C++ string 类模拟实现详解

C++ string 类模拟实现

1.1 经典的 string 类问题

在面试中，面试官常要求模拟实现 string 类，核心在于构造、拷贝构造、赋值运算符重载及析构函数。以下 String 类实现存在潜在问题：

// 为了和标准库区分，此处使用 String
struct String {
public:
    // 构造 String 类对象时，如果传递 nullptr 指针，可以认为程序非空
    String(const char* str = "") {
        if (nullptr == str) {
            assert(false);
            return;
        }
        _str = new char[strlen(str) + 1];
        strcpy(_str, str);
    }

    ~String() {
        if (_str) {
            delete[] _str;
            _str = nullptr;
        }
    }

private:
    char* _str;
};

// 测试
void TestString() {
    String s1("hello bit!!!");
    String s2(s1);
}

上述 String 类没有显式定义其拷贝构造函数与赋值运算符重载，编译器会合成默认的。当用 s1 构造 s2 时，调用默认拷贝构造，导致 s1、s2 共用同一块内存空间。释放时同一块空间被释放多次而引起程序崩溃，这种拷贝方式称为浅拷贝。

1.2 浅拷贝

浅拷贝：也称位拷贝，编译器只是将对象中的值拷贝过来。如果对象中管理资源，最后就会导致多个对象共享同一份资源。当一个对象销毁时就会将该资源释放掉，而此时另一些对象不知道该资源已经被释放，以为还有效，所以当继续对资源进行操作时，就会发生访问违规。

可以采用深拷贝解决浅拷贝问题，即每个对象都有一份独立的资源，不要和其他对象共享。

1.3 深拷贝

如果一个类中涉及到资源的管理，其拷贝构造函数、赋值运算符重载以及析构函数必须要显式给出。一般情况都是按照深拷贝方式提供。

模拟实现

构造函数的模拟实现

// 现代写法
string(const string& s) {
    string tmp(s._str); // 默认构造
    swap(tmp);          // 把 tmp 和 s2 交换
}

赋值重载的模拟实现

// 最新版本的赋值
string& operator=(string tmp) {
    swap(tmp);
    return *this;
}

析构的模拟实现

~string() {
    delete[] _str;
    _str = nullptr;
    _capacity = _size = 0;
}

clear 的模拟实现

void clear() {
    _str[0] = '\0';
    _size = 0;
}

reserve 的模拟实现

void string::reserve(size_t n) {
    if (n > _capacity) {
        char* tmp = new char[n + 1]; // 永远多开一个空间
        strcpy(tmp, _str);
        delete[] _str;
        _str = tmp;
        _capacity = n;
    }
}

push_back 的模拟实现

void string::push_back(char ch) {
    if (_size == _capacity) {
        reserve(_capacity == 0 ? 4 : _capacity * 2);
    }
    _str[_size] = ch;
    ++_size;
    _str[_size] = '\0';
}

append 的模拟实现

void string::append(const char* str) {
    size_t len = strlen(str);
    if (_size + len > _capacity) {
        reserve(_size + len > _capacity * 2 ? _size + len : _capacity * 2);
    }
    strcpy(_str + _size, str); // _str+size 就是\0 的位置
    _size += len;
}

insert 的模拟实现

void string::insert(size_t pos, char ch) { // 插字符
    assert(pos <= _size);
    if (_size == _capacity) {
        reserve(_capacity == 0 ? 4 : _capacity * 2);
    }
    size_t end = _size + 1;
    while (end > pos) {
        _str[end] = _str[end - 1];
        --end;
    }
    _str[pos] = ch;
    ++_size;
}

void string::insert(size_t pos, const char* str) { // 插字符串
    assert(pos <= _size);
    size_t len = strlen(str);
    if (_size + len > _capacity) {
        reserve(_size + len > _capacity * 2 ? _size + len : _capacity * 2);
    }
    size_t end = _size + len;
    if (len == 0) return;
    while (end > pos + len - 1) {
        _str[end] = _str[end - len];
        --end;
    }
    for (size_t i = 0; i < len; ++i) {
        _str[pos + i] = str[i];
    }
    _size += len;
}

erase 的模拟实现

void string::erase(size_t pos, size_t len) {
    assert(pos < _size);
    if (len > _size - pos) {
        _str[pos] = '\0';
        _size = pos;
    } else {
        for (size_t i = pos + len; i <= _size; i++) {
            _str[i - len] = _str[i];
        }
        _size -= len;
    }
}

find 的模拟实现

size_t string::find(char ch, size_t pos) {
    for (size_t i = pos; i < _size; i++) {
        if (_str[i] == ch) return i;
    }
    return npos;
}

size_t string::find(const char* str, size_t pos) {
    assert(pos < _size);
    const char* ptr = strstr(_str + pos, str);
    if (ptr == nullptr) {
        return npos;
    } else {
        return ptr - _str;
    }
}

substr 的模拟实现

string string::substr(size_t pos, size_t len) {
    assert(pos < _size);
    if (len > _size - pos) {
        len = _size - pos;
    }
    string sub;
    sub.reserve(len);
    for (size_t i = 0; i < len; ++i) {
        sub += _str[pos + i];
    }
    return sub;
}

