Update lint_urls.sh (#154838)

Do not match empty urls pieces like "https://"
Add headers for better handling urls like "https://www.amd.com/content/dam/amd/en/documents/instinct-tech-docs/data-sheets/amd-instinct-mi300x-data-sheet.pdf"

Pull Request resolved: https://github.com/pytorch/pytorch/pull/154838
Approved by: https://github.com/Skylion007
This commit is contained in:
Anthony Shoumikhin
2025-06-02 14:50:34 +00:00
committed by PyTorch MergeBot
parent c65e9ad77a
commit dfd6849e77

View File

@ -19,7 +19,7 @@ while IFS=: read -r filepath url; do
code=$(curl -k -gsLm30 --retry 3 --retry-delay 3 --retry-connrefused -o /dev/null -w "%{http_code}" -I "$url") || code=000 code=$(curl -k -gsLm30 --retry 3 --retry-delay 3 --retry-connrefused -o /dev/null -w "%{http_code}" -I "$url") || code=000
if [ "$code" -lt 200 ] || [ "$code" -ge 400 ]; then if [ "$code" -lt 200 ] || [ "$code" -ge 400 ]; then
sleep 1 sleep 1
code=$(curl -k -gsLm30 --retry 3 --retry-delay 3 --retry-connrefused -o /dev/null -w "%{http_code}" -r 0-0 -A "$user_agent" "$url") || code=000 code=$(curl -k -gsLm30 --retry 3 --retry-delay 3 --retry-connrefused -o /dev/null -w "%{http_code}" -r 0-0 -A "$user_agent" -H "Accept-Language: en-US,en" -H "Connection: keep-alive" "$url") || code=000
fi fi
if [ "$code" -lt 200 ] || [ "$code" -ge 400 ]; then if [ "$code" -lt 200 ] || [ "$code" -ge 400 ]; then
sleep 1 sleep 1
@ -62,7 +62,7 @@ while IFS=: read -r filepath url; do
sleep 1 sleep 1
done done
done < <( done < <(
pattern='(?!.*@lint-ignore)(?<!git\+)(?<!\$\{)https?://(?![^/]*@)(?![^\s<>\")]*[<>\{\}\$])[^[:space:]<>")\[\]\\|]+' pattern='(?!.*@lint-ignore)(?<!git\+)(?<!\$\{)https?://(?![^/]*@)(?![^\s<>\")]*[<>\{\}\$])[[:alnum:]][^[:space:]<>")\[\]\\|]*'
excludes=( excludes=(
':(exclude,glob)**/.*' ':(exclude,glob)**/.*'
':(exclude,glob)**/*.lock' ':(exclude,glob)**/*.lock'