NVBIO
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
sequence_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 
32 #include <nvbio/io/output_stream.h>
33 #include <nvbio/basic/console.h>
34 
35 #include <zlib/zlib.h>
36 
37 namespace nvbio {
38 namespace io {
39 
42 
45 
48 
54 {
55 protected:
57  const char* read_file_name,
58  const SequenceDataFile::Options& options,
59  const uint32 buffer_size = 64536u)
60  : SequenceDataFile( options ),
61  m_file_name(read_file_name),
62  m_buffer(buffer_size),
63  m_buffer_size(buffer_size),
64  m_buffer_pos(buffer_size),
65  m_line(0),
66  m_name( 1024*1024 ),
67  m_read_bp( 1024*1024 ),
68  m_read_q( 1024*1024 )
69  {}
70 
71  // get next read chunk from file and parse it (up to max reads)
72  // this can cause m_file_state to change
73  virtual int nextChunk(struct SequenceDataEncoder *output, uint32 max_reads, uint32 max_bps);
74 
75  // fill m_buffer with data from the file, return the new file state
76  // this should only report EOF when no more bytes could be read
77  // derived classes should override this method to return actual file data
78  virtual FileState fillBuffer(void) = 0;
79 
80  virtual bool gets(char* buffer, int len) = 0;
81 
82 private:
83  // get next character from file
84  char get();
85 
86 protected:
87  // file name we're reading from
88  const char * m_file_name;
89 
90  // buffers input from the fastq file
91  std::vector<char> m_buffer;
94 
95  // counter for which line we're at
97 
98  // error reporting from the parser: stores the character that generated an error
100 
101  // temp buffers for data coming in from the FASTQ file: read name, base pairs and qualities
102  std::vector<char> m_name;
103  std::vector<uint8> m_read_bp;
104  std::vector<uint8> m_read_q;
105 };
106 
111 {
113  const char* read_file_name,
114  const SequenceDataFile::Options& options);
115 
117 
118  virtual FileState fillBuffer(void);
119 
120  virtual bool gets(char* buffer, int len) { return gzgets( m_file, buffer, len ) != NULL; };
121 
124  virtual bool rewind();
125 
126 private:
127  gzFile m_file;
128 };
129 
130 
136 {
140  const char* file_name,
141  const char* compressor,
142  const char* options);
143 
146  void next(const SequenceDataHost& sequence_data);
147 
150  bool is_ok();
151 
152 private:
153  // file name we're reading from
154  const char* m_file_name;
155  OutputStream* m_file;
156 };
157 
161 
162 inline char SequenceDataFile_FASTQ_parser::get(void)
163 {
164  if (m_buffer_pos >= m_buffer_size /*|| m_buffer[m_buffer_pos] == '\0'*/)
165  {
166  // check whether we had already reached the end of file
167  if (m_buffer_size < m_buffer.size())
168  {
170  return 0;
171  }
172  else
173  {
174  // grab more data from the underlying file
176  m_buffer_pos = 0;
177 
178  // if we failed to read more data, return \0
179  if (m_file_state != FILE_OK)
180  return 0;
181  }
182  }
183 
184  return m_buffer[m_buffer_pos++];
185 }
186 
187 } // namespace io
188 } // namespace nvbio