This file is indexed.

/usr/share/doc/python-tables-doc/bench/blosc.py is in python-tables-doc 3.1.1-0ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
from __future__ import print_function
import os
import sys
from time import time
import numpy as np
import tables as tb


niter = 3
dirname = "/scratch2/faltet/blosc-data/"
#expression = "a**2 + b**3 + 2*a*b + 3"
#expression = "a+b"
#expression = "a**2 + 2*a/b + 3"
#expression = "(a+b)**2 - (a**2 + b**2 + 2*a*b) + 1.1"
expression = "3*a-2*b+1.1"
shuffle = True


def create_file(kind, prec, synth):
    prefix_orig = 'cellzome/cellzome-'
    iname = dirname + prefix_orig + 'none-' + prec + '.h5'
    f = tb.open_file(iname, "r")

    if prec == "single":
        type_ = tb.Float32Atom()
    else:
        type_ = tb.Float64Atom()

    if synth:
        prefix = 'synth/synth-'
    else:
        prefix = 'cellzome/cellzome-'

    for clevel in range(10):
        oname = '%s/%s-%s%d-%s.h5' % (dirname, prefix, kind, clevel, prec)
        # print "creating...", iname
        f2 = tb.open_file(oname, "w")

        if kind in ["none", "numpy"]:
            filters = None
        else:
            filters = tb.Filters(
                complib=kind, complevel=clevel, shuffle=shuffle)

        for name in ['maxarea', 'mascotscore']:
            col = f.get_node('/', name)
            r = f2.create_carray('/', name, type_, col.shape, filters=filters)
            if synth:
                r[:] = np.arange(col.nrows, dtype=type_.dtype)
            else:
                r[:] = col[:]
        f2.close()
        if clevel == 0:
            size = 1.5 * float(os.stat(oname)[6])
    f.close()
    return size


def create_synth(kind, prec):

    prefix_orig = 'cellzome/cellzome-'
    iname = dirname + prefix_orig + 'none-' + prec + '.h5'
    f = tb.open_file(iname, "r")

    if prec == "single":
        type_ = tb.Float32Atom()
    else:
        type_ = tb.Float64Atom()

    prefix = 'synth/synth-'
    for clevel in range(10):
        oname = '%s/%s-%s%d-%s.h5' % (dirname, prefix, kind, clevel, prec)
        # print "creating...", iname
        f2 = tb.open_file(oname, "w")

        if kind in ["none", "numpy"]:
            filters = None
        else:
            filters = tb.Filters(
                complib=kind, complevel=clevel, shuffle=shuffle)

        for name in ['maxarea', 'mascotscore']:
            col = f.get_node('/', name)
            r = f2.create_carray('/', name, type_, col.shape, filters=filters)
            if name == 'maxarea':
                r[:] = np.arange(col.nrows, dtype=type_.dtype)
            else:
                r[:] = np.arange(col.nrows, 0, dtype=type_.dtype)

        f2.close()
        if clevel == 0:
            size = 1.5 * float(os.stat(oname)[6])
    f.close()
    return size


def process_file(kind, prec, clevel, synth):

    if kind == "numpy":
        lib = "none"
    else:
        lib = kind
    if synth:
        prefix = 'synth/synth-'
    else:
        prefix = 'cellzome/cellzome-'
    iname = '%s/%s-%s%d-%s.h5' % (dirname, prefix, kind, clevel, prec)
    f = tb.open_file(iname, "r")
    a_ = f.root.maxarea
    b_ = f.root.mascotscore

    oname = '%s/%s-%s%d-%s-r.h5' % (dirname, prefix, kind, clevel, prec)
    f2 = tb.open_file(oname, "w")
    if lib == "none":
        filters = None
    else:
        filters = tb.Filters(complib=lib, complevel=clevel, shuffle=shuffle)
    if prec == "single":
        type_ = tb.Float32Atom()
    else:
        type_ = tb.Float64Atom()
    r = f2.create_carray('/', 'r', type_, a_.shape, filters=filters)

    if kind == "numpy":
        a2, b2 = a_[:], b_[:]
        t0 = time()
        r = eval(expression, {'a': a2, 'b': b2})
        print("%5.2f" % round(time() - t0, 3))
    else:
        expr = tb.Expr(expression, {'a': a_, 'b': b_})
        expr.set_output(r)
        expr.eval()
    f.close()
    f2.close()
    size = float(os.stat(iname)[6]) + float(os.stat(oname)[6])
    return size


if __name__ == '__main__':
    if len(sys.argv) > 3:
        kind = sys.argv[1]
        prec = sys.argv[2]
        if sys.argv[3] == "synth":
            synth = True
        else:
            synth = False
    else:
        print("3 parameters required")
        sys.exit(1)

    # print "kind, precision, synth:", kind, prec, synth

    # print "Creating input files..."
    size_orig = create_file(kind, prec, synth)

    # print "Processing files for compression levels in range(10)..."
    for clevel in range(10):
        t0 = time()
        ts = []
        for i in range(niter):
            size = process_file(kind, prec, clevel, synth)
            ts.append(time() - t0)
            t0 = time()
        ratio = size_orig / size
        print("%5.2f, %5.2f" % (round(min(ts), 3), ratio))