string类详解（下）

4. string类的模拟实现

首先，我们先补充一下关于编码的知识：

int main()
{
	char buff1[] = "abcd";
	char buff2[] = "比特";
	
	cout << sizeof(buff1) << endl;
	cout << sizeof(buff2) << endl;

	cout << buff1 << endl;
	cout << buff2 << endl;

	return 0;
}

如果严格按照标准的话，我们应该要实现成 basic_string ，但是这样难度太大，要考虑各种编码的拷贝，所以我们就实现的稍微简单一些，不要实现成模板了。

4.1 构造 + 析构

//string::string()
//{
//	_str = new char[1]{ '\0' };
//	_size = 0;
//	_capacity = 0;
//}

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

//s2(s1)
string::string(const string& s)
{
	_str = new char[s._capacity + 1];
	strcpy(_str, s._str);
	_size = s._size;
	_capacity = s._capacity;
}

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

4.2 c_str

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

4.3 下标遍历

size_t string::size() const
{
	return _size;
}

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

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

4.4 迭代器

string::iterator string::begin()
{
	return _str;
}

string::iterator string::end()
{
	return _str + _size;
}

string::const_iterator string::begin() const
{
	return _str;
}

string::const_iterator string::end() const
{
	return _str + _size;
}

4.5 插入

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)
	{
		size_t newcapacity = 0 == _capacity ? 4 : _capacity * 2;
		reserve(newcapacity);
	}

	_str[_size] = ch;
	_str[_size + 1] = '\0';
	++_size;
}

//"hello"  "xxxxxxxxxxxxx"
void string::append(const char* str)
{
	size_t len = strlen(str);
	if (_size + len > _capacity)
	{
		reserve(_size + len);
	}

	strcpy(_str + _size, str);
	_size += len;
}

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

void string::insert(size_t pos, char ch)
{
	assert(pos <= _size);

	if (_size == _capacity)
	{
		size_t newcapacity = 0 == _capacity ? 4 : _capacity * 2;
		reserve(newcapacity);
	}

	/*int end = _size;
	while (end >= (int)pos)
	{
		_str[end + 1] = _str[end];
		--end;
	}*/

	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);
	}

	/*int end = _size;
	while (end >= (int)pos)
	{
		_str[end + len] = _str[end];
		--end;
	}*/

	size_t end = _size + len;
	while (end > pos + len - 1)
	{
		_str[end] = _str[end - len];
		--end;
	}

	memcpy(_str + pos, str, len);
	_size += len;
}

4.6 删除

const size_t string::npos = -1;

void string::erase(size_t pos, size_t len)
{
	assert(pos < _size);

	//len 大于等于后面字符个数时，有多少删多少
	if (len >= _size - pos)
	{
		_str[pos] = '\0';
		_size = pos;
	}
	else
	{
		strcpy(_str + pos, _str + pos + len);
		_size -= len;
	}
}

4.7 查找

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)
{
	char* p = strstr(_str + pos, str);
	return p - _str;
}

4.8 赋值

//s1 = s3
//s1 = s1
string& string::operator=(const string& s)
{
	if (this != &s)
	{
		char* tmp = new char[s._capacity + 1];
		strcpy(tmp, s._str);
		delete[] _str;
		_str = tmp;
		_size = s._size;
		_capacity = s._capacity;
	}

	return *this;
}

4.9 交换

//s1.swap(s3)
void string::swap(string& s)
{
	std::swap(_str, s._str);
	std::swap(_size, s._size);
	std::swap(_capacity, s._capacity);
}

4.10 提取子串

string string::substr(size_t pos, size_t len)
{
	//len大于后面剩余字符，有多少取多少
	if (len > _size - pos)
	{
		string sub(_str + pos);
		return sub;
	}
	else
	{
		string sub;
		sub.reserve(len);
		for (size_t i = 0; i < len; i++)
		{
			sub += _str[pos + i];
		}

		return sub;
	}
}

4.11 比较大小

bool string::operator<(const string& s) const
{
	return strcmp(_str, s._str) < 0;
}

bool string::operator>(const string& s) const
{
	return !(*this <= s);
}

bool string::operator<=(const string& s) const
{
	return *this < s || *this == s;
}

bool string::operator>=(const string& s) const
{
	return !(*this < s);
}

bool string::operator==(const string& s) const
{
	return strcmp(_str, s._str) == 0;
}

bool string::operator!=(const string& s) const
{
	return !(*this == s);
}

4.12 流插入 && 流提取

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

//一个字符一个字符放入str里，会有很多次扩容，可以优化
//istream& operator>> (istream& is, string& str)
//{
//	str.clear();

//	//流提取（>>）提取不了空格和换行，istream里的函数get()可以
//	char ch = is.get();
//	while (ch != ' ' && ch != '\n')
//	{
//		str += ch;
//		ch = is.get();
//	}

