crossrefware (19oct14)

git-svn-id: svn://tug.org/texlive/trunk@35401 c570f23f-e606-0410-a88d-b1316a301751

3 files changed, 942 insertions, 0 deletions

diff --git a/Master/texmf-dist/scripts/crossrefware/bibdoiadd.pl b/Master/texmf-dist/scripts/crossrefware/bibdoiadd.pl
new file mode 100755
index 00000000000..b9be8dec824
--- /dev/null
+++ b/Master/texmf-dist/scripts/crossrefware/bibdoiadd.pl
@@ -0,0 +1,267 @@
+#!/usr/bin/env perl
+
+=pod
+
+=head1 NAME
+
+bibdoiadd.pl - add DOI numbers to papers in a given bib file
+
+=head1 SYNOPSIS
+
+bibdoiadd [B<-c> I<config_file>]  [B<-o> I<output>] I<bib_file>
+
+=head1 OPTIONS
+
+=over 4
+
+=item B<-c> I<config_file>
+
+Configuration file.  If this file is absent, some defaults are used.
+See below for its format.
+
+
+=item B<-o> I<output>
+
+Output file.  If this option is not used, the name for the 
+output file is formed by adding C<_doi> to the input file
+
+=back
+
+=head1 DESCRIPTION
+
+The script reads a BibTeX file.  It checks whether the entries have
+DOIs.  If now, tries to contact http://www.crossref.org to get the
+corresponding DOI.  The result is a BibTeX file with the fields
+C<doi=...> added.  
+
+The name of the output file is either set by the B<-o> option or 
+is derived by adding the suffix C<_doi> to the output file.
+
+There are two options for making queries with Crossref: free account
+and paid membership.  In the first case you still must register with
+Crossref and are limited to a small number of queries, see the
+agreement at
+C<http://www.crossref.org/01company/free_services_agreement.html>.  In
+the second case you have a username and password, and can use them for
+automatic queries.  I am not sure whether the use of this script is
+allowed for the free account holders.  Anyway if you try to add DOI
+to a large number of entries, you should register as a paid member.
+
+
+
+=head1 CONFIGURATION FILE 
+
+The configuration file is mostly self-explanatory: it has comments
+(starting with C<#>) and assginments in the form
+
+   $field = value ;
+
+The important parameters are C<$mode> (C<'free'> or C<'paid'>,
+C<$email> (for free users) and C<$username> & C<$password> for paid
+members.
+
+
+=head1 EXAMPLES
+
+   bibdoiadd -c bibdoiadd.cfg citations.bib > result.bib
+   bibdoiadd -c bibdoiadd.cfg citations.bib -o result.bib
+
+=head1 AUTHOR
+
+Boris Veytsman
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2014  Boris Veytsman
+
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+L<http://www.gnu.org/licenses/gpl.html>.  There is NO WARRANTY, to the
+extent permitted by law.
+
+=cut
+
+use strict;
+use Text::BibTeX;
+use Text::BibTeX::Name;
+use Getopt::Std;
+use URI::Escape;
+use LWP::Simple;
+use TeX::Encode;
+use Encode;
+use HTML::Entities;
+use XML::Entities;
+
+my $USAGE="USAGE: $0 [-c config] [-o output] file\n";
+my $VERSION = <<END;
+bibdoiadd v1.0
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+http://www.gnu.org/licenses/gpl.html.  There is NO WARRANTY, to the
+extent permitted by law.
