def get_woven_logs(log_files, pod, filters, objref_dict):
lines = []
combined_lines = []
first_combined = ""
pod_re = regex.wordRE(pod)
# Produce a list of lines of all the selected logs
for log_file in log_files:
log = gcs_async.read(log_file).get_result()
log = log.decode('utf8', 'replace')
lines.extend(log.split('\n'))
# Combine lines without timestamp into previous line, except if it comes at the
# beginning of the file, in which case add it to the line with the first timestamp
for line in lines:
timestamp_re = regex.timestamp(line)
if timestamp_re and timestamp_re.group(0):
if not combined_lines:
# add beginning of file to first timestamp line
line = first_combined + line
combined_lines.append(line)
else:
if not combined_lines:
first_combined = first_combined + line
else:
combined_lines[-1] = combined_lines[-1] + line
lines = sorted(combined_lines, key=regex.sub_timestamp)
data = '\n'.join(lines)
woven_logs = log_parser.digest(data,
error_re=pod_re,
filters=filters,
objref_dict=objref_dict)
return woven_logs
def get_woven_logs(log_files, pod, filters, objref_dict):
lines = []
combined_lines = []
first_combined = ""
pod_re = regex.wordRE(pod)
# Produce a list of lines of all the selected logs
for log_file in log_files:
log = gcs_async.read(log_file).get_result()
log = log.decode('utf8', 'replace')
lines.extend(log.split('\n'))
# Combine lines without timestamp into previous line, except if it comes at the
# beginning of the file, in which case add it to the line with the first timestamp
for line in lines:
timestamp_re = regex.timestamp(line)
if timestamp_re and timestamp_re.group(0):
if not combined_lines:
# add beginning of file to first timestamp line
line = first_combined + line
combined_lines.append(line)
else:
if not combined_lines:
first_combined = first_combined + line
else:
combined_lines[-1] = combined_lines[-1] + line
lines = sorted(combined_lines, key=regex.sub_timestamp)
data = '\n'.join(lines)
woven_logs = log_parser.digest(data, error_re=pod_re,
filters=filters, objref_dict=objref_dict)
return woven_logs
def test_timestamp(self):
for text, matches in [
('I0629 17:33:09.813041', True),
('2016-07-22T19:01:11.150204523Z', True),
('629 17:33:09.813041:', False),
('629 17:33:09', False),
]:
self.assertEqual(bool(regex.timestamp(text)), matches,
'test_timestamp(%r) should be %r' % (text, matches))
def test_timestamp(self):
for text, matches in [
('I0629 17:33:09.813041', True),
('2016-07-22T19:01:11.150204523Z', True),
('629 17:33:09.813041:', False),
('629 17:33:09', False),
]:
self.assertEqual(bool(regex.timestamp(text)), matches,
'test_timestamp(%r) should be %r' % (text, matches))