//	return is;
//}

istream& operator>> (istream& is, string& str)
{
	str.clear();

	char buff[128];
	int i = 0;
	char ch = is.get();
	while (ch != ' ' && ch != '\n')
	{
		buff[i++] = ch;

		// 0 - 126
		if (i == 127)
		{
			buff[i] = '\0';
			str += buff;
			i = 0;
		}

		ch = is.get();
	}

	if (i != 0)
	{
		buff[i] = '\0';
		str += buff;
	}

	return is;
}

ostream& operator<< (ostream& os, const string& str)
{
	for (size_t i = 0; i < str.size(); i++)
	{
		os << str[i];
	}

	return os;
}

5. 现代版写法的String类

我们之前写的拷贝构造和赋值运算符重载是传统写法，其实还有现代写法：

//现代写法（让别人干活，交换）
//s2(s1)
string::string(const string& s)
{
	string tmp(s._str);
	/*std::swap(tmp._str, _str);
	std::swap(tmp._size, _size);
	std::swap(tmp._capacity, _capacity);*/
	
	//这个是我们写的string类里的交换函数
	swap(tmp);
}

/*string& string::operator=(const string& s)
{
	if (this != &s)
	{
		string tmp(s._str);
		swap(tmp);
	}

	return *this;
}*/

//s1 = s3
string& string::operator=(string tmp)
{
	swap(tmp);

	return *this;
}

5.1 完整代码

//string.h

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

namespace bit
{
	class string
	{
	public:
		typedef char* iterator;
		typedef const char* const_iterator;

		iterator begin();
		iterator end();

		const_iterator begin() const;
		const_iterator end() const;

		//string();
		string(const char* str = "");
		string(const string& s);
		//string& operator=(const string& s);
		string& operator=(string tmp);
		~string();
		
		const char* c_str() const;
		
		size_t size() const;
		char& operator[](size_t pos);
		const char& operator[](size_t pos) const;

		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 = 0, size_t len = npos);

		size_t find(char ch, size_t pos = 0);
		size_t find(const char* str, size_t pos =  0);

		void swap(string& s);
		string substr(size_t pos = 0, size_t len = npos);

		bool operator<(const string& s) const;
		bool operator>(const string& s) const;
		bool operator<=(const string& s) const;
		bool operator>=(const string& s) const;
		bool operator==(const string& s) const;
		bool operator!=(const string& s) const;
		void clear();

	private:
		//char _buff[16];

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

		const static size_t npos;
		
		//特例，const静态成员变量只有整型可以这样声明定义（了解即可，不建议这样写）
		//const static size_t npos = -1;
		
		//不支持
		//const static double N = 2.2;
	};

	istream& operator>> (istream& is, string& str);
	ostream& operator<< (ostream& os, const string& str);
}

//string.cpp

#include "string.h"

namespace bit
{
	const size_t string::npos = -1;

	//string::string()
	//{
	//	_str = new char[1]{ '\0' };
	//	_size = 0;
	//	_capacity = 0;
	//}

	string::iterator string::begin()
	{
		return _str;
	}

	string::iterator string::end()
	{
		return _str + _size;
	}

	string::const_iterator string::begin() const
	{
		return _str;
	}

	string::const_iterator string::end() const
	{
		return _str + _size;
	}

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

	//传统写法（实在人）
	//s2(s1)
	/*string::string(const string& s)
	{
		_str = new char[s._capacity + 1];
		strcpy(_str, s._str);
		_size = s._size;
		_capacity = s._capacity;
	}*/

	//现代写法（让别人干活，交换）
	//s2(s1)
	string::string(const string& s)
	{
		string tmp(s._str);
		/*std::swap(tmp._str, _str);
		std::swap(tmp._size, _size);
		std::swap(tmp._capacity, _capacity);*/
		
		//这个是我们写的string类里的交换函数
		swap(tmp);
	}

	//s1 = s3
	//s1 = s1
	/*string& string::operator=(const string& s)
	{
		if (this != &s)
		{
			char* tmp = new char[s._capacity + 1];
			strcpy(tmp, s._str);
			delete[] _str;
			_str = tmp;
			_size = s._size;
			_capacity = s._capacity;
		}

		return *this;
	}*/

	/*string& string::operator=(const string& s)
	{
		if (this != &s)
		{
			string tmp(s._str);
			swap(tmp);
		}

		return *this;
	}*/
	
	//s1 = s3
	string& string::operator=(string tmp)
	{
		swap(tmp);

		return *this;
	}

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

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

	size_t string::size() const
	{
		return _size;
	}

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

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

	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)
		{
			size_t newcapacity = 0 == _capacity ? 4 : _capacity * 2;
			reserve(newcapacity);
		}

