Cancel')}
          </button>
         </div>
         <div class="clearfix"></div>
         ${h.end_form()}
     %endif
     </div>
 </div>
 
 %endif
 <%
 collapse_all = len(diffset.files) > collapse_when_files_over
 %>
 
 %if c.diffmode == 'sideside':
 <style>
 .wrapper {
     max-width: 1600px !important;
 }
 </style>
 %endif
 
 %if ruler_at_chars:
 <style>
 .diff table.cb .cb-content:after {
     content: "";
     border-left: 1px solid blue;
     position: absolute;
     top: 0;
     height: 18px;
     opacity: .2;
     z-index: 10;
     //## +5 to account for diff action (+/-)
     left: ${ruler_at_chars + 5}ch;
 </style>
 %endif
 
 <div class="diffset ${disable_new_comments and 'diffset-comments-disabled'}">
     <div class="diffset-heading ${diffset.limited_diff and 'diffset-heading-warning' or ''}">
         %if commit:
             <div class="pull-right">
                 <a class="btn tooltip" title="${h.tooltip(_('Browse Files at revision {}').format(commit.raw_id))}" href="${h.route_path('repo_files',repo_name=diffset.repo_name, commit_id=commit.raw_id, f_path='')}">
                     ${_('Browse Files')}
                 </a>
             </div>
         %endif
         <h2 class="clearinner">
         %if commit:
             <a class="tooltip revision" title="${h.tooltip(commit.message)}" href="${h.route_path('repo_commit',repo_name=c.repo_name,commit_id=commit.raw_id)}">${'r%s:%s' % (commit.revision,h.short_id(commit.raw_id))}</a> -
             ${h.age_component(commit.date)} -
         %endif
 
         %if diffset.limited_diff:
             ${_('The requested commit is too big and content was truncated.')}
 
             ${_ungettext('%(num)s file changed.', '%(num)s files changed.', diffset.changed_files) % {'num': diffset.changed_files}}
             <a href="${h.current_route_path(request, fulldiff=1)}" onclick="return confirm('${_("Showing a big diff might take some time and resources, continue?")}')">${_('Show full diff')}</a>
         %else:
             ${_ungettext('%(num)s file changed: %(linesadd)s inserted, ''%(linesdel)s deleted',
                         '%(num)s files changed: %(linesadd)s inserted, %(linesdel)s deleted', diffset.changed_files) % {'num': diffset.changed_files, 'linesadd': diffset.lines_added, 'linesdel': diffset.lines_deleted}}
         %endif
 
         </h2>
     </div>
 
     %if diffset.has_hidden_changes:
         <p class="empty_data">${_('Some changes may be hidden')}</p>
     %elif not diffset.files:
         <p class="empty_data">${_('No files')}</p>
     %endif
 
     <div class="filediffs">
     ## initial value could be marked as False later on
     <% over_lines_changed_limit = False %>
     %for i, filediff in enumerate(diffset.files):
 
         <%
         lines_changed = filediff.patch['stats']['added'] + filediff.patch['stats']['deleted']
         over_lines_changed_limit = lines_changed > lines_changed_limit
         %>
 
         <input ${(collapse_all and 'checked' or '')} class="filediff-collapse-state" id="filediff-collapse-${id(filediff)}" type="checkbox">
         <div
             class="filediff"
             data-f-path="${filediff.patch['filename']}"
             id="a_${h.FID('', filediff.patch['filename'])}"
         >
 
         <label for="filediff-collapse-${id(filediff)}" class="filediff-heading">
             <div class="filediff-collapse-indicator"></div>
             ${diff_ops(filediff)}
         </label>
         ${diff_menu(filediff, use_comments=use_comments)}
         <table class="cb cb-diff-${c.diffmode} code-highlight ${(over_lines_changed_limit and 'cb-collapsed' or '')}">
 
         ## new/deleted/empty content case
         % if not filediff.hunks:
             ## Comment container, on "fakes" hunk that contains all data to render comments
             ${render_hunk_lines(c.diffmode, filediff.hunk_ops, use_comments=use_comments, inline_comments=inline_comments)}
         % endif
 
