| 1 | /* Boost.MultiIndex example of use of sequenced indices. |
| 2 | * |
| 3 | * Copyright 2003-2008 Joaquin M Lopez Munoz. |
| 4 | * Distributed under the Boost Software License, Version 1.0. |
| 5 | * (See accompanying file LICENSE_1_0.txt or copy at |
| 6 | * http://www.boost.org/LICENSE_1_0.txt) |
| 7 | * |
| 8 | * See http://www.boost.org/libs/multi_index for library home page. |
| 9 | */ |
| 10 | |
| 11 | #if !defined(NDEBUG) |
| 12 | #define BOOST_MULTI_INDEX_ENABLE_INVARIANT_CHECKING |
| 13 | #define BOOST_MULTI_INDEX_ENABLE_SAFE_MODE |
| 14 | #endif |
| 15 | |
| 16 | #include <boost/multi_index_container.hpp> |
| 17 | #include <boost/multi_index/identity.hpp> |
| 18 | #include <boost/multi_index/ordered_index.hpp> |
| 19 | #include <boost/multi_index/sequenced_index.hpp> |
| 20 | #include <boost/tokenizer.hpp> |
| 21 | #include <algorithm> |
| 22 | #include <iomanip> |
| 23 | #include <iostream> |
| 24 | #include <iterator> |
| 25 | #include <string> |
| 26 | |
| 27 | using boost::multi_index_container; |
| 28 | using namespace boost::multi_index; |
| 29 | |
| 30 | /* text_container holds words as inserted and also keep them indexed |
| 31 | * by dictionary order. |
| 32 | */ |
| 33 | |
| 34 | typedef multi_index_container< |
| 35 | std::string, |
| 36 | indexed_by< |
| 37 | sequenced<>, |
| 38 | ordered_non_unique<identity<std::string> > |
| 39 | > |
| 40 | > text_container; |
| 41 | |
| 42 | /* ordered index */ |
| 43 | |
| 44 | typedef nth_index<text_container,1>::type ordered_text; |
| 45 | |
| 46 | typedef boost::tokenizer<boost::char_separator<char> > text_tokenizer; |
| 47 | |
| 48 | int main() |
| 49 | { |
| 50 | std::string text= |
| 51 | "Alice was beginning to get very tired of sitting by her sister on the " |
| 52 | "bank, and of having nothing to do: once or twice she had peeped into the " |
| 53 | "book her sister was reading, but it had no pictures or conversations in " |
| 54 | "it, 'and what is the use of a book,' thought Alice 'without pictures or " |
| 55 | "conversation?'" ; |
| 56 | |
| 57 | /* feed the text into the container */ |
| 58 | |
| 59 | text_container tc; |
| 60 | text_tokenizer tok(text,boost::char_separator<char>(" \t\n.,;:!?'\"-" )); |
| 61 | std::copy(first: tok.begin(),last: tok.end(),result: std::back_inserter(x&: tc)); |
| 62 | |
| 63 | /* list all words in alphabetical order along with their number |
| 64 | * of occurrences |
| 65 | */ |
| 66 | |
| 67 | ordered_text& ot=get<1>(m&: tc); |
| 68 | for(ordered_text::iterator it=ot.begin();it!=ot.end();){ |
| 69 | std::cout<<std::left<<std::setw(14)<<*it<<":" ; /* print the word */ |
| 70 | ordered_text::iterator it2=ot.upper_bound(x: *it); /* jump to next */ |
| 71 | std::cout<<std::right<<std::setw(3) /* and compute the distance */ |
| 72 | <<std::distance(first: it,last: it2)<<" times" <<std::endl; |
| 73 | it=it2; |
| 74 | } |
| 75 | |
| 76 | /* reverse the text and print it out */ |
| 77 | |
| 78 | tc.reverse(); |
| 79 | std::cout<<std::endl; |
| 80 | std::copy( |
| 81 | first: tc.begin(),last: tc.end(),result: std::ostream_iterator<std::string>(std::cout," " )); |
| 82 | std::cout<<std::endl; |
| 83 | tc.reverse(); /* undo */ |
| 84 | |
| 85 | /* delete most common English words and print the result */ |
| 86 | |
| 87 | std::string common_words[]= |
| 88 | {"the" ,"of" ,"and" ,"a" ,"to" ,"in" ,"is" ,"you" ,"that" ,"it" , |
| 89 | "he" ,"for" ,"was" ,"on" ,"are" ,"as" ,"with" ,"his" ,"they" ,"at" }; |
| 90 | |
| 91 | for(std::size_t n=0;n<sizeof(common_words)/sizeof(common_words[0]);++n){ |
| 92 | ot.erase(x: common_words[n]); |
| 93 | } |
| 94 | std::cout<<std::endl; |
| 95 | std::copy( |
| 96 | first: tc.begin(),last: tc.end(),result: std::ostream_iterator<std::string>(std::cout," " )); |
| 97 | std::cout<<std::endl; |
| 98 | |
| 99 | return 0; |
| 100 | } |
| 101 | |