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

Merge branch 'limit_revisits' into qa

Browse Source
This commit is contained in:
Barbara Miller 2023-09-11 16:03:16 -07:00
commit e0b92bc901
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
warcprox/dedup.py
View File

@ -63,7 +63,7 @@ class DedupableMixin(object):
return recorded_url.response_recorder.payload_size() > self.min_binary_size return recorded_url.response_recorder.payload_size() > self.min_binary_size
def cache_true(func): def cache_true(func):
@functools.wraps(func) @wraps(func)
def wrapper(*args, **kwargs): def wrapper(*args, **kwargs):
result = func(*args, **kwargs) result = func(*args, **kwargs)
if result: if result:
@ -116,7 +116,7 @@ class LimitRevisitsPGMixin:
""" """
tracks revisits, returns True when we've seen revisit before, else False tracks revisits, returns True when we've seen revisit before, else False
""" """
self.logger.info('%s', skip_revisit.cache_info()) # self.logger.info('%s', skip_revisit.cache_info())
if not hash_plus_url: if not hash_plus_url:
digest = warcprox.digest_str(recorded_url.payload_digest, digest = warcprox.digest_str(recorded_url.payload_digest,