		_str[_size] = ch;
		_str[_size + 1] = '\0';
		++_size;*/

		insert(_size, ch);
	}

	//"hello"  "xxxxxxxxxxxxx"
	void string::append(const char* str)
	{
		/*size_t len = strlen(str);
		if (_size + len > _capacity)
		{
			reserve(_size + len);
		}

		strcpy(_str + _size, str);
		_size += len;*/

		insert(_size, str);
	}

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

	void string::insert(size_t pos, char ch)
	{
		assert(pos <= _size);

		if (_size == _capacity)
		{
			size_t newcapacity = 0 == _capacity ? 4 : _capacity * 2;
			reserve(newcapacity);
		}

		/*int end = _size;
		while (end >= (int)pos)
		{
			_str[end + 1] = _str[end];
			--end;
		}*/

		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);
		}

		/*int end = _size;
		while (end >= (int)pos)
		{
			_str[end + len] = _str[end];
			--end;
		}*/

		size_t end = _size + len;
		while (end > pos + len - 1)
		{
			_str[end] = _str[end - len];
			--end;
		}

		memcpy(_str + pos, str, len);
		_size += len;
	}

	void string::erase(size_t pos, size_t len)
	{
		assert(pos < _size);

		//len 大于等于后面字符个数时，有多少删多少
		if (len >= _size - pos)
		{
			_str[pos] = '\0';
			_size = pos;
		}
		else
		{
			strcpy(_str + pos, _str + pos + len);
			_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)
	{
		char* p = strstr(_str + pos, str);
		return p - _str;
	}

	//s1.swap(s3)
	void string::swap(string& s)
	{
		std::swap(_str, s._str);
		std::swap(_size, s._size);
		std::swap(_capacity, s._capacity);
	}

	string string::substr(size_t pos, size_t len)
	{
		//len大于后面剩余字符，有多少取多少
		if (len > _size - pos)
		{
			string sub(_str + pos);
			return sub;
		}
		else
		{
			string sub;
			sub.reserve(len);
			for (size_t i = 0; i < len; i++)
			{
				sub += _str[pos + i];
			}

			return sub;
		}
	}

	bool string::operator<(const string& s) const
	{
		return strcmp(_str, s._str) < 0;
	}

	bool string::operator>(const string& s) const
	{
		return !(*this <= s);
	}

	bool string::operator<=(const string& s) const
	{
		return *this < s || *this == s;
	}

	bool string::operator>=(const string& s) const
	{
		return !(*this < s);
	}
	
	bool string::operator==(const string& s) const
	{
		return strcmp(_str, s._str) == 0;
	}

	bool string::operator!=(const string& s) const
	{
		return !(*this == s);
	}

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

	//一个字符一个字符放入str里，会有很多次扩容，可以优化
	//istream& operator>> (istream& is, string& str)
	//{
	//	str.clear();

	//	//流提取（>>）提取不了空格和换行，istream里的函数get()可以
	//	char ch = is.get();
	//	while (ch != ' ' && ch != '\n')
	//	{
	//		str += ch;
	//		ch = is.get();
	//	}

	//	return is;
	//}

	istream& operator>> (istream& is, string& str)
	{
		str.clear();

		char buff[128];
		int i = 0;
		char ch = is.get();
		while (ch != ' ' && ch != '\n')
		{
			buff[i++] = ch;

			// 0 - 126
			if (i == 127)
			{
				buff[i] = '\0';
				str += buff;
				i = 0;
			}

			ch = is.get();
		}

		if (i != 0)
		{
			buff[i] = '\0';
			str += buff;
		}

		return is;
	}

	ostream& operator<< (ostream& os, const string& str)
	{
		for (size_t i = 0; i < str.size(); i++)
		{
			os << str[i];
		}

		return os;
	}
}

//Test.cpp

#include "string.h"

namespace bit
{
	void test_string1()
	{
		string s1("hello world");
		cout << s1.c_str() << endl;

		for (size_t i = 0; i < s1.size(); i++)
		{
			s1[i]++;
		}

		for (size_t i = 0; i < s1.size(); i++)
		{
			cout << s1[i] << " ";
		}
		cout << endl;

		//封装：统一屏蔽了底层实现细节，提供了一种简单通用的访问容器的方式
		string::iterator it1 = s1.begin();
		while (it1 != s1.end())
		{
			cout << *it1 << " ";
			++it1;
		}
		cout << endl;

		for (auto e : s1)
		{
			cout << e << " ";
		}
		cout << endl;

		string s2;
		cout << s2.c_str() << endl;

		const string s3("xxxxxxx");

		string::const_iterator it3 = s3.begin();
		while (it3 != s3.end())
		{
			//*it3 = 'y';//err

			cout << *it3 << " ";
			++it3;
		}
		cout << endl;

		for (size_t i = 0; i < s3.size(); i++)
		{
			//s3[i]++;
			cout << s3[i] << " ";
		}
		cout << endl;
	}

