\#$bkcontents<\/div>\#";
$bkcontents =~ s/
]+>(.+?)(?=\@?)?]+?>)/$1/g;
$poetrycontents = "$poetrycontents";
return $poetrycontents;
}
sub poetry {
$poetrycontents = @_[0];
$poetrycontents =~ s/^()+//;
$poetrycontents =~ s/()+$//;
$poetrycontents = "" . $poetrycontents . "<\/l><\/lg>\#";
$poetrycontents =~ s//<\/l>\#/g;
if ($poetrycontents =~ //) {
# $poetrycontents =~ s///;
# $poetrycontents =~ s/<\/lg>/<\/lg><\/lg>/;
$poetrycontents = "$poetrycontents<\/lg>";
$poetrycontents =~ s//<\/l><\/lg>\#/g;
}
return $poetrycontents;
}
sub buildheader {
$type = @_[0];
$contents = @_[1];
if ($type eq "1") {
$Htitle = $contents;
}
elsif ($type eq "4") {
$Hcopyright = $contents;
}
elsif ($type eq "C") {
$Hcreator = $contents;
}
return "";
}
#construct header
$bible =~ s/(.+?)(?=<)/buildheader($1,$2)/eg;
$header = "\#$date<\/date>Initial conversion from GBF using gbf2osis.pl.<\/p><\/revisionDesc>\#\#<\/work>\#<\/header>\#";
if ($Htitle ne "") {$header =~ s/<\/work>/$Htitle<\/title>\#<\/work>/g;}
if ($Hcreator ne "") {$header =~ s/<\/work>/<creator>$Hcreator<\/creator>\#<\/work>/g;}
if ($Hcopyright ne "") {$header =~ s/<\/work>/<rights>$Hcopyright<\/rights>\#<\/work>/g;}
$header = "<\?xml version=\"1.0\" encoding=\"UTF-8\"?>\#<osis xmlns=\"http:\/\/www.bibletechnologies.net\/2003\/OSIS\/namespace\" xmlns:xsi=\"http:\/\/www.w3.org\/2001\/XMLSchema-instance\" xsi:schemaLocation=\"http:\/\/www.bibletechnologies.net\/2003\/OSIS\/namespace http:\/\/www.bibletechnologies.net\/osisCore.$osisVersion.xsd\">\#<osisText osisRefWork=\"Bible\" xml:lang=\"en\" osisIDWork=\"$osisWork\">\#$header";
$bible =~ s/<H0[\d][\d]>.+<BO>/<BO>/;
#early reformatting
$bible =~ s/<PP><CM>\@<SC60><SV1>/<CM>\@<SC60><PP><SV1>/;
$bible =~ s/<PP>(.+?)<Pp>/poetrychunk($1)/eg;
#deal with body
$bible =~ s/<B[OAN]>(.+?)(?=<B|<ZZ)/<div type="bookGroup" canonical="true">\#$1<\/div>\#/g;
$bk = 0;
$bible =~ s/(<CM>[\@\#]*)+<SB/\#<SB/g;
$bible =~ s/<SB([^>]+)>(.+?)(?=<SB|<\/div)/bookdivs($1,$2)/eg;
$bible =~ s/<RB>(.+?)<RF>(.+?)<Rf>/$1<note><catchWord>$1<\/catchWord> $2<\/note>/g;
$bible =~ s/<RF>(.+?)<Rf>/<note>$1<\/note>/g;
$bible =~ s/<TC>(.+?)<Tc>//g;
$bible =~ s/<TN>(.+?)<Tn>//g;
$bible =~ s/<TT>(.+?)(<CM>[\#\@]*)<Tt>/<title>$1<\/title>\#/g;
