Bio/Index/Fastq.pm

filter: Statementstmt 28.2% 11 / 39 Branchbran 0.0% 0 / 10 Conditioncond 0.0% 0 / 2 MC/DCmcdc 0.0% 0 / 1 Subroutinesub 37.5% 3 / 8 Podpod 100% 2 / 2 totaltotal 25.8% 16 / 62 CC 8 SCAR 26.1
CC
8
Cov
22%
_index_file
30.0
id_parser
12.0
default_id_parser
6.0
CRAP 13.7
« Bio/SearchIO/waba.pm ↑ Summary Bio/Index/Qual.pm »
1 # BioPerl module for Bio::Index::Fastq
2 #
3 # Please direct questions and support issues to <bioperl-l@bioperl.org>
4 #
5 # Cared for by Tony Cox <avc@sanger.ac.uk>
6 #
7 # You may distribute this module under the same terms as perl itself
8  
9 # POD documentation - main docs before the code
10  
11 =head1 NAME
12  
13 Bio::Index::Fastq - Interface for indexing (multiple) fastq files
14  
15 =head1 SYNOPSIS
16  
17 # Complete code for making an index for several
18 # fastq files
19 use Bio::Index::Fastq;
20 use strict;
21  
22 my $Index_File_Name = shift;
23 my $inx = Bio::Index::Fastq->new(
24 '-filename' => $Index_File_Name,
25 '-write_flag' => 1);
26 $inx->make_index(@ARGV);
27  
28 # Print out several sequences present in the index
29 # in Fastq format
30 use Bio::Index::Fastq;
31 use strict;
32  
33 my $Index_File_Name = shift;
34 my $inx = Bio::Index::Fastq->new('-filename' => $Index_File_Name);
35 my $out = Bio::SeqIO->new('-format' => 'Fastq','-fh' => \*STDOUT);
36  
37 foreach my $id (@ARGV) {
38 my $seq = $inx->fetch($id); # Returns Bio::Seq::Quality object
39 $out->write_seq($seq);
40 }
41  
42 # or, alternatively
43 my $id;
44 my $seq = $inx->get_Seq_by_id($id); #identical to fetch
45  
46 =head1 DESCRIPTION
47  
48 Inherits functions for managing dbm files from Bio::Index::Abstract.pm,
49 and provides the basic funtionality for indexing fastq files, and
50 retrieving the sequence from them. Note: for best results 'use strict'.
51  
52 Bio::Index::Fastq supports the Bio::DB::BioSeqI interface, meaning
53 it can be used as a Sequence database for other parts of bioperl
54  
55 =head1 FEED_BACK
56  
57 =head2 Mailing Lists
58  
59 User feedback is an integral part of the evolution of this and other
60 Bioperl modules. Send your comments and suggestions preferably to one
61 of the Bioperl mailing lists. Your participation is much appreciated.
62  
63 bioperl-l@bioperl.org - General discussion
64 http://bioperl.org/wiki/Mailing_lists - About the mailing lists
65  
66 =head2 Support
67  
68 Please direct usage questions or support issues to the mailing list:
69  
70 I<bioperl-l@bioperl.org>
71  
72 rather than to the module maintainer directly. Many experienced and
73 reponsive experts will be able look at the problem and quickly
74 address it. Please include a thorough description of the problem
75 with code and data examples if at all possible.
76  
77 =head2 Reporting Bugs
78  
79 Report bugs to the Bioperl bug tracking system to help us keep track
80 the bugs and their resolution. Bug reports can be submitted via the
81 web:
82  
83 https://github.com/bioperl/bioperl-live/issues
84  
85 =head1 AUTHOR - Tony Cox
86  
87 Email - avc@sanger.ac.uk
88  
89 =head1 APPENDIX
90  
91 The rest of the documentation details each of the object
92 methods. Internal methods are usually preceded with a _
93  
94 =cut
95  
96  
97 # Let the code begin...
98  
99  
100 package Bio::Index::Fastq;
101 1 $Bio::Index::Fastq::VERSION = '1.7.8';
102 1 ▶use strict;
Subroutine BEGIN: called CC=1 SCAR=0.0
103  
104 1 ▶use Bio::Seq;
Subroutine BEGIN: called CC=1 SCAR=0.0
105  
106 1 ▶use base qw(Bio::Index::AbstractSeq);
Subroutine BEGIN: called CC=1 SCAR=0.0
107  
108 #
109 # Suggested fix by Michael G Schwern <schwern@pobox.com> to
110 # get around a clash with CPAN shell...
111 #
112  
113 0 ▶sub _version {
Subroutine _version: not called CC=1 SCAR=6.9
114 0 return 0.2;
115 }
116  
117 =head2 _file_format
118  
119 Title : _file_format
120 Function: The file format for this package, which is needed
121 by the SeqIO system when reading the sequence.
