mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Fix #725 - correctly parse tags on json import

Browse source
This commit is contained in:
hannah98 2021-12-20 08:58:58 -06:00
parent 989937796a
commit 4b8962b60b
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
archivebox/index/sql.py
View file

@ -34,8 +34,11 @@ def write_link_to_sql_index(link: Link):
from core.models import Snapshot, ArchiveResult from core.models import Snapshot, ArchiveResult
info = {k: v for k, v in link._asdict().items() if k in Snapshot.keys} info = {k: v for k, v in link._asdict().items() if k in Snapshot.keys}
tags = info.pop("tags") tags = info.pop("tags")
if tags is None:
tags = [] tag_set = (
set(tag.strip() for tag in (link.tags or '').split(','))
)
tag_list = list(tag_set) or []
try: try:
info["timestamp"] = Snapshot.objects.get(url=link.url).timestamp info["timestamp"] = Snapshot.objects.get(url=link.url).timestamp
@ -44,7 +47,7 @@ def write_link_to_sql_index(link: Link):
info["timestamp"] = str(float(info["timestamp"]) + 1.0) info["timestamp"] = str(float(info["timestamp"]) + 1.0)
snapshot, _ = Snapshot.objects.update_or_create(url=link.url, defaults=info) snapshot, _ = Snapshot.objects.update_or_create(url=link.url, defaults=info)
snapshot.save_tags(tags) snapshot.save_tags(tag_list)
for extractor, entries in link.history.items(): for extractor, entries in link.history.items():
for entry in entries: for entry in entries: