1 | ##########################################################################
|
---|
2 | #
|
---|
3 | # CSVFieldSeparator -- helper plugin that 'auto' works out what the
|
---|
4 | # comma-separated field character is
|
---|
5 | #
|
---|
6 | # A component of the Greenstone digital library software
|
---|
7 | # from the New Zealand Digital Library Project at the
|
---|
8 | # University of Waikato, New Zealand.
|
---|
9 | #
|
---|
10 | # Copyright (C) 2019 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful,
|
---|
18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | # GNU General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 | package CSVFieldSeparator;
|
---|
29 |
|
---|
30 | use PrintInfo;
|
---|
31 |
|
---|
32 | use strict;
|
---|
33 | no strict 'refs'; # make an exception so we can use variables as filehandles
|
---|
34 |
|
---|
35 | BEGIN {
|
---|
36 | @CSVFieldSeparator::ISA = ('PrintInfo');
|
---|
37 | }
|
---|
38 |
|
---|
39 | my $arguments =
|
---|
40 | [
|
---|
41 | { 'name' => "separate_char",
|
---|
42 | 'desc' => "{CSVFieldSeparator.separate_char}",
|
---|
43 | 'type' => "string",
|
---|
44 | 'deft' => "auto",
|
---|
45 | 'reqd' => "no" }
|
---|
46 | ];
|
---|
47 |
|
---|
48 | my $options = { 'name' => "CSVFieldSeparator",
|
---|
49 | 'desc' => "{CSVFieldSeparator.desc}",
|
---|
50 | 'abstract' => "yes",
|
---|
51 | 'inherits' => "yes",
|
---|
52 | 'args' => $arguments };
|
---|
53 |
|
---|
54 | sub new {
|
---|
55 | my ($class) = shift (@_);
|
---|
56 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
57 | push(@$pluginlist, $class);
|
---|
58 |
|
---|
59 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
60 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
61 |
|
---|
62 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
63 |
|
---|
64 | return bless $self, $class;
|
---|
65 |
|
---|
66 | }
|
---|
67 |
|
---|
68 |
|
---|
69 | sub resolve_auto
|
---|
70 | {
|
---|
71 | my ($self) = shift @_;
|
---|
72 | my ($line,$plugin_name,$outhandle,$verbosity) = @_;
|
---|
73 |
|
---|
74 |
|
---|
75 | # count number of char matches for common separates such as ',' ';' '\t' and '|'
|
---|
76 | my $comma_count = () = ($line =~ m/,/g);
|
---|
77 | my $separate_char = ",";
|
---|
78 | my $max_count = $comma_count;
|
---|
79 |
|
---|
80 | my $semicolon_count = () = ($line =~ m/\;/g);
|
---|
81 | if ($semicolon_count > $max_count) {
|
---|
82 | $separate_char = ";";
|
---|
83 | $max_count = $semicolon_count;
|
---|
84 | }
|
---|
85 |
|
---|
86 | my $tab_count = () = ($line =~ m/\t/g);
|
---|
87 | if ($tab_count > $max_count) {
|
---|
88 | $separate_char = "\t";
|
---|
89 | $max_count = $tab_count;
|
---|
90 | }
|
---|
91 |
|
---|
92 | my $pipe_count = () = ($line =~ m/\|/g);
|
---|
93 | if ($pipe_count > $max_count) {
|
---|
94 | $separate_char = "|";
|
---|
95 | $max_count = $pipe_count;
|
---|
96 | }
|
---|
97 |
|
---|
98 | if ($outhandle) {
|
---|
99 | print $outhandle "$plugin_name: Auto selecting '$separate_char' as -separate_char\n" if ($verbosity) > 1;
|
---|
100 | }
|
---|
101 |
|
---|
102 | return $separate_char;
|
---|
103 | }
|
---|
104 |
|
---|
105 | 1;
|
---|