+$USAGE
+END
+my %opts;
+getopts('c:o:hV',\%opts) or die $USAGE;
+
+if ($opts{h} || $opts{V}){
+    print $VERSION;
+    exit 0;
+}
+
+################################################################
+# Defaults and parameters
+################################################################
+
+my $inputfile = shift;
+
+my $outputfile = $inputfile;
+
+$outputfile =~ s/\.([^\.]*)$/_doi.$1/;
+
+if ($opts{o}) {
+    $outputfile = $opts{o};
+}
+
+our $mode='free';
+our $email;
+our $username;
+our $password;
+
+if ($opts{c}) {
+    if (-r $opts{c}) {
+	push @INC, ".";
+	require $opts{c};
+    } else {
+	die "Cannot read options $opts{c}.  $USAGE";
+    }
+}
+
+
+# Check the consistency
+
+if ($mode eq 'free' && !length($email)) {
+    die "Crossref requires a registered e-mail for the free mode queries\n";
+}
+
+if ($mode eq 'paid' && (!length($username) || !length($password))) {
+    die 
+	"Crossref requires a username and password for the paid mode queries\n";
+}
+
+my $input = new Text::BibTeX::File "$inputfile" or 
+    die "Cannot BibTeX file $inputfile\n";
+my $output = new Text::BibTeX::File "> $outputfile" or 
+    die "Cannot write to $outputfile\n";
+
+my $prefix = 
+    "http://www.crossref.org/openurl?redirect=false";
+if ($mode eq 'free') {
+    $prefix .= '&pid='.uri_escape($email);
+} else {
+    $prefix .= '&pid='.uri_escape($username).":".
+	uri_escape($password);
+}
+
+# Processing the input
+while (my $entry = new Text::BibTeX::Entry $input) {
+    if (!$entry->parse_ok()) {
+	print STDERR "Cannot understand entry: ";
+	$entry->print(*STDERR);
+	print STDERR "Skipping this entry\n";
+	next;
+    }
+    if (!(($entry->metatype() eq BTE_REGULAR) &&
+	  ($entry->type() eq 'article'))) {
+	$entry->write($output);
+	next;
+    }
+    if ($entry->exists('doi')) {
+	$entry->write($output);
+	next;
+    }
+    
+
+    # Now we have an entry with no doi.  Let us get to work.
+    my $doi = GetDoi($prefix,$entry);
+    if (length($doi)) {
+	$entry->set('doi',$doi);
+    }
+    $entry->write($output);
+
+}
+
+$input->close();
+$output->close();
+exit 0;
+
+###############################################################
+#  Getting one doi
+###############################################################
+
+sub GetDoi {
+    my ($url,$entry) = @_;
+    if ($entry->exists('issn')) {
+	$url .= "&issn=".uri_escape(SanitizeText($entry->get('issn')));
+    }
+    if ($entry->exists('journal')) {
+	$url .= "&title=".uri_escape(SanitizeText($entry->get('journal')));
+    }
+    my @names=$entry->names ('author');
+    if (scalar(@names)) {
+	my @lastnames = $names[0]->part ('last');
+	if (scalar(@lastnames)) {
+	    my $lastname = SanitizeText(join(' ',@lastnames));
+	    $url .= "&aulast=".uri_escape($lastname);
+	}
+    }
+    if ($entry->exists('volume')) {
+	$url .= "&volume=".uri_escape($entry->get('volume'));
+    }    
+    if ($entry->exists('number')) {
+	$url .= "&issue=".uri_escape($entry->get('number'));
+    }    
+    if ($entry->exists('pages')) {
+	my $pages=$entry->get('pages');
+	$pages =~ s/-.*$//;
+	$url .= "&spage=".uri_escape($pages);
+    }    
+    if ($entry->exists('year')) {
+	$url .= "&date=".uri_escape($entry->get('year'));
+    }    
+
+    my $result=get($url);
+
+    if ($result =~ m/<doi [^>]*>(.*)<\/doi>/) {
+	return $1;
+    } else {
+	return "";
+    }
+}
+	
+###############################################################
+#  Sanitization of a text string
+###############################################################
+sub SanitizeText {
+    my $string = shift;
