HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Update convert_plaintext_links_to_html (#18786)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2025-01-21 02:20:26 +01:00 • committed by GitHub
parent 28818801cb
commit 617dea8e25
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/build_docs.py
View file

@ -37,6 +37,7 @@ from tqdm import tqdm
os.environ["JUPYTER_PLATFORM_DIRS"] = "1" # fix DeprecationWarning: Jupyter is migrating to use standard platformdirs os.environ["JUPYTER_PLATFORM_DIRS"] = "1" # fix DeprecationWarning: Jupyter is migrating to use standard platformdirs
DOCS = Path(__file__).parent.resolve() DOCS = Path(__file__).parent.resolve()
SITE = DOCS.parent / "site" SITE = DOCS.parent / "site"
LINK_PATTERN = re.compile(r"(https?://[^\s()<>]*[^\s()<>.,:;!?\'\"])")
def create_vercel_config(): def create_vercel_config():
@ -72,7 +73,6 @@ def prepare_docs_markdown(clone_repos=True):
def update_page_title(file_path: Path, new_title: str): def update_page_title(file_path: Path, new_title: str):
"""Update the title of an HTML file.""" """Update the title of an HTML file."""
# Read the content of the file
with open(file_path, encoding="utf-8") as file: with open(file_path, encoding="utf-8") as file:
content = file.read() content = file.read()
@ -206,11 +206,7 @@ def convert_plaintext_links_to_html(content):
for paragraph in main_content.find_all(["p", "li"]): # Focus on paragraphs and list items for paragraph in main_content.find_all(["p", "li"]): # Focus on paragraphs and list items
for text_node in paragraph.find_all(string=True, recursive=False): for text_node in paragraph.find_all(string=True, recursive=False):
if text_node.parent.name not in {"a", "code"}: # Ignore links and code blocks if text_node.parent.name not in {"a", "code"}: # Ignore links and code blocks
new_text = re.sub( new_text = LINK_PATTERN.sub(r'<a href="\1">\1</a>', str(text_node))
r"(https?://[^\s()<>]*[^\s()<>.,:;!?\'\"])",
r'<a href="\1">\1</a>',
str(text_node),
)
if "<a href=" in new_text: if "<a href=" in new_text:
# Parse the new text with BeautifulSoup to handle HTML properly # Parse the new text with BeautifulSoup to handle HTML properly
new_soup = BeautifulSoup(new_text, "html.parser") new_soup = BeautifulSoup(new_text, "html.parser")