C++Boost库操作字符串与正则

发表于 2021-02-27 更新于 2023-05-25 分类于《C/C++ 入门系列教程》

字符串的查找与替换一直是C++的若是，运用Boost这个准标准库，将可以很好的弥补C++的不足，使针对字符串的操作更加容易。

字符串格式转换:

#include <iostream>
#include <Windows.h>
#include <boost\lexical_cast.hpp>
#include <string>

using namespace std;
using namespace boost;

int main(int argc, char * argv[])
{
	string str[3] = { "100", "102", "3.14159" };

	// 字符串转换为数值类型
	std::cout << "字符串转为整数: " << lexical_cast<int>(str[0]) << std::endl;
	std::cout << "字符串转为长整数: " << lexical_cast<long>(str[1]) << std::endl;
	std::cout << "字符串转为浮点数: " << lexical_cast<float>(str[2]) << std::endl;

	// 数值类型转化为字符串
	std::cout << "数值转为字符串: " << lexical_cast<string>(100) << std::endl;
	std::cout << "十六进制转为十进制: " << lexical_cast<string>(0x10) << std::endl;

	system("pause");
	return 0;
}

format格式化：

#include <iostream>
#include <Windows.h>
#include <string>
#include <boost\format.hpp>

using namespace std;
using namespace boost;

int main(int argc, char * argv[])
{
	// 第一种输出方式: 直接填充字符串
	boost::format fmtA("姓名: %s -> 年龄: %d -> 性别: %s");
	fmtA %"lyshark";
	fmtA % 22;
	fmtA %"男";

	std::string str = fmtA.str();
	std::cout << "格式化后: " << str << std::endl;

	// 第二种方式: 拷贝的使用
	boost::format fmtB("姓名: %s -> 年龄: %d -> 性别: %s");
	cout << format(fmtB) % "lyshark" % 23 % "男" << std::endl;

	system("pause");
	return 0;
}

string_algo 大小写转化函数

#include <iostream>
#include <Windows.h>
#include <string>
#include <vector>
#include <boost\algorithm\string.hpp>

using namespace std;
using namespace boost;

int main(int argc, char * argv[])
{

	string str("readme.log");

	if (ends_with(str, "log"))
	{
		cout << "转化为大写: " << to_upper_copy(str) << endl;
		cout << "转化为小写: " << to_lower_copy(str) << endl;
	}

	// 替换开头
	replace_first(str, "readme", "lyshark");
	std::cout << "替换开头: " << str << std::endl;

	// 执行删除后缀
	vector<char> v(str.begin(), str.end());
	vector<char> v2 = to_upper_copy(erase_first_copy(v, ".log"));

	for (auto x : v2)
	{
		cout << x ;
	}


	system("pause");
	return 0;
}

判断类

#include <iostream>
#include <Windows.h>
#include <string>
#include <vector>
#include <boost\algorithm\string.hpp>

using namespace std;
using namespace boost;

int main(int argc, char * argv[])
{

	string str[6] = { "hello lyshark", "hello LyShark", "ABC", "ABC", "FCE" ,"lyshark"};

	cout << "大小写不敏感判断后缀: " << iends_with(str[0], "lyshark") << endl;
	cout << "大小写敏感判断前缀: " << starts_with(str[1], "Hello") << endl;

	cout << "测试包含关系: " << contains(str[0], str[5]) << endl;
	cout << "测试前5个字母是否为小写: " << all(str[0].substr(0, 5), is_lower()) << endl;

	
	is_any_of()
	system("pause");
	return 0;
}

修正

#include <iostream>
#include <string>

#include <boost\format.hpp>
#include <boost\algorithm\string.hpp>

using namespace std;
using namespace boost;

int main(int argc, char * argv[])
{

	string str[3] = { "hello LyShark", "hello LyShark", "lyshark" };

	cout << "大小写不敏感判断后缀: " << iends_with(str[0], "lyshark") << endl;
	cout << "大小写敏感判断前缀: " << starts_with(str[1], "Hello") << endl;

	cout << "测试包含关系: " << contains(str[0], str[2]) << endl;
	cout << "前5个字母是否为小写: " << all(str[0].substr(0, 5), is_lower()) << endl;
	cout << "前2个字符是否为字母: " << all(str[1].substr(0,2), is_alpha()) << endl;

