use strict; use warnings; use XML::Parser; use XML::Twig; my $xmlfile = 'input1.xml'; # the file to parse # initialize parser object and parse the string my $parser = XML::Parser->new( ErrorContext => 2 ); eval { $parser->parsefile( $xmlfile ); }; # report any error that stopped parsing, or announce success if( $@ ) { $@ =~ s/at \/.*?$//s; # remove module line number print STDERR "\nERROR in '$xmlfile':\n$@\n"; exit; } my $twig=XML::Twig->new(twig_handlers=>{ indd_document=>\&root_process, div => \&div_handler, content=> \&content_handler, }); $twig->parsefile( $xmlfile); open(FH,">output.xml") or die "cannot open output.xml: $!"; my $temp = $twig->toString; print FH $temp; close (FH); $twig->purge; #root tag "indd_document" process here sub root_process { my( $twig, $root)= @_; $root->set_tag( 'document'); $root->set_atts({OutputCreationDate=>'20090510', OutputCreationTime=>'00:00:00', 'xml:space'=>"preserve"}); $root->purge; } #paragraph element process goes here sub div_handler { my ($twig, $div)= @_; $div->set_tag('paragraph'); $div->del_att('cstyID','pstyID'); my $attval=$div->att('class'); $attval=~s/P_//; $div->set_att(style => $attval); $attval=~s/_//g; $attval="P".$attval; $div->set_att(class =>$attval); } #content tag handler sub content_handler { my ($twig, $content)= @_; my $tagname=$content->xpath(q{//box[@textflowid="rc_u50c6"]}); print $tagname; #For textbox element if($content->{'att'}->{'type'} eq "text") { $content->set_tag('textbox'); my $parent='qxpobject'; } }