	void test_string2()
	{
		string s1("hello world");
		cout << s1.c_str() << endl;
	
		s1.push_back('x');
		cout << s1.c_str() << endl;
		
		s1.append("yyyyy");
		cout << s1.c_str() << endl;
	
		s1 += 'z';
		s1 += "mmmmmm";
		cout << s1.c_str() << endl;
	}

	void test_string3()
	{
		string s1("hello world");
		cout << s1.c_str() << endl;

		s1.insert(6, 'x');
		cout << s1.c_str() << endl;

		s1.insert(0, 'x');
		cout << s1.c_str() << endl;
	
		string s2("hello world");
		cout << s2.c_str() << endl;

		s2.insert(6, "yyy");
		cout << s2.c_str() << endl;

		s2.insert(0, "yyy");
		cout << s2.c_str() << endl;

		string s3("hello world");
		cout << s3.c_str() << endl;
		//s3.erase(6, 10);
		s3.erase(6);
		cout << s3.c_str() << endl;

		string s4("hello world");
		cout << s4.c_str() << endl;
		s4.erase(6, 3);
		cout << s4.c_str() << endl;
	}

	void test_string4()
	{
		string s1("hello world");
		cout << s1.find('o') << endl;
		cout << s1.find("wor") << endl;
	}

	void test_string5()
	{
		string s1("hello world");
		string s2(s1);

		s1[0] = 'x';
		cout << s1.c_str() << endl;
		cout << s2.c_str() << endl;
	
		string s3("yyyy");
		s1 = s3;
		cout << s1.c_str() << endl;
		cout << s3.c_str() << endl;
	
		string s4("zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz");
		s1 = s4;
		cout << s1.c_str() << endl;
		cout << s4.c_str() << endl;
	
		s1 = s1;
		cout << s1.c_str() << endl;
		cout << s3.c_str() << endl;
		
		std::swap(s1, s3);
		cout << s1.c_str() << endl;
		cout << s3.c_str() << endl;

		s1.swap(s3);
		cout << s1.c_str() << endl;
		cout << s3.c_str() << endl;
	}

	void test_string6()
	{
		string url("https://gitee.com/ailiangshilove/cpp-class/blob/master/%E8%AF%BE%E4%BB%B6%E4%BB%A3%E7%A0%81/C++%E8%AF%BE%E4%BB%B6V6/string%E7%9A%84%E6%8E%A5%E5%8F%A3%E6%B5%8B%E8%AF%95%E5%8F%8A%E4%BD%BF%E7%94%A8/TestString.cpp");
		size_t pos1 = url.find(':');
		string url1 = url.substr(0, pos1 - 0);
		cout << url1.c_str() << endl;

		size_t pos2 = url.find('/', pos1 + 3);
		string url2 = url.substr(pos1 + 3, pos2 - (pos1 + 3));
		cout << url2.c_str() << endl;

		string url3 = url.substr(pos2 + 1);
		cout << url3.c_str() << endl;
	}

	void test_string7()
	{
		//string s1("hello world");
		//cout << s1 << endl;
		
		string s1;
		cin >> s1;
		cout << s1 << endl;
	}

	void test_string8()
	{
		string s1("hello world");
		string s2(s1);
		cout << s1 << endl;
		cout << s2 << endl;

		string s3("xxxxxxxxxxxxxxxxxxxxxxxxx");
		s1 = s3;
		cout << s1 << endl;
		cout << s3 << endl;
	}
}

int main()
{
	bit::test_string8();

	return 0;
}

6. 写时拷贝（了解）

写时拷贝就是一种拖延症，是在浅拷贝的基础之上增加了引用计数的方式来实现的。

引用计数：用来记录资源使用者的个数。在构造时，将资源的计数给成1，每增加一个对象使用该资源，就给计数增加1，当某个对象被销毁时，先给该计数减1，然后再检查是否需要释放资源，如果计数为1，说明该对象时资源的最后一个使用者，将该资源释放；否则就不能释放，因为还有其他对象在使用该资源。

举个例子：

void copy_on_write()
{
	//如果计数不等于1，再去做深拷贝
}

void string::push_back(char ch)
{
	//写时拷贝
	copy_on_write();

	/*if (_size == _capacity)
	{
		size_t newcapacity = 0 == _capacity ? 4 : _capacity * 2;
		reserve(newcapacity);
	}

	_str[_size] = ch;
	_str[_size + 1] = '\0';
	++_size;*/

	insert(_size, ch);
}

可以用下面的代码来看是否是用了写时拷贝：

void test_string9()
{
	std::string s1("hello world");
	std::string s2(s1);

	cout << (void*)s1.c_str() << endl;
	cout << (void*)s2.c_str() << endl;
}

Windows的VS下没有用写时拷贝，而Linux的g++就使用了写时拷贝。