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

extracted the process_row function because it was

Browse Source 
becoming quite big
This commit is contained in:
Karma Riuk
2025-02-28 14:14:20 +01:00
parent a6d7bdb865
commit a4be07c04e
1 changed files with 35 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
clone_repos.py
View File

@ -117,33 +117,7 @@ def remove_dir(dir: str) -> None:
shutil.rmtree(parent)
def clone_repos(file: str, dest: str, force: bool =False, verbose: bool = False) -> None:
"""
Download the repos listed in the file passed as argument. The downloaded repos will be placed in the folder that is named as the dest argument.
Arguments:
file (str): The name of the file to download the repos from. Must be a .csv.gz file (downloaded from https://seart-ghs.si.usi.ch)
dest (str): The name of the root directory in which to download the repos
verbose (bool): If `True`, outputs detailed process information. Defaults to `False`.
"""
if verbose: print(f"Reading CSV file {file}")
df = pd.read_csv(file)
df["successfully_cloned"] = None
df["build_system"] = None
df["depth_of_build_file"] = None
df["detected_source_of_tests"] = None
df["error_msg"] = None
df["good_repo_for_crab"] = False
df["n_tests"] = None
df["n_tests_with_grep"] = None
df["n_tests_passed"] = None
df["n_tests_failed"] = None
df["n_tests_skipped"] = None
if verbose: print("Cloning repositories")
def _process(row)->None:
def process_row(row, dest: str, force: bool = False, verbose: bool = False):
repo = row["name"]
if repo in EXCLUSION_LIST:
row["error_msg"] = "Repo in exclusion list"
@ -175,13 +149,38 @@ def clone_repos(file: str, dest: str, force: bool =False, verbose: bool = False)
# If repo was not removed, then it is a good repo
row["good_repo_for_crab"] = True
def clone_repos(file: str, dest: str, force: bool =False, verbose: bool = False) -> None:
"""
Download the repos listed in the file passed as argument. The downloaded repos will be placed in the folder that is named as the dest argument.
Arguments:
file (str): The name of the file to download the repos from. Must be a .csv.gz file (downloaded from https://seart-ghs.si.usi.ch)
dest (str): The name of the root directory in which to download the repos
verbose (bool): If `True`, outputs detailed process information. Defaults to `False`.
"""
if verbose: print(f"Reading CSV file {file}")
df = pd.read_csv(file)
df["successfully_cloned"] = None
df["build_system"] = None
df["depth_of_build_file"] = None
df["detected_source_of_tests"] = None
df["error_msg"] = None
df["good_repo_for_crab"] = False
df["n_tests"] = None
df["n_tests_with_grep"] = None
df["n_tests_passed"] = None
df["n_tests_failed"] = None
df["n_tests_skipped"] = None
try:
df.progress_apply(_process, axis=1)
if verbose: print("Processing repositories")
df.progress_apply(lambda row: process_row(row, dest, force=force, verbose=verbose), axis=1)
except KeyboardInterrupt:
print("Keyboard interrupt detected. Stopping the processing of the repos...")
if verbose: print("Writing CSV file")
if verbose: print("Writing results...")
df.to_csv("results.csv.gz", index=False)