$bible =~ s/<TB>(.+?)(<CM>[\#\@]*)<Tb>/<title>$1<\/title>\#/g;
$bible =~ s/<TH>(.+?)(<CM>[\#\@]*)<Th>/<title type="psalm">$1<\/title>\#/g;
$bible =~ s/<TS>(.+?)(<CM>|[\#\@])*<Ts>/<speaker>$1<\/speaker>\#/g;
$bible =~ s/<PP>(.+?)<Pp>/poetry($1)/eg;
$bible =~ s/<CL>/<lb\/>/g;
$bible =~ s/<FI>(.+?)<Fi>/<hi type=\"italic\">$1<\/hi>/g;
$bible =~ s/<CM>/<\/p>\#<p>/g;
$bible =~ s/<JR>([^<]+?)<\/lg>/<l type=\"selah\">$1<\/l><\/lg>/g;
$bible =~ s/<JL>//g;
$qn = 0;
$bible =~ s/<FR>(.+?)?<Fr>/"<q marker=\"“\" level=\"1\" sID=\"q." . ++$qn . "\" who=\"Jesus\"\/>$1<q marker=\"”\" eID=\"q." . $qn . "\"\/>"/eg;
$bible =~ s/<FR>(.+?)?<Fr>/"<q marker=\"‘\" level=\"2\" sID=\"q2." . ++$qn . "\" who=\"Jesus\"\/>$1<q marker=\"’\" eID=\"q2." . $qn . "\"\/>"/eg;
$bible =~ s/(.+?)/"<q marker=\"“\" level=\"1\" sID=\"q." . ++$qn . "\"\/>$1<q marker=\"”\" eID=\"q." . $qn . "\"\/>"/eg;
$bible =~ s/(.+?)/"<q marker=\"“\" level=\"2\" sID=\"q2." . ++$qn . "\"\/>$1<q marker=\"’\" eID=\"q2." . $qn . "\"\/>"/eg;
$bible =~ s/(\w+)<WTP>/<w morph="pl">$1<\/w>/g;
$bible =~ s/(\w+)<WTf>/<w morph="2">$1<\/w>/g;
$bible =~ s/(<\/p>\#<p>)\@?(<verse eID[^>]+>)\#?/$2$1/g;
$bible =~ s/(<\/p>)(<verse eID[^>]+>)/$2$1/g;
$bible =~ s/<l> +/<l>/g;
$bible =~ s/<p> +/<p>/g;
$bible =~ s/<l>\@?<JR>/<l type=\"selah\">/g;
$bible =~ s/<ZZ>/<\/osisText>\#<\/osis>\#/g;
$bible = $header . $bible;
$bible =~ s/\@//g;
$bible =~ s/\s*\#+\s*/\#/g;
# cleanups
sub nukelongcw {
$cw = @_[0];
if ($cw =~ /<verse /) {return "";}
else {return $cw};
}
$bible =~ s/<lg><l><\/l><\/lg>\#//g;
$bible =~ s/<p><\/p>\#//g;
$bible =~ s/<lg><lg><l>(<title type=\"psalm\">[^<]+<\/title>)\#<\/l><\/lg>/$1<lg>\#/g;
$bible =~ s/<lg><l>(<title type=\"psalm\">[^<]+<\/title>)\#<\/l><\/lg>/<\/lg>\#$1<lg>\#/g;
$bible =~ s/(<catchWord>[^<]+)<\/l>\#<l>([^<]+<\/catchWord>)/$1<lb\/>$2/g;
$bible =~ s/(<catchWord>.+?<\/catchWord> *)/nukelongcw($1)/eg; # nuke overly long (multi-verse) catchWords
#$bible =~ s/(<\/p>\#<\/chapter>\#<chapter osisID=\"[^\"]+\">\#<p>)(<\/l><\/lg>)\#(<lg><l>)/$2<\/lg>$1<lg>$3/g;
$bible =~ s/\#/\n/g;
# encoding stuff
use encoding 'latin1';
utf8::encode($bible);
$bible =~ s/“/“/g;
$bible =~ s/”/”/g;
$bible =~ s/‘/‘/g;
$bible =~ s/’/’/g;
$bible =~ s/\&/\&/g;
print OUTF "$bible";
close (INF);