         %if filediff.limited_diff:
                 <tr class="cb-warning cb-collapser">
                     <td class="cb-text" ${(c.diffmode == 'unified' and 'colspan=4' or 'colspan=6')}>
                         ${_('The requested commit is too big and content was truncated.')} <a href="${h.current_route_path(request, fulldiff=1)}" onclick="return confirm('${_("Showing a big diff might take some time and resources, continue?")}')">${_('Show full diff')}</a>
                     </td>
                 </tr>
         %else:
             %if over_lines_changed_limit:
                     <tr class="cb-warning cb-collapser">
                         <td class="cb-text" ${(c.diffmode == 'unified' and 'colspan=4' or 'colspan=6')}>
                             ${_('This diff has been collapsed as it changes many lines, (%i lines changed)' % lines_changed)}
                             <a href="#" class="cb-expand"
                                onclick="$(this).closest('table').removeClass('cb-collapsed'); return false;">${_('Show them')}
                             </a>
                             <a href="#" class="cb-collapse"
                                onclick="$(this).closest('table').addClass('cb-collapsed'); return false;">${_('Hide them')}
                             </a>
                         </td>
                     </tr>
             %endif
         %endif
 
         % for hunk in filediff.hunks:
             <tr class="cb-hunk">
                 <td ${(c.diffmode == 'unified' and 'colspan=3' or '')}>
                     ## TODO: dan: add ajax loading of more context here
                     ## <a href="#">
                         <i class="icon-more"></i>
                     ## </a>
                 </td>
                 <td ${(c.diffmode == 'sideside' and 'colspan=5' or '')}>
                     @@
                     -${hunk.source_start},${hunk.source_length}
                     +${hunk.target_start},${hunk.target_length}
                     ${hunk.section_header}
                 </td>
             </tr>
             ${render_hunk_lines(c.diffmode, hunk, use_comments=use_comments, inline_comments=inline_comments)}
         % endfor
 
         <% unmatched_comments = (inline_comments or {}).get(filediff.patch['filename'], {}) %>
 
         ## outdated comments that do not fit into currently displayed lines
         % for lineno, comments in unmatched_comments.items():
 
             %if c.diffmode == 'unified':
                 % if loop.index == 0:
                 <tr class="cb-hunk">
                     <td colspan="3"></td>
                     <td>
                         <div>
                         ${_('Unmatched inline comments below')}
                         </div>
                     </td>
                 </tr>
                 % endif
                 <tr class="cb-line">
                     <td class="cb-data cb-context"></td>
                     <td class="cb-lineno cb-context"></td>
                     <td class="cb-lineno cb-context"></td>
                     <td class="cb-content cb-context">
                         ${inline_comments_container(comments, inline_comments)}
                     </td>
                 </tr>
             %elif c.diffmode == 'sideside':
                 % if loop.index == 0:
                 <tr class="cb-hunk">
                     <td colspan="2"></td>
                     <td class="cb-line" colspan="6">
                         <div>
                         ${_('Unmatched comments below')}
                         </div>
                     </td>
                 </tr>
                 % endif
                 <tr class="cb-line">
                     <td class="cb-data cb-context"></td>
                     <td class="cb-lineno cb-context"></td>
                     <td class="cb-content cb-context">
                         % if lineno.startswith('o'):
                             ${inline_comments_container(comments, inline_comments)}
                         % endif
                     </td>
 
                     <td class="cb-data cb-context"></td>
                     <td class="cb-lineno cb-context"></td>
                     <td class="cb-content cb-context">
                         % if lineno.startswith('n'):
                             ${inline_comments_container(comments, inline_comments)}
                         % endif
                     </td>
                 </tr>
             %endif
 
         % endfor
 
             </table>
         </div>
     %endfor
 
     ## outdated comments that are made for a file that has been deleted
     % for filename, comments_dict in (deleted_files_comments or {}).items():
         <%
             display_state = 'display: none'
             open_comments_in_file = [x for x in comments_dict['comments'] if x.outdated is False]
             if open_comments_in_file:
                 display_state = ''
         %>
         <div class="filediffs filediff-outdated" style="${display_state}">
             <input ${(collapse_all and 'checked' or '')} class="filediff-collapse-state" id="filediff-collapse-${id(filename)}" type="checkbox">
             <div class="filediff" data-f-path="${filename}"  id="a_${h.FID('', filename)}">
                 <label for="filediff-collapse-${id(filename)}" class="filediff-heading">
                     <div class="filediff-collapse-indicator"></div>
                     <span class="pill">
                         ## file was deleted
                         <strong>${filename}</strong>
                     </span>
                     <span class="pill-group" style="float: left">
                         ## file op, doesn't need translation
                         <span class="pill" op="removed">removed in this version</span>
                     </span>
                     <a class="pill filediff-anchor" href="#a_${h.FID('', filename)}">¶</a>
                     <span class="pill-group" style="float: right">
                         <span class="pill" op="deleted">-${comments_dict['stats']}</span>
                     </span>
                 </label>
 
