NVBIO
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
sequence_txt.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 
49 // SequenceDataFile from a FASTQ file
50 // contains the code to parse FASTQ files and dump the results into a SequenceDataRAM object
51 // file access is done via derived classes
53 {
54 protected:
56  const char* read_file_name,
57  const Options& options,
58  const uint32 buffer_size = 64536u)
59  : SequenceDataFile( options ),
60  m_file_name(read_file_name),
61  m_buffer(buffer_size),
62  m_buffer_size(buffer_size),
63  m_buffer_pos(buffer_size),
64  m_line(0)
65  {};
66 
67  // get next read chunk from file and parse it (up to max reads)
68  // this can cause m_file_state to change
69  virtual int nextChunk(struct SequenceDataEncoder* output, uint32 max_reads, uint32 max_bps);
70 
71  // fill m_buffer with data from the file, return the new file state
72  // this should only report EOF when no more bytes could be read
73  // derived classes should override this method to return actual file data
74  virtual FileState fillBuffer(void) = 0;
75 
76  virtual bool gets(char* buffer, int len) = 0;
77 
78 private:
79  // get next character from file
80  uint8 get();
81 
82 protected:
83  // file name we're reading from
84  const char * m_file_name;
85 
86  // buffers input from the fastq file
87  std::vector<char> m_buffer;
90 
91  // counter for which line we're at
93 
94  // error reporting from the parser: stores the character that generated an error
96 
97  // temp buffers for data coming in from the FASTQ file: read name, base pairs and qualities
98  std::vector<char> m_name;
99  std::vector<uint8> m_read_bp;
100  std::vector<uint8> m_read_q;
101 };
102 
103 // loader for gzipped files
104 // this also works for plain uncompressed files, as zlib does that transparently
106 {
108  const char* read_file_name,
109  const Options& options,
110  const uint32 buffer_size = 64536u);
111 
113 
116  virtual FileState fillBuffer(void);
117 
118  virtual bool gets(char* buffer, int len) { return gzgets( m_file, buffer, len ) != NULL; };
119 
122  virtual bool rewind();
123 
124 private:
125  gzFile m_file;
126 };
127 
133 {
137  const char* file_name,
138  const char* compressor,
139  const char* options);
140 
143  void next(const SequenceDataHost& sequence_data);
144 
147  bool is_ok();
148 
149 private:
150  // file name we're reading from
151  const char* m_file_name;
152  OutputStream* m_file;
153 };
154 
158 
159 inline uint8 SequenceDataFile_TXT::get(void)
160 {
162  {
163  // grab more data from the underlying file
165  m_buffer_pos = 0;
166 
167  // if we failed to read more data, return \0
168  if (m_file_state != FILE_OK)
169  return 0;
170  }
171 
172  return m_buffer[m_buffer_pos++];
173 }
174 
175 } // namespace io
176 } // namespace nvbio