src/hg/encode/validateFiles/validateFiles.c 1.24

Index: src/hg/encode/validateFiles/validateFiles.c
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/encode/validateFiles/validateFiles.c,v
retrieving revision 1.23
retrieving revision 1.24
diff -b -B -U 4 -r1.23 -r1.24
--- src/hg/encode/validateFiles/validateFiles.c	10 Aug 2009 17:22:49 -0000	1.23
+++ src/hg/encode/validateFiles/validateFiles.c	10 Aug 2009 18:57:18 -0000	1.24
@@ -110,8 +110,19 @@
    {"version", OPTION_BOOLEAN},
    {NULL, 0},
 };
 
+boolean checkMismatch(int ch1, int ch2)
+// checkMismatch -- if the sequence has an N, we call this a mismatch
+//   by default unless nMatch is set, in which case we don't call
+//   it a mismatch
+{
+if (ch1 != 'n')
+    return ch1 != ch2;
+
+return !nMatch;
+}
+
 void initArrays()
 // Set up array of chars
 // dnaChars:  DNA chars ACGTNacgtn, and optionally include colorspace 0-3
 // qualChars: fastq quality scores as ascii [!-~] (ord(!)=33, ord(~)=126)
@@ -599,9 +610,9 @@
     }
 for (i=0 ; i < g->size ; ++i)
     {
     char c = tolower(seq[i]);
-    if (!((nMatch && c == 'n') || c == g->dna[i]))
+    if (checkMismatch(c,  g->dna[i]))
         ++mm;
     }
 if (mm > mismatches)
     {
@@ -645,16 +656,16 @@
 mm1 = 0;
 for (i=0 ; i < g1->size ; ++i)
     {
     char c = tolower(seq1[i]);
-    if (!((nMatch && c == 'n') || c == g1->dna[i]))
+    if (checkMismatch(c,  g1->dna[i]))
         ++mm1;
     }
 mm2 = 0;
 for (i=0 ; i < g2->size ; ++i)
     {
     char c = tolower(seq2[i]);
-    if (!((nMatch && c == 'n') || c == g2->dna[i]))
+    if (checkMismatch(c,  g2->dna[i]))
         ++mm2;
     }
 if (mmPerPair)
     {