Re: [PATCH 2/3] gnu: Add python-pyxb.

[Marius Bakke <mbakke@fastmail.com>]

[-- Attachment #1: Type: text/plain, Size: 1254 bytes --]

Marius Bakke <mbakke@fastmail.com> writes:

> Ben Woodcroft <b.woodcroft@uq.edu.au> writes:
>
>>>
>>>> Also, I notice that pysam bundles htslib, bcftools and samtools C code.
>>>> Hopefully it should be straightforward enough to remove htslib as there
>>>> are install instructions, I'm not sure about the other two. This
>>>> shouldn't block the patch here, but would you mind taking a look?
>>>> http://pysam.readthedocs.io/en/latest/installation.html#installation
>>> I had a go at this, and also enabled tests since I was reading the build
>>> system anyway. Samtools and bcftools does not seem possible to un-bundle
>>> at this time, but htslib was straightforward.
>> OK. I don't think it needs to be propagated though, right? Also, would 
>> you mind separating the change to modify-phases syntax and unbundling of 
>> htslib into two patches please? Other than that this whole series LGTM.
>
> Modify-phases is now a separate patch. Htslib is propagated because it
> is included by the installed samtools and bcftools headers; at least one
> of pysams dependencies failed to build when it was a regular input.
>
> I added some comments and other cosmetic changes. Updated patch below.

Oops, found a spelling error in the previous patch. Fixed.


[-- Attachment #2: pysam-and-pbcore-update.patch --]
[-- Type: text/x-patch, Size: 15360 bytes --]

From eaa38fb4174997f6282ff7d278a6aa4153b75bcf Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Fri, 16 Sep 2016 18:05:15 +0100
Subject: [PATCH 1/7] gnu: python-pysam: Update to 0.9.1.4.

* gnu/packages/bioinformatics.scm (python-pysam, python2-pysam): Update
to 0.9.1.4.
---
 gnu/packages/bioinformatics.scm | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 1bf91a9..6e83461 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -1290,13 +1290,13 @@ multiple sequence alignments.")
 (define-public python-pysam
   (package
     (name "python-pysam")
-    (version "0.8.4")
+    (version "0.9.1.4")
     (source (origin
               (method url-fetch)
               (uri (pypi-uri "pysam" version))
               (sha256
                (base32
-                "1slx5mb94mzm5qzk52q270sab0sar95j67w1g1k452nz3s9j7krh"))))
+                "1i1djacqbr88y7w18b4aa78zxnsyr4sz7yqdq2spi7gs0y6pzvjn"))))
     (build-system python-build-system)
     (arguments
      `(#:tests? #f ; tests are excluded in the manifest
-- 
2.10.0


From 5431b05fe66398f5c44a1f0a81e1e90663550ac1 Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Sat, 17 Sep 2016 10:33:28 +0100
Subject: [PATCH 2/7] gnu: Add python-pyxb.

* gnu/packages/xml.scm (python-pyxb, python2-pyxb): New variables.
---
 gnu/packages/xml.scm | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/gnu/packages/xml.scm b/gnu/packages/xml.scm
index 7befad5..cd3426b 100644
--- a/gnu/packages/xml.scm
+++ b/gnu/packages/xml.scm
@@ -13,6 +13,7 @@
 ;;; Copyright © 2016 Jan Nieuwenhuizen <janneke@gnu.org>
 ;;; Copyright © 2016 ng0 <ng0@we.make.ritual.n0.is>
 ;;; Copyright © 2016 Tobias Geerinckx-Rice <me@tobias.gr>
+;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
 ;;;
 ;;; This file is part of GNU Guix.
 ;;;
@@ -729,6 +730,30 @@ different Unicode encodings which happen automatically during
 parsing/saving.")
     (license license:expat)))
 
