spacecheck.pl: verify tests/data/test* for non-ASCII chars

Exclude test data files (4 of them) based on existing feature tags:
`codeset-utf8` and `Unicode`.

Add the new keyword `non-ascii` to mark remaining exceptions (9 files).

Follow-up to 838dc53bb7 #17247

Closes #17329

.github/scripts/spacecheck.pl

@@ -69,7 +69,6 @@ my @non_ascii = (
     "docs/THANKS",
     "docs/THANKS-filter",
     "tests/libtest/lib1560.c",
-    "^tests/data/test",
 );
 
 sub fn_match {
@@ -162,7 +161,7 @@ while(my $filename = <$git_ls_files>) {
     $content =~ s/[$non_ascii_allowed]//g;
 
     if(!fn_match($filename, @non_ascii) &&
-       $content =~ /([\x80-\xff]+)/) {
+       ($content =~ /([\x80-\xff]+)/ && $content !~ /^(codeset-utf8|Unicode|non-ascii)/m)) {
         push @err, "content: has non-ASCII: '$1'";
     }
 

tests/FILEFORMAT.md

@@ -226,6 +226,10 @@ Tests that have strict timing dependencies have the `timing-dependent` keyword.
 These are intended to eventually be treated specially on CI builds which are
 often run on overloaded machines with unpredictable timing.
 
+Tests using non-7-bit-ASCII characters, and not using features `Unicode` or
+`codeset-utf8`, need to add the `non-ascii` keyword to tell the code checker
+to allow these characters.
+
 ## `<reply>`
 
 ### `<data [nocheck="yes"] [sendzero="yes"] [hex="yes"] [nonewline="yes"] [crlf="yes"]>`

tests/data/test1138

@@ -4,6 +4,7 @@
 HTTP
 HTTP GET
 followlocation
+non-ascii
 </keywords>
 </info>
 #

tests/data/test1160

@@ -5,6 +5,7 @@
 HTTP
 HTTP GET
 cookies
+non-ascii
 </keywords>
 </info>
 

tests/data/test1631

@@ -4,6 +4,7 @@
 FTP
 HTTPS proxy
 flaky
+non-ascii
 </keywords>
 </info>
 

tests/data/test1632

@@ -4,6 +4,7 @@
 FTP
 HTTPS proxy
 flaky
+non-ascii
 </keywords>
 </info>
 

tests/data/test31

@@ -5,6 +5,7 @@ HTTP
 HTTP GET
 cookies
 cookiejar
+non-ascii
 </keywords>
 </info>
 # Server-side

tests/data/test469

@@ -2,6 +2,7 @@
 <info>
 <keywords>
 HTTP
+non-ascii
 </keywords>
 </info>
 

tests/data/test470

@@ -2,6 +2,7 @@
 <info>
 <keywords>
 HTTP
+non-ascii
 </keywords>
 </info>
 

tests/data/test497

@@ -3,6 +3,7 @@
 <keywords>
 HTTP
 HTTP GET
+non-ascii
 </keywords>
 </info>
 

tests/data/test498

@@ -3,6 +3,7 @@
 <keywords>
 HTTP
 HTTP GET
+non-ascii
 </keywords>
 </info>
 

tests/data/test649

@@ -3,6 +3,7 @@
 <keywords>
 SMTP
 MULTIPART
+non-ascii
 </keywords>
 </info>