1 /*
2     This file is part of BioD.
3     Copyright (C) 2012    Artem Tarasov <lomereiter@gmail.com>
4 
5     Permission is hereby granted, free of charge, to any person obtaining a
6     copy of this software and associated documentation files (the "Software"),
7     to deal in the Software without restriction, including without limitation
8     the rights to use, copy, modify, merge, publish, distribute, sublicense,
9     and/or sell copies of the Software, and to permit persons to whom the
10     Software is furnished to do so, subject to the following conditions:
11     
12     The above copyright notice and this permission notice shall be included in
13     all copies or substantial portions of the Software.
14     
15     THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16     IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17     FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18     AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19     LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20     FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
21     DEALINGS IN THE SOFTWARE.
22 
23 */
24 module bio.std.sff.reader;
25 
26 public import bio.std.sff.index;
27 import bio.std.sff.read;
28 import bio.std.sff.readrange;
29 import bio.std.sff.constants;
30 
31 import bio.core.utils.stream;
32 import contrib.undead.stream;
33 import std.system;
34 import std.range;
35 import std.exception;
36 
37 /// SFF file reader
38 class SffReader {
39 
40     /// Open file by filename
41     this(string filename) {
42         _filename = filename;
43 
44         _readHeader();
45     }
46 
47     /// Reads
48     auto reads() @property {
49         auto stream = new bio.core.utils.stream.File(filename);
50         Stream sff = new EndianStream(stream, Endian.bigEndian);
51 
52         sff.seekSet(_header_length);
53         auto sff_reads = SffReadRange(sff, cast(ushort)_flow_chars.length, _index_location);
54         return takeExactly(sff_reads, _n_reads);
55     }
56 
57     ///
58     SffRead getReadAtOffset(size_t offset) {
59         auto stream = new bio.core.utils.stream.File(filename);
60         Stream sff = new EndianStream(stream, Endian.bigEndian);
61 
62         sff.seekSet(offset);
63         auto read = SffReadRange(sff, cast(ushort)_flow_chars.length, _index_location).front;
64         sff.close();
65         return read;
66     }
67 
68     /// File name
69     string filename() @property const {
70         return _filename;
71     }
72 
73     /// Location of the index (if included).
74     IndexLocation index_location() @property const {
75         return _index_location;
76     }
77 
78     ///
79     bool has_index() @property const {
80         return _index_location.offset != 0 && _index_location.length != 0;
81     }
82 
83     /// Set index location (saves new index location to the file)
84     void index_location(IndexLocation location) @property {
85         _index_location = location;
86 
87         // offset spans 8 bytes (8 .. 16),
88         // length spans 4 bytes (16 .. 20)
89 
90         auto stream = new bio.core.utils.stream.File(filename, "r+");
91         stream.seekSet(8);
92         auto endian_stream = new EndianStream(stream, Endian.bigEndian);
93         endian_stream.write(location.offset);
94         endian_stream.write(location.length);
95         endian_stream.close();
96     }
97 
98     /// Nucleotides used for each flow of each read
99     string flow_order() @property const {
100         return _flow_chars;
101     }
102 
103     /// Nucleotide bases of the key sequence used for each read
104     string key_sequence() @property const {
105         return _key_sequence;
106     }
107 
108     private {
109         string _filename;
110 
111         uint _magic_number;
112         char[4] _version;
113 
114         uint _n_reads;
115         ushort _header_length;
116 
117         string _flow_chars;
118         string _key_sequence;
119 
120         IndexLocation _index_location;
121 
122         void _readHeader() {
123             auto stream = new bio.core.utils.stream.File(_filename);
124             auto sff = new EndianStream(stream, Endian.bigEndian);
125             
126             sff.read(_magic_number);
127             enforce(_magic_number == SFF_MAGIC, "Wrong magic number, expected 0x2E736666");
128 
129             sff.readExact(_version.ptr, 4);
130             enforce(_version == SFF_VERSION, "Unsupported version, expected 1");
131 
132             sff.read(_index_location.offset);
133             sff.read(_index_location.length);
134 
135             sff.read(_n_reads);
136             sff.read(_header_length);
137 
138             ushort _key_length;
139             ushort _number_of_flows;
140             ubyte _flowgram_format_code;
141 
142             sff.read(_key_length);
143             sff.read(_number_of_flows);
144             sff.read(_flowgram_format_code);
145             enforce(_flowgram_format_code == 1, 
146                     "Flowgram format codes other than 1 are not supported");
147 
148             _flow_chars = cast(string)sff.readString(_number_of_flows);
149             _key_sequence = cast(string)sff.readString(_key_length);
150         }
151     }
152 }