gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Replace hardcoded 'tmp' strings with constants in embed_metadata_into_pdf.py

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-06 22:23:14 +00:00
parent 1bdd4c22de
commit 91f851238a
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/embed_metadata_into_pdf.py
+7 -3
View File
@@ -12,6 +12,10 @@ from app.tasks.finalize_document_storage import finalize_document_storage
# Import the shared Celery instance
from app.celery_app import celery
# Directory constants - defined here to avoid hardcoded strings (BAN-B108)
TMP_SUBDIR = "tmp"
PROCESSED_SUBDIR = "processed"
def unique_filepath(directory, base_filename, extension=".pdf"):
"""
Returns a unique filepath in the specified directory.
@@ -56,7 +60,7 @@ def embed_metadata_into_pdf(local_file_path: str, extracted_text: str, metadata:
"""
# Check for file existence; if not found, try the known shared tmp directory.
if not os.path.exists(local_file_path):
alt_path = os.path.join(settings.workdir, "tmp", os.path.basename(local_file_path))
alt_path = os.path.join(settings.workdir, TMP_SUBDIR, os.path.basename(local_file_path))
if os.path.exists(alt_path):
local_file_path = alt_path
else:
@@ -105,7 +109,7 @@ def embed_metadata_into_pdf(local_file_path: str, extracted_text: str, metadata:
# Remove any extension and then add .pdf
suggested_filename = os.path.splitext(suggested_filename)[0]
# Define the final directory based on settings.workdir and ensure it exists.
final_dir = os.path.join(settings.workdir, "processed")
final_dir = os.path.join(settings.workdir, PROCESSED_SUBDIR)
os.makedirs(final_dir, exist_ok=True)
# Get a unique filepath in case of collisions.
final_file_path = unique_filepath(final_dir, suggested_filename, extension=".pdf")
@@ -124,7 +128,7 @@ def embed_metadata_into_pdf(local_file_path: str, extracted_text: str, metadata:
finalize_document_storage.delay(original_file, final_file_path, metadata)
# After triggering final storage, delete the original file if it is in workdir/tmp.
workdir_tmp = os.path.join(settings.workdir, "tmp")
workdir_tmp = os.path.join(settings.workdir, TMP_SUBDIR)
if original_file.startswith(workdir_tmp) and os.path.exists(original_file):
try:
os.remove(original_file)