+    # There is a bug in the decode function, which we need to work 
+    # around:  it adds space to constructions like \o x
+    $string =~ s/(\\[a-zA-Z])\s+/$1/g;
+    $string =~ s/\\newblock//g;
+    $string =~ s/\\urlprefix//g;
+    $string =~ s/\\emph//g;
+    $string =~ s/\\enquote//g;
+    $string =~ s/\\url/URL: /g;
+    $string =~ s/\\doi/DOI: /g;
+    $string =~ s/\\\\/ /g;
+    $string = decode('latex', $string);
+    $string =~ s/\\[a-zA-Z]+/ /g;
+    $string =~ s/\\\\/ /g;
+    $string =~ s/[\[\{\}\]]/ /g;
+    $string = encode_entities($string);
+    $string = XML::Entities::numify('all', $string);
+    $string =~ s/amp;//g;
+    $string =~ s/~/ /g;
+    $string =~ s/\s*([\.;,])/$1/g;
+    return $string;
+}
diff --git a/Master/texmf-dist/scripts/crossrefware/bibzbladd.pl b/Master/texmf-dist/scripts/crossrefware/bibzbladd.pl
new file mode 100755
index 00000000000..4059b7b0a12
--- /dev/null
+++ b/Master/texmf-dist/scripts/crossrefware/bibzbladd.pl
@@ -0,0 +1,215 @@
+#!/usr/bin/env perl
+
+=pod
+
+=head1 NAME
+
+bibzbladd.pl - add Zbl numbers to papers in a given bib file
+
+=head1 SYNOPSIS
+
+bibzbladd  [B<-o> I<output>] I<bib_file>
+
+=head1 OPTIONS
+
+=over 4
+
+
+=item B<-o> I<output>
+
+Output file.  If this option is not used, the name for the 
+output file is formed by adding C<_zbl> to the input file
+
+=back
+
+=head1 DESCRIPTION
+
+The script reads a BibTeX file.  It checks whether the entries have
+Zbls.  If now, tries to contact internet to get the numbers.  The
+result is a BibTeX file with the fields 
+C<zblnumber=...> added.  
+
+The name of the output file is either set by the B<-o> option or 
+is derived by adding the suffix C<_zbl> to the output file.
+
+=head1 AUTHOR
+
+Boris Veytsman
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2014  Boris Veytsman
+
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+L<http://www.gnu.org/licenses/gpl.html>.  There is NO WARRANTY, to the
+extent permitted by law.
+
+=cut
+
+use strict;
+use Text::BibTeX;
+use Text::BibTeX::Name;
+use Getopt::Std;
+use URI::Escape;
+use LWP::UserAgent;
+use TeX::Encode;
+
+my $USAGE="USAGE: $0  [-o output] file\n";
+my $VERSION = <<END;
+bibzbladd v1.0
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+http://www.gnu.org/licenses/gpl.html.  There is NO WARRANTY, to the
+extent permitted by law.
+$USAGE
+END
+my %opts;
+getopts('o:hV',\%opts) or die $USAGE;
+
+if ($opts{h} || $opts{V}){
+    print $VERSION;
+    exit 0;
+}
+
+################################################################
+# Defaults and parameters
+################################################################
+
+my $inputfile = shift;
+
+my $outputfile = $inputfile;
+
+$outputfile =~ s/\.([^\.]*)$/_zbl.$1/;
+
+if ($opts{o}) {
+    $outputfile = $opts{o};
+}
+
+my $input = new Text::BibTeX::File "$inputfile" or 
+    die "Cannot BibTeX file $inputfile\n";
+my $output = new Text::BibTeX::File "> $outputfile" or 
+    die "Cannot write to $outputfile\n";
+
+
+# Creating the HTTP parameters
+my $mirror =
+    "http://www.zentralblatt-math.org/MIRROR/zmath/en/search/";
+my $userAgent = LWP::UserAgent->new;
+
+# Processing the input
+while (my $entry = new Text::BibTeX::Entry $input) {
+    if (!$entry->parse_ok()) {
+	print STDERR "Cannot understand entry: ";
+	$entry->print(*STDERR);
+	print STDERR "Skipping this entry\n";
+	next;
+    }
+    if (!(($entry->metatype() eq BTE_REGULAR))) {
+	$entry->write($output);
+	next;
+    }
+    if ($entry->exists('zblnumber')) {
+	$entry->write($output);
+	next;
+    }
+    
+
+    # Now we have an entry with no Zbl.  Let us get to work.
