int file_reader_fastq(FILE * fp, Sequence * seq, int max_read_length, boolean new_entry, boolean * full_entry){
* full_entry = true;
if (new_entry!= true){
die("new_entry has to be true for fastq");
}
return read_sequence_from_fastq(fp,seq,max_read_length,fastq_ascii_offset);
}
int main( int argc, char ** argv){
log_and_screen_printf("Demultiplexer\n\n");
log_and_screen_printf(SVN_VERSION);
log_and_screen_printf(SVN_COMMIT_DATE);
log_and_screen_printf("Compiled on %s at %s \n\n", __DATE__, __TIME__);
if (argc < 2) {
print_help();
}
log_write_timestamp(1);
if (argc == 0) {
print_help();
}
DemultiplexerCmdLine cmd = parse_args(argc, argv);
FILE * in = stdin;
if (cmd.input_reads != NULL) {
in = fopen(cmd.input_reads, "r");
if(in == NULL){
log_and_screen_printf("Unable to open file %s\n", cmd.input_reads);
exit(-1);
}
}
Sequence * seq = sequence_new(cmd.max_read_length, cmd.max_name_length, 33);
seq->header = new_sequence_header(CASAVA_1_8);
header_function * f = (header_function *) seq->header;
char * index = f->get_index(seq);
size_t prefix_length = strlen(cmd.output_folder);
char * output_file = calloc(prefix_length + MAX_FIELD_SIZE + 1, sizeof(char *));
char * index_pointer = output_file + prefix_length;
strcpy(output_file, cmd.output_folder);
printf("prefix: %s\n", output_file);
while (read_sequence_from_fastq(in, seq, cmd.max_read_length)) {
strcpy(index_pointer, index);
// printf("index: %s\n new output: %s\n", index, output_file);
append_sequence(output_file, seq, FASTQ);
}
if (in != stdin) {
fclose(in);
}
return 0;
}
void test_read_sequence_from_fastq_with_bad_reads_and_long_reads()
{
int ascii_offset=33;
//pre-allocate space where to read the sequences
Sequence* seq = malloc(sizeof(Sequence));
if (seq==NULL){
fputs("Out of memory trying to allocate a Sequence",stderr);
exit(1);
}
int max_read_length=200;
alloc_sequence(seq,max_read_length,LINE_MAX,ascii_offset);
int length_seq;
FILE* fp1 = fopen("../data/test/basic/includes_one_read_that_is_too_long.fastq", "r");
// @read1
// ACGT
// +
// !!!!
// @read2
// CCCC
// +
// 5555
// @read3
// AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
// -
// 0000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000
// @read4
// ACGT
// +
// 3333
length_seq = read_sequence_from_fastq(fp1,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read1",seq->name);
CU_ASSERT_STRING_EQUAL("ACGT",seq->seq);
CU_ASSERT((int) (seq->qual[0])==0);
CU_ASSERT((int) (seq->qual[1])==0);
CU_ASSERT((int) (seq->qual[2])==0);
CU_ASSERT((int) (seq->qual[3])==0);
length_seq = read_sequence_from_fastq(fp1,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read2",seq->name);
CU_ASSERT_STRING_EQUAL("CCCC",seq->seq);
CU_ASSERT((int) (seq->qual[0])==20);
CU_ASSERT((int) (seq->qual[1])==20);
CU_ASSERT((int) (seq->qual[2])==20);
CU_ASSERT((int) (seq->qual[3])==20);
length_seq = read_sequence_from_fastq(fp1,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 100);
CU_ASSERT_STRING_EQUAL("read3",seq->name);
CU_ASSERT((int) (seq->qual[0])==15); // 0 translates as ascii 48; subtract 33 and get 15
length_seq = read_sequence_from_fastq(fp1,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read4",seq->name);
CU_ASSERT_STRING_EQUAL("ACGT",seq->seq);
CU_ASSERT((int) (seq->qual[0])==18);
fclose(fp1);
FILE* fp2 = fopen("../data/test/basic/includes_reads_with_bad_characters.fastq", "r");
//@read1
//ACGTACGTACGTACGT
//+
//WEW2WEW2WEW2WEWA
//@read2
//AAAA#5A
//+
//1234567
//@read3
//TTTT
//+
//3333
length_seq = read_sequence_from_fastq(fp2,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 16);
CU_ASSERT_STRING_EQUAL("read1",seq->name);
CU_ASSERT_STRING_EQUAL("ACGTACGTACGTACGT",seq->seq);
length_seq = read_sequence_from_fastq(fp2,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read3",seq->name);
CU_ASSERT_STRING_EQUAL("TTTT",seq->seq);
length_seq = read_sequence_from_fastq(fp2,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 0);
fclose(fp2);
FILE* fp3 = fopen("../data/test/basic/includes_one_read_where_quality_is_longer_than_seq.fastq", "r");
//@read1
//ACGTACGTACGTACGT
//+
//WEW2WEW2WEW2WEWA
//@read2
//AAAA#5A
//+
//!!!!!!!!!!!!!!!!!!!!!!
