Skip to content

fix: layout cluster & unit test #475

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
renpengli01 wants to merge 2 commits into from
Closed

fix: layout cluster & unit test #475

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ca379e8
fix: layout cluster & unit test
renpengli01 Jun 25, 2025
05201ac
Merge branch 'dev' into rpl011
renpengli01 Jun 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions llm_web_kit/html_layout/html_layout_cosin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,8 +103,7 @@ def __get_children(el_lst: List[HtmlElement], layer_n: int, tag_attr: Dict):
parent_tag_attr.add(f'<{tag}>')
else:
attrs_str = __parse_attributes(child)
if attrs_str is not None:
parent_tag_attr.add(f'<{tag} {attrs_str}>' if attrs_str else f'<{tag}>')
parent_tag_attr.add(f'<{tag} {attrs_str}>' if attrs_str else f'<{tag}>')

el_tag_attr.append(parent_tag_attr)

Expand All @@ -130,15 +129,15 @@ def __parse_attributes(element: HtmlElement):
class_d = class_attr.split()
if len(class_d) > 1:
class_s = ' '.join([i for i in class_d if not RE_NUM.search(i)])
else:
elif len(class_d) == 1:
class_s = __standardizing_dynamic_attributes(class_d[0])

id_attr = element.get('id')
if id_attr:
id_d = id_attr.split()
if len(id_d) > 1:
id_s = ' '.join([i for i in id_d if not RE_NUM.search(i)])
else:
elif len(id_d) == 1:
id_s = __standardizing_dynamic_attributes(id_d[0])

if not class_s and not id_s:
Expand Down Expand Up @@ -269,7 +268,7 @@ def __parse_valid_layer(features: List[Dict]) -> int:
layer_max_l.append(max_key)
counter = Counter(layer_max_l)
layer_n = counter.most_common(1)[0][0]
return layer_n if layer_n > 5 else len(features[0]['tags'])
return layer_n if layer_n > 1 else len(features[0]['tags'])


def cluster_html_struct(sampled_list: List[Dict], threshold=0.95) -> List[Dict]:
Expand Down
7 changes: 7 additions & 0 deletions tests/llm_web_kit/html_layout/test_html_layout_cosin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,11 @@
4: ['div', 'div', 'header', 'article', 'aside', 'div', 'a', 'div', 'div']}},
'expected': {'layer_n': {1: 1, 2: 5, 3: 7, 4: 9}, 'total_n': 22}}
]
TEST_CLUSTER_TEST = [
{'feature': {'tags': {'2': ['img', 'a']}}, 'layer_n': {'2': 2}, 'total_n': 2},
{'feature': {'tags': {'2': ['img', 'a']}}, 'layer_n': {'2': 2}, 'total_n': 2},
{'feature': {'tags': {'2': ['img', 'a']}}, 'layer_n': {'2': 2}, 'total_n': 2}
]


class TestHtmllayoutcosin(unittest.TestCase):
Expand All @@ -72,6 +77,8 @@ def test_cluster_html_struct(self):
TEST_CLUSTER_HTML['input']]
res, layout_list = cluster_html_struct(features)
self.assertEqual(TEST_CLUSTER_HTML['expected'], layout_list)
res, layout_list = cluster_html_struct(TEST_CLUSTER_TEST)
self.assertEqual(layout_list, [0])

def test_similarity(self):
for TEST_SIMIL_HTML in TEST_SIMIL_HTMLS:
Expand Down
Loading