+    my $zbl = GetZbl($entry, $userAgent, $mirror);
+    if (length($zbl)) {
+	$entry->set('zblnumber',$zbl);
+    }
+    $entry->write($output);
+
+}
+
+$input->close();
+$output->close();
+exit 0;
+
+###############################################################
+#  Getting one Zbl
+###############################################################
+
+sub GetZbl {
+    my $entry=shift;
+    my $userAgent=shift;
+    my $mirror=shift;
+    
+    my @query;
+
+    my @names=$entry->names ('author');
+    if (scalar(@names)) {
+	foreach my $name (@names) {
+	    my @lastnames = $name->part ('last');
+	    if (scalar(@lastnames)) {
+		foreach my $lastname (@lastnames) {
+		    push @query, "au:$lastname";
+		}
+	    }
+	}
+    }
+    if (my $title = $entry->get('title')) {
+	push @query, "ti:$title";
+    }
+    
+    if (my $year = $entry->get('year')) {
+	push @query, "py:$year";
+    }
+
+    if (my $year = $entry->get('year')) {
+	push @query, "py:$year";
+    }
+
+    my $type = $entry->type;
+    if ($type eq 'article') {
+	push @query, "dt:j";
+    }
+    if ($type eq 'book') {
+	push @query, "dt:b";
+    }
+    if ($type eq 'inproceedings' || $type eq 'incollection') {
+	push @query, "dt:a";
+    }
+
+    my $source = "";
+    if ($type eq 'article') {
+	if ($entry->get('journal')) {
+	    $source .= $entry->get('journal');
+	}
+	if (my $vol=$entry->get('volume')) {
+	    $source .= ",$vol";
+	}
+	if (my $pages=$entry->get('pages')) {
+	    $source .= ",$pages";
+	}
+    } else {
+	if (my $bt=$entry->get('booktitle')) {
+	    $source .= "$bt";
+	}
+    }
+
+    if ($source) {
+	push @query, "so:$source";
+    }
+
+
+    my $qstring = join(" & ", @query);
+#    print STDERR "$qstring\n";
+
+    my $form;
+
+    $form->{name}='form';
+    $form->{q} =  $qstring;
+    $form->{type} = "ascii";
+    $form->{submit} = 'Search';
+
+    my $response = $userAgent->post($mirror, $form);
+    if ($response->decoded_content =~ /^an:\s*Zbl\s*(\S+)\s*$/m) {
+	return $1;
+    } else {
+	return ("");
+    }
+}
+	
diff --git a/Master/texmf-dist/scripts/crossrefware/ltx2crossrefxml.pl b/Master/texmf-dist/scripts/crossrefware/ltx2crossrefxml.pl
new file mode 100755
index 00000000000..5ceee5f13df
--- /dev/null
+++ b/Master/texmf-dist/scripts/crossrefware/ltx2crossrefxml.pl
@@ -0,0 +1,460 @@
+#!/usr/bin/env perl
+
+=pod
+
+=head1 NAME
+
+ltx2crossrefxml.pl - a tool for creation of XML files for submitting to crossref.
+
+=head1 SYNOPSIS
+
+ltx2crossrefxml [B<-c> I<config_file>]  [B<-o> I<output>] I<latex_file> I<latex_file> ...
+
+
+=head1 OPTIONS
+
+=over 4
+
+=item B<-c> I<config_file>
+
+Configuration file.  If this file is absent, some defaults are used.
+See below for its format.
+
+
+=item B<-o> I<output>
+
+Output file.  If this option is not used, the XML is output to stdout.
+
+=back
+
+=head1 DESCRIPTION
+
+The script takes a number of latex files and produces an XML file
+ready for submission to Crossref.  Each file must be previously processed
+by LaTeX with the newest C<resphilosophica> package: the package creates
+the file C<.rti> wtih the information about the bibliography.
+
+The processing of reference list is at present rather limited: only so
+called unstructured references are produced.
