Blog·Tanky WooABOUTRSS

一个简单的文本查询程序---摘至《C++ Primer》

11 Nov 2010
这篇博客是从旧博客 WordPress 迁移过来,内容可能存在转换异常。

这是在《C++ Primer》上第十章最后的一个小节。以前把这里漏掉了,刚才看了下,觉得这个程序很不错,便于对vector, map, set的基本掌握。特地把这一个小程序记录下来。

/*
 *目的:一个简单的文本查询程序
 *作用:程序将读取用户指定的任意文本文件,然后允许用户从该文件中查找单词。
 *查询的结果是该单词出现的次数,并列出每次出现所在的行。
 *如果某单词在同一行中多次出现,程序将只显示该行一次。
 *行号按升序显示,即第 7 行应该在第 9 行之前输出,依此类推。
 */
/*思路:
 *1.使用一个 vector 类型的对象存储整个输入文件的副本。
 *   输入文件的每一行是该 vector 对象的一个元素。
 *   因而,在希望输出某一行时,只需以行号为下标获取该行所在的元素即可。
 *2.将每个单词所在的行号存储在一个 set 容器对象中。
 *   使用 set 就可确保每行只有一个条目,而且行号将自动按升序排列。
 *3.使用一个 map 容器将每个单词与一个 set 容器对象关联起来,
 *   该 set 容器对象记录此单词所在的行号。
 */

TextQuery.H文件

#ifndef TEXTQUERY_H
#define TEXTQUERY_H
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 

class TextQuery {
    // as before
public:
    // typedef to make declarations easier
    typedef std::string::size_type str_size;
    typedef std::vector::size_type line_no;

    /* interface:
     *    read_file builds internal data structures for the given file
     *    run_query finds the given word and returns set of lines on which it appears
     *    text_line returns a requested line from the input file
    */
    void read_file(std::ifstream &is;) 
               { store_file(is); build_map(); }
    std::set run_query(const std::string&) const; 
    std::string text_line(line_no) const;
    str_size size() const { return lines_of_text.size(); }
    void display_map();        // debugging aid: print the map

private:
    // utility functions used by read_file
    void store_file(std::ifstream&); // store input file
    void build_map(); // associated each word with a set of line numbers

    // remember the whole input file
    std::vector lines_of_text; 

    // map word to set of the lines on which it occurs
    std::map< std::string, std::set > word_map;  
    // characters that constitute whitespace
    static std::string whitespace_chars;     
    // canonicalizes text: removes punctuation and makes everything lower case
    static std::string cleanup_str(const std::string&);
};
#endif

TextQuery.CPP 文件

#include "TextQuery.h"
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 

using std::istringstream;
using std::set;
using std::string;
using std::getline;
using std::map;
using std::vector;
using std::cerr;
using std::cout;
using std::cin;
using std::ifstream;
using std::endl;
using std::ispunct;
using std::tolower;
using std::strlen;
using std::out_of_range;

string TextQuery::text_line(line_no line) const
{
    if (line < lines_of_text.size())
        return lines_of_text[line];
    throw std::out_of_range("line number out of range");
}

// read input file: store each line as element in lines_of_text 
void TextQuery::store_file(ifstream &is;)
{
    string textline;
    while (getline(is, textline))
       lines_of_text.push_back(textline);
}

// \v: vertical tab; \f: formfeed; \r: carriage return are
// treated as whitespace characters along with space, tab and newline
string TextQuery::whitespace_chars(" \t\n\v\r\f");

// finds whitespace-separated words in the input vector
// and puts the word in word_map along with the line number
void TextQuery::build_map()
{
    // process each line from the input vector
    for (line_no line_num = 0; 
                 line_num != lines_of_text.size();
                 ++line_num)
    {
        // we'll use line to read the text a word at a time
        istringstream line(lines_of_text[line_num]);
        string word;
        while (line >> word)
            // add this line number to the set;
            // subscript will add word to the map if it's not already there
            word_map[cleanup_str(word)].insert(line_num);
    }
}

set
TextQuery::run_query(const string &query;_word) const
{
    // Note: must use find and not subscript the map directly
    // to avoid adding words to word_map!
    map >::const_iterator 
                          loc = word_map.find(cleanup_str(query_word));
    if (loc == word_map.end()) 
        return set();  // not found, return empty set
    else
        // fetch and return set of line numbers for this word
        return loc->second;
}

void TextQuery::display_map()
{
    map< string, set >::iterator iter = word_map.begin(),
                                       iter_end = word_map.end();

    // for each word in the map
    for ( ; iter != iter_end; ++iter) {
        cout << "word: " << iter->first << " {";

        // fetch location vector as a const reference to avoid copying it
        const set &text;_locs = iter->second;
        set::const_iterator loc_iter = text_locs.begin(),
                                     loc_iter_end = text_locs.end();

        // print all line numbers for this word
        while (loc_iter != loc_iter_end)
        {
            cout << *loc_iter;

            if (++loc_iter != loc_iter_end)
                 cout << ", ";

         }

         cout << "}\n";  // end list of output this word
    }
    cout << endl;  // finished printing entire map
}


// lower-case to upper-case
string TextQuery::cleanup_str(const string &word;)
{
    string ret;
    for (string::const_iterator it = word.begin(); it != word.end(); ++it) {
        if (!ispunct(*it))
            ret += tolower(*it);
    }
    return ret;
}

主函数

#include "TextQuery.h"
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 

using std::set;
using std::string;
using std::map;
using std::vector;
using std::cerr;
using std::cout;
using std::cin;
using std::ifstream;
using std::endl;

string make_plural(size_t, const string&, const string&);
ifstream& open_file(ifstream&, const string&);

void print_results(const set& locs, 
                   const string& sought, const TextQuery &file;)
{
    // if the word was found, then print count and all occurrences
    typedef set line_nums; 
    line_nums::size_type size = locs.size();
    cout << "\n" << sought << " occurs "
         << size << " "
         << make_plural(size, "time", "s") << endl;

    // print each line in which the word appeared
    line_nums::const_iterator it = locs.begin();
    for ( ; it != locs.end(); ++it) {
        cout << "\t(line "
             // don't confound user with text lines starting at 0
             << (*it) + 1 << ") "
             << file.text_line(*it) << endl;
    }
}


// program takes single argument specifying the file to query
int main()
{
    // open the file from which user will query words
    ifstream infile;
    if (!open_file(infile, "Tanky_Woo.txt")) {
        cerr << "No input file!" << endl;
        return EXIT_FAILURE;
    }

    TextQuery tq;
    tq.read_file(infile);  // builds query map

    // iterate with the user: prompt for a word to find and print results
    // loop indefinitely; the loop exit is inside the while
    while (true) {
        cout << "enter word to look for, or q to quit: ";
        string s;
        cin >> s;

        // stop if hit eof on input or a 'q' is entered
        if (!cin || s == "q") break;

        // get the set of line numbers on which this word appears
        set locs = tq.run_query(s);

        // print count and all occurrences, if any
        print_results(locs, s, tq);
     }
    return 0;
}

string make_plural (size_t ctr , const string &word; , 
const string &ending;) 
{ 
    return ( ctr == 1 ) ? word : word + ending; 
} 

ifstream& open_file(ifstream &in;, const string &file;)
{
    in.close();  // close in case it was already open
    in.clear();  // clear any existing errors

    // if the open fails, the stream will be in an invalid state
    in.open(file.c_str()); // open the file we were given

    return in; // condition state is good if open succeeded
}