[32812] | 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 | [
|
---|
[32817] | 41 | { 'name' => "csv_field_separator",
|
---|
| 42 | 'desc' => "{CSVFieldSeparator.csv_field_separator}",
|
---|
[32812] | 43 | 'type' => "string",
|
---|
| 44 | 'deft' => "auto",
|
---|
[32818] | 45 | 'reqd' => "no" },
|
---|
| 46 | { 'name' => "metadata_value_separator",
|
---|
| 47 | 'desc' => "{CSVFieldSeparator.metadata_value_separator}",
|
---|
| 48 | 'type' => "string",
|
---|
| 49 | 'deft' => "",
|
---|
[32812] | 50 | 'reqd' => "no" }
|
---|
| 51 | ];
|
---|
| 52 |
|
---|
| 53 | my $options = { 'name' => "CSVFieldSeparator",
|
---|
| 54 | 'desc' => "{CSVFieldSeparator.desc}",
|
---|
| 55 | 'abstract' => "yes",
|
---|
| 56 | 'inherits' => "yes",
|
---|
| 57 | 'args' => $arguments };
|
---|
| 58 |
|
---|
| 59 | sub new {
|
---|
| 60 | my ($class) = shift (@_);
|
---|
| 61 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 62 | push(@$pluginlist, $class);
|
---|
| 63 |
|
---|
| 64 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 65 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
| 66 |
|
---|
| 67 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
| 68 |
|
---|
| 69 | return bless $self, $class;
|
---|
| 70 |
|
---|
| 71 | }
|
---|
| 72 |
|
---|
| 73 |
|
---|
| 74 | sub resolve_auto
|
---|
| 75 | {
|
---|
| 76 | my ($self) = shift @_;
|
---|
[33020] | 77 | my ($line,$plugin_name) = @_;
|
---|
[32812] | 78 |
|
---|
[33020] | 79 | my $outhandle = $self->{'outhandle'};
|
---|
| 80 | my $verbosity = $self->{'verbosity'};
|
---|
[32812] | 81 |
|
---|
| 82 | # count number of char matches for common separates such as ',' ';' '\t' and '|'
|
---|
| 83 | my $comma_count = () = ($line =~ m/,/g);
|
---|
| 84 | my $separate_char = ",";
|
---|
| 85 | my $max_count = $comma_count;
|
---|
| 86 |
|
---|
| 87 | my $semicolon_count = () = ($line =~ m/\;/g);
|
---|
| 88 | if ($semicolon_count > $max_count) {
|
---|
| 89 | $separate_char = ";";
|
---|
| 90 | $max_count = $semicolon_count;
|
---|
| 91 | }
|
---|
| 92 |
|
---|
| 93 | my $tab_count = () = ($line =~ m/\t/g);
|
---|
| 94 | if ($tab_count > $max_count) {
|
---|
| 95 | $separate_char = "\t";
|
---|
| 96 | $max_count = $tab_count;
|
---|
| 97 | }
|
---|
| 98 |
|
---|
| 99 | my $pipe_count = () = ($line =~ m/\|/g);
|
---|
| 100 | if ($pipe_count > $max_count) {
|
---|
| 101 | $separate_char = "|";
|
---|
| 102 | $max_count = $pipe_count;
|
---|
| 103 | }
|
---|
| 104 |
|
---|
| 105 | if ($outhandle) {
|
---|
| 106 | print $outhandle "$plugin_name: Auto selecting '$separate_char' as -separate_char\n" if ($verbosity) > 1;
|
---|
| 107 | }
|
---|
| 108 |
|
---|
| 109 | return $separate_char;
|
---|
| 110 | }
|
---|
| 111 |
|
---|
| 112 | 1;
|
---|