Python 3 fixes

py/docex.py

@@ -38,13 +38,13 @@
     writing "1+1==2 ==> True" and having it work in versions of Python
     where True prints as "1" rather than as "True", and so on,
     but doctest has the edge if you want to compare against something
-    that doesn't have an eval-able output, or if you want to test 
+    that doesn't have an eval-able output, or if you want to test
     printed output.
 
 (4) Doctest has many more features, and is better supported.
     I wrote docex before doctest was an official part of Python, but
     with the refactoring of doctest in Python 2.4, I decided to switch
-    my code over to doctest, even though I prefer the brevity of docex. 
+    my code over to doctest, even though I prefer the brevity of docex.
     I still offer docex for those who want it.
 
 From Python, when you want to test modules m1, m2, ... do:
@@ -70,8 +70,9 @@
             First y is evaled to yield an exception type, then x is execed.
             If x doesn't raise the right exception, an error msg is printed.
     (5) Of the form 'statement'. Statement is execed for side effect.
-    (6) Of the form 'expression'. Expression is evaled for side effect. 
+    (6) Of the form 'expression'. Expression is evaled for side effect.
 """
+from __future__ import print_function
 
 import re, sys, types
 
@@ -96,9 +97,9 @@ def __init__(self, modules=None, html=0, out=None,
             if out:
                 sys.stdout = sys.__stdout__
                 out.close()
-                
+
     def __repr__(self):
-	if self.failed:
+        if self.failed:
             return ('<Test: #### failed %d, passed %d>'
                     % (self.failed, self.passed))
         else:
@@ -141,8 +142,8 @@ def run_docstring(self, object, search=re.compile(r'(?m)^\s*Ex: ').search):
                 match = search(s)
                 if match: self.run_string(s[match.end():])
         if hasattr(object, '_docex'):
-                self.run_string(object._docex)
-        
+            self.run_string(object._docex)
+
     def run_string(self, teststr):
         """Run a test string, printing inputs and results."""
         if not teststr: return
@@ -163,7 +164,7 @@ def run_string(self, teststr):
             try:
                 self.evaluate(teststr)
             except SyntaxError:
-                exec teststr in self.dictionary
+                exec(teststr, self.dictionary)
 
     def evaluate(self, teststr, resultstr=None):
         "Eval teststr and check if resultstr (if given) evals to the same."
@@ -172,26 +173,26 @@ def evaluate(self, teststr, resultstr=None):
         self.dictionary['_'] = result
         self.writeln(repr(result))
         if resultstr == None:
-          return
+            return
         elif result == eval(resultstr, self.dictionary):
-          self.passed += 1
+            self.passed += 1
         else:
-          self.fail(teststr, resultstr)
-    
+            self.fail(teststr, resultstr)
+
     def raises(self, teststr, exceptionstr):
         teststr = teststr.strip()
         self.writeln('>>> ' + teststr)
         except_class = eval(exceptionstr, self.dictionary)
         try:
-            exec teststr in self.dictionary
+            exec(teststr, self.dictionary)
         except except_class:
             self.writeln('# raises %s as expected' % exceptionstr)
             self.passed += 1
             return
         self.fail(teststr, exceptionstr)
 
     def fail(self, teststr, resultstr):
-        self.writeln('###### ERROR, TEST FAILED: expected %s for %s' 
+        self.writeln('###### ERROR, TEST FAILED: expected %s for %s'
                      % (resultstr, teststr),
                      '<font color=red><b>', '</b></font>')
         self.failed += 1
@@ -201,9 +202,9 @@ def writeln(self, s, before='', after=''):
         s = str(s)
         if self.html:
             s = s.replace('&','&amp;').replace('<','&lt;').replace('>','&gt;')
-            print '%s%s%s' % (before, s, after)
+            print('%s%s%s' % (before, s, after))
         else:
-            print s
+            print(s)
 
     def seen(self, object):
         """Return true if this object has been seen before.
@@ -213,7 +214,7 @@ def seen(self, object):
         return result
 
