int main(int argc, char **argv)
{
const char* progname = "rm";
struct arg_lit *dir = arg_lit0("d", "directory", "unlink file(s), even if it is a non-empty directory");
struct arg_rem *dir2 = arg_rem( NULL, "(super-user only)");
struct arg_lit *force = arg_lit0("f", "force", "ignore nonexistant files, never prompt");
struct arg_lit *inter = arg_lit0("i", "interactive", "prompt before any removal");
struct arg_lit *recur = arg_lit0("rR","recursive", "remove the contents of directories recursively");
struct arg_lit *verb = arg_lit0("v", "verbose", "explain what is being done");
struct arg_lit *help = arg_lit0(NULL,"help", "print this help and exit");
struct arg_lit *vers = arg_lit0(NULL,"version", "print version information and exit");
struct arg_file *files = arg_filen(NULL,NULL,NULL,1,argc+2,NULL);
struct arg_end *end = arg_end(20);
void* argtable[] = {dir,dir2,force,inter,recur,verb,help,vers,files,end};
int exitcode=0;
int nerrors;
/* verify the argtable[] entries were allocated sucessfully */
if (arg_nullcheck(argtable) != 0)
{
/* NULL entries were detected, some allocations must have failed */
printf("%s: insufficient memory\n",progname);
exitcode=1;
goto exit;
}
/* Parse the command line as defined by argtable[] */
nerrors = arg_parse(argc,argv,argtable);
/* special case: '--help' takes precedence over error reporting */
if (help->count > 0)
{
printf("Usage: %s", progname);
arg_print_syntax(stdout,argtable,"\n");
printf("Remove (unlink) the specified file(s).\n\n");
arg_print_glossary(stdout,argtable," %-20s %s\n");
printf("\nReport bugs to <no-one> as this is just an example program.\n");
exitcode=0;
goto exit;
}
/* special case: '--version' takes precedence error reporting */
if (vers->count > 0)
{
printf("'%s' example program for the \"argtable\" command line argument parser.\n",progname);
printf("September 2003, Stewart Heitmann\n");
exitcode=0;
goto exit;
}
/* If the parser returned any errors then display them and exit */
if (nerrors > 0)
{
/* Display the error details contained in the arg_end struct.*/
arg_print_errors(stdout,end,progname);
printf("Try '%s --help' for more information.\n",progname);
exitcode=1;
goto exit;
}
/* command line options are all ok, now perform the "rm" functionality */
mymain(dir->count, force->count, inter->count, recur->count, verb->count, files->filename, files->count);
exit:
/* deallocate each non-null entry in argtable[] */
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
return exitcode;
}
int main(int argc, char *argv[]) {
#ifndef _OPENMP
fprintf(stderr, "\nERROR: Program built with compiler lacking OpenMP support.\n");
fprintf(stderr, "See SEAStAR README file for information about suitable compilers.\n");
exit(EXIT_FAILURE);
#endif
///////////////////////////
// Variable declarations
///////////////////////////
// Input filenames
UT_string *in_read1_fq_fn, *in_read2_fq_fn, *in_single1_fq_fn, *in_single2_fq_fn;
utstring_new(in_read1_fq_fn);
utstring_new(in_read2_fq_fn);
utstring_new(in_single1_fq_fn);
utstring_new(in_single2_fq_fn);
// Output filenames
UT_string *out_read1_fn, *out_read2_fn, *out_single1_fn, *out_single2_fn, *out_mates_fn, *out_filetype;
utstring_new(out_filetype);
utstring_new(out_read1_fn);
utstring_new(out_read2_fn);
utstring_new(out_single1_fn);
utstring_new(out_single2_fn);
utstring_new(out_mates_fn);
// Read name prefix
UT_string *out_read_prefix;
utstring_new(out_read_prefix);
// Flags
int singles_flag = 0; // 1 when two output singles files being written
int num_input_singles_files = 0;
// Read counters
unsigned long int mp_org = 0, R1_org = 0, R2_org = 0, singlet1_org = 0, singlet2_org = 0;
unsigned long int mp_cnt = 0, R1_cnt = 0, R2_cnt = 0, singlet1_cnt = 0, singlet2_cnt = 0, s1_cnt = 0, s2_cnt = 0;
unsigned long int comp_r1 = 0, comp_r2 = 0, comp_s1 = 0, comp_s2 = 0;
unsigned long int read1_singlet_cnt = 0, read2_singlet_cnt = 0;
////////////////////////////////////////////////////////////////////////
// All done with variable declarations!!
///////////////////////////////////
// Command line argtable settings
///////////////////////////////////
struct arg_lit *gzip = arg_lit0("z", "gzip", "Output converted files in gzip compressed format. [NULL]");
struct arg_lit *inv_singles = arg_lit0("v", "invert_singles", "Causes singles output to be the inverse of the input. 2->1 or 1->2 [NULL]");
struct arg_lit *num_singles = arg_lit0("s", "singles", "Write two singlet files, one for each mate-paired input file. [NULL]");
struct arg_rem *sing_rem = arg_rem(NULL, "Note! -v is only valid when there are input singlet reads. -s is only valid when there are NO input singlet reads.");
struct arg_str *pre_read_id = arg_str0(NULL, "prefix", "<string>", "Prefix to add to read identifiers. [out_prefix]");
struct arg_lit *no_pre = arg_lit0(NULL, "no_prefix", "Do not change the read names in any way. [NULL]");
struct arg_lit *pre_read_len = arg_lit0(NULL, "add_len", "Add the final trimmed length value to the read id prefix. [length not added]");
struct arg_dbl *prob = arg_dbl0("p","correct_prob","<d>","Probability that output reads are correct. 0.0 disables quality trimming. [0.5]");
struct arg_int *fixed_len = arg_int0("f","fixed_len","<u>","Trim all reads to a fixed length, still filtering on quality [no fixed length]");
struct arg_int *len = arg_int0("l","min_read_len","<u>","Minimum length of a singlet or longest-mate in nucleotides [24]");
struct arg_int *mate_len = arg_int0("m","min_mate_len","<u>","Minimum length of the shortest mate in nucleotides [min_read_len]");
struct arg_dbl *entropy = arg_dbl0("e","entropy_filter","<d>","Remove reads with per position information below given value (in bits per dinucleotide) [No filter]");
struct arg_lit *entropy_strict = arg_lit0(NULL, "entropy_strict", "Reject reads for low entropy overall, not just the retained part after trimming [NULL]");
struct arg_lit *mates = arg_lit0(NULL, "mates_file", "Produce a Velvet compatible interleaved paired read output file (e.g. <out_prefix>_mates.fastq). [NULL]");
struct arg_lit *no_rev = arg_lit0(NULL, "no_rev", "By default, the second read in each pair is reversed for colorspace --mate-file output. --no_rev disables reversing. [rev]");
struct arg_lit *only_mates = arg_lit0(NULL, "only_mates", "Supress writing .read1 and .read2 outputs. Requires --mates_file. [NULL]");
struct arg_lit *fasta = arg_lit0(NULL, "fasta", "Write FASTA format files instead of FASTQ for all outputs (e.g. <out_prefix>.<read_type>.fasta). [FASTQ]");
struct arg_file *input = arg_file1(NULL, NULL, "<in_prefix>", "Input file prefix: (e.g. <in_prefix>_single.fastq [<in_prefix>_read1.fastq <in_prefix>_read2.fastq]) ");
struct arg_file *output = arg_file1(NULL, NULL, "<out_prefix>", "Output file prefix: (e.g. <out_prefix>_single.fastq [<out_prefix>_read1.fastq <out_prefix>_read2.fastq]) ");
struct arg_lit *version = arg_lit0(NULL,"version","Print the build version and exit.");
struct arg_lit *h = arg_lit0("h", "help", "Request help.");
struct arg_end *end = arg_end(20);
void *argtable[] = {h,version,gzip,inv_singles,num_singles,sing_rem,prob,len,mate_len,fixed_len,pre_read_id,pre_read_len,no_pre,entropy,entropy_strict,mates,no_rev,only_mates,fasta,input,output,end};
int arg_errors = 0;
////////////////////////////////////////////////////////////////////////
// Handle command line processing (via argtable2 library)
////////////////////////////////////////////////////////////////////////
arg_errors = arg_parse(argc, argv, argtable);
if (version->count) {
fprintf(stderr, "%s version: %s\n", argv[0], SS_BUILD_VERSION);
exit(EXIT_SUCCESS);
