Rebase hardening commits from dev

cron/build_chrom_db.py

@@ -17,8 +17,8 @@
 import os
 import sys
 
+import requests
 from six.moves.urllib.parse import urlencode
-from six.moves.urllib.request import urlopen
 
 import parse_builds
 
@@ -36,8 +36,8 @@ def getchrominfo(url, db):
         "hgta_regionType": "",
         "position": "",
         "hgta_doTopSubmit": "get info"})
-    page = urlopen(URL)
-    for line in page:
+    page = requests.get(URL).text
+    for line in page.split('\n'):
         line = line.rstrip( "\r\n" )
         if line.startswith("#"):
             continue

cron/parse_builds.py

@@ -9,18 +9,17 @@
 import sys
 import xml.etree.ElementTree as ElementTree
 
-from six.moves.urllib.request import urlopen
+import requests
 
 
 def getbuilds(url):
     try:
-        page = urlopen(url)
+        text = requests.get(url).text
     except:
         print("#Unable to open " + url)
         print("?\tunspecified (?)")
         sys.exit(1)
 
-    text = page.read()
     try:
         tree = ElementTree.fromstring(text)
     except:

cron/parse_builds_3_sites.py

@@ -6,7 +6,7 @@
 
 import xml.etree.ElementTree as ElementTree
 
-from six.moves.urllib.request import urlopen
+import requests
 
 sites = ['http://genome.ucsc.edu/cgi-bin/',
          'http://archaea.ucsc.edu/cgi-bin/',
@@ -20,11 +20,11 @@ def main():
         trackurl = sites[i] + "hgTracks?"
         builds = []
         try:
-            page = urlopen(site)
+            text = requests.get(site).text
         except:
             print("#Unable to connect to " + site)
             continue
-        text = page.read()
+
         try:
             tree = ElementTree.fromstring(text)
         except:

lib/galaxy/datatypes/binary.py

@@ -241,10 +241,8 @@ def merge(split_files, output_file):
 
     def _is_coordinate_sorted( self, file_name ):
         """See if the input BAM file is sorted from the header information."""
-        params = [ "samtools", "view", "-H", file_name ]
-        output = subprocess.Popen( params, stderr=subprocess.PIPE, stdout=subprocess.PIPE ).communicate()[0]
-        # find returns -1 if string is not found
-        return output.find( "SO:coordinate" ) != -1 or output.find( "SO:sorted" ) != -1
+        output = subprocess.check_output(["samtools", "view", "-H", file_name])
+        return 'SO:coordinate' in output or 'SO:sorted' in output
 
     def dataset_content_needs_grooming( self, file_name ):
         """See if file_name is a sorted BAM file"""
@@ -269,8 +267,7 @@ def dataset_content_needs_grooming( self, file_name ):
                 return False
             index_name = tempfile.NamedTemporaryFile( prefix="bam_index" ).name
             stderr_name = tempfile.NamedTemporaryFile( prefix="bam_index_stderr" ).name
-            command = 'samtools index %s %s' % ( file_name, index_name )
-            proc = subprocess.Popen( args=command, shell=True, stderr=open( stderr_name, 'wb' ) )
+            proc = subprocess.Popen(['samtools', 'index', file_name, index_name], stderr=open(stderr_name, 'wb'))
             proc.wait()
             stderr = open( stderr_name ).read().strip()
             if stderr:
@@ -313,8 +310,8 @@ def groom_dataset_content( self, file_name ):
         tmp_sorted_dataset_file_name_prefix = os.path.join( tmp_dir, 'sorted' )
         stderr_name = tempfile.NamedTemporaryFile( dir=tmp_dir, prefix="bam_sort_stderr" ).name
         samtools_created_sorted_file_name = "%s.bam" % tmp_sorted_dataset_file_name_prefix  # samtools accepts a prefix, not a filename, it always adds .bam to the prefix
-        command = "samtools sort %s %s" % ( file_name, tmp_sorted_dataset_file_name_prefix )
-        proc = subprocess.Popen( args=command, shell=True, cwd=tmp_dir, stderr=open( stderr_name, 'wb' ) )
+        proc = subprocess.Popen(['samtools', 'sort', file_name, tmp_sorted_dataset_file_name_prefix],
+                                cwd=tmp_dir, stderr=open(stderr_name, 'wb'))
         exit_code = proc.wait()
         # Did sort succeed?
         stderr = open( stderr_name ).read().strip()

