remove six dependency

gffutils/attributes.py

@@ -1,4 +1,3 @@
-import six
 import collections
 
 try:
@@ -95,7 +94,7 @@ def __str__(self):
  return "\n".join(s)
 
  def update(self, *args, **kwargs):
- for k, v in six.iteritems(dict(*args, **kwargs)):
+ for k, v in dict(*args, **kwargs).items():
  self[k] = v
 
 

gffutils/biopython_integration.py

@@ -2,7 +2,6 @@
 Module for integration with BioPython, specifically SeqRecords and SeqFeature
 objects.
 """
-import six
 
 try:
  from Bio.SeqFeature import SeqFeature, FeatureLocation
@@ -15,7 +14,8 @@
 _biopython_strand = {
  "+": 1,
  "-": -1,
- ".": 0,
+ ".": None,
+ "?": 0,
 }
 _feature_strand = dict((v, k) for k, v in _biopython_strand.items())
 
@@ -33,7 +33,7 @@ def to_seqfeature(feature):
  If string, assume it is a GFF or GTF-format line; otherwise just use
  the provided feature directly.
  """
- if isinstance(feature, six.string_types):
+ if isinstance(feature, str):
  feature = feature_from_line(feature)
 
  qualifiers = {
@@ -68,7 +68,7 @@ def from_seqfeature(s, **kwargs):
  score = s.qualifiers.get("score", ".")[0]
  seqid = s.qualifiers.get("seqid", ".")[0]
  frame = s.qualifiers.get("frame", ".")[0]
- strand = _feature_strand[s.strand]
+ strand = _feature_strand[s.location.strand]
 
  # BioPython parses 1-based GenBank positions into 0-based for use within
  # Python. We need to convert back to 1-based GFF format here.

gffutils/convert.py

@@ -2,7 +2,6 @@
 Conversion functions that operate on :class:`FeatureDB` classes.
 """
 
-import six
 
 
 def to_bed12(f, db, child_type="exon", name_field="ID"):
@@ -22,7 +21,7 @@ def to_bed12(f, db, child_type="exon", name_field="ID"):
  Attribute to be used in the "name" field of the BED12 entry. Usually
  "ID" for GFF; "transcript_id" for GTF.
  """
- if isinstance(f, six.string_types):
+ if isinstance(f, str):
  f = db[f]
  children = list(db.children(f, featuretype=child_type, order_by="start"))
  sizes = [len(i) for i in children]

gffutils/create.py

@@ -5,7 +5,6 @@
 import sys
 import os
 import sqlite3
-import six
 from textwrap import dedent
 from gffutils import constants
 from gffutils import version
@@ -119,7 +118,7 @@ def __init__(
  os.unlink(dbfn)
  self.dbfn = dbfn
  self.id_spec = id_spec
- if isinstance(dbfn, six.string_types):
+ if isinstance(dbfn, str):
  conn = sqlite3.connect(dbfn)
  else:
  conn = dbfn
@@ -171,7 +170,7 @@ def _id_handler(self, f):
  """
 
  # If id_spec is a string or callable, convert to iterable for later
- if isinstance(self.id_spec, six.string_types):
+ if isinstance(self.id_spec, str):
  id_key = [self.id_spec]
  elif hasattr(self.id_spec, "__call__"):
  id_key = [self.id_spec]
@@ -181,7 +180,7 @@ def _id_handler(self, f):
  elif isinstance(self.id_spec, dict):
  try:
  id_key = self.id_spec[f.featuretype]
- if isinstance(id_key, six.string_types):
+ if isinstance(id_key, str):
  id_key = [id_key]
 
  # Otherwise, use default auto-increment.
@@ -684,7 +683,7 @@ def _update_relations(self):
  # c.execute('CREATE INDEX childindex ON relations (child)')
  # self.conn.commit()
 
- if isinstance(self._keep_tempfiles, six.string_types):
+ if isinstance(self._keep_tempfiles, str):
  suffix = self._keep_tempfiles
  else:
  suffix = ".gffutils"
@@ -883,7 +882,7 @@ def _update_relations(self):
  msg = "transcript"
  logger.info("Inferring %s extents " "and writing to tempfile" % msg)
 
