mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00

* updated the base-model and added the asciidoc_backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the asciidoc backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Ensure all models work only on valid pages (#158) Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * ci: run ci also on forks (#160) --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> * fix: fix legacy doc ref (#162) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> * docs: typo fix (#155) * Docs: Typo fix - Corrected spelling of invidual to automatic Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> * add synchronize event for forks Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> * feat: add coverage_threshold to skip OCR for small images (#161) * feat: add coverage_threshold to skip OCR for small images Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * filter individual boxes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rename option Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * chore: bump version to 2.1.0 [skip ci] * adding tests for asciidocs Signed-off-by: Peter Staar <taa@zurich.ibm.com> * first working asciidoc parser Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the code Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * adding test_02.asciidoc Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Drafting Markdown backend via Marko library Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * work in progress on MD backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * md_backend produces docling document with headers, paragraphs, lists Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Improvements in md parsing Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Detecting and assembling tables in markdown in temporary buffers Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Added initial docling table support to md_backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Cleaned code, improved logging for MD Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixes MyPy requirements, and rest of pre-commit Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed example run_md, added origin info to md_backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * working on asciidocs, struggling with ImageRef Signed-off-by: Peter Staar <taa@zurich.ibm.com> * able to parse the captions and image uri's Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Update all backends with proper filename in DocumentOrigin Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update to docling-core v2.1.0 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for MD Backend, to avoid duplicated text inserts into docling doc Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fix styling Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Added support for code blocks and fenced code in MD Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * cleaned prints Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Added proper processing of in-line textual elements for MD backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed issues with duplicated paragraphs and incorrect lists in pptx Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed issue with group ordeering in pptx backend, added gebug log into run with formats Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Peter Staar <taa@zurich.ibm.com> Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
82 lines
2.6 KiB
Python
82 lines
2.6 KiB
Python
import json
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
import yaml
|
|
|
|
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.document_converter import (
|
|
DocumentConverter,
|
|
PdfFormatOption,
|
|
WordFormatOption,
|
|
)
|
|
from docling.pipeline.simple_pipeline import SimplePipeline
|
|
from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
|
def main():
|
|
input_paths = [
|
|
Path("README.md"),
|
|
Path("tests/data/wiki_duck.html"),
|
|
Path("tests/data/word_sample.docx"),
|
|
Path("tests/data/lorem_ipsum.docx"),
|
|
Path("tests/data/powerpoint_sample.pptx"),
|
|
Path("tests/data/2305.03393v1-pg9-img.png"),
|
|
Path("tests/data/2206.01062.pdf"),
|
|
Path("tests/data/test_01.asciidoc"),
|
|
Path("tests/data/test_01.asciidoc"),
|
|
]
|
|
|
|
## for defaults use:
|
|
# doc_converter = DocumentConverter()
|
|
|
|
## to customize use:
|
|
|
|
doc_converter = (
|
|
DocumentConverter( # all of the below is optional, has internal defaults.
|
|
allowed_formats=[
|
|
InputFormat.PDF,
|
|
InputFormat.IMAGE,
|
|
InputFormat.DOCX,
|
|
InputFormat.HTML,
|
|
InputFormat.PPTX,
|
|
InputFormat.ASCIIDOC,
|
|
InputFormat.MD,
|
|
], # whitelist formats, non-matching files are ignored.
|
|
format_options={
|
|
InputFormat.PDF: PdfFormatOption(
|
|
pipeline_cls=StandardPdfPipeline, backend=PyPdfiumDocumentBackend
|
|
),
|
|
InputFormat.DOCX: WordFormatOption(
|
|
pipeline_cls=SimplePipeline # , backend=MsWordDocumentBackend
|
|
),
|
|
},
|
|
)
|
|
)
|
|
|
|
conv_results = doc_converter.convert_all(input_paths)
|
|
|
|
for res in conv_results:
|
|
out_path = Path("scratch")
|
|
print(
|
|
f"Document {res.input.file.name} converted."
|
|
f"\nSaved markdown output to: {str(out_path)}"
|
|
)
|
|
_log.debug(res.document._export_to_indented_text(max_text_len=16))
|
|
# Export Docling document format to markdowndoc:
|
|
with (out_path / f"{res.input.file.stem}.md").open("w") as fp:
|
|
fp.write(res.document.export_to_markdown())
|
|
|
|
with (out_path / f"{res.input.file.stem}.json").open("w") as fp:
|
|
fp.write(json.dumps(res.document.export_to_dict()))
|
|
|
|
with (out_path / f"{res.input.file.stem}.yaml").open("w") as fp:
|
|
fp.write(yaml.safe_dump(res.document.export_to_dict()))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|