Add Python 3.2-3.4 compatibility and enable distribution as a wheel

.gitignore

@@ -1,3 +1,61 @@
 *~
 .*.swp
-*.pyc
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/

MANIFEST.in

@@ -0,0 +1,4 @@
+include LICENSE.txt
+include tests.txt
+include zxcvbn/generated/frequency_lists.json
+include zxcvbn/generated/adjacency_graphs.json

setup.cfg

@@ -0,0 +1,5 @@
+[bdist_wheel]
+# This flag says that the code is written to work on both Python 2 and Python
+# 3. If at all possible, it is good practice to do this. If you cannot, you
+# will need to generate wheels for each Python version that you support.
+universal=1

setup.py

@@ -1,4 +1,4 @@
-from distutils.core import setup
+from setuptools import setup
 
 setup(name='zxcvbn',
       version='1.0',
@@ -7,5 +7,19 @@
       author_email='[email protected]',
       url='https://www.github.com/rpearl/python-zxcvbn',
       packages=['zxcvbn'],
-      package_data={'zxcvbn': ['generated/frequency_lists.json', 'generated/adjacency_graphs.json']}
+      package_data={
+        'zxcvbn': ['generated/frequency_lists.json',
+                   'generated/adjacency_graphs.json',
+                   ],
+        },
+      classifiers=[
+        'Intended Audience :: Developers',
+        'Programming Language :: Python :: 2',
+        'Programming Language :: Python :: 2.6',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.2',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+        ],
      )

zxcvbn/__init__.py

@@ -1,3 +1,6 @@
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 from zxcvbn import main
 
 __all__ = ['password_strength']
@@ -7,12 +10,18 @@
 
 if __name__ == '__main__':
     import fileinput
-    ignored = ('match_sequence', 'password')
+    # Ensure fields are displayed in a deterministic order
+    display_fields = [
+            'crack_time_display',
+            'crack_time',
+            'score',
+            'entropy',
+            'calc_time',
+            ]
 
     for line in fileinput.input():
         pw = line.strip()
-        print "Password: " + pw
+        print("Password: " + pw)
         out = password_strength(pw)
-        for key, value in out.iteritems():
-            if key not in ignored:
-                print "\t%s: %s" % (key, value)
+        for key in display_fields:
+            print("\t%s: %s" % (key, out[key]))

zxcvbn/main.py

@@ -1,3 +1,6 @@
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import time
 
 from zxcvbn.matching import omnimatch

zxcvbn/matching.py

@@ -1,6 +1,10 @@
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 from itertools import groupby
 import pkg_resources
 import re
+import sys
 
 try:
     import simplejson as json
@@ -29,8 +33,8 @@ def dictionary_match(password, ranked_dict):
 
     pw_lower = password.lower()
 
-    for i in xrange(0, length):
-        for j in xrange(i, length):
+    for i in range(0, length):
+        for j in range(i, length):
             word = pw_lower[i:j+1]
             if word in ranked_dict:
                 rank = ranked_dict[word]
@@ -64,22 +68,24 @@ def _build_ranked_dict(unranked_list):
 
 def _load_frequency_lists():
     data = pkg_resources.resource_string(__name__, 'generated/frequency_lists.json')
+    data = data.decode('utf-8')
     dicts = json.loads(data)
-    for name, wordlist in dicts.items():
+    for name, wordlist in list(dicts.items()):
         DICTIONARY_MATCHERS.append(_build_dict_matcher(name, _build_ranked_dict(wordlist)))
 
 
 def _load_adjacency_graphs():
     global GRAPHS
     data = pkg_resources.resource_string(__name__, 'generated/adjacency_graphs.json')
+    data = data.decode('utf-8')
     GRAPHS = json.loads(data)
 
