At present the unicode filtering seems to get confused at times with this error:
UnicodeDecodeError: 'ascii' codec can't decode byte 0x80 in position 32: ordinal not in range(128)
It seems to be due to self._nonprint being interpreted as UTF-8. Fix it by using ordinals instead of characters, changing the string to set.
Signed-off-by: Simon Glass sjg@chromium.org Reviewed-by: Stephen Warren swarren@nvidia.com ---
Changes in v2: None
test/py/multiplexed_log.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/test/py/multiplexed_log.py b/test/py/multiplexed_log.py index f23d5dec68c..637a3bd257b 100644 --- a/test/py/multiplexed_log.py +++ b/test/py/multiplexed_log.py @@ -314,8 +314,9 @@ $(document).ready(function () {
# The set of characters that should be represented as hexadecimal codes in # the log file. - _nonprint = ('%' + ''.join(chr(c) for c in range(0, 32) if c not in (9, 10)) + - ''.join(chr(c) for c in range(127, 256))) + _nonprint = {ord('%')} + _nonprint.update({c for c in range(0, 32) if c not in (9, 10)}) + _nonprint.update({c for c in range(127, 256)})
def _escape(self, data): """Render data format suitable for inclusion in an HTML document. @@ -331,7 +332,7 @@ $(document).ready(function () { """
data = data.replace(chr(13), '') - data = ''.join((c in self._nonprint) and ('%%%02x' % ord(c)) or + data = ''.join((ord(c) in self._nonprint) and ('%%%02x' % ord(c)) or c for c in data) data = cgi.escape(data) return data