polished read_sam

[biopieces.git] / code_perl / Maasha / RestrictEnz.pm

diff --git a/code_perl/Maasha/RestrictEnz.pm b/code_perl/Maasha/RestrictEnz.pm
index 9b1dd27a5b52ccea6fbea5d8f9d0a44f0849764e..836835b08c76f3f4ed3fc9e597ae511d370c260f 100644 (file)
--- a/code_perl/Maasha/RestrictEnz.pm
+++ b/code_perl/Maasha/RestrictEnz.pm
@@ -65,6 +65,7 @@ use Inline ( C => <<'END_C', DIRECTORY => $ENV{ "BP_TMP" } );
 # N1111100000000000
 */
 
+/* 2-dimensional array for fast lookup of nucleotide match. */
 
 char ambi_match[16][16] = {
     "1000011100011101",
@@ -88,6 +89,11 @@ char ambi_match[16][16] = {
 
 int hash( char c )
 {
+    /* Martin A. Hansen, August 2009. */
+
+    /* Given a nucletotide returns the position of this */
+    /* on the edge of the symetrical ambi_match lookup table. */
+
     switch ( toupper( c ) )
     {
         case 'A': return 0;
@@ -105,7 +111,7 @@ int hash( char c )
         case 'H': return 12;
         case 'D': return 13;
         case 'B': return 14;
-        case 'N': return 0;
+        case 'N': return 15;
         default: return -1;
     }
 }
@@ -113,12 +119,17 @@ int hash( char c )
 
 void scan( char *seq, char *pat, int seq_len, int pat_len )
 {
+    /* Martin A. Hansen, August 2009. */
+
+    /* Scans a sequence for a subsequence allowing for ambiguity */
+    /* codes ala UIPAC. */
+
     int i;
 
     Inline_Stack_Vars;
     Inline_Stack_Reset;
 
-    for ( i = 0; i < seq_len - pat_len; i++ )
+    for ( i = 0; i < seq_len - pat_len + 1; i++ )
     {
         if ( match( &seq[ i ], pat, pat_len ) ) {
           Inline_Stack_Push( sv_2mortal( newSViv( i ) ) );
@@ -131,6 +142,11 @@ void scan( char *seq, char *pat, int seq_len, int pat_len )
 
 int match( char *seq1, char *seq2, int len )
 {
+    /* Martin A. Hansen, August 2009. */
+
+    /* Checks if two sequences are identical allowing for */
+    /* IUPAC amabiguity codes over a given length. */
+
     int  i = 0;
     char c1;
     char c2;
@@ -158,10 +174,17 @@ END_C
 
 sub re_scan
 {
+    # Martin A. Hansen, August 2009.
+
+    # Calls C function to scan a given sequence for a given
+    # restriction site.
+
     my ( $seq,   # sequence to scan
          $re,    # hashref with RE info
        ) = @_; 
 
+    # Returns a list of integers.
+
     my ( @matches );
 
     @matches = scan( $seq, $re->{ "pattern" }, length $seq, $re->{ "len" } );
@@ -172,6 +195,12 @@ sub re_scan
 
 sub parse_re_data
 {
+    # Martin A. Hansen, August 2009.
+    
+    # Parses restriction enzyme data from __DATA__ section in this module.
+
+    # Returns a list of hashrefs.
+
     my ( @lines, $line, @fields, @re_data );
 
     @lines = <DATA>;