add setup.py so it pip installs, minor code cleanups

LICENCE.txt

@@ -0,0 +1,2 @@
+graftm - Licence
+========================

MANIFEST.in

@@ -0,0 +1,2 @@
+include *.txt
+recursive-include examples *.txt *.py

bin/graftM

@@ -17,8 +17,9 @@ __license__ = "GPL3"
 __maintainer__ = "Joel Boyd, Ben Woodcroft"
 __email__ = "joel.boyd near uq.net.au, b.woodcroft near uq.edu.au"
 __status__ = "Development"
-__version__ = "0.4.2"
 
+
+import graftm
 from graftm.Run import Run
 import argparse
 import sys
@@ -62,13 +63,14 @@ UTILITIES
                         e.g. usage:
                             graftM filter --reads <READS> --graftM_package <GRAFTM_PACKAGE> 
 =====================================================================================================
-""" % (__version__)
+""" % (graftm.__version__)
 
 
 
 if __name__ == '__main__':
 
     parser = argparse.ArgumentParser(add_help=False)
+    parser.add_argument('--version', action='version', version='graftM v%s' % graftm.__version__)
 
     subparsers = parser.add_subparsers(help="--", dest='subparser_name')
 
@@ -90,7 +92,6 @@ if __name__ == '__main__':
     graft_parser.add_argument('--seach_and_align_only', action="store_true", help='Stop after reads have been identified and aligned (default=False)', default=False)
     graft_parser.add_argument('--search_only', action="store_true", help='Stop after reads have been identified (default=False)', default=False)
     graft_parser.add_argument('--check_total_euks', action="store_true", help='Search whole sample for 18S and attempt to estimate relative percentage of Eukaryotes (default=False)', default=False)
-    graft_parser.add_argument('--version', action='version', version='graftM v%s' % __version__)
     graft_parser.add_argument('--output_directory', metavar='reference_package', type=str, help='Output directory name. If unspecified, this file will be named GraftM_proc', default=argparse.SUPPRESS)
 
 
@@ -114,7 +115,6 @@ if __name__ == '__main__':
     assemble_parser.add_argument('--graft_run', metavar='File produced ', help='guppy file produced by graftM, comma separated (default=True)', default=True)
     assemble_parser.add_argument('--kmer', metavar='k-mer',  help='k-mer to use for assembly with velvet', default = '51')
     assemble_parser.add_argument('--assembly_type', metavar='type of assembly', help='phrap or velvet assembly',choices = ['phrap', 'velvet', 'finishm'], default='velvet')
-    assemble_parser.add_argument('--version', action='version', version='graftM v%s' % __version__)
     assemble_parser.add_argument('--finish', action = 'store_true', help='finish the velvet assembly with an overlap assembly (default=False)', default=False)
 
     # Manage - various tools that make the management of graftM output easier
@@ -127,7 +127,6 @@ if __name__ == '__main__':
     manage_parser.add_argument('--profile', metavar='graftM_profile', help='GraftM profile produced by graftM graft run (required=True)', required=True)
     manage_parser.add_argument('--non_cumil', action = 'store_true', help='Return all sequences exclusively at this taxonomic rank (i.e. do not return sequences that were classified to a higher resolution, default=False)', default=False)
     manage_parser.add_argument('--file', action = 'store_true', help='Lineages are in a file, one entry per line (default=False)', default=False)
-    manage_parser.add_argument('--version', action='version', version='graftM v%s' % __version__)
 
     # Pathfinder - Find a whole pathway of genes in a metagenome/transcriptome.
     pathfinder_parser = subparsers.add_parser('pathfinder',
@@ -138,14 +137,13 @@ if __name__ == '__main__':
 
 
 
-    if(len(sys.argv) == 1 or sys.argv[1] == '-h' or sys.argv == '--help'):
+    if(len(sys.argv) == 1 or sys.argv[1] == '-h' or sys.argv[1] == '--help'):
         phelp()
         exit(0)
     else:
         args = parser.parse_args()
 
     Run(args).main()
-    exit(0)
 
