beenull/mwmbl
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Add tests

Browse source
This commit is contained in:
Daoud Clarke 2023-10-04 20:19:42 +01:00
parent 593c71f689
commit 41061a695b
2 changed files with 48 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
mwmbl/indexer/update_urls.py
View file

@ -71,12 +71,12 @@ def record_urls_in_database(batches: Collection[HashedBatch], new_item_queue: Qu
continue
score_multiplier = 1 if crawled_page_domain in DOMAINS else UNKNOWN_DOMAIN_MULTIPLIER
for link in item.content.links:
process_link(batch, crawled_page_domain, link, score_multiplier, timestamp, url_scores,
process_link(batch.user_id_hash, crawled_page_domain, link, score_multiplier, timestamp, url_scores,
url_timestamps, url_users, False, blacklist_domains)
if item.content.extra_links:
for link in item.content.extra_links:
process_link(batch, crawled_page_domain, link, score_multiplier, timestamp, url_scores,
process_link(batch.user_id_hash, crawled_page_domain, link, score_multiplier, timestamp, url_scores,
url_timestamps, url_users, True, blacklist_domains)
found_urls = [FoundURL(url, url_users[url], url_scores[url], url_statuses[url], url_timestamps[url])
@ -94,7 +94,7 @@ def get_blacklist_domains():
return set(response.text.split())
def process_link(batch, crawled_page_domain, link, unknown_domain_multiplier, timestamp, url_scores, url_timestamps, url_users, is_extra: bool, blacklist_domains):
def process_link(user_id_hash, crawled_page_domain, link, unknown_domain_multiplier, timestamp, url_scores, url_timestamps, url_users, is_extra: bool, blacklist_domains):
parsed_link = urlparse(link)
if parsed_link.netloc in EXCLUDED_DOMAINS or DOMAIN_BLACKLIST_REGEX.search(parsed_link.netloc) is not None \
or parsed_link.netloc in blacklist_domains:
@ -104,11 +104,11 @@ def process_link(batch, crawled_page_domain, link, unknown_domain_multiplier, ti
extra_multiplier = EXTRA_LINK_MULTIPLIER if is_extra else 1.0
score = SCORE_FOR_SAME_DOMAIN if parsed_link.netloc == crawled_page_domain else SCORE_FOR_DIFFERENT_DOMAIN
url_scores[link] += score * unknown_domain_multiplier * extra_multiplier
url_users[link] = batch.user_id_hash
url_users[link] = user_id_hash
url_timestamps[link] = timestamp
domain = f'{parsed_link.scheme}://{parsed_link.netloc}/'
url_scores[domain] += SCORE_FOR_ROOT_PATH * unknown_domain_multiplier
url_users[domain] = batch.user_id_hash
url_users[domain] = user_id_hash
url_timestamps[domain] = timestamp

43
test/test_update_urls.py Normal file
View file

@ -0,0 +1,43 @@
from mwmbl.indexer.update_urls import process_link
def test_process_link_normal():
url_scores = {"https://somesite.com/something.html": 0.0, "https://somesite.com/": 0.0}
url_timestamps = {}
url_users = {}
process_link(
user_id_hash="abc123",
crawled_page_domain="somewhere.com",
link="https://somesite.com/something.html",
unknown_domain_multiplier=1,
timestamp=1234,
url_scores=url_scores,
url_timestamps=url_timestamps,
url_users=url_users,
is_extra=False, blacklist_domains=[]
)
assert url_scores["https://somesite.com/something.html"] > 0.0
def test_process_link_excludes_porn():
url_scores = {}
url_timestamps = {}
url_users = {}
process_link(
user_id_hash="abc123",
crawled_page_domain="somewhere.com",
link="https://somepornsite.com/something.html",
unknown_domain_multiplier=1,
timestamp=1234,
url_scores=url_scores,
url_timestamps=url_timestamps,
url_users=url_users,
is_extra=False, blacklist_domains=[]
)
assert url_scores == {}
assert url_timestamps == {}
assert url_users == {}