shaved off a couple of lines of code

Author: xrotwang

src/nexus/checker.py

@@ -1,17 +1,15 @@
+import string
 import statistics
+import collections
 
-from collections import Counter
-from string import ascii_lowercase, ascii_uppercase, digits
-
-SAFE_CHARACTERS = ascii_uppercase + ascii_lowercase + digits + '-_'
+SAFE_CHARACTERS = string.ascii_letters + string.digits + '-_'
 
 
 class Checker(object):
 
     EMPTY_STATES = ('?', '-', '0')
 
-    def __init__(self, nex, verbose=False):
-        self.verbose = verbose
+    def __init__(self, nex):
         self.errors, self.messages = [], []
         self.check(nex)
 
@@ -38,7 +36,7 @@ class DuplicateLabelChecker(Checker):
     Checks for Duplicate Character Labels
     """
     def check(self, nex):
-        labels = Counter(nex.data.charlabels.values())
+        labels = collections.Counter(nex.data.charlabels.values())
         for label in labels:
             if labels[label] > 1:
                 self.errors.append("Duplicate Label (n=%d): %s" % (labels[label], label))
@@ -82,7 +80,7 @@ class UnusualStateChecker(Checker):
     THRESHOLD = 0.001  # anything less than this is flagged
 
     def check(self, nex):
-        states = Counter()
+        states = collections.Counter()
         for s in nex.data.matrix.values():
             states.update(s)
         total = sum(states.values())
@@ -100,7 +98,7 @@ class EmptyCharacterChecker(Checker):
     MIN_COUNT = 0
 
     def check(self, nex):
-        tally = Counter()
+        tally = collections.Counter()
         for taxon in nex.data.matrix:
             tally.update([
                 i for i, c in enumerate(nex.data.matrix[taxon], 0)
@@ -111,8 +109,7 @@ def check(self, nex):
             n = tally.get(i, 0)
             if n == self.MIN_COUNT:
                 if 'ascert' in nex.data.charlabels.get(i, '').lower():  # ignore
-                    if self.verbose:
-                        self.log("Character %d is an ascertainment character" % i)
+                    self.log("Character %d is an ascertainment character" % i)
                 else:
                     self.errors.append("Character %d has count %d" % (i, self.MIN_COUNT))
         return not self.has_errors
@@ -159,7 +156,7 @@ def check(self, nex):
         # are they empty?
         for a in ascert:
             states = [nex.data.matrix[t][a] for t in nex.data.matrix]
-            states = Counter([s for s in states if s not in self.EMPTY_STATES])
+            states = collections.Counter([s for s in states if s not in self.EMPTY_STATES])
             if len(states):
                 self.errors.append(
                     "Character %d - %s should be an ascertainment character but has data (%r)" % (

src/nexus/commands/check.py

@@ -19,12 +19,6 @@ def register(parser):
         help="add ascertainment checks",
         action='store_true'
     )
-    parser.add_argument(
-        '-v', "--verbose",
-        help="more output",
-        default=True,
-        action='store_true'
-    )
 
 
 def run(args):
@@ -44,4 +38,4 @@ def run(args):
                 print("\t%s" % w)
 
     for checker in checkers:
-        checker(nex, verbose=args.verbose).status()
+        checker(nex).status()

src/nexus/handlers/__init__.py

@@ -57,10 +57,9 @@ def remove_comments(line):
         """
         Removes comments from lines
 
-        >>> g = GenericHandler()
-        >>> g.remove_comments("Hello [world]")
+        >>> GenericHandler.remove_comments("Hello [world]")
         'Hello '
-        >>> g.remove_comments("He[bite]ll[me]o")
+        >>> GenericHandler.remove_comments("He[bite]ll[me]o")
         'Hello'
 
         :param line: string

src/nexus/tools/combine_nexuses.py

@@ -8,13 +8,8 @@ def combine_nexuses(nexuslist):
     Combines a list of NexusReader instances into a single nexus
 
     :param nexuslist: A list of NexusReader instances
-    :type nexuslist: List
 
     :return: A NexusWriter instance
-
-    :raises TypeError: if nexuslist is not a list of NexusReader instances
-    :raises IOError: if unable to read an file in nexuslist
-    :raises NexusFormatException: if a nexus file does not have a `data` block
     """
     out = NexusWriter()
     # check they're all nexus instances and get all block types

src/nexus/tools/multistatise.py

@@ -12,8 +12,7 @@ def multistatise(nexus_obj, charlabel=None):
     :raises AssertionError: if nexus_obj is not a nexus
     :raises NexusFormatException: if nexus_obj does not have a `data` block
     """
-    if not charlabel:
-        charlabel = getattr(nexus_obj, 'short_filename', 1)
+    charlabel = charlabel or getattr(nexus_obj, 'short_filename', 1)
 
     states = {}
     for taxon in nexus_obj.data.matrix:

src/nexus/tools/shufflenexus.py

@@ -16,9 +16,7 @@ def shufflenexus(nexus_obj, resample=False):
     :type resample: Integer
 