- if isinstance(self._keep_tempfiles, six.string_types):
+ if isinstance(self._keep_tempfiles, str):
  suffix = self._keep_tempfiles
  else:
  suffix = ".gffutils"

gffutils/feature.py

@@ -1,5 +1,4 @@
 from pyfaidx import Fasta
-import six
 import simplejson as json
 from gffutils import constants
 from gffutils import helpers
@@ -166,7 +165,7 @@ def __init__(
  # for testing.
  attributes = attributes or dict_class()
 
- if isinstance(attributes, six.string_types):
+ if isinstance(attributes, str):
  try:
  attributes = helpers._unjsonify(attributes, isattributes=True)
 
@@ -182,7 +181,7 @@ def __init__(
  # If string, then try un-JSONifying it into a list; if that doesn't
  # work then assume it's tab-delimited and convert to a list.
  extra = extra or []
- if isinstance(extra, six.string_types):
+ if isinstance(extra, str):
  try:
  extra = helpers._unjsonify(extra)
  except json.JSONDecodeError:
@@ -254,10 +253,7 @@ def __setitem__(self, key, value):
  self.attributes[key] = value
 
  def __str__(self):
- if six.PY3:
- return self.__unicode__()
- else:
- return unicode(self).encode("utf-8")
+ return self.__unicode__()
 
  def __unicode__(self):
 
@@ -387,7 +383,7 @@ def sequence(self, fasta, use_strand=True):
  -------
  string
  """
- if isinstance(fasta, six.string_types):
+ if isinstance(fasta, str):
  fasta = Fasta(fasta, as_raw=False)
 
  # recall GTF/GFF is 1-based closed; pyfaidx uses Python slice notation

gffutils/gffwriter.py

@@ -1,7 +1,6 @@
 ##
 ## GFF Writer (writer): serializing gffutils records as GFF text files.
 ##
-import six
 import tempfile
 import shutil
 from time import strftime, localtime
@@ -41,7 +40,7 @@ def __init__(self, out, with_header=True, in_place=False):
  self.temp_file = None
  # Output stream to write to
  self.out_stream = None
- if isinstance(out, six.string_types):
+ if isinstance(out, str):
  if self.in_place:
  # Use temporary file
  self.temp_file = tempfile.NamedTemporaryFile(delete=False)

gffutils/helpers.py

@@ -4,7 +4,6 @@
 import simplejson as json
 import time
 import tempfile
-import six
 from gffutils import constants
 from gffutils import bins
 import gffutils
@@ -202,7 +201,7 @@ def make_query(
  # e.g., "featuretype = 'exon'"
  #
  # or, "featuretype IN ('exon', 'CDS')"
- if isinstance(featuretype, six.string_types):
+ if isinstance(featuretype, str):
  d["FEATURETYPE"] = "features.featuretype = ?"
  args.append(featuretype)
  else:
@@ -218,7 +217,7 @@ def make_query(
  # `limit` is a string or a tuple of (chrom, start, stop)
  #
  # e.g., "seqid = 'chr2L' AND start > 1000 AND end < 5000"
- if isinstance(limit, six.string_types):
+ if isinstance(limit, str):
  seqid, startstop = limit.split(":")
  start, end = startstop.split("-")
  else:
@@ -257,7 +256,7 @@ def make_query(
  # Default is essentially random order.
  #
  # e.g. "ORDER BY seqid, start DESC"
- if isinstance(order_by, six.string_types):
+ if isinstance(order_by, str):
  _order_by.append(order_by)
 
  else:
@@ -387,7 +386,7 @@ def merge_attributes(attr1, attr2, numeric_sort=False):
  if not isinstance(v, list):
  new_d[k] = [v]
 
- for k, v in six.iteritems(attr1):
+ for k, v in attr1.items():
  if k in attr2:
  if not isinstance(v, list):
  v = [v]
@@ -507,9 +506,9 @@ def is_gff_db(db_fname):
 
 
 def to_unicode(obj, encoding="utf-8"):
- if isinstance(obj, six.string_types):
- if not isinstance(obj, six.text_type):
- obj = six.text_type(obj, encoding)
+ if isinstance(obj, str):
+ if not isinstance(obj, str):
+ obj = str(obj, encoding)
  return obj
 
