blib/lib/Catmandu/Importer/Text.pm

filter: Statementstmt 100% 21 / 21 Branchbran 100% 4 / 4 Conditioncond n/a MC/DCmcdc n/a Subroutinesub 100% 7 / 7 Podpod 0.0% 0 / 1 totaltotal 96.9% 32 / 33 CC 3 SCAR 3.7
CC
3
Cov
100%
__ANON__
2.0
__ANON__
2.0
BEGIN
1.0
CRAP 1.4
« blib/lib/Catmandu/Fix/Inlineable.pm ↑ Summary blib/lib/Catmandu/Fix/Condition/SimpleAllTest.pm »
1 package Catmandu::Importer::Text;
2  
3 1 ▶use Catmandu::Sane;
Subroutine BEGIN: called CC=1 SCAR=0.0
4  
5 1 our $VERSION = '1.0201_02';
6  
7 1 ▶use Moo;
Subroutine BEGIN: called CC=1 SCAR=0.0
8 1 ▶use namespace::clean;
Subroutine BEGIN: called CC=1 SCAR=0.0
9  
10 1 with 'Catmandu::Importer';
11  
12 has pattern => (
13 is => 'ro',
14 coerce => sub {
15 5 ▶ $_[0] =~ /\n/m ? qr{$_[0]}x : qr{$_[0]};
Subroutine __ANON__: called CC=2 SCAR=6.9
Branch: 1 branch
BranchTrueFalseTotal
$_[0] =~ /\n/m ? : 1 4 5
16 },
17 1 );
18  
19 has split => (
20 is => 'ro',
21 coerce => sub {
22 4 ▶ length $_[0] == 1 ? quotemeta($_[0]) : qr{$_[0]};
Subroutine __ANON__: called CC=2 SCAR=6.9
Branch: 1 branch
BranchTrueFalseTotal
length $_[0] == 1 ? : 2 2 4
23 }
24 1 );
25  
26 sub generator {
27 9 ▶ my ($self) = @_;
Subroutine generator: called CC=1 SCAR=0.0
Pod undocumented
28 sub {
29 state $pattern = $self->pattern;
30 state $split = $self->split;
31 state $count = 0;
32 state $line;
33  
34 while (defined($line = $self->fh->getline)) {
35 chomp $line;
36 next if $pattern and $line !~ $pattern;
37  
38 my $data = {_id => ++$count};
39  
40 if (@+ < 2) { # no capturing groups
41 $data->{text} = $line;
42 }
43 elsif (%+) { # named capturing groups
44 $data->{match} = {%+};
45 }
46 else { # numbered capturing groups
47 1 ▶ no strict 'refs';
Subroutine BEGIN: called CC=1 SCAR=0.0
48 $data->{match} = [map {$$_} 1 .. @+ - 1];
49 }
50  
51 if ($split) {
52 $data->{text} = [split $split, $line];
53 }
54  
55 return $data;
56 }
57  
58 return;
59 9 };
60 }
61  
62 1 1;
63  
64 __END__
65  
66 =pod
67  
68 =head1 NAME
69  
70 Catmandu::Importer::Text - Package that imports textual data
71  
72 =head1 SYNOPSIS
73  
74 # From the command line
75  
76 # separate fields by whitespace sequences just like awk
77 catmandu convert Text --split '\s+'
78  
79 # import all lines starting with '#', omitting this character
80 catmandu convert Text --pattern '^#(.*)'
81  
82 # In a Perl script
83  
84 use Catmandu::Importer::Text;
85  
86 my $importer = Catmandu::Importer::text->new( file => "/foo/bar.txt" );
87  
88 # print all lines with line number
89 $importer->each(sub {
90 my $item = $_[0];
91 printf "%d: %s" , $item->{_id} , $item->{text};
92 });
93  
94 =head1 DESCRIPTION
95  
96 This package reads textual input line by line. Each line is
97 imported as item with line number in field C<_id> and text content in field
98 C<text>. Line separators are not included. Lines can further be split by
99 character or pattern and a regular expression can be specified to only import
100 selected lines and to translate pattern groups to fields.
101  
102 =head1 CONFIGURATION
103  
104 =over
105  
106 =item file
107  
108 Read input from a local file given by its path. Alternatively a scalar
109 reference can be passed to read from a string.
110  
111 =item fh
112  
113 Read input from an L<IO::Handle>. If not specified, L<Catmandu::Util::io> is used to
114 create the input stream from the C<file> argument or by using STDIN.
115  
116 =item encoding
117  
118 Binmode of the input stream C<fh>. Set to C<:utf8> by default.
119  
120 =item fix
121  
122 An ARRAY of one or more fixes or file scripts to be applied to imported items.
123  
124 =item split
125  
126 Single Character or regular expression (as string with a least two characters),
127 to split each line. Resulting parts are imported in field C<text> as array.
128  
129 =item pattern
130  
131 Regular expression, given as string, to only import matching lines.
132 Whitespaces in patterns are ignored or must be escaped if patterns consists of
133 multiple lines. If the pattern contains capturing groups, captured values are
134 imported in field C<match> instead of C<text>.
135  
136 For instance dates in C<YYYY-MM-DD> format can be imported as named fields with
137  
138 (?<year>\d\d\d\d)-(?<month>\d\d)-(?<day>\d\d)
139  
140 or as array with
141  
142 (\d\d\d\d)- # year
143 (\d\d)- # month
144 (\d\d) # day
145  
146 =back
147  
148 =head1 METHODS
149  
150 Every L<Catmandu::Importer> is a L<Catmandu::Iterable> with all its methods
151 inherited.
152  
153 =head1 SEE ALSO
154  
155 L<Catmandu::Exporter::Text>
156  
157 L<Catmandu::Fix::parse_text>
158  
159 Unix tools L<awk|https://en.wikipedia.org/wiki/AWK> and
160 L<sed|https://en.wikipedia.org/wiki/Sed>
161  
162 =cut
« blib/lib/Catmandu/Fix/Inlineable.pm ↑ Summary blib/lib/Catmandu/Fix/Condition/SimpleAllTest.pm »