Import of GAAS/URI-1.59 from CPAN.

gitpan-cpan-distribution: URI
gitpan-cpan-version:      1.59
gitpan-cpan-path:         GAAS/URI-1.59.tar.gz
gitpan-cpan-author:       GAAS
gitpan-cpan-maturity:     released

Changes

@@ -1,3 +1,16 @@
+2011-08-15   Gisle Aas <gisle@ActiveState.com>
+
+  Release 1.59
+
+  Make sure accessor methods don't return utf8::upgraded() bytes
+  for URLs initialized from Unicode strings.
+
+  Version number increments.
+
+  Documentation tweaks.
+
+
+
 2011-01-23   Gisle Aas <gisle@ActiveState.com>
 
   Release 1.58

META.yml

@@ -1,6 +1,6 @@
 --- #YAML:1.0
 name:               URI
-version:            1.58
+version:            1.59
 abstract:           Uniform Resource Identifiers (absolute and relative)
 author:
     - Gisle Aas <gisle@activestate.com>
@@ -22,7 +22,7 @@ no_index:
     directory:
         - t
         - inc
-generated_by:       ExtUtils::MakeMaker version 6.56
+generated_by:       ExtUtils::MakeMaker version 6.57_05
 meta-spec:
     url:      http://module-build.sourceforge.net/META-spec-v1.4.html
     version:  1.4

Makefile.PL

@@ -1,21 +1,6 @@
 require 5.008001;
 use ExtUtils::MakeMaker;
 
-if ("foo" !~ /\Afoo\z/) {
-    for $file ("URI", "URI/urn") {
-	print "\\z not supported by this perl.  Fixing $file.pm...\n";
-	rename("$file.pm", "$file.pm.bak") || die;
-	open( IN, "<$file.pm.bak" ) || die;
-	open( OUT, ">$file.pm" ) || die;
-	while( <IN> ) {
-	    $_ =~ s/\\z/\\Z/g;
-	    print OUT;
-	}
-	close( OUT ) || die;
-	close( IN ) || die;
-    }
-}
-
 WriteMakefile(
     'NAME'	   => 'URI',
     'VERSION_FROM' => 'URI.pm',

URI.pm

@@ -2,7 +2,7 @@ package URI;
 
 use strict;
 use vars qw($VERSION);
-$VERSION = "1.58";
+$VERSION = "1.59";
 
 use vars qw($ABS_REMOTE_LEADING_DOTS $ABS_ALLOW_RELATIVE_SCHEME $DEFAULT_QUERY_FORM_DELIMITER);
 
@@ -90,6 +90,7 @@ sub _uric_escape
 {
     my($class, $str) = @_;
     $str =~ s*([^$uric\#])* URI::Escape::escape_char($1) *ego;
+    utf8::downgrade($str);
     return $str;
 }
 
@@ -218,6 +219,7 @@ sub opaque
     my $new_opaque = shift;
     $new_opaque = "" unless defined $new_opaque;
     $new_opaque =~ s/([^$uric])/ URI::Escape::escape_char($1)/ego;
+    utf8::downgrade($new_opaque);
 
     $$self = defined($old_scheme) ? $old_scheme : "";
     $$self .= $new_opaque;
@@ -243,6 +245,7 @@ sub fragment
     my $new_frag = shift;
     if (defined $new_frag) {
 	$new_frag =~ s/([^$uric])/ URI::Escape::escape_char($1) /ego;
+	utf8::downgrade($new_frag);
 	$$self .= "#$new_frag";
     }
     $old;
@@ -470,7 +473,7 @@ argument, it updates the corresponding component in addition to
 returning the old value of the component.  Passing an undefined
 argument removes the component (if possible).  The description of
 each accessor method indicates whether the component is passed as
-an escaped or an unescaped string.  A component that can be further
+an escaped (percent-encoded) or an unescaped string.  A component that can be further
 divided into sub-parts are usually passed escaped, as unescaping might
 change its semantics.
 
@@ -1050,14 +1053,33 @@ delimited by ";" instead of "&" which is the default.
 
 =head1 BUGS
 
-Using regexp variables like $1 directly as arguments to the URI methods
+There are some things that are not quite right:
+
+=over
+
+=item *
+
+Using regexp variables like $1 directly as arguments to the URI accessor methods
 does not work too well with current perl implementations.  I would argue
 that this is actually a bug in perl.  The workaround is to quote
 them. Example:
 
    /(...)/ || die;
    $u->query("$1");
 
+
+=item *
+
+The escaping (percent encoding) of chars in the 128 .. 255 range passed to the
+URI constructor or when setting URI parts using the accessor methods depend on
+the state of the internal UTF8 flag (see utf8::is_utf8) of the string passed.
+If the UTF8 flag is set the UTF-8 encoded version of the character is percent
+encoded.  If the UTF8 flag isn't set the Latin-1 version (byte) of the
+character is percent encoded.  This basically exposes the internal encoding of
+Perl strings.
+
+=back
+
 =head1 PARSING URIs WITH REGEXP
 
 As an alternative to this module, the following (official) regular

URI/Escape.pm

@@ -140,7 +140,7 @@ our @ISA = qw(Exporter);
 our %escapes;
 our @EXPORT = qw(uri_escape uri_unescape uri_escape_utf8);
 our @EXPORT_OK = qw(%escapes);
-our $VERSION = "3.30";
+our $VERSION = "3.31";
 
 use Carp ();
 

