From 17fee1cbd39f34fa3742b22ce29788e76214e56d Mon Sep 17 00:00:00 2001
From: Anthony Shoumikhin <shoumikhin@meta.com>
Date: Thu, 17 Apr 2025 16:54:52 -0700
Subject: [PATCH 1/2] Script to validate URLs

---
 scripts/check_urls.sh | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100755 scripts/check_urls.sh

diff --git a/scripts/check_urls.sh b/scripts/check_urls.sh
new file mode 100755
index 00000000000..5dc60542f69
--- /dev/null
+++ b/scripts/check_urls.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+set -euo pipefail
+
+green='\e[1;32m'; red='\e[1;31m'; cyan='\e[1;36m'; yellow='\e[1;33m'; reset='\e[0m'
+last= rc=0
+while IFS=: read -r f u; do
+  if [ "$f" != "$last" ]; then
+    [ -n "$last" ] && echo
+    printf '%s:\n' "$f"
+    last=$f
+  fi
+  if curl --fail -s -m10 -o /dev/null "$u"; then
+    printf " ${green}[OK]${reset}  ${cyan}%s${reset}\n" "$u"
+  else
+    printf "${red}[FAIL]${reset} ${yellow}%s${reset}\n" "$u"
+    rc=1
+  fi
+done < <(
+  git --no-pager grep --no-color -I -o -E 'https?://[^[:space:]<>\")\{]+' \
+    -- '*' \
+    ':(exclude).*' ':(exclude)**/.*' ':(exclude)**/*.lock' ':(exclude)**/third-party/**' \
+  | sed 's/[."\’]$//'
+)
+exit $rc

From 497253288febe591e29521acac94295dc50dad39 Mon Sep 17 00:00:00 2001
From: Anthony Shoumikhin <shoumikhin@meta.com>
Date: Thu, 17 Apr 2025 23:46:25 -0700
Subject: [PATCH 2/2] Script to validate URLs

---
 scripts/check_urls.sh | 42 ++++++++++++++++++++++++++++--------------
 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/scripts/check_urls.sh b/scripts/check_urls.sh
index 5dc60542f69..8a8ca2a5815 100755
--- a/scripts/check_urls.sh
+++ b/scripts/check_urls.sh
@@ -7,24 +7,38 @@
 
 set -euo pipefail
 
+status=0
 green='\e[1;32m'; red='\e[1;31m'; cyan='\e[1;36m'; yellow='\e[1;33m'; reset='\e[0m'
-last= rc=0
-while IFS=: read -r f u; do
-  if [ "$f" != "$last" ]; then
-    [ -n "$last" ] && echo
-    printf '%s:\n' "$f"
-    last=$f
+last_filepath=
+
+while IFS=: read -r filepath url; do
+  if [ "$filepath" != "$last_filepath" ]; then
+    printf '\n%s:\n' "$filepath"
+    last_filepath=$filepath
+  fi
+  code=$(curl -gsLm30 -o /dev/null -w "%{http_code}" -I "$url") || code=000
+  if [ "$code" -ge 400 ]; then
+    code=$(curl -gsLm30 -o /dev/null -w "%{http_code}" -r 0-0 -A "Mozilla/5.0" "$url") || code=000
   fi
-  if curl --fail -s -m10 -o /dev/null "$u"; then
-    printf " ${green}[OK]${reset}  ${cyan}%s${reset}\n" "$u"
+  if [ "$code" -ge 200 ] && [ "$code" -lt 400 ]; then
+    printf "${green}%s${reset} ${cyan}%s${reset}\n" "$code" "$url"
   else
-    printf "${red}[FAIL]${reset} ${yellow}%s${reset}\n" "$u"
-    rc=1
+    printf "${red}%s${reset} ${yellow}%s${reset}\n" "$code" "$url" >&2
+    status=1
   fi
 done < <(
-  git --no-pager grep --no-color -I -o -E 'https?://[^[:space:]<>\")\{]+' \
+  git --no-pager grep --no-color -I -o -E \
+    'https?://[^[:space:]<>\")\{\(\$]+' \
     -- '*' \
-    ':(exclude).*' ':(exclude)**/.*' ':(exclude)**/*.lock' ':(exclude)**/third-party/**' \
-  | sed 's/[."\’]$//'
+    ':(exclude).*' \
+    ':(exclude)**/.*' \
+    ':(exclude)**/*.lock' \
+    ':(exclude)**/*.svg' \
+    ':(exclude)**/*.xml' \
+    ':(exclude)**/third-party/**' \
+  | sed 's/[[:punct:]]*$//' \
+  | grep -Ev '://(0\.0\.0\.0|127\.0\.0\.1|localhost)([:/])' \
+  || true
 )
-exit $rc
+
+exit $status