remove Python2 crumbs

bcbio/bam/__init__.py

@@ -1,6 +1,5 @@
 """Functionality to query and extract information from aligned BAM files.
 """
-from __future__ import print_function
 import collections
 import os
 import signal
@@ -10,7 +9,7 @@
 import pybedtools
 import pysam
 import toolz as tz
-from six.moves import zip_longest
+from itertools import zip_longest
 
 from bcbio import broad, utils
 from bcbio.bam import ref

bcbio/bam/counts.py

@@ -3,7 +3,6 @@
 These are useful for plotting comparisons between BAM files to look at
 differences in defined or random regions.
 """
-from __future__ import print_function
 import random
 import collections
 

bcbio/bam/coverage.py

@@ -3,7 +3,6 @@
 """
 import os
 
-import six
 import pandas as pd
 import pybedtools
 
@@ -121,9 +120,9 @@ def plot_multiple_regions_coverage(samples, out_file, data, region_bed=None, ste
         return out_file
     in_bams = [dd.get_align_bam(x) for x in samples]
     samplenames = [dd.get_sample_name(x) for x in samples]
-    if isinstance(region_bed, six.string_types):
+    if isinstance(region_bed, str):
         region_bed = pybedtools.BedTool(region_bed)
-    if isinstance(stem_bed, six.string_types):
+    if isinstance(stem_bed, str):
         stem_bed = pybedtools.BedTool(stem_bed)
     if stem_bed is not None:  # tabix indexed bedtools eval to false
         stem_bed = stem_bed.tabix()

bcbio/bam/fastq.py

@@ -1,8 +1,6 @@
 """Utilities for working with fastq files.
 """
 
-import six
-from six.moves import zip
 from itertools import product
 import os
 import random
@@ -250,7 +248,7 @@ def downsample(f1, f2, N, quick=False):
     out_files = (outf1, outf2) if outf2 else (outf1)
 
     with file_transaction(out_files) as tx_out_files:
-        if isinstance(tx_out_files, six.string_types):
+        if isinstance(tx_out_files, str):
             tx_out_f1 = tx_out_files
         else:
             tx_out_f1, tx_out_f2 = tx_out_files

bcbio/chipseq/macs2.py

@@ -1,7 +1,6 @@
 import os
 import glob
 import subprocess
-import sys
 
 from bcbio import utils
 from bcbio.provenance import do

bcbio/cwl/create.py

@@ -1,6 +1,5 @@
 """Create Common Workflow Language (CWL) runnable files and tools from a world object.
 """
-from __future__ import print_function
 import collections
 import copy
 import dateutil
@@ -12,7 +11,6 @@
 import tarfile
 
 import requests
-import six
 import toolz as tz
 import yaml
 
@@ -402,7 +400,7 @@ def _get_cur_remotes(path):
     elif isinstance(path, dict):
         for v in path.values():
             cur_remotes |= _get_cur_remotes(v)
-    elif path and isinstance(path, six.string_types):
+    elif path and isinstance(path, str):
         if path.startswith(tuple(INTEGRATION_MAP.keys())):
             cur_remotes.add(INTEGRATION_MAP.get(path.split(":")[0] + ":"))
     return cur_remotes
@@ -624,7 +622,7 @@ def _get_avro_type(val):
     elif val is None:
         return ["null"]
     # encode booleans as string True/False and unencode on other side
-    elif isinstance(val, bool) or isinstance(val, six.string_types) and val.lower() in ["true", "false", "none"]:
+    elif isinstance(val, bool) or isinstance(val, str) and val.lower() in ["true", "false", "none"]:
         return ["string", "null", "boolean"]
     elif isinstance(val, int):
         return "long"
@@ -747,7 +745,7 @@ def _item_to_cwldata(x, get_retriever, indexes=None):
     """
     if isinstance(x, (list, tuple)):
         return [_item_to_cwldata(subx, get_retriever) for subx in x]
-    elif (x and isinstance(x, six.string_types) and
+    elif (x and isinstance(x, str) and
           (((os.path.isfile(x) or os.path.isdir(x)) and os.path.exists(x)) or
            objectstore.is_remote(x))):
         if _file_local_or_remote(x, get_retriever):

