本文概述
标记字符串表示相对于某些定界符分割字符串。有很多标记字符串的方法。在本文中, 将对其中的四个进行说明:
使用stringstream
一种
串流
将字符串对象与流相关联, 使你可以像对待流一样读取字符串。
以下是C ++实现:
C ++
// Tokenizing a string using stringstream
#include <bits/stdc++.h>
using namespace std;
int main()
{
string line = "lsbin is a must try" ;
// Vector of string to save tokens
vector <string> tokens;
// stringstream class check1
stringstream check1(line);
string intermediate;
// Tokenizing w.r.t. space ' '
while (getline(check1, intermediate, ' ' ))
{
tokens.push_back(intermediate);
}
// Printing the token vector
for ( int i = 0; i < tokens.size(); i++)
cout << tokens[i] << '\n' ;
}
输出如下
lsbin
is
a
must
try
使用strtok()
// Splits str[] according to given delimiters.
// and returns next token. It needs to be called
// in a loop to get all tokens. It returns NULL
// when there are no more tokens.
char * strtok(char str[], const char *delims);
以下是C ++实现:
C ++
// C/C++ program for splitting a string
// using strtok()
#include <stdio.h>
#include <string.h>
int main()
{
char str[] = "Geeks-for-Geeks" ;
// Returns first token
char *token = strtok (str, "-" );
// Keep printing tokens while one of the
// delimiters present in str[].
while (token != NULL)
{
printf ( "%s\n" , token);
token = strtok (NULL, "-" );
}
return 0;
}
输出如下
Geeks
for
Geeks
strtok()的另一个示例:
C
// C code to demonstrate working of
// strtok
#include <string.h>
#include <stdio.h>
// Driver function
int main()
{
// Declaration of string
char gfg[100] = " Geeks - for - geeks - Contribute" ;
// Declaration of delimiter
const char s[4] = "-" ;
char * tok;
// Use of strtok
// get first token
tok = strtok (gfg, s);
// Checks for delimeter
while (tok != 0) {
printf ( " %s\n" , tok);
// Use of strtok
// go through other tokens
tok = strtok (0, s);
}
return (0);
}
输出如下
Geeks
for
geeks
Contribute
使用strtok_r()
就像C中的strtok()函数一样,
strtok_r()
执行将字符串解析为令牌序列的相同任务。 strtok_r()是strtok()的可重入版本。
有两种方法可以调用strtok_r()
// The third argument saveptr is a pointer to a char *
// variable that is used internally by strtok_r() in
// order to maintain context between successive calls
// that parse the same string.
char *strtok_r(char *str, const char *delim, char **saveptr);
下面是一个简单的C ++程序, 用于显示strtok_r()的用法:
CPP
// C/C++ program to demonstrate working of strtok_r()
// by splitting string based on space character.
#include<stdio.h>
#include<string.h>
int main()
{
char str[] = "Geeks for Geeks" ;
char *token;
char *rest = str;
while ((token = strtok_r(rest, " " , &rest)))
printf ( "%s\n" , token);
return (0);
}
输出如下
Geeks
for
Geeks
使用std :: sregex_token_iterator
在这种方法中, 基于正则表达式匹配进行标记化。当需要多个定界符时, 更适合用例。
下面是一个简单的C ++程序, 用于显示std :: sregex_token_iterator的用法:
C ++
// CPP program for above approach
#include <iostream>
#include <regex>
#include <string>
#include <vector>
/**
* @brief Tokenize the given vector
according to the regex
* and remove the empty tokens.
*
* @param str
* @param re
* @return std::vector<std::string>
*/
std::vector<std::string> tokenize(
const std::string str, const std::regex re)
{
std::sregex_token_iterator it{ str.begin(), str.end(), re, -1 };
std::vector<std::string> tokenized{ it, {} };
// Additional check to remove empty strings
tokenized.erase(
std::remove_if(tokenized.begin(), tokenized.end(), [](std::string const & s) {
return s.size() == 0;
}), tokenized.end());
return tokenized;
}
// Driver Code
int main()
{
const std::string str = "Break string
a, spaces, and, commas";
const std::regex re(R "([\s|, ]+)" );
// Function Call
const std::vector<std::string> tokenized =
tokenize(str, re);
for (std::string token : tokenized)
std::cout << token << std::endl;
return 0;
}
输出如下
Break
string
a
spaces
and
commas