Skip to content
Open
Changes from all commits
Commits
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
32 changes: 22 additions & 10 deletions run_pageindex.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,10 @@
parser.add_argument('--pdf_path', type=str, help='Path to the PDF file')
parser.add_argument('--md_path', type=str, help='Path to the Markdown file')

parser.add_argument('--output-dir', type=str, default='./results',
help='Output directory for results (default: ./results)')
parser.add_argument('--output-file', type=str, default=None,
help='Output file path (overrides default naming)')
parser.add_argument('--model', type=str, default=None, help='Model to use (overrides config.yaml)')

parser.add_argument('--toc-check-pages', type=int, default=None,
Expand Down Expand Up @@ -67,11 +71,15 @@
# Process the PDF
toc_with_page_number = page_index_main(args.pdf_path, opt)
print('Parsing done, saving to file...')

# Save results
pdf_name = os.path.splitext(os.path.basename(args.pdf_path))[0]
output_dir = './results'
output_file = f'{output_dir}/{pdf_name}_structure.json'

# Determine output path
if args.output_file:
output_file = args.output_file
output_dir = os.path.dirname(output_file) or './results'
else:
pdf_name = os.path.splitext(os.path.basename(args.pdf_path))[0]
output_dir = args.output_dir
output_file = f'{output_dir}/{pdf_name}_structure.json'
os.makedirs(output_dir, exist_ok=True)

with open(output_file, 'w', encoding='utf-8') as f:
Expand Down Expand Up @@ -121,11 +129,15 @@
))

print('Parsing done, saving to file...')

# Save results
md_name = os.path.splitext(os.path.basename(args.md_path))[0]
output_dir = './results'
output_file = f'{output_dir}/{md_name}_structure.json'

# Determine output path
if args.output_file:
output_file = args.output_file
output_dir = os.path.dirname(output_file) or './results'
else:
md_name = os.path.splitext(os.path.basename(args.md_path))[0]
output_dir = args.output_dir
output_file = f'{output_dir}/{md_name}_structure.json'
os.makedirs(output_dir, exist_ok=True)

with open(output_file, 'w', encoding='utf-8') as f:
Expand Down