[BACK]Return to pa_charset.h CVS log [TXT] [DIR] Up to [parser3project] / parser3 / src / include

Diff for /parser3/src/include/pa_charset.h between versions 1.32 and 1.43

version 1.32, 2005/12/16 10:15:12 version 1.43, 2009/10/03 02:18:04
Line 1 Line 1
 /** @file  /** @file
         Parser: Charset connection decl.          Parser: Charset connection decl.
   
         Copyright (c) 2001-2005 ArtLebedev Group (http://www.artlebedev.com)          Copyright (c) 2001-2009 ArtLebedev Group (http://www.artlebedev.com)
         Author: Alexandr Petrosian <paf@design.ru> (http://paf.design.ru)          Author: Alexandr Petrosian <paf@design.ru> (http://paf.design.ru)
 */  */
   
Line 16  static const char * const IDENT_CHARSET_ Line 16  static const char * const IDENT_CHARSET_
 #include "pa_hash.h"  #include "pa_hash.h"
 #include "pa_array.h"  #include "pa_array.h"
   
 // hiding into namespace so to avoid stupid conflict  // pcre.h must be included BEFORE pcre_internal.h
 namespace PCRE {  
 #include "pcre.h"  #include "pcre.h"
 #       include "internal.h"  // have to call config.h for using pcre_internal.h as well
 };  #include "../lib/pcre/config.h"
   #include "pcre_internal.h"
   
 #ifdef XML  #ifdef XML
 #include "libxml/encoding.h"  #include "libxml/encoding.h"
Line 32  namespace PCRE { Line 32  namespace PCRE {
   
 #define MAX_CHARSET_UNI_CODES 500  #define MAX_CHARSET_UNI_CODES 500
   
 #       ifndef XMLCh   #ifndef XMLCh 
                 typedef unsigned int XMLCh;          typedef unsigned int XMLCh;
 #       endif  #endif
 #       ifndef XMLByte  #ifndef XMLByte
                 typedef unsigned char XMLByte;          typedef unsigned char XMLByte;
 #       endif  #endif
   
 // helpers  // helpers
   
 typedef Hash<const String::Body, String::Body> HashStringString;  typedef HashString<String::Body> HashStringString;
   
 /**     charset holds name & transcode tables   /**     charset holds name & transcode tables 
         registers libxml transcoders          registers libxml transcoders
Line 57  public: Line 57  public:
         bool isUTF8() const { return fisUTF8; }          bool isUTF8() const { return fisUTF8; }
   
         static String::C transcode(const String::C src,          static String::C transcode(const String::C src,
                 const Charset& source_transcoder,                   const Charset& source_charset, 
                 const Charset& dest_transcoder                  const Charset& dest_charset);
         );  
   
         static String& transcode(const String& src,          static String& transcode(const String& src,
                 const Charset& source_transcoder,                   const Charset& source_transcoder, 
Line 77  public: Line 76  public:
                 const Charset& source_transcoder,                   const Charset& source_transcoder, 
                 const Charset& dest_transcoder);                  const Charset& dest_transcoder);
   
           static String::C escape(const String::C src,
                   const Charset& source_charset);
   
           static String::Body escape(const String::Body src,
                   const Charset& source_charset);
   
           static String& escape(const String& src,
                   const Charset& source_charset);
   
           void store_Char(XMLByte*& outPtr, XMLCh src, XMLByte not_found);
   
 #ifdef XML  #ifdef XML
         xmlCharEncodingHandler& transcoder(const String::Body NAME);          xmlCharEncodingHandler& transcoder(const String::Body NAME);
 #endif  #endif
Line 160  private: Line 170  private:
 extern Charset::UTF8CaseTable UTF8CaseToUpper;  extern Charset::UTF8CaseTable UTF8CaseToUpper;
 extern Charset::UTF8CaseTable UTF8CaseToLower;  extern Charset::UTF8CaseTable UTF8CaseToLower;
 void change_case_UTF8(const XMLByte* srcData, size_t srcLen,  void change_case_UTF8(const XMLByte* srcData, size_t srcLen,
                                           XMLByte* toFill, size_t toFillLen,                                          XMLByte* toFill, size_t toFillLen,
                                           const Charset::UTF8CaseTable& table);                                          const Charset::UTF8CaseTable& table);
   size_t getUTF8BytePos(const XMLByte* srcBegin, const XMLByte* srcEnd, size_t charPos/*position in characters*/);
   size_t getUTF8CharPos(const XMLByte* srcBegin, const XMLByte* srcEnd, size_t bytePos/*position in bytes*/);
   size_t lengthUTF8(const XMLByte* srcBegin, const XMLByte* srcEnd);
   
   
   class UTF8_string_iterator {
           public:
                   UTF8_string_iterator(const String& astring): fsrcPtr((XMLByte*)astring.cstr()), fsrcEnd(fsrcPtr + astring.length()) {}
                   UTF8_string_iterator(XMLByte* asrcPtr, size_t length): fsrcPtr(asrcPtr), fsrcEnd(fsrcPtr + length) {}
   
                   bool has_next();
                   XMLCh next() { return fUTF8Char; }
                   XMLByte getFirstByte(){ return ffirstByte; }
                   size_t getCharSize(){ return fcharSize; }
           private:
                   const XMLByte* fsrcPtr;
                   const XMLByte* fsrcEnd;
                   size_t fcharSize;
                   XMLByte ffirstByte;
                   XMLCh fUTF8Char;
   };
   
 #endif  #endif
Removed from v.1.32  
changed lines
  Added in v.1.43

E-mail: