Spaces:
Sleeping
Sleeping
File size: 2,044 Bytes
bb869fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import logging
import json
from rule_extractor import get_rules_from_url, format_rules_for_display
from doc_analyzer import analyze_document
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
def combine_rules(url_rules, pasted_rules):
"""Combine URL-extracted rules and manually pasted rules"""
combined_rules = ""
if url_rules and (url_rules.strip().startswith('[') or url_rules.strip().startswith('{')):
try:
rules_data = json.loads(url_rules)
if isinstance(rules_data, list) and len(rules_data) > 0:
rules_data = rules_data[0]
url_rules = format_rules_for_display(rules_data)
except Exception as e:
logging.error(f"Failed to parse URL rules as JSON: {e}")
if url_rules:
combined_rules += url_rules
if pasted_rules:
if url_rules:
combined_rules += "\n\n## Additional Manually Pasted Rules\n\n" + pasted_rules
else:
combined_rules = "# Manually Pasted Rules\n\n" + pasted_rules
return combined_rules
def extract_rules(journal_url):
"""Extract formatting rules from a given URL."""
try:
logging.info(f"Extracting rules from URL: {journal_url}")
rules = get_rules_from_url(journal_url)
logging.info("Successfully extracted rules from URL.")
return rules
except Exception as e:
logging.error(f"Error extracting rules from URL: {e}")
return {"error": f"Failed to extract rules from URL: {e}"}
def analyze_uploaded_document(uploaded_file, rules):
"""Analyze the uploaded document against the provided rules."""
try:
logging.info(f"Analyzing document: {uploaded_file.name}")
results = analyze_document(uploaded_file, rules)
logging.info("Successfully analyzed document.")
return results
except Exception as e:
logging.error(f"Error analyzing document: {e}")
return {"error": f"Failed to analyze document: {e}"}
|