Skip to content

fix(commentPreprocessor, licenseDownloader): normalize keyword matching, SPDX URL handling, missing comma #123

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

Open
divyamagrawal06 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix(commentPreprocessor, licenseDownloader): normalize keyword matching, SPDX URL handling, missing comma #123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
239430c
fix: missing comma in keywords list
divyamagrawal06 Mar 24, 2026
ffb5c01
fix(licenseDownloader,commentPreprocessor): normalize SPDX URLs and k…
divyamagrawal06 Mar 24, 2026
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: 1 addition & 1 deletion atarashi/libs/commentPreprocessor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@
args = None

def licenseComment(data):
match_list = ['source', 'free', 'under','use', 'copyright', 'grant', 'software', 'license','licence', 'agreement', 'distribute', 'redistribution', 'liability', 'rights', 'reserved', 'general', 'public', 'modify', 'modified', 'modification', 'permission','permitted' 'granted', 'distributed', 'notice', 'distribution', 'terms', 'freely', 'licensed', 'merchantibility','redistributed', 'see', 'read', '(c)', 'copying', 'legal', 'licensing', 'spdx']
match_list = ['source', 'free', 'under', 'use', 'copyright', 'grant', 'software', 'license', 'licence', 'agreement', 'distribute', 'redistribution', 'liability', 'rights', 'reserved', 'general', 'public', 'modify', 'modified', 'modification', 'permission', 'permitted', 'granted', 'distributed', 'notice', 'distribution', 'terms', 'freely', 'licensed', 'merchantibility', 'merchantability', 'redistributed', 'see', 'read', '(c)', 'copying', 'legal', 'licensing', 'spdx']

MLmapCount, CSLmapCount, SLmapCount = [], [], []
comment = ""
Expand Down
10 changes: 5 additions & 5 deletions atarashi/license/licenseDownloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,7 +91,7 @@ def download_license(threads=os.cpu_count(), force=False):
licenses = jsonData.get('licenses')

version = jsonData.get('licenseListVersion').replace(".", "_")
releaseDate = jsonData.get('releaseDate')
releaseDate = jsonData.get('releaseDate').replace(':','-').replace('T','_').replace('Z','')
if licenses is not None:
fileName = releaseDate + '_' + version + '.csv'
directory = os.path.dirname(os.path.abspath(__file__))
Expand Down Expand Up @@ -140,12 +140,12 @@ def fetch_license(license):
nextUrl = "https://spdx.org/licenses/{0}.json".format(licenseDict['shortname'])
licenseData = LicenseDownloader._download_json(nextUrl)
licenseDict['text'] = licenseData.get('licenseText')
licenseDict['url'] = licenseData.get('seeAlso')
licenseDict['url'] = ', '.join(licenseData.get('seeAlso', [])) if isinstance(licenseData.get('seeAlso'), list) else licenseData.get('seeAlso', '')
licenseDict['license_header'] = licenseData.get('standardLicenseHeader', '')
if 'There is no standard license header for the license' in licenseDict['license_header']:
licenseDict['license_header'] = ''

return pd.DataFrame(licenseDict, columns=csvColumns)
return pd.DataFrame([licenseDict], columns=csvColumns)

@staticmethod
def fetch_exceptional_license(license):
Expand All @@ -161,11 +161,11 @@ def fetch_exceptional_license(license):
nextUrl = "https://spdx.org/licenses/{0}.json".format(licenseDict['shortname'])
licenseData = LicenseDownloader._download_json(nextUrl)
licenseDict['text'] = licenseData.get('licenseExceptionText')
licenseDict['url'] = licenseData.get('seeAlso')
licenseDict['url'] = ', '.join(licenseData.get('seeAlso', [])) if isinstance(licenseData.get('seeAlso'), list) else licenseData.get('seeAlso', '')
licenseDict['license_header'] = licenseData.get('standardLicenseHeader', '')
if 'There is no standard license header for the license' in licenseDict['license_header']:
licenseDict['license_header'] = ''
return pd.DataFrame(licenseDict, columns=csvColumns)
return pd.DataFrame([licenseDict], columns=csvColumns)


if __name__ == "__main__":
Expand Down