update from Atlas with major reorg

03-dict-set/support/container_perftest.py

@@ -0,0 +1,55 @@
+"""
+Container ``in`` operator performance test
+"""
+import sys
+import timeit
+
+SETUP = '''
+import array
+selected = array.array('d')
+with open('selected.arr', 'rb') as fp:
+    selected.fromfile(fp, {size})
+if {container_type} is dict:
+    haystack = dict.fromkeys(selected, 1)
+else:
+    haystack = {container_type}(selected)
+if {verbose}:
+    print(type(haystack), end='  ')
+    print('haystack: %10d' % len(haystack), end='  ')
+needles = array.array('d')
+with open('not_selected.arr', 'rb') as fp:
+    needles.fromfile(fp, 500)
+needles.extend(selected[::{size}//500])
+if {verbose}:
+    print(' needles: %10d' % len(needles), end='  ')
+'''
+
+TEST = '''
+found = 0
+for n in needles:
+    if n in haystack:
+        found += 1
+if {verbose}:
+    print('  found: %10d' % found)
+'''
+
+def test(container_type, verbose):
+    MAX_EXPONENT = 7
+    for n in range(3, MAX_EXPONENT + 1):
+        size = 10**n
+        setup = SETUP.format(container_type=container_type,
+                             size=size, verbose=verbose)
+        test = TEST.format(verbose=verbose)
+        tt = timeit.repeat(stmt=test, setup=setup, repeat=5, number=1)
+        print('|{:{}d}|{:f}'.format(size, MAX_EXPONENT + 1, min(tt)))
+
+if __name__=='__main__':
+    if '-v' in sys.argv:
+        sys.argv.remove('-v')
+        verbose = True
+    else:
+        verbose = False
+    if len(sys.argv) != 2:
+        print('Usage: %s <container_type>' % sys.argv[0])
+    else:
+        test(sys.argv[1], verbose)

03-dict-set/support/container_perftest_datagen.py

@@ -0,0 +1,37 @@
+"""
+Generate data for container performance test
+"""
+
+import random
+import array
+
+MAX_EXPONENT = 7
+HAYSTACK_LEN = 10 ** MAX_EXPONENT
+NEEDLES_LEN = 10 ** (MAX_EXPONENT - 1)
+SAMPLE_LEN = HAYSTACK_LEN + NEEDLES_LEN // 2
+
+needles = array.array('d')
+
+sample = {1/random.random() for i in range(SAMPLE_LEN)}
+print('initial sample: %d elements' % len(sample))
+
+# complete sample, in case duplicate random numbers were discarded
+while len(sample) < SAMPLE_LEN:
+    sample.add(1/random.random())
+
+print('complete sample: %d elements' % len(sample))
+
+sample = array.array('d', sample)
+random.shuffle(sample)
+
+not_selected = sample[:NEEDLES_LEN // 2]
+print('not selected: %d samples' % len(not_selected))
+print('  writing not_selected.arr')
+with open('not_selected.arr', 'wb') as fp:
+    not_selected.tofile(fp)
+
+selected = sample[NEEDLES_LEN // 2:]
+print('selected: %d samples' % len(selected))
+print('  writing selected.arr')
+with open('selected.arr', 'wb') as fp:
+    selected.tofile(fp)

03-dict-set/support/hashdiff.py

@@ -0,0 +1,20 @@
+import sys
+
+MAX_BITS = len(format(sys.maxsize, 'b'))
+print('%s-bit Python build' % (MAX_BITS + 1))
+
+def hash_diff(o1, o2):
+    h1 = '{:>0{}b}'.format(hash(o1), MAX_BITS)
+    h2 = '{:>0{}b}'.format(hash(o2), MAX_BITS)
+    diff = ''.join('!' if b1 != b2 else ' ' for b1, b2 in zip(h1, h2))
+    count = '!= {}'.format(diff.count('!'))
+    width = max(len(repr(o1)), len(repr(o2)), 8)
+    sep = '-' * (width * 2 + MAX_BITS)
+    return '{!r:{width}} {}\n{:{width}} {} {}\n{!r:{width}} {}\n{}'.format(
+    		o1, h1, ' ' * width, diff, count, o2, h2, sep, width=width)
+
+if __name__ == '__main__':
+    print(hash_diff(1, 1.0))
+    print(hash_diff(1.0, 1.0001))
+    print(hash_diff(1.0001, 1.0002))
+    print(hash_diff(1.0002, 1.0003))