MSWord-ToHTML

 view release on metacpan or  search on metacpan

lib/MSWord/ToHTML/Roles/HasHTML.pm  view on Meta::CPAN

use feature 'say';

has 'style' => (
    is      => 'ro',
    lazy    => 1,
    default => sub {
        my $self = shift;
        $self->parser->load_xml(
            location =>
                'http://docbook.sourceforge.net/release/xsl/current/xhtml-1_1/docbook.xsl',
            no_cdata => 1
        );
    },
);

has 'parser' => (
    is      => 'ro',
    isa     => 'XML::LibXML',
    lazy    => 1,
    default => sub {
        XML::LibXML->new;

lib/MSWord/ToHTML/Roles/HasHTML.pm  view on Meta::CPAN

    return $tree;
}

method html_to_html5( IO::All $base_html) {
    try {
        system(
            "/usr/bin/tidy",                 "-f",
            "$base_html.err",                "-m",
            "-clean",                        "-quiet",
            "--preserve-entities",           "yes",
            "--indent-cdata",                "yes",
            "--escape-cdata",                "yes",
            "--repeated-attributes",         "keep-last",
            "--char-encoding",               "utf8",
            "--output-encoding",             "utf8",
            "--merge-spans",                 "yes",
            "--bare",                        "yes",
            "--logical-emphasis",            "yes",
            "--word-2000",                   "yes",
            "--drop-empty-paras",            "yes",
            "--drop-font-tags",              "yes",
            "--drop-proprietary-attributes", "yes",



( run in 0.638 second using v1.01-cache-2.11-cpan-454fe037f31 )