我目前正在尝试用 C++ 编写一个字数统计程序,但在解析字符串并将字词彼此分开时遇到了困难。除此之外,我很难让唯一单词的字数在每次重复单词时增加。据我所知,我的 findWord() 和 DistinctWords() 函数很可能是问题所在。也许您会看到我在其他功能中没有看到的东西,至于上述功能,我不知道它们中有什么问题。这些是我的导师提供的指示:
创建一个程序,计算并报告文本文件中不同的、不区分大小写的单词的出现次数。
程序应该有一个循环:
1.提示用户输入文件名。如果用户仅按下 Enter 键,则终止循环和程序。
2.验证输入名称的文件是否存在。如果文件不存在,则显示相应的消息并返回到步骤 1。
3.读取并显示文件内容。
4.显示文件中不同单词的计数。
5.显示文件中每个不同单词的排序列表以及每个单词的出现次数。按字数降序排列列表,按字数升序排列。
我现在很困,我的作业在午夜到期。帮助当然会非常感激。感谢您的时间。这是我的代码,我还将在其后复制粘贴示例测试文本文件:
#include <iostream>
#include <iomanip>
#include <string>
#include <fstream> // Needed to use files
#include <vector>
#include <algorithm> // Needed for sort from standard libraries
using namespace std;
struct WordCount{
string word; // Word
int count; // Occurence #
void iCount(){ count++; }
WordCount(string s){ word = s; count = 1;}
};
// Function prototypes
string InputText(); // Get user file name and get text from said file
string Normalize(string); // Convert string to lowercase and remove punctuation
vector<WordCount> DistinctWords(string); // Sorted vector of word count structures
bool findWord(string, vector<WordCount>); // Linear search for word in vector of structures
void DisplayResults(vector<WordCount>); // Display results
// Main
int main(int argc, char** argv) {
// Program Title
cout << "Lab 9 - Text File Word Counter\n";
cout << "-------------------------------\n\n";
// Input text from file
string buffer = InputText();
while (buffer != ""){
// Title for text file reading
cout << "\nThis is the text string read from the file\n";
cout << "-------------------------------------------\n";
cout << buffer << endl << endl;
// Build vector of words and counts
vector<WordCount> words = DistinctWords(buffer);
// Display results
cout << "There are " << words.size() << " unique words in the above text." << endl;
cout << "--------------------------------------------" << endl << endl;
DisplayResults(words);
buffer = InputText();
}
return 0;
}
/***********************************************
InputText() -
Gets user file name and gets text from the file.
************************************************/
string InputText(){
string fileName;
ifstream inputFile; // Input file stream object
string str; // Temporary string
string text; // Text file string
cout << "File name? ";
getline(cin, fileName);
// Case to terminate the program for enter key
if (fileName.empty()){ exit(0);}
// Open file
inputFile.open(fileName);
if (!inputFile){
cout << "Error opening data file\n";
cout << "File name? "; cin >> fileName;
}
else{
while (!inputFile.eof()){
getline(inputFile, str);
text += str;
}
}
inputFile.close(); return text;
}
/****************************************************
Normalize(string) -
Converts string to lowercase and removes punctuation.
*****************************************************/
string Normalize(string s){
// Initialize variables
string nString;
char c;
// Make all text lowercase
for (int i = 0; i < s.length(); i++){
c = s[i];
c = tolower(c);
nString += c;
}
// Remove punctuation
for (int i = 0; i < nString.length(); i++){
if (ispunct(nString[i]))
nString.erase(i, 1);
}
// Return converted string
return nString;
}
/******************************************
vector<WordCount> DistinctWords(string) -
Sorts vector of word count structures.
*******************************************/
vector<WordCount> DistinctWords(string s){
vector<WordCount> words; // Initialize vector for words
string nString = Normalize(s); // Convert passed string to lowercase and remove punctuation
// Parse string
istringstream iss(nString);
while(iss >> nString){
string n; // Intialize temporary string
iss >> n; // Put word in n
if (findWord(n, words) == true){ continue; } // Check to verify that there is no preexisting occurence of the word passed
else{
WordCount tempO(n); // Make structure object with n
words.push_back(tempO); // Push structure object into words vector
}
}
return words;
}
/*********************************************
bool findWord(string, vector<WordCount>) -
Linear search for word in vector of structures
**********************************************/
bool findWord(string s, vector<WordCount> words){
// Search through vector
for (auto r : words){
if (r.word == s){ // Increment count of object if found again
r.iCount(); return true;
}
else // Go back to main function if not found
return false;
}
}
/***********************************************
void DisplayResults(vector<WordCount>) -
Displays results.
