backup/warcprox
1
0
Fork 0
mirror of https://github.com/internetarchive/warcprox.git synced 2025-01-18 13:22:09 +01:00
Code Issues Projects Releases Activity

appease some warnings

Browse Source
This commit is contained in:
Noah Levitt 2019-03-21 14:17:24 -07:00
parent f2eebae641
commit a25971e06b
8 changed files with 26 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
tests/test_warcprox.py
View File

@ -68,6 +68,10 @@ import certauth.certauth
import warcprox
import warcprox.main
# https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
import urllib3
urllib3.disable_warnings()
try:
import http.client as http_client
except ImportError:
@ -144,7 +148,7 @@ def dump_state(signum=None, frame=None):
stack = traceback.format_stack(sys._current_frames()[th.ident])
state_strs.append("".join(stack))
logging.warn("dumping state (caught signal {})\n{}".format(signum, "\n".join(state_strs)))
logging.warning("dumping state (caught signal {})\n{}".format(signum, "\n".join(state_strs)))
signal.signal(signal.SIGQUIT, dump_state)
@ -446,7 +450,7 @@ def warcprox_(request, http_daemon, https_daemon):
logging.info('dropping rethinkdb database %r', parsed.database)
rr.db_drop(parsed.database).run()
except Exception as e:
logging.warn(
logging.warning(
'problem deleting rethinkdb database %r: %s',
parsed.database, e)
logging.info('deleting working directory %r', work_dir)
@ -1762,7 +1766,7 @@ def test_crawl_log(warcprox_, http_daemon, archiving_proxies):
crawl_log = open(default_crawl_log_path, 'rb').read()
# tests will fail in year 3000 :)
assert re.match(b'\A2[^\n]+\n\Z', crawl_log)
assert re.match(br'\A2[^\n]+\n\Z', crawl_log)
assert crawl_log[24:31] == b' 200 '
assert crawl_log[31:42] == b' 54 '
fields = crawl_log.split()
@ -1782,7 +1786,7 @@ def test_crawl_log(warcprox_, http_daemon, archiving_proxies):
assert extra_info['contentSize'] == 145
crawl_log_1 = open(file, 'rb').read()
assert re.match(b'\A2[^\n]+\n\Z', crawl_log_1)
assert re.match(br'\A2[^\n]+\n\Z', crawl_log_1)
assert crawl_log_1[24:31] == b' 200 '
assert crawl_log_1[31:42] == b' 54 '
fields = crawl_log_1.split()
@ -1820,7 +1824,7 @@ def test_crawl_log(warcprox_, http_daemon, archiving_proxies):
crawl_log_2 = open(file, 'rb').read()
assert re.match(b'\A2[^\n]+\n\Z', crawl_log_2)
assert re.match(br'\A2[^\n]+\n\Z', crawl_log_2)
assert crawl_log_2[24:31] == b' 200 '
assert crawl_log_2[31:42] == b' 54 '
fields = crawl_log_2.split()
@ -1853,7 +1857,7 @@ def test_crawl_log(warcprox_, http_daemon, archiving_proxies):
assert os.path.exists(file)
crawl_log_3 = open(file, 'rb').read()
assert re.match(b'\A2[^\n]+\n\Z', crawl_log_3)
assert re.match(br'\A2[^\n]+\n\Z', crawl_log_3)
assert crawl_log_3[24:31] == b' 200 '
assert crawl_log_3[31:42] == b' 0 '
fields = crawl_log_3.split()
@ -1893,7 +1897,7 @@ def test_crawl_log(warcprox_, http_daemon, archiving_proxies):
assert os.path.exists(file)
crawl_log_4 = open(file, 'rb').read()
assert re.match(b'\A2[^\n]+\n\Z', crawl_log_4)
assert re.match(br'\A2[^\n]+\n\Z', crawl_log_4)
assert crawl_log_4[24:31] == b' 204 '
assert crawl_log_4[31:42] == b' 38 '
fields = crawl_log_4.split()

4
warcprox/bigtable.py
View File

@ -71,7 +71,7 @@ class RethinkCaptures:
"unexpected result saving batch of %s: %s "
"entries" % (len(self._batch), result))
if result["replaced"] > 0 or result["unchanged"] > 0:
self.logger.warn(
self.logger.warning(
"inserted=%s replaced=%s unchanged=%s in big "
"captures table (normally replaced=0 and "
"unchanged=0)", result["inserted"],
@ -148,7 +148,7 @@ class RethinkCaptures:
recorded_url.payload_digest.digest()
).decode("utf-8")
else:
self.logger.warn(
self.logger.warning(
"digest type is %r but big captures table is indexed "
"by sha1",
recorded_url.payload_digest.name)

