试了一把PCRE

虽然我在C++里用正则表达式已经有一些年头了，不过一直都是用的boost里那个库。坦白说，不是很好用。虽然我很早就知道PCRE，但一直都以为这是一个为PHP开发的库。实在是火星人啊。囧

前两天在推土上提起这事时，火炬向我推荐说PCRE比boost里那个正则库好用，于是试了一下，结果可耻滴发现BCB自带了PCRE，只不过没有在文档里提到罢了。

不 过PCRE是一个C语言的库，用起来不够方便。虽然也有PCRE++这种C++封装的版本，但是只提供了GNU编译配置，移植到BCB里估计比较麻烦，因 为我用到的功能也不多，就自己做了个简单的封装，用了一些VCL的AnsiString/StringList之类。用起来方便不少。

#include <pcre.h>


class TPCRE

{

private:

    AnsiString FPattern;

    pcre * FRE;

    TStrings * FMatches;


public:

  __fastcall TPCRE(AnsiString aPattern="");

  __fastcall ~TPCRE();


  void __fastcall compile(AnsiString aPattern="");

  int  __fastcall exec(AnsiString aStr);  //  return matched count

  AnsiString __fastcall repeat_replace(AnsiString aStr, AnsiString aRepStr="");


  __property TStrings * Matches = { read = FMatches };

};


__fastcall TPCRE::TPCRE(AnsiString aPattern)

    : FRE(NULL), FMatches(new TStringList())

{

    FPattern = aPattern;

    if ( FPattern != "" )

        compile();

}


__fastcall TPCRE::~TPCRE()

{

    if (FRE)

        free(FRE);

    delete FMatches;

}


void __fastcall TPCRE::compile(AnsiString aPattern)

{

    if ( aPattern != "" )

        FPattern = aPattern;

    const char * error;

    int erroffset;

    if (FRE)

        free(FRE);

    FRE = pcre_compile(FPattern.c_str(), 0, &error, &erroffset, NULL);

    // if ( FRE == NULL )

    // PCRE compilation failed at offset %d: %s, erroffset, error

}


int __fastcall TPCRE::exec(AnsiString aStr)

{

    if (!FRE)

        throw Exception("No pattern or have not be compiled!");

    const int OVECCOUNT = 30;

    int ovector[OVECCOUNT];

    int rc = pcre_exec(FRE, NULL, aStr.c_str(), aStr.Length(), 0, ovector, OVECCOUNT);

    if (rc < 0) {

        if (rc == PCRE_ERROR_NOMATCH)

            throw Exception("Sorry, no match ...");

        else

            throw Exception(AnsiString("Matching error ") + IntToStr(rc));

    }

    // OK, has matched ...

    FMatches->Clear();

    for (int i = 0; i < rc; i++)

        FMatches->Add(aStr.SubString(

            ovector[2*i]+1, ovector[2*i+1]-ovector[2*i]));

    return rc;

}


AnsiString __fastcall TPCRE::repeat_replace(AnsiString aStr, AnsiString aRepStr)

{

    if (!FRE)

        throw Exception("No pattern or have not be compiled!");

    const int OVECCOUNT = 30;

    int ovector[OVECCOUNT];

    int rc=1;

    char *p = aStr.c_str();

    int n = 1;

    int len = aStr.Length();

    AnsiString s="";

    while (rc>0) {

        rc = pcre_exec(FRE, NULL, p, len, 0, ovector, OVECCOUNT);

        if (rc < 0) {

            if (rc == PCRE_ERROR_NOMATCH) {

                if (s=="")

                    s = aStr;

                else

                    s += aStr.SubString(n,aStr.Length()-n+1);

                break;

            }

            else

                throw Exception(AnsiString("Matching error ") + IntToStr(rc));

        }

        // OK, has matched ...

        s += aStr.SubString(n,ovector[0])+aRepStr;

        n += ovector[1];

        p = aStr.c_str()+n-1;

        len = aStr.Length()-n+1;

    }

    return s;

}

用法很简单，这是一段示例代码，可以把HTML转换成TXT：

// 输入：const char *s

// 输出：AnsiString sResult

    std::auto_ptr<TPCRE> re(new TPCRE("(?ims)<title>([^<]*)"));

    AnsiString sResult;

    if (re->exec(s)>1)

        sResult = re->Matches->Strings[1].Trim();

    re->compile("(?ims)<body[^>]*>(.*)");

    if (re->exec(s)>1) {

        AnsiString str = re->Matches->Strings[1].Trim();

        str = StringReplace(str,"\r","",TReplaceFlags()<<rfReplaceAll);

        str = StringReplace(str,"\n","",TReplaceFlags()<<rfReplaceAll);

        str = StringReplace(str,"&nbsp;"," ",TReplaceFlags()<<rfReplaceAll);

        //  replace <br /> to \r\n

        re->compile("(?i)<br\s*/?>");

        str = re->repeat_replace(str,"\r\n");

        //  remove <script...>...</script>

        re->compile("(?ims)<script[^>]*>.*</script>");

        str = re->repeat_replace(str);

        //  remove <!-- ... -->

        re->compile("(?ims)<!--.*-->");

        str = re->repeat_replace(str);

        //  remove <...>

        re->compile("(?ims)<[^>]*>");

        str = re->repeat_replace(str);

        sResult += str;

    }

主要就是取出title部分和body部分，然后将body部分的回车全部去掉， 替换成空格，br换成回车，脚本和注释去掉，最后去掉所有HTML的标记。