spacecheck.pl: check for non-ASCII chars, fix fallouts

Reported-by: James Fuller
Assisted-by: Dan Fandrich

Closes #17247

.github/scripts/spacecheck.pl

@@ -47,6 +47,31 @@ my @space_at_eol = (
     "^tests/data/test",
 );
 
+my @non_ascii_allowed = (
+    '\xC3\xA1',          # UTF-8 for https://codepoints.net/U+00E1 LATIN SMALL LETTER A WITH ACUTE
+    '\xC3\xA5',          # UTF-8 for https://codepoints.net/U+00E5 LATIN SMALL LETTER A WITH RING ABOVE
+    '\xC3\xA4',          # UTF-8 for https://codepoints.net/U+00E4 LATIN SMALL LETTER A WITH DIAERESIS
+    '\xC3\xB6',          # UTF-8 for https://codepoints.net/U+00F6 LATIN SMALL LETTER O WITH DIAERESIS
+    '\xC2\xB1',          # UTF-8 for https://codepoints.net/U+00B1 PLUS-MINUS SIGN
+    '\xC2\xA7',          # UTF-8 for https://codepoints.net/U+00A7 SECTION SIGN
+    '\xC3\x9F',          # UTF-8 for https://codepoints.net/U+00DF LATIN SMALL LETTER SHARP S
+    '\xF0\x9F\x99\x8F',  # UTF-8 for https://codepoints.net/U+1f64f PERSON WITH FOLDED HANDS
+);
+
+my $non_ascii_allowed = join(', ', @non_ascii_allowed);
+
+my @non_ascii = (
+    ".github/scripts/spellcheck.words",
+    ".mailmap",
+    "RELEASE-NOTES",
+    "docs/BINDINGS.md",
+    "docs/CIPHERS.md",
+    "docs/THANKS",
+    "docs/THANKS-filter",
+    "tests/libtest/lib1560.c",
+    "^tests/data/test",
+);
+
 sub fn_match {
     my ($filename, @masklist) = @_;
 
@@ -134,6 +159,13 @@ while(my $filename = <$git_ls_files>) {
         push @err, "content: has binary contents";
     }
 
+    $content =~ s/[$non_ascii_allowed]//g;
+
+    if(!fn_match($filename, @non_ascii) &&
+       $content =~ /([\x80-\xff]+)/) {
+        push @err, "content: has non-ASCII: '$1'";
+    }
+
     if(@err) {
         $issues++;
         foreach my $err (@err) {

CMakeLists.txt

@@ -2030,9 +2030,9 @@ function(curl_transform_makefile_inc _input_file _output_file)
   string(REPLACE "$(top_srcdir)"   "\${PROJECT_SOURCE_DIR}" _makefile_inc_text ${_makefile_inc_text})
   string(REPLACE "$(top_builddir)" "\${PROJECT_BINARY_DIR}" _makefile_inc_text ${_makefile_inc_text})
 
-  string(REGEX REPLACE "\\\\\n" "!π!α!" _makefile_inc_text ${_makefile_inc_text})
+  string(REGEX REPLACE "\\\\\n" "!^!^!" _makefile_inc_text ${_makefile_inc_text})
   string(REGEX REPLACE "([a-zA-Z_][a-zA-Z0-9_]*)[\t ]*=[\t ]*([^\n]*)" "set(\\1 \\2)" _makefile_inc_text ${_makefile_inc_text})
-  string(REPLACE "!π!α!" "\n" _makefile_inc_text ${_makefile_inc_text})
+  string(REPLACE "!^!^!" "\n" _makefile_inc_text ${_makefile_inc_text})
 
   # Replace $() with ${}
   string(REGEX REPLACE "\\$\\(([a-zA-Z_][a-zA-Z0-9_]*)\\)" "\${\\1}" _makefile_inc_text ${_makefile_inc_text})

lib/asyn-ares.c

@@ -810,7 +810,7 @@ struct Curl_addrinfo *Curl_async_getaddrinfo(struct Curl_easy *data,
 }
 
 /* Set what DNS server are is to use. This is called in 2 situations:
- * 1. when the application does `CURLOPT_DNS_SERVERS´ and passing NULL
+ * 1. when the application does 'CURLOPT_DNS_SERVERS' and passing NULL
  *    means any previous set value should be unset. Which means
  *    we need to destroy and create the are channel anew, if there is one.
  * 2. When we lazy init the ares channel and NULL means that there

tests/server/util.c

@@ -302,11 +302,11 @@ curl_off_t our_getpid(void)
   pid = (curl_off_t)curlx_getpid();
 #ifdef _WIN32
   /* store pid + MAX_PID to avoid conflict with Cygwin/msys PIDs, see also:
-   * - 2019-01-31: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit; ↵
+   * - 2019-01-31: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit;
    *               h=b5e1003722cb14235c4f166be72c09acdffc62ea
-   * - 2019-02-02: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit; ↵
+   * - 2019-02-02: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit;
    *               h=448cf5aa4b429d5a9cebf92a0da4ab4b5b6d23fe
-   * - 2024-12-19: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit; ↵
+   * - 2024-12-19: https://cygwin.com/git/?p=newlib-cygwin.git;a=commit;
    *               h=363357c023ce01e936bdaedf0f479292a8fa4e0f
    */
   pid += 4194304;