EBCDIC: disable also Unicode::Collate and

Unicode::Normalize for now.  Real users of
EBCDIC have to decide what they want.

p4raw-id: //depot/perl@14848

diff --git a/ext/Unicode/Normalize/Normalize.pm b/ext/Unicode/Normalize/Normalize.pm
index eed1858..db173c5 100644 (file)
--- a/ext/Unicode/Normalize/Normalize.pm
+++ b/ext/Unicode/Normalize/Normalize.pm
@@ -1,5 +1,11 @@
 package Unicode::Normalize;
 
+BEGIN {
+    if (ord("A") == 193) {
+       die "Unicode::Normalize not ported to EBCDIC\n";
+    }
+}
+
 use 5.006;
 use strict;
 use warnings;
@@ -146,6 +152,16 @@ C<NFC>, C<NFD>, C<NFKC>, C<NFKD>: by default.
 
 C<normalize> and other some functions: on request.
 
+=head2 TODO
+
+Unicode::Normalize has not been ported to EBCDIC.  The code mostly
+would work just fine but a decision needs to be made: how the module
+should work in EBCDIC?  Should the low 256 characters be understood as
+Unicode or as EBCDIC code points?  Should one be chosen or should
+there be a way to do either?  Or should such translation be left
+outside the module for the user to do, for example by using
+Encode::from_to()?
+
 =head1 AUTHOR
 
 SADAHIRO Tomoyuki, E<lt>SADAHIRO@cpan.orgE<gt>

diff --git a/ext/Unicode/Normalize/t/func.t b/ext/Unicode/Normalize/t/func.t
index fbbcb28..6f0ff08 100644 (file)
--- a/ext/Unicode/Normalize/t/func.t
+++ b/ext/Unicode/Normalize/t/func.t
@@ -1,6 +1,13 @@
 # Before `make install' is performed this script should be runnable with
 # `make test'. After `make install' it should work as `perl test.pl'
 
+BEGIN {
+    if (ord("A") == 193) {
+       print "1..0 # Unicode::Normalize not ported to EBCDIC\n";
+       exit 0;
+    }
+}
+
 #########################
 
 use Test;

diff --git a/ext/Unicode/Normalize/t/norm.t b/ext/Unicode/Normalize/t/norm.t
index 970e671..b32bf03 100644 (file)
--- a/ext/Unicode/Normalize/t/norm.t
+++ b/ext/Unicode/Normalize/t/norm.t
@@ -1,6 +1,13 @@
 # Before `make install' is performed this script should be runnable with
 # `make test'. After `make install' it should work as `perl test.pl'
 
+BEGIN {
+    if (ord("A") == 193) {
+       print "1..0 # Unicode::Normalize not ported to EBCDIC\n";
+       exit 0;
+    }
+}
+
 #########################
 
 use Test;

diff --git a/ext/Unicode/Normalize/t/test.t b/ext/Unicode/Normalize/t/test.t
index d02bcc0..198bf07 100644 (file)
--- a/ext/Unicode/Normalize/t/test.t
+++ b/ext/Unicode/Normalize/t/test.t
@@ -1,6 +1,13 @@
 # Before `make install' is performed this script should be runnable with
 # `make test'. After `make install' it should work as `perl test.pl'
 
+BEGIN {
+    if (ord("A") == 193) {
+       print "1..0 # Unicode::Normalize not ported to EBCDIC\n";
+       exit 0;
+    }
+}
+
 #########################
 
 use Test;
@@ -24,24 +31,9 @@ sub hexNFD {
   unpack 'U*', NFD pack 'U*', map hex(), split ' ', shift;
 }
 