//@read3
//TTTT
//+
//3333
length_seq = read_sequence_from_fastq(fp3,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 16);
CU_ASSERT_STRING_EQUAL("read1",seq->name);
CU_ASSERT_STRING_EQUAL("ACGTACGTACGTACGT",seq->seq);
length_seq = read_sequence_from_fastq(fp3,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read3",seq->name);
CU_ASSERT_STRING_EQUAL("TTTT",seq->seq);
length_seq = read_sequence_from_fastq(fp3,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 0);
fclose(fp3);
FILE* fp4 = fopen("../data/test/basic/includes_multiline_reads.fastq", "r");
// @read1
// ACGT
// +
// @@@@
// @read2 45 bases
// AAAAAAAAAAAAAAA
// CCCCCCCCCCCCCCC
// GGGGGGGGGGGGGGG
// +
// 222222222222222
// 333333333333333
// 444444444444444
// @read3
// TTT
// -
// ggg
length_seq = read_sequence_from_fastq(fp4,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("read1",seq->name);
CU_ASSERT_STRING_EQUAL("ACGT",seq->seq);
length_seq = read_sequence_from_fastq(fp4,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 45);
CU_ASSERT_STRING_EQUAL("read2",seq->name);
CU_ASSERT_STRING_EQUAL("AAAAAAAAAAAAAAACCCCCCCCCCCCCCCGGGGGGGGGGGGGGG",seq->seq);
length_seq = read_sequence_from_fastq(fp4,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 3);
CU_ASSERT_STRING_EQUAL("read3",seq->name);
CU_ASSERT_STRING_EQUAL("TTT",seq->seq);
length_seq = read_sequence_from_fastq(fp4,seq,max_read_length);
CU_ASSERT_EQUAL(length_seq, 0);
fclose(fp4);
free_sequence(&seq);
}
void test_read_sequence_from_fastq(){
int ascii_offset = 33;
//pre-allocate space where to read the sequences
Sequence* seq = malloc(sizeof(Sequence));
if (seq==NULL){
fputs("Out of memory trying to allocate a Sequence",stderr);
exit(1);
}
alloc_sequence(seq,200,LINE_MAX, ascii_offset);
int length_seq;
FILE* fp1 = fopen("../data/test/basic/one_entry.fastq", "r");
// 1. Read from simple fasta:
// >Zam
// ACGT
// +
// &&&&
length_seq = read_sequence_from_fastq(fp1,seq,1000);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("Zam",seq->name);
CU_ASSERT_STRING_EQUAL("ACGT",seq->seq);
// CU_ASSERT_STRING_EQUAL("&&&&",seq->qual);/Zam says - /changed this line when I changed the ual reading code to offset by 33
CU_ASSERT((int) seq->qual[0] == 5);
FILE* fp2 = fopen("../data/test/basic/three_entries.fastq", "r");
//2. Read from fastq:
// @Zam1
//ACGT
//+
//&&&&
//@Zam2
//AAAAAAAA
//+
//!((/8F+,
//@Zam3
//ATATATAT
//TTTTTTTTTT
//-
//(((((((+AAAAAABAAA
length_seq = read_sequence_from_fastq(fp2,seq, 1000);
CU_ASSERT_EQUAL(length_seq, 4);
CU_ASSERT_STRING_EQUAL("Zam1",seq->name);
CU_ASSERT_STRING_EQUAL("ACGT",seq->seq);
// CU_ASSERT_STRING_EQUAL("&&&&",seq->qual);/Zam says - /changed this line when I changed the ual reading code to offset by 33
CU_ASSERT((int) seq->qual[0] == 5);
