# HG changeset patch
# User domruf <dominikruf@gmail.com>
# Date 2017-05-04 20:51:26
# Node ID 07f026cdf7ace27701d2667a7c27128eeab5d934
# Parent  6fde53180c50963924900b48c2789a9ab17d57c5

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.

diff --git a/kallithea/lib/diffs.py b/kallithea/lib/diffs.py
--- a/kallithea/lib/diffs.py
+++ b/kallithea/lib/diffs.py
@@ -31,10 +31,10 @@ 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__)
@@ -218,7 +218,7 @@ def wrapped_diff(filenode_old, filenode_
         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'))
 
@@ -257,8 +257,12 @@ def get_diff(scm_instance, rev1, rev2, p
     """
     A thin wrapper around vcs lib get_diff.
     """
-    return scm_instance.get_diff(rev1, rev2, path=path,
-                                 ignore_whitespace=ignore_whitespace, context=context)
+    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