6
warcprox/dedup.py
View File

@ -374,7 +374,7 @@ class BatchTroughStorer(warcprox.BaseBatchPostfetchProcessor):
except futures.TimeoutError as e:
# the remaining threads actually keep running in this case,
# there's no way to stop them, but that should be harmless
logging.warn(
logging.warning(
'timed out saving dedup info to trough', exc_info=True)
class BatchTroughLoader(warcprox.BaseBatchPostfetchProcessor):
@ -458,7 +458,7 @@ class BatchTroughLoader(warcprox.BaseBatchPostfetchProcessor):
recorded_url.dedup_info = entry
except Exception as e:
# batch_lookup raised exception or something
logging.warn(
logging.warning(
'problem looking up dedup info for %s urls '
'in bucket %s', len(buckets[bucket]), bucket,
exc_info=True)
@ -474,7 +474,7 @@ class BatchTroughLoader(warcprox.BaseBatchPostfetchProcessor):
except futures.TimeoutError as e:
# the remaining threads actually keep running in this case,
# there's no way to stop them, but that should be harmless
self.logger.warn(
self.logger.warning(
'timed out loading dedup info from trough', exc_info=True)
class TroughDedupDb(DedupDb, DedupableMixin):

4
warcprox/main.py
View File

@ -264,7 +264,7 @@ def dump_state(signum=None, frame=None):
except Exception as e:
state_strs.append('<n/a:%r>' % e)
logging.warn(
logging.warning(
'dumping state (caught signal %s)\n%s',
signum, '\n'.join(state_strs))
@ -402,7 +402,7 @@ def ensure_rethinkdb_tables(argv=None):
did_something = True
if args.rethinkdb_trough_db_url:
dedup_db = warcprox.dedup.TroughDedupDb(options)
logging.warn(
logging.warning(
'trough is responsible for creating most of the rethinkdb '
'tables that it uses')
did_something = True

10
warcprox/mitmproxy.py
View File

@ -100,7 +100,7 @@ class ProxyingRecorder(object):
self.proxy_client.sendall(hunk)
except BaseException as e:
self._proxy_client_conn_open = False
self.logger.warn(
self.logger.warning(
'%s sending data to proxy client for url %s',
e, self.url)
self.logger.info(
@ -283,7 +283,7 @@ class MitmProxyHandler(http_server.BaseHTTPRequestHandler):
self._remote_server_conn.sock = ssl.wrap_socket(
self._remote_server_conn.sock)
except ssl.SSLError:
self.logger.warn(
self.logger.warning(
"failed to establish ssl connection to %s; "
"python ssl library does not support SNI, "
"consider upgrading to python 2.7.9+ or 3.4+",
@ -332,7 +332,7 @@ class MitmProxyHandler(http_server.BaseHTTPRequestHandler):
else:
self.send_error(500, str(e))
except Exception as f:
self.logger.warn("failed to send error response ({}) to proxy client: {}".format(e, f))
self.logger.warning("failed to send error response ({}) to proxy client: {}".format(e, f))
return
# Reload!
@ -386,7 +386,7 @@ class MitmProxyHandler(http_server.BaseHTTPRequestHandler):
return self._proxy_request()
except Exception as e:
if self.server.shutting_down:
self.logger.warn(
self.logger.warning(
'sending 503 warcprox shutting down %r: %r',
self.requestline, e)
self.send_error(503, 'warcprox shutting down')
@ -521,7 +521,7 @@ class MitmProxyHandler(http_server.BaseHTTPRequestHandler):
return self.do_COMMAND
def log_error(self, fmt, *args):
self.logger.warn(fmt, *args)
self.logger.warning(fmt, *args)
class PooledMixIn(socketserver.ThreadingMixIn):
logger = logging.getLogger("warcprox.mitmproxy.PooledMixIn")

2
warcprox/stats.py
View File

@ -81,7 +81,7 @@ def unravel_buckets(url, warcprox_meta):
for bucket in warcprox_meta["stats"]["buckets"]:
if isinstance(bucket, dict):
if not 'bucket' in bucket:
self.logger.warn(
self.logger.warning(
'ignoring invalid stats bucket in '
'warcprox-meta header %s', bucket)
continue

2
warcprox/trough.py
View File

@ -190,7 +190,7 @@ class TroughClient(object):
return
if response.status_code != 200:
self._write_url_cache.pop(segment_id, None)
self.logger.warn(
self.logger.warning(
'unexpected response %r %r %r from %r to sql=%r',
response.status_code, response.reason, response.text,
write_url, sql)

2
warcprox/warcproxy.py
View File

@ -530,6 +530,6 @@ class WarcProxy(SingleThreadedWarcProxy, warcprox.mitmproxy.PooledMitmProxy):
self.remote_connection_pool.clear()
def handle_error(self, request, client_address):
self.logger.warn(
self.logger.warning(
"exception processing request %s from %s", request,
client_address, exc_info=True)