bcbio/cwl/cwlutils.py

@@ -10,7 +10,6 @@
 import pprint
 import tarfile
 
-import six
 import toolz as tz
 
 from bcbio import bam, utils
@@ -58,7 +57,7 @@ def normalize_missing(xs):
             xs[k] = normalize_missing(v)
     elif isinstance(xs, (list, tuple)):
         xs = [normalize_missing(x) for x in xs]
-    elif isinstance(xs, six.string_types):
+    elif isinstance(xs, str):
         if xs.lower() in ["none", "null"]:
             xs = None
         elif xs.lower() == "true":
@@ -81,7 +80,7 @@ def unpack_tarballs(xs, data, use_subdir=True):
             xs[k] = unpack_tarballs(v, data, use_subdir)
     elif isinstance(xs, (list, tuple)):
         xs = [unpack_tarballs(x, data, use_subdir) for x in xs]
-    elif isinstance(xs, six.string_types):
+    elif isinstance(xs, str):
         if os.path.isfile(xs.encode("utf-8", "ignore")) and xs.endswith("-wf.tar.gz"):
             if use_subdir:
                 tarball_dir = utils.safe_makedir(os.path.join(dd.get_work_dir(data), "wf-inputs"))

bcbio/cwl/tool.py

@@ -3,7 +3,6 @@
 Handles wrapping and integrating with multiple tools making it easier
 to run bcbio in a standard way in many environments.
 """
-from __future__ import print_function
 import glob
 import json
 import os

bcbio/cwl/workflow.py

@@ -3,7 +3,6 @@
 import copy
 import pprint
 
-import six
 import toolz as tz
 
 from bcbio.pipeline import alignment
@@ -234,7 +233,7 @@ def _flatten_nested_input(v):
         for x in v["type"]:
             if isinstance(x, dict) and x["type"] == "array":
                 new_type = x["items"]
-            elif isinstance(x, six.string_types) and x == "null":
+            elif isinstance(x, str) and x == "null":
                 want_null = True
             else:
                 new_type = x
@@ -272,15 +271,15 @@ def _clean_output(v):
     return out
 
 def _get_string_vid(vid):
-    if isinstance(vid, six.string_types):
+    if isinstance(vid, str):
         return vid
     assert isinstance(vid, (list, tuple)), vid
     return "__".join(vid)
 
 def _get_variable(vid, variables):
     """Retrieve an input variable from our existing pool of options.
     """
-    if isinstance(vid, six.string_types):
+    if isinstance(vid, str):
         vid = get_base_id(vid)
     else:
         vid = _get_string_vid(vid)
@@ -426,7 +425,7 @@ def _create_variable(orig_v, step, variables):
         v = _get_variable(orig_v["id"], variables)
     except ValueError:
         v = copy.deepcopy(orig_v)
-        if not isinstance(v["id"], six.string_types):
+        if not isinstance(v["id"], str):
             v["id"] = _get_string_vid(v["id"])
     for key, val in orig_v.items():
         if key not in ["id", "type"]:

bcbio/distributed/objectstore.py

@@ -13,7 +13,6 @@
 import time
 import zlib
 
-import six
 
 from bcbio.distributed.transaction import file_transaction
 from bcbio.provenance import do
@@ -23,8 +22,7 @@
 BIODATA_INFO = {"s3": "s3://biodata/prepped/{build}/{build}-{target}.tar.gz"}
 REGIONS_NEWPERMS = {"s3": ["eu-central-1"]}
 
-@six.add_metaclass(abc.ABCMeta)
-class FileHandle(object):
+class FileHandle(metaclass=abc.ABCMeta):
 
     """Contract class for the file handle."""
 
@@ -221,8 +219,7 @@ def close(self):
         pass
 
 
-@six.add_metaclass(abc.ABCMeta)
-class StorageManager(object):
+class StorageManager(metaclass=abc.ABCMeta):
 
     """The contract class for all the storage managers."""
 

bcbio/distributed/runfn.py

@@ -10,7 +10,6 @@
 import pprint
 import shutil
 
-import six
 import toolz as tz
 import yaml
 
@@ -129,7 +128,7 @@ def _add_resources(data, runtime):
         data["config"] = {}
     # Convert input resources, which may be a JSON string
     resources = data.get("resources", {}) or {}
-    if isinstance(resources, six.string_types) and resources.startswith(("{", "[")):
+    if isinstance(resources, str) and resources.startswith(("{", "[")):
         resources = json.loads(resources)
         data["resources"] = resources
     assert isinstance(resources, dict), (resources, data)
@@ -561,7 +560,7 @@ def _file_and_exists(val, input_files):
 def _to_cwl(val, input_files):
     """Convert a value into CWL formatted JSON, handling files and complex things.
     """
-    if isinstance(val, six.string_types):
+    if isinstance(val, str):
         if _file_and_exists(val, input_files):
             val = {"class": "File", "path": val}
             secondary = []

