mirror of
https://github.com/docling-project/docling.git
synced 2025-07-03 07:09:22 +00:00

* feat: added excel backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * first msexcel backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added tooling for the cli Signed-off-by: Peter Staar <taa@zurich.ibm.com> * first working version for excel parsing of tables Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added proper typing for mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added proper typing for mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * refactor EXCEL to XLSX Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added the unit tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * ran poetry lock Signed-off-by: Peter Staar <taa@zurich.ibm.com> * adding images to output [WIP] 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> * updated the msexcel Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the msexcel (2) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * added tests for merged cells in excel Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the code Signed-off-by: Peter Staar <taa@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com>
78 lines
2.0 KiB
Python
78 lines
2.0 KiB
Python
import json
|
|
import os
|
|
from pathlib import Path
|
|
|
|
from docling.backend.msword_backend import MsWordDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.document import (
|
|
ConversionResult,
|
|
InputDocument,
|
|
SectionHeaderItem,
|
|
)
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
GENERATE = False
|
|
|
|
|
|
def get_xlsx_paths():
|
|
|
|
# Define the directory you want to search
|
|
directory = Path("./tests/data/xlsx/")
|
|
|
|
# List all PDF files in the directory and its subdirectories
|
|
pdf_files = sorted(directory.rglob("*.xlsx"))
|
|
return pdf_files
|
|
|
|
|
|
def get_converter():
|
|
|
|
converter = DocumentConverter(allowed_formats=[InputFormat.XLSX])
|
|
|
|
return converter
|
|
|
|
|
|
def verify_export(pred_text: str, gtfile: str):
|
|
|
|
if not os.path.exists(gtfile) or GENERATE:
|
|
with open(gtfile, "w") as fw:
|
|
fw.write(pred_text)
|
|
|
|
return True
|
|
|
|
else:
|
|
with open(gtfile, "r") as fr:
|
|
true_text = fr.read()
|
|
|
|
assert pred_text == true_text, "pred_itxt==true_itxt"
|
|
return pred_text == true_text
|
|
|
|
|
|
def test_e2e_xlsx_conversions():
|
|
|
|
xlsx_paths = get_xlsx_paths()
|
|
converter = get_converter()
|
|
|
|
for xlsx_path in xlsx_paths:
|
|
# print(f"converting {xlsx_path}")
|
|
|
|
gt_path = (
|
|
xlsx_path.parent.parent / "groundtruth" / "docling_v2" / xlsx_path.name
|
|
)
|
|
|
|
conv_result: ConversionResult = converter.convert(xlsx_path)
|
|
|
|
doc: DoclingDocument = conv_result.document
|
|
|
|
pred_md: str = doc.export_to_markdown()
|
|
assert verify_export(pred_md, str(gt_path) + ".md"), "export to md"
|
|
|
|
pred_itxt: str = doc._export_to_indented_text(
|
|
max_text_len=70, explicit_tables=False
|
|
)
|
|
assert verify_export(
|
|
pred_itxt, str(gt_path) + ".itxt"
|
|
), "export to indented-text"
|
|
|
|
pred_json: str = json.dumps(doc.export_to_dict(), indent=2)
|
|
assert verify_export(pred_json, str(gt_path) + ".json"), "export to json"
|