}
if (h->count) {
fprintf(stderr,"\ntrim_fastq is a utility for performing quality and information-based\n");
fprintf(stderr,"trimming on paired or unpaired, nucleotide or SOLiD colorspace reads. \n\n");
arg_print_syntaxv(stderr, argtable, "\n\n");
arg_print_glossary(stderr, argtable, "%-25s %s\n");
fprintf(stderr, "\nInput and output \"prefixes\" are the part of the filename before:\n");
fprintf(stderr, "_single.fastq [_read1.fastq _read2.fastq] A singlets (single) file\n");
fprintf(stderr, "is required. Mate-paired read files are automatically used if present.\n");
fprintf(stderr, "Multiple output files only produced for mate-paired inputs.\n");
fprintf(stderr, "\nNote! Input and output files may be gzipped, and outputs can be written\n");
fprintf(stderr, "as either FASTQ or FASTA format files.\n");
exit(EXIT_FAILURE);
}
if (arg_errors) {
arg_print_errors(stderr, end, "trimfastq");
arg_print_syntaxv(stderr, argtable, "\n");
exit(EXIT_FAILURE);
}
// Validate entropy
if (entropy->count) {
entropy_cutoff = entropy->dval[0];
if ((entropy_cutoff < 0.0) || (entropy_cutoff > 4.0)) {
fprintf(stderr, "entropy_filter must be [0.0 - 4.0] \n");
exit(EXIT_FAILURE);
}
strict_ent = entropy_strict->count;
} else {
if (entropy_strict->count) {
fprintf(stderr, "Error: --entropy_strict requires --entropy_filter.\n");
exit(EXIT_FAILURE);
}
entropy_cutoff = -1.0;
}
// Validate error_prob
if (prob->count) {
err_prob = prob->dval[0];
if ((err_prob < 0.0) || (err_prob > 1.0)) {
fprintf(stderr, "--correct_prob (-p) must be 0.0 - 1.0 inclusive\n");
exit(EXIT_FAILURE);
}
} else {
err_prob = 0.5;
}
// Validate min read len
if (len->count) {
min_len = len->ival[0];
if (min_len <= 0) {
fprintf(stderr, "min_read_len must be > 0\n");
exit(EXIT_FAILURE);
}
} else {
min_len = 24;
}
// Validate min mate len
if (mate_len->count) {
min_mate_len = mate_len->ival[0];
if (min_mate_len <= 0) {
fprintf(stderr, "min_mate_len must be > 0\n");
exit(EXIT_FAILURE);
}
if (min_mate_len > min_len) {
fprintf(stderr, "min_mate_len must be <= min_len\n");
exit(EXIT_FAILURE);
}
} else {
min_mate_len = min_len;
}
if (fixed_len->count) {
fix_len = min_mate_len = min_len = fixed_len->ival[0];
if ((mate_len->count) || (len->count)) {
fprintf(stderr, "fixed_len cannot be used with min_read_len or min_mate_len\n");
exit(EXIT_FAILURE);
}
if (fix_len <= 0) {
fprintf(stderr, "fixed_len must be > 0\n");
exit(EXIT_FAILURE);
}
} else {
fix_len = 0;
}
if (pre_read_id->count) {
if (no_pre->count) {
fprintf(stderr, "Error: Both --prefix and --no_prefix were specified.\n");
exit(EXIT_FAILURE);
}
if (! strlen(pre_read_id->sval[0])) {
fprintf(stderr, "Read ID prefix may not be zero length.\n");
exit(EXIT_FAILURE);
}
if (strchr(pre_read_id->sval[0], ':') || strchr(pre_read_id->sval[0], '|') || strchr(pre_read_id->sval[0], '+') || strchr(pre_read_id->sval[0], '/')) {
fprintf(stderr, "Read ID prefix '%s' may not contain the characters ':', '|', '+' or '/'.\n", pre_read_id->sval[0]);
exit(EXIT_FAILURE);
}
// Build default read ID prefix
ss_strcat_utstring(out_read_prefix, pre_read_id->sval[0]);
} else {
if (!no_pre->count) {
if (strchr(output->filename[0], ':') || strchr(output->filename[0], '|') || strchr(output->filename[0], '+') || strchr(output->filename[0], '/')) {
fprintf(stderr, "Read ID prefix '%s' (from output prefix) may not contain the characters ':', '|', '+' or '/'.\n", output->filename[0]);
fprintf(stderr, "Hint: Use the --prefix parameter if the output file prefix contains path information.\n");
exit(EXIT_FAILURE);
}
// Build default read ID prefix
ss_strcat_utstring(out_read_prefix, output->filename[0]);
}
}
if ((only_mates->count) && (!mates->count)) {
fprintf(stderr, "--only_mates requires --mates.\n");
exit(EXIT_FAILURE);
}
if ((no_rev->count) && (!mates->count)) {
fprintf(stderr, "--no_rev requires --mates.\n");
exit(EXIT_FAILURE);
}
// Check for null string prefixes
if (!(strlen(input->filename[0]) && strlen(output->filename[0]))) {
fprintf(stderr, "Error: NULL prefix strings are not permitted.\n");
exit(EXIT_FAILURE);
}
// Construct input filenames
utstring_printf(in_read1_fq_fn, "%s.read1.fastq", input->filename[0]);
utstring_printf(in_read2_fq_fn, "%s.read2.fastq", input->filename[0]);
utstring_printf(in_single1_fq_fn, "%s.single.fastq", input->filename[0]);
FILE *in_read_file = NULL;
num_input_singles_files = 1;
// Try to open a singlet fastq file
// Check singlet output options -s and -v
// Set input singlet names to
// - *.single.fastq or
// - *.single1.fastq and *.single2.fastq
if (!(in_read_file = ss_get_gzFile(utstring_body(in_single1_fq_fn), "r"))) {
utstring_clear(in_single1_fq_fn);
utstring_printf(in_single1_fq_fn, "%s.single1.fastq", input->filename[0]);
utstring_printf(in_single2_fq_fn, "%s.single2.fastq", input->filename[0]);
num_input_singles_files = 2;
if ((in_read_file = ss_get_gzFile(utstring_body(in_single1_fq_fn), "r")) || (in_read_file = ss_get_gzFile(utstring_body(in_single2_fq_fn), "r"))) {
singles_flag = 1; // Two singlet outputs
} else {
singles_flag = num_singles->count; // Number of singlet outputs set by -s parm
if (inv_singles->count) {
fprintf(stderr, "Error: Invalid option -v, No input singlet file(s) found. Use -s to select multiple output singlet files.\n");
exit(EXIT_FAILURE);
}
}
}
if (in_read_file) {
gzclose(in_read_file);
if (num_singles->count) {
fprintf(stderr, "Error: Invalid option -s, Input singlet file(s) found, use -v to change the number of output singlet files.\n");
exit(EXIT_FAILURE);
}
}
// singles->count inverts the current singles file input scheme
singles_flag = (singles_flag ^ inv_singles->count);
// Check if input fastq is colorspace
// If some files are colorspace and some are basespace, throw an error
int fcount = 0;
int cscount = 0;
fcount += ss_is_fastq(utstring_body(in_read1_fq_fn));
fcount += ss_is_fastq(utstring_body(in_read2_fq_fn));
fcount += ss_is_fastq(utstring_body(in_single1_fq_fn));
fcount += ss_is_fastq(utstring_body(in_single2_fq_fn));
cscount += (ss_is_fastq(utstring_body(in_read1_fq_fn)) && ss_is_colorspace_fastq(utstring_body(in_read1_fq_fn)));
cscount += (ss_is_fastq(utstring_body(in_read2_fq_fn)) && ss_is_colorspace_fastq(utstring_body(in_read2_fq_fn)));
cscount += (ss_is_fastq(utstring_body(in_single1_fq_fn)) && ss_is_colorspace_fastq(utstring_body(in_single1_fq_fn)));
cscount += (ss_is_fastq(utstring_body(in_single2_fq_fn)) && ss_is_colorspace_fastq(utstring_body(in_single2_fq_fn)));
if (cscount && (cscount != fcount)) {
printf("Error: Mixed colorspace and basespace FASTQ files detected\n");
exit(EXIT_FAILURE);
}
colorspace_flag = cscount ? 1 : 0;
// Output filenames
if (fasta->count) {
ss_strcat_utstring(out_filetype, "fasta");
read_count_divisor = 2;
} else {
ss_strcat_utstring(out_filetype, "fastq");
read_count_divisor = 4;
}
if (!only_mates->count) {
utstring_printf(out_read1_fn, "%s.read1.%s", output->filename[0], utstring_body(out_filetype));
utstring_printf(out_read2_fn, "%s.read2.%s", output->filename[0], utstring_body(out_filetype));
}
if (singles_flag == 1) {
utstring_printf(out_single1_fn, "%s.single1.%s", output->filename[0], utstring_body(out_filetype));
utstring_printf(out_single2_fn, "%s.single2.%s", output->filename[0], utstring_body(out_filetype));
} else {
utstring_printf(out_single1_fn, "%s.single.%s", output->filename[0], utstring_body(out_filetype));
}
if (mates->count) {
utstring_printf(out_mates_fn, "%s.mates.%s", output->filename[0], utstring_body(out_filetype));
}
////////////////////////////////////////////////////////////////////////////////////////////////
// Begin processing!
