如何解决在.txt文件中查找热门单词计数-while循环进行得非常慢，无法正常工作
我试图从本质上遍历.txt文件中的每个单词，当我发现一个单词（从我的单词映射中）的单词超过maxwordcount变量时，我将其添加到topwords向量的前面
int main(int argc,char** argv) {
fstream txtfile;
string filename = argv[1];
string word,tempword;
int maxwordcount = 0;
int wordcount = 0;
int uniquewordcount = 0;
vector<pair <string,int> > topwords;
map<string,int> words;
if (argc != 2) {
cout << "Incorrect number of arguments on the command line bud" << endl;
}else{
txtfile.open(filename.c_str());
if (txtfile.is_open()) {
while (txtfile >> word){
//removePunctuation(word);
//transform(word.begin(),word.end(),word.begin(),[](unsigned char c){ return::tolower(c); }); //makes string lowercase using iterator
if (words.find(word) == words.end()) {
words[word] = 1; //adds word into the map as a pair starting with a word count of 1
if (words[word] > maxwordcount) { //For case if word is the first word added to the map
maxwordcount = words[word]; //change maxwordcount
topwords.insert( topwords.begin(),make_pair(word,words[word]) ); //insert word into the front of the top words vector
cout << "word: '" << word << "' word-count: " << words[word] << endl;
}
uniquewordcount++;
}else{ //the word is found
words[word]++; //increment count for word by 1
if (words[word] > maxwordcount) { //check if wordcount > maxwordcount
topwords.insert( topwords.begin(),words[word]) ); //insert word into the front of the top words vector
}
}
wordcount++;
}
在程序结束时，我想显示txt文件中的前10个字。我通过显示实时单词计数（cout）测试了while循环是否正在运行。这个数字上升了，但是上升得非常慢。另外，我正在为txt文件使用大量书籍。
我也不完全了解在地图和向量中插入变量，因此那里可能出了问题。
我已经走到了尽头，所以这时任何事情都会有所帮助。
我也使用了一个较小的文本文件进行测试：
This is a small sentence to test test test
hey hey
结果：
word: 'This' word-count: 1
1
2
3
4
5
6
7
7
7
8
8
There were 11 words in the file.
There were 8 unique words in the file.
Top 20 words in little.txt:
hey 2
test 3
test 2
This 1
Segmentation fault
我知道我做错了什么，但是我不知道下一步该做什么或要测试什么。还是C ++和C的业余爱好者。
解决方法
您应该逐行读取文件，逐行处理
按行读取文件文件：https://www.systutorials.com/how-to-process-a-file-line-by-line-in-c/
https://www.geeksforgeeks.org/split-a-sentence-into-words-in-cpp/
https://www.w3schools.com/cpp/cpp_functions.asp
https://www.w3schools.com/cpp/cpp_function_param.asp
https://www.w3schools.com/cpp/cpp_function_return.asp
https://www.w3schools.com/cpp/cpp_pointers.asp
https://www.w3schools.com/cpp/cpp_references.asp
#include <bits/stdc++.h>
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
#include <string>
#include <algorithm>
#include <sstream>
#include <regex>
#include <iterator>
using namespace std;
vector<std::pair <string,int> > topwords;
void store(vector<pair <string,int> > &topwords,string str){
auto pos = std::find_if(topwords.begin(),topwords.end(),[str](std::pair<string,int> const &b) {
return b.first == str;
});
//std::cout<< pos->first << endl;
if(pos != topwords.end()){
std::cout << "word: " << pos->first << " " << pos->second << " found" << endl;
pos->second++;
}
else{
std::cout << "not found" << endl;
topwords.push_back( make_pair(str,1) );
}
}
void removeDupWord(string str)
{
// Used to split string around spaces.
