3 # Copyright 2009-2012, Equinox Software, Inc.
5 # This program is free software; you can redistribute it and/or
6 # modify it under the terms of the GNU General Public License
7 # as published by the Free Software Foundation; either version 2
8 # of the License, or (at your option) any later version.
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
15 # You should have received a copy of the GNU General Public License
16 # along with this program; if not, write to the Free Software
17 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 # Converts a Unicorn users.data, bill.data, or charge.data file to a tab-separated file.
20 # 2009-08-10 Ben Ostrowsky <ben@esilibrary.com>
33 # print STDERR "Loaded this line: " . $_;
35 # Is this the start of a new record?
36 if ( /^... DOCUMENT BOUNDARY ...$/ ) {
39 $section = ''; # just in case this didn't get reset in the previous record
40 print STDERR "Processing record $serial.\n";
44 # Is this a FORM= line?
46 $records[$serial]{'l_form'} = $1;
50 # If this isn't the start of the new record, it's a new line in the present record.
53 # Is this line the beginning of a block of data (typically an address or a note)?
54 if ( /^\.(.*?)_BEGIN.$/ ) {
55 print STDERR "I think this might be the beginning of a beautiful " . $1 . ".\n";
60 # Is this line the beginning of a block of data (typically an address or a note)?
61 if ( /^\.(.*?)_END.$/ ) {
62 if ("$1." ne $section) {
63 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";
65 print STDERR "It's been fun, guys, but... this is the end of the " . $1 . ".\n";
70 # Looks like we've got some actual data! Let's store it.
71 # FIXME: For large batches of data, we may run out of memory and should store this on disk.
72 if ( /^\.(.*?).\s+(\|a)?(.*)$/ ) {
74 # Build the name of this field (taking note of whether we're in a named section of data)
81 # Store the field as a key of an array. If it already exists, oh well, now it still exists.
82 $unique_fields{$field} = 1;
84 # Now we can actually store this line of data!
85 $records[$serial]{$field} = $3;
87 print STDERR "Data extracted: \$records[$serial]{'$field'} = '$3'\n";
92 # This is the continuation of the previous line.
95 $records[$serial]{$field} .= ' ' . $_;
96 print STDERR "Appended data to previous field. \$records[$serial]{'$field'} is now '" . $records[$serial]{$field} . "'.\n";
101 print STDERR "Loaded " . scalar(@records) . " records.\n";
104 # Print a header line
106 @sorted_fields = sort keys %unique_fields;
107 foreach $i (@sorted_fields) {
114 for (my $u = 0; $u < @records; $u++) {
116 foreach $f (@sorted_fields) {
117 if (defined $records[$u]{$f}) {
118 print $records[$u]{$f};
125 print STDERR "Wrote " . scalar(@records) . " records.\n";
126 # uh-bdee-uh-bdee-uh-bdee-uh- THAT'S ALL, FOLKS