我目前正在开发一个 C++ 预处理器，我需要匹配超过 0 个字母的字符串常量，如 "hey I'm a string .
我目前正在这里使用这个 \"([^\\\"]+|\\.)+\"但它在我的一个测试用例中失败了。

测试用例:

std::cout << "hello" << " world";
std::cout << "He said: \"bananas\"" << "...";
std::cout << "";
std::cout << "\x12\23\x34";

std::cout << String("hello") << String(" world");
std::cout << String("He said: \"bananas\"") << String("...");
std::cout << "";
std::cout << String("\x12\23\x34");

std::cout << String("He said: \")bananas\"String(" << ")...";

std::string in_line = "std::cout << \"He said: \\\"bananas\\\"\" << \"...\";";
std::regex r("\"([^\"]+|\\.|(?<=\\\\)\")+\"");
in_line = std::regex_replace(in_line, r, "String($&)");

最佳答案

对源文件进行词法分析对于正则表达式来说是一项很好的工作。但是对于这样的任务，让我们使用比 std::regex 更好的正则表达式引擎.让我们首先使用 PCRE(或 boost::regex)。在这篇文章的最后，我将展示您可以使用功能较少的引擎做什么。

我们只需要进行部分词法分析，忽略所有不会影响字符串文字的无法识别的标记。我们需要处理的是:

The characters /* start a comment, which terminates with the characters */. These comments do not nest. The characters // start a comment, which terminates immediately before the next new-line character. If there is a form-feed or a vertical-tab character in such a comment, only white-space characters shall appear between it and the new-line that terminates the comment; no diagnostic is required. [ Note: The comment characters //, /*, and */ have no special meaning within a // comment and are treated just like other characters. Similarly, the comment characters // and /* have no special meaning within a /* comment. — end note ]

# singleline comment
// .* (*SKIP)(*FAIL)

# multiline comment
| /\* (?s: .*? ) \*/ (*SKIP)(*FAIL)

 character-literal:  
    encoding-prefix(opt) ’ c-char-sequence ’
  encoding-prefix:
    one of u8 u U L
  c-char-sequence:
    c-char
    c-char-sequence c-char
  c-char:
    any member of the source character set except the single-quote ’, backslash \, or new-line character
    escape-sequence
    universal-character-name
  escape-sequence:
    simple-escape-sequence
    octal-escape-sequence
    hexadecimal-escape-sequence
  simple-escape-sequence: one of \’ \" \? \\ \a \b \f \n \r \t \v
  octal-escape-sequence:
    \ octal-digit
    \ octal-digit octal-digit
    \ octal-digit octal-digit octal-digit
  hexadecimal-escape-sequence:
    \x hexadecimal-digit
    hexadecimal-escape-sequence hexadecimal-digit

(?(DEFINE)
  (?<prefix> (?:u8?|U|L)? )
  (?<escape> \\ (?:
    ['"?\\abfnrtv]         # simple escape
    | [0-7]{1,3}           # octal escape
    | x [0-9a-fA-F]{1,2}   # hex escape
    | u [0-9a-fA-F]{4}     # universal character name
    | U [0-9a-fA-F]{8}     # universal character name
  ))
)

(?&prefix) ' (?> (?&escape) | [^'\\\r\n]+ )+ ' (*SKIP)(*FAIL)

  string-literal:
    encoding-prefix(opt) " s-char-sequence(opt) "
    encoding-prefix(opt) R raw-string
  s-char-sequence:
    s-char
    s-char-sequence s-char
  s-char:
    any member of the source character set except the double-quote ", backslash \, or new-line character
    escape-sequence
    universal-character-name

(?&prefix) " (?> (?&escape) | [^"\\\r\n]+ )* "

  raw-string:
    " d-char-sequence(opt) ( r-char-sequence(opt) ) d-char-sequence(opt) "
  r-char-sequence:
    r-char
    r-char-sequence r-char
  r-char:
    any member of the source character set, except a right parenthesis )
    followed by the initial d-char-sequence (which may be empty) followed by a double quote ".
  d-char-sequence:
    d-char
    d-char-sequence d-char
  d-char:
    any member of the basic source character set except:
    space, the left parenthesis (, the right parenthesis ), the backslash \,
    and the control characters representing horizontal tab,
    vertical tab, form feed, and newline.