lib/galaxy/datatypes/converters/interval_to_coverage.py

@@ -132,8 +132,9 @@ def close(self):
     # Sort through a tempfile first
     temp_file = tempfile.NamedTemporaryFile(mode="r")
     environ['LC_ALL'] = 'POSIX'
-    commandline = "sort -f -n -k %d -k %d -k %d -o %s %s" % (chr_col_1 + 1, start_col_1 + 1, end_col_1 + 1, temp_file.name, in_fname)
-    subprocess.check_call(commandline, shell=True)
+    subprocess.check_call([
+        'sort', '-f', '-n', '-k', chr_col_1 + 1, '-k', start_col_1 + 1, '-k', end_col_1 + 1, '-o', temp_file.name, in_fname
+    ])
 
     coverage = CoverageWriter( out_stream=open(out_fname, "a"),
                                chromCol=chr_col_2, positionCol=position_col_2,

lib/galaxy/datatypes/converters/lped_to_pbed_converter.py

@@ -72,9 +72,9 @@ def rgConv(inpedfilepath, outhtmlname, outfilepath, plink):
     if not missval:
         print('### lped_to_pbed_converter.py cannot identify missing value in %s' % pedf)
         missval = '0'
-    cl = '%s --noweb --file %s --make-bed --out %s --missing-genotype %s' % (plink, inpedfilepath, outroot, missval)
-    p = subprocess.Popen(cl, shell=True, cwd=outfilepath)
-    p.wait()  # run plink
+    subprocess.check_call([plink, '--noweb', '--file', inpedfilepath,
+                           '--make-bed', '--out', outroot,
+                           '--missing-genotype', missval], cwd=outfilepath)
 
 
 def main():

lib/galaxy/datatypes/converters/pbed_ldreduced_converter.py

@@ -41,8 +41,7 @@ def pruneLD(plinktasks=[], cd='./', vclbase=[]):
     for task in plinktasks:  # each is a list
         vcl = vclbase + task
         with open(plog, 'w') as sto:
-            x = subprocess.Popen(' '.join(vcl), shell=True, stdout=sto, stderr=sto, cwd=cd)
-            x.wait()
+            subprocess.check_call(vcl, stdout=sto, stderr=sto, cwd=cd)
         try:
             lplog = open(plog, 'r').readlines()
             lplog = [elem for elem in lplog if elem.find('Pruning SNP') == -1]

lib/galaxy/datatypes/converters/pbed_to_lped_converter.py

@@ -40,9 +40,7 @@ def rgConv(inpedfilepath, outhtmlname, outfilepath, plink):
     """
     basename = os.path.split(inpedfilepath)[-1]  # get basename
     outroot = os.path.join(outfilepath, basename)
-    cl = '%s --noweb --bfile %s --recode --out %s ' % (plink, inpedfilepath, outroot)
-    p = subprocess.Popen(cl, shell=True, cwd=outfilepath)
-    p.wait()  # run plink
+    subprocess.check_call([plink, '--noweb', '--bfile', inpedfilepath, '--recode', '--out', outroot], cwd=outfilepath)
 
 
 def main():

lib/galaxy/datatypes/sequence.py

@@ -8,6 +8,7 @@
 import os
 import re
 import string
+import subprocess
 from cgi import escape
 
 from six import PY3
@@ -662,8 +663,7 @@ def process_split_file(data):
         else:
             commands = Sequence.get_split_commands_sequential(is_gzip(input_name), input_name, output_name, start_sequence, sequence_count)
         for cmd in commands:
-            if 0 != os.system(cmd):
-                raise Exception("Executing '%s' failed" % cmd)
+            subprocess.check_call(cmd, shell=True)
         return True
     process_split_file = staticmethod(process_split_file)
 

lib/galaxy/datatypes/tabular.py

@@ -515,15 +515,12 @@ def merge( split_files, output_file):
         Multiple SAM files may each have headers. Since the headers should all be the same, remove
         the headers from files 1-n, keeping them in the first file only
         """
-        cmd = 'mv %s %s' % ( split_files[0], output_file )
-        result = os.system(cmd)
-        if result != 0:
-            raise Exception('Result %s from %s' % (result, cmd))
+        shutil.move(split_files[0], output_file)
+
         if len(split_files) > 1:
-            cmd = 'egrep -v -h "^@" %s >> %s' % ( ' '.join(split_files[1:]), output_file )
-        result = os.system(cmd)
-        if result != 0:
-            raise Exception('Result %s from %s' % (result, cmd))
+            cmd = ['egrep', '-v', '-h', '^@'] + split_files[1:] + ['>>', output_file]
+            subprocess.check_call(cmd, shell=True)
+
     merge = staticmethod(merge)
 
