Example: DNA substring search. More...

#include <iostream>
#include <sstream>
#include <chrono>
#include <regex>
#include <time.h>
#include <stdio.h>
#include <stdexcept>
#include <memory>
#include <vector>
#include <map>
#include <utility>
#include <algorithm>
#include <unordered_map>
#include "bm.h"
#include "bmalgo.h"
#include "bmserial.h"
#include "bmaggregator.h"
#include "bmdbg.h"
#include "bmtimer.h"
#include "bmundef.h"

Include dependency graph for xsample04.cpp:

Go to the source code of this file.

Data Structures
class	DNA_FingerprintScanner
	Utility for keeping all DNA finger print vectors and search using various techniques. More...

Typedefs
typedef std::map< std::string, unsigned >	freq_map

typedef std::vector< std::pair< unsigned, std::string > >	dict_vect

typedef bm::aggregator< bm::bvector<> >	aggregator_type

using	THitList = vector< unsigned >

Functions
static void	show_help ()
	More...

static int	parse_args (int argc, char *argv[])
	More...

static int	load_FASTA (const std::string &fname, std::vector< char > &seq_vect)
	More...

static void	generate_kmers (vector< tuple< string, int >> &top_words, vector< tuple< string, int >> &lo_words, const vector< char > &data, size_t N, unsigned word_size)
	generate the most frequent words of specified length from the input sequence More...

static void	find_word_2way (vector< char > &data, const char *word, unsigned word_size, THitList &r)
	2-way string matching More...

static void	find_words (const vector< char > &data, vector< const char * > words, unsigned word_size, vector< vector< unsigned >> &hits)
	Find all words in one pass (cache coherent algorithm) (variation of 2-way string matching for collection search) More...

static bool	hitlist_compare (const THitList &h1, const THitList &h2)
	Check search result match. More...

int	main (int argc, char *argv[])
	More...

Variables
std::string	ifa_name
	More...

bool	is_diag = false
	More...

bool	is_timing = false
	More...

bool	is_bench = false
	More...

bool	is_search = false
	More...

bool	h_word_set = true
	More...

bm::chrono_taker ::duration_map_type	timing_map
	More...

static const size_t	WORD_SIZE = 28
	More...

Detailed Description

Example: DNA substring search.

Definition in file xsample04.cpp.

Function Documentation

◆ find_word_2way()

static void find_word_2way	(	vector< char > &	data,
		const char *	word,
		unsigned	word_size,
		THitList &	r
	)

static

2-way string matching

Examples: xsample04.cpp.

Definition at line 421 of file xsample04.cpp.

Referenced by main().

◆ find_words()

static void find_words	(	const vector< char > &	data,
		vector< const char * >	words,
		unsigned	word_size,
		vector< vector< unsigned >> &	hits
	)

static

Find all words in one pass (cache coherent algorithm) (variation of 2-way string matching for collection search)

Examples: xsample04.cpp.

Definition at line 451 of file xsample04.cpp.

Referenced by main().

◆ generate_kmers()

static void generate_kmers	(	vector< tuple< string, int >> &	top_words,
		vector< tuple< string, int >> &	lo_words,
		const vector< char > &	data,
		size_t	N,
		unsigned	word_size
	)