Skip to content

⚡️ Speed up function can_unstructured_elements_be_merged by 97% #5

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

Open
codeflash-ai wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up function can_unstructured_elements_be_merged by 97% #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 8 additions & 6 deletions unstructured/partition/html/transformations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from __future__ import annotations

import functools
import html
from collections import OrderedDict
from itertools import chain
Expand Down Expand Up @@ -161,12 +162,8 @@ def can_unstructured_elements_be_merged(
if current_element.metadata.category_depth != next_element.metadata.category_depth:
return False

current_html_tags = BeautifulSoup(
current_element.metadata.text_as_html, "html.parser"
).find_all(recursive=False)
next_html_tags = BeautifulSoup(next_element.metadata.text_as_html, "html.parser").find_all(
recursive=False
)
current_html_tags = _cached_html_tags(current_element.metadata.text_as_html)
next_html_tags = _cached_html_tags(next_element.metadata.text_as_html)

ontology_elements = [
parse_html_to_ontology_element(html_tag)
Expand Down Expand Up @@ -478,3 +475,8 @@ def get_escaped_attributes(soup: Tag) -> dict[str, str | list[str]]:
escaped_value = html.escape(value)
escaped_attrs[escaped_key] = escaped_value
return escaped_attrs


@functools.lru_cache(maxsize=4096)
def _cached_html_tags(text_as_html: str):
return BeautifulSoup(text_as_html, "html.parser").find_all(recursive=False)