X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Futf8.t;h=a5827f48c0084fd536a951fa2f75e68349deab07;hb=aa10195b3aa19bb4f167204cdce8fb75d361ccb8;hp=85dfb2cb2ef2cc64d5497fa3a11552f0106c0b3c;hpb=a6d0563455796929d2aae5a18fb57e80a20f87bd;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/lib/utf8.t b/lib/utf8.t
index 85dfb2c..a5827f4 100644
--- a/lib/utf8.t
+++ b/lib/utf8.t
@@ -37,7 +37,7 @@ no utf8; # Ironic, no?
 #
 #
 
-plan tests => 99;
+plan tests => 150;
 
 {
     # bug id 20001009.001
@@ -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;
@@ -323,8 +326,128 @@ 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");
+    if (ord('A') == 193) { # EBCDIC.
+	is(utf8::upgrade($b), 1, "utf8::upgrade beyond");
+    } else {
+	is(utf8::upgrade($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");
+    if (ord('A') == 193) { # EBCDIC.
+	is(length($b), 1, "beyond length");
+    } else {
+	is(length($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($a), "!utf8::is_utf8 basic");
+    if (ord('A') == 193) { # EBCDIC.
+	ok( utf8::is_utf8(pack('U',0x0ff)), " utf8::is_utf8 beyond");
+    } else {
+	ok( utf8::is_utf8($b), " utf8::is_utf8 beyond"); # $b stays in UTF-8.
+    }
+    ok( utf8::is_utf8($c), " utf8::is_utf8 unicode");
+}
+
+{
+    eval {utf8::encode("£")};
+    like($@, qr/^Modification of a read-only value attempted/,
+	 "utf8::encode should refuse to touch read-only values");
+}
+
+{
+    my $a = "456\xb6";
+    utf8::upgrade($a);
+
+    my $b = "123456\xb6";
+    $b =~ s/^...//;
+    utf8::upgrade($b);
+    is($b, $a, "utf8::upgrade OffsetOK");
+}
+
+{
+    fresh_perl_like ('use utf8; utf8::moo()',
+		     qr/Undefined subroutine utf8::moo/, {stderr=>1},
+		    "Check Carp is loaded for AUTOLOADing errors")
+}
+
+{
+    # failure of is_utf8_char() without NATIVE_TO_UTF on EBCDIC (0260..027F)
+    ok(utf8::valid(chr(0x250)), "0x250");
+    ok(utf8::valid(chr(0x260)), "0x260");
+    ok(utf8::valid(chr(0x270)), "0x270");
+    ok(utf8::valid(chr(0x280)), "0x280");
+}