c++ - 使用正则表达式匹配和提取数据

Question

问题:找到匹配的字符串并从匹配的字符串中提取数据。有许多带有关键字和数据的命令字符串。

命令示例:

1. 问名字给我打电话
2. 通知执行此操作的名称
3. 请求的消息名称

关键词:Ask, Notify, Message, to, that。数据:

输入字符串:

1. 让彼得给我打电话
2. 通知珍娜我要离开
3. 告诉家里我要迟到了

我的问题由两个问题组成1)查找匹配命令2)提取数据

这是我正在做的:我创建了多个正则表达式:"Ask[[:s:]][[:w:]]+[[:s:]]to[[:s:]][[:w:]]+"或 "Ask([^\t\n]+?)到([^\t\n]+?)""Notify[[:s:]][[:w:]]+[[:s:]]that[[:s:]][[:w:]]+"或 "Notify([^\t\n]+?)那([^\t\n]+?)"

void searchExpression(const char *regString)
{
    std::string str;
    boost::regex callRegEx(regString, boost::regex_constants::icase);
    boost::cmatch im;

    while(true) {
       std::cout << "Enter String: ";
       getline(std::cin, str);
       fprintf(stderr, "str %s regstring %s\n", str.c_str(), regString);

       if(boost::regex_search(str.c_str(), im, callRegEx)) {
             int num_var = im.size() + 1;
             fprintf(stderr, "Matched num_var %d\n", num_var);
             for(int j = 0; j <= num_var; j++) {
                    fprintf(stderr, "%d) Found %s\n",j, std::string(im[j]).c_str());
             }
      }
      else {
          fprintf(stderr, "Not Matched\n");
      }
   }
}

我能够找到匹配的字符串，但我无法提取数据。这是输出:

input_string: Ask peter to call Regex Ask[[:s:]][[:w:]]+[[:s:]]to[[:s:]][[:w:]]+
Matched num_var 2
0) Found Ask peter to call
1) Found
2) Found

我想从 Ask Peter to call 中提取 peter 和 call。

Answer 1

既然你真的想解析一个语法，你应该考虑使用 Boost 的解析器生成器。

您只需自上而下地编写整个内容:

auto sentence  = [](auto&& v, auto&& p) { 
    auto verb     = lexeme [ no_case [  as_parser(v) ] ];
    auto name     = lexeme [ +graph ];
    auto particle = lexeme [ no_case [  as_parser(p) ] ];
    return confix(verb, particle) [ name ]; 
};

auto ask     = sentence("ask",     "to")   >> lexeme[+char_];
auto notify  = sentence("notify",  "that") >> lexeme[+char_];
auto message = sentence("message", "that") >> lexeme[+char_];

auto command = ask | notify | message;

这是它的 Spirit X3 语法。将 lexeme 读作“保留整个单词”(不要忽略空格)。

在这里，“名称”被认为是任何符合预期的粒子¹

如果你只想返回匹配的原始字符串，这就足够了:

Live On Coliru

#include <iostream>
#include <boost/spirit/home/x3.hpp>
#include <boost/spirit/home/x3/directive/confix.hpp>

namespace x3 = boost::spirit::x3;

namespace commands {
    namespace grammar {
        using namespace x3;

        auto sentence  = [](auto&& v, auto&& p) { 
            auto verb     = lexeme [ no_case [  as_parser(v) ] ];
            auto name     = lexeme [ +graph ];
            auto particle = lexeme [ no_case [  as_parser(p) ] ];
            return confix(verb, particle) [ name ]; 
        };

        auto ask     = sentence("ask",     "to")   >> lexeme[+char_];
        auto notify  = sentence("notify",  "that") >> lexeme[+char_];
        auto message = sentence("message", "that") >> lexeme[+char_];

        auto command = ask | notify | message;

        auto parser  = raw [ skip(space) [ command ] ];
    }
}

int main() {
    for (std::string const input : {
            "Ask peter to call me",
            "Notify Jenna that I am going to be away",
            "Message home that I am running late",
            })
    {
        std::string matched;

        if (parse(input.begin(), input.end(), commands::grammar::parser, matched))
            std::cout << "Matched: '" << matched << "'\n";
        else
            std::cout << "No match in '" << input << "'\n";
    }

}

打印:

Matched: 'Ask peter to call me'
Matched: 'Notify Jenna that I am going to be away'
Matched: 'Message home that I am running late'

奖金

当然，您实际上想要提取相关信息。

这是我该的做法。让我们解析成一个结构:

struct Command {
    enum class Type { ask, message, notify } type;
    std::string name;
    std::string message;
};

让我们把 main() 写成:

commands::Command cmd;

if (parse(input.begin(), input.end(), commands::grammar::parser, cmd))
    std::cout << "Matched: " << cmd.type << "|" << cmd.name << "|" << cmd.message << "\n";
else
    std::cout << "No match in '" << input << "'\n";

Live On Coliru

#include <iostream>
#include <boost/fusion/adapted/struct.hpp>
#include <boost/spirit/home/x3.hpp>
#include <boost/spirit/home/x3/directive/confix.hpp>

namespace x3 = boost::spirit::x3;

namespace commands {

    struct Command {
        enum class Type { ask, message, notify } type;
        std::string name;
        std::string message;

        friend std::ostream& operator<<(std::ostream& os, Type t) { return os << static_cast<int>(t); } // TODO
    };

}

BOOST_FUSION_ADAPT_STRUCT(commands::Command, type, name, message)

namespace commands {

    namespace grammar {
        using namespace x3;

        auto sentence  = [](auto type, auto&& v, auto&& p) { 
            auto verb     = lexeme [ no_case [  as_parser(v) ] ];
            auto name     = lexeme [ +graph ];
            auto particle = lexeme [ no_case [  as_parser(p) ] ];
            return attr(type) >> confix(verb, particle) [ name ]; 
        };

        using Type = Command::Type;
        auto ask     = sentence(Type::ask,     "ask",     "to")   >> lexeme[+char_];
        auto notify  = sentence(Type::notify,  "notify",  "that") >> lexeme[+char_];
        auto message = sentence(Type::message, "message", "that") >> lexeme[+char_];

        auto command // = rule<struct command, Command> { }
                     = ask | notify | message;

        auto parser  = skip(space) [ command ];
    }
}

int main() {
    for (std::string const input : {
            "Ask peter to call me",
            "Notify Jenna that I am going to be away",
            "Message home that I am running late",
            })
    {
        commands::Command cmd;

        if (parse(input.begin(), input.end(), commands::grammar::parser, cmd))
            std::cout << "Matched: " << cmd.type << "|" << cmd.name << "|" << cmd.message << "\n";
        else
            std::cout << "No match in '" << input << "'\n";
    }

}

打印

Matched: 0|peter|call me
Matched: 2|Jenna|I am going to be away
Matched: 1|home|I am running late

---

¹ 我不是英语语言学家，所以我不知道这是否是正确的语法术语 :)