比较运算符的模拟实现

bool operator<(const string& s1, const string& s2) {
    return strcmp(s1.c_str(), s2.c_str()) < 0;
}
bool operator==(const string& s1, const string& s2) {
    return strcmp(s1.c_str(), s2.c_str()) == 0;
}
bool operator>(const string& s1, const string& s2) {
    return !(s1 < s2 || s1 == s2);
}
bool operator<=(const string& s1, const string& s2) {
    return s1 < s2 || s1 == s2;
}
bool operator>=(const string& s1, const string& s2) {
    return !(s1 < s2);
}
bool operator!=(const string& s1, const string& s2) {
    return !(s1 == s2);
}

流插入的模拟实现

ostream& operator<<(ostream& out, const string& s) {
    for (auto ch : s) {
        out << ch;
    }
    return out;
}

流提取的模拟实现

istream& operator>>(istream& in, string& s) {
    s.clear();
    const int N = 256;
    char buff[N];
    int i = 0;
    char ch;
    ch = in.get();
    while (ch != ' ' && ch != '\n') {
        buff[i++] = ch;
        if (i == N - 1) {
            buff[i] = '\0';
            s += buff;
            i = 0;
        }
        s += ch;
        ch = in.get();
        if (i > 0) {
            buff[i] = '\0';
            s += buff;
        }
    }
    return in;
}

完整代码

string.cpp

#include "string.h"
namespace bit {
void string::reserve(size_t n) {
    if (n > _capacity) {
        char* tmp = new char[n + 1];
        strcpy(tmp, _str);
        delete[] _str;
        _str = tmp;
        _capacity = n;
    }
}

void string::push_back(char ch) {
    if (_size == _capacity) {
        reserve(_capacity == 0 ? 4 : _capacity * 2);
    }
    _str[_size] = ch;
    ++_size;
    _str[_size] = '\0';
}

string& string::operator+=(char ch) {
    push_back(ch);
    return *this;
}

void string::append(const char* str) {
    size_t len = strlen(str);
    if (_size + len > _capacity) {
        reserve(_size + len > _capacity * 2 ? _size + len : _capacity * 2);
    }
    strcpy(_str + _size, str);
    _size += len;
}

string& string::operator+=(const char* str) {
    append(str);
    return *this;
}

void string::insert(size_t pos, char ch) {
    assert(pos <= _size);
    if (_size == _capacity) {
        reserve(_capacity == 0 ? 4 : _capacity * 2);
    }
    size_t end = _size + 1;
    while (end > pos) {
        _str[end] = _str[end - 1];
        --end;
    }
    _str[pos] = ch;
    ++_size;
}

void string::insert(size_t pos, const char* str) {
    assert(pos <= _size);
    size_t len = strlen(str);
    if (_size + len > _capacity) {
        reserve(_size + len > _capacity * 2 ? _size + len : _capacity * 2);
    }
    size_t end = _size + len;
    if (len == 0) return;
    while (end > pos + len - 1) {
        _str[end] = _str[end - len];
        --end;
    }
    for (size_t i = 0; i < len; ++i) {
        _str[pos + i] = str[i];
    }
    _size += len;
}

void string::erase(size_t pos, size_t len) {
    assert(pos < _size);
    if (len > _size - pos) {
        _str[pos] = '\0';
        _size = pos;
    } else {
        for (size_t i = pos + len; i <= _size; i++) {
            _str[i - len] = _str[i];
        }
        _size -= len;
    }
}

size_t string::find(char ch, size_t pos) {
    for (size_t i = pos; i < _size; i++) {
        if (_str[i] == ch) return i;
    }
    return npos;
}

size_t string::find(const char* str, size_t pos) {
    assert(pos < _size);
    const char* ptr = strstr(_str + pos, str);
    if (ptr == nullptr) {
        return npos;
    } else {
        return ptr - _str;
    }
}

