分割字符串

Posted 2022-07-13 htj10

```
find() : Finds the first substring equal to the given character sequence
find_first_of() : Finds the first character equal to one of characters in the given character sequence
//字符串分割函数 str为待分割的字符串 pattern为任意分割符(**每一个字符都为分割符**)，例如：";,"是以 ‘;‘ 和 ‘,‘ 分割，并且去掉了分割后的空字符串。 sbcssdfs 以s分割得 "bc" "df"
vector<string> split(string str, string pattern)

    vector<string> ret;
    if (pattern.empty()) return ret;
    size_t start = 0;
    size_t index = str.find_first_of(pattern, 0);
    while (index != string::npos)
    
        if (start != index)
            ret.push_back(str.substr(start, index - start));
        start = index + 1;
        index = str.find_first_of(pattern, start);
    
 
    if (!str.substr(start).empty())
        ret.push_back(str.substr(start));
    return ret;

//分割后保留空字符串。sbcssdfs 以s分割得 "" "bc" "" "df" ""
vector<string> split(string str, string pattern)

    vector<string> ret;
    if (pattern.empty()) return ret;
    size_t start = 0;
    size_t index = str.find_first_of(pattern, 0);
    while (index != string::npos)
    
        ret.push_back(str.substr(start, index - start));
        start = index + 1;
        index = str.find_first_of(pattern, start);
    
    ret.push_back(str.substr(start));
    return ret;

```
用Poco中的StringTokenizer
```
#include "Poco/StringTokenizer.h"
#include "Poco/String.h" // for cat
// 分割字符串，s:将被分割的字符串，k：分割符
// 例如： k是 ";,"表示用 ‘;‘ 和 ‘,‘ 分割
std::vector<std::string> SplitString(std::string s, std::string k)

    /*
    Poco::StringTokenizer t1("red, green, blue", ",");
    // "red", " green", " blue"     (note the whitespace)
    Poco::StringTokenizer t2("red,green,,blue", ",");
    // "red", "green", "", "blue"
    Poco::StringTokenizer t3("red ; green , blue", ",;",
        Poco::StringTokenizer::TOK_TRIM);
    // "red", "green", "blue"
    Poco::StringTokenizer t4("red; green,, blue", ",;",
        Poco::StringTokenizer::TOK_TRIM | Poco::StringTokenizer::TOK_IGNORE_EMPTY);
    // "red", "green", "blue"
    std::string ss(Poco::cat(std::string("; "), t4.begin(), t4.end()));
    // "red; green; blue
    */
    Poco::StringTokenizer st(s, k);//这样是不去掉 "" ,当加上 TOK_IGNORE_EMPTY（宏定义为1）即去掉 "" 了。
    std::vector<std::string> vecRet(st.begin(), st.end());
    return vecRet;

```
另外一个字符串整体为分割符：（单个字符就跟上面的一样了）
```
//pattern作为一个整体当分割符,(不去掉 "")
vector<string> split(string str, string pattern)

    vector<string> ret;
    if (pattern.empty()) return ret;
    size_t start = 0;
    size_t index = str.find(pattern, 0);
    while (index != string::npos)
    
        ret.push_back(str.substr(start, index - start));
        start = index + pattern.size();
        index = str.find(pattern, start);
    
    ret.push_back(str.substr(start));
    return ret;

```