#ifdef _OPENMP
omp_set_num_threads(10);
#endif
// This is the value of a non-valid pipe descriptor
#define NO_PIPE 0
int r1_pipe[2];
int r2_pipe[2];
int s1_pipe[2];
int s2_pipe[2];
pipe(r1_pipe);
pipe(r2_pipe);
pipe(s1_pipe);
pipe(s2_pipe);
int r1_out_pipe[2];
int r2_out_pipe[2];
int mates_out_pipe[2];
int s1_out_pipe[2];
int s2_out_pipe[2];
pipe(r1_out_pipe);
pipe(r2_out_pipe);
pipe(mates_out_pipe);
pipe(s1_out_pipe);
pipe(s2_out_pipe);
#pragma omp parallel sections default(shared)
{
#pragma omp section
{ // Read1 reader
fq_stream_trimmer(in_read1_fq_fn, r1_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_r1, &R1_org, '\0', fasta->count);
}
#pragma omp section
{ // Read1 writer
R1_cnt = ss_stream_writer(out_read1_fn, r1_out_pipe[0], gzip->count) / read_count_divisor;
}
#pragma omp section
{ // Read2 reader
fq_stream_trimmer(in_read2_fq_fn, r2_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_r2, &R2_org, '\0', fasta->count);
}
#pragma omp section
{ // Read2 writer
R2_cnt = ss_stream_writer(out_read2_fn, r2_out_pipe[0], gzip->count) / read_count_divisor;
}
#pragma omp section
{ // Single1 reader
// When there is only one input singles file, but two output singles files, then supply which mate to use for this stream in the split parameter
if ((singles_flag) && (num_input_singles_files == 1)) {
singlet1_cnt = fq_stream_trimmer(in_single1_fq_fn, s1_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_s1, &singlet1_org, '1', fasta->count);
} else {
singlet1_cnt = fq_stream_trimmer(in_single1_fq_fn, s1_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_s1, &singlet1_org, '\0', fasta->count);
}
}
#pragma omp section
{ // Single1 writer
s1_cnt = ss_stream_writer(out_single1_fn, s1_out_pipe[0], gzip->count) / read_count_divisor;
}
#pragma omp section
{ // Single2 reader
// When there is only one input singles file, but two output singles files, then supply which mate to use for this stream in the split parameter
if ((singles_flag) && (num_input_singles_files == 1)) {
singlet2_cnt = fq_stream_trimmer(in_single1_fq_fn, s2_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_s2, &singlet2_org, '2', fasta->count);
} else {
singlet2_cnt = fq_stream_trimmer(in_single2_fq_fn, s2_pipe[1], out_read_prefix, no_pre->count, pre_read_len->count, &comp_s2, &singlet2_org, '\0', fasta->count);
}
}
#pragma omp section
{ // Single2 writer
s2_cnt = ss_stream_writer(out_single2_fn, s2_out_pipe[0], gzip->count) / read_count_divisor;
}
#pragma omp section
{ // Velvet mates writer
// Divide count by 2 because both R1 and R2 reads go through this writer
mp_cnt = ss_stream_writer(out_mates_fn, mates_out_pipe[0], gzip->count) / 2 / read_count_divisor;
}
#pragma omp section
{ // Dispatcher
// Allocate data buffer strings
UT_string *r1_data;
utstring_new(r1_data);
UT_string *r2_data;
utstring_new(r2_data);
UT_string *s1_data;
utstring_new(s1_data);
UT_string *s2_data;
utstring_new(s2_data);
UT_string *rev_tmp;
utstring_new(rev_tmp);
UT_string *rev_data;
utstring_new(rev_data);
// Pipes
FILE *r1_in = fdopen(r1_pipe[0],"r");
FILE *r2_in = fdopen(r2_pipe[0],"r");
FILE *s1_in = fdopen(s1_pipe[0],"r");
FILE *s2_in = fdopen(s2_pipe[0],"r");
FILE *mates_out = fdopen(mates_out_pipe[1],"w");
FILE *r1_out = fdopen(r1_out_pipe[1],"w");
FILE *r2_out = fdopen(r2_out_pipe[1],"w");
FILE *s1_out = fdopen(s1_out_pipe[1],"w");
FILE *s2_out = fdopen(s2_out_pipe[1],"w");
if (!singles_flag) {
fclose(s2_out);
s2_out = s1_out;
}
// Flags for data left in single files
int single1_hungry = 1;
int single2_hungry = 1;
// Handle read1 and read2 files
while (ss_get_utstring(r1_in, r1_data)) {
if (!ss_get_utstring(r2_in, r2_data)) {
fprintf(stderr, "Error: Input read1 and read2 files are not synced\n");
exit(EXIT_FAILURE);
}
if (keep_read(r1_data)) {
if (keep_read(r2_data)) {
// Output both read1 and read2
if (mates->count) {
if (only_mates->count) {
// Interleaved velvet output only
output_read(r1_data, NULL, NULL, r1_in, NULL, mates_out, fasta->count);
if (no_rev->count || !colorspace_flag) {
output_read(r2_data, NULL, NULL, r2_in, NULL, mates_out, fasta->count);
} else {
output_read(r2_data, rev_data, rev_tmp, r2_in, NULL, mates_out, fasta->count);
}
} else {
// Interleaved velvet output and normal read file output
output_read(r1_data, NULL, NULL, r1_in, r1_out, mates_out, fasta->count);
if (no_rev->count || !colorspace_flag) {
output_read(r2_data, NULL, NULL, r2_in, r2_out, mates_out, fasta->count);
} else {
output_read(r2_data, rev_data, rev_tmp, r2_in, r2_out, mates_out, fasta->count);
}
}
} else {
// No interleaved velvet output
output_read(r1_data, NULL, NULL, r1_in, r1_out, NULL, fasta->count);
output_read(r2_data, NULL, NULL, r2_in, r2_out, NULL, fasta->count);
}
} else {
// Discard read2, output read1 as singlet
output_read(r1_data, NULL, NULL, r1_in, s1_out, NULL, fasta->count);
read1_singlet_cnt++;
}
} else {
if (keep_read(r2_data)) {
// Discard read1, output read2 as singlet
output_read(r2_data, NULL, NULL, r2_in, s2_out, NULL, fasta->count);
read2_singlet_cnt++;
}
}
// Process reads from singles here to take advantage of
// parallelism
if (single1_hungry || single2_hungry) {
if (single1_hungry) {
if (ss_get_utstring(s1_in, s1_data)) {
if (keep_read(s1_data)) {
output_read(s1_data, NULL, NULL, s1_in, s1_out, NULL, fasta->count);
}
} else {
single1_hungry = 0;
}
}
if (single2_hungry) {
if (ss_get_utstring(s2_in, s2_data)) {
if (keep_read(s2_data)) {
output_read(s2_data, NULL, NULL, s2_in, s2_out, NULL, fasta->count);
}
} else {
single2_hungry = 0;
}
}
}
}
while (single1_hungry || single2_hungry) {
if (single1_hungry) {
if (ss_get_utstring(s1_in, s1_data)) {
if (keep_read(s1_data)) {
output_read(s1_data, NULL, NULL, s1_in, s1_out, NULL, fasta->count);
}
} else {
single1_hungry = 0;
}
}
if (single2_hungry) {
if (ss_get_utstring(s2_in, s2_data)) {
if (keep_read(s2_data)) {
output_read(s2_data, NULL, NULL, s2_in, s2_out, NULL, fasta->count);
}
} else {
single2_hungry = 0;
}
}
}
fclose(r1_in);
fclose(r2_in);
fclose(s1_in);
fclose(s2_in);
fclose(mates_out);
fclose(r1_out);
fclose(r2_out);
fclose(s1_out);
if (singles_flag) {
fclose(s2_out);
}
// Free buffers
utstring_free(r1_data);
utstring_free(r2_data);
utstring_free(s1_data);
utstring_free(s2_data);
utstring_free(rev_tmp);
utstring_free(rev_data);
}
}
if (!(R1_org+singlet1_org+singlet2_org)) {
fprintf(stderr, "ERROR! No reads found in input files, or input(s) not found.\n");
exit(EXIT_FAILURE);
}
if (R1_org != R2_org) {
fprintf(stderr, "\nWarning! read1 and read2 fastq files did not contain an equal number of reads. %lu %lu\n", R1_org, R2_org);
}
