X-Git-Url: http://git.equinoxoli.org/?p=migration-tools.git;a=blobdiff_plain;f=extract_holdings;h=619aec14853e961d5fa21aaf7530c1ddc1cb0ef1;hp=d39aac9bddb1d0e033e65d33a8fdbe302d7e82dc;hb=3e12dd990b438752403a9e21bdfbd47deb95ca17;hpb=5a0ffda818989fddf5c3315d00c87fdf348cae92

diff --git a/extract_holdings b/extract_holdings
index d39aac9..619aec1 100755
--- a/extract_holdings
+++ b/extract_holdings
@@ -1,4 +1,21 @@
 #!/usr/bin/perl
+
+# Copyright 2009-2012, Equinox Software, Inc.
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+
 use strict;
 use warnings;
 
@@ -45,6 +62,8 @@ sub extract_holdings {
           { open my $fh, ">", ($c->{prefix} . "-HOLDINGS-MULT-$t$s.pg"); $MULTIFILE{"$t$s"} = $fh }
     }
 
+    my $parallel_fields = $m->get_parallel_fields;
+
     my $i = 0; # record counter
     my $j = 0; # holdings counter
 
@@ -72,7 +91,9 @@ sub extract_holdings {
             for my $sub ( sort keys %{$multis->{$tagid}} ) {
                 for my $value ( @{$rec->{tags}[$holdidx]{multi}{$sub}} ) {
                   my $fh = $MULTIFILE{"$tagid$sub"};
-                  print $fh join("\t", $rec->{egid}, $j, $value), "\n";
+                  my $clean_value = $value;
+                  $clean_value =~ s/[\r\n\t]//g;
+                  print $fh join("\t", $rec->{egid}, $j, $clean_value), "\n";
               }
             }
 
@@ -85,27 +106,45 @@ sub extract_holdings {
                     push @out, '';
                     next;
                 }
+
+                # handle parallel fields
+                if (exists($parallel_fields->{$othertag})) {
+                    my $num_fields = $#{ $rec->{tmap}{$othertag} };
+                    my $tag_idx;
+                    if ($holdidx > $num_fields) {
+                        $tag_idx = -1;
+                    } else {
+                        $tag_idx = $rec->{tmap}{$othertag}[$holdidx];
+                    }
+                    for my $sub ( sort keys %{ $parallel_fields->{$othertag } } ) {
+                        push @out, $tag_idx > -1 ? $rec->{tags}[$tag_idx]{parallel}{$sub}->[0] : '';
+                        print HOLDINGS "l_", $m->name($rec->{tags}[$tag_idx]{tag}, $sub), ", " unless $j;
+                    }
+                }
+
                 # handle only first other tag unless it is known to be multi
                 my $limit = 0;
                 if (exists($multis->{$othertag})) {
                     $limit = $#{ $rec->{tmap}{$othertag} };
                 }
                 foreach my $idx (0..$limit) {
-                    for my $sub ( sort keys %{$rec->{tags}[$idx]{uni}} ) {
-                        if ($m->first_only($rec->{tags}[$idx]{tag}, $sub)) {
-                            push @out, ($k == 1) ? $rec->{tags}[$idx]{uni}{$sub} : '';
+                    my $tag_idx = $rec->{tmap}{$othertag}[$idx];
+                    for my $sub ( sort keys %{$rec->{tags}[$tag_idx]{uni}} ) {
+                        if ($m->first_only($rec->{tags}[$tag_idx]{tag}, $sub)) {
+                            push @out, ($k == 1) ? $rec->{tags}[$tag_idx]{uni}{$sub} : '';
                         } else {
-                            push @out, $rec->{tags}[$idx]{uni}{$sub};
+                            push @out, $rec->{tags}[$tag_idx]{uni}{$sub};
                         }
-                        print HOLDINGS "l_", $m->name($rec->{tags}[$idx]{tag}, $sub), ", "
-                        unless $j;
+                        print HOLDINGS "l_", $m->name($rec->{tags}[$tag_idx]{tag}, $sub), ", " unless $j;
                     }
                     next unless exists($multis->{$othertag});
                     for my $sub ( sort keys %{$multis->{$othertag}} ) {
-                        next if $m->first_only($rec->{tags}[$idx]{tag}, $sub) and ($k > 1);
-                        for my $value ( @{$rec->{tags}[$idx]{multi}{$sub}} ) {
+                        next if $m->first_only($rec->{tags}[$tag_idx]{tag}, $sub) and ($k > 1);
+                        for my $value ( @{$rec->{tags}[$tag_idx]{multi}{$sub}} ) {
                             my $fh = $MULTIFILE{"$othertag$sub"};
-                            print $fh join("\t", $rec->{egid}, $j, $value), "\n";
+                            my $clean_value = $value;
+                            $clean_value =~ s/[\r\n\t]//g;
+                            print $fh normalize_output(join("\t", $rec->{egid}, $j, $clean_value)), "\n";
                         }
                     }
                 }
@@ -113,7 +152,7 @@ sub extract_holdings {
 
