line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Text::NSR; |
2
|
|
|
|
|
|
|
|
3
|
2
|
|
|
2
|
|
139639
|
use warnings; |
|
2
|
|
|
|
|
13
|
|
|
2
|
|
|
|
|
60
|
|
4
|
2
|
|
|
2
|
|
10
|
use strict; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
35
|
|
5
|
|
|
|
|
|
|
|
6
|
2
|
|
|
2
|
|
1912
|
use Path::Tiny; |
|
2
|
|
|
|
|
30110
|
|
|
2
|
|
|
|
|
919
|
|
7
|
|
|
|
|
|
|
|
8
|
|
|
|
|
|
|
our $VERSION = '0.20'; |
9
|
|
|
|
|
|
|
|
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
sub new { |
12
|
3
|
|
|
3
|
1
|
7419
|
my ($class, %arg) = @_; |
13
|
|
|
|
|
|
|
my $self = bless { |
14
|
|
|
|
|
|
|
filepath => $arg{filepath}, |
15
|
|
|
|
|
|
|
fieldspec => $arg{fieldspec}, |
16
|
3
|
|
|
|
|
16
|
}, $class; |
17
|
|
|
|
|
|
|
|
18
|
3
|
50
|
|
|
|
14
|
die "Text::NSR: no filepath given!" if !$self->{filepath}; |
19
|
|
|
|
|
|
|
|
20
|
3
|
|
|
|
|
12
|
$self->{pathtiny} = path($self->{filepath}); |
21
|
|
|
|
|
|
|
|
22
|
3
|
50
|
|
|
|
150
|
die "Text::NSR: filepath '". $self->{filepath} ."' not found!" if ! $self->{pathtiny}->exists; |
23
|
|
|
|
|
|
|
|
24
|
3
|
|
|
|
|
150
|
return $self; |
25
|
|
|
|
|
|
|
} |
26
|
|
|
|
|
|
|
|
27
|
|
|
|
|
|
|
sub read { |
28
|
2
|
|
|
2
|
1
|
10
|
my $self = shift; |
29
|
|
|
|
|
|
|
|
30
|
2
|
|
|
|
|
7
|
my $lines = $self->{pathtiny}->slurp_utf8; |
31
|
|
|
|
|
|
|
|
32
|
2
|
|
|
|
|
1430
|
$lines =~ s/^\n+//; # delete leading newlines |
33
|
2
|
|
|
|
|
25
|
$lines =~ s/\n+$//; # delete trailing newlines |
34
|
|
|
|
|
|
|
|
35
|
2
|
|
|
|
|
23
|
my @arr = split(/\n\n/, $lines); |
36
|
|
|
|
|
|
|
|
37
|
2
|
|
|
|
|
4
|
my $newline = "\n"; |
38
|
2
|
|
|
|
|
4
|
my @records; |
39
|
|
|
|
|
|
|
# each "stanza" |
40
|
2
|
|
|
|
|
5
|
for my $elem (@arr){ |
41
|
16
|
|
|
|
|
40
|
my $cnt =()= $elem =~ /\n/g; # zero based; count newlines to see how many lines are in one "stanza" |
42
|
|
|
|
|
|
|
|
43
|
16
|
|
|
|
|
55
|
my @fieldvalues = split(/\n/, $elem); |
44
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
# replace literal newlines with newline chars |
46
|
16
|
|
|
|
|
22
|
for(@fieldvalues){ |
47
|
64
|
100
|
|
|
|
149
|
$_ =~ s/\\n/\n/ if index($_, '\n') != -1; |
48
|
|
|
|
|
|
|
} |
49
|
|
|
|
|
|
|
|
50
|
16
|
100
|
|
|
|
27
|
if($self->{fieldspec}){ |
51
|
|
|
|
|
|
|
# my %hash = map { $self->{fieldspec}->[$_] => $fieldvalues[$_] } (0 .. $#{$self->{fieldspec}}); |
52
|
8
|
|
|
|
|
10
|
my %hash; |
53
|
8
|
|
|
|
|
14
|
for(0 .. $cnt){ |
54
|
32
|
|
66
|
|
|
80
|
$hash{ $self->{fieldspec}->[$_] || $_ } = $fieldvalues[$_]; |
55
|
|
|
|
|
|
|
} |
56
|
8
|
|
|
|
|
24
|
push(@records, \%hash); |
57
|
|
|
|
|
|
|
}else{ |
58
|
8
|
|
|
|
|
15
|
push(@records, \@fieldvalues); |
59
|
|
|
|
|
|
|
} |
60
|
|
|
|
|
|
|
} |
61
|
|
|
|
|
|
|
|
62
|
2
|
|
|
|
|
4
|
$self->{records} = \@records; |
63
|
|
|
|
|
|
|
|
64
|
2
|
|
|
|
|
10
|
return \@records; |
65
|
|
|
|
|
|
|
} |
66
|
|
|
|
|
|
|
|
67
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
=pod |
69
|
|
|
|
|
|
|
|
70
|
|
|
|
|
|
|
=head1 NAME |
71
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
Text::NSR - Read "newline separated records" (NSR) structured text files |
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
=head1 SYNOPSIS |
75
|
|
|
|
|
|
|
|
76
|
|
|
|
|
|
|
use Text::NSR; |
77
|
|
|
|
|
|
|
my $nsr = Text::NSR->new( |
78
|
|
|
|
|
|
|
filepath => 't/test.nsr', |
79
|
|
|
|
|
|
|
fieldspec => ['f1','f2','f3','f4'] |
80
|
|
|
|
|
|
|
); |
81
|
|
|
|
|
|
|
my $records = $nsr->read(); |
82
|
|
|
|
|
|
|
|
83
|
|
|
|
|
|
|
=head1 DESCRIPTION |
84
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
There are a number of data exchange formats out there that strive to be structured in a way that is both, |
86
|
|
|
|
|
|
|
easily and intuitively editable by humans and reliably parseable by machines. This module here adds yet another |
87
|
|
|
|
|
|
|
structured file format, a file composed of "newline separated records". |
