r77515 - in /branches/upstream/libhtml-format-perl/current: Build.PL Changes META.json META.yml README lib/HTML/FormatPS.pm lib/HTML/FormatRTF.pm lib/HTML/FormatText.pm lib/HTML/Formatter.pm t/rt69426.t
ansgar at users.alioth.debian.org
ansgar at users.alioth.debian.org
Sat Jul 16 10:21:02 UTC 2011
Author: ansgar
Date: Sat Jul 16 10:21:00 2011
New Revision: 77515
URL: http://svn.debian.org/wsvn/pkg-perl/?sc=1&rev=77515
Log:
[svn-upgrade] new version libhtml-format-perl (2.09)
Modified:
branches/upstream/libhtml-format-perl/current/Build.PL
branches/upstream/libhtml-format-perl/current/Changes
branches/upstream/libhtml-format-perl/current/META.json
branches/upstream/libhtml-format-perl/current/META.yml
branches/upstream/libhtml-format-perl/current/README
branches/upstream/libhtml-format-perl/current/lib/HTML/FormatPS.pm
branches/upstream/libhtml-format-perl/current/lib/HTML/FormatRTF.pm
branches/upstream/libhtml-format-perl/current/lib/HTML/FormatText.pm
branches/upstream/libhtml-format-perl/current/lib/HTML/Formatter.pm
branches/upstream/libhtml-format-perl/current/t/rt69426.t
Modified: branches/upstream/libhtml-format-perl/current/Build.PL
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/Build.PL?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/Build.PL (original)
+++ branches/upstream/libhtml-format-perl/current/Build.PL Sat Jul 16 10:21:00 2011
@@ -7,7 +7,6 @@
my %module_build_args = (
'build_requires' => {
- 'Data::Dump' => '0',
'English' => '0',
'File::Find' => '0',
'File::Slurp' => '0',
@@ -28,7 +27,7 @@
'Gisle Aas <gisle at ActiveState.com>'
],
'dist_name' => 'HTML-Format',
- 'dist_version' => '2.08',
+ 'dist_version' => '2.09',
'license' => 'perl',
'module_name' => 'HTML::Format',
'recommends' => {},
Modified: branches/upstream/libhtml-format-perl/current/Changes
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/Changes?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/Changes (original)
+++ branches/upstream/libhtml-format-perl/current/Changes Sat Jul 16 10:21:00 2011
@@ -1,3 +1,8 @@
+2.09 2011-07-15 14:20:12 Europe/London
+ - Reworking of HTML quote issue in FormatPS
+ - Now remap all double quotes to " in FormatPS (which is not
+ really right, but the best I can do with latin1 output)
+
2.08 2011-07-13 16:20:54 Europe/London
- RT#69426 - issues with HTML quotes
- UTF8 handling requires perl 5.8, so minimum requirement bumped
Modified: branches/upstream/libhtml-format-perl/current/META.json
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/META.json?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/META.json (original)
+++ branches/upstream/libhtml-format-perl/current/META.json Sat Jul 16 10:21:00 2011
@@ -53,7 +53,6 @@
},
"test" : {
"requires" : {
- "Data::Dump" : 0,
"English" : 0,
"File::Find" : 0,
"File::Slurp" : 0,
@@ -68,19 +67,19 @@
"provides" : {
"HTML::FormatPS" : {
"file" : "lib/HTML/FormatPS.pm",
- "version" : "2.08"
+ "version" : "2.09"
},
"HTML::FormatRTF" : {
"file" : "lib/HTML/FormatRTF.pm",
- "version" : "2.08"
+ "version" : "2.09"
},
"HTML::FormatText" : {
"file" : "lib/HTML/FormatText.pm",
- "version" : "2.08"
+ "version" : "2.09"
},
"HTML::Formatter" : {
