r913: output tag "rl", length of unseedable regs

format.c

@@ -301,11 +301,12 @@ static inline void write_tags(kstring_t *s, const mm_reg1_t *r)
 	if (r->split) mm_sprintf_lite(s, "\tzd:i:%d", r->split);
 }
 
-void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag)
+void mm_write_paf3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag, int rep_len)
 {
 	s->l = 0;
 	if (r == 0) {
 		mm_sprintf_lite(s, "%s\t%d", t->name, t->l_seq);
+		if (rep_len >= 0) mm_sprintf_lite(s, "\trl:i:%d", rep_len);
 		return;
 	}
 	mm_sprintf_lite(s, "%s\t%d\t%d\t%d\t%c\t", t->name, t->l_seq, r->qs, r->qe, "+-"[r->rev]);
@@ -315,6 +316,7 @@ void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const m
 	mm_sprintf_lite(s, "\t%d\t%d", r->mlen, r->blen);
 	mm_sprintf_lite(s, "\t%d", r->mapq);
 	write_tags(s, r);
+	if (rep_len >= 0) mm_sprintf_lite(s, "\trl:i:%d", rep_len);
 	if (r->p && (opt_flag & MM_F_OUT_CG)) {
 		uint32_t k;
 		mm_sprintf_lite(s, "\tcg:Z:");
@@ -327,6 +329,11 @@ void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const m
 		mm_sprintf_lite(s, "\t%s", t->comment);
 }
 
+void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag)
+{
+	mm_write_paf3(s, mi, t, r, km, opt_flag, -1);
+}
+
 static void sam_write_sq(kstring_t *s, char *seq, int l, int rev, int comp)
 {
 	extern unsigned char seq_comp_table[256];
@@ -377,7 +384,7 @@ static void write_sam_cigar(kstring_t *s, int sam_flag, int in_tag, int qlen, co
 	}
 }
 
-void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km, int opt_flag)
+void mm_write_sam3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km, int opt_flag, int rep_len)
 {
 	const int max_bam_cigar_op = 65535;
 	int flag, n_regs = n_regss[seg_idx], cigar_in_tag = 0;
@@ -528,13 +535,19 @@ void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
 		if (cigar_in_tag)
 			write_sam_cigar(s, flag, 1, t->l_seq, r, opt_flag);
 	}
+	if (rep_len >= 0) mm_sprintf_lite(s, "\trl:i:%d", rep_len);
 
 	if ((opt_flag & MM_F_COPY_COMMENT) && t->comment)
 		mm_sprintf_lite(s, "\t%s", t->comment);
 
 	s->s[s->l] = 0; // we always have room for an extra byte (see str_enlarge)
 }
 
+void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km, int opt_flag)
+{
+	mm_write_sam3(s, mi, t, seg_idx, reg_idx, n_seg, n_regss, regss, km, opt_flag, -1);
+}
+
 void mm_write_sam(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, int n_regs, const mm_reg1_t *regs)
 {
 	int i;

main.c

@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.15-r911-dirty"
+#define MM_VERSION "2.15-r913-dirty"
 
 #ifdef __linux__
 #include <sys/resource.h>

map.c

@@ -584,16 +584,16 @@ static void *worker_pipeline(void *shared, int step, void *in)
 						if ((p->opt->flag & MM_F_NO_PRINT_2ND) && r->id != r->parent)
 							continue;
 						if (p->opt->flag & MM_F_OUT_SAM)
-							mm_write_sam2(&p->str, mi, t, i - seg_st, j, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag);
+							mm_write_sam3(&p->str, mi, t, i - seg_st, j, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag, s->rep_len[i]);
 						else
-							mm_write_paf(&p->str, mi, t, r, km, p->opt->flag);
+							mm_write_paf3(&p->str, mi, t, r, km, p->opt->flag, s->rep_len[i]);
 						mm_err_puts(p->str.s);
 					}
 				} else if (p->opt->flag & (MM_F_OUT_SAM|MM_F_PAF_NO_HIT)) { // output an empty hit, if requested
 					if (p->opt->flag & MM_F_OUT_SAM)
-						mm_write_sam2(&p->str, mi, t, i - seg_st, -1, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag);
+						mm_write_sam3(&p->str, mi, t, i - seg_st, -1, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag, s->rep_len[i]);
 					else
-						mm_write_paf(&p->str, mi, t, 0, 0, p->opt->flag);
+						mm_write_paf3(&p->str, mi, t, 0, 0, p->opt->flag, s->rep_len[i]);
 					mm_err_puts(p->str.s);
 				}
 			}

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "10 January 2019" "minimap2-2.15-dirty (r911)" "Bioinformatics tools"
+.TH minimap2 1 "5 Feburary 2019" "minimap2-2.15-dirty (r913)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -617,6 +617,7 @@ cg	Z	CIGAR string (only in PAF)
 cs	Z	Difference string
 dv	f	Approximate per-base sequence divergence
 de	f	Gap-compressed per-base sequence divergence
+rl	i	Length of query regions harboring repetitive seeds
 .TE
 
 .PP

mmpriv.h

@@ -61,8 +61,10 @@ void mm_sketch(void *km, const char *str, int len, int w, int k, uint32_t rid, i
 
 void mm_write_sam_hdr(const mm_idx_t *mi, const char *rg, const char *ver, int argc, char *argv[]);
 void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag);
+void mm_write_paf3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag, int rep_len);
 void mm_write_sam(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, int n_regs, const mm_reg1_t *regs);
 void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regs, const mm_reg1_t *const* regs, void *km, int opt_flag);
+void mm_write_sam3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km, int opt_flag, int rep_len);
 
 void mm_idxopt_init(mm_idxopt_t *opt);
 const uint64_t *mm_idx_get(const mm_idx_t *mi, uint64_t minier, int *n);