             # and dump it
             print HOLDINGS "\n" unless $j;
-            print HOLDINGS join("\t", @out);
+            print HOLDINGS normalize_output(join("\t", @out));
             print HOLDINGS "\n";
             $j++;
         }
@@ -156,7 +195,7 @@ sub dump_sample_detail {
         for my $subkey (sort keys %{ $tags->{$tag} }) {
             my $sub = $tags->{$tag}{$subkey};
             print "|| $subkey | ", $sub->{value}, " | ", 
-              $sub->{count}, "/", $sub->{tcnt}, " |  ||\n";
+              $sub->{count}, "/", $sub->{tcnt}, " | ", ($sub->{count} > $sub->{tcnt}) ? "MULTI" : "", " ||\n";
         }
         print "\n";
     }
@@ -170,6 +209,8 @@ sub dump_sample_detail {
         print "\n";
     }
     select STDOUT;
+    print "Saved results as ", ($c->{prefix} . "-HOLDINGS-DETAIL.txt"), " and ",
+        ($c->{prefix} . "-HOLDINGS-SUBCOUNTS.txt"), "\n";
 }
 
 sub dump_sample_overview {
@@ -195,7 +236,7 @@ sub dump_sample_overview {
         print " (", sprintf("%03d", int($tags->{ $tagsbycount[$i] } / $count * 100)), "%)\n";
     }
     select STDOUT;
-    print "\n";
+    print "Saved results as ", ($c->{prefix} . "-HOLDINGS-OVERVIEW.txt"), "\n";
     close SAMPLE;
 }
 
@@ -217,6 +258,7 @@ sub initialize {
                          'holdings|h=i',
                          'copyid|c=s',
                          'prefix|p=s',
+                         'disable-pg-normalization',
                          'version|v',
                          'help',
                        );
@@ -243,12 +285,18 @@ sub initialize {
     return $c;
 }
 
+sub normalize_output {
+    my $str = shift;
+    $str =~ s!\\!\\\\!g unless $c->{'disable-pg-normalization'};
+    return $str;
+}
+
 sub show_help {
     my ($msg) = @_;
     print "\nERROR - $msg\n" if $msg;
     print <<HELP;
 
-Usage is: extract_holdings -p PREFIX -m MARCFILE [ARGUMENTS]
+Usage is: extract_holdings --prefix PREFIX --marcfile MARCFILE [ARGUMENTS]
 
 REQUIRED ARGUMENTS
   --prefix   -p  Prefix string for output filenames
@@ -270,6 +318,10 @@ HOLDINGS EXTRACTION ARGUMENTS
                  used to extract holdings data from the input MARC file
   --holdings -h  Specifies actual holdings tag
   --copyid   -c  Specifies subfield of holdings with unique copy identifier
+  --disable-pg-normalization  By default, output is normalized so that a Postgres
+                              copy or \\copy can import the data without choking on
+                              backslashes; use this command-line option if
+                              output is not meant to be consumed by psql.
 
   All three of these must be given together.
 HELP