Import statement updates from docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-15 10:11:10 +02:00
parent 8710506072
commit dac82ca7f2
29 changed files with 65 additions and 85 deletions

View File

@@ -32,23 +32,23 @@ def export_documents(
doc_filename = conv_res.input.file.stem
if USE_V2:
# Export Docling document format to JSON (experimental):
# Export Docling document format to JSON:
with (output_dir / f"{doc_filename}.json").open("w") as fp:
fp.write(json.dumps(conv_res.document.export_to_dict()))
# Export Docling document format to YAML (experimental):
# Export Docling document format to YAML:
with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
fp.write(yaml.safe_dump(conv_res.document.export_to_dict()))
# Export Docling document format to doctags (experimental):
# Export Docling document format to doctags:
with (output_dir / f"{doc_filename}.doctags.txt").open("w") as fp:
fp.write(conv_res.document.export_to_document_tokens())
# Export Docling document format to markdown (experimental):
# Export Docling document format to markdown:
with (output_dir / f"{doc_filename}.md").open("w") as fp:
fp.write(conv_res.document.export_to_markdown())
# Export Docling document format to text (experimental):
# Export Docling document format to text:
with (output_dir / f"{doc_filename}.txt").open("w") as fp:
fp.write(conv_res.document.export_to_markdown(strict_text=True))

View File

@@ -58,8 +58,8 @@ for res in conv_results:
f"Document {res.input.file.name} converted."
f"\nSaved markdown output to: {str(out_path)}"
)
# print(res.experimental.export_to_markdown())
# Export Docling document format to markdown (experimental):
# print(res.docdocument.export_to_markdown())
# Export Docling document format to markdowndoc:
with (out_path / f"{res.input.file.name}.md").open("w") as fp:
fp.write(res.document.export_to_markdown())