URI/Heuristic.pm

@@ -93,7 +93,7 @@ use vars qw(@EXPORT_OK $VERSION $MY_COUNTRY %LOCAL_GUESSING $DEBUG);
 require Exporter;
 *import = \&Exporter::import;
 @EXPORT_OK = qw(uf_uri uf_uristr uf_url uf_urlstr);
-$VERSION = "4.19";
+$VERSION = "4.20";
 
 sub MY_COUNTRY() {
     for ($MY_COUNTRY) {

URI/URL.pm

@@ -6,7 +6,7 @@ require URI::WithBase;
 use strict;
 use vars qw(@EXPORT $VERSION);
 
-$VERSION = "5.03";
+$VERSION = "5.04";
 
 # Provide as much as possible of the old URI::URL interface for backwards
 # compatibility...

URI/WithBase.pm

@@ -4,7 +4,7 @@ use strict;
 use vars qw($AUTOLOAD $VERSION);
 use URI;
 
-$VERSION = "2.19";
+$VERSION = "2.20";
 
 use overload '""' => "as_string", fallback => 1;
 

URI/_generic.pm

@@ -23,6 +23,7 @@ sub authority
 	my $rest = $3;
 	if (defined $auth) {
 	    $auth =~ s/([^$ACHAR])/ URI::Escape::escape_char($1)/ego;
+	    utf8::downgrade($auth);
 	    $$self .= "//$auth";
 	}
 	_check_path($rest, $$self);
@@ -42,6 +43,7 @@ sub path
 	my $new_path = shift;
 	$new_path = "" unless defined $new_path;
 	$new_path =~ s/([^$PCHAR])/ URI::Escape::escape_char($1)/ego;
+	utf8::downgrade($new_path);
 	_check_path($new_path, $$self);
 	$$self .= $new_path . $rest;
     }
@@ -59,6 +61,7 @@ sub path_query
 	my $new_path = shift;
 	$new_path = "" unless defined $new_path;
 	$new_path =~ s/([^$URI::uric])/ URI::Escape::escape_char($1)/ego;
+	utf8::downgrade($new_path);
 	_check_path($new_path, $$self);
 	$$self .= $new_path . $rest;
     }

URI/_ldap.pm

@@ -7,7 +7,7 @@ package URI::_ldap;
 use strict;
 
 use vars qw($VERSION);
-$VERSION = "1.11";
+$VERSION = "1.12";
 
 use URI::Escape qw(uri_unescape);
 

URI/_punycode.pm

@@ -1,7 +1,7 @@
 package URI::_punycode;
 
 use strict;
-our $VERSION = "0.03";
+our $VERSION = "0.04";
 
 require Exporter;
 our @ISA    = qw(Exporter);

URI/_query.pm

@@ -14,6 +14,7 @@ sub query
 	$$self = $1;
 	if (defined $q) {
 	    $q =~ s/([^$URI::uric])/ URI::Escape::escape_char($1)/ego;
+	    utf8::downgrade($q);
 	    $$self .= "?$q";
 	}
 	$$self .= $3;

URI/file.pm

@@ -5,7 +5,7 @@ use vars qw(@ISA $VERSION $DEFAULT_AUTHORITY %OS_CLASS);
 
 require URI::_generic;
 @ISA = qw(URI::_generic);
-$VERSION = "4.20";
+$VERSION = "4.21";
 
 use URI::Escape qw(uri_unescape);
 
@@ -227,12 +227,12 @@ usually many URIs that map to any given file name.  For instance, an
 authority of "localhost" maps the same as a URI with a missing or empty
 authority.
 
-Example 1: The Mac uses ":" as path separator, but not in the same way
-as a generic URI. ":foo" is a relative name.  "foo:bar" is an absolute
-name.  Also, path segments can contain the "/" character as well as the
-literal "." or "..".  So the mapping looks like this:
+Example 1: The Mac classic (Mac OS 9 and earlier) used ":" as path separator,
+but not in the same way as a generic URI. ":foo" was a relative name.  "foo:bar"
+was an absolute name.  Also, path segments could contain the "/" character as well
+as the literal "." or "..".  So the mapping looks like this:
 
-  Mac                   URI
+  Mac classic           URI
   ----------            -------------------
   :foo:bar     <==>     foo/bar
   :            <==>     ./

URI/ldap.pm

@@ -7,7 +7,7 @@ package URI::ldap;
 use strict;
 
 use vars qw(@ISA $VERSION);
-$VERSION = "1.11";
+$VERSION = "1.12";
 
 require URI::_server;
 require URI::_ldap;

URI/sip.pm

@@ -15,7 +15,7 @@ use strict;
 use vars qw(@ISA $VERSION);
 use URI::Escape qw(uri_unescape);
 
-$VERSION = "0.10";
+$VERSION = "0.11";
 
 sub default_port { 5060 }
 

t/utf8.t

@@ -13,3 +13,10 @@ is(URI->new('http://foobar/mooi€e')->as_string, 'http://foobar/mooi%E2%82%ACe'
 my $uri = URI->new('http:');
 $uri->query_form("mooi€e" => "mooi€e");
 is( $uri->query, "mooi%E2%82%ACe=mooi%E2%82%ACe" );
+is( ($uri->query_form)[1], "mooi\xE2\x82\xACe" );
+
+# RT#70161
+use Encode;
+$uri = URI->new(decode_utf8 '?Query=%C3%A4%C3%B6%C3%BC');
+is( ($uri->query_form)[1], "\xC3\xA4\xC3\xB6\xC3\xBC");
+is( decode_utf8(($uri->query_form)[1]), 'äöü');