	// 字符串修剪 去空格
	boost::format fmt("|%s|\n");
	std::string my_string = "   hello  lyshark   ";

	cout << "删除两端空格: " << fmt %trim_copy(my_string) << endl;
	cout << "删除左端空格: " << fmt %trim_left_copy(my_string) << endl;

	trim_right(my_string);
	cout << "原地删除右端空格: " << fmt %my_string << endl;

	// 字符串修建 去特殊符号
	std::string my_stringa = "2021 happy new Year !!!";

	cout << "删除左端数字: " << fmt %trim_left_copy_if(my_stringa, is_digit()) << endl;
	cout << "删除右端标点: " << fmt %trim_right_copy_if(my_stringa, is_punct()) << endl;
	cout << "删除两端(标点|数字|空格): " << trim_copy_if(my_stringa, is_punct() || is_digit() || is_space()) << endl;

	system("pause");
	return 0;
}

字符串查找

#include <iostream>
#include <string>

#include <boost\format.hpp>
#include <boost\algorithm\string.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	boost::format fmt("|%s|. pos = %d\n");
	std::string my_string = "Long long ago, there was Ago king as long.";

	iterator_range<std::string::iterator> reg;   // 定义迭代区间

	// 寻找第一次出现的位置(大小写敏感)
	reg = find_first(my_string, "Ago");
	cout << fmt %reg % (reg.begin() - my_string.begin()) << endl;

	// 寻找最后一次出现的位置(大小写不敏感)
	reg = ifind_last(my_string, "ago");
	cout << fmt %reg % (reg.begin() - my_string.begin()) << endl;

	// 寻找第三次出现long的位置(大小写不敏感)
	reg = ifind_nth(my_string, "long", 2);
	cout << fmt %reg % (reg.begin() - my_string.begin()) << endl;

	// 取前四个字符和后四个字符
	reg = find_head(my_string, 4);
	cout << fmt %reg % (reg.begin() - my_string.begin()) << endl;

	reg = find_tail(my_string, 4);
	cout << fmt %reg % (reg.begin() - my_string.begin()) << endl;

	// 找不到则输出
	reg = find_first(my_string, "lyshark");
	cout << "flag = " << (reg.empty() && !reg) << endl;


	getchar();
	return 0;
}

替换与删除 注意带有_copy的为拷贝，代表可以使用string变量来接收，不带的直接操作原始字符串。

#include <iostream>
#include <string>

#include <boost\format.hpp>
#include <boost\algorithm\string.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	boost::format fmt("|%s|. pos = %d\n");
	std::string my_string = "Long long ago, there was Ago king as long.";

	// 替换开头字符串(两种替换方式)
	std::string str_copy = replace_first_copy(my_string, "long", "LONG");
	cout << "替换后返回字符串: " << str_copy << endl;

	replace_first(my_string, "ago", "AGO");
	cout << "直接替换在原始字符串上: " << my_string << endl;

	// 替换开头或结尾前后5个字符
	replace_tail(my_string, 5, "lyshark");
	cout << "替换结尾5个字符: " << my_string << endl;
	replace_head(my_string, 5, "lyshark");
	cout << "替换开头5个字符: " << my_string << endl;

	// 替换第一次出现long的位置为AGES
	replace_nth(my_string, "long", 0, "AGES");
	cout << "第一次出现位置: " << my_string << endl;

	// 替换所有出现过的位置
	std::string str_copy_a = replace_all_copy(my_string, "lyshark", "LYSSHARK");
	cout << "替换所有位置: " << str_copy_a << endl;
	

	// 删除第1次出现was位置的字符串
	std::string del_str_copy = erase_nth_copy(my_string, "was", 0);
	cout << "删除后的字符串: " << del_str_copy << endl;

