X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=samtools.git;a=blobdiff_plain;f=sam_view.c;h=06dd01a5ffa951dcb950a97681e7c5aca0b88971;hp=02aee3c034cbc668b51295039d92a6adb1e74d51;hb=317f5e8dd22cc9e1e5e05fbcaeb3b9aca7447351;hpb=b27e00385f41769d03a8cca4dbd71275fc9fa906 diff --git a/sam_view.c b/sam_view.c index 02aee3c..06dd01a 100644 --- a/sam_view.c +++ b/sam_view.c @@ -2,25 +2,45 @@ #include #include #include +#include +#include "sam_header.h" #include "sam.h" +#include "faidx.h" static int g_min_mapQ = 0, g_flag_on = 0, g_flag_off = 0; static char *g_library, *g_rg; +static int g_sol2sanger_tbl[128]; + +static void sol2sanger(bam1_t *b) +{ + int l; + uint8_t *qual = bam1_qual(b); + if (g_sol2sanger_tbl[30] == 0) { + for (l = 0; l != 128; ++l) { + g_sol2sanger_tbl[l] = (int)(10.0 * log(1.0 + pow(10.0, (l - 64 + 33) / 10.0)) / log(10.0) + .499); + if (g_sol2sanger_tbl[l] >= 93) g_sol2sanger_tbl[l] = 93; + } + } + for (l = 0; l < b->core.l_qseq; ++l) { + int q = qual[l]; + if (q > 127) q = 127; + qual[l] = g_sol2sanger_tbl[q]; + } +} static inline int __g_skip_aln(const bam_header_t *h, const bam1_t *b) { if (b->core.qual < g_min_mapQ || ((b->core.flag & g_flag_on) != g_flag_on) || (b->core.flag & g_flag_off)) return 1; - if (g_library || g_rg) { + if (g_rg) { uint8_t *s = bam_aux_get(b, "RG"); - if (s) { - if (g_rg && strcmp(g_rg, (char*)(s + 1)) == 0) return 0; - if (g_library) { - const char *p = bam_strmap_get(h->rg2lib, (char*)(s + 1)); - return (p && strcmp(p, g_library) == 0)? 0 : 1; - } return 1; - } else return 1; - } else return 0; + if (s && strcmp(g_rg, (char*)(s + 1)) == 0) return 0; + } + if (g_library) { + const char *p = bam_get_library((bam_header_t*)h, b); + return (p && strcmp(p, g_library) == 0)? 0 : 1; + } + return 0; } // callback function for bam_fetch() @@ -31,18 +51,20 @@ static int view_func(const bam1_t *b, void *data) return 0; } -static int usage(void); +static int usage(int is_long_help); int main_samview(int argc, char *argv[]) { - int c, is_header = 0, is_header_only = 0, is_bamin = 1, ret = 0, is_uncompressed = 0, is_bamout = 0; + int c, is_header = 0, is_header_only = 0, is_bamin = 1, ret = 0, is_uncompressed = 0, is_bamout = 0, slx2sngr = 0; + int of_type = BAM_OFDEC, is_long_help = 0; samfile_t *in = 0, *out = 0; - char in_mode[5], out_mode[5], *fn_out = 0, *fn_list = 0; + char in_mode[5], out_mode[5], *fn_out = 0, *fn_list = 0, *fn_ref = 0; /* parse command-line options */ strcpy(in_mode, "r"); strcpy(out_mode, "w"); - while ((c = getopt(argc, argv, "Sbt:hHo:q:f:F:ul:r:")) >= 0) { + while ((c = getopt(argc, argv, "Sbt:hHo:q:f:F:ul:r:xX?T:C")) >= 0) { switch (c) { + case 'C': slx2sngr = 1; break; case 'S': is_bamin = 0; break; case 'b': is_bamout = 1; break; case 't': fn_list = strdup(optarg); is_bamin = 0; break; @@ -55,22 +77,36 @@ int main_samview(int argc, char *argv[]) case 'u': is_uncompressed = 1; break; case 'l': g_library = strdup(optarg); break; case 'r': g_rg = strdup(optarg); break; - default: return usage(); + case 'x': of_type = BAM_OFHEX; break; + case 'X': of_type = BAM_OFSTR; break; + case '?': is_long_help = 1; break; + case 'T': fn_ref = strdup(optarg); is_bamin = 0; break; + default: return usage(is_long_help); } } if (is_uncompressed) is_bamout = 1; if (is_header_only) is_header = 1; if (is_bamout) strcat(out_mode, "b"); + else { + if (of_type == BAM_OFHEX) strcat(out_mode, "x"); + else if (of_type == BAM_OFSTR) strcat(out_mode, "X"); + } if (is_bamin) strcat(in_mode, "b"); if (is_header) strcat(out_mode, "h"); if (is_uncompressed) strcat(out_mode, "u"); - if (argc == optind) return usage(); + if (argc == optind) return usage(is_long_help); + // generate the fn_list if necessary + if (fn_list == 0 && fn_ref) fn_list = samfaipath(fn_ref); // open file handlers if ((in = samopen(argv[optind], in_mode, fn_list)) == 0) { fprintf(stderr, "[main_samview] fail to open file for reading.