1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
use strict;
use warnings;
use Test::More;
use_ok 'Catmandu::Importer::Text';
require_ok 'Catmandu::Importer::Text';
my $text = <<EOF;
Roses are red,
Violets are blue,
Sugar is sweet,
And so| are you.
EOF
sub text {
Catmandu::Importer::Text->new(file => \$text, @_)->to_array;
}
is_deeply text(),
[
{_id => 1, text => "Roses are red,"},
{_id => 2, text => "Violets are blue,"},
{_id => 3, text => "Sugar is sweet,"},
{_id => 4, text => "And so| are you."},
],
'simple text import';
is_deeply text(pattern => 'are'),
[
{_id => 1, text => "Roses are red,"},
{_id => 2, text => "Violets are blue,"},
{_id => 3, text => "And so| are you."},
],
'simple pattern match';
is_deeply text(pattern => '(\w+)(.).*\.$'),
[{_id => 1, match => ["And", " "]},], 'numbered capturing groups';
my $items = [
{_id => 1, match => {first => "Roses", second => "are"}},
{_id => 2, match => {first => "Violets", second => "are"}}
];
is_deeply text(pattern => '^(?<first>\w+) (?<second>are).*\,$'), $items,
'named capturing groups';
my $pattern = <<'PAT';
^(?<first> \w+) # first word
\ # space
(?<second> are ) # second word = 'are'
PAT
is_deeply text(pattern => $pattern), $items, 'multiline pattern';
is_deeply [map {$_->{text}} @{text(split => ' ')}],
[map {[split ' ', $_]} split "\n", $text], 'split by character';
is_deeply [map {$_->{text}} @{text(split => '|')}],
[map {[split '\\|', $_]} split "\n", $text],
'split by character (no regexp)';
is_deeply [map {$_->{text}} @{text(split => 'is|are')}],
[map {[split /is|are/, $_]} split "\n", $text], 'split by regexp';
is_deeply text(split => ' is | are ', pattern => '^And so. (.*)'),
[{_id => 1, text => ['And so|', 'you.'], match => ['are you.']}],
'split and pattern';
done_testing;
|