+
+=head1 CONFIGURATION FILE FORMAT
+
+The configuration file is mostly self-explanatory: it has comments
+(starting with C<#>) and assginments in the form
+
+   $field = value ;
+
+=head1 EXAMPLES
+
+  ltx2crossrefxml.pl ../paper1/paper1.tex ../paper2/paper2.tex -o result.xml
+
+  ltx2crossrefxml.pl -c myconfig.cnf paper.tex -o paper.xml
+
+=head1 AUTHOR
+
+Boris Veytsman
+
+=head1 COPYRIGHT AND LICENSE
+
+Copyright (C) 2012  Boris Veytsman
+
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+L<http://www.gnu.org/licenses/gpl.html>.  There is NO WARRANTY, to the
+extent permitted by law.
+
+
+=cut
+
+ use strict;
+ use POSIX qw(strftime);
+ use Text::BibTeX;
+ use Text::BibTeX::Name;
+ use TeX::Encode;
+ use Encode;
+ use HTML::Entities;
+ use XML::Entities;
+ use File::Basename;
+ use File::Spec;
+ my $USAGE="USAGE: $0 [-c config] [-o output] file1 file2 ...\n";
+my $VERSION = <<END;
+ltx2crossrefxml v1.0
+This is free software.  You may redistribute copies of it under the
+terms of the GNU General Public License
+http://www.gnu.org/licenses/gpl.html.  There is NO WARRANTY, to the
+extent permitted by law.
+$USAGE
+END
+ use Getopt::Std;
+ my %opts;
+ getopts('c:o:hV',\%opts) or die $USAGE;
+
+if ($opts{h} || $opts{V}){
+    print $VERSION;
+    exit 0;
+}
+
+ ################################################################
+ # Defaults and parameters
+ ################################################################
+
+ *OUT=*STDOUT;
+ 
+ if (defined($opts{o})) {
+     open (OUT, ">$opts{o}") or die "Cannot open file $opts{o} for writing\n";
+ }
+
+
+ our $depositorName='DEPOSITOR_NAME';
+ our $depositorEmail='DEPOSITOR_EMAIL';
+ our $registrant='REGISTRANT';
+ our $fullTitle = "FULL TITLE";
+ our $abbrevTitle = "ABBR. Title.";
+ our $issn = "1234-5678";
+ our $coden = "CODEN";
+ our $batchId="ltx2crossref$$";
+ our $timestamp=strftime("%Y%m%d%H%M%S", gmtime);
+
+
+ if ($opts{c}) {
+     if (-r $opts{c}) {
+	 require $opts{c};
+     } else {
+	 die "Cannot read options $opts{c}.  $USAGE";
+     }
+ }
+
+
+
+ PrintHead();
+
+ # 
+ # The hash %papers.  Keys year->vol->issue->number
+ #
+ my %papers;
+
+ foreach my $file (@ARGV) {
+     AddPaper($file);
+ }
+
+ foreach my $year (keys %papers) {
+     foreach my $volume (keys %{$papers{$year}}) {
+	 foreach my $issue (keys %{$papers{$year}->{$volume}}) {
+	     PrintIssueHead($year, $volume, $issue);
+	     my $paperList = $papers{$year}->{$volume}->{$issue};
+	     foreach my $paper (@{$paperList}) {
+		 PrintPaper($paper);
+	     }
+	 }
+     }
+
+ }
+
+ PrintTail();
+
+ exit(0);
+
+
+#####################################################
+#  Printing the head and the tail
+#####################################################
+
+sub PrintHead {
+
+
+    print OUT <<END;
+<doi_batch xmlns="http://www.crossref.org/schema/4.3.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" version="4.3.0" xsi:schemaLocation="http://www.crossref.org/schema/4.3.0 http://www.crossref.org/schema/deposit/crossref4.3.0.xsd">
+  <head>
+    <doi_batch_id>$batchId</doi_batch_id>
+    <timestamp>$timestamp</timestamp>
+    <depositor>
+      <name>$depositorName</name>
+      <email_address>$depositorEmail</email_address>
+    </depositor>
+    <registrant>$registrant</registrant>
+  </head>
+  <body>
+    <journal>
+      <journal_metadata language="en">
+        <full_title>$fullTitle</full_title>
+        <abbrev_title>$abbrevTitle</abbrev_title>
+	<issn>$issn</issn>
+	<coden>$coden</coden>
+      </journal_metadata>