if ((R1_org + R2_org) && !(singlet1_cnt + singlet2_cnt)) {
fprintf(stderr, "\nWarning! read1/read2 files were processed, but no corresponding input singlets were found.\n");
}
if (entropy->count) {
printf("\nLow complexity reads discarded: Read1: %lu, Read2: %lu, Singlets: %lu %lu\n", comp_r1, comp_r2, comp_s1, comp_s2);
}
mp_org = R1_org;
if (!only_mates->count) {
mp_cnt = R1_cnt;
}
printf("\nMatepairs: Before: %lu, After: %lu\n", mp_org, mp_cnt);
printf("Singlets: Before: %lu %lu After: %lu %lu\n", singlet1_org, singlet2_org, s1_cnt, s2_cnt);
printf("Read1 singlets: %lu, Read2 singlets: %lu, Original singlets: %lu %lu\n", read1_singlet_cnt, read2_singlet_cnt, singlet1_cnt, singlet2_cnt);
printf("Total Reads Processed: %lu, Reads retained: %lu\n", 2*mp_org+singlet1_org+singlet2_org, 2*mp_cnt+s1_cnt+s2_cnt);
utstring_free(in_read1_fq_fn);
utstring_free(in_read2_fq_fn);
utstring_free(in_single1_fq_fn);
utstring_free(in_single2_fq_fn);
utstring_free(out_read1_fn);
utstring_free(out_read2_fn);
utstring_free(out_single1_fn);
utstring_free(out_single2_fn);
utstring_free(out_mates_fn);
utstring_free(out_filetype);
utstring_free(out_read_prefix);
exit(EXIT_SUCCESS);
}
int main(int argc, char **argv)
{
const char *progname = "mv";
struct arg_str *backupc = arg_str0(NULL, "backup", "[CONTROL]", "make a backup of each existing destination file");
struct arg_lit *backup = arg_lit0("b", NULL, "like --backup but does not accept an argument");
struct arg_lit *force = arg_lit0("f", "force", "do not prompt before overwriting");
struct arg_rem *force1 = arg_rem (NULL, " equivalent to --reply=yes");
struct arg_lit *interact = arg_lit0("i", "interactive", "Prompt before overwriting");
struct arg_rem *interact1= arg_rem (NULL, " equivalent to --reply=yes");
struct arg_str *reply = arg_str0(NULL,"reply", "{yes,no,query}", "specify how to handle the prompt about an");
struct arg_rem *reply1 = arg_rem (NULL, " existing destination file");
struct arg_lit *strpslsh = arg_lit0(NULL,"strip-trailing-slashes", "remove any trailing slashes from each SOURCE argument");
struct arg_str *suffix = arg_str0("S", "suffix", "SUFFIX", "override the usual backup suffix");
struct arg_str *targetd = arg_str0(NULL,"target-directory", "DIRECTORY", "move all SOURCE arguments into DIRECTORY");
struct arg_lit *update = arg_lit0("u", "update", "copy only when the SOURCE file is newer");
struct arg_rem *update1 = arg_rem (NULL, " than the destination file or when the");
struct arg_rem *update2 = arg_rem (NULL, " destination file is missing");
struct arg_lit *verbose = arg_lit0("v", "verbose", "explain what is being done");
struct arg_lit *help = arg_lit0(NULL,"help", "display this help and exit");
struct arg_lit *version = arg_lit0(NULL,"version", "display version information and exit");
struct arg_file *files = arg_filen(NULL, NULL, "SOURCE", 1, argc+2, NULL);
struct arg_rem *dest = arg_rem ("DEST|DIRECTORY", NULL);
struct arg_end *end = arg_end(20);
void* argtable[] = {backupc,backup,force,force1,interact,interact1,reply,reply1,strpslsh,suffix,targetd,update,update1,update2,verbose,help,version,files,dest,end};
int exitcode=0;
int nerrors;
/* verify the argtable[] entries were allocated sucessfully */
if (arg_nullcheck(argtable) != 0)
{
/* NULL entries were detected, some allocations must have failed */
printf("%s: insufficient memory\n",progname);
exitcode=1;
goto exit;
}
/* Set default argument values prior to parsing */
backupc->sval[0] = "existing"; /* --backup={none,off,numbered,t,existing,nil,simple,never} */
suffix->sval[0] = "~"; /* --suffix=~ */
reply->sval[0] = "query"; /* --reply={yes,no,query} */
targetd->sval[0] = NULL;
/* Parse the command line as defined by argtable[] */
nerrors = arg_parse(argc,argv,argtable);
/* special case: '--help' takes precedence over error reporting */
if (help->count > 0)
{
printf("Usage: %s", progname);
arg_print_syntax(stdout,argtable,"\n");
printf("Rename SOURCE to DEST, or move SOURCE(s) to DIRECTORY.\n\n");
arg_print_glossary(stdout,argtable," %-30s %s\n");
printf("\nThe backup suffix is \"~\", unless set with --suffix or SIMPLE_BACKUP_SUFFIX.\n"
"The version control method may be selected via the --backup option or through\n"
"the VERSION_CONTROL environment variable. Here are the values:\n\n"
" none, off never make backups (even if --backup is given)\n"
" numbered, t make numbered backups\n"
" existing, nil numbered if numbered backups exist, simple otherwise\n"
" simple, never always make simple backups\n\n"
"Report bugs to <foo@bar>.\n");
exitcode=0;
goto exit;
}
/* special case: '--version' takes precedence error reporting */
if (version->count > 0)
{
printf("'%s' example program for the \"argtable\" command line argument parser.\n",progname);
printf("September 2003, Stewart Heitmann\n");
exitcode=0;
goto exit;
}
/* If the parser returned any errors then display them and exit */
if (nerrors > 0)
{
/* Display the error details contained in the arg_end struct.*/
arg_print_errors(stdout,end,progname);
printf("Try '%s --help' for more information.\n",progname);
exitcode=1;
goto exit;
}
/* Command line parsing is complete, do the main processing */
exitcode = mymain(backupc->sval[0],
backup->count,
force->count,
interact->count,
reply->sval[0],
strpslsh->count,
suffix->sval[0],
targetd->sval[0],
update->count,
verbose->count,
files->filename,
files->count);
exit:
/* deallocate each non-null entry in argtable[] */
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
return exitcode;
}
int main(int argc, char **argv)
{
/* The argtable[] entries define the command line options */
void *argtable[] = {
a = arg_lit0("a", "all", "do not hide entries starting with ."),
A = arg_lit0("A", "almost-all", "do not list implied . and .."),
author = arg_lit0(NULL,"author", "print the author of each file"),
b = arg_lit0("b", "escape", "print octal escapes for nongraphic characters"),
blocksize = arg_int0(NULL,"block-size","SIZE", "use SIZE-byte blocks"),
B = arg_lit0("B", "ignore-backups", "do not list implied entries ending with ~"),
c = arg_lit0("c", NULL, "with -lt: sort by, and show, ctime (time of last"),
arg_rem(NULL, " modification of file status information)"),
arg_rem(NULL, " with -l: show ctime and sort by name"),
arg_rem(NULL, " otherwise: sort by ctime"),
C = arg_lit0("C", NULL, "list entries by columns"),
color = arg_str0(NULL,"color","WHEN", "control whether color is used to distinguish file"),
arg_rem(NULL, " types. WHEN may be `never', `always', or `auto'"),
d = arg_lit0("d", "directory", "list directory entries instead of contents,"),
arg_rem(NULL, " and do not dereference symbolic links"),