+(define-public python-pyxb
+  (package
+    (name "python-pyxb")
+    (version "1.2.5")
+    (source (origin
+              (method url-fetch)
+              (uri (pypi-uri "PyXB" version))
+              (sha256
+               (base32
+                "0rzzwibfqa28gxgcxx4cybx1qcg0g6fand06ykj3gz7z5kp653sf"))))
+    (build-system python-build-system)
+    (home-page "http://pyxb.sourceforge.net/")
+    (synopsis "Python XML Schema Bindings")
+    (description
+     "PyXB (\"pixbee\") is a pure Python package that generates Python source
+code for classes that correspond to data structures defined by XMLSchema.")
+    (license (list license:asl2.0    ; Most files.
+                   license:expat     ; pyxb/utils/six.py
+                   license:gpl2      ; bundled jquery in doc is dual MIT/GPL2
+                   license:psfl))))  ; pyxb/utils/activestate.py
+
+(define-public python2-pyxb
+  (package-with-python2 python-pyxb))
+
 (define-public xmlto
   (package
     (name "xmlto")
-- 
2.10.0


From 923fc43d8c665d1a2795ea2c221003e54544a06b Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Sat, 17 Sep 2016 10:42:56 +0100
Subject: [PATCH 3/7] gnu: python2-pbcore: Update to 1.2.10.

* gnu/packages/bioinformatics.scm (python2-pbcore): Update to 1.2.10.
[propagated-inputs]: New field. Add python2-pyxb.
---
 gnu/packages/bioinformatics.scm | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 6e83461..a935d5a 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3376,13 +3376,13 @@ interrupted by stop codons.  OrfM finds and prints these ORFs.")
 (define-public python2-pbcore
   (package
     (name "python2-pbcore")
-    (version "1.2.8")
+    (version "1.2.10")
     (source (origin
               (method url-fetch)
               (uri (pypi-uri "pbcore" version))
               (sha256
                (base32
-                "02pfn5raa3zf739672bg0dkx7z3j2c4nx7vmpfjqy5b12jrqpymk"))))
+                "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
     (build-system python-build-system)
     (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
     (inputs
@@ -3395,6 +3395,8 @@ interrupted by stop codons.  OrfM finds and prints these ORFs.")
        ("python-nose" ,python2-nose)
        ("python-setuptools" ,python2-setuptools)
        ("python-sphinx" ,python2-sphinx)))
+    (propagated-inputs
+     `(("python-pyxb" ,python2-pyxb)))
     (home-page "http://pacificbiosciences.github.io/pbcore/")
     (synopsis "Library for reading and writing PacBio data files")
     (description
-- 
2.10.0


From 7748677c13242b7edb6ddae1efed7f0699e487bf Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Thu, 22 Sep 2016 13:47:53 +0100
Subject: [PATCH 4/7] gnu: Add bcftools.

* gnu/packages/bioinformatics.scm (bcftools): New variable.
---
 gnu/packages/bioinformatics.scm | 58 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index a935d5a..679502e 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -265,6 +265,64 @@ instance, it implements several methods to assess contig-wise read coverage.")
 BAM files.")
     (license license:expat)))
 
