Commit 3379f3b3 authored by icecraft's avatar icecraft
Browse files

fix: support non-pdf file in batch mode

parent e38efb97
...@@ -137,6 +137,10 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id): ...@@ -137,6 +137,10 @@ def cli(path, output_dir, method, lang, debug_able, start_page_id, end_page_id):
doc_paths = [] doc_paths = []
for doc_path in Path(path).glob('*'): for doc_path in Path(path).glob('*'):
if doc_path.suffix in pdf_suffixes + image_suffixes + ms_office_suffixes: if doc_path.suffix in pdf_suffixes + image_suffixes + ms_office_suffixes:
if doc_path.suffix not in ms_office_suffixes:
basename = Path(doc_path).stem
convert_file_to_pdf(str(doc_path), temp_dir)
doc_path = Path(os.path.join(temp_dir, f'{basename}.pdf'))
doc_paths.append(doc_path) doc_paths.append(doc_path)
datasets = batch_build_dataset(doc_paths, 4, lang) datasets = batch_build_dataset(doc_paths, 4, lang)
batch_do_parse(output_dir, [str(doc_path.stem) for doc_path in doc_paths], datasets, method, debug_able, lang=lang) batch_do_parse(output_dir, [str(doc_path.stem) for doc_path in doc_paths], datasets, method, debug_able, lang=lang)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment