Sync with the latest MakeMaker snapshot.

[perl5.git] / lib / utf8.t

diff --git a/lib/utf8.t b/lib/utf8.t
index 8072c87..33cd596 100644 (file)
--- a/lib/utf8.t
+++ b/lib/utf8.t
@@ -37,7 +37,7 @@ no utf8; # Ironic, no?
 #
 #
 
-plan tests => 98;
+plan tests => 143;
 
 {
     # bug id 20001009.001
@@ -189,7 +189,7 @@ BANG
     print
         "# Again! Again! [but this time as eval, and not the explosive one]\n";
     # and now we've safely done them all as separate files, check that the
-    # evals do the same thing. Hopefully doing it later sucessfully decouples
+    # evals do the same thing. Hopefully doing it later successfully decouples
     # the previous tests from anything messy that may go wrong with the evals.
     foreach (@tests) {
         my ($why, $prog, $expect) = @$_;
@@ -272,14 +272,17 @@ BANG
 # before the patch, the eval died with an error like:
 #   "my" variable $strict::VERSION can't be in a package
 #
-ok('' eq runperl(prog => <<'CODE'), "change #17928");
-    my $code = qq{ my \$\xe3\x83\x95\xe3\x83\xbc = 5; };
+SKIP: {
+    skip("Embedded UTF-8 does not work in EBCDIC", 1) if ord("A") == 193;
+    ok('' eq runperl(prog => <<'CODE'), "change #17928");
+       my $code = qq{ my \$\xe3\x83\x95\xe3\x83\xbc = 5; };
     {
        use utf8;
        eval $code;
        print $@ if $@;
     }
 CODE
+}
 
 {
     use utf8;
@@ -323,3 +326,86 @@ END
     is("@i", "60 62 58 50 52 48 70 72 68", "utf8 heredoc index and rindex");
 }
 
+SKIP: {
+    skip("Embedded UTF-8 does not work in EBCDIC", 1) if ord("A") == 193;
+    use utf8;
+    eval qq{is(q \xc3\xbc test \xc3\xbc, qq\xc2\xb7 test \xc2\xb7,
+              "utf8 quote delimiters [perl #16823]");};
+}
+
+# Test the "internals".
+
+{
+    my $a = "A";
+    my $b = chr(0x0FF);
+    my $c = chr(0x100);
+
+    ok( utf8::valid($a), "utf8::valid basic");
+    ok( utf8::valid($b), "utf8::valid beyond");
+    ok( utf8::valid($c), "utf8::valid unicode");
+
+    ok(!utf8::is_utf8($a), "!utf8::is_utf8 basic");
+    ok(!utf8::is_utf8($b), "!utf8::is_utf8 beyond");
+    ok( utf8::is_utf8($c), "utf8::is_utf8 unicode");
+
+    is(utf8::upgrade($a), 1, "utf8::upgrade basic");
+    is(utf8::upgrade($b), 2, "utf8::upgrade beyond");
+    is(utf8::upgrade($c), 2, "utf8::upgrade unicode");
+
+    is($a, "A",       "basic");
+    is($b, "\xFF",    "beyond");
+    is($c, "\x{100}", "unicode");
+
+    ok( utf8::valid($a), "utf8::valid basic");
+    ok( utf8::valid($b), "utf8::valid beyond");
+    ok( utf8::valid($c), "utf8::valid unicode");
+
+    ok( utf8::is_utf8($a), "utf8::is_utf8 basic");
+    ok( utf8::is_utf8($b), "utf8::is_utf8 beyond");
+    ok( utf8::is_utf8($c), "utf8::is_utf8 unicode");
+
+    is(utf8::downgrade($a), 1, "utf8::downgrade basic");
+    is(utf8::downgrade($b), 1, "utf8::downgrade beyond");
+
+    is($a, "A",       "basic");
+    is($b, "\xFF",    "beyond");
+
+    ok( utf8::valid($a), "utf8::valid basic");
+    ok( utf8::valid($b), "utf8::valid beyond");
+
+    ok(!utf8::is_utf8($a), "!utf8::is_utf8 basic");
+    ok(!utf8::is_utf8($b), "!utf8::is_utf8 beyond");
+
+    utf8::encode($a);
+    utf8::encode($b);
+    utf8::encode($c);
+
+    is($a, "A",       "basic");
+    is(length($b), 2, "beyond length");
+    is(length($c), 2, "unicode length");
+
+    ok(utf8::valid($a), "utf8::valid basic");
+    ok(utf8::valid($b), "utf8::valid beyond");
+    ok(utf8::valid($c), "utf8::valid unicode");
+
+    # encode() clears the UTF-8 flag (unlike upgrade()).
+    ok(!utf8::is_utf8($a), "!utf8::is_utf8 basic");
+    ok(!utf8::is_utf8($b), "!utf8::is_utf8 beyond");
+    ok(!utf8::is_utf8($c), "!utf8::is_utf8 unicode");
+
+    utf8::decode($a);
+    utf8::decode($b);
+    utf8::decode($c);
+
+    is($a, "A",       "basic");
+    is($b, "\xFF",    "beyond");
+    is($c, "\x{100}", "unicode");
+
+    ok(utf8::valid($a), "!utf8::valid basic");
+    ok(utf8::valid($b), "!utf8::valid beyond");
+    ok(utf8::valid($c), " utf8::valid unicode");
+
+    ok(!utf8::is_utf8($a), "!utf8::is_utf8 basic");
+    ok( utf8::is_utf8($b), " utf8::is_utf8 beyond"); # $b stays in UTF-8.
+    ok( utf8::is_utf8($c), " utf8::is_utf8 unicode");
+}