                 <table class="cb cb-diff-${c.diffmode} code-highlight ${over_lines_changed_limit and 'cb-collapsed' or ''}">
                     <tr>
                         % if c.diffmode == 'unified':
                         <td></td>
                         %endif
 
                         <td></td>
                         <td class="cb-text cb-${op_class(BIN_FILENODE)}" ${c.diffmode == 'unified' and 'colspan=4' or 'colspan=5'}>
                         ${_('File was deleted in this version. There are still outdated/unresolved comments attached to it.')}
                         </td>
                     </tr>
                     %if c.diffmode == 'unified':
                     <tr class="cb-line">
                         <td class="cb-data cb-context"></td>
                         <td class="cb-lineno cb-context"></td>
                         <td class="cb-lineno cb-context"></td>
                         <td class="cb-content cb-context">
                             ${inline_comments_container(comments_dict['comments'], inline_comments)}
                         </td>
                     </tr>
                     %elif c.diffmode == 'sideside':
                     <tr class="cb-line">
                         <td class="cb-data cb-context"></td>
                         <td class="cb-lineno cb-context"></td>
                         <td class="cb-content cb-context"></td>
 
                         <td class="cb-data cb-context"></td>
                         <td class="cb-lineno cb-context"></td>
                         <td class="cb-content cb-context">
                             ${inline_comments_container(comments_dict['comments'], inline_comments)}
                         </td>
                     </tr>
                     %endif
                 </table>
             </div>
         </div>
     % endfor
 
 </div>
 </div>
 </%def>
 
 <%def name="diff_ops(filediff)">
 <%
 from rhodecode.lib.diffs import NEW_FILENODE, DEL_FILENODE, \
     MOD_FILENODE, RENAMED_FILENODE, CHMOD_FILENODE, BIN_FILENODE, COPIED_FILENODE
 %>
     <span class="pill">
         %if filediff.source_file_path and filediff.target_file_path:
             %if filediff.source_file_path != filediff.target_file_path:
                  ## file was renamed, or copied
                 %if RENAMED_FILENODE in filediff.patch['stats']['ops']:
                     <strong>${filediff.target_file_path}</strong> ⬅ <del>${filediff.source_file_path}</del>
                     <% final_path = filediff.target_file_path %>
                 %elif COPIED_FILENODE in filediff.patch['stats']['ops']:
                     <strong>${filediff.target_file_path}</strong> ⬅ ${filediff.source_file_path}
                     <% final_path = filediff.target_file_path %>
                 %endif
             %else:
                 ## file was modified
                 <strong>${filediff.source_file_path}</strong>
                 <% final_path = filediff.source_file_path %>
             %endif
         %else:
             %if filediff.source_file_path:
                 ## file was deleted
                 <strong>${filediff.source_file_path}</strong>
                 <% final_path = filediff.source_file_path %>
             %else:
                 ## file was added
                 <strong>${filediff.target_file_path}</strong>
                 <% final_path = filediff.target_file_path %>
             %endif
         %endif
         <i style="color: #aaa" class="tooltip icon-clipboard clipboard-action" data-clipboard-text="${final_path}" title="${_('Copy the full path')}" onclick="return false;"></i>
     </span>
     <span class="pill-group" style="float: left">
         %if filediff.limited_diff:
         <span class="pill tooltip" op="limited" title="The stats for this diff are not complete">limited diff</span>
         %endif
 
         %if RENAMED_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="renamed">renamed</span>
         %endif
 
         %if COPIED_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="copied">copied</span>
         %endif
 
         %if NEW_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="created">created</span>
             %if filediff['target_mode'].startswith('120'):
         <span class="pill" op="symlink">symlink</span>
             %else:
         <span class="pill" op="mode">${nice_mode(filediff['target_mode'])}</span>
             %endif
         %endif
 
         %if DEL_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="removed">removed</span>
         %endif
 
         %if CHMOD_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="mode">
             ${nice_mode(filediff['source_mode'])} ➡ ${nice_mode(filediff['target_mode'])}
         </span>
         %endif
     </span>
 
     <a class="pill filediff-anchor" href="#a_${h.FID('', filediff.patch['filename'])}">¶</a>
 
