NVBIO
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
reads_fastq.h
Go to the documentation of this file.
1 /*
2  * nvbio
3  * Copyright (c) 2011-2014, NVIDIA CORPORATION. All rights reserved.
4  *
5  * Redistribution and use in source and binary forms, with or without
6  * modification, are permitted provided that the following conditions are met:
7  * * Redistributions of source code must retain the above copyright
8  * notice, this list of conditions and the following disclaimer.
9  * * Redistributions in binary form must reproduce the above copyright
10  * notice, this list of conditions and the following disclaimer in the
11  * documentation and/or other materials provided with the distribution.
12  * * Neither the name of the NVIDIA CORPORATION nor the
13  * names of its contributors may be used to endorse or promote products
14  * derived from this software without specific prior written permission.
15  *
16  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19  * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20  * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26  */
27 
28 #pragma once
29 
30 #include <nvbio/io/reads/reads.h>
32 #include <nvbio/basic/console.h>
33 
34 #include <zlib/zlib.h>
35 
36 namespace nvbio {
37 namespace io {
38 
41 
44 
47 
48 // ReadDataFile from a FASTQ file
49 // contains the code to parse FASTQ files and dump the results into a ReadDataRAM object
50 // file access is done via derived classes
52 {
53 protected:
54  ReadDataFile_FASTQ_parser(const char *read_file_name,
55  const QualityEncoding quality_encoding,
56  const uint32 max_reads,
57  const uint32 max_read_len,
58  const ReadEncoding flags,
59  const uint32 buffer_size = 64536u)
60  : ReadDataFile(max_reads, max_read_len, flags),
61  m_file_name(read_file_name),
62  m_quality_encoding(quality_encoding),
63  m_buffer(buffer_size),
64  m_buffer_size(buffer_size),
65  m_buffer_pos(buffer_size),
66  m_line(0),
67  m_name( 1024*1024 ),
68  m_read_bp( 1024*1024 ),
69  m_read_q( 1024*1024 )
70  {};
71 
72  // get next read chunk from file and parse it (up to max reads)
73  // this can cause m_file_state to change
74  virtual int nextChunk(ReadDataRAM *output, uint32 max_reads, uint32 max_bps);
75 
76  // fill m_buffer with data from the file, return the new file state
77  // this should only report EOF when no more bytes could be read
78  // derived classes should override this method to return actual file data
79  virtual FileState fillBuffer(void) = 0;
80 
81 private:
82  // get next character from file
83  uint8 get();
84 
85 protected:
86  // file name we're reading from
87  const char * m_file_name;
88  // the quality encoding we're using (for FASTQ, this comes from the command line or defaults to Phred33)
90 
91  // buffers input from the fastq file
92  std::vector<char> m_buffer;
95 
96  // counter for which line we're at
98 
99  // error reporting from the parser: stores the character that generated an error
101 
102  // temp buffers for data coming in from the FASTQ file: read name, base pairs and qualities
103  std::vector<char> m_name;
104  std::vector<uint8> m_read_bp;
105  std::vector<uint8> m_read_q;
106 };
107 
108 // loader for gzipped files
109 // this also works for plain uncompressed files, as zlib does that transparently
111 {
112  ReadDataFile_FASTQ_gz(const char *read_file_name,
113  const QualityEncoding qualities,
114  const uint32 max_reads,
115  const uint32 max_read_len,
116  const ReadEncoding flags);
117 
118  virtual FileState fillBuffer(void);
119 
120 private:
121  gzFile m_file;
122 };
123 
127 
128 inline uint8 ReadDataFile_FASTQ_parser::get(void)
129 {
131  {
132  // grab more data from the underlying file
134  m_buffer_pos = 0;
135 
136  // if we failed to read more data, return \0
137  if (m_file_state != FILE_OK)
138  return 0;
139  }
140 
141  return m_buffer[m_buffer_pos++];
142 }
143 
144 } // namespace io
145 } // namespace nvbio