From: Viktor Szakats <commit@vsz.me>
Date: Mon, 12 May 2025 17:20:40 +0000 (+0200)
Subject: spacecheck.pl: verify `tests/data/test*` for non-ASCII chars
X-Git-Tag: curl-8_14_0~97
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=9243ed59b387a90940fa4a16ebfd99ad7d6c2f63;p=thirdparty%2Fcurl.git

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 838dc53bb7bf52039b23af0e9ccffa51cf9ad7d0 #17247

Closes #17329
---

diff --git a/.github/scripts/spacecheck.pl b/.github/scripts/spacecheck.pl
index e8b64f2dc7..b47dbc6a8c 100755
--- a/.github/scripts/spacecheck.pl
+++ b/.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'";
     }
 
diff --git a/tests/FILEFORMAT.md b/tests/FILEFORMAT.md
index 436c4ce29b..263ce7f067 100644
--- a/tests/FILEFORMAT.md
+++ b/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"]>`
diff --git a/tests/data/test1138 b/tests/data/test1138
index 9afe8d7fbd..7464818496 100644
--- a/tests/data/test1138
+++ b/tests/data/test1138
@@ -4,6 +4,7 @@
 HTTP
 HTTP GET
 followlocation
+non-ascii
 </keywords>
 </info>
 #
diff --git a/tests/data/test1160 b/tests/data/test1160
index 0e946b34bf..77ea92a042 100644
--- a/tests/data/test1160
+++ b/tests/data/test1160
@@ -5,6 +5,7 @@
 HTTP
 HTTP GET
 cookies
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test1631 b/tests/data/test1631
index 16786b879a..db7d391233 100644
--- a/tests/data/test1631
+++ b/tests/data/test1631
@@ -4,6 +4,7 @@
 FTP
 HTTPS proxy
 flaky
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test1632 b/tests/data/test1632
index 1494eb40ac..c72296bd2f 100644
--- a/tests/data/test1632
+++ b/tests/data/test1632
@@ -4,6 +4,7 @@
 FTP
 HTTPS proxy
 flaky
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test31 b/tests/data/test31
index bdc0a8d1d5..0392207f65 100644
--- a/tests/data/test31
+++ b/tests/data/test31
@@ -5,6 +5,7 @@ HTTP
 HTTP GET
 cookies
 cookiejar
+non-ascii
 </keywords>
 </info>
 # Server-side
diff --git a/tests/data/test469 b/tests/data/test469
index b6f0bdbdea..ace2694933 100644
--- a/tests/data/test469
+++ b/tests/data/test469
@@ -2,6 +2,7 @@
 <info>
 <keywords>
 HTTP
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test470 b/tests/data/test470
index 7b2da01e83..f99d461b77 100644
--- a/tests/data/test470
+++ b/tests/data/test470
@@ -2,6 +2,7 @@
 <info>
 <keywords>
 HTTP
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test497 b/tests/data/test497
index 3966ab2256..300201b1fc 100644
--- a/tests/data/test497
+++ b/tests/data/test497
@@ -3,6 +3,7 @@
 <keywords>
 HTTP
 HTTP GET
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test498 b/tests/data/test498
index 6c9f8d239e..4426f7a29c 100644
--- a/tests/data/test498
+++ b/tests/data/test498
@@ -3,6 +3,7 @@
 <keywords>
 HTTP
 HTTP GET
+non-ascii
 </keywords>
 </info>
 
diff --git a/tests/data/test649 b/tests/data/test649
index 502e16ea56..25128aee67 100644
--- a/tests/data/test649
+++ b/tests/data/test649
@@ -3,6 +3,7 @@
 <keywords>
 SMTP
 MULTIPART
+non-ascii
 </keywords>
 </info>