	// 删除字符串中所有的LYSSHARK
	erase_all(my_string, "LYSSHARK");
	cout << "删除后的字符串: " << my_string << endl;

	getchar();
	return 0;
}

切割合并字符串：

#include <iostream>
#include <string>
#include <algorithm>

#include <boost\algorithm\string.hpp>
#include <boost\assign.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	std::string my_string = "lyshark,Link.Zelda:Mario-Ligui+zelda,ZELDA";
	std::string my_string_b("hello||lyshark||welcome||link");

	// 查找字符串中的特定字符串
	deque<std::string> deq;

	ifind_all(deq, my_string, "zelda");
	cout << "查找字符串个数(不区分大小写): " << deq.size() << endl;
	if (deq.size() == 3)
	{
		for (auto each : deq)
			cout << "[ " << each << " ]" << endl;
	}

	// 切割字符串(1)
	list<iterator_range<std::string::iterator>> ptr;
	split(ptr, my_string, is_any_of(",.:-+"));
	for (auto each : ptr)
		cout << "[ " << each << " ]" << endl;

	// 切割字符串(2)
	ptr.clear();
	split(ptr, my_string, is_any_of(".:-"), token_compress_on);
	for (auto each : ptr)
		cout << "[ " << each << " ]" << endl;

	// 合并字符串
	std::vector<string> vct;

	vct.push_back("hello");
	vct.push_back("lyshark");
	cout << "用空格将其连接起来: " << join(vct, " ") << endl;

	// 查找迭代器的使用
	typedef find_iterator<string::iterator> string_find_iterator;
	string_find_iterator pos, end;
	for (pos = make_find_iterator(my_string_b, first_finder("lyshark", is_iequal())); pos != end; ++pos)
	{
		cout << "[ " << *pos << " ]" << endl;
	}

	// 分割迭代器的使用
	typedef split_iterator<string::iterator> string_split_iterator;
	string_split_iterator p, endp;
	for (p = make_split_iterator(my_string_b, first_finder("||", is_iequal())); p != endp; ++p)
	{
		cout << "[ " << *p << " ]" << endl;
	}

	getchar();
	return 0;
}

正则模块的使用:

正则匹配

#include <iostream>
#include <string>
#include <algorithm>

#include <boost\algorithm\string.hpp>
#include <boost\xpressive\xpressive.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	using namespace boost::xpressive;

	// 简单匹配字符串
	cregex regxA = cregex::compile("a.c");
	cout << "匹配字符串: " << regex_match("abd", regxA) << endl;

	std::string StringA = "hello lyshark a.c";
	cregex regxD = cregex::compile("a.c");
	cout << "匹配字符串: " << regex_match((char *)&StringA, regxD) << endl;

	// 数组方式引用正则
	cregex_compiler regc;

	regc["regxA"] = regc.compile("a|b|c");
	regc["regxB"] = regc.compile("\\d*");

	cout << regex_match("abcdefg", regc["regxA"]) << endl;
	cout << regex_match("123123", regc["regxB"]) << endl;

	// 使用C++ 11 匹配身份证
	cregex regxB = cregex::compile(R"---(\d{6}(1|2)\d{3}(0|1)\d[0-3]\d\d{3}(X|\d))---", icase);
	cout << "验证身份证: " << regex_match("513436200002247099", regxB) << endl;

	// 使用C++ 98 匹配身份证
	cregex regxC = cregex::compile("\\d{6}((1|2)\\d{3})((0|1)\\d)([0-3]\\d)(\\d{3}(X|\\d))", icase);
	cmatch what;

	regex_match("513436200002247099", what, regxC);
	for (auto &each : what)
	{
		cout << "[ " << each << " ]" << endl;
	}
	cout << "生日为: " << what[1] << what[3] << what[5] << endl;