     # Dataproviders

lib/galaxy/datatypes/text.py

@@ -10,6 +10,8 @@
 import subprocess
 import tempfile
 
+from six.moves import shlex_quote
+
 from galaxy.datatypes.data import get_file_peek, Text
 from galaxy.datatypes.metadata import MetadataElement, MetadataParameter
 from galaxy.datatypes.sniff import get_headers
@@ -144,13 +146,12 @@ def _display_data_trusted(self, trans, dataset, preview=False, filename=None, to
             ofilename = ofile_handle.name
             ofile_handle.close()
             try:
-                cmd = 'ipython nbconvert --to html --template full %s --output %s' % (dataset.file_name, ofilename)
-                log.info("Calling command %s" % cmd)
-                subprocess.call(cmd, shell=True)
+                cmd = ['ipython', 'nbconvert', '--to', 'html', '--template', 'full', dataset.file_name, '--output', ofilename]
+                subprocess.check_call(cmd)
                 ofilename = '%s.html' % ofilename
-            except:
+            except subprocess.CalledProcessError:
                 ofilename = dataset.file_name
-                log.exception( 'Command "%s" failed. Could not convert the IPython Notebook to HTML, defaulting to plain text.' % cmd )
+                log.exception('Command "%s" failed. Could not convert the IPython Notebook to HTML, defaulting to plain text.', ' '.join(map(shlex_quote, cmd)))
             return open( ofilename )
 
     def set_meta( self, dataset, **kwd ):

lib/galaxy/external_services/actions.py

@@ -1,6 +1,6 @@
 # Contains actions that are used in External Services
 import logging
-from urllib import urlopen
+import requests
 from galaxy.web import url_for
 from galaxy.util.template import fill_template
 from result_handlers.basic import ExternalServiceActionResultHandler
@@ -104,7 +104,7 @@ def __init__( self, name, param_dict, url, method, target ):  # display_handler
     @property
     def content( self ):
         if self._content is None:
-            self._content = urlopen( self.url ).read()
+            self._content = requests.get(self.url).text
         return self._content
 
 

lib/galaxy/jobs/deferred/pacific_biosciences_smrt_portal.py

@@ -2,13 +2,15 @@
 Module for managing jobs in Pacific Bioscience's SMRT Portal and automatically transferring files
 produced by SMRT Portal.
 """
-import json
 import logging
 import urllib2
 from string import Template
 
+import requests
+
 from data_transfer import DataTransfer
 
+
 log = logging.getLogger( __name__ )
 
 __all__ = [ 'SMRTPortalPlugin' ]
@@ -87,8 +89,8 @@ def check_job( self, job ):
             if self._missing_params( job.params, [ 'smrt_host', 'smrt_job_id' ] ):
                 return self.job_states.INVALID
             url = 'http://' + job.params[ 'smrt_host' ] + self.api_path + '/Jobs/' + job.params[ 'smrt_job_id' ] + '/Status'
-            r = urllib2.urlopen( url )
-            status = json.loads( r.read() )
+            r = requests.get(url)
+            status = r.json()
             # TODO: error handling: unexpected json or bad response, bad url, etc.
             if status[ 'Code' ] == 'Completed':
                 log.debug( "SMRT Portal job '%s' is Completed.  Initiating transfer." % job.params[ 'smrt_job_id' ] )

lib/galaxy/jobs/runners/pulsar.py

@@ -8,6 +8,7 @@
 import errno
 import logging
 import os
+import subprocess
 from time import sleep
 
 from pulsar.client import build_client_manager
@@ -210,7 +211,7 @@ def __init_pulsar_app( self, pulsar_conf_path ):
         else:
             log.info("Loading Pulsar app configuration from %s" % pulsar_conf_path)
             with open(pulsar_conf_path, "r") as f:
-                conf.update(yaml.load(f) or {})
+                conf.update(yaml.safe_load(f) or {})
         if "job_metrics_config_file" not in conf:
             conf["job_metrics"] = self.app.job_metrics
         if "staging_directory" not in conf:
@@ -375,8 +376,7 @@ def __prepare_input_files_locally(self, job_wrapper):
         prepare_input_files_cmds = getattr(job_wrapper, 'prepare_input_files_cmds', None)
         if prepare_input_files_cmds is not None:
             for cmd in prepare_input_files_cmds:  # run the commands to stage the input files
-                if 0 != os.system(cmd):
-                    raise Exception('Error running file staging command: %s' % cmd)
+                subprocess.check_call(cmd, shell=True)
             job_wrapper.prepare_input_files_cmds = None  # prevent them from being used in-line
 
     def _populate_parameter_defaults( self, job_destination ):

lib/galaxy/jobs/runners/util/job_script/__init__.py

@@ -117,9 +117,8 @@ def _handle_script_integrity(path, config):
     sleep_amt = getattr(config, "check_job_script_integrity_sleep", DEFAULT_INTEGRITY_SLEEP)
     for i in range(count):
         try:
-            proc = subprocess.Popen([path], shell=True, env={"ABC_TEST_JOB_SCRIPT_INTEGRITY_XYZ": "1"})
-            proc.wait()
-            if proc.returncode == 42:
+            returncode = subprocess.call([path], env={"ABC_TEST_JOB_SCRIPT_INTEGRITY_XYZ": "1"})
+            if returncode == 42:
                 script_integrity_verified = True
                 break
 