     # Summary of class abbreviations:
     # Messenger         = M

ez_setup.py

@@ -0,0 +1,259 @@
+
+#!python
+"""Bootstrap setuptools installation
+
+If you want to use setuptools in your package's setup.py, just include this
+file in the same directory with it, and add this to the top of your setup.py::
+
+from ez_setup import use_setuptools
+use_setuptools()
+
+If you want to require a specific version of setuptools, set a download
+mirror, or use an alternate download directory, you can do so by supplying
+the appropriate options to ``use_setuptools()``.
+
+This file can also be run as a script to install or upgrade setuptools.
+"""
+import os
+import shutil
+import sys
+import tempfile
+import tarfile
+import optparse
+import subprocess
+
+from distutils import log
+
+try:
+    from site import USER_SITE
+except ImportError:
+    USER_SITE = None
+
+DEFAULT_VERSION = "0.9.6"
+DEFAULT_URL = "https://pypi.python.org/packages/source/s/setuptools/"
+
+def _python_cmd(*args):
+    args = (sys.executable,) + args
+    return subprocess.call(args) == 0
+
+def _install(tarball, install_args=()):
+    # extracting the tarball
+    tmpdir = tempfile.mkdtemp()
+    log.warn('Extracting in %s', tmpdir)
+    old_wd = os.getcwd()
+    try:
+        os.chdir(tmpdir)
+        tar = tarfile.open(tarball)
+        _extractall(tar)
+        tar.close()
+
+        # going in the directory
+        subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+        os.chdir(subdir)
+        log.warn('Now working in %s', subdir)
+
+        # installing
+        log.warn('Installing Setuptools')
+        if not _python_cmd('setup.py', 'install', *install_args):
+            log.warn('Something went wrong during the installation.')
+            log.warn('See the error message above.')
+            # exitcode will be 2
+            return 2
+    finally:
+        os.chdir(old_wd)
+        shutil.rmtree(tmpdir)
+
+
+def _build_egg(egg, tarball, to_dir):
+    # extracting the tarball
+    tmpdir = tempfile.mkdtemp()
+    log.warn('Extracting in %s', tmpdir)
+    old_wd = os.getcwd()
+    try:
+        os.chdir(tmpdir)
+        tar = tarfile.open(tarball)
+        _extractall(tar)
+        tar.close()
+
+        # going in the directory
+        subdir = os.path.join(tmpdir, os.listdir(tmpdir)[0])
+        os.chdir(subdir)
+        log.warn('Now working in %s', subdir)
+
+        # building an egg
+        log.warn('Building a Setuptools egg in %s', to_dir)
+        _python_cmd('setup.py', '-q', 'bdist_egg', '--dist-dir', to_dir)
+
+    finally:
+        os.chdir(old_wd)
+        shutil.rmtree(tmpdir)
+    # returning the result
+    log.warn(egg)
+    if not os.path.exists(egg):
+        raise IOError('Could not build the egg.')
+
+
+def _do_download(version, download_base, to_dir, download_delay):
+    egg = os.path.join(to_dir, 'setuptools-%s-py%d.%d.egg'
+                       % (version, sys.version_info[0], sys.version_info[1]))
+    if not os.path.exists(egg):
+        tarball = download_setuptools(version, download_base,
+                                      to_dir, download_delay)
+        _build_egg(egg, tarball, to_dir)
+    sys.path.insert(0, egg)
+    import setuptools
+    setuptools.bootstrap_install_from = egg
+
+
+def use_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+                   to_dir=os.curdir, download_delay=15):
+    # making sure we use the absolute path
+    to_dir = os.path.abspath(to_dir)
+    was_imported = 'pkg_resources' in sys.modules or \
+        'setuptools' in sys.modules
+    try:
+        import pkg_resources
+    except ImportError:
+        return _do_download(version, download_base, to_dir, download_delay)
+    try:
+        pkg_resources.require("setuptools>=" + version)
+        return
+    except pkg_resources.VersionConflict:
+        e = sys.exc_info()[1]
+        if was_imported:
+            sys.stderr.write(
+            "The required version of setuptools (>=%s) is not available,\n"
+            "and can't be installed while this script is running. Please\n"
+            "install a more recent version first, using\n"
+            "'easy_install -U setuptools'."
+            "\n\n(Currently using %r)\n" % (version, e.args[0]))
+            sys.exit(2)
+        else:
+            del pkg_resources, sys.modules['pkg_resources'] # reload ok
+            return _do_download(version, download_base, to_dir,
+                                download_delay)
+    except pkg_resources.DistributionNotFound:
+        return _do_download(version, download_base, to_dir,
+                            download_delay)
+
+
+def download_setuptools(version=DEFAULT_VERSION, download_base=DEFAULT_URL,
+                        to_dir=os.curdir, delay=15):
+    """Download setuptools from a specified location and return its filename
+
+`version` should be a valid setuptools version number that is available
+as an egg for download under the `download_base` URL (which should end
+with a '/'). `to_dir` is the directory where the egg will be downloaded.
+`delay` is the number of seconds to pause before an actual download
+attempt.
+"""
+    # making sure we use the absolute path
+    to_dir = os.path.abspath(to_dir)
+    try:
+        from urllib.request import urlopen
+    except ImportError:
+        from urllib2 import urlopen
+    tgz_name = "setuptools-%s.tar.gz" % version
+    url = download_base + tgz_name
+    saveto = os.path.join(to_dir, tgz_name)
+    src = dst = None
+    if not os.path.exists(saveto): # Avoid repeated downloads
+        try:
+            log.warn("Downloading %s", url)
+            src = urlopen(url)
+            # Read/write all in one block, so we don't create a corrupt file
+            # if the download is interrupted.
+            data = src.read()
+            dst = open(saveto, "wb")
+            dst.write(data)
+        finally:
+            if src:
+                src.close()
+            if dst:
+                dst.close()
+    return os.path.realpath(saveto)
+
+
+def _extractall(self, path=".", members=None):
+    """Extract all members from the archive to the current working
+directory and set owner, modification time and permissions on
+directories afterwards. `path' specifies a different directory
+to extract to. `members' is optional and must be a subset of the
+list returned by getmembers().
+"""
+    import copy
+    import operator
+    from tarfile import ExtractError
+    directories = []
+
+    if members is None:
+        members = self
+
+    for tarinfo in members:
+        if tarinfo.isdir():
+            # Extract directories with a safe mode.
+            directories.append(tarinfo)
+            tarinfo = copy.copy(tarinfo)
+            tarinfo.mode = 448 # decimal for oct 0700
+        self.extract(tarinfo, path)
+
+    # Reverse sort directories.
+    if sys.version_info < (2, 4):
+        def sorter(dir1, dir2):
+            return cmp(dir1.name, dir2.name)
+        directories.sort(sorter)
+        directories.reverse()
+    else:
+        directories.sort(key=operator.attrgetter('name'), reverse=True)
+
+    # Set correct owner, mtime and filemode on directories.
+    for tarinfo in directories:
+        dirpath = os.path.join(path, tarinfo.name)
+        try:
+            self.chown(tarinfo, dirpath)
+            self.utime(tarinfo, dirpath)
+            self.chmod(tarinfo, dirpath)
+        except ExtractError:
+            e = sys.exc_info()[1]
+            if self.errorlevel > 1:
+                raise
+            else:
+                self._dbg(1, "tarfile: %s" % e)
+
+
+def _build_install_args(options):
+    """
+Build the arguments to 'python setup.py install' on the setuptools package
+"""
+    install_args = []
+    if options.user_install:
+        if sys.version_info < (2, 6):
+            log.warn("--user requires Python 2.6 or later")
+            raise SystemExit(1)
+        install_args.append('--user')
+    return install_args
+
+def _parse_args():
+    """
+Parse the command line for options
+"""
+    parser = optparse.OptionParser()
+    parser.add_option(
+        '--user', dest='user_install', action='store_true', default=False,
+        help='install in user site package (requires Python 2.6 or later)')
+    parser.add_option(
+        '--download-base', dest='download_base', metavar="URL",
+        default=DEFAULT_URL,
+        help='alternative URL from where to download the setuptools package')
+    options, args = parser.parse_args()
+    # positional arguments are ignored
+    return options
+
+def main(version=DEFAULT_VERSION):
+    """Install or upgrade setuptools and EasyInstall"""
+    options = _parse_args()
+    tarball = download_setuptools(download_base=options.download_base)
+    return _install(tarball, _build_install_args(options))
+
+if __name__ == '__main__':
+    sys.exit(main())

