[16025] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # EmailAddressExtractor - helper plugin that extracts email addresses from text
|
---|
| 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 (C) 2008 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 |
|
---|
[15867] | 27 | package EmailAddressExtractor;
|
---|
| 28 |
|
---|
| 29 | use PrintInfo;
|
---|
[15887] | 30 | use strict;
|
---|
[15867] | 31 |
|
---|
[25797] | 32 | use gsprintf 'gsprintf';
|
---|
| 33 |
|
---|
[15867] | 34 | BEGIN {
|
---|
| 35 | @EmailAddressExtractor::ISA = ('PrintInfo');
|
---|
| 36 | }
|
---|
| 37 |
|
---|
| 38 | my $arguments = [
|
---|
| 39 | { 'name' => "extract_email",
|
---|
| 40 | 'desc' => "{EmailAddressExtractor.extract_email}",
|
---|
| 41 | 'type' => "flag",
|
---|
| 42 | 'reqd' => "no" },
|
---|
| 43 | { 'name' => "new_extract_email",
|
---|
| 44 | 'desc' => "",
|
---|
| 45 | 'type' => "flag",
|
---|
| 46 | 'reqd' => "no",
|
---|
| 47 | 'hiddengli' => "yes" }
|
---|
| 48 | ];
|
---|
| 49 |
|
---|
| 50 | my $options = { 'name' => "EmailAddressExtractor",
|
---|
| 51 | 'desc' => "{EmailAddressExtractor.desc}",
|
---|
| 52 | 'abstract' => "yes",
|
---|
| 53 | 'inherits' => "yes",
|
---|
| 54 | 'args' => $arguments };
|
---|
| 55 |
|
---|
| 56 |
|
---|
| 57 | sub new {
|
---|
| 58 | my ($class) = shift (@_);
|
---|
| 59 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
| 60 | push(@$pluginlist, $class);
|
---|
| 61 |
|
---|
| 62 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
| 63 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
| 64 |
|
---|
[15881] | 65 | my $self = new PrintInfo($pluginlist, $inputargs, $hashArgOptLists, 1);
|
---|
[15867] | 66 |
|
---|
| 67 | return bless $self, $class;
|
---|
| 68 |
|
---|
| 69 | }
|
---|
| 70 |
|
---|
| 71 | # extract metadata
|
---|
| 72 | sub extract_email_metadata {
|
---|
| 73 |
|
---|
| 74 | my $self = shift (@_);
|
---|
| 75 | my ($doc_obj) = @_;
|
---|
| 76 |
|
---|
| 77 | if ($self->{'extract_email'}) {
|
---|
| 78 | my $thissection = $doc_obj->get_top_section();
|
---|
| 79 | while (defined $thissection) {
|
---|
| 80 | my $text = $doc_obj->get_text($thissection);
|
---|
| 81 | $self->extract_email (\$text, $doc_obj, $thissection) if $text =~ /./;
|
---|
| 82 | $thissection = $doc_obj->get_next_section ($thissection);
|
---|
| 83 | }
|
---|
| 84 | }
|
---|
| 85 |
|
---|
| 86 | }
|
---|
| 87 |
|
---|
| 88 | sub extract_email {
|
---|
| 89 | my $self = shift (@_);
|
---|
| 90 | my ($textref, $doc_obj, $thissection) = @_;
|
---|
| 91 | my $outhandle = $self->{'outhandle'};
|
---|
| 92 |
|
---|
[16013] | 93 | gsprintf($outhandle, " {EmailAddressExtractor.extracting_emails}...\n")
|
---|
[15867] | 94 | if ($self->{'verbosity'} > 2);
|
---|
| 95 |
|
---|
| 96 | my @email = ($$textref =~ m/([-a-z0-9\.@+_=]+@(?:[-a-z0-9]+\.)+(?:com|org|edu|mil|int|net|[a-z][a-z]))/g);
|
---|
| 97 | @email = sort @email;
|
---|
| 98 |
|
---|
| 99 | # if($self->{"new_extract_email"} == 0)
|
---|
| 100 | # {
|
---|
| 101 | # my @email2 = ();
|
---|
| 102 | # foreach my $address (@email)
|
---|
| 103 | # {
|
---|
| 104 | # if (!(join(" ",@email2) =~ m/(^| )$address( |$)/ ))
|
---|
| 105 | # {
|
---|
| 106 | # push @email2, $address;
|
---|
[19541] | 107 | # $doc_obj->add_utf8_metadata ($thissection, "EmailAddress", $address);
|
---|
[15867] | 108 | # # print $outhandle " extracting $address\n"
|
---|
[16013] | 109 | # &gsprintf($outhandle, " {AutoExtractMetadata.extracting} $address\n")
|
---|
[15867] | 110 | # if ($self->{'verbosity'} > 3);
|
---|
| 111 | # }
|
---|
| 112 | # }
|
---|
| 113 | # }
|
---|
| 114 | # else
|
---|
| 115 | # {
|
---|
| 116 | my $hashExistMail = {};
|
---|
| 117 | foreach my $address (@email) {
|
---|
| 118 | if (!(defined $hashExistMail->{$address}))
|
---|
| 119 | {
|
---|
| 120 | $hashExistMail->{$address} = 1;
|
---|
[19541] | 121 | $doc_obj->add_utf8_metadata ($thissection, "EmailAddress", $address);
|
---|
[16013] | 122 | gsprintf($outhandle, " {AutoExtractMetadata.extracting} $address\n")
|
---|
[15867] | 123 | if ($self->{'verbosity'} > 3);
|
---|
| 124 | }
|
---|
| 125 | }
|
---|
[16013] | 126 | gsprintf($outhandle, " {EmailAddressExtractor.done_email_extract}\n")
|
---|
[15867] | 127 | if ($self->{'verbosity'} > 2);
|
---|
| 128 | }
|
---|
| 129 |
|
---|
| 130 |
|
---|
| 131 | 1;
|
---|