-my $ordA   = ord("A");
-my $ASCII  = $ordA == 0x41;
-my $EBCDIC = $ordA == 0xc1;
-
-if ($ASCII) {
-  ok(hexNFC("0061 0315 0300 05AE 05C4 0062"), "00E0 05AE 05C4 0315 0062");
-  ok(hexNFC("00E0 05AE 05C4 0315 0062"),      "00E0 05AE 05C4 0315 0062");
-  ok(hexNFC("0061 05AE 0300 05C4 0315 0062"), "00E0 05AE 05C4 0315 0062");
-} elsif ($EBCDIC) {
-  # A WITH GRAVE  is 0044 in EBCDIC, not 00E0
-  # SMALL LATIN B is 0082 in EBCDIC, not 0062
-  ok(hexNFC("0061 0315 0300 05AE 05C4 0062"), "0044 05AE 05C4 0315 0082");
-  ok(hexNFC("00E0 05AE 05C4 0315 0062"),      "0044 05AE 05C4 0315 0082");
-  ok(hexNFC("0061 05AE 0300 05C4 0315 0062"), "0044 05AE 05C4 0315 0082");
-} else {
-  skip("Neither ASCII nor EBCDIC based") for 1..3;
-}
-
+ok(hexNFC("0061 0315 0300 05AE 05C4 0062"), "00E0 05AE 05C4 0315 0062");
+ok(hexNFC("00E0 05AE 05C4 0315 0062"),      "00E0 05AE 05C4 0315 0062");
+ok(hexNFC("0061 05AE 0300 05C4 0315 0062"), "00E0 05AE 05C4 0315 0062");
 ok(hexNFC("0045 0304 0300 AC00 11A8"), "1E14 AC01");
 ok(hexNFC("1100 1161 1100 1173 11AF"), "AC00 AE00");
 ok(hexNFC("1100 0300 1161 1173 11AF"), "1100 0300 1161 1173 11AF");
@@ -49,39 +41,13 @@ ok(hexNFC("1100 0300 1161 1173 11AF"), "1100 0300 1161 1173 11AF");
 ok(hexNFD("0061 0315 0300 05AE 05C4 0062"), "0061 05AE 0300 05C4 0315 0062");
 ok(hexNFD("00E0 05AE 05C4 0315 0062"),      "0061 05AE 0300 05C4 0315 0062");
 ok(hexNFD("0061 05AE 0300 05C4 0315 0062"), "0061 05AE 0300 05C4 0315 0062");
-
-if ($ASCII) {
-  ok(hexNFC("0061 05C4 0315 0300 05AE 0062"), "0061 05AE 05C4 0300 0315 0062");
-  ok(hexNFC("0061 05AE 05C4 0300 0315 0062"), "0061 05AE 05C4 0300 0315 0062");
-} elsif ($EBCDIC) {
-  # SMALL LATIN A is 0081 in EBCDIC, not 0061
-  # SMALL LATIN B is 0082 in EBCDIC, not 0062
-  ok(hexNFC("0061 05C4 0315 0300 05AE 0062"), "0081 05AE 05C4 0300 0315 0082");
-  ok(hexNFC("0061 05AE 05C4 0300 0315 0062"), "0081 05AE 05C4 0300 0315 0082");
-} else {
-  skip("Neither ASCII nor EBCDIC based") for 1..2;
-}
-
+ok(hexNFC("0061 05C4 0315 0300 05AE 0062"), "0061 05AE 05C4 0300 0315 0062");
+ok(hexNFC("0061 05AE 05C4 0300 0315 0062"), "0061 05AE 05C4 0300 0315 0062");
 ok(hexNFD("0061 05C4 0315 0300 05AE 0062"), "0061 05AE 05C4 0300 0315 0062");
 ok(hexNFD("0061 05AE 05C4 0300 0315 0062"), "0061 05AE 05C4 0300 0315 0062");
-
-if ($ASCII) {
-  ok(hexNFC("0000 0041 0000 0000"), "0000 0041 0000 0000");
-} elsif ($EBCDIC) {
-  # CAPITAL LATIN A is 00C1 in EBCDIC, not 0041
-  ok(hexNFC("0000 0041 0000 0000"), "0000 00C1 0000 0000");
-} else {
-  skip("Neither ASCII nor EBCDIC based");
-}
-
+ok(hexNFC("0000 0041 0000 0000"), "0000 0041 0000 0000");
 ok(hexNFD("0000 0041 0000 0000"), "0000 0041 0000 0000");
 
 # should be unary.
-if ($ASCII) {
-  ok(NFC "\x{41}\x{0302}\x{0301}\x62" eq "\x{1EA4}\x62");
-} elsif ($EBCDIC) {
-  ok(NFC "\x{41}\x{0302}\x{0301}\x62" eq "\x{1EA4}\x82");
-} else {
-  skip("Neither ASCII nor EBCDIC based");
-}
+ok(NFC "\x{41}\x{0302}\x{0301}\x62" eq "\x{1EA4}\x62");
 ok(NFD "\x{E0}\x{AC00}" eq "\x{61}\x{0300}\x{1100}\x{1161}");

diff --git a/lib/Unicode/Collate.pm b/lib/Unicode/Collate.pm
index bd10fdd..8522a79 100644 (file)
--- a/lib/Unicode/Collate.pm
+++ b/lib/Unicode/Collate.pm
@@ -1,5 +1,11 @@
 package Unicode::Collate;
 
+BEGIN {
+    if (ord("A") == 193) {
+       die "Unicode::Collate not ported to EBCDIC\n";
+    }
+}
+
 use 5.006;
 use strict;
 use warnings;
@@ -776,6 +782,16 @@ is primary equal to C<"m>E<252>C<ss">.
 
 None by default.
 
+=head2 TODO
+
+Unicode::Collate has not been ported to EBCDIC.  The code mostly would
+work just fine but a decision needs to be made: how the module should
+work in EBCDIC?  Should the low 256 characters be understood as
+Unicode or as EBCDIC code points?  Should one be chosen or should
+there be a way to do either?  Or should such translation be left
+outside the module for the user to do, for example by using
+Encode::from_to()?
+
 =head2 CAVEAT
 
 Use of the C<normalization> parameter requires

diff --git a/lib/Unicode/Collate/t/test.t b/lib/Unicode/Collate/t/test.t
index d9ee1fe..57e2057 100644 (file)
--- a/lib/Unicode/Collate/t/test.t
+++ b/lib/Unicode/Collate/t/test.t
@@ -3,6 +3,13 @@
 
 #########################
 
+BEGIN {
+    if (ord("A") == 193) {
+       print "1..0 # Unicode::Collate not ported to EBCDIC\n";
+       exit 0;
+    }
+}
+
 use Test;
 BEGIN { plan tests => 54 };
 use Unicode::Collate;