+(define-public bcftools
+  (package
+    (name "bcftools")
+    (version "1.3.1")
+    (source (origin
+              (method url-fetch)
+              (uri (string-append
+                    "https://github.com/samtools/bcftools/releases/download/"
+                    version "/bcftools-" version ".tar.bz2"))
+              (sha256
+               (base32
+                "095ry68vmz9q5s1scjsa698dhgyvgw5aicz24c19iwfbai07mhqj"))
+              (modules '((guix build utils)))
+              (snippet
+               ;; Delete bundled htslib.
+               '(delete-file-recursively "htslib-1.3.1"))))
+    (build-system gnu-build-system)
+    (arguments
+     `(#:test-target "test"
+       #:make-flags
+       (list
+        "USE_GPL=1"
+        (string-append "prefix=" (assoc-ref %outputs "out"))
+        (string-append "HTSDIR=" (assoc-ref %build-inputs "htslib") "/include")
+        (string-append "HTSLIB=" (assoc-ref %build-inputs "htslib") "/lib/libhts.a")
+        (string-append "BGZIP=" (assoc-ref %build-inputs "htslib") "/bin/bgzip")
+        (string-append "TABIX=" (assoc-ref %build-inputs "htslib") "/bin/tabix"))
+       #:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'patch-Makefile
+           (lambda _
+             (substitute* "Makefile"
+               ;; Do not attempt to build htslib.
+               (("^include \\$\\(HTSDIR\\)/htslib\\.mk") "")
+               ;; Link against GSL cblas.
+               (("-lcblas") "-lgslcblas"))
+             #t))
+         (delete 'configure)
+         (add-before 'check 'patch-tests
+           (lambda _
+             (substitute* "test/test.pl"
+               (("/bin/bash") (which "bash")))
+             #t)))))
+    (native-inputs
+     `(("htslib" ,htslib)
+       ("perl" ,perl)))
+    (inputs
+     `(("gsl" ,gsl)
+       ("zlib" ,zlib)))
+    (home-page "https://samtools.github.io/bcftools/")
+    (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
+    (description
+     "BCFtools is a set of utilities that manipulate variant calls in the
+Variant Call Format (VCF) and its binary counterpart BCF.  All commands work
+transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
+    ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
+    (license (list license:gpl3+ license:expat))))
+
 (define-public bedops
   (package
     (name "bedops")
-- 
2.10.0


From d4fd6f8482a76ccfe4d33f80070445d284006166 Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Fri, 23 Sep 2016 06:40:40 +0100
Subject: [PATCH 5/7] gnu: python-pysam: Use 'modify-phases'.

* gnu/packages/bioinformatics.scm (python-pysam)[arguments]: Use
'modify-phases'.
---
 gnu/packages/bioinformatics.scm | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 679502e..518dfea 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -1359,12 +1359,12 @@ multiple sequence alignments.")
     (arguments
      `(#:tests? #f ; tests are excluded in the manifest
        #:phases
-       (alist-cons-before
-        'build 'set-flags
-        (lambda _
-          (setenv "LDFLAGS" "-lncurses")
-          (setenv "CFLAGS" "-D_CURSES_LIB=1"))
-        %standard-phases)))
+       (modify-phases %standard-phases
+         (add-before 'build 'set-flags
+           (lambda _
+             (setenv "LDFLAGS" "-lncurses")
+             (setenv "CFLAGS" "-D_CURSES_LIB=1")
+             #t)))))
     (inputs
      `(("ncurses"           ,ncurses)
        ("zlib"              ,zlib)))
-- 
2.10.0


From e4d3befdc33a77f6b3d1d241befd7077c0be7e70 Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Thu, 22 Sep 2016 14:08:05 +0100
Subject: [PATCH 6/7] gnu: python-pysam: Delete bundled htslib.

* gnu/packages/bioinformatics.scm (python-pysam)[source]: Add snippet
to delete htslib.
[arguments]: Add htslib flags in 'set-flags phase.
[propagated-inputs]: New field. Add htslib.
---
 gnu/packages/bioinformatics.scm | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 518dfea..a712a01 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -1354,17 +1354,28 @@ multiple sequence alignments.")
               (uri (pypi-uri "pysam" version))
               (sha256
                (base32
-                "1i1djacqbr88y7w18b4aa78zxnsyr4sz7yqdq2spi7gs0y6pzvjn"))))
+                "1i1djacqbr88y7w18b4aa78zxnsyr4sz7yqdq2spi7gs0y6pzvjn"))
+              (modules '((guix build utils)))
+              (snippet
+               ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
+               '(delete-file-recursively "htslib"))))
     (build-system python-build-system)
     (arguments
      `(#:tests? #f ; tests are excluded in the manifest
        #:phases
        (modify-phases %standard-phases
          (add-before 'build 'set-flags
-           (lambda _
+           (lambda* (#:key inputs #:allow-other-keys)
+             (setenv "HTSLIB_MODE" "external")
+             (setenv "HTSLIB_LIBRARY_DIR"
+                     (string-append (assoc-ref inputs "htslib") "/lib"))
+             (setenv "HTSLIB_INCLUDE_DIR"
+                     (string-append (assoc-ref inputs "htslib") "/include"))
              (setenv "LDFLAGS" "-lncurses")
              (setenv "CFLAGS" "-D_CURSES_LIB=1")
              #t)))))
+    (propagated-inputs
+     `(("htslib"            ,htslib))) ; Included from installed header files.
     (inputs
      `(("ncurses"           ,ncurses)
        ("zlib"              ,zlib)))
-- 
2.10.0


