karma/crab
1
0
Fork 0
mirror of https://github.com/karma-riuk/crab.git synced 2025-07-05 13:38:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

instead of adding the cache as we go through the

Browse Source 
repos, just add it before any processing, so we are sure to keep all the previously saved data
This commit is contained in:
Karma Riuk
2025-05-16 19:39:59 +02:00
parent b84ea797ff
commit 14e64984c5
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
pull_requests.py
View File

@ -382,9 +382,7 @@ def process_repo(
repo = g.get_repo(repo_name) repo = g.get_repo(repo_name)
already_seen_prs = set() already_seen_prs = set()
if repo.full_name in cache: if repo.full_name in cache:
dataset.entries.extend(cache[repo.full_name].values())
already_seen_prs = set(cache[repo.full_name].keys()) already_seen_prs = set(cache[repo.full_name].keys())
dataset.to_json(args.output)
prs = repo.get_pulls(state="closed") prs = repo.get_pulls(state="closed")
@ -422,6 +420,10 @@ def process_repos(
Passing it by reference in order have the latest information, in case of an error Passing it by reference in order have the latest information, in case of an error
verbose (bool): Whether to be verbose or not verbose (bool): Whether to be verbose or not
""" """
for pr2entry in tqdm(cache.values(), desc="Adding cache in dataset"):
dataset.entries.extend(pr2entry.values())
dataset.to_json(args.output)
with tqdm(total=len(df), desc="Processing repos") as pbar: with tqdm(total=len(df), desc="Processing repos") as pbar:
for _, row in df.iterrows(): for _, row in df.iterrows():
repo_name = row["name"] repo_name = row["name"]