声明:本文目的是为探寻string的底层原理,而不是细扣每一个函数的具体实现
1.头文件(先参考用,下面会逐个分析)
#define _CRT_SECURE_NO_WARNINGS 1
#pragma once
#include<iostream>
#include<string>
#include<assert.h>
using namespace std;
namespace CC
{
class string
{
public:
typedef char* iterator;
typedef const char* const_iterator;
iterator begin()
{
return _str;
}
iterator end()
{
return _str + _size;
}
const_iterator begin() const
{
return _str;
}
const_iterator end() const
{
return _str + _size;
}
string(const char* str = "")
{
_size = strlen(str);
_capacity = _size;
_str = new char[_capacity + 1];
strcpy(_str, str);
}
~string()
{
delete[] _str;
_str = nullptr;
_size = _capacity = 0;
}
size_t size() const
{
return _size;
}
size_t capacity() const
{
return _capacity;
}
char& operator[](size_t pos)
{
assert(pos < _size);
return _str[pos];
}
const char& operator[](size_t pos) const
{
assert(pos < _size);
return _str[pos];
}
//深拷贝
string(const string& s)
{
_str = new char[s._capacity + 1];
strcpy(_str, s._str);
_size = s._size;
_capacity = s._capacity;
}
//赋值
string& operator=(const string& s)
{
if (this != &s)
{
delete[] _str;
_str = new char[s._capacity + 1];
strcpy(_str, s._str);
_size = s._size;
_capacity = s._capacity;
}
return *this;
}
//现代写法(深拷贝,赋值)
void swap(string& s)
{
std::swap(_str, s._str);
std::swap(_size, s._size);
std::swap(_capacity, s._capacity);
}
string(const string& s)
{
string tmp(s._str);
swap(tmp);
}
string& operator=(string tmp)
{
swap(tmp);
return *this;
}
//流提取前清除
void clear()
{
_str[0] = '\0';
_size = 0;
}
//兼容c_str()函数
const char* c_str() const
{
return _str;
}
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);
private:
char* _str = nullptr;
size_t _size = 0;
size_t _capacity = 0;
static const size_t npos;
};
bool operator<(const string& s1, const string& s2);
bool operator<=(const string& s1, const string& s2);
bool operator>(const string& s1, const string& s2);
bool operator>=(const string& s1, const string& s2);
bool operator==(const string& s1, const string& s2);
bool operator!=(const string& s1, const string& s2);
ostream& operator<<(ostream& out, const string& s);
istream& operator>>(istream& in, string& s);
}
1)私有成员
char* _str = nullptr;
size_t _size = 0;//长度
size_t _capacity = 0;//容量
static const size_t npos;
//npos=-1(后面会定义),为了后面的函数使用,其实就是return -1的作用
2)迭代器实现
typedef char* iterator;//普通迭代器
typedef const char* const_iterator;//常量迭代器
iterator begin()
{
return _str;
}
iterator end()
{
return _str + _size;
}
const_iterator begin() const
{
return _str;
}
const_iterator end() const
{
return _str + _size;
}
3)构造与析构
string(const char* str = "")//初始化为"\0"
{
_size = strlen(str);//这里用到了string.h里的函数
_capacity = _size;
_str = new char[_capacity + 1];//为"\0"预留空间
strcpy(_str, str);//将后者拷贝给前者
}
~string()
{
delete[] _str;//销毁
_str = nullptr;//置空
_size = _capacity = 0;
}
4)深拷贝与赋值
string(const string& s)
{
_str = new char[s._capacity + 1];//为新地址开空间
strcpy(_str, s._str);//依次将s的值赋给_str
_size = s._size;
_capacity = s._capacity;
}
string& operator=(const string& s)
{
if (this != &s)
{
delete[] _str;//销毁原有空间,再用新值覆盖
_str = new char[s._capacity + 1];
strcpy(_str, s._str);
_size = s._size;
_capacity = s._capacity;
}
return *this;
}
//这是比较质朴的写法,下面介绍一种简洁写法(效率上是没什么差别的)
void swap(string& s)
{
std::swap(_str, s._str);
std::swap(_size, s._size);
std::swap(_capacity, s._capacity);
}
string(const string& s)
{
string tmp(s._str);//深拷贝不能改变原有的值,所以要定义临时变量