     <span class="pill-group" style="float: right">
         %if BIN_FILENODE in filediff.patch['stats']['ops']:
         <span class="pill" op="binary">binary</span>
             %if MOD_FILENODE in filediff.patch['stats']['ops']:
             <span class="pill" op="modified">modified</span>
             %endif
         %endif
         %if filediff.patch['stats']['added']:
         <span class="pill" op="added">+${filediff.patch['stats']['added']}</span>
         %endif
         %if filediff.patch['stats']['deleted']:
         <span class="pill" op="deleted">-${filediff.patch['stats']['deleted']}</span>
         %endif
     </span>
 
 </%def>
 
 <%def name="nice_mode(filemode)">
     ${filemode.startswith('100') and filemode[3:] or filemode}
 </%def>
 
 <%def name="diff_menu(filediff, use_comments=False)">
     <div class="filediff-menu">
 %if filediff.diffset.source_ref:
     %if filediff.operation in ['D', 'M']:
         <a
             class="tooltip"
             href="${h.route_path('repo_files',repo_name=filediff.diffset.repo_name,commit_id=filediff.diffset.source_ref,f_path=filediff.source_file_path)}"
             title="${h.tooltip(_('Show file at commit: %(commit_id)s') % {'commit_id': filediff.diffset.source_ref[:12]})}"
         >
             ${_('Show file before')}
         </a> |
     %else:
         <span
             class="tooltip"
             title="${h.tooltip(_('File no longer present at commit: %(commit_id)s') % {'commit_id': filediff.diffset.source_ref[:12]})}"
         >
             ${_('Show file before')}
         </span> |
     %endif
     %if filediff.operation in ['A', 'M']:
         <a
             class="tooltip"
             href="${h.route_path('repo_files',repo_name=filediff.diffset.source_repo_name,commit_id=filediff.diffset.target_ref,f_path=filediff.target_file_path)}"
             title="${h.tooltip(_('Show file at commit: %(commit_id)s') % {'commit_id': filediff.diffset.target_ref[:12]})}"
         >
             ${_('Show file after')}
         </a> |
     %else:
         <span
             class="tooltip"
             title="${h.tooltip(_('File no longer present at commit: %(commit_id)s') % {'commit_id': filediff.diffset.target_ref[:12]})}"
             >
                 ${_('Show file after')}
         </span> |
     %endif
         <a
             class="tooltip"
             title="${h.tooltip(_('Raw diff'))}"
             href="${h.route_path('repo_files_diff',repo_name=filediff.diffset.repo_name,f_path=filediff.target_file_path, _query=dict(diff2=filediff.diffset.target_ref,diff1=filediff.diffset.source_ref,diff='raw'))}"
         >
             ${_('Raw diff')}
         </a> |
         <a
             class="tooltip"
             title="${h.tooltip(_('Download diff'))}"
             href="${h.route_path('repo_files_diff',repo_name=filediff.diffset.repo_name,f_path=filediff.target_file_path, _query=dict(diff2=filediff.diffset.target_ref,diff1=filediff.diffset.source_ref,diff='download'))}"
         >
             ${_('Download diff')}
         </a>
         % if use_comments:
             |
         % endif
 
         ## TODO: dan: refactor ignorews_url and context_url into the diff renderer same as diffmode=unified/sideside. Also use ajax to load more context (by clicking hunks)
         %if hasattr(c, 'ignorews_url'):
         ${c.ignorews_url(request, h.FID('', filediff.patch['filename']))}
         %endif
         %if hasattr(c, 'context_url'):
         ${c.context_url(request, h.FID('', filediff.patch['filename']))}
         %endif
 
         %if use_comments:
         <a href="#" onclick="return Rhodecode.comments.toggleComments(this);">
             <span class="show-comment-button">${_('Show comments')}</span><span class="hide-comment-button">${_('Hide comments')}</span>
         </a>
         %endif
 %endif
     </div>
 </%def>
 
 
 <%def name="inline_comments_container(comments, inline_comments)">
 <div class="inline-comments">
     %for comment in comments:
         ${commentblock.comment_block(comment, inline=True)}
     %endfor
     % if comments and comments[-1].outdated:
     <span class="btn btn-secondary cb-comment-add-button comment-outdated}"
           style="display: none;}">
         ${_('Add another comment')}
     </span>
     % else:
     <span onclick="return Rhodecode.comments.createComment(this)"
           class="btn btn-secondary cb-comment-add-button">
         ${_('Add another comment')}
     </span>
     % endif
 