D = arg_lit0("D", "dired", "generate output designed for Emacs' dired mode"),
f = arg_lit0("f", NULL, "do not sort, enable -aU, disable -lst"),
F = arg_lit0("F", "classify", "append indicator (one of */=@|) to entries"),
format = arg_str0(NULL,"format","WORD", "across -x, commas -m, horizontal -x, long -l,"),
arg_rem (NULL, " single-column -1, verbose -l, vertical -C"),
fulltime = arg_lit0(NULL,"full-time", "like -l --time-style=full-iso"),
g = arg_lit0("g", NULL, "like -l, but do not list owner"),
G = arg_lit0("G", "no-group", "inhibit display of group information"),
h = arg_lit0("h", "human-readable", "print sizes in human readable format (e.g., 1K 234M 2G)"),
si = arg_lit0(NULL,"si", "likewise, but use powers of 1000 not 1024"),
H = arg_lit0("H", "dereference-command-line","follow symbolic links listed on the command line"),
deref = arg_lit0(NULL,"dereference-command-line-symlink-to-dir","follow each command line symbolic link"),
arg_rem(NULL, " that points to a directory"),
indic = arg_str0(NULL,"indicator-style","WORD","append indicator with style WORD to entry names:"),
arg_rem (NULL, " none (default), classify (-F), file-type (-p)"),
i = arg_lit0("i", "inode", "print index number of each file"),
I = arg_str0("I", "ignore","PATTERN", "do not list implied entries matching shell PATTERN"),
k = arg_lit0("k", NULL, "like --block-size=1K"),
l = arg_lit0("l", NULL, "use a long listing format"),
L = arg_lit0("L", "dereference", "when showing file information for a symbolic"),
arg_rem (NULL, " link, show information for the file the link"),
arg_rem (NULL, " references rather than for the link itself"),
m = arg_lit0("m", NULL, "fill width with a comma separated list of entries"),
n = arg_lit0("n", "numeric-uid-gid", "like -l, but list numeric UIDs and GIDs"),
N = arg_lit0("N", "literal", "print raw entry names (don't treat e.g. control"),
arg_rem (NULL, " characters specially)"),
o = arg_lit0("o", NULL, "like -l, but do not list group information"),
p = arg_lit0("p", "file-type", "append indicator (one of /=@|) to entries"),
q = arg_lit0("q", "hide-control-chars", "print ? instead of non graphic characters"),
shcont = arg_lit0(NULL,"show-control-chars", "show non graphic characters as-is (default"),
arg_rem (NULL, "unless program is `ls' and output is a terminal)"),
Q = arg_lit0("Q", "quote-name", "enclose entry names in double quotes"),
Qstyle = arg_str0(NULL,"quoting-style","WORD","use quoting style WORD for entry names:"),
arg_rem (NULL, " literal, locale, shell, shell-always, c, escape"),
r = arg_lit0("r", "reverse", "reverse order while sorting"),
R = arg_lit0("R", "recursive", "list subdirectories recursively"),
s = arg_lit0("s", "size", "print size of each file, in blocks"),
S = arg_lit0("S", NULL, "sort by file size"),
sort = arg_str0(NULL,"sort","WORD", "extension -X, none -U, size -S, time -t, version -v,"),
arg_rem (NULL, "status -c, time -t, atime -u, access -u, use -u"),
Time = arg_str0(NULL,"time","WORD", "show time as WORD instead of modification time:"),
arg_rem (NULL, " atime, access, use, ctime or status; use"),
arg_rem (NULL, " specified time as sort key if --sort=time"),
timesty = arg_str0(NULL, "time-style","STYLE", "show times using style STYLE:"),
arg_rem (NULL, " full-iso, long-iso, iso, locale, +FORMAT"),
arg_rem (NULL, "FORMAT is interpreted like `date'; if FORMAT is"),
arg_rem (NULL, "FORMAT1<newline>FORMAT2, FORMAT1 applies to"),
arg_rem (NULL, "non-recent files and FORMAT2 to recent files;"),
arg_rem (NULL, "if STYLE is prefixed with `posix-', STYLE"),
arg_rem (NULL, "takes effect only outside the POSIX locale"),
t = arg_lit0("t", NULL, "sort by modification time"),
T = arg_int0("T", "tabsize", "COLS", "assume tab stops at each COLS instead of 8"),
u = arg_lit0("u", NULL, "with -lt: sort by, and show, access time"),
arg_rem (NULL, " with -l: show access time and sort by name"),
arg_rem (NULL, " otherwise: sort by access time"),
U = arg_lit0("U", NULL, "do not sort; list entries in directory order"),
v = arg_lit0("v", NULL, "sort by version"),
w = arg_int0("w", "width", "COLS", "assume screen width instead of current value"),
x = arg_lit0("x", NULL, "list entries by lines instead of by columns"),
X = arg_lit0("X", NULL, "sort alphabetically by entry extension"),
one = arg_lit0("1", NULL, "list one file per line"),
help = arg_lit0(NULL,"help", "display this help and exit"),
version = arg_lit0(NULL,"version", "display version information and exit"),
files = arg_filen(NULL, NULL, "FILE", 0, argc+2, NULL),
end = arg_end(20),
};
const char *progname = "ls";
int exitcode=0;
int nerrors;
/* verify the argtable[] entries were allocated sucessfully */
if (arg_nullcheck(argtable) != 0)
{
/* NULL entries were detected, some allocations must have failed */
printf("%s: insufficient memory\n",progname);
exitcode=1;
goto exit;
}
/* allow optional argument values for --color */
/* and set the default value to "always" */
color->hdr.flag |= ARG_HASOPTVALUE;
color->sval[0] = "always";
/* Parse the command line as defined by argtable[] */
nerrors = arg_parse(argc,argv,argtable);
/* special case: '--help' takes precedence over error reporting */
if (help->count > 0)
{
printf("Usage: %s", progname);
arg_print_syntax(stdout,argtable,"\n");
printf("List information about the FILE(s) (the current directory by default).\n");
printf("Sort entries alphabetically if none of -cftuSUX nor --sort.\n\n");
arg_print_glossary(stdout,argtable," %-25s %s\n");
printf("\nSIZE may be (or may be an integer optionally followed by) one of following:\n"
"kB 1000, K 1024, MB 1,000,000, M 1,048,576, and so on for G, T, P, E, Z, Y.\n\n"
"By default, color is not used to distinguish types of files. That is\n"
"equivalent to using --color=none. Using the --color option without the\n"
"optional WHEN argument is equivalent to using --color=always. With\n"
"--color=auto, color codes are output only if standard output is connected\n"
"to a terminal (tty).\n\n"
"Report bugs to <foo@bar>.\n");
exitcode=0;
goto exit;
}
/* special case: '--version' takes precedence error reporting */
if (version->count > 0)
{
printf("'%s' example program for the \"argtable\" command line argument parser.\n",progname);
printf("September 2003, Stewart Heitmann\n");
exitcode=0;
goto exit;
}
/* If the parser returned any errors then display them and exit */
if (nerrors > 0)
{
/* Display the error details contained in the arg_end struct.*/
arg_print_errors(stdout,end,progname);
printf("Try '%s --help' for more information.\n",progname);
exitcode=1;
goto exit;
}