 

gffutils/interface.py

@@ -1,6 +1,5 @@
 import collections
 import os
-import six
 import sqlite3
 import shutil
 import warnings
@@ -694,7 +693,7 @@ def region(
  "If region is supplied, do not supply seqid, "
  "start, or end as separate kwargs"
  )
- if isinstance(region, six.string_types):
+ if isinstance(region, str):
  toks = region.split(":")
  if len(toks) == 1:
  seqid = toks[0]
@@ -774,7 +773,7 @@ def region(
 
  # Add the featuretype clause
  if featuretype is not None:
- if isinstance(featuretype, six.string_types):
+ if isinstance(featuretype, str):
  featuretype = [featuretype]
  feature_clause = " or ".join(["featuretype = ?" for _ in featuretype])
  query += " AND (%s) " % feature_clause
@@ -994,7 +993,7 @@ def delete(self, features, make_backup=True, **kwargs):
  FeatureDB object, with features deleted.
  """
  if make_backup:
- if isinstance(self.dbfn, six.string_types):
+ if isinstance(self.dbfn, str):
  shutil.copy2(self.dbfn, self.dbfn + ".bak")
 
  c = self.conn.cursor()
@@ -1006,12 +1005,12 @@ def delete(self, features, make_backup=True, **kwargs):
  """
  if isinstance(features, FeatureDB):
  features = features.all_features()
- if isinstance(features, six.string_types):
+ if isinstance(features, str):
  features = [features]
  if isinstance(features, Feature):
  features = [features]
  for feature in features:
- if isinstance(feature, six.string_types):
+ if isinstance(feature, str):
  _id = feature
  else:
  _id = feature.id
@@ -1060,7 +1059,7 @@ def update(self, data, make_backup=True, **kwargs):
  from gffutils import iterators
 
  if make_backup:
- if isinstance(self.dbfn, six.string_types):
+ if isinstance(self.dbfn, str):
  shutil.copy2(self.dbfn, self.dbfn + ".bak")
 
  # get iterator-specific kwargs
@@ -1139,9 +1138,9 @@ def child_func(parent, child):
  -------
  FeatureDB object with new relations added.
  """
- if isinstance(parent, six.string_types):
+ if isinstance(parent, str):
  parent = self[parent]
- if isinstance(child, six.string_types):
+ if isinstance(child, str):
  child = self[child]
 
  c = self.conn.cursor()

gffutils/iterators.py

@@ -16,13 +16,8 @@
 from gffutils.interface import FeatureDB
 from gffutils import helpers
 from textwrap import dedent
-import six
-from six.moves.urllib.request import urlopen
-
-if six.PY3:
- from urllib import parse as urlparse
-else:
- import urlparse
+from urllib.request import urlopen
+from urllib import parse as urlparse
 
 
 class Directive(object):
@@ -133,7 +128,7 @@ def _custom_iter(self):
  valid_lines = 0
  with self.open_function(self.data) as fh:
  for i, line in enumerate(fh):
- if isinstance(line, six.binary_type):
+ if isinstance(line, bytes):
  line = line.decode("utf-8")
  line = line.rstrip("\n\r")
  self.current_item = line
@@ -295,11 +290,11 @@ def DataIterator(
  force_dialect_check=force_dialect_check,
  **kwargs,
  )
- if isinstance(data, six.string_types):
+ if isinstance(data, str):
  if from_string:
  tmp = tempfile.NamedTemporaryFile(delete=False)
  data = dedent(data)
- if isinstance(data, six.text_type):
+ if isinstance(data, str):
  data = data.encode("utf-8")
  tmp.write(data)
  tmp.close()

gffutils/parser.py

@@ -3,7 +3,7 @@
 import re
 import copy
 import collections
-from six.moves import urllib
+import urllib
 from gffutils import constants
 from gffutils.exceptions import AttributeStringError
 

gffutils/pybedtools_integration.py

@@ -6,7 +6,6 @@
 import pybedtools
 from pybedtools import featurefuncs
 from gffutils import helpers
-import six
 
 
 def to_bedtool(iterator):
@@ -210,7 +209,7 @@ def gen():
 
  if merge_overlapping or as_bed6:
 
- if isinstance(attrs, six.string_types):
+ if isinstance(attrs, str):
  attrs = [attrs]
 
  def to_bed(f):

gffutils/scripts/gffutils-cli

@@ -1,7 +1,5 @@
 #!/usr/bin/python
 
-from __future__ import print_function
-
 """
 Command line interface for gffutils.