karma/crab
1
0
Fork 0
mirror of https://github.com/karma-riuk/crab.git synced 2025-07-05 05:28:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

populating cache only if there is any cache

Browse Source
This commit is contained in:
Karma Riuk
2025-05-20 09:57:04 +02:00
parent 15ffe67b0e
commit 04a37030f4
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
pull_requests.py
View File

@ -454,9 +454,10 @@ def process_repos_parallel(
archive_destination: Directory for archives archive_destination: Directory for archives
cache: Optional cache of previously processed PR entries cache: Optional cache of previously processed PR entries
""" """
for pr2entry in tqdm(cache.values(), desc="Adding cache in dataset"): if len(cache) > 0:
dataset.entries.extend(pr2entry.values()) for pr2entry in tqdm(list(cache.values()), desc="Adding cache in dataset"):
dataset.to_json(args.output) dataset.entries.extend(pr2entry.values())
dataset.to_json(args.output)
repo_names = df["name"] repo_names = df["name"]
free_positions = list(range(1, n_workers + 1)) free_positions = list(range(1, n_workers + 1))
@ -529,9 +530,10 @@ 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"): if len(cache) > 0:
dataset.entries.extend(pr2entry.values()) for pr2entry in tqdm(list(cache.values()), desc="Adding cache in dataset"):
dataset.to_json(args.output) 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():