port to python 3

c/test_librgt/viactypes.py

@@ -1,4 +1,4 @@
-from __future__ import print_function
+
 import os.path
 from ctypes import *
 from rgt.GenomicRegionSet import GenomicRegionSet

data/setupBinaries.py

@@ -5,7 +5,7 @@
 ###################################################################################################
 
 # Import
-from __future__ import print_function
+
 
 from optparse import OptionParser
 from os import system, path, mkdir

data/setupGenomicData.py

@@ -6,7 +6,7 @@
 ###################################################################################################
 
 # Import
-from __future__ import print_function
+
 import gzip
 from optparse import OptionParser
 from os import system, path, remove, mkdir
@@ -110,7 +110,7 @@ def download(url, prefix, output=None):
         print("OK")
     else:
         gen_root_url = "http://hgdownload.cse.ucsc.edu/goldenPath/hg19/chromosomes/"
-        chr_list = ["chr" + str(e) for e in range(1, 23) + ["X", "Y", "M"]]
+        chr_list = ["chr" + str(e) for e in list(range(1, 23)) + ["X", "Y", "M"]]
         output_genome_file = open(output_genome_file_name, "w")
         to_remove = []
         for chr_name in chr_list:
@@ -219,7 +219,7 @@ def download(url, prefix, output=None):
         print("OK")
     else:
         gen_root_url = "http://hgdownload.cse.ucsc.edu/goldenPath/mm9/chromosomes/"
-        chr_list = ["chr" + str(e) for e in range(1, 20) + ["X", "Y", "M"]]
+        chr_list = ["chr" + str(e) for e in list(range(1, 20)) + ["X", "Y", "M"]]
         output_genome_file = open(output_genome_file_name, "w")
         to_remove = []
         for chr_name in chr_list:

data/setupLogoData.py

@@ -7,7 +7,7 @@
 ###################################################################################################
 
 # Import
-from __future__ import print_function
+
 
 import argparse
 from os import path, mkdir, listdir, walk

docs/conf.py

@@ -45,8 +45,8 @@
 master_doc = 'index'
 
 # General information about the project.
-project = u'RGT'
-copyright = u'2016, Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa'
+project = 'RGT'
+copyright = '2016, Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -217,8 +217,8 @@
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-  ('index', 'RGT.tex', u'RGT Documentation',
-   u'Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa', 'manual'),
+  ('index', 'RGT.tex', 'RGT Documentation',
+   'Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -247,8 +247,8 @@
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'rgt', u'RGT Documentation',
-     [u'Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa'], 1)
+    ('index', 'rgt', 'RGT Documentation',
+     ['Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa'], 1)
 ]
 
 # If true, show URL addresses after external links.
@@ -261,8 +261,8 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'RGT', u'RGT Documentation',
-   u'Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa', 'RGT', 'One line description of project.',
+  ('index', 'RGT', 'RGT Documentation',
+   'Manuel Allhoff, Joseph C.C. Kuo, Eduardo G. Gusmao, Ivan G. Costa', 'RGT', 'One line description of project.',
    'Miscellaneous'),
 ]
 

rgt/AnnotationSet.py

@@ -8,7 +8,7 @@
 """
 
 # Python 3 compatibility
-from __future__ import print_function
+
 
 # Python
 import os
@@ -231,13 +231,13 @@ def load_gene_list(self, file_name, filter_havana=True, protein_coding=False, kn
                 pass
 
             addt_list = line_list[8].split(";")
-            addt_list = filter(None, addt_list)
+            addt_list = [_f for _f in addt_list if _f]
 
             # Processing additional list of options
             addt_dict = dict()
             for addt_element in addt_list:
                 addt_element_list = addt_element.split(" ")
-                addt_element_list = filter(None, addt_element_list)
+                addt_element_list = [_f for _f in addt_element_list if _f]
                 # Removing " symbol from string options
                 addt_element_list[1] = addt_element_list[1].replace("\"", "")
                 addt_dict[addt_element_list[0]] = addt_element_list[1]
@@ -487,11 +487,11 @@ def get(self, query=None, list_type=DataType.GENE_LIST, return_type=ReturnType.A
         if isinstance(query, dict):
 
