gsuffix/gs2k.h File Reference

Main header file for the gsuffix library. More...

#include <stdio.h>

Include dependency graph for gs2k.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	plain_sequence
	Represents a sequence entry. More...
struct	plain_fasta
	Represents the contents of a fasta file without any further interpretation. More...
struct	labeled_sequence
	Represents a labeled sequence. More...
struct	labeled_fasta
	Represents labeled sequences. More...
struct	gsuffix
	An opaque data type representing an index. More...
Defines
#define	is_amino(c)   (__amino[(unsigned char)c])
	is the given character an amino acid?
#define	is_extamino(c)   (__ext_amino[(unsigned char)c])
	is the given character an extended amino acid?
#define	is_dna(c)   (__dna[(unsigned char)(c)])
	is the given character an dna character?
#define	GENSARRAY_OPT_DIRECT_INDEX_SEARCH   (1<<0)
#define	GENSARRAY_OPT_BINARY_INDEX_SEARCH   (1<<1)
#define	GENSARRAY_OPT_8BIT   (1<<2)
#define	GENHASH_OPT_DIRECT_INDEX_SEARCH   (1<<0)
#define	GENHASH_OPT_BINARY_INDEX_SEARCH   (1<<1)
Enumerations
enum	gsuffix_type {   GSUFFIX_SUFFIXARRAY, GSUFFIX_LOTRUNCSUFFIXTREE, GSUFFIX_HASH, GSUFFIX_LOSUFFIXTREE,   GSUFFIX_DIRECT }
	types of index data structures supported by gsuffix_create(). More...
Functions
void	init_amino (void)
	initialize character tables.
int	are_sequences_dna (const char **seq, int nseq)
int	fasta_read (FILE *fh, int(*sequence_function)(char *name, char *sequence, int sequence_len, void *userdata), void *userdata)
	Read and parse a FASTA file.
struct plain_fasta *	fasta_read_plain (FILE *fh)
	Parses the FASTA file from the given filehandle and returns the contents.
void	fasta_free_plain (struct plain_fasta *fasta)
	Free all memory associated with the given fasta instance.
struct labeled_fasta *	fasta_read_labeled (FILE *fh)
	Parse and read a labeled FASTA file.
void	fasta_free_labeled (struct labeled_fasta *fasta)
	Frees all memory associated with the given a labeled fasta instance.
struct gsuffix *	gsuffix_create (char **strings, int nstrings, enum gsuffix_type type, int query_length, int options)
	Create an index data structure of the given type.
void	gsuffix_delete (struct gsuffix *gs)
	Frees all resources of the given gsuffix instance.
int	gsuffix_lookup (struct gsuffix *gs, const char *p, int m, int(*hit_callback)(int index, int pos, void *userdata), void *userdata)
	Look up an individual query sequence.
int	gsuffix_lookup_exists (struct gsuffix *gs, const char *p, int m)
	Check whether the given pattern of size m exists in the index.
int	gsuffix_enum_k_mers (struct gsuffix *gs, int k, int(*callback)(char *kmer, int id, int pos, void *userdata), void *userdata)
	Enumerates all k-mers of the given length.
Variables
unsigned char	__amino [256]
	table for amino acids
unsigned char	__ext_amino [256]
	table for extended amio acids
unsigned char	__dna [256]
	table for dna

---

Detailed Description

Main header file for the gsuffix library.

---

Function Documentation

int are_sequences_dna	(	const char **	seq,
		int	nseq
	)

Returns whether the given sequences are all dna sequences.

Parameters:

	seq	array of sequences to be checked. Every sequence should be 0-byte terminated.
	nseq	number of sequences to be checked.

Returns:

1 if all sequences are composed of letters of the DNA alphabet.

Examples:

measure.c.

void init_amino

(

void

)

initialize character tables.

Call this before using is_amino(), is_extamino(c), is_dna(), or are_sequences_dna().

Examples:

measure.c.