"file" : "lib/HTML/Formatter.pm",
- "version" : "2.08"
+ "version" : "2.09"
}
},
"release_status" : "stable",
@@ -96,7 +95,7 @@
"web" : "http://github.com/nigelm/html-format"
}
},
- "version" : "2.08",
+ "version" : "2.09",
"x_Dist_Zilla" : {
"plugins" : [
{
Modified: branches/upstream/libhtml-format-perl/current/META.yml
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/META.yml?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/META.yml (original)
+++ branches/upstream/libhtml-format-perl/current/META.yml Sat Jul 16 10:21:00 2011
@@ -5,7 +5,6 @@
- 'Sean M Burke <sburke at cpan.org>'
- 'Gisle Aas <gisle at ActiveState.com>'
build_requires:
- Data::Dump: 0
English: 0
File::Find: 0
File::Slurp: 0
@@ -27,16 +26,16 @@
provides:
HTML::FormatPS:
file: lib/HTML/FormatPS.pm
- version: 2.08
+ version: 2.09
HTML::FormatRTF:
file: lib/HTML/FormatRTF.pm
- version: 2.08
+ version: 2.09
HTML::FormatText:
file: lib/HTML/FormatText.pm
- version: 2.08
+ version: 2.09
HTML::Formatter:
file: lib/HTML/Formatter.pm
- version: 2.08
+ version: 2.09
requires:
Carp: 0
Data::Dumper: 0
@@ -63,7 +62,7 @@
bugtracker: http://rt.cpan.org/Public/Dist/Display.html?Name=HTML-Format
homepage: http://search.cpan.org/dist/HTML-Format
repository: git://github.com/nigelm/html-format.git
-version: 2.08
+version: 2.09
x_Dist_Zilla:
plugins:
-
Modified: branches/upstream/libhtml-format-perl/current/README
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/README?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/README (original)
+++ branches/upstream/libhtml-format-perl/current/README Sat Jul 16 10:21:00 2011
@@ -2,7 +2,7 @@
HTML::Formatter - Base class for HTML formatters
VERSION
- version 2.08
+ version 2.09
SYNOPSIS
use HTML::FormatSomething;
Modified: branches/upstream/libhtml-format-perl/current/lib/HTML/FormatPS.pm
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/lib/HTML/FormatPS.pm?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/lib/HTML/FormatPS.pm (original)
+++ branches/upstream/libhtml-format-perl/current/lib/HTML/FormatPS.pm Sat Jul 16 10:21:00 2011
@@ -13,7 +13,7 @@
use base 'HTML::Formatter';
-our $VERSION = '2.08'; # VERSION
+our $VERSION = '2.09'; # VERSION
our $AUTHORITY = 'cpan:NIGELM'; # AUTHORITY
# We now use Smart::Comments in place of the old DEBUG framework.
@@ -262,11 +262,14 @@
# ------------------------------------------------------------------------
sub width {
my $self = shift;
+ my $str = shift;
my $w = 0;
my $wx = $self->{wx};
my $sz = $self->{pointsize};
- for ( unpack( "C*", $_[0] ) ) {
+
+ # need to encode to same encoding as font before getting width
+ for ( unpack( "C*", $self->encode_string($str) ) ) {
# if the character is outside the table, assume its m sized
$w += ( ( $_ > $#{$wx} ) ? $wx->[ ord('m') ] : $wx->[$_] ) * $sz # unless $_ eq 0xAD; # optional hyphen
@@ -509,19 +512,11 @@
$str =~ tr/\x01//d;
return unless length $str;
- # the string from the parser is normally unicode, and may contain
- # some punctuation characters in the 'General Punctuation' block
- # which can be expressed in latin1, but Encode module fails on them
- # so we will manually hack these...