 def main(args):
-    """Run Docex.  args should be a list of python filenames.  
+    """Run Docex.  args should be a list of python filenames.
     If the first arg is a non-python filename, it is taken as the
     name of a log file to which output is written.  If it ends in
     ".htm" or ".html", then the output is written as html.  If the
@@ -230,9 +231,7 @@ def main(args):
         for file in glob.glob(arg):
             if file.endswith('.py'):
                 modules.append(__import__(file[:-3]))
-    print Docex(modules, html=html, out=out)
+    print(Docex(modules, html=html, out=out))
 
 if __name__ == '__main__':
     main(sys.argv[1:])
-
-

py/ibol.py

@@ -1,10 +1,11 @@
+from __future__ import print_function
 from collections import defaultdict
 
 def get_genomes(fname="byronbayseqs.fas.txt"):
     "Return a list of genomes, and a list of their corresponding names."
     import re
     names, species, genomes = [], [], []
-    for name, g in re.findall('>(.*?)\r([^\r]*)\r*', file(fname).read()):
+    for name, g in re.findall('>(.*?)\r([^\r]*)\r*', open(fname).read()):
         names.append(name)
         species.append(name.split('|')[-1])
         genomes.append(g)
@@ -14,7 +15,7 @@ def get_neighbors(fname="editdistances.txt"):
     "Return dict: neighbors[i][j] = neighbors[j][i] = d means i,j are d apart."
     ## Read the data pre-computed from the Java program
     neighbors = dict((i, {}) for i in range(n))
-    for line in file(fname):
+    for line in open(fname):
         i,j,d = map(int, line.split())
         neighbors[i][j] = neighbors[j][i] = d
     return neighbors
@@ -75,15 +76,15 @@ def showh(d):
     return ' '.join('%s:%s' % i for i in sorted(d.items()))
 
 def greport(genomes):
-    print "Number of genomes: %d (%d distinct)" % (len(genomes), len(set(genomes)))
+    print("Number of genomes: %d (%d distinct)" % (len(genomes), len(set(genomes))))
     G = dict((g, set()) for g in genomes)
     for i in range(n):
         G[genomes[i]].add(species[i])
-    print "Multi-named genomes:", (
-        len([s for s in G.values() if len(s) > 1]))
+    print("Multi-named genomes:", (
+        len([s for s in G.values() if len(s) > 1])))
     lens = map(len, genomes)
-    print "Genome lengths: min=%d, max=%d" % (min(lens), max(lens))
-    print "Character counts: ", showh(c for g in genomes for c in g)
+    print("Genome lengths: min=%d, max=%d" % (min(lens), max(lens)))
+    print("Character counts: ", showh(c for g in genomes for c in g))
 
 def nreport(neighbors):
     NN, NumN = defaultdict(int), defaultdict(int) ## Nearest, Number of neighbors
@@ -92,9 +93,9 @@ def nreport(neighbors):
         NN[nn] += 1
         for d2 in neighbors[n].values():
             NumN[d2] += 1 
-    print
-    print "Nearest neighbor counts:", showh(NN)
-    print "Number of neighbors at each distance:", showh(NumN)
+    print()
+    print("Nearest neighbor counts:", showh(NN))
+    print("Number of neighbors at each distance:", showh(NumN))
 
 def nspecies(c): return len(set(species[g] for g in c))
 
@@ -104,34 +105,34 @@ def showc(c):
 