length_seq = read_sequence_from_fastq(fp2,seq,1000);
CU_ASSERT_EQUAL(length_seq, 8);
CU_ASSERT_STRING_EQUAL("Zam2",seq->name);
CU_ASSERT_STRING_EQUAL("AAAAAAAA",seq->seq);
CU_ASSERT((int) seq->qual[0] == 0);//! is quality 0 - take 33 off its ascii code, can check on http://www.asciitable.com/
CU_ASSERT((int) seq->qual[1] == 7);// ( is quality 7
CU_ASSERT((int) seq->qual[2] == 7);// ( is quality 7
CU_ASSERT((int) seq->qual[3] == 14);// / is quality 14
CU_ASSERT((int) seq->qual[4] == 23);// 8 is quality 23
CU_ASSERT((int) seq->qual[5] == 37);// F is quality 37
CU_ASSERT((int) seq->qual[6] == 10);// + is quality 10
CU_ASSERT((int) seq->qual[7] == 11);// , is quality 11
length_seq = read_sequence_from_fastq(fp2,seq,1000);
CU_ASSERT_EQUAL(length_seq, 18);
CU_ASSERT_STRING_EQUAL("Zam3",seq->name);
CU_ASSERT_STRING_EQUAL("ATATATATTTTTTTTTTT",seq->seq);
CU_ASSERT((int) seq->qual[0] == 7);// ( is quality 7
length_seq = read_sequence_from_fastq(fp2,seq,1000);
CU_ASSERT_EQUAL(length_seq, 0);
fclose(fp2);
free_sequence(&seq);
}
int main(int argc, char **argv){
CmdLine cmd_line = parse_cmdline(argc,argv,sizeof(Element));
long long As=0;
long long Cs=0;
long long Gs=0;
long long Ts=0;
long long Us=0;
int max_read_length = 1000;
FILE* fp = fopen(cmd_line.input_filename, "r");
if (fp == NULL){
fprintf(stderr,"cannot open file:%s\n",cmd_line.input_filename);
exit(1); //TODO - prefer to print warning and skip file and return an error code?
}
//----------------------------------
// preallocate the memory used to read the sequences
//----------------------------------
Sequence * seq = malloc(sizeof(Sequence));
if (seq == NULL){
fputs("Out of memory trying to allocate Sequence\n",stderr);
exit(1);
}
alloc_sequence(seq,max_read_length,LINE_MAX, cmd_line.quality_offset);
int entry_length=0;
boolean new_entry = true;
boolean full_entry;
do {
switch (cmd_line.input_file_format) {
case FASTQ:
entry_length = read_sequence_from_fastq(fp,seq,max_read_length);
break;
case FASTA:
entry_length = read_sequence_from_fasta(fp,seq,max_read_length,new_entry,&full_entry,0);
new_entry = full_entry;
break;
}
int i;
for(i=0;i<entry_length;i++){
//printf("index %i char %c\n",i,seq->seq[i]);
switch (seq->seq[i])
{
case 'A':
As++;
break;
case 'C':
Cs++;
break;
case 'G':
Gs++;
break;
case 'T':
Ts++;
break;
case 'a':
As++;
break;
case 'c':
Cs++;
break;
case 'g':
Gs++;
break;
case 't':
Ts++;
break;
default:
Us++;
}
}
} while (entry_length>0);
long long total = As + Cs + Gs + Ts + Us;
printf("%qd As counted - %5.2f%%\n",As, (As*100.0)/total);
printf("%qd Cs counted - %5.2f%%\n",Cs,(Cs*100.0)/total);
printf("%qd Gs counted - %5.2f%%\n",Gs,(Gs*100.0)/total);
printf("%qd Ts counted - %5.2f%%\n",Ts,(Ts*100.0)/total);
printf("%qd Us counted - %5.2f%%\n",Us,(Us*100.0)/total);
return 0;
}