graftm/Alignment_Manager.py

@@ -1,7 +1,7 @@
-#!/usr/bin/env python
+
 from Bio import SeqIO
 from collections import OrderedDict
-import IPython
+
 class Alignment_Manager:
 
     def alignment_correcter(self, alignment_file_list, output_file_name):

graftm/DatManip.py

@@ -1,10 +1,9 @@
-#!/usr/bin/env python
+
 from graftm.Messenger import Messenger
-import IPython
 import subprocess
 import re
 import json
-import shutil
+
 # Constants
 FORMAT_FASTA = 'FORMAT_FASTA'
 FORMAT_FASTQ_GZ = 'FORMAT_FASTQ_GZ'

graftm/Extract_Sequences.py

@@ -1,17 +1,8 @@
-#!/usr/bin/env python
-__author__ = "Joel Boyd, Ben Woodcroft"
-__copyright__ = "Copyright 2014"
-__credits__ = ["Joel Boyd", "Ben Woodcroft"]
-__license__ = "GPL3"
-__maintainer__ = "Joel Boyd, Ben Woodcroft"
-__email__ = "joel.boyd near uq.net.au, b.woodcroft near uq.edu.au"
-__status__ = "Development"
-__version__ = "0.4.0"
 
 from graftm.Messenger import Messenger
 from graftm.assembler import TaxoGroup
 from Bio import SeqIO
-import IPython
+
 class Extract:
 
     def __init__(self):

graftm/GraftMFiles.py

@@ -1,6 +1,5 @@
-#!/usr/bin/env python
+
 import os
-import IPython
 
 class GraftMFiles:
 
@@ -58,9 +57,6 @@ def conv_output_path(self, out_path):
 
     def comb_aln_fa(self, out_path):
         return os.path.join(self.outdir, out_path, "%s_comb.aln.fa" % self.basename)
-
-    def conv_output_rev_path(self, out_path):
-        return os.path.join(self.outdir, out_path, "%s_conv_rev.faa" % self.basename)
 
     def reverse_read_hmmsearch_output_path(self, out_path):
         return os.path.join(self.outdir, out_path, "%s_rev.hmmout.csv" % self.basename)

graftm/Hmmer.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+
 import subprocess
 from graftm.GraftMFiles import GraftMFiles
 from graftm.Messenger import Messenger