libstdc++-v3/testsuite/20_util/hash/chi2_q_document_words.cc

   1 // On some simulators, the workload is simply too large with values big
   2 // enough for the test to pass the quality test, so just skip it altogether.
   3 // { dg-do run { target { ! simulator } } }
   4 // { dg-options "-std=gnu++0x" }
   5
   6 // Copyright (C) 2010-2014 Free Software Foundation, Inc.
   7 //
   8 // This file is part of the GNU ISO C++ Library.  This library is free
   9 // software; you can redistribute it and/or modify it under the
  10 // terms of the GNU General Public License as published by the
  11 // Free Software Foundation; either version 3, or (at your option)
  12 // any later version.
  13 //
  14 // This library is distributed in the hope that it will be useful,
  15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  17 // GNU General Public License for more details.
  18 //
  19 // You should have received a copy of the GNU General Public License
  20 // along with this library; see the file COPYING3.  If not see
  21 // <http://www.gnu.org/licenses/>.
  22
  23 #include "chi2_quality.h"
  24
  25 // Tests chi^2 for a set of words taken from a document written in English.
  26 void
  27 test_document_words()
  28 {
  29   bool test __attribute__((unused)) = true;
  30   const std::string f_name = "thirty_years_among_the_dead_preproc.txt";
  31   std::ifstream in(f_name);
  32   VERIFY( in.is_open() );
  33   std::vector<std::string> words;
  34   words.assign(std::istream_iterator<std::string>(in),
  35                std::istream_iterator<std::string>());
  36   VERIFY( words.size() > 100000 );
  37   std::sort(words.begin(), words.end());
  38   auto it = std::unique(words.begin(), words.end());
  39   words.erase(it, words.end());
  40   VERIFY( words.size() > 5000 );
  41
  42   const unsigned long k = words.size() / 20;
  43   double chi2 = chi2_hash(words, k);
  44   VERIFY( chi2 < k*1.1 );
  45 }
  46
  47 int
  48 main()
  49 {
  50   test_document_words();
  51   return 0;
  52 }