[PATCH] Add FASTX Toolkit.

[Ricardo Wurmus]

Hi Guix,

attached are patches to add fastx-toolkit, and its dependency
libgtextutils.

"fastx-toolkit" installs three m4 files to "$out/share/aclocal", and
libgtextutils installs an empty "$out/share/aclocal" directoy.  I
reported this upstream, but I did not add a phase to remove these files,
because I think it's not a big deal.  Is this okay or should I modify
the sources to avoid installing these files?

~~ Ricardo

>From 673f316fd41b0d0d7679a7a69ed4755923873653 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Tue, 14 Apr 2015 16:35:30 +0200
Subject: [PATCH 1/2] gnu: Add libgtextutils.

* gnu/packages/textutils.scm (libgtextutils): New variable.
---
 gnu/packages/textutils.scm | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/gnu/packages/textutils.scm b/gnu/packages/textutils.scm
index d6cc577..2f367ce 100644
--- a/gnu/packages/textutils.scm
+++ b/gnu/packages/textutils.scm
@@ -23,6 +23,7 @@
   #:use-module (guix download)
   #:use-module (guix git-download)
   #:use-module (guix build-system gnu)
+  #:use-module (gnu packages autotools)
   #:use-module (gnu packages python))
 
 (define-public recode
@@ -122,3 +123,33 @@ libenca and several charset conversion libraries and 
tools.")
 normalization, case-folding, and other operations for data in the UTF-8
 encoding, supporting Unicode version 7.0.")
     (license license:expat)))
+
+(define-public libgtextutils
+  (package
+    (name "libgtextutils")
+    (version "0.7")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (string-append
+             "https://github.com/agordon/libgtextutils/releases/download/";
+             version "/libgtextutils-" version ".tar.gz"))
+       (sha256
+        (base32 "0jiybkb2z58wa2msvllnphr4js2hvjvh988pavb3mzkgr6ihwbkr"))))
+    (build-system gnu-build-system)
+    (arguments
+     '(#:phases
+       (alist-cons-after
+        'unpack 'autoreconf
+        (lambda _ (zero? (system* "autoreconf" "-vif")))
+        %standard-phases)))
+    (native-inputs
+     `(("autoconf" ,autoconf)
+       ("automake" ,automake)
+       ("libtool" ,libtool)))
+    (home-page "http://hannonlab.cshl.edu/fastx_toolkit";)
+    (synopsis "Gordon's text utils library")
+    (description
+     "libgtextutils is a text utilities library used by the fastx toolkit from
+the Hannon Lab.")
+    (license license:agpl3+)))
-- 
2.1.0

>From 1d386b93064eb839e0156938ac38919daa654839 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Tue, 14 Apr 2015 16:36:30 +0200
Subject: [PATCH 2/2] gnu: Add FASTX Toolkit.

* gnu/packages/bioinformatics.scm (fastx-toolkit): New variable.
---
 gnu/packages/bioinformatics.scm | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 615d70d..0239e97 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -41,6 +41,7 @@
   #:use-module (gnu packages statistics)
   #:use-module (gnu packages swig)
   #:use-module (gnu packages tbb)
+  #:use-module (gnu packages textutils)
   #:use-module (gnu packages vim)
   #:use-module (gnu packages xml)
   #:use-module (gnu packages zip))
@@ -473,6 +474,38 @@ file formats including SAM/BAM, Wiggle/BigWig, BED, 
GFF/GTF, VCF.")
 other types of unwanted sequence from high-throughput sequencing reads.")
     (license license:expat)))
 
+(define-public fastx-toolkit
+  (package
+    (name "fastx-toolkit")
+    (version "0.0.14")
+    (source (origin
+              (method url-fetch)
+              (uri
+               (string-append
+                "https://github.com/agordon/fastx_toolkit/releases/download/";
+                version "/fastx_toolkit-" version ".tar.bz2"))
+              (sha256
+               (base32
+                "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
+    (build-system gnu-build-system)
+    (inputs
+     `(("libgtextutils" ,libgtextutils)))
+    (native-inputs
+     `(("pkg-config" ,pkg-config)))
+    (home-page "http://hannonlab.cshl.edu/fastx_toolkit/";)
+    (synopsis "Tools for FASTA/FASTQ file preprocessing")
+    (description
+     "The FASTX-Toolkit is a collection of command line tools for Short-Reads
+FASTA/FASTQ files preprocessing.
+
+Next-Generation sequencing machines usually produce FASTA or FASTQ files,
+containing multiple short-reads sequences.  The main processing of such
+FASTA/FASTQ files is mapping the sequences to reference genomes.  However, it
+is sometimes more productive to preprocess the files before mapping the
+sequences to the genome---manipulating the sequences to produce better mapping
+results.  The FASTX-Toolkit tools perform some of these preprocessing tasks.")
+    (license license:agpl3+)))
+
 (define-public flexbar
   (package
     (name "flexbar")
-- 
2.1.0