 </div>
 </%def>
 
 <%!
 def get_comments_for(diff_type, comments, filename, line_version, line_number):
     if hasattr(filename, 'unicode_path'):
         filename = filename.unicode_path
 
     if not isinstance(filename, basestring):
         return None
 
     line_key = '{}{}'.format(line_version, line_number) ## e.g o37, n12
 
     if comments and filename in comments:
         file_comments = comments[filename]
         if line_key in file_comments:
             data = file_comments.pop(line_key)
             return data
 %>
 
 <%def name="render_hunk_lines_sideside(hunk, use_comments=False, inline_comments=None)">
 
     %for i, line in enumerate(hunk.sideside):
     <%
     old_line_anchor, new_line_anchor = None, None
     if line.original.lineno:
         old_line_anchor = diff_line_anchor(hunk.source_file_path, line.original.lineno, 'o')
     if line.modified.lineno:
         new_line_anchor = diff_line_anchor(hunk.target_file_path, line.modified.lineno, 'n')
     %>
 
     <tr class="cb-line">
         <td class="cb-data ${action_class(line.original.action)}"
             data-line-no="${line.original.lineno}"
             >
             <div>
 
             <% line_old_comments = None %>
             %if line.original.get_comment_args:
                 <% line_old_comments = get_comments_for('side-by-side', inline_comments, *line.original.get_comment_args) %>
             %endif
             %if line_old_comments:
                 <% has_outdated = any([x.outdated for x in line_old_comments]) %>
                 % if has_outdated:
                     <i title="${_('comments including outdated')}:${len(line_old_comments)}" class="icon-comment_toggle" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % else:
                     <i title="${_('comments')}: ${len(line_old_comments)}" class="icon-comment" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % endif
             %endif
             </div>
         </td>
         <td class="cb-lineno ${action_class(line.original.action)}"
             data-line-no="${line.original.lineno}"
             %if old_line_anchor:
             id="${old_line_anchor}"
             %endif
         >
             %if line.original.lineno:
             <a name="${old_line_anchor}" href="#${old_line_anchor}">${line.original.lineno}</a>
             %endif
         </td>
         <td class="cb-content ${action_class(line.original.action)}"
             data-line-no="o${line.original.lineno}"
             >
             %if use_comments and line.original.lineno:
             ${render_add_comment_button()}
             %endif
             <span class="cb-code">${line.original.action} ${line.original.content or '' | n}</span>
 
             %if use_comments and line.original.lineno and line_old_comments:
                 ${inline_comments_container(line_old_comments, inline_comments)}
             %endif
 
         </td>
         <td class="cb-data ${action_class(line.modified.action)}"
             data-line-no="${line.modified.lineno}"
             >
             <div>
 
             %if line.modified.get_comment_args:
                 <% line_new_comments = get_comments_for('side-by-side', inline_comments, *line.modified.get_comment_args) %>
             %else:
                 <% line_new_comments = None%>
             %endif
             %if line_new_comments:
                 <% has_outdated = any([x.outdated for x in line_new_comments]) %>
                 % if has_outdated:
                     <i title="${_('comments including outdated')}:${len(line_new_comments)}" class="icon-comment_toggle" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % else:
                     <i title="${_('comments')}: ${len(line_new_comments)}" class="icon-comment" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % endif
             %endif
             </div>
         </td>
         <td class="cb-lineno ${action_class(line.modified.action)}"
             data-line-no="${line.modified.lineno}"
             %if new_line_anchor:
             id="${new_line_anchor}"
             %endif
             >
             %if line.modified.lineno:
                 <a name="${new_line_anchor}" href="#${new_line_anchor}">${line.modified.lineno}</a>
             %endif
         </td>
         <td class="cb-content ${action_class(line.modified.action)}"
             data-line-no="n${line.modified.lineno}"
             >
             %if use_comments and line.modified.lineno:
             ${render_add_comment_button()}
             %endif
             <span class="cb-code">${line.modified.action} ${line.modified.content or '' | n}</span>
             %if use_comments and line.modified.lineno and line_new_comments:
             ${inline_comments_container(line_new_comments, inline_comments)}
             %endif
         </td>
     </tr>
     %endfor
 </%def>
 