lib/galaxy/jobs/runners/util/kill.py

@@ -1,4 +1,5 @@
 import os
+import subprocess
 from platform import system
 from time import sleep
 from subprocess import Popen
@@ -41,8 +42,8 @@ def _stock_kill_pid(pid):
 
 def __kill_windows(pid):
     try:
-        Popen("taskkill /F /T /PID %i" % pid, shell=True)
-    except Exception:
+        subprocess.check_call(['taskkill', '/F', '/T', '/PID', pid])
+    except subprocess.CalledProcessError:
         pass
 
 

lib/galaxy/jobs/transfer_manager.py

@@ -9,6 +9,8 @@
 import subprocess
 import threading
 
+from six.moves import shlex_quote
+
 from galaxy.util import listify, sleeper
 from galaxy.util.json import jsonrpc_request, validate_jsonrpc_response
 
@@ -22,8 +24,8 @@ class TransferManager( object ):
     def __init__( self, app ):
         self.app = app
         self.sa_session = app.model.context.current
-        self.command = 'python %s' % os.path.abspath( os.path.join( os.getcwd(), 'scripts', 'transfer.py' ) )
-        if app.config.get_bool( 'enable_job_recovery', True ):
+        self.command = ['python', os.path.abspath(os.path.join(os.getcwd(), 'scripts', 'transfer.py'))]
+        if app.config.get_bool('enable_job_recovery', True):
             # Only one Galaxy server process should be able to recover jobs! (otherwise you'll have nasty race conditions)
             self.running = True
             self.sleeper = sleeper.Sleeper()
@@ -67,9 +69,9 @@ def run( self, transfer_jobs ):
             # The transfer script should daemonize fairly quickly - if this is
             # not the case, this process will need to be moved to a
             # non-blocking method.
-            cmd = '%s %s' % ( self.command, tj.id )
-            log.debug( 'Transfer command is: %s' % cmd )
-            p = subprocess.Popen( cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT )
+            cmd = self.command + [tj.id]
+            log.debug('Transfer command is: %s', ' '.join(map(shlex_quote, cmd)))
+            p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
             p.wait()
             output = p.stdout.read( 32768 )
             if p.returncode != 0:

lib/galaxy/managers/citations.py

@@ -1,6 +1,6 @@
 import functools
 import os
-import urllib2
+import requests
 
 from beaker.cache import CacheManager
 from beaker.util import parse_cache_config_options
@@ -47,10 +47,8 @@ def __init__( self, config ):
     def _raw_get_bibtex( self, doi ):
         dx_url = "http://dx.doi.org/" + doi
         headers = {'Accept': 'text/bibliography; style=bibtex, application/x-bibtex'}
-        req = urllib2.Request(dx_url, data="", headers=headers)
-        response = urllib2.urlopen(req)
-        bibtex = response.read()
-        return bibtex
+        req = requests.get(dx_url, headers=headers)
+        return req.text
 
     def get_bibtex( self, doi ):
         createfunc = functools.partial(self._raw_get_bibtex, doi)

lib/galaxy/objectstore/s3.py

@@ -13,7 +13,7 @@
 from datetime import datetime
 
 from galaxy.exceptions import ObjectNotFound, ObjectInvalid
-from galaxy.util import string_as_bool, umask_fix_perms, safe_relpath, directory_hash_id
+from galaxy.util import string_as_bool, umask_fix_perms, safe_relpath, directory_hash_id, which
 from galaxy.util.sleeper import Sleeper
 from .s3_multipart_upload import multipart_upload
 from ..objectstore import ObjectStore, convert_bytes
@@ -59,10 +59,9 @@ def __init__(self, config, config_xml):
             self.cache_monitor_thread.start()
             log.info("Cache cleaner manager started")
         # Test if 'axel' is available for parallel download and pull the key into cache
-        try:
-            subprocess.call('axel')
+        if which('axel'):
             self.use_axel = True
-        except OSError:
+        else:
             self.use_axel = False
 
     def _configure_connection(self):
@@ -333,7 +332,7 @@ def _download(self, rel_path):
                 log.debug("Parallel pulled key '%s' into cache to %s", rel_path, self._get_cache_path(rel_path))
                 ncores = multiprocessing.cpu_count()
                 url = key.generate_url(7200)
-                ret_code = subprocess.call("axel -a -n %s '%s'" % (ncores, url))
+                ret_code = subprocess.call(['axel', '-a', '-n', ncores, url])
                 if ret_code == 0:
                     return True
             else: