1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # CSVPlugin.pm -- A plugin for files in comma-separated value format
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software
|
---|
6 | # from the New Zealand Digital Library Project at the
|
---|
7 | # University of Waikato, New Zealand.
|
---|
8 | #
|
---|
9 | # Copyright 2006 New Zealand Digital Library Project
|
---|
10 | #
|
---|
11 | # This program is free software; you can redistribute it and/or modify
|
---|
12 | # it under the terms of the GNU General Public License as published by
|
---|
13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
14 | # (at your option) any later version.
|
---|
15 | #
|
---|
16 | # This program is distributed in the hope that it will be useful,
|
---|
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | # GNU General Public License for more details.
|
---|
20 | #
|
---|
21 | # You should have received a copy of the GNU General Public License
|
---|
22 | # along with this program; if not, write to the Free Software
|
---|
23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | #
|
---|
25 | ###########################################################################
|
---|
26 |
|
---|
27 | package CSVPlugin;
|
---|
28 |
|
---|
29 |
|
---|
30 | use SplitTextFile;
|
---|
31 | use strict;
|
---|
32 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
33 |
|
---|
34 |
|
---|
35 | # CSVPlugin is a sub-class of SplitTextFile.
|
---|
36 | sub BEGIN {
|
---|
37 | @CSVPlugin::ISA = ('SplitTextFile');
|
---|
38 | }
|
---|
39 |
|
---|
40 |
|
---|
41 | my $arguments =
|
---|
42 | [ { 'name' => "process_exp",
|
---|
43 | 'desc' => "{BasePlugin.process_exp}",
|
---|
44 | 'type' => "regexp",
|
---|
45 | 'reqd' => "no",
|
---|
46 | 'deft' => &get_default_process_exp() },
|
---|
47 | { 'name' => "split_exp",
|
---|
48 | 'desc' => "{SplitTextFile.split_exp}",
|
---|
49 | 'type' => "regexp",
|
---|
50 | 'reqd' => "no",
|
---|
51 | 'deft' => &get_default_split_exp(),
|
---|
52 | 'hiddengli' => "yes" }
|
---|
53 | ];
|
---|
54 |
|
---|
55 |
|
---|
56 | my $options = { 'name' => "CSVPlugin",
|
---|
57 | 'desc' => "{CSVPlugin.desc}",
|
---|
58 | 'abstract' => "no",
|
---|
59 | 'inherits' => "yes",
|
---|
60 | 'explodes' => "yes",
|
---|
61 | 'args' => $arguments };
|
---|
62 |
|
---|
63 |
|
---|
64 | # This plugin processes files with the suffix ".csv"
|
---|
65 | sub get_default_process_exp {
|
---|
66 | return q^(?i)(\.csv)$^;
|
---|
67 | }
|
---|
68 |
|
---|
69 |
|
---|
70 | # This plugin splits the input text by line
|
---|
71 | sub get_default_split_exp {
|
---|
72 | return q^\r?\n^;
|
---|
73 | }
|
---|
74 |
|
---|
75 |
|
---|
76 | sub new
|
---|
77 | {
|
---|
78 | my ($class) = shift (@_);
|
---|
79 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
80 | push(@$pluginlist, $class);
|
---|
81 |
|
---|
82 | push(@{$hashArgOptLists->{"ArgList"}}, @{$arguments});
|
---|
83 | push(@{$hashArgOptLists->{"OptList"}}, $options);
|
---|
84 |
|
---|
85 | my $self = new SplitTextFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
86 |
|
---|
87 | return bless $self, $class;
|
---|
88 | }
|
---|
89 |
|
---|
90 |
|
---|
91 | sub read_file
|
---|
92 | {
|
---|
93 | my $self = shift (@_);
|
---|
94 | my ($filename, $encoding, $language, $textref) = @_;
|
---|
95 | my $outhandle = $self->{'outhandle'};
|
---|
96 |