 def creport(drange, dcrange):
     def table(what, fn):
-        print "\n" + what
-        print ' '*8, ' '.join([' '+pct(dc, glen) for dc in dcrange])
+        print("\n" + what)
+        print(' '*8, ' '.join([' '+pct(dc, glen) for dc in dcrange]))
         for d in drange:
-            print '%s (%2d)' % (pct(d, glen), d),
+            print('%s (%2d)' % (pct(d, glen), d), end=' ')
             for dc in dcrange:
-                print '%5s' % fn(cluster(neighbors, d, dc)),
-            print
-    print '\nNearest neighbor must be closer than this percentage (places). '
-    print 'Each column: all genomes in cluster within this percentage of each other.'
+                print('%5s' % fn(cluster(neighbors, d, dc)), end=' ')
+            print()
+    print('\nNearest neighbor must be closer than this percentage (places). ')
+    print('Each column: all genomes in cluster within this percentage of each other.')
     table("Number of clusters", len)
     cluster1 = cluster(neighbors, 8, 15) ## splits Cleora
-    print '\nNumber of clusters of different sizes:', showh(len(c) for c in cluster1)
+    print('\nNumber of clusters of different sizes:', showh(len(c) for c in cluster1))
     M, T = defaultdict(int), defaultdict(int)
     for c in cluster1:
         M[margin(c)] += 1; T[margin(c)] += len(c)
-    for x in M: print '%d\t%d\t%d'% (x,M[x],T[x])
-    print '\nMargins', showh(M)
+    for x in M: print('%d\t%d\t%d'% (x,M[x],T[x]))
+    print('\nMargins', showh(M))
     for c in cluster1:
         if margin(c) <= 16:
-            print showc(c)
-    print '\nScatter plot of cluster diameter vs. margin.'
+            print(showc(c))
+    print('\nScatter plot of cluster diameter vs. margin.')
     for c in cluster1:
         if diameter(c) > 0:
             pass
             #print '%d\t%d' % (diameter(c), margin(c))
-    print '\nDifference from cluster(neighbors, 11, 14):'
+    print('\nDifference from cluster(neighbors, 11, 14):')
     #table(lambda cl: pct(len(cluster1)-compare(cluster1, cl),max(len(cluster1),len(cl))))
-    print '\nNumber of clusters witth more than one species name:'
+    print('\nNumber of clusters witth more than one species name:')
     #table(lambda cl: sum(nspecies(c) > 1 for c in cl))
     def pct_near_another(clusters, P=1.25):
         total = 0
@@ -143,21 +144,21 @@ def pct_near_another(clusters, P=1.25):
                         total += 1
         return pct(total, n)
     def f(P):
-        print '\nPercent of individuals within %.2f*diameter of another cluster.'%P
+        print('\nPercent of individuals within %.2f*diameter of another cluster.'%P)
         table(lambda cl: pct_near_another(cl, P))
     #map(f, [1.2, 1.33, 1.5])
 
 def sreport(species):
     SS = defaultdict(int)
-    print
+    print()
     for s in set(species):
         c = [g for g in range(n) if species[g] == s]
         d = diameter(c)
         if d > 14:
             if d==glen: d = '>25'
-            print 'diameter %s for %s (%d elements)' % (d, s, len(c))
+            print('diameter %s for %s (%d elements)' % (d, s, len(c)))
         SS[d] += 1
-    print 'Diameters of %d labeled clusters: %s' % (len(set(species)), showh(SS))
+    print('Diameters of %d labeled clusters: %s' % (len(set(species)), showh(SS)))
 
 def compare(cl1, cl2):
     "Compare two lists of clusters"
@@ -174,7 +175,7 @@ def unit_tests():
     assert diameter(set()) == 0
     assert diameter([17, 42]) == dist(17, 42)
     assert pct(1, 2) == '50.0%'
-    print '\nAll tests pass.\n'
+    print('\nAll tests pass.\n')
 
 
 

py/lettercount.py

@@ -23,6 +23,7 @@
 """
 
 from __future__ import division
+from __future__ import print_function
 from collections import Counter, defaultdict
 
 #### Read files in Books-Ngram format; convert to a dict
@@ -31,7 +32,7 @@ def read_year_file(filename, dic=None):
     """Read a file of 'word year word_count book_count' lines and convert to a dict
     {WORD: totalcount}. Uppercase all words, and only include all-alphabetic words."""
     if dic is None: dic = {}
-    for line in file(filename):
+    for line in open(filename):
         word, year, c1, c2 = line.split('\t')
         if '_' in word:
             word = word[:word.index('_')]
@@ -44,14 +45,14 @@ def read_year_file(filename, dic=None):
 
 def write_dict(dic, filename):
     "Write a {word:count} dict as 'word \t count' lines in filename."
-    out = file(filename, 'w')
+    out = open(filename, 'w')
     for key in sorted(dic):
         out.write('%s\t%s\n' % (key, dic[key]))
     return out.close()
 
 def read_dict(filename, sep='\t'):
     "Read 'word \t count' lines from file and make them into a dict of {word:count}."
-    pairs = (line.split(sep) for line in file(filename))
+    pairs = (line.split(sep) for line in open(filename))
     return {word: int(count) for (word, count) in pairs}
 
