More documentation for walkers that I'm familiar with in the collection of core walkers.

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@2328 348d0f76-0448-11de-a6fe-93d51630548a

java/src/org/broadinstitute/sting/gatk/walkers/FixBAMSortOrderTag.java

@@ -22,10 +22,10 @@ import net.sf.samtools.SAMFileWriterFactory;
 import java.io.File;
 
 /**
- * Created by IntelliJ IDEA.
- * User: aaron
- * Date: Oct 9, 2009
- * Time: 2:21:08 PM
+ * Fixes slightly corrupted BAM files by rewriting the input BAM file, altering
+ * the header by changing the sort order tag (SO) to coordinate sort order.  Will NOT
+ * verify the contents of the file to ensure that the data is actually in coordinate sorted
+ * order. 
  */
 public class FixBAMSortOrderTag extends ReadWalker<SAMRecord, SAMFileWriter> {
 

java/src/org/broadinstitute/sting/gatk/walkers/FlagStatWalker.java

@@ -32,12 +32,10 @@ import java.text.NumberFormat;
  */
 
 /**
+ * A reimplementation of the 'samtools flagstat' subcommand in the GATK.  Walks
+ * over all input data, accumulating statistics such as total number of reads,
+ * reads with QC failure flag set, number of duplicates, percentage mapped, etc.
  * @author aaron
- *         <p/>
- *         Class FlagStatWalker
- *         <p/>
- *         This walker mirrors that stats that are generated by the flagstat
- *         command of samtools.
  */
 @Requires({DataSource.READS})
 public class FlagStatWalker extends ReadWalker<Integer, Integer> {

java/src/org/broadinstitute/sting/gatk/walkers/PileupWalker.java

@@ -51,6 +51,13 @@ import java.util.ArrayList;
  * Also at the read base column, a symbol '^' marks the start of a read segment which is a contiguous subsequence on the read
  * separated by 'N/S/H' CIGAR operations. The ASCII of the character following '^' minus 33 gives the mapping quality.
  * A symbol '$' marks the end of a read segment.
+ *
+ * @help.description Prints the alignment in the pileup format. In the pileup format, each line represents a genomic position,
+ * consisting of chromosome name, coordinate, reference base, read bases, read qualities and alignment mapping
+ * qualities. Information on match, mismatch, indel, strand, mapping quality and start and end of a read are all
+ * encoded at the read base column. At this column, a dot stands for a match to the reference base on the forward strand,
+ * a comma for a match on the reverse strand, 'ACGTN' for a mismatch on the forward strand and 'acgtn' for a mismatch on the
+ * reverse strand.
  */
 public class PileupWalker extends LocusWalker<Integer, Integer> implements TreeReducible<Integer> {
     @Argument(fullName="alwaysShowSecondBase",doc="If true, prints dummy bases for the second bases in the BAM file where they are missing",required=false)

java/src/org/broadinstitute/sting/gatk/walkers/PrintRODsWalker.java

@@ -32,7 +32,8 @@ import org.broadinstitute.sting.utils.genotype.Variation;
 import java.util.Iterator;
 
 /**
- * PrintRODsWalker prints out all of the RODs that it sees (using the ROD's toString method)
+ * Prints out all of the RODs in the input data set. Data is rendered using the toString() method
+ * of the given ROD.
  */
 public class PrintRODsWalker extends RodWalker<Integer, Integer> {
 

java/src/org/broadinstitute/sting/gatk/walkers/PrintReadsWalker.java

@@ -31,10 +31,10 @@ import org.broadinstitute.sting.utils.cmdLine.Argument;
  */
 
 /**
- * This walker prints out the reads from the BAM files provided to the traversal engines.
- * It also supports the command line option '-outputBamFile filname', which outputs all the
- * reads to a specified BAM file
- * The walker now also optionally filters reads based on command line options.
+ * Renders, in SAM/BAM format, all reads from the input data set in the order in which they appear
+ * in the input file.  It can dynamically merge the contents of multiple input BAM files, resulting
+ * in merged output sorted in coordinate order.  Can also optionally filter reads based on the --read-filter
+ * command line argument.
  */
 @Requires({DataSource.READS, DataSource.REFERENCE})
 public class PrintReadsWalker extends ReadWalker<SAMRecord, SAMFileWriter> {

java/src/org/broadinstitute/sting/gatk/walkers/SplitSamFileWalker.java

@@ -32,6 +32,10 @@ import org.apache.log4j.Logger;
 
 import java.util.*;
 
+/**
+ * Divides the input data set into separate BAM files, one for each sample in the input data set.  The split
+ * files are named concatenating the sample name to the end of the provided outputRoot command-line argument.
+ */
 @WalkerName("SplitSamFile")
 @Requires({DataSource.READS})
 public class SplitSamFileWalker extends ReadWalker<SAMRecord, Map<String, SAMFileWriter>> {