--- /dev/null
+
+fastq-tools is written and maintained by:
+
+Daniel C. Jones <dcjones@cs.washington.edu>
+
+
--- /dev/null
+
+Copyright (C) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+
--- /dev/null
+
+fastq-tools
+===========
+
+This package provides a number of small and efficient programs to perform common
+tasks with high throughput sequencing data in the FASTQ format. All of the
+programs work with typical FASTQ files as well as gzipped FASTQ files.
+
+
+index
+-----
+
+The following programs are provided. See the individual man pages for more
+information.
+
+
+*fastq-grep* : match sequences against regular expressions
+
+*fastq-kmers* : count k-mer occurrences
+
+*fastq-match* : (smith-waterman) local sequence alignment
+
+*fastq-uniq* : count duplicate reads
+
+
+install
+-------
+
+On most systems, this is a simple `./configure && make install`.
+
+The only external dependencies are PCRE (http://www.pcre.org/) and zlib
+(http://zlib.net/).
+
+
+contribute
+----------
+
+If you have written any small but useful programs to deal with FASTQ files,
+please consider submitting them for inclusion in fastq-tools. Check out the
+Github page (https://github.com/dcjones/fastq-tools) or send mail to the author
+(dcjones@cs.washington.edu).
+
+
+copying
+-------
+
+This package is provided under a permissive MIT-style license. In particular:
+
+Copyright (C) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+
--- /dev/null
+
+general
+=======
+
+Man pages!
+
+
+I would like to encorporate some domain-specific compression algorithm. Options
+I know of:
+ * G-SQZ (http://www.tgen.org/research/gsqueez.cfm) : not open source (i.e. not an option)
+ * fqzcomp (http://seqanswers.com/forums/archive/index.php/t-6349.html)
+ * DSRC (http://bioinformatics.oxfordjournals.org/cgi/content/short/27/6/860?rss=1) :
+ Not yet available?
+ * Invent my own.
+
+
+
+
+
+
+program specific
+================
+
+
+fastq-grep
+----------
+
+
+
+fastq-kmers
+-----------
+
+
+
+fastq-match
+-----------
+
+Specifying the score matrix, rather than using a hardcoded.
+
+The implementation of the Smith-Waterman algorithm could be more efficient. We
+might look to Phil Green's cross_match implementation for ideas.
+
+An option to return the sequences that match past a certain threshold would be
+useful.
+
+
+
+fastq-uniq
+----------
+
+
+/*
+ * This file is part of fastq-tools.
+ *
+ * Copyright (c) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
+ *
+ */
+
+
#include "hash.h"
#include "common.h"
#include <stdlib.h>
+/*
+ * This file is part of fastq-tools.
+ *
+ * Copyright (c) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
+ *
+ * hash :
+ * A quick and simple all-purpose hash table.
+ *
+ */
+
#ifndef FASTQ_TOOLS_HASH_H
#define FASTQ_TOOLS_HASH_H
*
* Copyright (c) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
*
- * fastq-parse :
+ * parse :
* A parser for FASTQ files.
*
- * This parser is mostly derivative of Heng Li's.
- * See: http://lh3lh3.users.sourceforge.net/kseq.shtml
- *
*/
#ifndef FASTQ_TOOLS_PARSE_H
*
* Copyright (c) 2011 by Daniel C. Jones <dcjones@cs.washington.edu>
*
- * fastq-sw :
+ * sw :
* Local alignments of nucleotide sequences via Smith-Waterman.
*
*/