string string::substr(size_t pos, size_t len) {
    assert(pos < _size);
    if (len > _size - pos) {
        len = _size - pos;
    }
    string sub;
    sub.reserve(len);
    for (size_t i = 0; i < len; ++i) {
        sub += _str[pos + i];
    }
    return sub;
}

void test_string1() {
    string s1;
    string s2("hello world");
    cout << s1.c_str() << endl;
    cout << s2.c_str() << endl;
    for (size_t i = 0; i < s2.size(); ++i) {
        s2[i] += 2;
    }
    cout << s2.c_str() << endl;
    for (auto e : s2) {
        cout << e << " ";
    }
    cout << endl;
    string::iterator it = s2.begin();
    while (it != s2.end()) {
        cout << *it << " ";
        ++it;
    }
}

void test_string2() {
    string s1("hello wwww");
    s1 += 'x';
    cout << s1.c_str() << endl;
    s1.insert(3, "sss");
    cout << s1.c_str() << endl;
    s1.erase(3, 2);
    cout << s1.c_str() << endl;
}

void test_string3() {
    string s("666.cpp.zip");
    size_t pos = s.find('.');
    string suffix = s.substr(pos);
    cout << suffix.c_str() << endl;
    string copy(s);
    cout << copy.c_str() << endl;
}

bool operator<(const string& s1, const string& s2) {
    return strcmp(s1.c_str(), s2.c_str()) < 0;
}

bool operator==(const string& s1, const string& s2) {
    return strcmp(s1.c_str(), s2.c_str()) == 0;
}

bool operator>(const string& s1, const string& s2) {
    return !(s1 < s2 || s1 == s2);
}

bool operator<=(const string& s1, const string& s2) {
    return s1 < s2 || s1 == s2;
}

bool operator>=(const string& s1, const string& s2) {
    return !(s1 < s2);
}

bool operator!=(const string& s1, const string& s2) {
    return !(s1 == s2);
}

ostream& operator<<(ostream& out, const string& s) {
    for (auto ch : s) {
        out << ch;
    }
    return out;
}

istream& operator>>(istream& in, string& s) {
    s.clear();
    const int N = 256;
    char buff[N];
    int i = 0;
    char ch;
    ch = in.get();
    while (ch != ' ' && ch != '\n') {
        buff[i++] = ch;
        if (i == N - 1) {
            buff[i] = '\0';
            s += buff;
            i = 0;
        }
        s += ch;
        ch = in.get();
        if (i > 0) {
            buff[i] = '\0';
            s += buff;
        }
    }
    return in;
}

void test_string4() {
    string s1("hello");
    cin >> s1;
    cout << s1 << endl;
    cout << "he";
}

int main() {
    bit::test_string4();
}
}

string.h

#pragma once
#include <iostream>
#include <assert.h>
#include <string.h>
using namespace std;

namespace bit {
class string {
public:
    typedef char* iterator;
    iterator begin() {
        return _str;
    }
    iterator end() {
        return _str + _size;
    }

    typedef const char* const_iterator;
    const_iterator begin() const {
        return _str;
    }
    const_iterator end() const {
        return _str + _size;
    }

    size_t capacity() const {
        return _capacity;
    }

    void reserve(size_t n);
    void push_back(char ch);
    void append(const char* str);
    string& operator+=(char ch);
    string& operator+=(const char* str);
    void insert(size_t pos, char ch);
    void insert(size_t pos, const char* str);
    void erase(size_t pos, size_t len = npos);
    size_t find(char ch, size_t pos = 0);
    size_t find(const char* str, size_t pos = 0);
    string substr(size_t pos = 0, size_t len = npos);

    string(const char* str = "") {
        _size = strlen(str);
        _capacity = _size;
        _str = new char[_capacity + 1];
        strcpy(_str, str);
    }

    string(const string& s) {
        string tmp(s._str);
        swap(tmp);
    }

    string& operator=(string tmp) {
        swap(tmp);
        return *this;
    }

    void swap(string& s) {
        std::swap(_str, s._str);
        std::swap(_size, s._size);
        std::swap(_capacity, s._capacity);
    }

    ~string() {
        delete[] _str;
        _str = nullptr;
        _capacity = _size = 0;
    }

    void clear() {
        _str[0] = '\0';
        _size = 0;
    }

    const char* c_str() const {
        return _str;
    }

    size_t size() const {
        return _size;
    }

    char& operator[](size_t pos) {
        assert(pos < _size);
        return _str[pos];
    }

    const char& operator[](size_t pos) const {
        assert(pos < _size);
        return _str[pos];
    }

private:
    char* _str = nullptr;
    size_t _size = 0;
    size_t _capacity = 0;

    static const size_t npos = -1;
};
}