Merge pull request #11 from mruffalo/master

Minor tweaks/updates

ez_setup.py

@@ -13,6 +13,7 @@
 
 This file can also be run as a script to install or upgrade setuptools.
 """
+from __future__ import print_function
 import sys
 DEFAULT_VERSION = "0.6c11"
 DEFAULT_URL     = "http://pypi.python.org/packages/%s/s/setuptools/" % sys.version[:3]
@@ -63,17 +64,16 @@
 }
 
 import sys, os
-try: from hashlib import md5
-except ImportError: from md5 import md5
+from hashlib import md5
 
 def _validate_md5(egg_name, data):
     if egg_name in md5_data:
         digest = md5(data).hexdigest()
         if digest != md5_data[egg_name]:
-            print >>sys.stderr, (
+            print((
                 "md5 validation of %s failed!  (Possible download problem?)"
                 % egg_name
-            )
+            ), file=sys.stderr)
             sys.exit(2)
     return data
 
@@ -103,14 +103,14 @@ def do_download():
         return do_download()       
     try:
         pkg_resources.require("setuptools>="+version); return
-    except pkg_resources.VersionConflict, e:
+    except pkg_resources.VersionConflict as e:
         if was_imported:
-            print >>sys.stderr, (
+            print((
             "The required version of setuptools (>=%s) is not available, and\n"
             "can't be installed while this script is running. Please install\n"
             " a more recent version first, using 'easy_install -U setuptools'."
             "\n\n(Currently using %r)"
-            ) % (version, e.args[0])
+            ) % (version, e.args[0]), file=sys.stderr)
             sys.exit(2)
         else:
             del pkg_resources, sys.modules['pkg_resources']    # reload ok
@@ -216,10 +216,10 @@ def main(argv, version=DEFAULT_VERSION):
                 os.unlink(egg)
     else:
         if setuptools.__version__ == '0.0.1':
-            print >>sys.stderr, (
+            print((
             "You have an obsolete version of setuptools installed.  Please\n"
             "remove it from your system entirely before rerunning this script."
-            )
+            ), file=sys.stderr)
             sys.exit(2)
 
     req = "setuptools>="+version
@@ -238,8 +238,8 @@ def main(argv, version=DEFAULT_VERSION):
             from setuptools.command.easy_install import main
             main(argv)
         else:
-            print "Setuptools version",version,"or greater has been installed."
-            print '(Run "ez_setup.py -U setuptools" to reinstall or upgrade.)'
+            print("Setuptools version",version,"or greater has been installed.")
+            print('(Run "ez_setup.py -U setuptools" to reinstall or upgrade.)')
 
 def update_md5(filenames):
     """Update our built-in md5 registry"""
@@ -252,7 +252,7 @@ def update_md5(filenames):
         md5_data[base] = md5(f.read()).hexdigest()
         f.close()
 
-    data = ["    %r: %r,\n" % it for it in md5_data.items()]
+    data = ["    %r: %r,\n" % it for it in md5_data.iteritems()]
     data.sort()
     repl = "".join(data)
 
@@ -262,7 +262,7 @@ def update_md5(filenames):
 
     match = re.search("\nmd5_data = {\n([^}]+)}", src)
     if not match:
-        print >>sys.stderr, "Internal error!"
+        print("Internal error!", file=sys.stderr)
         sys.exit(2)
 
     src = src[:match.start(1)] + repl + src[match.end(1):]

pyfasta/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 import sys
 from fasta import Fasta, complement, DuplicateHeaderException
 from records import *
@@ -23,15 +24,15 @@ def main():
         pyfasta extract --help
     """        
     if len(sys.argv) == 1:
-        print help
+        print(help)
         sys.exit()
 
     action = sys.argv[1]
 
     sglobals = globals()
     if not action in sglobals:
-        print "%s not a valid action" % action
-        print help
+        print("%s not a valid action" % action)
+        print(help)
         sys.exit()
 
     globals()[action](sys.argv[2:])
@@ -74,8 +75,8 @@ def info(args):
         else:
             info.sort()
 
-        print "\n" + fasta
-        print "=" * len(fasta)
+        print("\n" + fasta)
+        print("=" * len(fasta))
         for k, l in info:
             gc = ""
             if options.gc:
@@ -84,12 +85,12 @@ def info(args):
                 c = seq.count('C')
                 gc = 100.0 * (g + c) / float(l)
                 gc = "gc:%.2f%%" % gc
-            print (">%s length:%i " % (k, l)) + gc
+            print((">%s length:%i " % (k, l)) + gc)
 
         if total_len > 1000000:
             total_len = "%.3fM" % (total_len / 1000000.)
-        print
-        print "%s basepairs in %i sequences" % (total_len, nseqs)
+        print()
+        print("%s basepairs in %i sequences" % (total_len, nseqs))
 
 def flatten(args):
     """
@@ -132,8 +133,8 @@ def extract(args):
     for seqname in seqs:
         seq = f[seqname]
         if options.header:
-            print ">%s" % seqname
-        print seq
+            print(">%s" % seqname)
+        print(seq)
 
 
 if __name__ == "__main__":

pyfasta/fasta.py

@@ -29,7 +29,7 @@ def __init__(self, fasta_name, record_class=NpyFastaRecord,
         """
             >>> from pyfasta import Fasta, FastaRecord
 
