fixed word error that resulted from copy and paste

[migration-tools.git] / extract_holdings

diff --git a/extract_holdings b/extract_holdings
index db10ded..028378d 100755 (executable)
--- 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;
 
@@ -36,15 +53,17 @@ sub extract_holdings {
 
     print "Writing holdings to output file(s)...\n";
     # open main holdings file
-    open HOLDINGS, '>', ($c->{prefix} . "-HOLDINGS.pg");
+    open HOLDINGS, '>', ($c->{prefix} . "-" . $c->{suffix} . ".pg");
     # create multi files
     my $multis = $m->get_multis;
     my %MULTIFILE = ();
     for my $t ( keys %{$multis} ) {
         for my $s ( keys %{$multis->{$t}}) 
-          { open my $fh, ">", ($c->{prefix} . "-HOLDINGS-MULT-$t$s.pg"); $MULTIFILE{"$t$s"} = $fh }
+          { open my $fh, ">", ($c->{prefix} . "-" . $c->{suffix} . "-MULT-$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";
               }
             }
 
@@ -85,6 +106,22 @@ 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})) {
@@ -105,7 +142,9 @@ sub extract_holdings {
                         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 normalize_output(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";
                         }
                     }
                 }
@@ -149,19 +188,19 @@ sub dump_sample_detail {
     my $count = $s->{data}{rcnt};
     my $scnt  = $s->{data}{scnt};
 
-    open DETAIL, '>', ($c->{prefix} . "-HOLDINGS-DETAIL.txt");
+    open DETAIL, '>', ($c->{prefix} . "-" . $c->{suffix} . "-DETAIL.txt");
     select DETAIL;
     for my $tag (sort keys %{ $tags }) {
         print ">>>>> TAG $tag\n\n";
         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} > $sub->{tcnt}) ? "MULTI" : "", " ||\n";
         }
         print "\n";
     }
     close DETAIL;
-    open SCOUNT, '>', ($c->{prefix} . "-HOLDINGS-SUBCOUNTS.txt");
+    open SCOUNT, '>', ($c->{prefix} . "-" . $c->{suffix} . "-SUBCOUNTS.txt");
     select SCOUNT;
     for my $tag (sort keys %{ $scnt }) {
         print ">>>>> TAG $tag\n\n";
@@ -170,6 +209,8 @@ sub dump_sample_detail {
         print "\n";
     }
     select STDOUT;
+    print "Saved results as ", ($c->{prefix} . "-" . $c->{suffix} . "-DETAIL.txt"), " and ",
+        ($c->{prefix} . "-" . $c->{suffix} . "-SUBCOUNTS.txt"), "\n";
 }
 
 sub dump_sample_overview {
@@ -180,7 +221,7 @@ sub dump_sample_overview {
     my @tagsbyname  = sort keys %{$tags};
     my @tagsbycount = reverse sort { $tags->{$a} <=> $tags->{$b} } keys %{$tags};
 
-    open SAMPLE, '>', ($c->{prefix} . "-HOLDINGS-OVERVIEW.txt");
+    open SAMPLE, '>', ($c->{prefix} . "-" . $c->{suffix} . "-OVERVIEW.txt");
     select SAMPLE;
     print "SAMPLE REPORT FOR ", $c->{prefix},": $count records\n\n";
     print "FOUND TAGS (BY TAG)           FOUND TAGS (BY COUNT)\n";
@@ -195,7 +236,7 @@ sub dump_sample_overview {
         print " (", sprintf("%03d", int($tags->{ $tagsbycount[$i] } / $count * 100)), "%)\n";
     }
     select STDOUT;
-    print "\n";
+    print "Saved results as ", ($c->{prefix} . "-" . $c->{suffix} . "-OVERVIEW.txt"), "\n";
     close SAMPLE;
 }
 
@@ -217,6 +258,7 @@ sub initialize {
                          'holdings|h=i',
                          'copyid|c=s',
                          'prefix|p=s',
+                         'suffix|o=s',
                          'disable-pg-normalization',
                          'version|v',
                          'help',
@@ -229,6 +271,9 @@ sub initialize {
       if ($c->{map} and !($c->{holdings} and $c->{copyid}));
     show_version() if $c->{version};
 
+    if (! $c->{suffix}) {
+        $c->{suffix} = 'HOLDINGS';
+    }
     if ($c->{prefix} and !$c->{marcfile}) {
         $c->{marcfile} = $c->{prefix} . ".clean.marc.xml";
     }
@@ -259,6 +304,7 @@ Usage is: extract_holdings --prefix PREFIX --marcfile MARCFILE [ARGUMENTS]
 
 REQUIRED ARGUMENTS
   --prefix   -p  Prefix string for output filenames
+  --suffix   -o  Suffix string for output filenames (defaults to HOLDINGS)
   --marcfile     MARCXML to use as source data
                  Defaults to 'PREFIX.clean.marc.xml'