Refactor project structure, move sources under src/, tests under tests/

and other commands under bin/.

count-bits

@@ -1,25 +0,0 @@
-#!/usr/local/pypy-1.6/bin/pypy
-
-import sys
-
-total_bits = 0
-bits_set = 0
-
-while True:
-	block = sys.stdin.read(2**19)
-	if not block:
-		break
-	total_bits += len(block) * 8
-	#print('got block of length %d' % len(block))
-	for char in block:
-		byte = ord(char)
-		#print('got char %d' % byte)
-		for exponent in range(8):
-			bitmask = 2**exponent
-			#print('checking mask %d' % bitmask)
-			if byte & bitmask != 0:
-				#print('adding 1 to count')
-				bits_set += 1
-
-print('%s set, %s present, %6.2f%%' % (bits_set, total_bits, bits_set * 100.0 / total_bits))
-

gen-performance-graph

@@ -1,107 +0,0 @@
-#!/usr/bin/python
-
-import sys
-import anydbm
-from pychart import *
-
-def get_timing(kind):
-    database = anydbm.open('performance-numbers', 'r')
-    list_ = []
-    for key in database.keys():
-        fields = key.split()
-        #print fields[0], kind
-        if fields[0] == kind:
-            set_size = float(fields[1])
-            duration = float(database[key])
-            list_.append( ( set_size, duration ) )
-    database.close()
-    list_.sort()
-    return list_
-
-#def get_timing(filename):
-#    file_ = open(filename, 'r')
-#    list_ = []
-#    for line in file_:
-#        fields = line.split()
-#        set_size = float(fields[0])
-#        duration = float(fields[1])
-#        list_.append( ( set_size, duration ) )
-#    file_.close()
-#    return list_
-
-def get_hybrid_timing():
-    return get_timing('hybrid')
-
-def get_array_timing():
-    return get_timing('array')
-
-def get_seek_timing():
-    return get_timing('seek')
-
-def get_mmap_timing():
-    return get_timing('mmap')
-
-def desired_y_max(*list_):
-    maximum = 0.0
-    for element in list_:
-        for set_size, duration in element:
-            maximum = max(duration, maximum)
-    return maximum
-
-def main():
-    theme.get_options()
-    theme.output_format = 'pdf'
-    theme.use_color = 1
-    theme.output_file = 'performance-graph.pdf'
-    theme.default_font_size = 15
-    theme.reinitialize()
-
-    width = 800
-    height = width * 4 // 5
-    size = (width, height)
-
-    hybrid_timing_data = get_hybrid_timing()
-    print 'hybrid', hybrid_timing_data
-    array_timing_data = get_array_timing()
-    print 'array', array_timing_data
-    seek_timing_data = get_seek_timing()
-    print 'seek', seek_timing_data
-    mmap_timing_data = get_mmap_timing()
-    print 'mmap', mmap_timing_data
-
-    y_max = desired_y_max(array_timing_data, seek_timing_data, hybrid_timing_data, mmap_timing_data)
-
-    can = canvas.default_canvas()
-
-    ar = area.T(
-        size = size,
-        legend=legend.T(),
-        x_range = (1, None),
-        y_range = (0.0001, y_max + 100),
-        #x_coord = log_coord.T(),
-        #y_coord = log_coord.T(),
-        x_coord = linear_coord.T(),
-        y_coord = linear_coord.T(),
-        x_axis = axis.X(format="%g", label="Number of elements in set"),
-        y_axis = axis.Y(format="%g", label="Seconds"),
-        )
-
-    lp = line_plot.T(data=array_timing_data, label="Array")
-    ar.add_plot(lp)
-                    
-    lp = line_plot.T(data=seek_timing_data, label="Seek")
-    ar.add_plot(lp)
-                    
-    lp = line_plot.T(data=hybrid_timing_data, label="Hybrid")
-    ar.add_plot(lp)
-                    
-    lp = line_plot.T(data=mmap_timing_data, label="mmap")
-    ar.add_plot(lp)
-                    
-    ar.draw()
-
-    #can.show(ar.x_pos(4), ar.y_pos(970), "/a50{}seek")
-
-main()
-
-

setup.py

@@ -1,16 +1,40 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+from __future__ import absolute_import
+from __future__ import print_function
+
+import io
+import re
+from glob import glob
+from os.path import basename
+from os.path import dirname
+from os.path import join
+from os.path import splitext
+
+from setuptools import find_packages
+from setuptools import setup
+
+
+def read(*names, **kwargs):
+    return io.open(
+        join(dirname(__file__), *names),
+        encoding=kwargs.get('encoding', 'utf8')
+    ).read()
+
 
-from setuptools import setup, find_packages
 setup(
-    name = "drs-bloom-filter",
-    version = "1.01",
-    packages = find_packages(),
-    scripts = ['drs_bloom_filter.py', 'python2x3.py' ],
+    name="drs-bloom-filter",
+    version="1.01",
+    packages=find_packages('src'),
+    package_dir={'': 'src'},
+    py_modules=[splitext(basename(path))[0] for path in glob('src/*.py')],
+    # scripts=['drs_bloom_filter.py', 'python2x3.py'],
 
     # metadata for upload to PyPI
-    author = "Daniel Richard Stromberg",
-    author_email = "strombrg@gmail.com",
+    author="Daniel Richard Stromberg",
+    author_email="strombrg@gmail.com",
     description='Pure Python Bloom Filter module',
-    long_description='''
+    long_description="""
 A pure python bloom filter (low storage requirement, probabilistic
 set datastructure) is provided.  It is known to work on CPython 2.x,
 CPython 3.x, Pypy and Jython.
@@ -20,16 +44,15 @@ Includes mmap, in-memory and disk-seek backends.
 The user specifies the desired maximum number of elements and the
 desired maximum false positive probability, and the module
 calculates the rest.
-''',
-    license = "MIT",
-    keywords = "probabilistic set datastructure",
-	 url='http://stromberg.dnsalias.org/~strombrg/drs-bloom-filter/',
-	 platforms='Cross platform',
-	 classifiers=[
-		 "Development Status :: 5 - Production/Stable",
-		 "Intended Audience :: Developers",
-		 "Programming Language :: Python :: 2",
-		 "Programming Language :: Python :: 3",
-		 ],
+""",
+    license="MIT",
+    keywords="probabilistic set datastructure",
+    url='http://stromberg.dnsalias.org/~strombrg/drs-bloom-filter/',
+    platforms='Cross platform',
+    classifiers=[
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Developers",
+        "Programming Language :: Python :: 2",
+        "Programming Language :: Python :: 3",
+    ],
 )
-