 
 <%def name="render_hunk_lines_unified(hunk, use_comments=False,  inline_comments=None)">
     %for old_line_no, new_line_no, action, content, comments_args in hunk.unified:
     <%
     old_line_anchor, new_line_anchor = None, None
     if old_line_no:
         old_line_anchor = diff_line_anchor(hunk.source_file_path, old_line_no, 'o')
     if new_line_no:
         new_line_anchor = diff_line_anchor(hunk.target_file_path, new_line_no, 'n')
     %>
     <tr class="cb-line">
         <td class="cb-data ${action_class(action)}">
             <div>
 
             %if comments_args:
                 <% comments = get_comments_for('unified', inline_comments, *comments_args) %>
             %else:
-                <% comments = None%>
+                <% comments = None %>
             %endif
 
             % if comments:
                 <% has_outdated = any([x.outdated for x in comments]) %>
                 % if has_outdated:
                     <i title="${_('comments including outdated')}:${len(comments)}" class="icon-comment_toggle" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % else:
                     <i title="${_('comments')}: ${len(comments)}" class="icon-comment" onclick="return Rhodecode.comments.toggleLineComments(this)"></i>
                 % endif
             % endif
             </div>
         </td>
         <td class="cb-lineno ${action_class(action)}"
             data-line-no="${old_line_no}"
             %if old_line_anchor:
             id="${old_line_anchor}"
             %endif
         >
             %if old_line_anchor:
             <a name="${old_line_anchor}" href="#${old_line_anchor}">${old_line_no}</a>
             %endif
         </td>
         <td class="cb-lineno ${action_class(action)}"
             data-line-no="${new_line_no}"
             %if new_line_anchor:
             id="${new_line_anchor}"
             %endif
         >
             %if new_line_anchor:
             <a name="${new_line_anchor}" href="#${new_line_anchor}">${new_line_no}</a>
             %endif
         </td>
         <td class="cb-content ${action_class(action)}"
             data-line-no="${new_line_no and 'n' or 'o'}${new_line_no or old_line_no}"
             >
             %if use_comments:
             ${render_add_comment_button()}
             %endif
             <span class="cb-code">${action} ${content or '' | n}</span>
             %if use_comments and comments:
             ${inline_comments_container(comments, inline_comments)}
             %endif
         </td>
     </tr>
     %endfor
 </%def>
 
 
 <%def name="render_hunk_lines(diff_mode, hunk, use_comments, inline_comments)">
     % if diff_mode == 'unified':
         ${render_hunk_lines_unified(hunk, use_comments=use_comments, inline_comments=inline_comments)}
     % elif diff_mode == 'sideside':
         ${render_hunk_lines_sideside(hunk, use_comments=use_comments, inline_comments=inline_comments)}
     % else:
         <tr class="cb-line">
             <td>unknown diff mode</td>
         </tr>
     % endif
 </%def>
 
 
 <%def name="render_add_comment_button()">
 <button class="btn btn-small btn-primary cb-comment-box-opener" onclick="return Rhodecode.comments.createComment(this)">
     <span><i class="icon-comment"></i></span>
 </button>
 </%def>
 
 <%def name="render_diffset_menu()">
 
     <div class="diffset-menu clearinner">
         <div class="pull-right">
             <div class="btn-group">
 
                 <a
                   class="btn ${c.diffmode == 'sideside' and 'btn-primary'} tooltip"
                   title="${h.tooltip(_('View side by side'))}"
                   href="${h.current_route_path(request, diffmode='sideside')}">
                     <span>${_('Side by Side')}</span>
                 </a>
                 <a
                   class="btn ${c.diffmode == 'unified' and 'btn-primary'} tooltip"
                   title="${h.tooltip(_('View unified'))}" href="${h.current_route_path(request, diffmode='unified')}">
                     <span>${_('Unified')}</span>
                 </a>
             </div>
         </div>
 
         <div class="pull-left">
           <div class="btn-group">
               <a
                   class="btn"
                   href="#"
                   onclick="$('input[class=filediff-collapse-state]').prop('checked', false); return false">${_('Expand All Files')}</a>
               <a
                   class="btn"
                   href="#"
                   onclick="$('input[class=filediff-collapse-state]').prop('checked', true); return false">${_('Collapse All Files')}</a>
               <a
                   class="btn"
                   href="#"
                   onclick="return Rhodecode.comments.toggleWideMode(this)">${_('Wide Mode Diff')}</a>
           </div>
         </div>
     </div>
 </%def>