kallithea Changeset - 07f026cdf7ac

Changeset - 07f026cdf7ac

Parent rev.

Child rev.

[Not reviewed]

default

0 1 0

domruf - 9 years ago 2017-05-04 20:51:26
dominikruf@gmail.com

vcs: catch MemoryErrors when calling Git diff

Binary diffs can make the diffs VERY big and cause MemoryError exceptions.

Before giving MemoryError, the system might start swapping, any process might
fail when allocating memory, random processes might get killed, and our process
might fail in other places. The proper fix would be to avoid the problem by not
trying to process more data than we can handle - for example by not processing
more than a certain amount of Git output.

Before, memory errors were shown to the user as a 500 Internal Server Error
page.

Now, as long as we have no better/safer way get the diff, catch the MemoryError
and show the page with a flash error message and no diff.

The error handling is placed in the diffs module to avoid leaking flash
messages into the vcs lib.

1 file changed with 6 insertions and 2 deletions:

kallithea/lib/diffs.py

0 comments (0 inline, 0 general)

kallithea/lib/diffs.py

➞

Show inline comments

@@ @@ -22,28 +22,28 @@ This file was forked by the Kallithea pr @@
 Original author and date, and relevant copyright and licensing information is below:
 :created_on: Dec 4, 2011
 :author: marcink
 :copyright: (c) 2013 RhodeCode GmbH, and others.
 :license: GPLv3, see LICENSE.md for more details.
 """
 import re
 import difflib
 import logging
 from tg.i18n import ugettext as _
 from kallithea.lib import helpers as h
 from kallithea.lib.vcs.exceptions import VCSError
 from kallithea.lib.vcs.nodes import FileNode, SubModuleNode
 from kallithea.lib.vcs.backends.base import EmptyChangeset
 from kallithea.lib.helpers import escape
 from kallithea.lib.utils2 import safe_unicode
 log = logging.getLogger(__name__)
 def _safe_id(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
@@ @@ -209,25 +209,25 @@ def wrapped_diff(filenode_old, filenode_ @@
         html_diff = as_html(parsed_lines=diff_processor.parsed, enable_comments=enable_comments)
         stats = diff_processor.stat()
     else:
         html_diff = wrap_to_table(_('Changeset was too big and was cut off, use '
                                'diff menu to display this diff'))
         stats = (0, 0)
     if not html_diff:
         submodules = filter(lambda o: isinstance(o, SubModuleNode),
                             [filenode_new, filenode_old])
         if submodules:
             html_diff = wrap_to_table(escape('Submodule %r' % submodules[0]))
+            html_diff = wrap_to_table(h.escape('Submodule %r' % submodules[0]))
         else:
             html_diff = wrap_to_table(_('No changes detected'))
     cs1 = filenode_old.changeset.raw_id
     cs2 = filenode_new.changeset.raw_id
     return cs1, cs2, a_path, html_diff, stats, op
 def get_gitdiff(filenode_old, filenode_new, ignore_whitespace=True, context=3):
     """
     Returns git style diff between given ``filenode_old`` and ``filenode_new``.
@@ @@ -248,26 +248,30 @@ def get_gitdiff(filenode_old, filenode_n @@
     old_raw_id = getattr(filenode_old.changeset, 'raw_id', repo.EMPTY_CHANGESET)
     new_raw_id = getattr(filenode_new.changeset, 'raw_id', repo.EMPTY_CHANGESET)
     vcs_gitdiff = get_diff(repo, old_raw_id, new_raw_id, filenode_new.path,
                            ignore_whitespace, context)
     return vcs_gitdiff
 def get_diff(scm_instance, rev1, rev2, path=None, ignore_whitespace=False, context=3):
     """
     A thin wrapper around vcs lib get_diff.
     """
     try:
     return scm_instance.get_diff(rev1, rev2, path=path,
                                  ignore_whitespace=ignore_whitespace, context=context)
     except MemoryError:
         h.flash('MemoryError: Diff is too big', category='error')
         return ''
 NEW_FILENODE = 1
 DEL_FILENODE = 2
 MOD_FILENODE = 3
 RENAMED_FILENODE = 4
 COPIED_FILENODE = 5
 CHMOD_FILENODE = 6
 BIN_FILENODE = 7
 class DiffProcessor(object):

0 comments (0 inline, 0 general)