Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Filename hash bug fix #6

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Filename hash bug fix #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cac86c7
cleaning a bug
reshinthadithyan Oct 24, 2021
6d3c546
Clean up
reshinthadithyan Sep 12, 2022
4af9d3c
Further clean up
reshinthadithyan Sep 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
.tmp
github_data
17 changes: 9 additions & 8 deletions download_repo_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
import argparse
import subprocess
from itertools import repeat

import copy
bad_extensions = [
'app',
'bin',
Expand Down Expand Up @@ -164,7 +164,7 @@ def get_content(f):


def _process_repo(repo_data, repodir):
out = None
out = []
# get metadata
name, stars, lang = repo_data
meta = {'repo_name': name, 'stars': stars, 'repo_language': lang}
Expand Down Expand Up @@ -192,13 +192,14 @@ def _process_repo(repo_data, repodir):
text_outputs.append(None)
for i in range(len(files)):
text = text_outputs[i]
meta_ind = copy.deepcopy(meta)
if text is not None:
meta['file_name'] = filenames[i]
meta['mime_type'] = extensions[i]
meta_ind['file_name'] = filenames[i]
meta_ind['mime_type'] = extensions[i]
if out is None:
out = [[text, meta]]
out = [[text, meta_ind]]
else:
out.append([text, meta])
out.append([text,meta_ind])
shutil.rmtree(repodir, ignore_errors=True)
except TimeoutError:
print(f"Processing for {name} timed out")
Expand Down Expand Up @@ -226,7 +227,7 @@ def process_repo_list(repo_data, clone_timeout, processing_timeout):
p.kill()
shutil.rmtree(f'{repodir}/.git', ignore_errors=True)
# extracts text files from repo and returns them as list : [[text, metadata], ... ]
out = process_repo(repo_data, repodir, processing_timeout=processing_timeout)
out = _process_repo(repo_data, repodir)#, processing_timeout=processing_timeout)
except Exception:
err = traceback.format_exc()
if verbose:
Expand Down Expand Up @@ -315,4 +316,4 @@ def process_args():
success_hist.append((not_none / len(repos_out)) * 100)
success_rate = sum(success_hist) / len(success_hist)
pbar.set_postfix({"Success Rate": success_rate})
ar.commit() # final commit
ar.commit() # final commit
1 change: 0 additions & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,4 +3,3 @@ requests=='2.21.0'
tqdm=='4.47.0'
joblib=='0.16.0'
fire=='0.3.1'
python-magic