a8c6b29a67
* Use docling-parse page-by-page Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Propagate document_hash to PDF backends, use docling-parse 1.0.0 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Upgrade lockfile Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * repin after more packages on pypi Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
80 lines
2.2 KiB
Python
80 lines
2.2 KiB
Python
import json
|
|
import logging
|
|
import time
|
|
from io import BytesIO
|
|
from pathlib import Path
|
|
from typing import Iterable
|
|
|
|
from docling.datamodel.base_models import (
|
|
ConversionStatus,
|
|
DocumentStream,
|
|
PipelineOptions,
|
|
)
|
|
from docling.datamodel.document import ConvertedDocument, DocumentConversionInput
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
|
def export_documents(
|
|
converted_docs: Iterable[ConvertedDocument],
|
|
output_dir: Path,
|
|
):
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
success_count = 0
|
|
failure_count = 0
|
|
|
|
for doc in converted_docs:
|
|
if doc.status == ConversionStatus.SUCCESS:
|
|
success_count += 1
|
|
doc_filename = doc.input.file.stem
|
|
|
|
# Export Deep Search document JSON format:
|
|
with (output_dir / f"{doc_filename}.json").open("w") as fp:
|
|
fp.write(json.dumps(doc.render_as_dict()))
|
|
|
|
# Export Markdown format:
|
|
with (output_dir / f"{doc_filename}.md").open("w") as fp:
|
|
fp.write(doc.render_as_markdown())
|
|
else:
|
|
_log.info(f"Document {doc.input.file} failed to convert.")
|
|
failure_count += 1
|
|
|
|
_log.info(
|
|
f"Processed {success_count + failure_count} docs, of which {failure_count} failed"
|
|
)
|
|
|
|
|
|
def main():
|
|
logging.basicConfig(level=logging.INFO)
|
|
|
|
input_doc_paths = [
|
|
Path("./test/data/2206.01062.pdf"),
|
|
Path("./test/data/2203.01017v2.pdf"),
|
|
Path("./test/data/2305.03393v1.pdf"),
|
|
Path("./test/data/redp5110.pdf"),
|
|
Path("./test/data/redp5695.pdf"),
|
|
]
|
|
|
|
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())
|
|
# docs = [DocumentStream(filename="my_doc.pdf", stream=buf)]
|
|
# input = DocumentConversionInput.from_streams(docs)
|
|
|
|
doc_converter = DocumentConverter(pipeline_options=PipelineOptions(do_ocr=False))
|
|
|
|
input = DocumentConversionInput.from_paths(input_doc_paths)
|
|
|
|
start_time = time.time()
|
|
|
|
converted_docs = doc_converter.convert(input)
|
|
export_documents(converted_docs, output_dir=Path("./scratch"))
|
|
|
|
end_time = time.time() - start_time
|
|
|
|
_log.info(f"All documents were converted in {end_time:.2f} seconds.")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|