 
 # on qwerty, 'g' has degree 6, being adjacent to 'ftyhbv'. '\' has degree 1.
 # this calculates the average over all keys.
 def _calc_average_degree(graph):
     average = 0.0
-    for neighbors in graph.values():
+    for neighbors in list(graph.values()):
         average += len([n for n in neighbors if n is not None])
 
     average /= len(graph)
@@ -122,7 +128,7 @@ def relevant_l33t_subtable(password):
     password_chars = set(password)
 
     filtered = {}
-    for letter, subs in L33T_TABLE.items():
+    for letter, subs in list(L33T_TABLE.items()):
         relevent_subs = [sub for sub in subs if sub in password_chars]
         if len(relevent_subs) > 0:
             filtered[letter] = relevent_subs
@@ -142,7 +148,7 @@ def dedup(subs):
                 deduped.append(sub)
         return deduped
 
-    keys = table.keys()
+    keys = list(table.keys())
     while len(keys) > 0:
         first_key = keys[0]
         rest_keys = keys[1:]
@@ -166,7 +172,7 @@ def dedup(subs):
                     next_subs.append(sub_alternative)
         subs = dedup(next_subs)
         keys = rest_keys
-    return map(dict, subs)
+    return [dict(sub) for sub in subs]
 
 
 def l33t_match(password):
@@ -182,13 +188,13 @@ def l33t_match(password):
                 if token.lower() == match['matched_word']:
                     continue
                 match_sub = {}
-                for subbed_chr, char in sub.items():
+                for subbed_chr, char in list(sub.items()):
                     if token.find(subbed_chr) != -1:
                         match_sub[subbed_chr] = char
                 match['l33t'] = True
                 match['token'] = token
                 match['sub'] = match_sub
-                match['sub_display'] = ', '.join([("%s -> %s" % (k, v)) for k, v in match_sub.items()])
+                match['sub_display'] = ', '.join([("%s -> %s" % (k, v)) for k, v in list(match_sub.items())])
                 matches.append(match)
     return matches
 
@@ -198,7 +204,7 @@ def l33t_match(password):
 
 def spatial_match(password):
     matches = []
-    for graph_name, graph in GRAPHS.items():
+    for graph_name, graph in list(GRAPHS.items()):
         matches.extend(spatial_match_helper(password, graph, graph_name))
     return matches
 
@@ -293,7 +299,7 @@ def sequence_match(password):
         seq = None           # either lower, upper, or digits
         seq_name = None
         seq_direction = None # 1 for ascending seq abcd, -1 for dcba
-        for seq_candidate_name, seq_candidate in SEQUENCES.items():
+        for seq_candidate_name, seq_candidate in list(SEQUENCES.items()):
             i_n = seq_candidate.find(password[i])
             j_n = seq_candidate.find(password[j]) if j < len(password) else -1
 

zxcvbn/scoring.py

@@ -1,3 +1,6 @@
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import math
 import re
 
@@ -253,7 +256,7 @@ def spatial_entropy(match):
     if 'shifted_count' in match:
         S = match['shifted_count']
         U = L - S # unshifted count
-        possibilities = sum(binom(S + U, i) for i in xrange(0, min(S, U) + 1))
+        possibilities = sum(binom(S + U, i) for i in range(0, min(S, U) + 1))
         entropy += lg(possibilities)
     return entropy
 
@@ -294,7 +297,7 @@ def extra_l33t_entropy(match):
     if 'l33t' not in match or not match['l33t']:
         return 0
     possibilities = 0
-    for subbed, unsubbed in match['sub'].items():
+    for subbed, unsubbed in list(match['sub'].items()):
         sub_len = len([x for x in match['token'] if x == subbed])
         unsub_len = len([x for x in match['token'] if x == unsubbed])
         possibilities += sum(binom(unsub_len + sub_len, i) for i in range(0, min(unsub_len, sub_len) + 1))
@@ -330,14 +333,14 @@ def display_time(seconds):
     if seconds < minute:
         return 'instant'
     elif seconds < hour:
-        return str(1 + math.ceil(seconds / minute)) + " minutes"
+        return '%s minutes' % (1 + math.ceil(seconds / minute),)
     elif seconds < day:
-        return str(1 + math.ceil(seconds / hour)) + " hours"
+        return '%s hours' % (1 + math.ceil(seconds / hour),)
     elif seconds < month:
-        return str(1 + math.ceil(seconds / day)) + " days"
+        return '%s days' % (1 + math.ceil(seconds / day),)
     elif seconds < year:
-        return str(1 + math.ceil(seconds / month)) + " months"
+        return '%s months' % (1 + math.ceil(seconds / month),)
     elif seconds < century:
-        return str(1 + math.ceil(seconds / year)) + " years"
+        return '%s years' % (1 + math.ceil(seconds / year),)
     else:
         return 'centuries'