+END
+
+}
+
+sub PrintTail {
+    print OUT <<END;
+    </journal>
+  </body>
+</doi_batch>
+END
+
+return;
+}
+
+
+#######################################################
+#  Adding one paper
+#######################################################
+
+sub AddPaper {
+    my $file = shift;
+    my ($name,$path,$suffix) = fileparse($file, '\.[^\.]*$');
+    my $rpifile = File::Spec->catfile($path, "$name.rpi");
+    open (RPI, $rpifile) or die 
+     "Cannot find $rpifile.  Did you process $file?\n";
+    my %data;
+    while (<RPI>) {
+	chomp;
+        if (/^%([^=]*)\s*=\s*(.*)\s*$/) {
+           $data{$1}=$2;
+        }
+    }
+    close RPI;
+    my @bibliography;
+    foreach my $bibfile ($file, File::Spec->catfile($path, "$name.bbl")) {
+         @bibliography = (@bibliography, 
+          AddBibliography($bibfile));
+    }
+    $data{'bibliography'}=\@bibliography;
+    push @{$papers{$data{year}}->{$data{volume}}->{$data{issue}}}, \%data;
+}
+
+############################################################## 
+# Reading a list of papers and adding  it to the
+# bibliography
+##############################################################
+
+sub AddBibliography {
+    my $bibfile = shift;
+    open (BIB, $bibfile) or return;
+    my $insidebibliography = 0;
+    my $currpaper="";
+    my @result;
+    my $key;
+    while (<BIB>) {
+	chomp;
+	if (/^\s*\\bibitem(?:\[.*\])?+\{(.+)\}/) {
+	    if ($insidebibliography) {
+		if ($currpaper) {
+		    my %paperhash;
+		    $paperhash{$key}=$currpaper;
+		    push @result, \%paperhash;
+		}
+	    }
+	    $key = $1;
+	    $currpaper="";
+	    $insidebibliography=1;
+	    next;
+	}
+	if (/^\s*\\end\{thebibliography\}/) {
+	    if ($currpaper) {
+		    my %paperhash;
+		    $paperhash{$key}=$currpaper;
+		    push @result, \%paperhash;
+	    }
+	    $currpaper="";
+	    $insidebibliography=0;
+	    next;
+	}
+	if ($insidebibliography) {
+	    $currpaper .= " $_";
+	}
+    }
+    close BIB;
+    return @result;
+}
+
+#################################################################
+#  Printing information about one issue
+#################################################################
+
+sub PrintIssueHead {
+    my ($year, $volume, $issue) = @_;
+    print OUT <<END;
+      <journal_issue>
+        <publication_date media_type="print">
+          <year>$year</year>
+        </publication_date>
+        <journal_volume>
+          <volume>$volume</volume>
+        </journal_volume>
+        <issue>$issue</issue>
+      </journal_issue>
+END
+}
+
+###############################################################
+# Printing information about one paper
+###############################################################
+sub PrintPaper {
+    my $paper = shift;
+    my $title=SanitizeText($paper->{title});
+    my $url=GetURL($paper);
+    print OUT <<END;
+      <journal_article publication_type="full_text">
+        <titles>
+           <title>
+             $title
+           </title>
+        </titles>
+        <contributors>
+END
+my @authors = split /\s*\\and\s*/, $paper->{authors};
+    my $seq='first';
+    foreach my $author (@authors) {
+	print OUT <<END;
+          <person_name sequence="$seq" contributor_role="author">
+END
+$seq='additional';
+	PrintAuthor($author);
+	print OUT <<END;
+          </person_name>
+END
+
+    }
+
+    print OUT <<END;
+        </contributors>
+        <publication_date media_type="print">
+           <year>$paper->{year}</year>
+        </publication_date>
+        <pages>
