Files
@ 8993d401575b
Branch filter:
Location: kallithea/scripts/validate-commits - annotation
8993d401575b
1.7 KiB
text/plain
files: fix raw download of repo files with names with unicode points above 256 in name
Raw download had apparently only been tested with non-ascii characters that
were latin1. That was apparently a (too) simple case that worked without
crashing.
Files with unicode code points above 256 in their name would fail to download,
when Waitress failed like this, trying to get a real byte string by encoding
WSGI headers to latin1:
UnicodeEncodeError: 'latin-1' codec can't encode characters in position 84-85: ordinal not in range(256)
HTTP headers are of course byte strings on the network, but Python3 WSGI does
unfortunately neither expose it as bytes nor as unicode strings to be encoded
as utf-8. Instead, it uses unicode strings with byte values encoded as code
points 0-255. That is achieved by decoding the utf-8 encoded bytes as latin1.
For raw downloads, the recommended download filename is provided in the
Content-Disposition header. The problem is that it was provided as a real
unicode string.
Fixed by applying the "proper" latin1-decoding of a utf8-encoding.
Raw download had apparently only been tested with non-ascii characters that
were latin1. That was apparently a (too) simple case that worked without
crashing.
Files with unicode code points above 256 in their name would fail to download,
when Waitress failed like this, trying to get a real byte string by encoding
WSGI headers to latin1:
UnicodeEncodeError: 'latin-1' codec can't encode characters in position 84-85: ordinal not in range(256)
HTTP headers are of course byte strings on the network, but Python3 WSGI does
unfortunately neither expose it as bytes nor as unicode strings to be encoded
as utf-8. Instead, it uses unicode strings with byte values encoded as code
points 0-255. That is achieved by decoding the utf-8 encoded bytes as latin1.
For raw downloads, the recommended download filename is provided in the
Content-Disposition header. The problem is that it was provided as a real
unicode string.
Fixed by applying the "proper" latin1-decoding of a utf8-encoding.
37ac2ac0a9ae 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 68861940ee1e 68861940ee1e 68861940ee1e 68861940ee1e 68861940ee1e 68861940ee1e 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 68861940ee1e 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 89e9aef9b983 69f70de15f26 69f70de15f26 d9e37f7fd35b 69f70de15f26 69f70de15f26 bf85e6018daa bf85e6018daa 69f70de15f26 69f70de15f26 bf85e6018daa bf85e6018daa bf85e6018daa bf85e6018daa bf85e6018daa bf85e6018daa bf85e6018daa bf85e6018daa 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 69f70de15f26 | #!/bin/bash
# Validate the specified commits against test suite and other checks.
if [ -n "$VIRTUAL_ENV" ]; then
echo "Please run this script from outside a virtualenv."
exit 1
fi
if ! hg update --check -q .; then
echo "Working dir is not clean, please commit/revert changes first."
exit 1
fi
revset=$1
if [ -z "$revset" ]; then
echo "Warning: no revisions specified, checking draft changes up to the current one."
revset='draft() and ancestors(.)'
fi
venv=$(mktemp -d kallithea-validatecommits-env-XXXXXX)
resultfile=$(mktemp kallithea-validatecommits-result-XXXXXX)
echo > "$resultfile"
cleanup()
{
rm -rf /tmp/kallithea-test*
rm -rf "$venv"
}
finish()
{
cleanup
# print (possibly intermediate) results
cat "$resultfile"
rm "$resultfile"
}
trap finish EXIT
for rev in $(hg log -r "$revset" -T '{node}\n'); do
hg log -r "$rev"
hg update "$rev"
cleanup
python3 -m venv "$venv"
source "$venv/bin/activate"
pip install --upgrade pip setuptools
pip install -e . -r dev_requirements.txt python-ldap python-pam
# run-all-cleanup
if ! scripts/run-all-cleanup ; then
echo "run-all-cleanup encountered errors!"
result="NOK"
else
if ! hg update --check -q .; then
echo "run-all-cleanup did not give clean results!"
result="NOK"
hg diff
hg revert -a
else
result=" OK"
fi
fi
echo "$result: $rev (run-all-cleanup)" >> "$resultfile"
# pytest
if py.test; then
result=" OK"
else
result="NOK"
fi
echo "$result: $rev (pytest)" >> "$resultfile"
deactivate
echo
done
|