bcbio/distributed/split.py

@@ -10,7 +10,6 @@
 """
 import collections
 
-import six
 
 from bcbio import utils
 
@@ -60,7 +59,7 @@ def parallel_split_combine(args, split_fn, parallel_fn,
     split_args, combine_map, finished_out, extras = _get_split_tasks(args, split_fn, file_key,
                                                                      split_outfile_i)
     split_output = parallel_fn(parallel_name, split_args)
-    if isinstance(combiner, six.string_types):
+    if isinstance(combiner, str):
         combine_args, final_args = _organize_output(split_output, combine_map,
                                                     file_key, combine_arg_keys)
         parallel_fn(combiner, combine_args)

bcbio/galaxy/api.py

@@ -1,6 +1,7 @@
 """Access Galaxy NGLIMS functionality via the standard API.
 """
-from six.moves import urllib
+import urllib.parse
+import urllib.request
 import json
 import time
 

bcbio/galaxy/nglims.py

@@ -1,6 +1,5 @@
 """Integration with Galaxy nglims.
 """
-from __future__ import print_function
 import collections
 import copy
 import glob
@@ -9,7 +8,6 @@
 import subprocess
 
 import joblib
-import six
 import yaml
 
 from bcbio import utils
@@ -106,7 +104,7 @@ def _select_default_algorithm(analysis):
 def _relative_paths(xs, base_path):
     """Adjust paths to be relative to the provided base path.
     """
-    if isinstance(xs, six.string_types):
+    if isinstance(xs, str):
         if xs.startswith(base_path):
             return xs.replace(base_path + "/", "", 1)
         else:

bcbio/graph/graph.py

@@ -1,4 +1,3 @@
-from __future__ import print_function
 
 from datetime import datetime
 import collections

bcbio/heterogeneity/__init__.py

@@ -5,7 +5,6 @@
 to infer these sub-clones to help improve variant calls and interpretation
 especially in complex cancer samples.
 """
-from __future__ import print_function
 import collections
 import os
 

bcbio/heterogeneity/bubbletree.py

@@ -3,7 +3,6 @@
 http://www.bioconductor.org/packages/release/bioc/html/BubbleTree.html
 http://www.bioconductor.org/packages/release/bioc/vignettes/BubbleTree/inst/doc/BubbleTree-vignette.html
 """
-from __future__ import print_function
 import collections
 import csv
 import os

bcbio/heterogeneity/loh.py

@@ -9,8 +9,7 @@
 import uuid
 
 import pandas as pd
-import six
-from six import StringIO
+from io import StringIO
 import toolz as tz
 import yaml
 
@@ -59,7 +58,7 @@ def _matches(tocheck, target):
 def _civic_regions(civic_file, variant_types=None, diseases=None, drugs=None):
     """Retrieve gene regions and names filtered by variant_types and diseases.
     """
-    if isinstance(diseases, six.string_types):
+    if isinstance(diseases, str):
         diseases = [diseases]
     with utils.open_gzipsafe(civic_file) as in_handle:
         reader = csv.reader(in_handle, delimiter="\t")
@@ -369,15 +368,15 @@ def __read_token(self):
                     cp = c
                     c = self.__read_fd(1)
                 e = c
-                v = unicode(''.join(buf).decode('unicode-escape'))
+                v = str(''.join(buf).decode('unicode-escape'))
 
             elif t == "datetime":
                 ## skip "inst"
                 self.__read_fd(4)
 
                 ## read next value as string
                 s = self.__read_token()
-                if not isinstance(s, six.string_types):
+                if not isinstance(s, str):
                     raise ValueError('Str expected, but got %s' % str(s))
 
                 ## remove read string from the value_stack
@@ -392,7 +391,7 @@ def __read_token(self):
 
                 ## read next value as string
                 s = self.__read_token()
-                if not isinstance(s, six.string_types):
+                if not isinstance(s, str):
                     raise ValueError('Str expected, but got %s' % str(s))
 
                 ## remove read string from the value_stack

bcbio/heterogeneity/phylowgs.py

@@ -6,7 +6,6 @@
 https://github.com/morrislab/phylowgs
 http://genomebiology.com/2015/16/1/35
 """
-from __future__ import print_function
 import collections
 import os
 import sys

bcbio/hla/optitype.py

@@ -6,7 +6,6 @@
 import glob
 import os
 import re
-import sys
 import shutil
 
 import toolz as tz

bcbio/hmmer/search.py

@@ -6,8 +6,8 @@
 
 https://github.com/nickloman/entrezajax
 """
-from __future__ import print_function
-from six.moves import urllib
+import urllib.parse
+import urllib.request
 import logging
 
 class SmartRedirectHandler(urllib.request.HTTPRedirectHandler):