line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Geo::Parser::Text; |
2
|
|
|
|
|
|
|
|
3
|
1
|
|
|
1
|
|
13119
|
use 5.006; |
|
1
|
|
|
|
|
3
|
|
4
|
1
|
|
|
1
|
|
3
|
use strict; |
|
1
|
|
|
|
|
1
|
|
|
1
|
|
|
|
|
19
|
|
5
|
1
|
|
|
1
|
|
2
|
use warnings; |
|
1
|
|
|
|
|
4
|
|
|
1
|
|
|
|
|
20
|
|
6
|
|
|
|
|
|
|
|
7
|
1
|
|
|
1
|
|
702
|
use XML::Simple; |
|
1
|
|
|
|
|
6034
|
|
|
1
|
|
|
|
|
5
|
|
8
|
1
|
|
|
1
|
|
649
|
use LWP::UserAgent; |
|
1
|
|
|
|
|
31262
|
|
|
1
|
|
|
|
|
27
|
|
9
|
1
|
|
|
1
|
|
6
|
use HTTP::Request; |
|
1
|
|
|
|
|
1
|
|
|
1
|
|
|
|
|
18
|
|
10
|
1
|
|
|
1
|
|
3
|
use URI; |
|
1
|
|
|
|
|
1
|
|
|
1
|
|
|
|
|
16
|
|
11
|
1
|
|
|
1
|
|
530
|
use Data::Dumper; |
|
1
|
|
|
|
|
4772
|
|
|
1
|
|
|
|
|
58
|
|
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
|
14
|
1
|
|
|
1
|
|
5
|
use constant DEBUG => 0; |
|
1
|
|
|
|
|
1
|
|
|
1
|
|
|
|
|
49
|
|
15
|
1
|
|
|
1
|
|
4
|
use constant GEO_HOST => q{http://geocode.xyz}; |
|
1
|
|
|
|
|
1
|
|
|
1
|
|
|
|
|
439
|
|
16
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
sub new { |
18
|
0
|
|
|
0
|
1
|
|
my $class = shift; |
19
|
|
|
|
|
|
|
|
20
|
0
|
|
|
|
|
|
my $self = { |
21
|
|
|
|
|
|
|
geo_host => shift |
22
|
|
|
|
|
|
|
}; |
23
|
|
|
|
|
|
|
|
24
|
0
|
|
|
|
|
|
bless ($self, $class); |
25
|
0
|
|
|
|
|
|
return $self; |
26
|
|
|
|
|
|
|
} |
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
sub geodata { |
29
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
30
|
0
|
0
|
|
|
|
|
$self->{geodata} = $_[0] if $_[0]; |
31
|
0
|
|
|
|
|
|
return $self->{geodata}; |
32
|
|
|
|
|
|
|
} |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
sub geoit { |
35
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
36
|
0
|
0
|
|
|
|
|
$self->{geoit} = $_[0] if $_[0]; |
37
|
0
|
|
|
|
|
|
return $self->{geoit}; |
38
|
|
|
|
|
|
|
} |
39
|
|
|
|
|
|
|
|
40
|
|
|
|
|
|
|
sub scantext { |
41
|
0
|
|
|
0
|
1
|
|
my $self = shift; |
42
|
0
|
0
|
|
|
|
|
$self->{scantext} = $_[0] if $_[0]; |
43
|
0
|
|
|
|
|
|
return $self->{scantext}; |
44
|
|
|
|
|
|
|
} |
45
|
|
|
|
|
|
|
|
46
|
|
|
|
|
|
|
sub locate { |
47
|
0
|
|
|
0
|
1
|
|
my $self = shift; |
48
|
0
|
0
|
|
|
|
|
$self->{locate} = $_[0] if $_[0]; |
49
|
0
|
|
|
|
|
|
return $self->{locate}; |
50
|
|
|
|
|
|
|
} |
51
|
|
|
|
|
|
|
sub geo_result { |
52
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
53
|
0
|
0
|
|
|
|
|
$self->{geo_result} = $_[0] if $_[0]; |
54
|
0
|
|
|
|
|
|
return $self->{geo_result}; |
55
|
|
|
|
|
|
|
} |
56
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
sub geocode { |
58
|
0
|
|
|
0
|
1
|
|
my $self = shift; |
59
|
|
|
|
|
|
|
|
60
|
0
|
|
|
|
|
|
my %form_values; |
61
|
0
|
|
|
|
|
|
foreach my $param (qw(scantext locate)) { |
62
|
0
|
|
|
|
|
|
$form_values{$param} = $self->$param; |
63
|
|
|
|
|
|
|
} |
64
|
0
|
|
|
|
|
|
$form_values{geoit} = 'XML'; |
65
|
|
|
|
|
|
|
|
66
|
0
|
|
|
|
|
|
warn Data::Dumper->Dump([\%form_values],['Form Values']) if DEBUG; |
67
|
|
|
|
|
|
|
|
68
|
0
|
|
|
|
|
|
$self->process_request(%form_values); |
69
|
|
|
|
|
|
|
|
70
|
0
|
|
|
|
|
|
my $geodata = $self->geodata; |
71
|
0
|
|
|
|
|
|
my @a = split(//,$geodata); |
72
|
0
|
|
|
|
|
|
my $geod = pop @a; |
73
|
0
|
|
|
|
|
|
$geod = '' . $geod; |
74
|
0
|
|
|
|
|
|
my $ref = XMLin($geod); |
75
|
0
|
|
|
|
|
|
warn Data::Dumper->Dump([$ref],['Response']) if DEBUG; |
76
|
0
|
|
|
|
|
|
$self->geo_result($ref); |
77
|
|
|
|
|
|
|
|
78
|
0
|
|
|
|
|
|
return $self->geo_result; |
79
|
|
|
|
|
|
|
} |
80
|
|
|
|
|
|
|
|
81
|
|
|
|
|
|
|
sub process_request { |
82
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
83
|
0
|
|
|
|
|
|
my %form_values = @_; |
84
|
0
|
0
|
|
|
|
|
$self->{geo_host} = GEO_HOST unless $self->{geo_host}; |
85
|
|
|
|
|
|
|
|
86
|
0
|
|
|
|
|
|
my $uri = URI->new; |
87
|
0
|
|
|
|
|
|
$uri->query_form(%form_values); |
88
|
0
|
|
|
|
|
|
my $ua = LWP::UserAgent->new; |
89
|
0
|
|
|
|
|
|
my $req = HTTP::Request->new(POST => $self->{geo_host}); |
90
|
0
|
|
|
|
|
|
$req->content_type('application/x-www-form-urlencoded'); |
91
|
0
|
|
|
|
|
|
$req->content($uri->query); |
92
|
|
|
|
|
|
|
|
93
|
0
|
|
|
|
|
|
my $res = $ua->request($req); |
94
|
0
|
|
|
|
|
|
my $result = $res->as_string; |
95
|
|
|
|
|
|
|
|
96
|
0
|
|
|
|
|
|
warn $result if DEBUG; |
97
|
|
|
|
|
|
|
|
98
|
0
|
|
|
|
|
|
my $geodata = $result; |
99
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
101
|
0
|
|
|
|
|
|
return $self->geodata($geodata); |
102
|
|
|
|
|
|
|
} |
103
|
|
|
|
|
|
|
|
104
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
|
106
|
|
|
|
|
|
|
=head1 NAME |
107
|
|
|
|
|
|
|
|
108
|
|
|
|
|
|
|
Geo::Parser::Text - Perl extension for parsing and geocoding locations from free form text. (See Geocode.xyz or Geolytica.com or addrs.xyz for coverage details) |
109
|
|
|
|
|
|
|
|
110
|
|
|
|
|
|
|
=head1 VERSION |
111
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
Version 0.03 |
113
|
|
|
|
|
|
|
|
114
|
|
|
|
|
|
|
=cut |
115
|
|
|
|
|
|
|
|
116
|
|
|
|
|
|
|
our $VERSION = '0.03'; |
117
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
=head1 SYNOPSIS |
120
|
|
|
|
|
|
|
|
121
|
|
|
|
|
|
|
use Geo::Parser::Text; |
122
|
|
|
|
|
|
|
|
123
|
|
|
|
|
|
|
# initialize with your host |
124
|
|
|
|
|
|
|
my $g = Geo::Parser::Text->new([geo_host]); |
125
|
|
|
|
|
|
|
|
126
|
|
|
|
|
|
|
# Scan text for locations... |
127
|
|
|
|
|
|
|
$g->scantext($text); |
128
|
|
|
|
|
|
|
|
129
|
|
|
|
|
|
|
# Geocode a single location... |
130
|
|
|
|
|
|
|
$g->locate($string); |
131
|
|
|
|
|
|
|
# |
132
|
|
|
|
|
|
|
if ($g->geocode) { |
133
|
|
|
|
|
|
|
my $hashref = $g->geocode; |
134
|
|
|
|
|
|
|
} |
135
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
# Example... |
137
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
use Geo::Parser::Text; |
139
|
|
|
|
|
|
|
use Data::Dumper; |
140
|
|
|
|
|
|
|
my $g = Geo::Parser::Text->new('http://geocode.xyz'); |
141
|
|
|
|
|
|
|
|
142
|
|
|
|
|
|
|
$g->scantext('The most important museums of Amsterdam are located on the Museumplein, located at the southwestern side of the Rijksmuseum.'); |
143
|
|
|
|
|
|
|
print Dumper $g->geocode; |
144
|
|
|
|
|
|
|
|
145
|
|
|
|
|
|
|
#or |
146
|
|
|
|
|
|
|
|
147
|
|
|
|
|
|
|
$g->locate('10 Downing St, London SW1A 2AA, United Kingdom'); |
148
|
|
|
|
|
|
|
print Dumper $g->geocode; |
149
|
|
|
|
|
|
|
|
150
|
|
|
|
|
|
|
|
151
|
|
|
|
|
|
|
|
152
|
|
|
|
|
|
|
=head1 DESCRIPTION |
153
|
|
|
|
|
|
|
|
154
|
|
|
|
|
|
|
This module provides a Perl frontend for the geocode.xyz API. It allows the programmer to extract locations containing street addresses, street intersections and city names along with their geocoded latitude,longitude from bodies of text such as microblogs or wikipedia entries. (It should work with any type of text, but dumping html text or paragraphs containing over 200 words, will slow down the response considerably. If you need faster parsing grab the geocode.xyz server image on the AWS, and run it on a faster server (it is currenly running on a micro instance and is shared as a free public API without any throttling or rate limiting in place.) |
155
|
|
|
|
|
|
|
If you run your own instance, make sure to pass the instance ip address or domain name at invocation eg, Geo::Parser::Text->new($server). For North American locations use geolytica.com, and for Australia and New Zealand use addrs.xyz |
156
|
|
|
|
|
|
|
|
157
|
|
|
|
|
|
|
The api also geocodes single locations (returning the location matched with the highest probability from a string of text. If you pass a latitude,longitude pair, it will reverse geocode that point) |
158
|
|
|
|
|
|
|
|
159
|
|
|
|
|
|
|
For explanation on the API responses see http://geocode.xyz/api |
160
|
|
|
|
|
|
|
|
161
|
|
|
|
|
|
|
=head2 METHODS |
162
|
|
|
|
|
|
|
|
163
|
|
|
|
|
|
|
=head2 new ( host => 'geocode.xyz'); |
164
|
|
|
|
|
|
|
|
165
|
|
|
|
|
|
|
Initialize with the default server. geocode.xyz for Europe, geocoder.ca for North America, addrs.xyz for Australia and New Zealand. |
166
|
|
|
|
|
|
|
|
167
|
|
|
|
|
|
|
=item scantext($text) |
168
|
|
|
|
|
|
|
|
169
|
|
|
|
|
|
|
Set the text to be scanned. |
170
|
|
|
|
|
|
|
|
171
|
|
|
|
|
|
|
=item locate($string) |
172
|
|
|
|
|
|
|
|
173
|
|
|
|
|
|
|
Set the string to be geocoded. ($string may contain an address, city name, post code, for forward geocoding; or latitude,longitude pair for reverse geocoding) |
174
|
|
|
|
|
|
|
|
175
|
|
|
|
|
|
|
=item geocode() |
176
|
|
|
|
|
|
|
|
177
|
|
|
|
|
|
|
Send the text/string to geocode.xyz and return the hash reference with the response. |
178
|
|
|
|
|
|
|
You are required to set either the scantext or locate method before calling geocode(). |
179
|
|
|
|
|
|
|
|
180
|
|
|
|
|
|
|
|
181
|
|
|
|
|
|
|
=head1 EXPORT |
182
|
|
|
|
|
|
|
|
183
|
|
|
|
|
|
|
None by default. |
184
|
|
|
|
|
|
|
|
185
|
|
|
|
|
|
|
|
186
|
|
|
|
|
|
|
|
187
|
|
|
|
|
|
|
=head1 REQUIREMENTS |
188
|
|
|
|
|
|
|
|
189
|
|
|
|
|
|
|
XML::Simple, |
190
|
|
|
|
|
|
|
LWP::UserAgent, |
191
|
|
|
|
|
|
|
HTTP::Request, |
192
|
|
|
|
|
|
|
URI |
193
|
|
|
|
|
|
|
|
194
|
|
|
|
|
|
|
=head1 AUTHOR |
195
|
|
|
|
|
|
|
|
196
|
|
|
|
|
|
|
Ervin Ruci, C<< >> |
197
|
|
|
|
|
|
|
|
198
|
|
|
|
|
|
|
=head1 BUGS |
199
|
|
|
|
|
|
|
|
200
|
|
|
|
|
|
|
Please report any bugs or feature requests to C, or through |
201
|
|
|
|
|
|
|
the web interface at L. I will be notified, and then you'll |
202
|
|
|
|
|
|
|
automatically be notified of progress on your bug as I make changes. |
203
|
|
|
|
|
|
|
|
204
|
|
|
|
|
|
|
|
205
|
|
|
|
|
|
|
|
206
|
|
|
|
|
|
|
|
207
|
|
|
|
|
|
|
=head1 SUPPORT |
208
|
|
|
|
|
|
|
|
209
|
|
|
|
|
|
|
You can find documentation for this module with the perldoc command. |
210
|
|
|
|
|
|
|
|
211
|
|
|
|
|
|
|
perldoc Geo::Parser::Text |
212
|
|
|
|
|
|
|
|
213
|
|
|
|
|
|
|
|
214
|
|
|
|
|
|
|
You can also look for information at: |
215
|
|
|
|
|
|
|
|
216
|
|
|
|
|
|
|
=over 4 |
217
|
|
|
|
|
|
|
|
218
|
|
|
|
|
|
|
=item * RT: CPAN's request tracker (report bugs here) |
219
|
|
|
|
|
|
|
|
220
|
|
|
|
|
|
|
L |
221
|
|
|
|
|
|
|
|
222
|
|
|
|
|
|
|
=item * AnnoCPAN: Annotated CPAN documentation |
223
|
|
|
|
|
|
|
|
224
|
|
|
|
|
|
|
L |
225
|
|
|
|
|
|
|
|
226
|
|
|
|
|
|
|
=item * CPAN Ratings |
227
|
|
|
|
|
|
|
|
228
|
|
|
|
|
|
|
L |
229
|
|
|
|
|
|
|
|
230
|
|
|
|
|
|
|
=item * Search CPAN |
231
|
|
|
|
|
|
|
|
232
|
|
|
|
|
|
|
L |
233
|
|
|
|
|
|
|
|
234
|
|
|
|
|
|
|
=back |
235
|
|
|
|
|
|
|
|
236
|
|
|
|
|
|
|
|
237
|
|
|
|
|
|
|
=head1 ACKNOWLEDGEMENTS |
238
|
|
|
|
|
|
|
|
239
|
|
|
|
|
|
|
|
240
|
|
|
|
|
|
|
=head1 LICENSE AND COPYRIGHT |
241
|
|
|
|
|
|
|
|
242
|
|
|
|
|
|
|
Copyright 2016 Ervin Ruci. |
243
|
|
|
|
|
|
|
|
244
|
|
|
|
|
|
|
This program is free software; you can redistribute it and/or modify it |
245
|
|
|
|
|
|
|
under the terms of the the Artistic License (2.0). You may obtain a |
246
|
|
|
|
|
|
|
copy of the full license at: |
247
|
|
|
|
|
|
|
|
248
|
|
|
|
|
|
|
L |
249
|
|
|
|
|
|
|
|
250
|
|
|
|
|
|
|
Any use, modification, and distribution of the Standard or Modified |
251
|
|
|
|
|
|
|
Versions is governed by this Artistic License. By using, modifying or |
252
|
|
|
|
|
|
|
distributing the Package, you accept this license. Do not use, modify, |
253
|
|
|
|
|
|
|
or distribute the Package, if you do not accept this license. |
254
|
|
|
|
|
|
|
|
255
|
|
|
|
|
|
|
If your Modified Version has been derived from a Modified Version made |
256
|
|
|
|
|
|
|
by someone other than you, you are nevertheless required to ensure that |
257
|
|
|
|
|
|
|
your Modified Version complies with the requirements of this license. |
258
|
|
|
|
|
|
|
|
259
|
|
|
|
|
|
|
This license does not grant you the right to use any trademark, service |
260
|
|
|
|
|
|
|
mark, tradename, or logo of the Copyright Holder. |
261
|
|
|
|
|
|
|
|
262
|
|
|
|
|
|
|
This license includes the non-exclusive, worldwide, free-of-charge |
263
|
|
|
|
|
|
|
patent license to make, have made, use, offer to sell, sell, import and |
264
|
|
|
|
|
|
|
otherwise transfer the Package with respect to any patent claims |
265
|
|
|
|
|
|
|
licensable by the Copyright Holder that are necessarily infringed by the |
266
|
|
|
|
|
|
|
Package. If you institute patent litigation (including a cross-claim or |
267
|
|
|
|
|
|
|
counterclaim) against any party alleging that the Package constitutes |
268
|
|
|
|
|
|
|
direct or contributory patent infringement, then this Artistic License |
269
|
|
|
|
|
|
|
to you shall terminate on the date that such litigation is filed. |
270
|
|
|
|
|
|
|
|
271
|
|
|
|
|
|
|
Disclaimer of Warranty: THE PACKAGE IS PROVIDED BY THE COPYRIGHT HOLDER |
272
|
|
|
|
|
|
|
AND CONTRIBUTORS "AS IS' AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES. |
273
|
|
|
|
|
|
|
THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR |
274
|
|
|
|
|
|
|
PURPOSE, OR NON-INFRINGEMENT ARE DISCLAIMED TO THE EXTENT PERMITTED BY |
275
|
|
|
|
|
|
|
YOUR LOCAL LAW. UNLESS REQUIRED BY LAW, NO COPYRIGHT HOLDER OR |
276
|
|
|
|
|
|
|
CONTRIBUTOR WILL BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, OR |
277
|
|
|
|
|
|
|
CONSEQUENTIAL DAMAGES ARISING IN ANY WAY OUT OF THE USE OF THE PACKAGE, |
278
|
|
|
|
|
|
|
EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
279
|
|
|
|
|
|
|
|
280
|
|
|
|
|
|
|
|
281
|
|
|
|
|
|
|
=head1 SEE ALSO |
282
|
|
|
|
|
|
|
|
283
|
|
|
|
|
|
|
Geo::Coder::Canada |
284
|
|
|
|
|
|
|
Geo::Parse::OSM |
285
|
|
|
|
|
|
|
Text::NLP |
286
|
|
|
|
|
|
|
=cut |
287
|
|
|
|
|
|
|
|
288
|
|
|
|
|
|
|
1; # End of Geo::Parser::Text |