mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Examples: Don't export experimental output by default

Browse Source 
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
1 changed files with 29 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
examples/batch_convert.py
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],
@ -32,30 +34,6 @@ 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 Docling document format to JSON (experimental):
with (output_dir / f"{doc_filename}.experimental.json").open("w") as fp:
fp.write(
json.dumps(
conv_res.experimental.model_dump(mode="json", by_alias=True)
)
)
# Export Docling document format to YAML (experimental):
with (output_dir / f"{doc_filename}.experimental.yaml").open("w") as fp:
fp.write(
yaml.safe_dump(
conv_res.experimental.model_dump(mode="json", by_alias=True)
)
)
# Export Docling document format to doctags (experimental):
with (output_dir / f"{doc_filename}.experimental.doctags").open("w") as fp:
fp.write(conv_res.experimental.export_to_document_tokens())
# Export Docling document format to markdown (experimental):
with (output_dir / f"{doc_filename}.experimental.md").open("w") as fp:
fp.write(conv_res.experimental.export_to_markdown())
# Export Text format: # Export Text format:
with (output_dir / f"{doc_filename}.txt").open("w") as fp: with (output_dir / f"{doc_filename}.txt").open("w") as fp:
fp.write(conv_res.render_as_text()) fp.write(conv_res.render_as_text())
@ -68,6 +46,33 @@ def export_documents(
with (output_dir / f"{doc_filename}.doctags").open("w") as fp: with (output_dir / f"{doc_filename}.doctags").open("w") as fp:
fp.write(conv_res.render_as_doctags()) fp.write(conv_res.render_as_doctags())
if USE_EXPERIMENTAL:
# Export Docling document format to JSON (experimental):
with (output_dir / f"{doc_filename}.experimental.json").open("w") as fp:
fp.write(
json.dumps(
conv_res.experimental.model_dump(mode="json", by_alias=True)
)
)
# Export Docling document format to YAML (experimental):
with (output_dir / f"{doc_filename}.experimental.yaml").open("w") as fp:
fp.write(
yaml.safe_dump(
conv_res.experimental.model_dump(mode="json", by_alias=True)
)
)
# Export Docling document format to doctags (experimental):
with (output_dir / f"{doc_filename}.experimental.doctags").open(
"w"
) as fp:
fp.write(conv_res.experimental.export_to_document_tokens())
# Export Docling document format to markdown (experimental):
with (output_dir / f"{doc_filename}.experimental.md").open("w") as fp:
fp.write(conv_res.experimental.export_to_markdown())
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:"