File: fahash_create2.cpp

package info (click to toggle)
epcr 2.3.12-1-9
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 916 kB
  • sloc: cpp: 5,730; ansic: 231; makefile: 31; python: 26; sh: 12
file content (322 lines) | stat: -rw-r--r-- 10,360 bytes parent folder | download | duplicates (7)
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
/* $Id: fahash_create2.cpp,v 1.6 2008/04/28 16:38:45 rotmistr Exp $
 * ===========================================================================
 *
 *                            PUBLIC DOMAIN NOTICE
 *               National Center for Biotechnology Information
 *
 *  This software/database is a "United States Government Work" under the
 *  terms of the United States Copyright Act.  It was written as part of
 *  the author's official duties as a United States Government employee and
 *  thus cannot be copyrighted.  This software/database is freely available
 *  to the public for use. The National Library of Medicine and the U.S.
 *  Government have not placed any restriction on its use or reproduction.
 *
 *  Although all reasonable efforts have been taken to ensure the accuracy
 *  and reliability of the software and data, the NLM and the U.S.
 *  Government do not and cannot warrant the performance or results that
 *  may be obtained by using this software or data. The NLM and the U.S.
 *  Government disclaim all warranties, express or implied, including
 *  warranties of performance, merchantability or fitness for any particular
 *  purpose.
 *
 *  Please cite the author in any work or product based on this material.
 *
 * =========================================================================
 *
 * Author: Kirill Rotmistrovsky
 *
 * ========================================================================= */

#include <epcr/fahash.hpp>
#include <epcr/bin-io.hpp>
#include "fahash_defines.h"

#include <iostream>
#include <stdexcept>
#include <sstream>
#include <cstring>
#include <memory>

#include <errno.h>
#include <assert.h>

USING_NCBI_SCOPE;
USING_SCOPE(EPCR_SCOPE);

#include "fahash_internal.hpp"

////////////////////////////////////////////////////////////////////////

void CFaIndexer2::AddSequence( const char * sequence, unsigned len, off64_t pos )
{
    m_Seqlst.push_back( SSeqDesc( m_Fapath.size() - 1, pos ) );

	m_Hash.Begin( sequence );
		
	THashElement sid = ( m_Seqlst.size() - 1 ) | kHighBit;

	assert( m_Hash.GetWordCount() == m_Data.size() );
	for( ; m_Hash.GetPosition() < len/*!m_Hash.End()*/; m_Hash.Next() ) {
        if( m_Cbk && m_Hash.GetPosition() % 100 == 0 ) m_Cbk->CbkProgress( m_Hash.GetPosition(), len );
		for( unsigned wd = 0; wd < m_Hash.GetWordCount(); ++wd ) {
			assert( m_Hash.GetTableSize( wd ) == m_Data[wd].size() );
			if( m_Hash.Good( wd ) ) {
				THashElement val = m_Hash.GetValue( wd );
				if( m_LastSid[wd][val] != sid ) {
					m_LastSid[wd][val] = sid;
					m_Seqs[wd][val]++;
				}
				m_Data[wd][val]++;
			}
		}
	}
}

void CFaIndexer2::AttachFile( const string& path )
{
    AttachHeaderDefault( path, FILE_VERSION2 );
}

void CFaIndexer2::DumpTables()
{
    if( m_Cbk ) m_Cbk->CbkResetStart();

	// Allocate Space
	unsigned entries = 0;
	for( unsigned wd = 0; wd < m_Hash.GetWordCount(); ++wd ) {
		entries += m_Hash.GetTableSize(wd);
	}

	off64_t start_off = SeekAlign( m_File );
	off64_t curr = start_off;

	TStatVector& pos = m_Cursor;
	pos.resize( m_Hash.GetWordCount() );
    m_Cache.resize( m_Hash.GetWordCount() );
	for( unsigned wd = 0; wd < m_Hash.GetWordCount(); ++wd ) {
		pos[wd].resize( m_Hash.GetTableSize(wd) );
        m_Cache[wd].resize( m_Hash.GetTableSize(wd) );
		curr += m_Hash.GetTableSize( wd ) * ( sizeof(off64_t) + sizeof(THashElement) );
	}

	m_Tabloc.push_back( make_pair( start_off, curr - start_off ) );

	off64_t totalseq = 0, maxseq = 0, nullseq = 0, totalwd = 0, maxwd = 0;
	for( unsigned wd = 0; wd < m_Hash.GetWordCount(); ++wd ) {
		for( unsigned el = 0; el < m_Hash.GetTableSize( wd ); ++el ) {
			// Set starting position
            Write<off64_t>( m_File, curr );
            Write<Uint4>( m_File, m_Seqs[wd][el] + m_Data[wd][el] );
            