istringstream ss(str);
// Traverse through all words
/*
do {
// Read a word
string word;
ss >> word;
// Print the read word
cout << word << endl;
store(topwords,word );
// While there is more to read
} while (ss);
*/
string word;
while (ss >> word) {
//cout << word << endl;
const std::regex sanitized{ R"([-[\]{}()*+?.,\^$|#\s])" };
std::stringstream result;
std::regex_replace(std::ostream_iterator<char>(result),word.begin(),word.end(),sanitized,"");
//store(topwords,word );
store(topwords,result.str() );
}
}
void readReadFile(string &fileName){
std::cout << "fileName" << fileName << endl;
std::ifstream file(fileName);
std::string str;
while (std::getline(file,str)) {
//std::cout << str << "\n";
removeDupWord(str);
//store(topwords,str);
}
}
bool compareFunction (const std::pair<std::string,int> &a,const std::pair<std::string,int> &b) {
return a.first<b.first; // sort by letter
}
bool compareFunction2 (const std::pair<std::string,int> &b) {
return a.second>b.second; // sort by count
}
bool cmp(pair<string,int> &A,pair<string,int> &B) {
return A.second < B.second;
}
void check(vector<pair <string,int> > &topwords){
std::pair<string,int> mostUsedWord = make_pair("",0);
for(auto ii : topwords){
std::cout << "word: " << ii.first << " count: " << ii.second << endl;
if(ii.second > mostUsedWord.second){
mostUsedWord.first = ii.first;
mostUsedWord.second = ii.second;
}
}
std::cout << "most used Word: " << mostUsedWord.first << " x " << mostUsedWord.second << " Times." << endl;
}
void get_higestTopTenValues(vector<pair <string,int> > &topwords){
std::sort(topwords.begin(),compareFunction2);//sort the vector by count
int MAX = std::max_element(topwords.begin(),cmp)->second;
std::cout << "max: " << MAX << endl;
for(auto ii : topwords){
//std::cout << "word: " << ii.first << " count: " << ii.second << endl;
if(ii.second >= (MAX - 10)){
std::cout << ii.first << " " << ii.second << endl;
}
}
}
void get_LowestTopTenValues(vector<pair <string,compareFunction2);//sort the vector by count
int MIN = std::min_element(topwords.begin(),cmp)->second;
std::cout << "min: " << MIN << endl;
for(auto ii : topwords){
//std::cout << "word: " << ii.first << " count: " << ii.second << endl;
if(ii.second <= (MIN + 9)){
std::cout << ii.first << " " << ii.second << endl;
}
}
}
int main ()
{
std::string word,fileName;
fileName = "input.txt";
readReadFile(fileName);
topwords.push_back( make_pair("ba",1) );
topwords.push_back( make_pair("bu",1) );
topwords.push_back( make_pair("hmmm",1) );
topwords.push_back( make_pair("what",1) );
topwords.push_back( make_pair("and",1) );
topwords.push_back( make_pair("hello",1) );
word = "hellos";
store(topwords,word);
store(topwords,word);
word = "hello";
store(topwords,word);
std::sort(topwords.begin(),compareFunction);//sort the vector by letter
// or
//std::sort(topwords.begin(),compareFunction2);//sort the vector by count
std::cout << "---------------------------------------" << endl;
std::cout << " get all values" << endl;
std::cout << "---------------------------------------" << endl;
check(topwords);
std::cout << "---------------------------------------" << endl;
std::cout << " get the top 10 highest values" << endl;
std::cout << "---------------------------------------" << endl;
get_higestTopTenValues(topwords);
std::cout << "---------------------------------------" << endl;
std::cout << " get the top 10 lowest values" << endl;
std::cout << "---------------------------------------" << endl;
get_LowestTopTenValues(topwords);
}
这个问题很久以前就有人回答了。我偶然发现了这个问题并回答了，我发现一切都过于复杂。
因此，我想添加一个使用现有 STL 元素的更现代的 C++ 解决方案。
这使得代码更加紧凑。
请看下面：
#include <iostream>
#include <utility>
#include <unordered_map>
#include <vector>
#include <algorithm>
#include <string>
#include <fstream>
const std::string fileName{"r:\\loremipsum.txt"};
int main() {
if (std::ifstream textFileStream{ fileName }; textFileStream) {
// Here we store the count of all words
std::unordered_map<std::string,size_t> counter{};
size_t countOfOverallWords{}; // Counter for the number of all words
// Read all words from file,remove punctuation,and count teh occurence
for (std::string word; textFileStream >> word; counter[word]++) {
word.erase(std::remove_if(word.begin(),ispunct),word.end());
++countOfOverallWords;
}
// For storing the top 10
std::vector<std::pair<std::string,size_t>> top(10);
// Get top 10
std::partial_sort_copy(counter.begin(),counter.end(),top.begin(),top.end(),[](const std::pair<std::string,size_t >& p1,size_t>& p2) { return p1.second > p2.second; });
// Now show result
std::cout << "Count of overall words:\t " << countOfOverallWords << "\nCount of unique words:\t " << counter.size() << "\n\nTop 10:\n";
for (const auto& t : top) std::cout << "Value: " << t.first << "\t Count: " << t.second << '\n';
}
else std::cerr << "\n\nError: Could not open source file '" << fileName << "'\n\n";
return 0;
}
使用 Microsoft Visual Studio Community 2019 版本 16.8.2 进行开发和测试。
使用带有标志 --std=c++17 -Wall -Wextra -Wpedantic
语言：C++17
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。