122 Returns : 'Fastq'
123  
124 =cut
125  
126 0 ▶sub _file_format {
Subroutine _file_format: not called CC=1 SCAR=6.9
127 0 return 'Fastq';
128 }
129  
130  
131  
132 =head2 _index_file
133  
134 Title : _index_file
135 Usage : $index->_index_file( $file_name, $i )
136 Function: Specialist function to index FASTQ format files.
137 Is provided with a filename and an integer
138 by make_index in its SUPER class.
139 Example :
140 Returns :
141 Args :
142  
143 =cut
144  
145 0 ▶sub _index_file {
Subroutine _index_file: not called CC=5 SCAR=34.0
146 0 my( $self,
147 $file, # File name
148 $i, # Index-number of file being indexed
149 ) = @_;
150
151 0 my( $begin, # Offset from start of file of the start
152 # of the last found record.
153 );
154  
155 0 $begin = 0;
156  
157 0 my $id_parser = $self->id_parser;
158 0 my $c = 0;
159 0 ▶ open my $FASTQ, '<', $file or $self->throw("Could not read file '$file': $!");
Branch: 1 branch
BranchTrueFalseTotal
open my $FASTQ, "<", $file or $self->throw("Could not read file '${file}': $!") 0 0 0
160  
161 # In Windows, text files have '\r\n' as line separator, but when reading in
162 # text mode Perl will only show the '\n'. This means that for a line "ABC\r\n",
163 # "length $_" will report 4 although the line is 5 bytes in length.
164 # We assume that all lines have the same line separator and only read current line.
165 0 my $init_pos = tell($FASTQ);
166 0 my $curr_line = <$FASTQ>;
167 0 my $pos_diff = tell($FASTQ) - $init_pos;
168 0 my $correction = $pos_diff - length $curr_line;
169 0 seek $FASTQ, $init_pos, 0; # Rewind position to proceed to read the file
170  
171 # Main indexing loop
172 0 ▶ while (<$FASTQ>) {
Branch: 1 branch
BranchTrueFalseTotal
if (defined($_ = readline $FASTQ)) 0 0 0
173 0 ▶ if (/^@/) {
Branch: 1 branch
BranchTrueFalseTotal
if (/^@/) 0 0 0
174 0 my $begin = tell($FASTQ) - length( $_ ) - $correction;
175 0 foreach my $id (&$id_parser($_)) {
176 0 $self->add_record($id, $i, $begin);
177 0 $c++;
178 }
179 }
180 }
181  
182 0 close $FASTQ;
183 0 return ($c);
184 }
185  
186 =head2 id_parser
187  
188 Title : id_parser
189 Usage : $index->id_parser( CODE )
190 Function: Stores or returns the code used by record_id to
191 parse the ID for record from a string. Useful
192 for (for instance) specifying a different
193 parser for different flavours of FASTQ file.
194 Returns \&default_id_parser (see below) if not
195 set. If you supply your own id_parser
196 subroutine, then it should expect a fastq
197 description line. An entry will be added to
198 the index for each string in the list returned.
199 Example : $index->id_parser( \&my_id_parser )
200 Returns : ref to CODE if called without arguments
201 Args : CODE
202  
203 =cut
204  
205 0 ▶sub id_parser {
Subroutine id_parser: not called CC=3 SCAR=24.8
Pod documented
206 0 my( $self, $code ) = @_;
207
208 0 ▶ if ($code) {
Branch: 1 branch
BranchTrueFalseTotal
if ($code) 0 0 0
209 0 $self->{'_id_parser'} = $code;
210 }
211 0 ▶ return $self->{'_id_parser'} || \&default_id_parser;
Condition0%0/2
$self->{'_id_parser'} || \&Bio::Index::Fastq::default_id_parser
l!l
00
MC/DC0%0/1
$self->{'_id_parser'} || \&Bio::Index::Fastq::default_id_parser
$self->{'_id_parser'}
Truth table0%0/2
A
A= $self->{'_id_parser'}
Aresult
11
00
212 }
213  
214  
215  
216 =head2 default_id_parser
217  
218 Title : default_id_parser
219 Usage : $id = default_id_parser( $header )
220 Function: The default Fastq ID parser for Fastq.pm
221 Returns $1 from applying the regexp /^>\s*(\S+)/
222 to $header.
223 Returns : ID string
224 Args : a fastq header line string
225  
226 =cut
227  
228 0 ▶sub default_id_parser {
Subroutine default_id_parser: not called CC=2 SCAR=17.9
Pod documented
229 0 ▶ if ($_[0] =~ /^@\s*(\S+)/) {
Branch: 1 branch
BranchTrueFalseTotal
if ($_[0] =~ /^\@\s*(\S+)/) { } 0 0 0
230 0 return $1;
231 } else {
232 0 return;
233 }
234 }
235  
236 1 1;
« Bio/SearchIO/waba.pm ↑ Summary Bio/Index/Qual.pm »