X-Git-Url: http://git.equinoxoli.org/?p=migration-tools.git;a=blobdiff_plain;f=unicorn%2Funicorn_to_tsv.pl;h=a6cdf475229b736110fb78da2f7e9b99e0232491;hp=3af493f56667efdf18eda321502c74efd59174a2;hb=9de57ed3344ac49d97437f9f13362bb7ba1bd64b;hpb=3021cf9f0f0e23e6c003802e2425273618f56087

diff --git a/unicorn/unicorn_to_tsv.pl b/unicorn/unicorn_to_tsv.pl
index 3af493f..a6cdf47 100755
--- a/unicorn/unicorn_to_tsv.pl
+++ b/unicorn/unicorn_to_tsv.pl
@@ -1,5 +1,21 @@
 #!/usr/bin/perl -w
 
+# 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.
+
 # Converts a Unicorn users.data, bill.data, or charge.data file to a tab-separated file.
 # 2009-08-10 Ben Ostrowsky <ben@esilibrary.com>
 
@@ -21,7 +37,7 @@ while (<>) {
 		$line = 0;
 		$serial++;
 		$section = ''; # just in case this didn't get reset in the previous record
-		# print STDERR "Processing record $serial.\n";
+		print STDERR "Processing record $serial.\n";
 		next;
 	}
 
@@ -36,7 +52,7 @@ while (<>) {
 
 	# Is this line the beginning of a block of data (typically an address or a note)?
 	if ( /^\.(.*?)_BEGIN.$/ ) {
-		# print STDERR "I think this might be the beginning of a beautiful " . $1 . ".\n";
+		print STDERR "I think this might be the beginning of a beautiful " . $1 . ".\n";
 		$section = "$1.";
 		next;
 	}
@@ -46,14 +62,14 @@ while (<>) {
 		if ("$1." ne $section) {
 			print STDERR "Error in record $serial, line $line (input line $.): got an end-of-$1 but I thought I was in a $section block!\n";
 		}
-		# print STDERR "It's been fun, guys, but... this is the end of the " . $1 . ".\n";
+		print STDERR "It's been fun, guys, but... this is the end of the " . $1 . ".\n";
 		$section = '';
 		next;
 	}
 
 	# Looks like we've got some actual data!  Let's store it.
 	# FIXME: For large batches of data, we may run out of memory and should store this on disk.
-	if ( /^\.([A-Z]*?).\s+(\|a)?(.*)$/ ) {
+	if ( /^\.([A-Z0-9_\/]+?)\.\s+(\|a)?(.*)$/ ) {
 
 		# Build the name of this field (taking note of whether we're in a named section of data)
 		$field = '';
@@ -68,7 +84,7 @@ while (<>) {
 		# Now we can actually store this line of data!
 		$records[$serial]{$field} = $3;		
 
-		# print STDERR "Data extracted: \$records[$serial]{'$field'} = '$3'\n";
+		print STDERR "Data extracted: \$records[$serial]{'$field'} = '$3'\n";
 
 		next;
 	}	
@@ -77,7 +93,7 @@ while (<>) {
 	else {
 		chomp($_);
 		$records[$serial]{$field} .= ' ' . $_;
-		# print STDERR "Appended data to previous field. \$records[$serial]{'$field'} is now '" . $records[$serial]{$field} . "'.\n";
+		print STDERR "Appended data to previous field. \$records[$serial]{'$field'} is now '" . $records[$serial]{$field} . "'.\n";
 	}
 
 }