+           <first_page>$paper->{startpage}</first_page>
+           <last_page>$paper->{endpage}</last_page>
+        </pages>
+        <doi_data>
+          <doi>$paper->{doi}</doi>
+          <timestamp>$timestamp</timestamp>
+	  <resource>$url</resource>
+        </doi_data>
+END
+
+if (scalar(@{$paper->{bibliography}})) {
+    print OUT <<END;
+        <citation_list>
+END
+    foreach my $citation (@{$paper->{bibliography}}) {
+	PrintCitation($citation);
+    }
+    print OUT <<END;
+        </citation_list>
+END
+}
+
+    print OUT <<END;
+      </journal_article>
+END
+
+
+}
+
+
+###############################################################
+#  Sanitization of a text string
+###############################################################
+sub SanitizeText {
+    my $string = shift;
+    # There is a bug in the decode function, which we need to work 
+    # around:  it adds space to constructions like \o x
+    $string =~ s/(\\[a-zA-Z])\s+/$1/g;
+    $string =~ s/\\newblock//g;
+    $string =~ s/\\bgroup//g;
+    $string =~ s/\\egroup//g;
+    $string =~ s/\\scshape//g;
+    $string =~ s/\\urlprefix//g;
+    $string =~ s/\\emph//g;
+    $string =~ s/\\textbf//g;
+    $string =~ s/\\enquote//g;
+    $string =~ s/\\url/URL: /g;
+    $string =~ s/\\doi/DOI: /g;
+    $string =~ s/\\\\/ /g;
+    $string =~ s/\$//g;
+    $string = decode('latex', $string);
+    $string =~ s/\\[a-zA-Z]+/ /g;
+    $string =~ s/\\\\/ /g;
+    $string =~ s/[\[\{\}\]]/ /g;
+    $string = encode_entities($string);
+    $string = XML::Entities::numify('all', $string);
+    $string =~ s/amp;//g;
+    $string =~ s/~/ /g;
+    $string =~ s/\s*([\.;,])/$1/g;
+    return $string;
+}
+
+################################################################
+# Printing one author
+################################################################
+sub PrintAuthor {
+    my $author=shift;
+
+    my $person=new Text::BibTeX::Name ($author);
+
+    if ($person->part('first')) {
+	my @tokens = $person->part('first');
+	my $line = join(" ", @tokens);
+	$line = SanitizeText($line);
+	print OUT <<END;
+            <given_name>$line</given_name>
+END
+
+    }
+
+    if ($person->part('last')) {
+	my $line = SanitizeText($person->part('last'));
+	print OUT <<END;
+            <surname>$line</surname>
+END
+
+    }
+
+    if ($person->part('jr')) {
+	my $line = SanitizeText($person->part('jr'));
+	print OUT <<END;
+            <suffix>$line</suffix>
+END
+
+    }
+
+}
+
+#############################################################
+#  Printing citations
+#############################################################
+sub PrintCitation {
+    my $paperhash=shift;
+    foreach my $key (keys (%{$paperhash})) {
+	my $citation=$paperhash->{$key};
+	$citation=SanitizeText($citation);
+
+	print OUT <<END;
+          <citation key="$key">
+             <unstructured_citation>
+               $citation
+             </unstructured_citation>
+          </citation>
+END
+}
+
+}
+
+##############################################################
+#  Calculating URL
+##############################################################
+
+sub GetURL {
+    my $paper = shift;
+
+    my $result;
+    if ($paper->{paperUrl}) {
+	$result= $paper->{paperUrl}
+    } else {
+	my $doi=$paper->{doi};
+	$result= 'http://www.pdcnet.org/oom/service?url_ver=Z39.88-2004&rft_val_fmt=&rft.imuse_synonym=resphilosophica&rft.DOI='.$doi.'&svc_id=info:www.pdcnet.org/collection';
+    }
+    $result =~ s/&/&#38;/g;
+    return $result;
+}