-            >>> f = Fasta('tests/data/three_chrs.fasta', 
+            >>> f = Fasta('tests/data/three_chrs.fasta',
             ...                          record_class=FastaRecord)
             >>> sorted(f.keys())
             ['chr1', 'chr2', 'chr3']
@@ -73,7 +73,7 @@ def gen_seqs_with_headers(self, key_fn=None):
         fh = open(self.fasta_name, 'r')
         # do the flattening (remove newlines)
         # check of unique-ness of headers.
-        seen_headers = {}
+        seen_headers = set()
         header = None
         seqs = None
         for line in fh:
@@ -83,7 +83,7 @@ def gen_seqs_with_headers(self, key_fn=None):
                 if seqs is not None:
                     if header in seen_headers:
                         raise DuplicateHeaderException(header)
-                    seen_headers[header] = None
+                    seen_headers.add(header)
                     yield header, "".join(seqs)
 
                 header = line[1:].strip()
@@ -93,7 +93,7 @@ def gen_seqs_with_headers(self, key_fn=None):
             else:
                 seqs.append(line)
 
-        if seqs != []:
+        if seqs:
             if header in seen_headers:
                 raise DuplicateHeaderException(header)
             yield header, "".join(seqs)
@@ -156,7 +156,7 @@ def sequence(self, f, asstring=True, auto_rc=True
             >>> f['chr3'][:][-10:]
             'CGCACGCTAC'
 
-        
+
         a feature can have exons:
             >>> feat = dict(start=9, stop=19, strand=1, chr='chr1'
             ...    , exons=[(9,11), (13, 15), (17, 19)])
@@ -189,7 +189,7 @@ def sequence(self, f, asstring=True, auto_rc=True
             sequence = self._seq_from_keys(f, fasta, exon_keys, one_based=one_based)
 
         if sequence is None:
-            start = f['start'] - int(one_based) 
+            start = f['start'] - int(one_based)
             sequence = fasta[start: f['stop']]
 
         if auto_rc and f.get('strand') in (-1, '-1', '-'):

pyfasta/records.py

@@ -85,9 +85,8 @@ def copy_inplace(klass, flat_name, fasta_name):
         os.rename(flat_name, fasta_name)
         # still need the flattend file to show
         # it's current.
-        flatfh = open(fasta_name + klass.ext, 'w')
-        flatfh.write(MAGIC)
-        flatfh.close()
+        with open(fasta_name + klass.ext, 'w') as flatfh:
+            flatfh.write(MAGIC)
 
 
 

pyfasta/split_fasta.py

@@ -1,3 +1,4 @@
+from __future__ import print_function
 from pyfasta import Fasta
 import operator
 import collections
@@ -47,8 +48,8 @@ def newnames(oldname, n, kmers=None, overlap=None, header=None):
     else:
         width = len(str(n))
         names = [pattern % str(i).rjust(width, '0') for i in range(n)]
-    print >>sys.stderr, "creating new files:"
-    print >>sys.stderr, "\n".join(names)
+    print("creating new files:", file=sys.stderr)
+    print("\n".join(names), file=sys.stderr)
     return names
 
 
@@ -57,8 +58,8 @@ def print_to_fh(fh, fasta, lens, seqinfo):
     lens[fh.name] += seqlen
     f = fasta
     assert len(str(f[key])) == seqlen, (key, seqlen, len(str(f[key])))
-    print >>fh, ">%s" % key
-    print >>fh, str(f[key])
+    print(">%s" % key, file=fh)
+    print(str(f[key]), file=fh)
 
 
 def format_kmer(seqid, start):
@@ -132,8 +133,8 @@ def with_header_names(f, names):
     """
     for seqid, name in names.iteritems():
         with open(name, 'w') as fh:
-            print >>fh, ">%s" % seqid
-            print >>fh, str(f[seqid])
+            print(">%s" % seqid, file=fh)
+            print(str(f[seqid]), file=fh)
 
 def with_kmers(f, names, k, overlap):
     """
@@ -148,8 +149,8 @@ def with_kmers(f, names, k, overlap):
         for (start0, subseq) in Fasta.as_kmers(seq, k, overlap=overlap):
 
             fh = fhs[i % len(fhs)]
-            print >>fh, ">%s" % format_kmer(seqid, start0)
-            print >>fh, subseq
+            print(">%s" % format_kmer(seqid, start0), file=fh)
+            print(subseq, file=fh)
             i += 1
     for fh in fhs:
         fh.close()

tests/bench.py

@@ -1,3 +1,5 @@
+from __future__ import print_function
+from itertools import islice
 import sys
 import os
 sys.path.insert(0, os.path.abspath("."))
@@ -14,15 +16,15 @@ def make_long_fasta(filename="t.fasta", nrecs=2500, seqlen=SEQLEN):
         #0123456789"
     s = "ACTGACTGAC"
     for i in range(nrecs):
-        print >>fh, ">header%i" % i
-        print >>fh, (s * (seqlen/10))
+        print(">header%i" % i, file=fh)
+        print(s * (seqlen/10), file=fh)
 
     fh.close()
     return filename
 
 def read(f, nreads=40000, seqlen=SEQLEN):
 
-    for k in f.keys()[:10]:
+    for k in islice(f.iterkeys(), 10):
         for i in range(nreads):
             start = random.randint(0, seqlen)
             end = min(seqlen, start + random.randint(1000, 2000))
@@ -35,12 +37,12 @@ def main():
 
     t = time.time()
     f = Fasta(fa)
-    print "flatten:", time.time() - t 
+    print("flatten:", time.time() - t)
 
 
     t = time.time()
     read(f)
-    print "read:", time.time() - t 
+    print("read:", time.time() - t)
 
 
 

tests/test_all.py

@@ -97,7 +97,7 @@ def check_reload(klass, fasta_name):
 
 
 def check_full_slice(f):
-    for k in f.keys():
+    for k in f.iterkeys():
         assert str(f[k]) == f[k][:]
         assert str(f[k]) == f[k][0:]