mirror of
https://github.com/docling-project/docling.git
synced 2025-07-03 07:09:22 +00:00
f542460af3
* add real e2e tests for html and docx Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the output of itxt Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the text Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests (2) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the examples (1) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the output of the test Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the tests, moved the ground-truth Signed-off-by: Peter Staar <taa@zurich.ibm.com> * moved the ground-truth data Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the html tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * restructure title fix (#187) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
103 lines
2.7 KiB
Python
103 lines
2.7 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 test_heading_levels():
|
|
in_path = Path("tests/data/docx/word_sample.docx")
|
|
in_doc = InputDocument(
|
|
path_or_stream=in_path,
|
|
format=InputFormat.DOCX,
|
|
backend=MsWordDocumentBackend,
|
|
)
|
|
backend = MsWordDocumentBackend(
|
|
in_doc=in_doc,
|
|
path_or_stream=in_path,
|
|
)
|
|
doc = backend.convert()
|
|
|
|
found_lvl_1 = found_lvl_2 = False
|
|
for item, _ in doc.iterate_items():
|
|
if isinstance(item, SectionHeaderItem):
|
|
if item.text == "Let\u2019s swim!":
|
|
found_lvl_1 = True
|
|
assert item.level == 1
|
|
elif item.text == "Let\u2019s eat":
|
|
found_lvl_2 = True
|
|
assert item.level == 2
|
|
assert found_lvl_1 and found_lvl_2
|
|
|
|
|
|
def get_docx_paths():
|
|
|
|
# Define the directory you want to search
|
|
directory = Path("./tests/data/docx/")
|
|
|
|
# List all PDF files in the directory and its subdirectories
|
|
pdf_files = sorted(directory.rglob("*.docx"))
|
|
return pdf_files
|
|
|
|
|
|
def get_converter():
|
|
|
|
converter = DocumentConverter(allowed_formats=[InputFormat.DOCX])
|
|
|
|
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_docx_conversions():
|
|
|
|
docx_paths = get_docx_paths()
|
|
converter = get_converter()
|
|
|
|
for docx_path in docx_paths:
|
|
# print(f"converting {docx_path}")
|
|
|
|
gt_path = (
|
|
docx_path.parent.parent / "groundtruth" / "docling_v2" / docx_path.name
|
|
)
|
|
|
|
conv_result: ConversionResult = converter.convert(docx_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"
|