     :return: A shuffled NexusReader instance
-    :raises AssertionError: if nexus_obj is not a nexus
     :raises ValueError: if resample is not False or a positive Integer
-    :raises NexusFormatException: if nexus_obj does not have a `data` block
     """
     if resample is False:
         resample = nexus_obj.data.nchar

src/nexus/tools/sites.py

@@ -10,15 +10,7 @@ def iter_constant_sites(nexus_obj):
     Returns a list of zero-based indices of the constant sites in a nexus
     """
     for i in range(0, nexus_obj.data.nchar):
-        states = []
-        for taxa, data in nexus_obj.data:
-            c = data[i]
-            if c in ('?', '-'):
-                continue  # pragma: no cover
-            elif c not in states:
-                states.append(c)
-
-        if len(states) == 1:
+        if len({data[i] for _, data in nexus_obj.data if data[i] not in {'?', '-'}}) == 1:
             yield i
 
 
@@ -61,12 +53,8 @@ def count_site_values(nexus_obj, characters=('-', '?')):
     :raises AssertionError: if nexus_obj is not a nexus
     :raises NexusFormatException: if nexus_obj does not have a `data` block
     """
-    if not isinstance(characters, Iterable):
-        raise TypeError("characters should be iterable")
-
-    tally = {}
+    tally = {taxon: 0 for taxon, _ in nexus_obj.data}
     for taxon, sites in nexus_obj.data:
-        tally[taxon] = tally.get(taxon, 0)
         for site in sites:
             if site in characters:
                 tally[taxon] += 1
@@ -172,8 +160,6 @@ def count_binary_set_size(nexus_obj):
     :type nexus_obj: NexusReader
 
     :return: A Dictionary
-    :raises AssertionError: if nexus_obj is not a nexus
-    :raises NexusFormatException: if nexus_obj does not have a `data` block
 
     e.g. {
         0: 0,

src/nexus/writer.py

@@ -57,7 +57,7 @@ def clean(self, s):
 
     @property
     def characters(self):
-        return self.data.keys()
+        return list(self.data.keys())
 
     @property
     def ntrees(self):
@@ -77,26 +77,23 @@ def symbols(self):
         symbols = [s for s in symbols if s not in ('-', '?')]
         return symbols
 
-    def _make_charlabel_block(self):
+    def _iter_charlabels(self):
         """Generates a character label block"""
-        out = ["CHARSTATELABELS"]
+        yield "CHARSTATELABELS"
         for i, char in enumerate(sorted(self.characters), 1):
-            out.append("\t\t%d %s," % (i, self.clean(str(char))))
-        out[-1] = out[-1].strip(',')  # remove trailing comma
-        out.append(";")
-        return "\n".join(out)
+            yield "\t\t%d %s%s" % (
+                i, self.clean(str(char)), '' if i == len(self.characters) else ',')
+        yield ";"
 
-    def _make_matrix_block(self, interleave):
+    def _iter_matrix(self, interleave):
         """Generates a matrix block"""
         max_taxon_size = max([len(t) for t in self.taxa]) + 3
 
-        out = []
         if interleave:
             for c in sorted(self.characters):
                 for t in self.taxa:
-                    out.append("%s %s" % (
-                        t.ljust(max_taxon_size), self.data[c].get(t, self.MISSING)))
-                out.append("")
+                    yield "%s %s" % (t.ljust(max_taxon_size), self.data[c].get(t, self.MISSING))
+                yield ""
         else:
             for t in sorted(self.taxa):
                 s = []
@@ -105,8 +102,7 @@ def _make_matrix_block(self, interleave):
                     if len(value) > 1:  # wrap equivocal states in ()'s
                         value = "(%s)" % value
                     s.append(value)
-                out.append("%s %s" % (t.ljust(max_taxon_size), ''.join(s)))
-        return "\n".join(out)
+                yield "%s %s" % (t.ljust(max_taxon_size), ''.join(s))
 
     def make_treeblock(self):
         return "\n".join(["    %s" % t.lstrip().strip() for t in self.trees])
@@ -148,9 +144,7 @@ def write(self, interleave=False, charblock=False, **kw):
         (basically a wrapper around make_nexus)
 
         :param interleave: Generate interleaved matrix or not
-        :type interleave: Boolean
         :param charblock: Include a characters block or not
-        :type charblock: Boolean
 
         :return: String
         """
@@ -182,8 +176,8 @@ def make_nexus(self, interleave=False, charblock=False):
             datablock = DATA_TEMPLATE % {
                 'ntax': len(self.taxa),
                 'nchar': len(self.characters),
-                'charblock': self._make_charlabel_block() if charblock else '',
-                'matrix': self._make_matrix_block(interleave=interleave),
+                'charblock': '\n'.join(self._iter_charlabels()) if charblock else '',
+                'matrix': '\n'.join(self._iter_matrix(interleave=interleave)),
                 'interleave': 'INTERLEAVE' if interleave else '',
                 'comments': self._make_comments(),
                 'symbols': ''.join(sorted(self.symbols)),

tests/test_checker.py

@@ -128,7 +128,7 @@ def test_EmptyCharacterChecker_ignore_ascert():
         C              001
         ;
     """)
-    c = EmptyCharacterChecker(nex, verbose=True)
+    c = EmptyCharacterChecker(nex)
     assert len(c.errors) == 1  # and not two!
     assert len(c.messages) == 1