Add fastx function, which prints fasta/fastq, originally in lh3/pull/12

README.md

@@ -53,27 +53,27 @@ See `awk.1`.
 
 2. Extract unmapped reads without header:
 
-        bioawk -c sam 'and($flag,4)' aln.sam.gz
+        bioawk -c sam 'and($flag, 4)' aln.sam.gz
 
 3. Extract mapped reads with header:
 
-        bioawk -Hc sam '!and($flag,4)'
+        bioawk -Hc sam '!and($flag, 4)'
 
 4. Reverse complement FASTA:
 
-        bioawk -c fastx '{print ">"$name;print revcomp($seq)}' seq.fa.gz
+        bioawk -c fastx '{print fastx($name, revcomp($seq))}' seq.fa.gz
 
 5. Create FASTA from SAM (uses revcomp if FLAG & 16)
 
         samtools view aln.bam | \
-            bioawk -c sam '{s=$seq; if(and($flag, 16)) {s=revcomp($seq)} print ">"$qname"\n"s}'
+            bioawk -c sam '{s=$seq; if(and($flag, 16)) {s=revcomp($seq)} print fastx($qname, s)}'
 
 6. Print the genotypes of sample `foo` and `bar` from a VCF:
 
         grep -v ^## in.vcf | bioawk -tc hdr '{print $foo,$bar}'
 
 7. Translate nucleotide into protein sequence
- 
+
         bioawk -c fastx '{print ">"$name;print translate($seq)}' seq.fa.gz
 can also use different translation tables.  To translate using the
 bactera/archaea code:
@@ -89,6 +89,22 @@ bactera/archaea code:
                         } \
                         if(tgs["NM"] < 3) print }' alignments.sam
 
+9. Get the %GC from FASTA
+
+        awk -c fastx '{print $name, gc($seq)}' seq.fa.gz
+
+10. Get the mean Phred quality score table from FASTQ:
+
+        awk -c fastx '{print $name, meanqual($qual)}' seq.fq.gz
+
+11. Take column name from the first line (where "age" appears in the first line) of input.txt):
+
+        awk -c header '{print $age}' input.txt
+
+12. Use awk's redirection to split a FASTA file by sequence lengths.
+
+        awk -c fastx '{if (length($seq) < 35) {print fastx($name, $seq) > "short.fasta"} else {print fastx($name, $seq) > "long.fasta"}}' seq.fq.gz
+
 
 ### Potential limitations
 

addon.c

@@ -111,14 +111,14 @@ static char comp_tab[] = {
 	'p', 'q', 'y', 's', 'a', 'a', 'b', 'w', 'x', 'r', 'z', 123, 124, 125, 126, 127
 };
 
-/* The master codon/protein table. 
+/* The master codon/protein table.
  *
  * http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi
  * Tables 7,8,17,18,19,20 are depreciated and do not exist
  * on the NCBI website
  *
  */
-const char codon_table[64][25] = 
+const char codon_table[64][25] =
 {
 /*        1    2    3    4    5    6    7     8     9    10   11   12   13   14   15   16   17    18    19    20   21   22   23   24   25*/
  /*ttt*/{'F', 'F', 'F', 'F', 'F', 'F', '\0', '\0', 'F', 'F', 'F', 'F', 'F', 'F', 'F', 'F', '\0', '\0', '\0', '\0', 'F', 'F', 'F', 'F', 'F'},
@@ -241,7 +241,7 @@ void bio_translate(char *dna, char *out, int table)
             }
             break;
     }
-    
+
     int i;
     int dnaSize;
     int protSize = 0;
@@ -449,6 +449,34 @@ Cell *bio_func(int f, Cell *x, Node **a)
         setsval(y, out);
         free(out);
 
+	} else if (f == BIO_FFASTX) {
+		if (a[1]->nnext == 0) {
+			FATAL("fastx requires at least two arguments");
+		} else {
+			char *buf, *name, *seq, *qual;
+			int bufsz=3*recsize;
+			int has_qual;
+			z = execute(a[1]->nnext);
+			if ((has_qual = a[1]->nnext->nnext != 0)) {
+				y = execute(a[1]->nnext->nnext);
+				qual = getsval(y);
+			}
+
+			if ((buf = (char *) malloc(bufsz)) == NULL)
+				FATAL("out of memory in fastx");
+
+			name = getsval(x);
+			seq = getsval(z);
+			if (!has_qual) {
+				sprintf(buf, ">%s\n%s", name, seq);
+			} else {
+				if (strlen(seq) != strlen(qual))
+					WARNING("fastx arguments seq and qual are not same length");
+				sprintf(buf, "@%s\n%s\n+\n%s", name, seq, qual);
+			}
+			setsval(y, buf);
+			free(buf);
+		}
     } /* else: never happens */
 	return y;
 }

addon.h

@@ -45,6 +45,7 @@ int bio_getrec(char **pbuf, int *psize, int isrecord);
 #define BIO_FMINQUAL    208
 #define BIO_FMAXQUAL    209
 #define BIO_FMEDIANQUAL    210
+#define BIO_FFASTX    211
 
 
 struct Cell;

lex.c

@@ -59,11 +59,12 @@ Keyword keywords[] ={	/* keep sorted: binary searched */
 	{ "else",	ELSE,		ELSE },
 	{ "exit",	EXIT,		EXIT },
 	{ "exp",	FEXP,		BLTIN },
+	{ "fastx",	BIO_FFASTX,	BLTIN },
 	{ "fflush",	FFLUSH,		BLTIN },
 	{ "for",	FOR,		FOR },
 	{ "func",	FUNC,		FUNC },
 	{ "function",	FUNC,		FUNC },
-	{ "gc",	BIO_FGC,		BLTIN },
+	{ "gc",		BIO_FGC,       	BLTIN },
 	{ "getline",	GETLINE,	GETLINE },
 	{ "gsub",	GSUB,		GSUB },
 	{ "if",		IF,		IF },
@@ -75,7 +76,7 @@ Keyword keywords[] ={	/* keep sorted: binary searched */
 	{ "lshift",     BIO_FLSHIFT,    BLTIN },
 	{ "match",	MATCHFCN,	MATCHFCN },
 	{ "maxqual",	BIO_FMAXQUAL,		BLTIN },
-	{ "meanqual",	BIO_FMEANQUAL,		BLTIN },
+	{ "meanqual",	BIO_FMEANQUAL,	BLTIN },
 	{ "medianqual",	BIO_FMEDIANQUAL,		BLTIN },
 	{ "minqual",	BIO_FMINQUAL,		BLTIN },
 	{ "next",	NEXT,		NEXT },
@@ -86,8 +87,8 @@ Keyword keywords[] ={	/* keep sorted: binary searched */
 	{ "qualcount",	BIO_FQUALCOUNT,	BLTIN },
 	{ "rand",	FRAND,		BLTIN },
 	{ "return",	RETURN,		RETURN },
-	{ "revcomp",BIO_FREVCOMP, BLTIN },
-	{ "reverse",BIO_FREVERSE, BLTIN },
+	{ "revcomp",	BIO_FREVCOMP,	BLTIN },
+	{ "reverse",	BIO_FREVERSE,	BLTIN },
 	{ "rshift",     BIO_FRSHIFT, BLTIN },
 	{ "sin",	FSIN,		BLTIN },
 	{ "split",	SPLIT,		SPLIT },