Examples: Don't export experimental output by default

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2024-09-25 15:56:29 +02:00
parent ad2bd714d4
commit ba9d115f64

View File

@ -12,6 +12,8 @@ from docling.document_converter import DocumentConverter
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
USE_EXPERIMENTAL = False
def export_documents( def export_documents(
conv_results: Iterable[ConversionResult], conv_results: Iterable[ConversionResult],
@ -32,6 +34,19 @@ def export_documents(
with (output_dir / f"{doc_filename}.json").open("w") as fp: with (output_dir / f"{doc_filename}.json").open("w") as fp:
fp.write(json.dumps(conv_res.render_as_dict())) fp.write(json.dumps(conv_res.render_as_dict()))
# Export Text format:
with (output_dir / f"{doc_filename}.txt").open("w") as fp:
fp.write(conv_res.render_as_text())
# Export Markdown format:
with (output_dir / f"{doc_filename}.md").open("w") as fp:
fp.write(conv_res.render_as_markdown())
# Export Document Tags format:
with (output_dir / f"{doc_filename}.doctags").open("w") as fp:
fp.write(conv_res.render_as_doctags())
if USE_EXPERIMENTAL:
# Export Docling document format to JSON (experimental): # Export Docling document format to JSON (experimental):
with (output_dir / f"{doc_filename}.experimental.json").open("w") as fp: with (output_dir / f"{doc_filename}.experimental.json").open("w") as fp:
fp.write( fp.write(
@ -49,25 +64,15 @@ def export_documents(
) )
# Export Docling document format to doctags (experimental): # Export Docling document format to doctags (experimental):
with (output_dir / f"{doc_filename}.experimental.doctags").open("w") as fp: with (output_dir / f"{doc_filename}.experimental.doctags").open(
"w"
) as fp:
fp.write(conv_res.experimental.export_to_document_tokens()) fp.write(conv_res.experimental.export_to_document_tokens())
# Export Docling document format to markdown (experimental): # Export Docling document format to markdown (experimental):
with (output_dir / f"{doc_filename}.experimental.md").open("w") as fp: with (output_dir / f"{doc_filename}.experimental.md").open("w") as fp:
fp.write(conv_res.experimental.export_to_markdown()) fp.write(conv_res.experimental.export_to_markdown())
# Export Text format:
with (output_dir / f"{doc_filename}.txt").open("w") as fp:
fp.write(conv_res.render_as_text())
# Export Markdown format:
with (output_dir / f"{doc_filename}.md").open("w") as fp:
fp.write(conv_res.render_as_markdown())
# Export Document Tags format:
with (output_dir / f"{doc_filename}.doctags").open("w") as fp:
fp.write(conv_res.render_as_doctags())
elif conv_res.status == ConversionStatus.PARTIAL_SUCCESS: elif conv_res.status == ConversionStatus.PARTIAL_SUCCESS:
_log.info( _log.info(
f"Document {conv_res.input.file} was partially converted with the following errors:" f"Document {conv_res.input.file} was partially converted with the following errors:"