swap(tmp);
}
string& operator=(string tmp)//这里其实相当于把s直接拷贝给了tmp,省了一步
{
swap(tmp);
return *this;
}
其余头文件内容都为一些函数声明与一些底层函数(浅显易懂),不做赘述
2.源文件
#include"string.h"
namespace CC
{
const size_t string::npos = -1;
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 (_capacity == _size)
{
reserve(_capacity == 0 ? 4 : 2 * _capacity);
}
_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 > 2 * _capacity ? _size + len : 2 * _capacity);
}
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);
reserve(_capacity == 0 ? 4 : 2 * _capacity);
size_t end = _size + 1;
while (pos < end)
{
_str[end] = _str[end - 1];
--end;
}
_str[pos] = ch;
++_size;
}
void string::insert(size_t pos, const char* s)
{
assert(pos < _size);
size_t len = strlen(s);
reserve(_size + len > 2 * _capacity ? _size + len : 2 * _capacity);
size_t end = _size + len;
while (pos + len - 1 < end)
{
_str[end] = _str[end - len];
--end;
}
for (size_t i = 0; i < len; i++)
{
_str[pos + i] = s[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)
{
assert(pos < _size);
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[i + pos];
}
return sub;
}
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);
}
bool operator>=(const string& s1, const string& s2)
{
return !(s1 < s2);
}
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);
}
ostream& operator<<(ostream& out, const string& s)
{
for (auto ch : s)
{
out << ch;
}
return out;
}
//istream& operator>>(istream& in, string& s)
//{
// s.clear();
// char ch;
// ch = in.get();
// while (ch != ' ' && ch != '\0')
// {
// s += ch;
// ch = in.get();
// }
// return in;
//}//此方法是从in中读取一个立即+=一个,效率较低
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 != '\0')
{
buff[i++] = ch;
if (i == n - 1)
{
buff[n] = '\0';
s += buff;
i = 0;
}
ch = in.get();
}
if (i > 0)
{
buff[i] = '\0';
s += buff;
}
return in;
}//创建了一个buff[]缓冲区,当buff[]储存满了再进行拷贝
}
1)reserve()扩容
void string::reserve(size_t n)
{
char* tmp = new char[n+1];
strcpy(tmp, _str);
delete[] _str;
_str = tmp;
_capacity = n;
}
const size_t string::npos = -1;//充当一个返回值
2)push_back()尾插 与 operator+=()
void string::push_back(char ch)//插入的是单个字符
{
if (_size == _capacity)
{
reserve(_capacity == 0 ? 4 : 2 * _capacity);
}
_str[_size] = ch;
_size++;
_str[_size] = '\0';
}
string& string::operator+=(char ch)
{
push_back(ch);
return *this;
}
3)append()尾插一个字符串 与 operator+=()
void string::append(const char* str)
{
size_t len = strlen(str);
if (len + _size > _capacity)
{
reserve(len + _size > 2 * _capacity ? _size + len : 2 * _capacity);
}
strcpy(_str + _size, str);
_size += len;
}
string& string::operator+=(const char* str)
{
append(str);
return *this;
}
4)insert()
void string::insert(size_t pos, char ch)
{
assert(pos < _size);
reserve(_capacity == 0 ? 4 : 2 * _capacity);
size_t end = _size + 1;
while (pos < end)
{
_str[end] = _str[end - 1];
end--;
}
_str[pos] = ch;
_size++;
}
void string::insert(size_t pos, const char* s)
{
assert(pos < _size);
size_t len = strlen(s);
reserve(_size + len > 2 * _capacity ? _size + len : 2 * _capacity);
size_t end = _size + len;
while (pos + len - 1 < end)//不要忘-1
{
_str[end] = _str[end - len];
--end;
}
for (size_t i = 0; i < len; i++)
{
_str[pos + i] = s[i];
}
_size += len;
}
-
这里不建议用strcpy()直接拷贝
-
使用for循环可以确保插入的字符串中如果包含了空字符('\0'),也能正确地复制到字符串中。而strcpy()函数会在遇到空字符时停止复制,可能会导致插入的字符串不完整。因此,为了保证插入的字符串完整地复制到目标位置,需要使用for循环逐个字符复制