- if ( utf8::is_utf8($str) ) {
- $str =~ tr/\x{2018}\x{2019}\x{201A}/`',/;
- }
-
# must escape parentheses and backslash
$str =~ s/([\(\)\\])/\\$1/g;
# encode output to latin1 when pushing it out
- $self->{line} .= "(" . $self->{encoder}->encode($str) . ")S\n";
+ $self->{line} .= "(" . $self->encode_string($str) . ")S\n";
$self->{showstring} = "";
}
@@ -682,6 +677,22 @@
}
# ------------------------------------------------------------------------
+sub encode_string { # converts string into latin1 charset
+ my ( $self, $str ) = @_;
+
+ # the string from the parser is normally unicode, and may contain
+ # some punctuation characters in the 'General Punctuation' block
+ # which can be expressed in latin1, but Encode module fails on them
+ # so we will manually hack these...
+ # Theres no usable latin1 for the double quote chars so map to "
+ if ( utf8::is_utf8($str) ) {
+ $str =~ tr/\x{2018}\x{2019}\x{201A}\x{201C}\x{201D}\x{201F}\x{2033}\x{2036}/`',"""""/;
+ }
+
+ return $self->{encoder}->encode($str);
+}
+
+# ------------------------------------------------------------------------
sub out { # Output a word
my ( $self, $text ) = @_;
@@ -865,7 +876,7 @@
=head1 VERSION
-version 2.08
+version 2.09
=head1 SYNOPSIS
@@ -1007,18 +1018,18 @@
L<HTML::Formatter>
+=head1 ISSUES
+
=over
=item *
Output is in ISO Latin1 format. The underlying HTML parsers tend to
-now work in Unicode (perl native) code points. There is an impedence
-match between these, which may give issues with complex characters
+now work in Unicode (perl native) code points. There is an impedance
+mismatch between these, which may give issues with complex characters
within HTML.
=back
-
-=head1 ISSUES
=head1 TO DO
Modified: branches/upstream/libhtml-format-perl/current/lib/HTML/FormatRTF.pm
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/lib/HTML/FormatRTF.pm?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/lib/HTML/FormatRTF.pm (original)
+++ branches/upstream/libhtml-format-perl/current/lib/HTML/FormatRTF.pm Sat Jul 16 10:21:00 2011
@@ -13,7 +13,7 @@
use base 'HTML::Formatter';
-our $VERSION = '2.08'; # VERSION
+our $VERSION = '2.09'; # VERSION
our $AUTHORITY = 'cpan:NIGELM'; # AUTHORITY
# ------------------------------------------------------------------------
@@ -509,7 +509,7 @@
=head1 VERSION
-version 2.08
+version 2.09
=head1 SYNOPSIS
Modified: branches/upstream/libhtml-format-perl/current/lib/HTML/FormatText.pm
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/lib/HTML/FormatText.pm?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/lib/HTML/FormatText.pm (original)
+++ branches/upstream/libhtml-format-perl/current/lib/HTML/FormatText.pm Sat Jul 16 10:21:00 2011
@@ -13,7 +13,7 @@
use base 'HTML::Formatter';
-our $VERSION = '2.08'; # VERSION
+our $VERSION = '2.09'; # VERSION
our $AUTHORITY = 'cpan:NIGELM'; # AUTHORITY
# ------------------------------------------------------------------------
@@ -221,7 +221,7 @@
=head1 VERSION
-version 2.08
+version 2.09
=head1 SYNOPSIS
Modified: branches/upstream/libhtml-format-perl/current/lib/HTML/Formatter.pm
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/lib/HTML/Formatter.pm?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/lib/HTML/Formatter.pm (original)
+++ branches/upstream/libhtml-format-perl/current/lib/HTML/Formatter.pm Sat Jul 16 10:21:00 2011
