From 6c9c024b0b0075d2c7f449c670532a19a7f5f7b8 Mon Sep 17 00:00:00 2001
From: Santiago Lo Coco <santilococo.01@gmail.com>
Date: Sun, 23 Jul 2023 17:28:25 +0200
Subject: [PATCH] Update *.pl files

---
 build.pl   | 40 +++++++++++++++++++++++++++++++---------
 marc2dc.pl | 18 ++++++++----------
 2 files changed, 39 insertions(+), 19 deletions(-)

diff --git a/build.pl b/build.pl
index 3e9c9f7..02ef90c 100755
--- a/build.pl
+++ b/build.pl
@@ -7,9 +7,18 @@ $/ = "</dublin_core>\n"; # record separator
 
 $what = 1000; # dummy id for when there’s no file
 
+$file = $ARGV[0];
+
+mkdir "import", 0755;
+
 while (<>) {
     $cul = "";
     $tac = "";
+    $url = "";
+
+    if (!(defined $_ and length $_ > 0)) {
+	exit;
+    }
 
     # discard the top and bottom tags
     s/<collection>\n//;
@@ -21,7 +30,8 @@ while (<>) {
     #if (s!<dcvalue element="relation" qualifier="uri">\s*(.*?)\s*<\/dcvalue>\n!!s) {
     if (/<dcvalue element="relation" qualifier="uri">\s*(.*?)\s*<\/dcvalue>\n/) {
 	$cul = $1;
-	if ($cul =~ /docs/) {
+	$url = $1;
+	if ($cul =~ /docs/ || $cul =~ /file/) {
 		#$cul =~ s@.*(folders/|d/)([^?&/]+).*@\2@;
 		$cul =~ s@.*(d/)([^?&/]+).*@$2@;
 		$tac = "https://drive.google.com/uc?export=download&id=$cul";
@@ -52,27 +62,39 @@ while (<>) {
 	print "$tac\n";
 	print "$cul\n";
 
+	my $duplicated = `grep -o \"$url\" $file | wc -l`;
+	if ($duplicated > 1) {
+		print "DUPLICATED";
+		next;
+	}
+
 	system "curl -L \"$tac\" -o import/$id/$cul";
 	#system "curl -s -L \"$tac\" -o import/$id/$cul";
 
 	my $output = `file import/$id/$cul`;
 	print $output;
 
+	$ext = '';
+
 	if ($output =~ /PDF/) {
 		$ext = "pdf";
+		system "mv import/$id/$cul import/$id/$cul.pdf";
 	}
 	if ($output =~ /Word/) {
 		system "soffice --headless --convert-to pdf import/$id/$cul";
-		$ext = "pdf";
+		$ext = "docx";
+		system "mv import/$id/$cul import/$id/$cul.docx";
+		system "mv $cul.pdf import/$id/$cul.pdf";
 	}
 
-	system "mv import/$id/$cul import/$id/$cul.$ext";
-
-        # ... create the contents file ...
-        open OUT, ">import/$id/contents"
-          or die "Cannot open contents for $id, $!\n";
-        print OUT "$cul.$ext";
-        close OUT;
+	if ($ext eq 'pdf' || $ext eq 'docx') {
+		# ... create the contents file ...
+		open OUT, ">import/$id/contents"
+		  or die "Cannot open contents for $id, $!\n";
+		print OUT "$cul.pdf";
+		print OUT "\n$cul.docx" if $ext eq 'docx';
+        	close OUT;
+	}
     }
 }
 
diff --git a/marc2dc.pl b/marc2dc.pl
index 82b9ecc..e8846b2 100755
--- a/marc2dc.pl
+++ b/marc2dc.pl
@@ -11,27 +11,25 @@ print qq|<collection>\n|;
 
 while (my $blob = <>) { # suck in one MARC record at a time
 
-        print qq|<dublin_core>\n|;
-
         # convert the MARC to DC
         my $marc = MARC::Record->new_from_usmarc( $blob );
         my $crosswalk = MARC::Crosswalk::DublinCore->new( qualified => 0 );
         my $dc        = $crosswalk->as_dublincore( $marc );
 
+	my $has_content = 0;
+
         # output the DC as XML
         for( $dc->elements ) {
+		if (!$has_content) {
+			$has_content = 1;
+        		print qq|<dublin_core>\n|;
+		}
+
 		my $element     = lc($_->name);
                 my $qualifier   = lc($_->qualifier);
                 my $scheme      = lc($_->scheme);
                 my $content     = $_->content;
 
-		##print $_->content;
-
-		#print qq|$element\n|;
-		#print qq|$qualifier\n|;
-		#print qq|$scheme\n|;
-		#print qq|$content\n|;
-
                 # escape reserved characters
                 $content =~ s/&/&amp;/gs;
                 $content =~ s/</&lt;/gs;
@@ -87,7 +85,7 @@ while (my $blob = <>) { # suck in one MARC record at a time
 	#                printf qq|>%s</dcvalue>\n|, $content;
 	#	}
 
-        print qq|</dublin_core>\n|;
+        print qq|</dublin_core>\n| if $has_content;
 }
 
 print qq|</collection>\n|;