From 91051e1ee8a2dfd6c4df2f3ed3c509a558f99fe2 Mon Sep 17 00:00:00 2001
From: Marius Bakke <mbakke@fastmail.com>
Date: Thu, 22 Sep 2016 14:11:59 +0100
Subject: [PATCH 7/7] gnu: python-pysam: Enable tests.

* gnu/packages/bioinformatics.scm (python-pysam)[source]: Change from
PyPi to source archive due to missing test data.
[arguments]: Add check phase after install.
[native-inputs]: Add python-nose, samtools and bcftools.
---
 gnu/packages/bioinformatics.scm | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index a712a01..f197ce8 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -1351,18 +1351,21 @@ multiple sequence alignments.")
     (version "0.9.1.4")
     (source (origin
               (method url-fetch)
-              (uri (pypi-uri "pysam" version))
+              ;; Test data is missing on PyPi.
+              (uri (string-append
+                    "https://github.com/pysam-developers/pysam/archive/v"
+                    version ".tar.gz"))
+              (file-name (string-append name "-" version ".tar.gz"))
               (sha256
                (base32
-                "1i1djacqbr88y7w18b4aa78zxnsyr4sz7yqdq2spi7gs0y6pzvjn"))
+                "0y41ssbg6nvn2jgcbnrvkzblpjcwszaiv1rgyd8dwzjkrbfsgsmc"))
               (modules '((guix build utils)))
               (snippet
                ;; Drop bundled htslib. TODO: Also remove samtools and bcftools.
                '(delete-file-recursively "htslib"))))
     (build-system python-build-system)
     (arguments
-     `(#:tests? #f ; tests are excluded in the manifest
-       #:phases
+     `(#:phases
        (modify-phases %standard-phases
          (add-before 'build 'set-flags
            (lambda* (#:key inputs #:allow-other-keys)
@@ -1373,7 +1376,24 @@ multiple sequence alignments.")
                      (string-append (assoc-ref inputs "htslib") "/include"))
              (setenv "LDFLAGS" "-lncurses")
              (setenv "CFLAGS" "-D_CURSES_LIB=1")
-             #t)))))
+             #t))
+         (delete 'check)
+         (add-after 'install 'check
+           (lambda* (#:key inputs outputs #:allow-other-keys)
+             (setenv "PYTHONPATH"
+                     (string-append
+                      (getenv "PYTHONPATH")
+                      ":" (assoc-ref outputs "out")
+                      "/lib/python"
+                      (string-take (string-take-right
+                                    (assoc-ref inputs "python") 5) 3)
+                      "/site-packages"))
+             ;; Step out of source dir so python does not import from CWD.
+             (chdir "tests")
+             (setenv "HOME" "/tmp")
+             (and (zero? (system* "make" "-C" "pysam_data"))
+                  (zero? (system* "make" "-C" "cbcf_data"))
+                  (zero? (system* "nosetests" "-v"))))))))
     (propagated-inputs
      `(("htslib"            ,htslib))) ; Included from installed header files.
     (inputs
@@ -1381,7 +1401,11 @@ multiple sequence alignments.")
        ("zlib"              ,zlib)))
     (native-inputs
      `(("python-cython"     ,python-cython)
-       ("python-setuptools" ,python-setuptools)))
+       ("python-setuptools" ,python-setuptools)
+       ;; Dependencies below are are for tests only.
+       ("samtools"          ,samtools)
+       ("bcftools"          ,bcftools)
+       ("python-nose"       ,python-nose)))
     (home-page "https://github.com/pysam-developers/pysam")
     (synopsis "Python bindings to the SAMtools C API")
     (description
-- 
2.10.0