从cppreference 示例开始
#include <iostream>
#include <regex>
void show_matches(const std::string& in, const std::string& re)
{
std::smatch m;
std::regex_search(in, m, std::regex(re));
if(m.empty()) {
std::cout << "input=[" << in << "], regex=[" << re << "]: NO MATCH\n";
} else {
std::cout << "input=[" << in << "], regex=[" << re << "]: ";
std::cout << "prefix=[" << m.prefix() << "] ";
for(std::size_t n = 0; n < m.size(); ++n)
std::cout << " m[" << n << "]=[" << m[n] << "] ";
std::cout << "suffix=[" << m.suffix() << "]\n";
}
}
int main()
{
// greedy match, repeats [a-z] 4 times
show_matches("abcdefghi", "(?:(?![aeiou])[a-z]){2,4}");
}
您可以在此处测试和检查正则表达式的详细信息。
选择使用非捕获组(?: ...)是为了防止它更改您的组，以防您在更大的正则表达式中使用它。
(?![aeiou])如果找到不匹配的字符，将匹配而不消耗输入[aeiou]，[a-z]则将匹配字母。结合这两个条件相当于你的字符类减法。
The{2,4}是一个量词，表示从 2 到 4，也可以+表示一个或多个，*表示零或多个。
编辑
阅读其他答案中的评论，我了解您想要支持XMLSchema。
下一个程序展示了如何使用 ECMA 正则表达式将“字符类差异”转换为 ECMA 兼容格式。
#include <iostream>
#include <regex>
#include <string>
#include <vector>
std::string translated_regex(const std::string &pattern){
// pattern to identify character class subtraction
std::regex class_subtraction_re(
"\\[((?:\\\\[\\[\\]]|[^[\\]])*)-\\[((?:\\\\[\\[\\]]|[^[\\]])*)\\]\\]"
);
// translate the regular expression to ECMA compatible
std::string translated = std::regex_replace(pattern,
class_subtraction_re, "(?:(?![$2])[$1])");
return translated;
}
void show_matches(const std::string& in, const std::string& re)
{
std::smatch m;
std::regex_search(in, m, std::regex(re));
if(m.empty()) {
std::cout << "input=[" << in << "], regex=[" << re << "]: NO MATCH\n";
} else {
std::cout << "input=[" << in << "], regex=[" << re << "]: ";
std::cout << "prefix=[" << m.prefix() << "] ";
for(std::size_t n = 0; n < m.size(); ++n)
std::cout << " m[" << n << "]=[" << m[n] << "] ";
std::cout << "suffix=[" << m.suffix() << "]\n";
}
}
int main()
{
std::vector<std::string> tests = {
"Some text [0-9-[4]] suffix",
"([abcde-[ae]])",
"[a-z-[aei]]|[A-Z-[OU]] "
};
std::string re = translated_regex("[a-z-[aeiou]]{2,4}");
show_matches("abcdefghi", re);
for(std::string test : tests){
std::cout << " " << test << '\n'
<< " -- " << translated_regex(test) << '\n';
}
return 0;
}
编辑：递归和命名字符类
上述方法不适用于递归字符类否定。并且没有办法仅使用正则表达式来处理递归替换。这使得解决方案变得不那么直接了。
解决方案有以下几个级别
- 一个函数扫描正则表达式以查找
[
- 当
[找到 a 时，有一个函数可以在找到 '-[` 时递归地处理字符类。
- 该模式
\p{xxxxx}被单独处理以识别命名字符模式。命名类在specialCharClass地图中定义，我填写了两个示例。
#include <iostream>
#include <regex>
#include <string>
#include <vector>
#include <map>
std::map<std::string, std::string> specialCharClass = {
{"IsDigit", "0-9"},
{"IsBasicLatin", "a-zA-Z"}
// Feel free to add the character classes you want
};
const std::string getCharClassByName(const std::string &pattern, size_t &pos){
std::string key;
while(++pos < pattern.size() && pattern[pos] != '}'){
key += pattern[pos];
}
++pos;
return specialCharClass[key];
}
std::string translate_char_class(const std::string &pattern, size_t &pos){
std::string positive;
std::string negative;
if(pattern[pos] != '['){
return "";
}
++pos;
while(pos < pattern.size()){
if(pattern[pos] == ']'){
++pos;
if(negative.size() != 0){
return "(?:(?!" + negative + ")[" + positive + "])";
}else{
return "[" + positive + "]";
}
}else if(pattern[pos] == '\\'){
if(pos + 3 < pattern.size() && pattern[pos+1] == 'p'){
positive += getCharClassByName(pattern, pos += 2);
}else{
positive += pattern[pos++];
positive += pattern[pos++];
}
}else if(pattern[pos] == '-' && pos + 1 < pattern.size() && pattern[pos+1] == '['){
if(negative.size() == 0){
negative = translate_char_class(pattern, ++pos);
}else{
negative += '|';
negative = translate_char_class(pattern, ++pos);
}
}else{
positive += pattern[pos++];
}
}
return '[' + positive; // there is an error pass, forward it
}
std::string translate_regex(const std::string &pattern, size_t pos = 0){
std::string r;
while(pos < pattern.size()){
if(pattern[pos] == '\\'){
r += pattern[pos++];
r += pattern[pos++];
}else if(pattern[pos] == '['){
r += translate_char_class(pattern, pos);
}else{
r += pattern[pos++];
}
}
return r;
}
void show_matches(const std::string& in, const std::string& re)
{
std::smatch m;
std::regex_search(in, m, std::regex(re));
if(m.empty()) {
std::cout << "input=[" << in << "], regex=[" << re << "]: NO MATCH\n";
} else {
std::cout << "input=[" << in << "], regex=[" << re << "]: ";
std::cout << "prefix=[" << m.prefix() << "] ";
for(std::size_t n = 0; n < m.size(); ++n)
std::cout << " m[" << n << "]=[" << m[n] << "] ";
std::cout << "suffix=[" << m.suffix() << "]\n";
}
}
int main()
{
std::vector<std::string> tests = {
"[a]",
"[a-z]d",
"[\\p{IsBasicLatin}-[\\p{IsDigit}-[89]]]",
"[a-z-[aeiou]]{2,4}",
"[a-z-[aeiou-[e]]]",
"Some text [0-9-[4]] suffix",
"([abcde-[ae]])",
"[a-z-[aei]]|[A-Z-[OU]] "
};
for(std::string test : tests){
std::cout << " " << test << '\n'
<< " -- " << translate_regex(test) << '\n';
// Construct a reegx (validate syntax)
std::regex(translate_regex(test));
}
std::string re = translate_regex("[a-z-[aeiou-[e]]]{2,10}");
show_matches("abcdefghi", re);
return 0;
}