de7b963b09
* fix(html): use 'start' attribute in ordered lists When parsing ordered lists in HTML, take into account the 'start' attribute if it exists. Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * chore(html): reduce verbosity in HTML backend Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> --------- Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
144 lines
3.9 KiB
Python
144 lines
3.9 KiB
Python
from io import BytesIO
|
|
from pathlib import Path
|
|
|
|
from docling.backend.html_backend import HTMLDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.document import (
|
|
ConversionResult,
|
|
DoclingDocument,
|
|
InputDocument,
|
|
SectionHeaderItem,
|
|
)
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
from .verify_utils import verify_document, verify_export
|
|
|
|
GENERATE = False
|
|
|
|
|
|
def test_heading_levels():
|
|
in_path = Path("tests/data/html/wiki_duck.html")
|
|
in_doc = InputDocument(
|
|
path_or_stream=in_path,
|
|
format=InputFormat.HTML,
|
|
backend=HTMLDocumentBackend,
|
|
)
|
|
backend = HTMLDocumentBackend(
|
|
in_doc=in_doc,
|
|
path_or_stream=in_path,
|
|
)
|
|
doc = backend.convert()
|
|
|
|
found_lvl_2 = found_lvl_3 = False
|
|
for item, _ in doc.iterate_items():
|
|
if isinstance(item, SectionHeaderItem):
|
|
if item.text == "Etymology":
|
|
found_lvl_2 = True
|
|
assert item.level == 2
|
|
elif item.text == "Feeding":
|
|
found_lvl_3 = True
|
|
assert item.level == 3
|
|
assert found_lvl_2 and found_lvl_3
|
|
|
|
|
|
def test_ordered_lists():
|
|
test_set: list[tuple[bytes, str]] = []
|
|
|
|
test_set.append(
|
|
(
|
|
b"<html><body><ol><li>1st item</li><li>2nd item</li></ol></body></html>",
|
|
"1. 1st item\n2. 2nd item",
|
|
)
|
|
)
|
|
test_set.append(
|
|
(
|
|
b'<html><body><ol start="1"><li>1st item</li><li>2nd item</li></ol></body></html>',
|
|
"1. 1st item\n2. 2nd item",
|
|
)
|
|
)
|
|
test_set.append(
|
|
(
|
|
b'<html><body><ol start="2"><li>1st item</li><li>2nd item</li></ol></body></html>',
|
|
"2. 1st item\n3. 2nd item",
|
|
)
|
|
)
|
|
test_set.append(
|
|
(
|
|
b'<html><body><ol start="0"><li>1st item</li><li>2nd item</li></ol></body></html>',
|
|
"0. 1st item\n1. 2nd item",
|
|
)
|
|
)
|
|
test_set.append(
|
|
(
|
|
b'<html><body><ol start="-5"><li>1st item</li><li>2nd item</li></ol></body></html>',
|
|
"1. 1st item\n2. 2nd item",
|
|
)
|
|
)
|
|
test_set.append(
|
|
(
|
|
b'<html><body><ol start="foo"><li>1st item</li><li>2nd item</li></ol></body></html>',
|
|
"1. 1st item\n2. 2nd item",
|
|
)
|
|
)
|
|
|
|
for pair in test_set:
|
|
in_doc = InputDocument(
|
|
path_or_stream=BytesIO(pair[0]),
|
|
format=InputFormat.HTML,
|
|
backend=HTMLDocumentBackend,
|
|
filename="test",
|
|
)
|
|
backend = HTMLDocumentBackend(
|
|
in_doc=in_doc,
|
|
path_or_stream=BytesIO(pair[0]),
|
|
)
|
|
doc: DoclingDocument = backend.convert()
|
|
assert doc
|
|
assert doc.export_to_markdown() == pair[1]
|
|
|
|
|
|
def get_html_paths():
|
|
|
|
# Define the directory you want to search
|
|
directory = Path("./tests/data/html/")
|
|
|
|
# List all HTML files in the directory and its subdirectories
|
|
html_files = sorted(directory.rglob("*.html"))
|
|
return html_files
|
|
|
|
|
|
def get_converter():
|
|
|
|
converter = DocumentConverter(allowed_formats=[InputFormat.HTML])
|
|
|
|
return converter
|
|
|
|
|
|
def test_e2e_html_conversions():
|
|
|
|
html_paths = get_html_paths()
|
|
converter = get_converter()
|
|
|
|
for html_path in html_paths:
|
|
# print(f"converting {html_path}")
|
|
|
|
gt_path = (
|
|
html_path.parent.parent / "groundtruth" / "docling_v2" / html_path.name
|
|
)
|
|
|
|
conv_result: ConversionResult = converter.convert(html_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"
|
|
|
|
assert verify_document(doc, str(gt_path) + ".json", GENERATE)
|