/* Command line parsing is complete, do the main processing */
exitcode = mymain();
exit:
/* deallocate each non-null entry in argtable[] */
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
return exitcode;
}
int ParseMyArgs(int argc, char *argv[])
{
int exitcode=0;
int nerrors;
argtable[0] =i= arg_lit0("i", "insert", "insert a tag into the text file");
argtable[1]=s= arg_lit0("s", "separate", "separate a text file into smaller parts");
arg_rem("NULL", "new files with number suffix");
argtable[2] =author= arg_lit0(NULL,"author", "print the author of each file");
argtable[3]=keyword= arg_str0(NULL, "keyword", "WORD", "keyword to seperate the parts in ");
arg_rem(NULL, " a text book");
argtable[4] =size= arg_int0(NULL,"size", "SIZE", "size of each of parts");
argtable[5] =help= arg_lit0(NULL,"help", "display this help and exit");
argtable[6] =version= arg_lit0(NULL,"version", "display version information and exit");
argtable[7] = files = arg_filen(NULL, NULL, "FILE", 0, argc+2, NULL),
argtable[8] = end= arg_end(20);
/* verify the argtable[] entries were allocated sucessfully */
if (arg_nullcheck(argtable) != 0)
{
/* NULL entries were detected, some allocations must have failed */
printf("%s: insufficient memory\n",argv[0]);
exitcode=1;
goto exit;
}
/* Parse the command line as defined by argtable[] */
nerrors = arg_parse(argc,argv,argtable);
if(author->count >0)
{
printf("This software is developed by a teacher and some students\n");
printf("Detail can be found in README file");
}
/* special case: '--help' takes precedence over error reporting */
if (help->count > 0)
{
printf("Usage: %s", argv[0]);
arg_print_syntax(stdout,argtable,"\n");
arg_print_glossary(stdout,argtable," %-25s %s\n");
exitcode=1;
goto exit;
}
/* special case: '--version' takes precedence error reporting */
if (version->count > 0){
printf("Dec 2010, \n");
exitcode=1;
goto exit;
}
/* If the parser returned any errors then display them and exit */
if (nerrors > 0)
{
/* Display the error details contained in the arg_end struct.*/
arg_print_errors(stdout,end,argv[0]);
printf("Try '%s --help' for more information.\n",argv[0]);
exitcode=1;
goto exit;
}
/* Command line parsing is complete, do the main processing */
exit:
return exitcode;
}
/**
* @brief Parse command line parameters. Will exit if help/usage etc
* are called or or call Log(&rLog, LOG_FATAL, ) if an error was detected.
*
* @param[out] user_opts
* User parameter struct, with defaults already set.
* @param[in] argc
* mains argc
* @param[in] argv
* mains argv
*
*/
void
ParseCommandLine(cmdline_opts_t *user_opts, int argc, char **argv)
{
/* argtable command line parsing:
* see
* http://argtable.sourceforge.net/doc/argtable2-intro.html
*
* basic structure is: arg_xxxN:
* xxx can be int, lit, db1, str, rex, file or date
* If N = 0, arguments may appear zero-or-once; N = 1 means
* exactly once, N = n means up to maxcount times
*
*
* @note: changes here, might also affect main.cpp:ConvertOldCmdLine()
*
*/
struct arg_rem *rem_seq_input = arg_rem(NULL, "\nSequence Input:");
struct arg_file *opt_seqin = arg_file0("i", "in,infile",
"{<file>,-}",
"Multiple sequence input file (- for stdin)");
struct arg_file *opt_hmm_in = arg_filen(NULL, "hmm-in", "<file>",
/*min*/ 0, /*max*/ 128,
"HMM input files");
struct arg_lit *opt_dealign = arg_lit0(NULL, "dealign",
"Dealign input sequences");
struct arg_file *opt_profile1 = arg_file0(NULL, "profile1,p1",
"<file>",
"Pre-aligned multiple sequence file (aligned columns will be kept fix)");
struct arg_file *opt_profile2 = arg_file0(NULL, "profile2,p2",
"<file>",
"Pre-aligned multiple sequence file (aligned columns will be kept fix)");
struct arg_str *opt_seqtype = arg_str0("t", "seqtype",
"{Protein, RNA, DNA}",
"Force a sequence type (default: auto)");
/* struct arg_lit *opt_force_protein = arg_lit0(NULL, "protein",
"Set sequence type to protein even if Clustal guessed nucleic acid"); */
struct arg_str *opt_infmt = arg_str0(NULL, "infmt",
"{a2m=fa[sta],clu[stal],msf,phy[lip],selex,st[ockholm],vie[nna]}",
"Forced sequence input file format (default: auto)");
struct arg_rem *rem_guidetree = arg_rem(NULL, "\nClustering:");
struct arg_str *opt_pairdist = arg_str0("p", "pairdist",
"{ktuple}",
"Pairwise alignment distance measure");
struct arg_file *opt_distmat_in = arg_file0(NULL, "distmat-in",
"<file>",
"Pairwise distance matrix input file (skips distance computation)");
struct arg_file *opt_distmat_out = arg_file0(NULL, "distmat-out",
"<file>",
"Pairwise distance matrix output file");
struct arg_file *opt_guidetree_in = arg_file0(NULL, "guidetree-in",
"<file>",
"Guide tree input file (skips distance computation and guide-tree clustering step)");
struct arg_file *opt_guidetree_out = arg_file0(NULL, "guidetree-out",
"<file>",
"Guide tree output file");
/* AW: mbed is default since at least R253
struct arg_lit *opt_mbed = arg_lit0(NULL, "mbed",
"Fast, Mbed-like clustering for guide-tree calculation");
struct arg_lit *opt_mbed_iter = arg_lit0(NULL, "mbed-iter",
"Use Mbed-like clustering also during iteration");
*/
/* Note: might be better to use arg_str (mbed=YES/NO) but I don't want to introduce an '=' into pipeline, FS, r250 -> */
struct arg_lit *opt_full = arg_lit0(NULL, "full",
"Use full distance matrix for guide-tree calculation (might be slow; mBed is default)");
struct arg_lit *opt_full_iter = arg_lit0(NULL, "full-iter",
"Use full distance matrix for guide-tree calculation during iteration (might be slowish; mBed is default)");
struct arg_str *opt_clustering = arg_str0("c", "clustering",
"{UPGMA}",
"Clustering method for guide tree");
struct arg_rem *rem_aln_output = arg_rem(NULL, "\nAlignment Output:");
struct arg_file *opt_outfile = arg_file0("o", "out,outfile",
"{file,-}",
"Multiple sequence alignment output file (default: stdout)");
struct arg_str *opt_outfmt = arg_str0(NULL, "outfmt",
"{a2m=fa[sta],clu[stal],msf,phy[lip],selex,st[ockholm],vie[nna]}",
"MSA output file format (default: fasta)");
struct arg_rem *rem_iteration = arg_rem(NULL, "\nIteration:");
struct arg_str *opt_num_iterations = arg_str0(NULL, "iterations,iter",
/* FIXME "{<n>,auto}", "Number of combined guide-tree/HMM iterations"); */
"<n>", "Number of (combined guide-tree/HMM) iterations");
struct arg_int *opt_max_guidetree_iterations = arg_int0(NULL, "max-guidetree-iterations",
"<n>", "Maximum number guidetree iterations");
struct arg_int *opt_max_hmm_iterations = arg_int0(NULL, "max-hmm-iterations",
"<n>", "Maximum number of HMM iterations");
struct arg_rem *rem_limits = arg_rem(NULL, "\nLimits (will exit early, if exceeded):");
struct arg_int *opt_max_seq = arg_int0(NULL, "maxnumseq", "<n>",
