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

Name match #66

Merged
merged 3 commits into from
Jan 14, 2025
Merged

Name match #66

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9c1ffa2
re bugfix
Jan 2, 2025
fbc32f8
Merge branch 'master' into jb/bugfix
Jan 2, 2025
b752a3a
loosen id and filename matching
Jan 7, 2025
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
18 changes: 10 additions & 8 deletions gdoc_api/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,8 +112,10 @@ def download(self, save_as: os.PathLike = None) -> Self:

# check both jobId and odsNo as the name of the file, as it has varied in the past
for field in ('jobId', 'odsNo'):
if any(filter(lambda x: re.match(rf'.*?{doc[field]}\.pdf', x), self.zipfile.namelist())):
found = True
if file_id := doc.get(field):
# look for a file with the file id anywhere in the filename
if any(filter(lambda x: re.search(file_id + r'\w*\.pdf$', x), self.zipfile.namelist())):
found = True

if not found:
print(json.dumps({'warning': f'File for {doc["symbol1"]} not found in zip file'}))
Expand All @@ -128,19 +130,19 @@ def iter_files(self, callback: Callable) -> Iterator:
at once.'''

for name in self.zipfile.namelist():
# filenames contain a series of digits preceeding the file extension that can be matched to the metadata
match = re.match(r'.*?(\d+)\.pdf$', name)
# filenames contain a series of digits (and letters?) preceeding the file extension that can be matched to the metadata
match = re.search(r'(\w+)\.pdf$', name)

if match:
filename = int(match.group(1))
filename = match.group(1)

# check both jobId and odsNo in the metadata, as the field used has varied in the past
if file_data := next(filter(lambda x: x['jobId'] == str(filename), self.data), None):
if file_data := next(filter(lambda x: x['jobId'] == filename, self.data), None):
yield callback(self.zipfile.open(name), file_data)
elif file_data := next(filter(lambda x: x['odsNo'] == str(filename), self.data), None):
elif file_data := next(filter(lambda x: x['odsNo'] == filename, self.data), None):
yield callback(self.zipfile.open(name), file_data)
else:
print(json.dumps({'warning': f'Data for "{name}" not found in zip file'}))
print(json.dumps({'warning': f'Data for "{name}" not found in zip file'}))

class Schema():
pass
Loading