45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
import os
|
|
import sys
|
|
import tempfile
|
|
from pathlib import Path
|
|
from mistral_ocr.commands import process, convert
|
|
|
|
def run(args):
|
|
# Ensure that if --images is true, include_image_base64 is also true
|
|
include_image_base64 = args.images
|
|
|
|
# If output file is specified, enable single file mode
|
|
if args.output_file:
|
|
args.single_file = True
|
|
|
|
# Create temporary file for JSON output if not specified
|
|
json_output_path = args.json_file
|
|
temp_file = None
|
|
|
|
if not json_output_path:
|
|
temp_file = tempfile.NamedTemporaryFile(suffix=".json", delete=False)
|
|
json_output_path = temp_file.name
|
|
temp_file.close()
|
|
|
|
try:
|
|
# Step 1: Process the document
|
|
if args.file_or_url.startswith(("http://", "https://")):
|
|
process.process_url(args.file_or_url, json_output_path, include_image_base64)
|
|
else:
|
|
process.process_local_file(args.file_or_url, json_output_path, include_image_base64)
|
|
|
|
# Step 2: Convert the JSON to markdown
|
|
print("Converting JSON to Markdown...")
|
|
convert.convert_json_to_markdown(json_output_path, args)
|
|
|
|
except Exception as e:
|
|
print(f"Error processing and converting document: {e}", file=sys.stderr)
|
|
sys.exit(1)
|
|
finally:
|
|
# Clean up temporary file if we created one
|
|
if temp_file and not args.json_file:
|
|
try:
|
|
os.unlink(temp_file.name)
|
|
except:
|
|
pass
|