"Maximum allowed number of sequences");
struct arg_int *opt_max_seqlen = arg_int0(NULL, "maxseqlen", "<l>",
"Maximum allowed sequence length");
struct arg_rem *rem_misc = arg_rem(NULL, "\nMiscellaneous:");
struct arg_lit *opt_autooptions = arg_lit0(NULL, "auto",
"Set options automatically (might overwrite some of your options)");
struct arg_int *opt_threads = arg_int0(NULL, "threads", "<n>",
"Number of processors to use");
struct arg_file *opt_logfile = arg_file0("l", "log",
"<file>",
"Log all non-essential output to this file");
struct arg_lit *opt_help = arg_lit0("h", "help",
"Print this help and exit");
struct arg_lit *opt_version = arg_lit0(NULL, "version",
"Print version information and exit");
struct arg_lit *opt_long_version = arg_lit0(NULL, "long-version",
"Print long version information and exit");
struct arg_lit *opt_verbose = arg_litn("v", "verbose",
0, 3,
"Verbose output (increases if given multiple times)");
struct arg_lit *opt_force = arg_lit0(NULL, "force",
"Force file overwriting");
struct arg_int *opt_macram = arg_int0(NULL, "MAC-RAM", "<n>", /* keep this quiet for the moment, FS r240 -> */
NULL/*"maximum amount of RAM to use for MAC algorithm (in MB)"*/);
struct arg_end *opt_end = arg_end(10); /* maximum number of errors
* to store */
void *argtable[] = {rem_seq_input,
opt_seqin,
opt_hmm_in,
opt_dealign,
opt_profile1,
opt_profile2,
opt_seqtype,
/* opt_force_protein, */
opt_infmt,
rem_guidetree,
#if 0
/* no other options then default available or not implemented */
opt_pairdist,
#endif
opt_distmat_in,
opt_distmat_out,
opt_guidetree_in,
opt_guidetree_out,
opt_full, /* FS, r250 -> */
opt_full_iter, /* FS, r250 -> */
#if 0
/* no other options then default available */
opt_clustering,
#endif
rem_aln_output,
opt_outfile,
opt_outfmt,
rem_iteration,
opt_num_iterations,
opt_max_guidetree_iterations,
opt_max_hmm_iterations,
rem_limits,
opt_max_seq,
opt_max_seqlen,
rem_misc,
opt_autooptions,
opt_threads,
opt_logfile,
opt_help,
opt_verbose,
opt_version,
opt_long_version,
opt_force,
opt_macram, /* FS, r240 -> r241 */
opt_end};
int nerrors;
/* Verify the argtable[] entries were allocated sucessfully
*/
if (arg_nullcheck(argtable)) {
Log(&rLog, LOG_FATAL, "insufficient memory (for argtable allocation)");
}
/* Parse the command line as defined by argtable[]
*/
nerrors = arg_parse(argc, argv, argtable);
/* Special case: '--help' takes precedence over error reporting
*/
if (opt_help->count > 0) {
printf("%s - %s (%s)\n", PACKAGE_NAME, PACKAGE_VERSION, PACKAGE_CODENAME);
printf("\n");
printf("If you like Clustal-Omega please cite:\n%s\n", CITATION);
printf("If you don't like Clustal-Omega, please let us know why (and cite us anyway).\n");
/* printf("You can contact reach us under %s\n", PACKAGE_BUGREPORT); */
printf("\n");
printf("Check http://www.clustal.org for more information and updates.\n");
printf("\n");
printf("Usage: %s", basename(argv[0]));
arg_print_syntax(stdout,argtable, "\n");
printf("\n");
printf("A typical invocation would be: %s -i my-in-seqs.fa -o my-out-seqs.fa -v\n",
basename(argv[0]));
printf("See below for a list of all options.\n");
arg_print_glossary(stdout, argtable, " %-25s %s\n");
arg_freetable(argtable, sizeof(argtable)/sizeof(argtable[0]));
exit(EXIT_SUCCESS);
}
/* Special case: '--version' takes precedence over error reporting
*/
if (opt_version->count > 0) {
printf("%s\n", PACKAGE_VERSION);
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
exit(EXIT_SUCCESS);
}
/* Special case: '--long-version' takes precedence over error reporting
*/
if (opt_long_version->count > 0) {
char zcLongVersion[1024];
PrintLongVersion(zcLongVersion, sizeof(zcLongVersion));
printf("%s\n", zcLongVersion);
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
exit(EXIT_SUCCESS);
}
/* If the parser returned any errors then display them and exit
*/
if (nerrors > 0) {
/* Display the error details contained in the arg_end struct.*/
arg_print_errors(stdout, opt_end, PACKAGE);
fprintf(stderr, "For more information try: %s --help\n", argv[0]);
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
exit(EXIT_FAILURE);
}
/* ------------------------------------------------------------
*
* Command line successfully parsed. Now transfer values to
* user_opts. While doing so, make sure that given input files
* exist and given output files are writable do not exist, or if
* they do, should be overwritten.
*
* No logic checks here! They are done in a different function
*
* ------------------------------------------------------------*/
/* not part of user_opts because it declared in src/util.h */
if (0 == opt_verbose->count) {
rLog.iLogLevelEnabled = LOG_WARN;
} else if (1 == opt_verbose->count) {
rLog.iLogLevelEnabled = LOG_INFO;
} else if (2 == opt_verbose->count) {
rLog.iLogLevelEnabled = LOG_VERBOSE;
} else if (3 == opt_verbose->count) {
rLog.iLogLevelEnabled = LOG_DEBUG;
}
user_opts->aln_opts.bAutoOptions = opt_autooptions->count;
user_opts->bDealignInputSeqs = opt_dealign->count;
/* NOTE: full distance matrix used to be default - there was
--mbed flag but no --full flag after r250 decided that mBed
should be default - now need --full flag to turn off mBed.
wanted to retain mBed Boolean, so simply added --full flag. if
both flags set (erroneously) want --mbed to overwrite --full,
therefore do --full 1st, the --mbed, FS, r250 */
if (opt_full->count){
user_opts->aln_opts.bUseMbed = FALSE;
}
if (opt_full_iter->count){
user_opts->aln_opts.bUseMbedForIteration = FALSE;
}
user_opts->bForceFileOverwrite = opt_force->count;
/* log-file
*/
if (opt_logfile->count > 0) {
user_opts->pcLogFile = CkStrdup(opt_logfile->filename[0]);
/* warn if already exists or not writable */
if (FileExists(user_opts->pcLogFile) && ! user_opts->bForceFileOverwrite) {
Log(&rLog, LOG_FATAL, "%s '%s'. %s",
"Cowardly refusing to overwrite already existing file",
user_opts->pcLogFile,
"Use --force to force overwriting.");
}
if (! FileIsWritable(user_opts->pcLogFile)) {
Log(&rLog, LOG_FATAL, "Sorry, I do not have permission to write to file '%s'.",
user_opts->pcLogFile);
}
}
/* normal sequence input (no profile)
*/
if (opt_seqin->count > 0) {
user_opts->pcSeqInfile = CkStrdup(opt_seqin->filename[0]);
}
/* Input limitations
*/
/* maximum number of sequences */
if (opt_max_seq->count > 0) {
user_opts->iMaxNumSeq = opt_max_seq->ival[0];
}
/* maximum sequence length */
if (opt_max_seqlen->count > 0) {
user_opts->iMaxSeqLen = opt_max_seqlen->ival[0];
}
/* Output format
*/
if (opt_infmt->count > 0) {
/* avoid gcc warning about discarded qualifier */
char *tmp = (char *)opt_infmt->sval[0];