@@ -14,7 +14,7 @@
# this should be commented out in release versions....
##use Smart::Comments;
-our $VERSION = '2.08'; # VERSION
+our $VERSION = '2.09'; # VERSION
our $AUTHORITY = 'cpan:NIGELM'; # AUTHORITY
#
@@ -798,7 +798,7 @@
=head1 VERSION
-version 2.08
+version 2.09
=head1 SYNOPSIS
Modified: branches/upstream/libhtml-format-perl/current/t/rt69426.t
URL: http://svn.debian.org/wsvn/pkg-perl/branches/upstream/libhtml-format-perl/current/t/rt69426.t?rev=77515&op=diff
==============================================================================
--- branches/upstream/libhtml-format-perl/current/t/rt69426.t (original)
+++ branches/upstream/libhtml-format-perl/current/t/rt69426.t Sat Jul 16 10:21:00 2011
@@ -1,8 +1,8 @@
use strict;
use warnings;
use Test::More 0.96;
-use Data::Dump qw[dump];
-use File::Slurp;
+##use Data::Dump qw[dump]; # uncomment if needed for debugging
+##use File::Slurp; # uncomment if needed for debugging
# Bug was that a right single quote character - ’
# caused a garbage character to go into the output. This was due to
@@ -16,42 +16,56 @@
BEGIN { use_ok("HTML::FormatPS"); use_ok("HTML::TreeBuilder"); }
-my $obj = new_ok("HTML::FormatPS");
-my $htree = new_ok("HTML::TreeBuilder");
+my $table = {
+ '’' => 'apostrophe/right single quote',
+ '‘' => 'left single quote',
+ '”' => 'right double quote',
+ '“' => 'left double quote',
+ '£' => 'pound symbol',
+};
-my $html = '<html><body>it’s an apostrophe.</body></html>';
-ok( $html, 'HTML string containing an apostrophe' );
+foreach my $quoted ( sort { $a cmp $b } keys %{$table} ) {
+ my $desc = $table->{$quoted};
+ subtest "Checking $quoted -> $desc", sub {
+ my $obj = new_ok("HTML::FormatPS");
+ my $htree = new_ok("HTML::TreeBuilder");
+ my $html = '<html><body>The ' . $desc . ' is a ' . $quoted . ' character</body></html>';
+ ok( $html, "HTML string containing an $desc" );
-ok( $htree->parse_content($html), 'Parse HTML content' );
+ ok( $htree->parse_content($html), 'Parse HTML content' );
-my $result = $obj->format_string($html);
-ok( $result, 'Converted HTML object' );
+ my $result = $obj->format_string($html);
+ ok( $result, 'Converted HTML object' );
-# count high bit characters
-my $count;
-{
- use bytes;
- $count = $result =~ tr/\177-\377//;
+ # count high bit characters
+ my $count;
+ {
+ use bytes;
+ if ( $quoted eq '£' ) {
+
+ # we must exclude latin1 pound - char \243
+ $count = $result =~ tr/\177-\242\244-\377//;
+ }
+ else {
+ $count = $result =~ tr/\177-\377//;
+ }
+ }
+
+ ok( ( $count == 0 ), 'No unexpected high-bit characters found' );
+
+ ## # stuff postscript out into file - uncomment if you need for debugging
+ ## my $fn = $quoted;
+ ## $fn =~ tr/a-z//cd;
+ ## $fn .= '.ps';
+ ## write_file( $fn, { binmode => ':raw' }, $result );
+
+ ## # tell details about errors - uncomment if needed
+ ## diag( dump( { orig => $html, dump => $htree->dump, result => $result } ) ) if ($count);
+
+ done_testing();
+ };
+
}
-
-ok( ( $count == 0 ), 'No unexpected high-bit characters found' );
-
-# same test, this time using a pound symbol (which exists in latin1)
-$html = '<html><body>A £ symbol</body></html>';
-ok( $html, 'HTML string containing a British pound symbol' );
-
-ok( $htree->parse_content($html), 'Parse HTML content' );
-
-$result = $obj->format_string($html);
-ok( $result, 'Converted HTML object' );
-
-# count high bit characters - excluding latin1 pound \243
-{
- use bytes;
- $count = $result =~ tr/\177-\242\244-\377//;
-}
-
-ok( ( $count == 0 ), 'No unexpected high-bit characters found' );
# finish up
done_testing();
More information about the Pkg-perl-cvs-commits
mailing list