1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
|
//Copyright 2007 Asim Siddiqui
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
//
#include <ios>
#include <stddef.h>
#include <vector>
#include <iostream>
#include <fstream>
#include <string>
#include <SRF_util.hh>
#include <SRF_ReadSet.hh>
#include <SRF_Ztr.hh>
#define HEADERTYPE 'H'
SRF_ReadSet::SRF_ReadSet( void )
{
ztrHeader.clear();
subBlockType = 'E';
}
SRF_ReadSet::~SRF_ReadSet( void )
{
}
bool
SRF_ReadSet::populate( std::fstream& file )
{
positionInFile = file.tellg();
// read dataBlockHeader fields
char headerType = ' ';
file.read ( &headerType, 1);
if ( headerType != HEADERTYPE )
{
SRF_ReportError( "unexpected header type" );
return FALSE;
}
blockSize = 0;
file.read( reinterpret_cast<char *>(&blockSize), 4 );
blockSize = be_int4(blockSize);
file.read ( &subBlockType, 1);
uniqueIdPrefix = SRF_readString( file );
uint32_t sizeZtrHeaderBlob = blockSize - 1 - 4 - 1 - uniqueIdPrefix.size() - 1;
if ( sizeZtrHeaderBlob < 0 )
{
SRF_ReportError( "invalid block size for read set" );
return FALSE;
}
ztrHeader.clear();
if ( sizeZtrHeaderBlob > 0 )
{
char cstr[sizeZtrHeaderBlob];
file.read( cstr, sizeZtrHeaderBlob);
ztrHeader.assign(cstr, sizeZtrHeaderBlob);
}
return TRUE;
}
ADOPT SRF_Read*
SRF_ReadSet::getRead( std::fstream& file )
{
if ( file.peek() == EOF )
{
return NULL;
}
SRF_Read* read = new SRF_Read;
if ( read->populate( ztrHeader, file ) == 0 )
{
delete read;
}
return read;
}
bool
SRF_ReadSet::readSetStart( std::fstream& file )
{
file.seekg( positionInFile );
return TRUE;
}
bool
SRF_ReadSet::readSetReadStart( std::fstream& file )
{
file.seekg( (off_t) positionInFile + blockSize );
return TRUE;
}
bool
SRF_ReadSet::setup( const std::string& uniqueIdPrefixIn, const std::string& ztrHeaderIn )
{
uniqueIdPrefix = uniqueIdPrefixIn;
ztrHeader = ztrHeaderIn;
return TRUE;
}
void
SRF_ReadSet::dump( void )
{
std::cout << "Size of read set block:" << blockSize <<std::endl;
std::cout << "Sub block Type" << subBlockType <<std::endl;
std::cout << "Unique Id Prefix:" << uniqueIdPrefix <<std::endl;
}
bool
SRF_ReadSet::write( std::fstream& file, const std::vector<ztr_t>& ztrBlobs, const std::vector<std::string>& readIds )
{
int sizeZtrHeaderBlob = ztrHeader.length();
blockSize = 1 + 4 + 1 + uniqueIdPrefix.size() + 1 + sizeZtrHeaderBlob;
// write dataBlockHeader fields
file << HEADERTYPE;
int32_t be_blockSize = be_int4(blockSize);
file.write(reinterpret_cast<const char*>(&be_blockSize),4);
file << subBlockType;
char* str = ADOPT SRF_cStrToPascalStr( uniqueIdPrefix.c_str() );
file << str;
delete [] str;
file.write(ztrHeader.data(), ztrHeader.length());
std::vector<std::string>::const_iterator stringListIterator = readIds.begin();
std::vector<ztr_t>::const_iterator ztrVecIterator = ztrBlobs.begin();
while( ztrVecIterator != ztrBlobs.end() )
{
// TODO check uniqueIdPrefix matches the start of readId
// writeRead
SRF_Read read( &(*stringListIterator), &(*ztrVecIterator) );
read.write( file );
// TOOO
// if ( indexContainer eq TRUE )
// store readOffset from start of file
// # will need to be stored in a tmp file
// endif
stringListIterator++;
ztrVecIterator++;
}
}
|
