C ++ 11 regex error

Just sample code from C++ Primer 5th Edition: 17.3.3. Using the Regular Expression Library

Main file main.cpp

:

#include <iostream>
#include "regexcase.h"
using namespace std;

int main() {
    using_regex();
    return 0;
}

      

Header file regexcase.h

:

#ifndef REGEXCASE_H_
#define REGEXCASE_H_

#include <regex>
#include <string>

void using_regex();
std::string parseCode(std::regex_constants::error_type etype);

#endif /* REGEXCASE_H_ */

      

Source file regexcase.cpp

:

#include "regexcase.h"
#include <iostream>
using namespace std;

void using_regex() {
    // look for words that violate a well-known spelling rule of thumb, "i before e, except after c":
    // find the characters ei that follow a character other than c
    string pattern("[^c]ei");
    // we want the whole word in which our pattern appears
    pattern = "[a-zA-Z]*" + pattern + "[a-zA-Z]*";  //[a-zA-Z]*   [[:alpha:]]*
    try {
        regex r(pattern, regex_constants::extended);    // construct a regex to find pattern                // , regex_constants::extended
        smatch results;     // define an object to hold the results of a search
        // define a string that has text that does and doesn't match pattern
        string test_str = "receipt freind theif receive";
        // use r to find a match to pattern in test_str
        if (regex_search(test_str, results, r)) // if there is a match
            cout << results.str() << endl;      // print the matching word
        else
            cout << "no match for " << pattern << endl;
    } catch (regex_error &e) {
        cout << "what: " << e.what() << "; code: " << parseCode(e.code()) << endl;
    }
}

string parseCode(regex_constants::error_type etype) {
    switch (etype) {
    case regex_constants::error_collate:
        return "error_collate: invalid collating element request";
    case regex_constants::error_ctype:
        return "error_ctype: invalid character class";
    case regex_constants::error_escape:
        return "error_escape: invalid escape character or trailing escape";
    case regex_constants::error_backref:
        return "error_backref: invalid back reference";
    case regex_constants::error_brack:
        return "error_brack: mismatched bracket([ or ])";
    case regex_constants::error_paren:
        return "error_paren: mismatched parentheses(( or ))";
    case regex_constants::error_brace:
        return "error_brace: mismatched brace({ or })";
    case regex_constants::error_badbrace:
        return "error_badbrace: invalid range inside a { }";
    case regex_constants::error_range:
        return "erro_range: invalid character range(e.g., [z-a])";
    case regex_constants::error_space:
        return "error_space: insufficient memory to handle this regular expression";
    case regex_constants::error_badrepeat:
        return "error_badrepeat: a repetition character (*, ?, +, or {) was not preceded by a valid regular expression";
    case regex_constants::error_complexity:
        return "error_complexity: the requested match is too complex";
    case regex_constants::error_stack:
        return "error_stack: insufficient memory to evaluate a match";
    default:
        return "";
    }
}

      

Call output using_regex();

iswhat: regex_error; code: error_brack: mismatched bracket([ or ])

It seems that the regex cannot parse the parenthesis.

Refer to the answers in this question , I use regex_constants::extended

to initialize a regex object which is thenregex r(pattern, regex_constants::extended);

Then the output no match for [[:alpha:]]*[^c]ei[[:alpha:]]*

It seems that the regex cannot match the pattern.

Then I use [a-zA-Z]*

to replace the character class [[:alpha:]]*

(with regex_constants::extended

still set). The output is stillno match for [a-zA-Z]*[^c]ei[a-zA-Z]*

Platform: windows

Used tools Eclipse for C/C++

:;MinGW (g++ --version: g++ 4.7.2)

EDIT : Thanks @sharth, add the main file to complete the code.

+3


source to share


1 answer


I just made a test using libc ++ and clang ++. This works as expected. Here's my main one:

int main() {
    string test_str = "receipt freind theif receive";
    string pattern = "[a-zA-Z]*[^c]ei[a-zA-Z]*";

    try {
        regex r(pattern, regex_constants::extended);
        smatch results;

        if (regex_search(test_str, results, r))
            cout << results.str() << endl;
        else
            cout << "no match for " << pattern << endl;
    } catch (regex_error &e) {
        cout << "what: " << e.what() << "; code: " << parseCode(e.code()) << endl;
    }
}

      

Output:

freind

      


On the other hand, GCC 4.7.2 gives the following output:



no match for [a-zA-Z]*[^c]ei[a-zA-Z]*

      

This is because in GCC 4.7.2 libstdC ++ they still don't implement regex. Here's the implementation regex_search

:

template<typename _Bi_iter, typename _Allocator, typename _Ch_type, typename _Rx_traits>
inline bool regex_search(_Bi_iter __first, _Bi_iter __last, match_results<_Bi_iter, _Allocator>& __m, const basic_regex<_Ch_type, _Rx_traits>& __re, regex_constants::match_flag_type __flags) {
    return false;
}

      


And just to point out, it's very helpful to include a little program that readers can compile. This way, there is no confusion about which code is being executed.

+4


source







All Articles