user_opts->iSeqInFormat = String2SeqfileFormat(tmp);
} else {
user_opts->iSeqInFormat = SQFILE_UNKNOWN;
}
/* Sequence type
*/
if (opt_seqtype->count > 0) {
if (STR_NC_EQ(opt_seqtype->sval[0], "protein")) {
user_opts->iSeqType = SEQTYPE_PROTEIN;
} else if (STR_NC_EQ(opt_seqtype->sval[0], "rna")) {
user_opts->iSeqType = SEQTYPE_RNA;
} else if (STR_NC_EQ(opt_seqtype->sval[0], "dna")) {
user_opts->iSeqType = SEQTYPE_DNA;
} else {
Log(&rLog, LOG_FATAL, "Unknown sequence type '%s'", opt_seqtype->sval[0]);
}
}
/* if (opt_force_protein->count > 0) {
user_opts->iSeqType = SEQTYPE_PROTEIN;
} */
/* Profile input
*/
if (opt_profile1->count > 0) {
user_opts->pcProfile1Infile = CkStrdup(opt_profile1->filename[0]);
if (! FileExists(user_opts->pcProfile1Infile)) {
Log(&rLog, LOG_FATAL, "File '%s' does not exist.", user_opts->pcProfile1Infile);
}
}
if (opt_profile2->count > 0) {
user_opts->pcProfile2Infile = CkStrdup(opt_profile2->filename[0]);
if (! FileExists(user_opts->pcProfile2Infile)) {
Log(&rLog, LOG_FATAL, "File '%s' does not exist.", user_opts->pcProfile2Infile);
}
}
/* HMM input
*/
user_opts->aln_opts.iHMMInputFiles = 0;
user_opts->aln_opts.ppcHMMInput = NULL;
if (opt_hmm_in->count>0) {
int iAux;
user_opts->aln_opts.iHMMInputFiles = opt_hmm_in->count;
user_opts->aln_opts.ppcHMMInput = (char **) CKMALLOC(
user_opts->aln_opts.iHMMInputFiles * sizeof(char*));
for (iAux=0; iAux<opt_hmm_in->count; iAux++) {
user_opts->aln_opts.ppcHMMInput[iAux] = CkStrdup(opt_hmm_in->filename[iAux]);
if (! FileExists(user_opts->aln_opts.ppcHMMInput[iAux])) {
Log(&rLog, LOG_FATAL, "File '%s' does not exist.", user_opts->aln_opts.ppcHMMInput[iAux]);
}
}
}
/* Pair distance method
*/
if (opt_pairdist->count > 0) {
if (STR_NC_EQ(opt_pairdist->sval[0], "ktuple")) {
user_opts->aln_opts.iPairDistType = PAIRDIST_KTUPLE;
} else {
Log(&rLog, LOG_FATAL, "Unknown pairdist method '%s'", opt_pairdist->sval[0]);
}
}
/* Distance matrix input
*/
if (opt_distmat_in->count > 0) {
user_opts->aln_opts.pcDistmatInfile = CkStrdup(opt_distmat_in->filename[0]);
if (! FileExists(user_opts->aln_opts.pcDistmatInfile)) {
Log(&rLog, LOG_FATAL, "File '%s' does not exist.", user_opts->aln_opts.pcDistmatInfile);
}
}
/* Distance matrix output
*/
if (opt_distmat_out->count > 0) {
user_opts->aln_opts.pcDistmatOutfile = CkStrdup(opt_distmat_out->filename[0]);
/* warn if already exists or not writable */
if (FileExists(user_opts->aln_opts.pcDistmatOutfile) && ! user_opts->bForceFileOverwrite) {
Log(&rLog, LOG_FATAL, "%s '%s'. %s",
"Cowardly refusing to overwrite already existing file",
user_opts->aln_opts.pcDistmatOutfile,
"Use --force to force overwriting.");
}
if (! FileIsWritable(user_opts->aln_opts.pcDistmatOutfile)) {
Log(&rLog, LOG_FATAL, "Sorry, I do not have permission to write to file '%s'.",
user_opts->aln_opts.pcDistmatOutfile);
}
}
/* Clustering
*
*/
if (opt_clustering->count > 0) {
if (STR_NC_EQ(opt_clustering->sval[0], "upgma")) {
user_opts->aln_opts.iClusteringType = CLUSTERING_UPGMA;
} else {
Log(&rLog, LOG_FATAL, "Unknown guide-tree clustering method '%s'", opt_clustering->sval[0]);
}
}
/* Guidetree input
*/
if (opt_guidetree_in->count > 0) {
user_opts->aln_opts.pcGuidetreeInfile = CkStrdup(opt_guidetree_in->filename[0]);
if (! FileExists(user_opts->aln_opts.pcGuidetreeInfile)) {
Log(&rLog, LOG_FATAL, "File '%s' does not exist.", user_opts->aln_opts.pcGuidetreeInfile);
}
}
/* Guidetree output
*/
if (opt_guidetree_out->count > 0) {
user_opts->aln_opts.pcGuidetreeOutfile = CkStrdup(opt_guidetree_out->filename[0]);
/* warn if already exists or not writable */
if (FileExists(user_opts->aln_opts.pcGuidetreeOutfile) && ! user_opts->bForceFileOverwrite) {
Log(&rLog, LOG_FATAL, "%s '%s'. %s",
"Cowardly refusing to overwrite already existing file",
user_opts->aln_opts.pcGuidetreeOutfile,
"Use --force to force overwriting.");
}
if (! FileIsWritable(user_opts->aln_opts.pcGuidetreeOutfile)) {
Log(&rLog, LOG_FATAL, "Sorry, I do not have permission to write to file '%s'.",
user_opts->aln_opts.pcGuidetreeOutfile);
}
}
/* max guidetree iterations
*/
if (opt_max_guidetree_iterations->count > 0) {
user_opts->aln_opts.iMaxGuidetreeIterations = opt_max_guidetree_iterations->ival[0];
}
/* max guidetree iterations
*/
if (opt_max_hmm_iterations->count > 0) {
user_opts->aln_opts.iMaxHMMIterations = opt_max_hmm_iterations->ival[0];
}
/* number of iterations
*/
if (opt_num_iterations->count > 0) {
if (STR_NC_EQ(opt_num_iterations->sval[0], "auto")) {
Log(&rLog, LOG_FATAL, "Automatic iteration not supported at the moment.");
user_opts->aln_opts.bIterationsAuto = TRUE;
} else {
int iAux;
user_opts->aln_opts.bIterationsAuto = FALSE;
for (iAux=0; iAux<(int)strlen(opt_num_iterations->sval[0]); iAux++) {
if (! isdigit(opt_num_iterations->sval[0][iAux])) {
Log(&rLog, LOG_FATAL, "Couldn't iteration parameter: %s",
opt_num_iterations->sval[0]);
}
}
user_opts->aln_opts.iNumIterations = atoi(opt_num_iterations->sval[0]);
}
}
/* Alignment output
*/
if (opt_outfile->count > 0) {
user_opts->pcAlnOutfile = CkStrdup(opt_outfile->filename[0]);
/* warn if already exists or not writable */
if (FileExists(user_opts->pcAlnOutfile) && ! user_opts->bForceFileOverwrite) {
Log(&rLog, LOG_FATAL, "%s '%s'. %s",
"Cowardly refusing to overwrite already existing file",
user_opts->pcAlnOutfile,
"Use --force to force overwriting.");
}
if (! FileIsWritable(user_opts->pcAlnOutfile)) {
Log(&rLog, LOG_FATAL, "Sorry, I do not have permission to write to file '%s'.",
user_opts->pcAlnOutfile);
}
}
/* Output format
*/
if (opt_outfmt->count > 0) {
/* avoid gcc warning about discarded qualifier */
char *tmp = (char *)opt_outfmt->sval[0];
user_opts->iAlnOutFormat = String2SeqfileFormat(tmp);
if (SQFILE_UNKNOWN == user_opts->iAlnOutFormat) {
Log(&rLog, LOG_FATAL, "Unknown output format '%s'", opt_outfmt->sval[0]);
}
}
/* Number of threads
*/
#ifdef HAVE_OPENMP
if (opt_threads->count > 0) {
if (opt_threads->ival[0] <= 0) {
Log(&rLog, LOG_FATAL, "Changing number of threads to %d doesn't make sense.",
opt_threads->ival[0]);
}
user_opts->iThreads = opt_threads->ival[0];
}
#else
if (opt_threads->count > 0) {
if (opt_threads->ival[0] > 1) {
Log(&rLog, LOG_FATAL, "Cannot change number of threads to %d. %s was build without OpenMP support.",
opt_threads->ival[0], PACKAGE_NAME);
}
}
#endif
/* max MAC RAM (maximum amount of RAM set aside for MAC algorithm)
*/
if (opt_macram->count > 0) { /* FS, r240 -> r241 */
user_opts->aln_opts.rHhalignPara.iMacRamMB = opt_macram->ival[0];
}
arg_freetable(argtable,sizeof(argtable)/sizeof(argtable[0]));
UserOptsLogicCheck(user_opts);
return;
}
