From 177eef259d1d3f3aa453dd6bb7222e1cc3a0ce52 Mon Sep 17 00:00:00 2001
From: John Marshall <jmarshall@hey.com>
Date: Fri, 9 Apr 2021 19:34:53 +0100
Subject: [PATCH] Use the full MIDNSHP=X string whenever printing CIGAR strings

Define MM_CIGAR_STR to the full string of CIGAR operators (including
the 'B' operator as well) and use it throughout the C code.

It would be possible to use it from the Cython code too, but it's easier
to keep that as a Cython string literal to avoid adding extra runtime
code to handle locale conversion.
---
 align.c          | 2 +-
 example.c        | 2 +-
 format.c         | 4 ++--
 minimap.h        | 2 ++
 misc/paftools.js | 6 +++---
 python/mappy.pyx | 2 +-
 6 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/align.c b/align.c
index f2f154f..3b5ff9a 100644
--- a/align.c
+++ b/align.c
@@ -333,7 +333,7 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 		int i;
 		fprintf(stderr, "score=%d, cigar=", ez->score);
 		for (i = 0; i < ez->n_cigar; ++i)
-			fprintf(stderr, "%d%c", ez->cigar[i]>>4, "MIDN"[ez->cigar[i]&0xf]);
+			fprintf(stderr, "%d%c", ez->cigar[i]>>4, MM_CIGAR_STR[ez->cigar[i]&0xf]);
 		fprintf(stderr, "\n");
 	}
 }
diff --git a/example.c b/example.c
index ca1fdbe..b495051 100644
--- a/example.c
+++ b/example.c
@@ -47,7 +47,7 @@ int main(int argc, char *argv[])
 				printf("%s\t%d\t%d\t%d\t%c\t", ks->name.s, ks->seq.l, r->qs, r->qe, "+-"[r->rev]);
 				printf("%s\t%d\t%d\t%d\t%d\t%d\t%d\tcg:Z:", mi->seq[r->rid].name, mi->seq[r->rid].len, r->rs, r->re, r->mlen, r->blen, r->mapq);
 				for (i = 0; i < r->p->n_cigar; ++i) // IMPORTANT: this gives the CIGAR in the aligned regions. NO soft/hard clippings!
-					printf("%d%c", r->p->cigar[i]>>4, "MIDNSH"[r->p->cigar[i]&0xf]);
+					printf("%d%c", r->p->cigar[i]>>4, MM_CIGAR_STR[r->p->cigar[i]&0xf]);
 				putchar('\n');
 				free(r->p);
 			}
diff --git a/format.c b/format.c
index 11f24b5..a33c3b6 100644
--- a/format.c
+++ b/format.c
@@ -325,7 +325,7 @@ void mm_write_paf3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const
 		uint32_t k;
 		mm_sprintf_lite(s, "\tcg:Z:");
 		for (k = 0; k < r->p->n_cigar; ++k)
-			mm_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, "MIDNSHP=XB"[r->p->cigar[k]&0xf]);
+			mm_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, MM_CIGAR_STR[r->p->cigar[k]&0xf]);
 	}
 	if (r->p && (opt_flag & (MM_F_OUT_CS|MM_F_OUT_MD)))
 		write_cs_or_MD(km, s, mi, t, r, !(opt_flag&MM_F_OUT_CS_LONG), opt_flag&MM_F_OUT_MD, 1);
@@ -382,7 +382,7 @@ static void write_sam_cigar(kstring_t *s, int sam_flag, int in_tag, int qlen, co
 			assert(clip_len[0] < qlen && clip_len[1] < qlen);
 			if (clip_len[0]) mm_sprintf_lite(s, "%d%c", clip_len[0], clip_char);
 			for (k = 0; k < r->p->n_cigar; ++k)
-				mm_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, "MIDNSHP=XB"[r->p->cigar[k]&0xf]);
+				mm_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, MM_CIGAR_STR[r->p->cigar[k]&0xf]);
 			if (clip_len[1]) mm_sprintf_lite(s, "%d%c", clip_len[1], clip_char);
 		}
 	}
diff --git a/minimap.h b/minimap.h
index 7386632..d095f46 100644
--- a/minimap.h
+++ b/minimap.h
@@ -46,6 +46,8 @@
 
 #define MM_MAX_SEG       255
 
+#define MM_CIGAR_STR  "MIDNSHP=XB"
+
 #ifdef __cplusplus
 extern "C" {
 #endif
diff --git a/misc/paftools.js b/misc/paftools.js
index f048b07..999aa78 100755
--- a/misc/paftools.js
+++ b/misc/paftools.js
@@ -1419,7 +1419,7 @@ function paf_view(args)
 
 	var s_ref = new Bytes(), s_qry = new Bytes(), s_mid = new Bytes(); // these are used to show padded alignment
 	var re_cs = /([:=\-\+\*])(\d+|[A-Za-z]+)/g;
-	var re_cg = /(\d+)([MIDNSH])/g;
+	var re_cg = /(\d+)([MIDNSHP=X])/g;
 
 	var buf = new Bytes();
 	var file = args[getopt.ind] == "-"? new File() : new File(args[getopt.ind]);
@@ -1899,7 +1899,7 @@ function paf_splice2bed(args)
 		a.length = 0;
 	}
 
-	var re = /(\d+)([MIDNSH])/g;
+	var re = /(\d+)([MIDNSHP=X])/g;
 	var c, fmt = "bed", fn_name_conv = null, keep_multi = false;
 	while ((c = getopt(args, "f:n:m")) != null) {
 		if (c == 'f') fmt = getopt.arg;
@@ -2369,7 +2369,7 @@ function paf_junceval(args)
 
 	file = getopt.ind+1 >= args.length || args[getopt.ind+1] == '-'? new File() : new File(args[getopt.ind+1]);
 	var last_qname = null;
-	var re_cigar = /(\d+)([MIDNSHX=])/g;
+	var re_cigar = /(\d+)([MIDNSHP=X])/g;
 	while (file.readline(buf) >= 0) {
 		var m, t = buf.toString().split("\t");
 		var ctg_name = null, cigar = null, pos = null, qname = t[0];
diff --git a/python/mappy.pyx b/python/mappy.pyx
index d0bf7f8..920bc0d 100644
--- a/python/mappy.pyx
+++ b/python/mappy.pyx
@@ -82,7 +82,7 @@ cdef class Alignment:
 
 	@property
 	def cigar_str(self):
-		return "".join(map(lambda x: str(x[0]) + 'MIDNSH'[x[1]], self._cigar))
+		return "".join(map(lambda x: str(x[0]) + 'MIDNSHP=XB'[x[1]], self._cigar))
 
 	def __str__(self):
 		if self._strand > 0: strand = '+'