zxcvbn/scripts/build_frequency_lists.py

@@ -1,4 +1,6 @@
-from __future__ import with_statement
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 import os
 import time
 import codecs
@@ -8,7 +10,10 @@
 except ImportError:
     import json
 
-import urllib2
+try:
+    import urllib.request as urllib_request
+except ImportError:
+    import urllib2 as urllib_request
 
 SLEEP_TIME = 20 # seconds
 
@@ -24,11 +29,11 @@ def get_ranked_english():
     '''
     URL_TMPL = 'http://en.wiktionary.org/wiki/Wiktionary:Frequency_lists/TV/2006/%s'
     urls = []
-    for i in xrange(10):
+    for i in range(10):
         freq_range = "%d-%d" % (i * 1000 + 1, (i+1) * 1000)
         urls.append(URL_TMPL % freq_range)
 
-    for i in xrange(0,15):
+    for i in range(0,15):
         freq_range = "%d-%d" % (10000 + 2 * i * 1000 + 1, 10000 + (2 * i + 2) * 1000)
         urls.append(URL_TMPL % freq_range)
 
@@ -53,15 +58,15 @@ def wiki_download(url):
 
     tmp_path = DOWNLOAD_TMPL % freq_range
     if os.path.exists(tmp_path):
-        print 'cached.......', url
+        print('cached.......', url)
         with codecs.open(tmp_path, 'r', 'utf8') as f:
             return f.read(), True
     with codecs.open(tmp_path, 'w', 'utf8') as f:
-        print 'downloading...', url
-        req = urllib2.Request(url, headers={
+        print('downloading...', url)
+        req = urllib_request.Request(url, headers={
                 'User-Agent': 'zxcvbn'
                 })
-        response = urllib2.urlopen(req)
+        response = urllib_request.urlopen(req)
         result = response.read().decode('utf8')
         f.write(result)
         return result, False
@@ -173,16 +178,16 @@ def main():
             out[lst_name] = lst
         json.dump(out, f)
 
-    print '\nall done! totals:\n'
-    print 'passwords....', len(passwords)
-    print 'male.........', len(male_names)
-    print 'female.......', len(female_names)
-    print 'surnames.....', len(surnames)
-    print 'english......', len(english)
-    print
+    print('\nall done! totals:\n')
+    print('passwords....', len(passwords))
+    print('male.........', len(male_names))
+    print('female.......', len(female_names))
+    print('surnames.....', len(surnames))
+    print('english......', len(english))
+    print()
 
 if __name__ == '__main__':
     if os.path.basename(os.getcwd()) != 'scripts':
-        print 'run this from the scripts directory'
+        print('run this from the scripts directory')
         exit(1)
     main()

zxcvbn/scripts/build_keyboard_adjacency_graph.py

@@ -1,4 +1,6 @@
-from __future__ import with_statement
+from __future__ import (absolute_import, division,
+                        print_function, unicode_literals)
+
 try:
     import simplejson as json
     json # silence pyflakes
@@ -71,7 +73,7 @@ def build_graph(layout_str, slanted):
             position_table[(x,y)] = token
 
     adjacency_graph = {}
-    for (x,y), chars in position_table.iteritems():
+    for (x,y), chars in position_table.items():
         for char in chars:
             adjacency_graph[char] = []
             for coord in adjacency_func(x, y):