|
---|
97 | # Read the CSV file content
|
---|
98 | open(FILE, $filename);
|
---|
99 | my $reader = new multiread();
|
---|
100 | $reader->set_handle('CSVPlugin::FILE');
|
---|
101 | $reader->set_encoding($encoding);
|
---|
102 | $reader->read_file($textref);
|
---|
103 | close(FILE);
|
---|
104 |
|
---|
105 | # Remove any blank lines so the data is split and processed properly
|
---|
106 | $$textref =~ s/\n(\s*)\n/\n/g;
|
---|
107 |
|
---|
108 | # The first line contains the metadata element names
|
---|
109 | $$textref =~ s/^(.*?)\r?\n//;
|
---|
110 | my @csv_file_fields = ();
|
---|
111 | my $csv_file_field_line = $1 . ","; # To make the regular expressions simpler
|
---|
112 | while ($csv_file_field_line ne "") {
|
---|
113 | # Handle quoted values
|
---|
114 | if ($csv_file_field_line =~ s/^\"(.*?)\"\,//) {
|
---|
115 | my $csv_file_field = $1;
|
---|
116 | $csv_file_field =~ s/ //g; # Remove any spaces from the field names
|
---|
117 | push(@csv_file_fields, $csv_file_field);
|
---|
118 | }
|
---|
119 | # Normal comma-separated case
|
---|
120 | elsif ($csv_file_field_line =~ s/^(.*?)\,//) {
|
---|
121 | my $csv_file_field = $1;
|
---|
122 | $csv_file_field =~ s/ //g; # Remove any spaces from the field names
|
---|
123 | push(@csv_file_fields, $csv_file_field);
|
---|
124 | }
|
---|
125 | # The line must be formatted incorrectly
|
---|
126 | else {
|
---|
127 | print STDERR "Error: Badly formatted CSV field line: $csv_file_field_line.\n";
|
---|
128 | last;
|
---|
129 | }
|
---|
130 | }
|
---|
131 | $self->{'csv_file_fields'} = \@csv_file_fields;
|
---|
132 | }
|
---|
133 |
|
---|
134 |
|
---|
135 | sub process
|
---|
136 | {
|
---|
137 | my $self = shift (@_);
|
---|
138 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
139 | my $outhandle = $self->{'outhandle'};
|
---|
140 |
|
---|
141 | my $section = $doc_obj->get_top_section();
|
---|
142 | my $csv_line = $$textref;
|
---|
143 | my @csv_file_fields = @{$self->{'csv_file_fields'}};
|
---|
144 |
|
---|
145 | # Add the raw line as the document text
|
---|
146 | $doc_obj->add_utf8_text($section, $csv_line);
|
---|
147 |
|
---|
148 | # Build a hash of metadata name to metadata value for this line
|
---|
149 | my $i = 0;
|
---|
150 | $csv_line .= ","; # To make the regular expressions simpler
|
---|
151 | while ($csv_line ne "") {
|
---|
152 | # Metadata values containing commas are quoted
|
---|
153 | if ($csv_line =~ s/^\"(.*?)\"\,//) {
|
---|
154 | # Only bother with non-empty values
|
---|
155 | if ($1 ne "" && defined($csv_file_fields[$i])) {
|
---|
156 | $doc_obj->add_utf8_metadata($section, $csv_file_fields[$i], $1);
|
---|
157 | }
|
---|
158 | }
|
---|
159 | # Normal comma-separated case
|
---|
160 | elsif ($csv_line =~ s/^(.*?)\,//) {
|
---|
161 | # Only bother with non-empty values
|
---|
162 | if ($1 ne "" && defined($csv_file_fields[$i])) {
|
---|
163 | $doc_obj->add_utf8_metadata($section, $csv_file_fields[$i], $1);
|
---|
164 | }
|
---|
165 | }
|
---|
166 | # The line must be formatted incorrectly
|
---|
167 | else {
|
---|
168 | print STDERR "Error: Badly formatted CSV line: $csv_line.\n";
|
---|
169 | last;
|
---|
170 | }
|
---|
171 |
|
---|
172 | $i++;
|
---|
173 | }
|
---|
174 |
|
---|
175 | # Record was processed successfully
|
---|
176 | return 1;
|
---|
177 | }
|
---|
178 |
|
---|
179 |
|
---|
180 | 1;
|
---|