 #### Convert a bunch of year files into dict file format.
@@ -61,9 +62,9 @@ def report(filename, D, adj):
         import time
         N = len(D)
         W = sum(v for v in D.itervalues())
-        print '%s: %s %s words (%s tokens) at %s' % (
+        print('%s: %s %s words (%s tokens) at %s' % (
             filename, adj, format(W, ',d'), format(N, ',d'),
-            time.strftime("%H:%M:%S", time.gmtime()))
+            time.strftime("%H:%M:%S", time.gmtime())))
     for f in filenames:
         report(f, {}, 'starting')
         D = read_year_file(f)
@@ -155,10 +156,10 @@ def getcount(counts, s, pos, length):
         return counts[s, pos, length]
 
 
-print 'start'
+print('start')
 #wc = word_counts('count_100K.txt')
 #counts = letter_counts(wc)
-print 'end'
+print('end')
 
 
 
@@ -172,18 +173,18 @@ def num(ch):
 
 def stats(D, NS = (1, 2, 3, 4, 5, 6)):
     counts = {n: Counter() for n in NS}
-    print 'words ' + ' '.join('   %d-grams  ' % n for n in NS)
+    print('words ' + ' '.join('   %d-grams  ' % n for n in NS))
     for (i, word) in enumerate(sortedby(D), 1):
         for n in NS:
             for ng in ngrams(word, n):
                 counts[n][ng] += 1
         if i % 5000 == 0 or i == len(D):
-            print "%4dK" % (i/1000),
+            print("%4dK" % (i/1000), end=' ')
             for n in NS:
                 c = len(counts[n])
                 field = "%5d (%d%%)" % (c, int(round(c*100/(26**n))))
-                print '%12s' % field,
-            print
+                print('%12s' % field, end=' ')
+            print()
 
 letters = 'ETAOINSRHLDCUMFPGWYBVKXJQZ'
 alphabet = ''.join(sorted(letters))
@@ -224,7 +225,7 @@ def substr(word, pos, length):
 def lettercount(D, pos):
     LC = histogram((substr(w, pos, 1), D[w]) for w in D)
     del LC[None]
-    print LC
+    print(LC)
     pos_name = (str(pos)+'+' if isinstance(pos, tuple) else
                 pos if pos < 0 else
                 pos+1)
@@ -293,7 +294,7 @@ def csvline(first, rest):
     return '\t'.join([first] + map(str, rest))
 
 def makecsv(n, D=D):
-    out = file('ngrams%d.csv' % n, 'w')
+    out = open('ngrams%d.csv' % n, 'w')
     cols = columns(n)
     Dng = defaultdict(lambda: defaultdict(int))
     for w in D:
@@ -310,9 +311,9 @@ def makecsv(n, D=D):
             if from_end <= 9:
                 entry[ANY, -from_end, -from_end+n-1] += N
         # enumerate ngrams from word and increment counts for each one
-    print >> out, csvline('%d-gram' % n,  map(colname, cols))
+    print(csvline('%d-gram' % n,  map(colname, cols)), file=out)
     for ng in sorted(Dng, key=lambda ng: -Dng[ng][(ANY, ANY)]):
-        print >> out, csvline(ng, [Dng[ng].get(col, 0) for col in cols])
+        print(csvline(ng, [Dng[ng].get(col, 0) for col in cols]), file=out)
     out.close()
     return Dng
 

py/lis.py

@@ -6,6 +6,11 @@
 import math
 import operator as op
 
+try:
+    raw_input          # Python 2
+except NameError:
+    raw_input = input  # Python 3
+
 ################ Types
 
 Symbol = str          # A Lisp Symbol is implemented as a Python str
@@ -96,7 +101,7 @@ def repl(prompt='lis.py> '):
     "A prompt-read-eval-print loop."
     while True:
         val = eval(parse(raw_input(prompt)))
-        if val is not None: 
+        if val is not None:
             print(lispstr(val))
 
 def lispstr(exp):