	// 正则匹配开头结尾
	string StringB("lyshark.log");

	sregex start_regx = sregex::compile("^ly.*");
	cout << "匹配开头: " << regex_match(StringB, start_regx) << endl;

	sregex end_regx = sregex::compile(".*log$");
	cout << "匹配结尾: " << regex_match(StringB, end_regx) << endl;

	getchar();
	return 0;
}

正则查找替换

#include <iostream>
#include <string>
#include <algorithm>

#include <boost\algorithm\string.hpp>
#include <boost\xpressive\xpressive.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	using namespace boost::xpressive;

	// 正则查找特定字符串
	char my_stringA[] = "This is power-studio territory";

	cregex regx = cregex::compile("(power)-(.{6})", icase);
	cmatch what;
	regex_search(my_stringA, what, regx);
	if (what.size() != 0)
	{
		for (int x = 0; x < what.size(); x++)
		{
			cout << what[x] << endl;
		}
	}

	// 正则替换特定字符串
	std::string my_stringB = "2020 Happy New Year !!!";

	sregex regxA = sregex::compile("^(\\d| )*");    // 匹配开头数字
	sregex regxB = sregex::compile("!*$");         // 匹配末尾标点符号

	cout << regex_replace(my_stringB, regxA, "2021") << endl;
	cout << regex_replace(my_stringB, regxB, "") << endl;

	getchar();
	return 0;
}

正则迭代与分词

#include <iostream>
#include <string>
#include <algorithm>

#include <boost\algorithm\string.hpp>
#include <boost\xpressive\xpressive.hpp>
#include <boost\xpressive\regex_iterator.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{
	using namespace boost::xpressive;

	// 正则迭代输出
	std::string my_string_a = "power-shell, power-studio,power-engine,super-user";

	sregex regxA = sregex::compile("power-(\\w{5})", icase);

	sregex_iterator start_ptr(my_string_a.begin(), my_string_a.end(), regxA);
	sregex_iterator end_ptr;
	for (; start_ptr != end_ptr; ++start_ptr)
	{
		cout << "[ " << (*start_ptr)[0] << " ]" << endl;
	}

	// 正则分词
	char my_string_b[] = "*lyshark*||+administrator+||root!!||metaper";

	cregex regxB = cregex::compile("\\w+", icase);   // 过滤出所有的字母
	cregex_token_iterator pos(my_string_b, my_string_b + strlen(my_string_b), regxB);
	for (; pos != cregex_token_iterator(); ++pos)
	{
		cout << "[ " << *pos << " ]" << endl;
	}

	// 正则切割
	cregex split_regx = cregex::compile("\\|\\|");
	pos = cregex_token_iterator(my_string_b, my_string_b + strlen(my_string_b), split_regx, -1);
	for (; pos != cregex_token_iterator(); ++pos)
	{
		cout << "[ " << *pos << " ]" << endl;
	}
	
	
	// 正则格式化(小写转大写)
	struct formater
	{
		string operator()(cmatch const &m) const
		{
			return boost::to_upper_copy(m[0].str());
		}
	};

	char my_string_c[] = "*lyshark*||+administrator+||root!!||metaper";
	cregex regxC = cregex::compile("\\w+", icase);
	cout << regex_replace(my_string_c, regxC, formater()) << endl;
	

	getchar();
	return 0;
}

分词器使用:

#include <iostream>
#include <boost/tokenizer.hpp>

using namespace std;
using namespace boost;

int main(int argc, char const *argv[])
{

	std::string strTag = "explorer.exe,1024";

	// 定义分割符号为逗号与空格 定义分词器
	boost::char_separator<char> sep(", ");

	typedef boost::tokenizer<boost::char_separator<char>> CustonTokenizer;
	CustonTokenizer tok(strTag, sep);

	// 将分词结果放入vector链表
	std::vector<std::string> vecSegTag;
	for (CustonTokenizer::iterator beg = tok.begin(); beg != tok.end(); ++beg)
	{
		vecSegTag.push_back(*beg);
	}

	// const_case 将string转换为char 8
	std::string ref_string = const_cast<char *>(vecSegTag[0].c_str());

	cout <<"进程名: " << ref_string << endl;
	cout << "分词数: " << vecSegTag.size() << endl;
	getchar();
	return 0;
}