\n"); goto view_end; } + if (in->header == 0) { + fprintf(stderr, "[main_samview] fail to read the header.\n"); + goto view_end; + } if ((out = samopen(fn_out? fn_out : "-", out_mode, in->header)) == 0) { fprintf(stderr, "[main_samview] fail to open file for writing.\n"); goto view_end; @@ -80,9 +116,12 @@ int main_samview(int argc, char *argv[]) if (argc == optind + 1) { // convert/print the entire file bam1_t *b = bam_init1(); int r; - while ((r = samread(in, b)) >= 0) // read one alignment from `in' - if (!__g_skip_aln(in->header, b)) + while ((r = samread(in, b)) >= 0) { // read one alignment from `in' + if (!__g_skip_aln(in->header, b)) { + if (slx2sngr) sol2sanger(b); samwrite(out, b); // write the alignment to `out' + } + } if (r < -1) fprintf(stderr, "[main_samview] truncated file.\n"); bam_destroy1(b); } else { // retrieve alignments in specified regions @@ -108,13 +147,13 @@ int main_samview(int argc, char *argv[]) view_end: // close files, free and return - free(fn_list); free(fn_out); free(g_library); free(g_rg); + free(fn_list); free(fn_ref); free(fn_out); free(g_library); free(g_rg); samclose(in); samclose(out); return ret; } -static int usage() +static int usage(int is_long_help) { fprintf(stderr, "\n"); fprintf(stderr, "Usage: samtools view [options] | [region1 [...]]\n\n"); @@ -123,15 +162,20 @@ static int usage() fprintf(stderr, " -H print header only (no alignments)\n"); fprintf(stderr, " -S input is SAM\n"); fprintf(stderr, " -u uncompressed BAM output (force -b)\n"); + fprintf(stderr, " -x output FLAG in HEX (samtools-C specific)\n"); + fprintf(stderr, " -X output FLAG in string (samtools-C specific)\n"); fprintf(stderr, " -t FILE list of reference names and lengths (force -S) [null]\n"); + fprintf(stderr, " -T FILE reference sequence file (force -S) [null]\n"); fprintf(stderr, " -o FILE output file name [stdout]\n"); fprintf(stderr, " -f INT required flag, 0 for unset [0]\n"); fprintf(stderr, " -F INT filtering flag, 0 for unset [0]\n"); fprintf(stderr, " -q INT minimum mapping quality [0]\n"); fprintf(stderr, " -l STR only output reads in library STR [null]\n"); fprintf(stderr, " -r STR only output reads in read group STR [null]\n"); - fprintf(stderr, "\n\ -Notes:\n\ + fprintf(stderr, " -? longer help\n"); + fprintf(stderr, "\n"); + if (is_long_help) + fprintf(stderr, "Notes:\n\ \n\ 1. By default, this command assumes the file on the command line is in\n\ the BAM format and it prints the alignments in SAM. If `-t' is\n\ @@ -141,7 +185,7 @@ Notes:\n\ corresponding sequence length. The `.fai' file generated by `faidx'\n\ can be used here. This file may be empty if reads are unaligned.\n\ \n\ - 2. SAM->BAM conversion: `samtools view -bt ref.fa.fai in.sam.gz'.\n\ + 2. SAM->BAM conversion: `samtools view -bT ref.fa in.sam.gz'.\n\ \n\ 3. BAM->SAM conversion: `samtools view in.bam'.\n\ \n\ @@ -151,6 +195,14 @@ Notes:\n\ \n\ 5. Option `-u' is preferred over `-b' when the output is piped to\n\ another samtools command.\n\ +\n\ + 6. In a string FLAG, each character represents one bit with\n\ + p=0x1 (paired), P=0x2 (properly paired), u=0x4 (unmapped),\n\ + U=0x8 (mate unmapped), r=0x10 (reverse), R=0x20 (mate reverse)\n\ + 1=0x40 (first), 2=0x80 (second), s=0x100 (not primary), \n\ + f=0x200 (failure) and d=0x400 (duplicate). Note that `-x' and\n\ + `-X' are samtools-C specific. Picard and older samtools do not\n\ + support HEX or string flags.\n\ \n"); return 1; }