************************************************/
void DisplayResults(vector<WordCount> words){
// TROUBLESHOOT FIRST ERASE THIS AFTER!!!!!
cout << "Word" << setw(20) << "Count\n";
cout << "-----------------------\n";
for (auto &r : words){
cout << setw(6) << left << r.word;
cout << setw(15) << right << r.count << endl;
}
}
这是最好的时代,这是最坏的时代,这是智慧的时代,这是愚蠢的时代,这是信仰的时代,这是怀疑的时代,这是不信任的时代光明,那是黑暗的季节,那是希望的 Spring ,那是绝望的冬天,我们拥有一切,我们一无所有,我们都直奔天堂,我们都直奔另一个方式 - 简而言之,那个时期与现在的时期非常相似,一些最喧闹的权威坚持认为它只是在最高级的比较中被接受,无论是好是坏。
This is the example display he provided for this particular test file
最佳答案
你几乎成功了! 您只是忘记通过引用而不是通过复制来传递“单词” vector 。 我还在末尾包含了一个用于排序的自定义比较器。
#include <iostream>
#include <sstream>
#include <iomanip>
#include <string>
#include <fstream> // Needed to use files
#include <vector>
#include <algorithm> // Needed for sort from standard libraries
using namespace std;
struct WordCount{
string word; // Word
int count; // Occurence #
void iCount(){ count++; }
WordCount(string s){ word = s; count = 1;}
};
struct {
bool operator()(const WordCount& a, const WordCount& b)
{
if (a.count < b.count)
return false;
else if (a.count > b.count)
return true;
else{
if (a.word < b.word)
return true;
else
return false;
}
}
} CompareWordCount;
// Function prototypes
string InputText(); // Get user file name and get text from said file
string Normalize(string); // Convert string to lowercase and remove punctuation
vector<WordCount> DistinctWords(string); // Sorted vector of word count structures
bool findWord(string, vector<WordCount>&); // Linear search for word in vector of structures
void DisplayResults(vector<WordCount>); // Display results
// Main
int main(int argc, char** argv) {
// Program Title
cout << "Lab 9 - Text File Word Counter\n";
cout << "-------------------------------\n\n";
// Input text from file
string buffer = InputText();
while (buffer != ""){
// Title for text file reading
cout << "\nThis is the text string read from the file\n";
cout << "-------------------------------------------\n";
cout << buffer << endl << endl;
// Build vector of words and counts
vector<WordCount> words = DistinctWords(buffer);
// Display results
cout << "There are " << words.size() << " unique words in the above text." << endl;
cout << "--------------------------------------------" << endl << endl;
DisplayResults(words);
buffer = InputText();
buffer = "";
}
return 0;
}
/***********************************************
InputText() -
Gets user file name and gets text from the file.
************************************************/
string InputText(){
string fileName;
ifstream inputFile; // Input file stream object
string str; // Temporary string
string text; // Text file string
cout << "File name? ";
getline(cin, fileName);
// Case to terminate the program for enter key
if (fileName.empty()){ exit(0);}
// Open file
inputFile.open(fileName);
if (!inputFile){
cout << "Error opening data file\n";
cout << "File name? "; cin >> fileName;
}
else{
while (!inputFile.eof()){
getline(inputFile, str);
text += str;
}
}
inputFile.close(); return text;
}
/****************************************************
Normalize(string) -
Converts string to lowercase and removes punctuation.
*****************************************************/
string Normalize(string s){
// Initialize variables
string nString;
char c;
// Make all text lowercase
for (int i = 0; i < s.length(); i++){
c = s[i];
c = tolower(c);
if (isalpha(c) || isblank(c))
nString += c;
}
// Return converted string
return nString;
}
/******************************************
vector<WordCount> DistinctWords(string) -
Sorts vector of word count structures.
*******************************************/
vector<WordCount> DistinctWords(string s){
vector<WordCount> words; // Initialize vector for words
string nString = Normalize(s); // Convert passed string to lowercase and remove punctuation
// Parse string
istringstream iss(nString);
string n; // Intialize temporary string
while(iss >> n){
if (findWord(n, words) == true){ continue; } // Check to verify that there is no preexisting occurence of the word passed
else{
WordCount tempO(n); // Make structure object with n
words.push_back(tempO); // Push structure object into words vector
}
}
return words;
}
/*********************************************
bool findWord(string, vector<WordCount>) -
Linear search for word in vector of structures
**********************************************/
bool findWord(string s, vector<WordCount>& words){
// Search through vector
for (auto& r : words){
if (r.word.compare(s) == 0){ // Increment count of object if found again
r.iCount(); return true;
}
}
}
/***********************************************
void DisplayResults(vector<WordCount>) -
Displays results.
************************************************/
void DisplayResults(vector<WordCount> words){
// TROUBLESHOOT FIRST ERASE THIS AFTER!!!!!
cout << "Word" << setw(20) << "Count\n";
cout << "-----------------------\n";
sort(words.begin(), words.end(),CompareWordCount);
for (auto &r : words){
cout << setw(6) << left << r.word;
cout << setw(15) << right << r.count << endl;
}
}
关于c++ - 字数统计程序 C++,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/43685816/