(?&prefix) R " (?<delimiter>[^ ()\\\t\x0B\r\n]*) \( (?s:.*?) \) \k<delimiter> "

(?(DEFINE)
  (?<prefix> (?:u8?|U|L)? )
  (?<escape> \\ (?:
    ['"?\\abfnrtv]         # simple escape
    | [0-7]{1,3}           # octal escape
    | x [0-9a-fA-F]{1,2}   # hex escape
    | u [0-9a-fA-F]{4}     # universal character name
    | U [0-9a-fA-F]{8}     # universal character name
  ))
)

# singleline comment
// .* (*SKIP)(*FAIL)

# multiline comment
| /\* (?s: .*? ) \*/ (*SKIP)(*FAIL)

# character literal
| (?&prefix) ' (?> (?&escape) | [^'\\\r\n]+ )+ ' (*SKIP)(*FAIL)

# standard string
| (?&prefix) " (?> (?&escape) | [^"\\\r\n]+ )* "

# raw string
| (?&prefix) R " (?<delimiter>[^ ()\\\t\x0B\r\n]*) \( (?s:.*?) \) \k<delimiter> "

#include <string>
#include <iostream>
#include <boost/regex.hpp>

static void test()
{
    boost::regex re(R"regex(
        (?(DEFINE)
          (?<prefix> (?:u8?|U|L) )
          (?<escape> \\ (?:
            ['"?\\abfnrtv]         # simple escape
            | [0-7]{1,3}           # octal escape
            | x [0-9a-fA-F]{1,2}   # hex escape
            | u [0-9a-fA-F]{4}     # universal character name
            | U [0-9a-fA-F]{8}     # universal character name
          ))
        )

        # singleline comment
        // .* (*SKIP)(*FAIL)

        # multiline comment
        | /\* (?s: .*? ) \*/ (*SKIP)(*FAIL)

        # character literal
        | (?&prefix)? ' (?> (?&escape) | [^'\\\r\n]+ )+ ' (*SKIP)(*FAIL)

        # standard string
        | (?&prefix)? " (?> (?&escape) | [^"\\\r\n]+ )* "

        # raw string
        | (?&prefix)? R " (?<delimiter>[^ ()\\\t\x0B\r\n]*) \( (?s:.*?) \) \k<delimiter> "
    )regex", boost::regex::perl | boost::regex::no_mod_s | boost::regex::mod_x | boost::regex::optimize);

    std::string subject(R"subject(
std::cout << L"hello" << " world";
std::cout << "He said: \"bananas\"" << "...";
std::cout << "";
std::cout << "\x12\23\x34";
std::cout << u8R"hello(this"is\a\""""single\\(valid)"
raw string literal)hello";

"" // empty string
'"' // character literal

// this is "a string literal" in a comment
/* this is
   "also inside"
   //a comment */

// and this /*
"is not in a comment"
// */

"this is a /* string */ with nested // comments"
    )subject");

    std::cout << boost::regex_replace(subject, re, "String\\($&\\)", boost::format_all) << std::endl;
}

int main(int argc, char **argv)
{
    try
    {
        test();
    }
    catch(std::exception ex)
    {
        std::cerr << ex.what() << std::endl;
    }

    return 0;
}

(\/\/.*|\/\*[\s\S]*?\*\/|(?:u8?|U|L)?'(?:\\(?:['"?\\abfnrtv]|[0-7]{1,3}|x[0-9a-fA-F]{1,2}|u[0-9a-fA-F]{4}|U[0-9a-fA-F]{8})|[^'\\\r\n])+')|(?:u8?|U|L)?"(?:\\(?:['"?\\abfnrtv]|[0-7]{1,3}|x[0-9a-fA-F]{1,2}|u[0-9a-fA-F]{4}|U[0-9a-fA-F]{8})|[^"\\\r\n])*"|(?:u8?|U|L)?R"([^ ()\\\t\x0B\r\n]*)\([\s\S]*?\)\2"

function run() {
    var re = /(\/\/.*|\/\*[\s\S]*?\*\/|(?:u8?|U|L)?'(?:\\(?:['"?\\abfnrtv]|[0-7]{1,3}|x[0-9a-fA-F]{1,2}|u[0-9a-fA-F]{4}|U[0-9a-fA-F]{8})|[^'\\\r\n])+')|(?:u8?|U|L)?"(?:\\(?:['"?\\abfnrtv]|[0-7]{1,3}|x[0-9a-fA-F]{1,2}|u[0-9a-fA-F]{4}|U[0-9a-fA-F]{8})|[^"\\\r\n])*"|(?:u8?|U|L)?R"([^ ()\\\t\x0B\r\n]*)\([\s\S]*?\)\2"/g;
    
    var input = document.getElementById("input").value;
    var output = input.replace(re, function(m, ignore) {
        return ignore ? m : "String(" + m + ")";
    });
    document.getElementById("output").innerText = output;
}

document.getElementById("input").addEventListener("input", run);
run();

<h2>Input:</h2>
<textarea id="input" style="width: 100%; height: 50px;">
std::cout << L"hello" << " world";
std::cout << "He said: \"bananas\"" << "...";
std::cout << "";
std::cout << "\x12\23\x34";
std::cout << u8R"hello(this"is\a\""""single\\(valid)"
raw string literal)hello";

"" // empty string
'"' // character literal

// this is "a string literal" in a comment
/* this is
   "also inside"
   //a comment */

// and this /*
"is not in a comment"
// */

"this is a /* string */ with nested // comments"
</textarea>
<h2>Output:</h2>
<pre id="output"></pre>

关于c++ - 用于匹配 C++ 字符串常量的正则表达式，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/41909225/