88
|
|
|
|
|
|
|
|
89
|
|
|
|
|
|
|
The guiding principal here is that each line in a file represents a value. And that multiple lines form a |
90
|
|
|
|
|
|
|
single record. Multiple records then are separated by one empty line. Exactly one empty line. A second empty |
91
|
|
|
|
|
|
|
line will be interpreted as the first line of the next record. The only exception to this rule are leading or |
92
|
|
|
|
|
|
|
trailing newlines on the "whole file" scope. They are considered "padding" and are dropped. |
93
|
|
|
|
|
|
|
|
94
|
|
|
|
|
|
|
Values may contain newlines (line feed). In a raw NSR file, newlines are represented literal chars "\n" ("backslash" |
95
|
|
|
|
|
|
|
plus "n"). After record-parsing, these chars are replaced by the newline char in the resulting data structure. |
96
|
|
|
|
|
|
|
|
97
|
|
|
|
|
|
|
NSR files can be used to hold very simple human editable databases. |
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
This module here helps with reading and parsing of such files. |
100
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
=head1 FUNCTIONS |
102
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
=head2 new() |
104
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
filepath is mandatory. fieldspec is optional, an array of hash key names. |
106
|
|
|
|
|
|
|
|
107
|
|
|
|
|
|
|
=head2 read() |
108
|
|
|
|
|
|
|
|
109
|
|
|
|
|
|
|
Returns an array of arrayrefs when no fieldspec was given upon construction. Each element of the referenced array |
110
|
|
|
|
|
|
|
will hold a record's lines in the order they were found in the file. |
111
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
When a fieldspec was provided to new(), read() will try to coerce record lines into a hash according to fieldspec. |
113
|
|
|
|
|
|
|
In case a record does not follow fieldspec and has more lines than expected, read() will add those lines with their |
114
|
|
|
|
|
|
|
zero-based line number as key to the resulting hashref. Fewer lines than in fieldspec will not create empty elements. |
115
|
|
|
|
|
|
|
|
116
|
|
|
|
|
|
|
=head1 EXPORT |
117
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
Nothing by default. |
119
|
|
|
|
|
|
|
|
120
|
|
|
|
|
|
|
=head1 CAVEATS |
121
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
Currently files are slurped completely and not streamed or read incrementally, so be careful with really large files. |
123
|
|
|
|
|
|
|
|
124
|
|
|
|
|
|
|
As stated above, trailing newlines on the "whole file" scope are considered "padding" and are dropped. Having a fieldspec |
125
|
|
|
|
|
|
|
should probably allow to have an empty last line as part of a record but the current implementation would drop an empty |
126
|
|
|
|
|
|
|
last record line. |
127
|
|
|
|
|
|
|
|
128
|
|
|
|
|
|
|
=head1 SEE ALSO |
129
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
Any other file format that contains well readable (mostly) textual data in a structured manner. This here shares the |
131
|
|
|
|
|
|
|
L<"stanza"|StanzaFile::Grub> idea with, for example, L, and the readable approach with L and the line |
132
|
|
|
|
|
|
|
by line aspect with L. Give a shout if you can name another one. |
133
|
|
|
|
|
|
|
|
134
|
|
|
|
|
|
|
=head1 AUTHOR |
135
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
Clipland GmbH L |
137
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
This module was developed for L infotainment website L. |
139
|
|
|
|
|
|
|
|
140
|
|
|
|
|
|
|
=head1 COPYRIGHT & LICENSE |
141
|
|
|
|
|
|
|
|
142
|
|
|
|
|
|
|
Copyright 2022 Clipland GmbH. All rights reserved. |
143
|
|
|
|
|
|
|
|
144
|
|
|
|
|
|
|
This library is free software, dual-licensed under L/L. |
145
|
|
|
|
|
|
|
You can redistribute it and/or modify it under the same terms as Perl itself. |
146
|
|
|
|
|
|
|
|
147
|
|
|
|
|
|
|
=cut |
148
|
|
|
|
|
|
|
|
149
|
|
|
|
|
|
|
1; |