mirror of
https://github.com/internetarchive/warcprox.git
synced 2025-01-18 13:22:09 +01:00
add logging
This commit is contained in:
parent
e6a1a7dd7e
commit
b67f1ad0f3
@ -384,6 +384,9 @@ class BatchTroughStorer(warcprox.BaseBatchPostfetchProcessor):
|
|||||||
self.trough_dedup_db.batch_save,
|
self.trough_dedup_db.batch_save,
|
||||||
buckets[bucket], bucket)
|
buckets[bucket], bucket)
|
||||||
fs[future] = bucket
|
fs[future] = bucket
|
||||||
|
logging.debug(
|
||||||
|
'storing dedup info for %s urls '
|
||||||
|
'in bucket %s', len(buckets[bucket]), bucket)
|
||||||
|
|
||||||
# wait for results
|
# wait for results
|
||||||
try:
|
try:
|
||||||
@ -434,6 +437,8 @@ class BatchTroughLoader(warcprox.BaseBatchPostfetchProcessor):
|
|||||||
warcprox.digest_str(
|
warcprox.digest_str(
|
||||||
recorded_url.payload_digest, self.options.base32)
|
recorded_url.payload_digest, self.options.base32)
|
||||||
if recorded_url.payload_digest else 'n/a')
|
if recorded_url.payload_digest else 'n/a')
|
||||||
|
self.logger.debug(
|
||||||
|
'hash_plus_urls: {}'.format(hash_plus_urls))
|
||||||
self.logger.debug(
|
self.logger.debug(
|
||||||
'len(batch)=%s len(discards)=%s buckets=%s',
|
'len(batch)=%s len(discards)=%s buckets=%s',
|
||||||
len(batch), len(discards),
|
len(batch), len(discards),
|
||||||
|
Loading…
x
Reference in New Issue
Block a user