Monks,

I need to use Win32::OLE to extract the text from MsWord. The best solution I could find to maintain a bit of formatting is to use the SaveAs function (I would prefer to read directly into a variable, but I can leave with it). The problem is I can NOT find how to set the parameters to save the file in Unicode (something you get asked by Word after clicking on SaveAs...). I've read all I could, but could not find any substitution/completion of "wdFormatTextLineBreaks" to achieve this goal. On Microsoft specification page, they speak about "wdFormatUnicodeText" with value "7". But I can't find how to specify it in my script (just replacing "wdFormatTextLineBreaks" with "wdFormatUnicodeText" does not produce any effect). Maybe some of you know the answer.

#!/usr/bin/perl

use strict;
use warnings;

use File::Spec::Functions qw( catfile );
use Cwd qw(cwd);
use Win32::OLE;
use Win32::OLE::Const 'Microsoft Word';

$Win32::OLE::Warn = 3;

my $dir = cwd;

my $word = get_word();
$word->{Visible} = 0;

my $doc = $word->{Documents}->Open(catfile $dir, 'test.docx');

$doc->SaveAs(
    catfile($dir, 'test.txt'),
    wdFormatTextLineBreaks
);

$doc->Close(0);

sub get_word {
    my $word;
    eval {
        $word = Win32::OLE->GetActiveObject('Word.Application');
    };

    die "$@\n" if $@;

    unless(defined $word) {
        $word = Win32::OLE->new('Word.Application', sub { $_[0]->Quit 
+})
            or die "Oops, cannot start Word: ",
                   Win32::OLE->LastError, "\n";
    }
    return $word;
}
__END__
[download]