mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(html): use 'start' attribute when parsing ordered lists from HTML docs (#1062)

Browse Source 
* 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>
This commit is contained in:
Cesar Berrospi Ramis
2025-02-27 09:46:57 +01:00
committed by GitHub
parent 37dd8c1cc7
commit de7b963b09
2 changed files with 76 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
tests/test_backend_html.py
View File

@@ -1,4 +1,4 @@
import os
from io import BytesIO
from pathlib import Path
from docling.backend.html_backend import HTMLDocumentBackend
@@ -41,6 +41,62 @@ def test_heading_levels():
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