			pos[wd][el] = curr;
			curr += ( m_Seqs[wd][el] + m_Data[wd][el] ) * sizeof(Uint4);
			// Reset lastsid
			m_LastSid[wd][el] = ~0U; 
			// Statistics
			totalseq += m_Seqs[wd][el];
			if( m_Seqs[wd][el] > maxseq ) maxseq = m_Seqs[wd][el];
			if( m_Seqs[wd][el] == 0 ) nullseq++;
			totalwd += m_Data[wd][el];
			if( m_Data[wd][el] > maxwd ) maxwd = m_Data[wd][el];
		}
	}

    if( m_Cbk ) m_Cbk->CbkResetEnd();

	// Print stat
	cerr << "Total number of sequences: " << m_Seqlst.size() << endl;

	cerr << "Number of hash entries: " 
		 << entries << endl;
	cerr << "Average number of sequences per hash entry: " 
		 << double(totalseq) / entries << endl;
	cerr << "Maximal number of sequences per hash entry: " 
		 << maxseq << endl;
	cerr << "Null hash entries: " 
		 << nullseq << endl;
	cerr << "Total number of hits: " 
		 << totalwd << endl;
	cerr << "Average number of hits per hash entry: " 
		 << double(totalwd) / entries << endl;
	cerr << "Maximal number of hits per hash entry: " 
		 << maxwd << endl;

	// Second pass
	auto_ptr<CFastaMap> fmap( 0 );
	Uint2 oldfid = ~Uint2(0);
    m_Count = 0;
    
	for( int sid = 0; sid < m_Seqlst.size(); ++sid ) {
		const SSeqDesc& sd = m_Seqlst[sid];
		if( oldfid != sd.fid ) {
			if( fmap.get() != 0 ) delete fmap.get();
			fmap.reset( new CFastaMap( m_Fapath[ oldfid = sd.fid ].path ) );
		}
        if( m_Cbk ) m_Cbk->CbkSequence( fmap->GetIdent( sd.data ).c_str() );
		CMmSequence seq( *fmap, sd.data );
		StoreSequence( sid, seq.data(), seq.size() );
	}
	WriteCache();
}

void CFaIndexer2::StoreSequence( unsigned sid, const char * seq, unsigned len )
{
	m_Hash.Begin( seq );
		
//	THashElement maxsid=(m_Seqlst.size()-1)|kHighBit;

	assert( m_Hash.GetWordCount() == m_Data.size() );

	for( ; m_Hash.GetPosition() < len/*!m_Hash.End()*/; m_Hash.Next() ) {
        if( m_Cbk && m_Hash.GetPosition() % 100 == 0 ) m_Cbk->CbkProgress( m_Hash.GetPosition(), len );
		for( unsigned wd = 0; wd < m_Hash.GetWordCount(); ++wd ) {
			if( m_Hash.Good(wd) ) {
				THashElement val = m_Hash.GetValue( wd );
				if( m_LastSid[wd][val] != sid ) {
					m_LastSid[wd][val] = sid;
                    m_Cache[wd][val].push_back( sid | kHighBit );
// 					Write<unsigned>(m_File,sid|kHighBit);
// 					m_Cursor[wd][val]+=sizeof(unsigned);
                    ++m_Count;
				}
                m_Cache[wd][val].push_back( m_Hash.GetPosition() );
// 				Write<unsigned>(m_File,m_Hash.GetPosition());
// 				m_Cursor[wd][val]+=sizeof(unsigned);
                ++m_Count;
			}
		}
        if( m_Count > m_CacheSize ) {
            // this value should be calculated based on statistics
            WriteCache();
            m_Count = 0;
        }
	}
}

void CFaIndexer2::WriteCache()
{
    if( m_Cbk ) m_Cbk->CbkDumpStart();
//    fprintf(stderr,"\nWriting cache...");
    for( unsigned wd = 0, cnt = 0; wd < m_Hash.GetWordCount(); ++wd ) {
		TData::value_type & wdCache( m_Cache[wd] );
        for( unsigned val = 0; val < wdCache.size(); ++val ) {
			THashList & cache( wdCache[val] );
			
            if( cache.size() ) {
				Uint8 & cursor = m_Cursor[wd][val];
                if( fseeko64( m_File, cursor, SEEK_SET ) ) {
					ostringstream err;
					err << "Failed to seek to pos " << cursor 
						<< "(uint" << ( 8 * sizeof( cursor ) ) << "): "
						<< strerror(errno) << "\n";
					throw runtime_error( err.str() );
				}

