int pull_by_re(char *input_file, pcre *re, pcre_extra *re_extra, int min, int max, int length, int exclude, int convert, int just_count) {
gzFile fp;
int count=0,l;
int excluded = 0;
int is_fasta = 0; /* assume fastq */
kseq_t *seq;
/* open fasta file */
fp = gzopen(input_file,"r");
if (!fp) {
fprintf(stderr,"%s - Couldn't open fasta file %s\n",progname,input_file);
exit(EXIT_FAILURE);
}
seq = kseq_init(fp);
/* determine file type */
l = kseq_read(seq); /* read the first sequence */
is_fasta = seq->qual.s == NULL ? 1 : 0;
gzrewind(fp);
kseq_rewind(seq); /* rewind to beginning for main loop */
if (verbose_flag) {
if (is_fasta)
fprintf(stderr, "Input is FASTA format\n");
else
fprintf(stderr, "Input is FASTQ format\n");
}
/* search through list and see if this header matches */
while((l = kseq_read(seq)) >= 0) {
if (exclude) {
if (search_header(re, re_extra, seq->name.s) || search_header(re, re_extra, seq->comment.s))
excluded++;
else {
/* regex doesn't match, so check size/print */
count += size_filter(seq, is_fasta, min, max, length, convert, just_count);
}
} else {
if (search_header(re, re_extra, seq->name.s) || search_header(re, re_extra, seq->comment.s)) {
/* regex matches so check size/print */
count += size_filter(seq, is_fasta, min, max, length, convert, just_count);
} else
excluded++;
}
} /* end of seq traversal */
kseq_destroy(seq);
gzclose(fp); /* done reading file so close */
if (just_count) {
fprintf(stdout, "Total output: %i\n", count);
fprintf(stdout, "Total excluded: %i\n", excluded);
}
return count;
}
/**
Read a number from the header and verify.
*/
double search_header_num_valid(const char *header, const char *key) {
double val=search_header_num(header, key);
if(is_nan(val)) {
error("Unable to read %s from %s. val=%s\n", key, header, search_header(header, key));
}
return val;
}
/**
Read a number from the header with key
*/
double search_header_num(const char *header, const char *key) {
if(!header) return NAN;
const char *val=search_header(header, key);
if(val) {
return readstr_num(val, NULL);
} else {
return NAN;/*not found. */
}
}
static bool message_search_more_decoded2(struct message_search_context *ctx,
struct message_block *block)
{
if (block->hdr != NULL) {
if (search_header(ctx, block->hdr))
return TRUE;
} else {
if (str_find_more(ctx->str_find_ctx, block->data, block->size))
return TRUE;
}
return FALSE;
}
int main(int argc, char *argv[]){
long Database_count, Alignment_count;
int alignment_status;
float preAlignmentScore=0, DatabaseScore=0, preDatabaseScore=0;
unsigned int alignmentShow=1;
interface(argc,argv);
protein_name=(char *)malloc((size_t)protein_name_length);
fileend=fgets_wrap(0, global_tmp,MAXLETTER-1,fin);
Query_count=0;
do{
blast_start:
Alignment_count=0;
Database_count=0;
preAlignmentScore=0;
preDatabaseScore=0;
DatabaseScore=0;
if(fileend==NULL) goto read_end;
/* search query name */
protein_name[0]='\0';
search_qname_and_other();
Database_count=0;
do{
if(fileend==NULL) goto read_end;
/* search database name */
if(search_dname_and_other()==1) goto blast_start;
if(fileend==NULL) goto read_end;
if(dname[0]=='\0' || qname[0]=='\0') {
goto blast_start;
}
preDatabaseScore=DatabaseScore;
DatabaseScore=0;
Alignment_count=0;
alignmentShow=1;
do{
if(fileend==NULL) goto read_end;
/* read alignments */
search_sp_name();
search_score_e_value();
search_identity_and_gaps();
alignment_status=read_one_alignment();
if(DatabaseScore<1){
DatabaseScore=score;
}
/* printf("\n %ld: %f -> %f\n",
Database_count, preDatabaseScore, DatabaseScore); */
if(Database_count==Database_number && Database_number>0){
if(preDatabaseScore!=DatabaseScore || AllowSameScore=='F'){
/* printf("break!!\n"); */
Database_count++;
break;
}else{
/* printf("###### SAME!!\n"); */
Database_count--;
}
}
/*
if(alignmentShow==1){
printf("\n %ld: %f -> %f\n",
Alignment_count, preAlignmentScore, score);
}
*/
if(Alignment_count>=Alignment_number &&
(score!=preAlignmentScore || AllowSameScore=='F')){
alignmentShow=0;
}
if(alignmentShow==1 || Alignment_number==0){
if(output()!=0) Alignment_count++;
}
preAlignmentScore=score;
}while(strncmp(global_tmp," Score =", 8)==0 &&
global_tmp[0]!='>' && fileend!=NULL &&
alignment_status!=1);
if(Alignment_count!=0) {
fprintf(fout,"\n");
Database_count++;
}
protein_name[0]='\0';
}while(global_tmp[0]=='>' &&
fileend!=NULL &&
(Database_number==0 || Database_count<=Database_number)&&
alignment_status!=1);
if(Database_count!=0) {
fprintf(fout,"\n");
}
search_header();
read_end:
;
}while(fileend!=NULL && Query_count!=Query_number);
if (verbose>=1){
fprintf(ferr,"filename %s output %ld sequences",filename,(Query_count-nohits));
if (nohits!=0) fprintf(ferr,", no hits %d, total %ld",nohits, Query_count);
fprintf(ferr,".\n");
}
return 0;
}