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 { c++11 && { ! simulator } } } }
   4
   5 // Copyright (C) 2010-2020 Free Software Foundation, Inc.
   6 //
   7 // This file is part of the GNU ISO C++ Library.  This library is free
   8 // software; you can redistribute it and/or modify it under the
   9 // terms of the GNU General Public License as published by the
  10 // Free Software Foundation; either version 3, or (at your option)
  11 // any later version.
  12 //
  13 // This library is distributed in the hope that it will be useful,
  14 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 // GNU General Public License for more details.
  17 //
  18 // You should have received a copy of the GNU General Public License
  19 // along with this library; see the file COPYING3.  If not see
  20 // <http://www.gnu.org/licenses/>.
  21
  22 #include "chi2_quality.h"
  23
  24 // Tests chi^2 for a set of words taken from a document written in English.
  25 void
  26 test_document_words()
  27 {
  28   const std::string f_name = "thirty_years_among_the_dead_preproc.txt";
  29   std::ifstream in(f_name);
  30   VERIFY( in.is_open() );
  31   std::vector<std::string> words;
  32   words.assign(std::istream_iterator<std::string>(in),
  33                std::istream_iterator<std::string>());
  34   VERIFY( words.size() > 100000 );
  35   std::sort(words.begin(), words.end());
  36   auto it = std::unique(words.begin(), words.end());
  37   words.erase(it, words.end());
  38   VERIFY( words.size() > 5000 );
  39
  40   const unsigned long k = words.size() / 20;
  41   double chi2 = chi2_hash(words, k);
  42   VERIFY( chi2 < k*1.1 );
  43 }
  44
  45 int
  46 main()
  47 {
  48   test_document_words();
  49   return 0;
  50 }