                Write( m_File, cache[0], cache.size() );
                cursor += sizeof( cache[0] ) * cache.size();
				
				cnt += cache.size();
                cache.resize(0);
				
				if(m_Cbk) m_Cbk->CbkDumpProgress( cnt, m_Count );
            }
        }
    }
//    fprintf(stderr,"...Done\n");
    if( m_Cbk ) m_Cbk->CbkDumpEnd();

}

void CFaIndexer2::SetHash( const CHashSet& hs )
{
// 	for(unsigned i=0; i<m_data.size();++i) {
// 		for(unsigned j=0; j<m_data[i].size();++j) {
// 			m_data[i][j].clear();
// 		}
// 		m_data[i].clear();
// 	}
 	if( m_Data.size() ) m_Data.clear();
 	if( m_Seqs.size() ) m_Seqs.clear();
 	if( m_LastSid.size() ) m_LastSid.clear();
	m_Data.resize( hs.GetWordCount() );
	m_Seqs.resize( hs.GetWordCount() );
	m_LastSid.resize( hs.GetWordCount() );
	for( unsigned i = 0; i < hs.GetWordCount(); ++i ) {
//		m_data[i].clear();
		m_Data[i].resize( hs.GetTableSize(i) );
		m_Seqs[i].resize( hs.GetTableSize(i) );
		m_LastSid[i].resize( hs.GetTableSize(i) );
// 		for(unsigned j=0; j<m_data[i].size();++j) {
// 			m_data[i][j].clear();
// 		}
	}
	m_Hash = hs;
	m_Count = 0;
}


/*
 * $Log: fahash_create2.cpp,v $
 * Revision 1.6  2008/04/28 16:38:45  rotmistr
 * Applied patch to build with gcc-4.3
 *
 * Revision 1.5  2007/07/11 20:49:29  rotmistr
 * Made 64bit-compatible
 *
 * Revision 1.4  2007/07/05 16:05:58  rotmistr
 * Made things compileable by MS Visual C++ 8.0
 *
 * Revision 1.3  2004/05/27 20:35:46  rotmistr
 * Version 2.1.0 with appropriate changes (see Changes) is ready for tests.
 *
 * Revision 1.2  2004/04/28 14:35:36  rotmistr
 * hashfile ver2 build/search works now
 *
 * Revision 1.1  2004/04/27 00:03:59  rotmistr
 * Test files for second version of re-PCR
 *
 * Revision 1.11  2004/04/06 04:53:17  rotmistr
 * All is compileable with BCC5.5 and runnable on WIndows
 *
 * Revision 1.10  2004/04/01 05:57:52  rotmistr
 * Compilable with borland C++
 *
 * Revision 1.9  2004/03/07 06:35:59  rotmistr
 * Many bugfixes and optimisations -- cgi is to go to production
 *
 * Revision 1.8  2004/02/18 05:44:25  rotmistr
 * Changes in CGI: sort order, separate misalignments for l and r primers, reload button
 *
 * Revision 1.7  2004/02/12 21:38:20  rotmistr
 * Fixed typo in seqcmp
 * Optimized and fixed lookup
 * Better look for reverse.cgi
 *
 * Revision 1.6  2004/02/11 04:34:55  rotmistr
 * Optimised lookup speed and memory usage
 * Fixed bug with end of sequence in stsmatch
 * Changing CGI look
 *
 * Revision 1.5  2004/02/05 23:41:21  rotmistr
 * Better reload, fixed margin report in commandline, unists tab in CGI form.
 *
 * Revision 1.4  2004/02/04 21:23:22  rotmistr
 * - gcc-3.3.2 compatible
 * - better postfiltering for reverse-e-PCR for discontiguos words
 * - cgi added, that supports:
 *  -- contig to chromosome mapping
 *  -- simple mapviewer links
 *  -- unists links
 *  -- discontiguos words
 *
 * Revision 1.3  2004/01/07 16:57:42  rotmistr
 * Fragment size is now configurable.
 *
 * Revision 1.2  2003/12/30 15:27:22  rotmistr
 * Fixed bug with sequence end
 *
 * Revision 1.1.1.1  2003/12/23 18:17:28  rotmistr
 * Package that includes e-PCR, reverse e-PCR, and sequence data preparation
 * program for reverse e-PCR looks ready
 *
 */