r5581 - in /packages/libmarc-charset-perl/branches/upstream/current: Changes META.yml lib/MARC/Charset.pm lib/MARC/Charset/Code.pm lib/MARC/Charset/Compiler.pm t/marc8_to_utf8.t t/space.t
dmn at users.alioth.debian.org
dmn at users.alioth.debian.org
Thu Jun 7 22:30:51 UTC 2007
Author: dmn
Date: Thu Jun 7 22:30:51 2007
New Revision: 5581
URL: http://svn.debian.org/wsvn/pkg-perl/?sc=1&rev=5581
Log:
[svn-upgrade] Integrating new upstream version, libmarc-charset-perl (0.97)
Removed:
packages/libmarc-charset-perl/branches/upstream/current/t/marc8_to_utf8.t
Modified:
packages/libmarc-charset-perl/branches/upstream/current/Changes
packages/libmarc-charset-perl/branches/upstream/current/META.yml
packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset.pm
packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Code.pm
packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Compiler.pm
packages/libmarc-charset-perl/branches/upstream/current/t/space.t
Modified: packages/libmarc-charset-perl/branches/upstream/current/Changes
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/Changes?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/Changes (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/Changes Thu Jun 7 22:30:51 2007
@@ -1,4 +1,14 @@
Revision history for MARC::Charset
+
+0.97 Sun May 20 13:48:31 EDT 2007
+ - added t/null.t
+ - fixed Charset::Compiler to use the <alt> element when <ucs> is not
+ defined. Previous versions of MARC::Charset would convert valid MARC8
+ to null when it encountered a mapping that lacked a UCS value
+ many thanks to Michael O'Connor.
+ - allow carriage return and line feeds to pass unmolesteed, much the
+ same as spaces today. Apparently, UNIMARC records embed these
+ formatting characters on a regular basis.
0.96 Wed Mar 14 01:24:48 EDT 2007
- added ignore_errors() to skip MARC8 -> UTF8 snafus
Modified: packages/libmarc-charset-perl/branches/upstream/current/META.yml
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/META.yml?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/META.yml (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/META.yml Thu Jun 7 22:30:51 2007
@@ -1,7 +1,7 @@
# http://module-build.sourceforge.net/META-spec.html
#XXXXXXX This is a prototype!!! It will change in the future!!! XXXXX#
name: MARC-Charset
-version: 0.96
+version: 0.97
version_from: lib/MARC/Charset.pm
installdirs: site
requires:
@@ -11,4 +11,4 @@
XML::SAX: 0
distribution_type: module
-generated_by: ExtUtils::MakeMaker version 6.17
+generated_by: ExtUtils::MakeMaker version 6.30
Modified: packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset.pm
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset.pm?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset.pm (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset.pm Thu Jun 7 22:30:51 2007
@@ -1,6 +1,6 @@
package MARC::Charset;
-our $VERSION = '0.96';
+our $VERSION = '0.97';
use strict;
use warnings;
@@ -9,6 +9,7 @@
use Unicode::Normalize;
use Encode 'decode';
+use charnames ':full';
use MARC::Charset::Table;
use MARC::Charset::Constants qw(:all);
@@ -153,10 +154,10 @@
my $combining = '';
CHAR_LOOP: while ($index < $length)
{
- # spaces just get added on unmolested
- if (substr($marc8, $index, 1) eq ' ')
- {
- $utf8 .= ' ';
+ # whitespace, line feeds and carriage returns just get added on unmolested
+ if (substr($marc8, $index, 1) =~ m/(\s+|\x0A+|\x0D+)/so)
+ {
+ $utf8 .= $1;
$index += 1;
next CHAR_LOOP;
}
Modified: packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Code.pm
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Code.pm?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Code.pm (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Code.pm Thu Jun 7 22:30:51 2007
@@ -8,7 +8,7 @@
use MARC::Charset::Constants qw(:all);
MARC::Charset::Code
- ->mk_accessors(qw(marc ucs name charset is_combining));
+ ->mk_accessors(qw(marc ucs name charset is_combining alt));
=head1 NAME
Modified: packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Compiler.pm
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Compiler.pm?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Compiler.pm (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/lib/MARC/Charset/Compiler.pm Thu Jun 7 22:30:51 2007
@@ -94,6 +94,12 @@
# if we're ending a code element
if ($code and $name eq 'code')
{
+ # if there is no ucs code, use what's in alt
+ $code->ucs($code->alt()) unless $code->ucs;
+
+ # can't process a code point that lacks a unicode representation
+ die("invalid code: " . $code->to_string()) unless $code->ucs;
+
# set the charset code
$code->charset($self->{current_charset});
@@ -109,7 +115,7 @@
}
# add these elements
- elsif ($code and $name =~ /marc|ucs|is_combining/)
+ elsif ($code and $name =~ /^(marc|ucs|is_combining|alt)$/)
{
$code->$name($self->text());
}
Modified: packages/libmarc-charset-perl/branches/upstream/current/t/space.t
URL: http://svn.debian.org/wsvn/pkg-perl/packages/libmarc-charset-perl/branches/upstream/current/t/space.t?rev=5581&op=diff
==============================================================================
--- packages/libmarc-charset-perl/branches/upstream/current/t/space.t (original)
+++ packages/libmarc-charset-perl/branches/upstream/current/t/space.t Thu Jun 7 22:30:51 2007
@@ -1,4 +1,4 @@
-use Test::More tests => 3;
+use Test::More tests => 4;
use strict;
use warnings;
@@ -7,6 +7,7 @@
is('foo bar', marc8_to_utf8('foo bar'), 'one space');
is('foo bar', marc8_to_utf8('foo bar'), 'two spaces');
+is("a\r \x{0A}b \x{0D}c\n", marc8_to_utf8("a\r \x{0A}b \x{0D}c\n"), 'spaces with newlines and carriage returns');
my $test =
'a ' .
@@ -18,4 +19,3 @@
my $expected = 'a ' . chr(0x0396) . ' b';
is(marc8_to_utf8($test), $expected, 'spacing with escape');
-
More information about the Pkg-perl-cvs-commits
mailing list