From 13981404e2e6ebee8c48cf63146de228ea4cf369 Mon Sep 17 00:00:00 2001
From: Heng Li <lh3@me.com>
Date: Mon, 5 Nov 2018 11:43:10 -0500
Subject: [PATCH] r876: skip DP if taking too much RAM (#259)

---
 align.c    | 5 ++++-
 main.c     | 4 +++-
 minimap.h  | 1 +
 minimap2.1 | 5 +++++
 4 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/align.c b/align.c
index ee4157e..25b19d0 100644
--- a/align.c
+++ b/align.c
@@ -300,7 +300,10 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 		for (i = 0; i < qlen; ++i) fputc("ACGTN"[qseq[i]], stderr);
 		fputc('\n', stderr);
 	}
-	if (opt->flag & MM_F_SPLICE)
+	if (opt->max_sw_mat > 0 && (int64_t)tlen * qlen > opt->max_sw_mat) {
+		ksw_reset_extz(ez);
+		ez->zdropped = 1;
+	} else if (opt->flag & MM_F_SPLICE)
 		ksw_exts2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->noncan, zdrop, flag, ez);
 	else if (opt->q == opt->q2 && opt->e == opt->e2)
 		ksw_extz2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, w, zdrop, end_bonus, flag, ez);
diff --git a/main.c b/main.c
index c24048b..237d8c6 100644
--- a/main.c
+++ b/main.c
@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.13-r875-dirty"
+#define MM_VERSION "2.13-r876-dirty"
 
 #ifdef __linux__
 #include <sys/resource.h>
@@ -60,6 +60,7 @@ static ko_longopt_t long_options[] = {
 	{ "split-prefix",   ko_required_argument, 334 },
 	{ "no-end-flt",     ko_no_argument,       335 },
 	{ "hard-mask-level",ko_no_argument,       336 },
+	{ "cap-sw-mat",     ko_required_argument, 337 },
 	{ "help",           ko_no_argument,       'h' },
 	{ "max-intron-len", ko_required_argument, 'G' },
 	{ "version",        ko_no_argument,       'V' },
@@ -190,6 +191,7 @@ int main(int argc, char *argv[])
 		else if (c == 334) opt.split_prefix = o.arg; // --split-prefix
 		else if (c == 335) opt.flag |= MM_F_NO_END_FLT; // --no-end-flt
 		else if (c == 336) opt.flag |= MM_F_HARD_MLEVEL; // --hard-mask-level
+		else if (c == 337) opt.max_sw_mat = mm_parse_num(o.arg); // --cap-sw-mat
 		else if (c == 314) { // --frag
 			yes_or_no(&opt, MM_F_FRAG_MODE, o.longidx, o.arg, 1);
 		} else if (c == 315) { // --secondary
diff --git a/minimap.h b/minimap.h
index 20328c8..652e62a 100644
--- a/minimap.h
+++ b/minimap.h
@@ -139,6 +139,7 @@ typedef struct {
 	int32_t mid_occ;     // ignore seeds with occurrences above this threshold
 	int32_t max_occ;
 	int mini_batch_size; // size of a batch of query bases to process in parallel
+	int64_t max_sw_mat;
 
 	const char *split_prefix;
 } mm_mapopt_t;
diff --git a/minimap2.1 b/minimap2.1
index 1d0c146..a05542e 100644
--- a/minimap2.1
+++ b/minimap2.1
@@ -373,6 +373,11 @@ It helps to avoid tiny terminal exons. [6]
 .B --no-end-flt
 Don't filter seeds towards the ends of chains before performing base-level
 alignment.
+.TP
+.BI --cap-sw-mat \ NUM
+Skip alignment if the DP matrix size is above
+.IR NUM .
+Set 0 to disable [0].
 .SS Input/output options
 .TP 10
 .B -a