             # Iterating over query elements
-            for query_key in query.keys():
+            for query_key in list(query.keys()):
 
                 # O(n) operation if a single value is being queried.
                 if not isinstance(query[query_key], list):
-                    current_list = filter(lambda k: k[query_key] == query[query_key], current_list)
+                    current_list = [k for k in current_list if k[query_key] == query[query_key]]
 
                 # O(n log n) operation if multiple values are being queried.
                 else:

rgt/CoverageSet.py

@@ -6,8 +6,8 @@
 """
 
 # Python 3 compatibility
-from __future__ import print_function
-from __future__ import division
+
+
 
 # Python
 from functools import reduce
@@ -568,14 +568,14 @@ def index2coordinates(self, index, regions):
         """
         r = regions
         iter = r.__iter__()
-        r = iter.next()
+        r = next(iter)
         sum = r.final
         last = 0
         i = 0
         while sum <= index * self.stepsize:
             last += len(self.coverage[i])
             try:
-                r = iter.next()
+                r = next(iter)
             except StopIteration:
                 sum += r.final
                 i += 1
@@ -706,7 +706,7 @@ def _map(self, x):
     # get first chromosome, typically chr1
     # for s in FastaReader(genome_path):
     #    chromosomes.append(s.name)
-    tmp = chrom_sizes_dict.keys()
+    tmp = list(chrom_sizes_dict.keys())
     # tmp = map(lambda x: x.replace('chr',''), chromosomes)
     tmp.sort()
     genome_fasta = pysam.Fastafile(genome_path)
@@ -739,7 +739,7 @@ def _map(self, x):
     content._compute()
     r = []
     for l in gc_content_cov:
-        tmp = map(content._map, l)
+        tmp = list(map(content._map, l))
         r.append(tmp)
 
     return r, content.g, content.g_gc

rgt/ExperimentalMatrix.py

@@ -6,7 +6,7 @@
 """
 
 # Python
-from __future__ import print_function
+
 
 import os
 
@@ -179,7 +179,7 @@ def read(self, file_path, is_bedgraph=False, verbose=False, test=False, add_regi
         if add_region_len:
             for i, bed in enumerate(self.get_regionsnames()):
                 l = str(len(self.get_regionsets()[i]))
-                for k in self.fieldsDict["factor"].keys():
+                for k in list(self.fieldsDict["factor"].keys()):
                     if bed in self.fieldsDict["factor"][k]:
                         self.fieldsDict["factor"][k + "(" + l + ")"] = self.fieldsDict["factor"][k]
                         del self.fieldsDict["factor"][k]
@@ -315,7 +315,7 @@ def match_ms_tags(self, field, test=False):
         """
 
         # check regions or reads have empty tag
-        altypes = self.fieldsDict[field].keys()
+        altypes = list(self.fieldsDict[field].keys())
         if "ALL" in altypes:
             altypes.remove("ALL")
             for name in self.fieldsDict[field]["ALL"]:
@@ -364,14 +364,14 @@ def remove_empty_regionset(self):
 
     def load_bed_url(self, temp_dir):
         """Load the BED files which contains url as file path to temporary directory."""
-        import urllib
-        for key, value in self.files.items():
+        import urllib.request, urllib.parse, urllib.error
+        for key, value in list(self.files.items()):
             if self.types[self.names.index(key)] == "regions" and "http" in value:
                 tmpfile = os.path.join(temp_dir, value.split('/')[-1])
                 dest_name = tmpfile.partition(".gz")[0]
                 if not os.path.isfile(dest_name):
                     if not os.path.isfile(tmpfile):
-                        urllib.urlretrieve(value, tmpfile)
+                        urllib.request.urlretrieve(value, tmpfile)
                     if value.endswith(".gz"):
                         import gzip
                         with gzip.open(tmpfile, 'rb') as infile:

rgt/GeneSet.py

@@ -10,7 +10,7 @@
 ###############################################################################
 
 # Python
-from __future__ import print_function
+
 
 # Internal
 from .Util import GenomeData