Treat url strings are unsplittable

Fixes #22498

etc/cert_generator.sh

@@ -18,9 +18,7 @@ set -o pipefail
 #    (some are Email-only), column 30 is printed, the raw certificate.
 # 6. All CA certs trusted for Websites are stored into the `certs` file.
 
-domain="ccadb-public.secure.force.com";
-curl "https://${domain}/mozilla/IncludedCACertificateReportPEMCSV" -sSf | \
-gawk -v RS="\"\n" -F'","|^"' \
+url="https://ccadb-public.secure.force.com/mozilla/IncludedCACertificateReportPEMCSV"
+curl "${url}" -sSf | gawk -v RS="\"\n" -F'","|^"' \
 '{gsub("\047","",$(30));gsub("\"","",$(30));if($(13)~/Websites/)print $(30)}' \
 > certs
-

python/tidy/servo_tidy/tidy.py

@@ -32,6 +32,8 @@ def wpt_path(*args):
 
 CONFIG_FILE_PATH = os.path.join(".", "servo-tidy.toml")
 WPT_MANIFEST_PATH = wpt_path("include.ini")
+# regex source https://stackoverflow.com/questions/6883049/
+URL_REGEX = re.compile('https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+')
 
 # Import wptmanifest only when we do have wpt in tree, i.e. we're not
 # inside a Firefox checkout.
@@ -261,8 +263,13 @@ def check_length(file_name, idx, line):
         yield (idx + 1, "Line is longer than %d characters" % max_length)
 
 
+def contains_url(line):
+    return bool(URL_REGEX.search(line))
+
+
 def is_unsplittable(file_name, line):
     return (
+        contains_url(line) or
         file_name.endswith(".rs") and
         line.startswith("use ") and
         "{" not in line

python/tidy/servo_tidy_tests/long_line.rs

@@ -3,3 +3,4 @@
  * file, You can obtain one at https://mozilla.org/MPL/2.0/. */
 
 println!("really really loooooooooooooooooooooooooooooooooooooooooooong  lineeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee");
+let url = "http://www.should.skip/really-looooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooong-url-strings";