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

style: fix code formatting with black, isort, and flake8

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-12 03:21:41 +00:00
parent f79bd2cb0c
commit ff9a3ff49f
87 changed files with 874 additions and 729 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/extract_metadata_with_gpt.py
+24 -10
View File
@@ -112,7 +112,11 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
content = completion.choices[0].message.content
logger.info(f"[{task_id}] Raw classification response for {filename}: {content[:200]}...")
log_task_progress(
task_id, "call_openai", "success", "Received OpenAI response", file_id=file_id,
task_id,
"call_openai",
"success",
"Received OpenAI response",
file_id=file_id,
detail=f"Raw classification response:\n{content}",
)
@@ -120,13 +124,17 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
if not json_text:
logger.error(f"[{task_id}] Could not find valid JSON in GPT response for {filename}.")
log_task_progress(
task_id, "extract_metadata_with_gpt", "failure", "Invalid JSON in response", file_id=file_id,
task_id,
"extract_metadata_with_gpt",
"failure",
"Invalid JSON in response",
file_id=file_id,
detail=f"Could not parse valid JSON from GPT response.\nRaw response:\n{content}",
)
return {}
metadata = json.loads(json_text)
# SECURITY: Validate filename format from GPT to prevent path traversal
# The prompt requests filenames with only letters, numbers, periods, and underscores
# Enforce this constraint to prevent malicious filenames
@@ -138,16 +146,18 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
# 1. Potential locale-specific \w behavior
# 2. Files literally named ".." which are valid but problematic
# 3. Future code changes that might relax the regex
if not re.match(r'^[\w\-\. ]+$', suggested_filename) or ".." in suggested_filename:
logger.warning(
f"[{task_id}] Invalid filename format from GPT: '{suggested_filename}', using fallback"
)
if not re.match(r"^[\w\-\. ]+$", suggested_filename) or ".." in suggested_filename:
logger.warning(f"[{task_id}] Invalid filename format from GPT: '{suggested_filename}', using fallback")
# Reset to empty to trigger fallback to original filename
metadata["filename"] = ""
logger.info(f"[{task_id}] Extracted metadata: {metadata}")
log_task_progress(
task_id, "parse_metadata", "success", f"Parsed metadata: {list(metadata.keys())}", file_id=file_id,
task_id,
"parse_metadata",
"success",
f"Parsed metadata: {list(metadata.keys())}",
file_id=file_id,
detail=f"Extracted metadata:\n{json.dumps(metadata, ensure_ascii=False, indent=2)}",
)
@@ -164,7 +174,11 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
except Exception as e:
logger.exception(f"[{task_id}] OpenAI classification failed for {filename}: {e}")
log_task_progress(
task_id, "extract_metadata_with_gpt", "failure", f"Exception: {str(e)}", file_id=file_id,
task_id,
"extract_metadata_with_gpt",
"failure",
f"Exception: {str(e)}",
file_id=file_id,
detail=f"OpenAI classification failed for {filename}.\nException: {str(e)}",
)
return {}