(file) Return to String.cpp CVS log (file) (dir) Up to [Pegasus] / pegasus / src / Pegasus / Common

Diff for /pegasus/src/Pegasus/Common/String.cpp between version 1.55 and 1.81

version 1.55, 2002/08/29 16:54:38 version 1.81, 2003/10/02 19:10:27
Line 29 
Line 29 
  
  
 #include <cctype> #include <cctype>
   #include <cstring>
 #include "String.h" #include "String.h"
 #include "Array.h" #include "Array.h"
 #include "InternalException.h" #include "InternalException.h"
 #include <iostream> #include <iostream>
   #include <fstream>
   #ifndef PEGASUS_REMOVE_DEPRECATED
   #include "System.h"  // for strcasecmp
   #endif
   
   #include "CommonUTF.h"
   
   #ifdef PEGASUS_HAS_ICU
   #include <unicode/unistr.h>
   #endif
  
 PEGASUS_USING_STD; PEGASUS_USING_STD;
  
Line 51 
Line 62 
  
 CString::CString(const CString& cstr) CString::CString(const CString& cstr)
 { {
     _rep = new char[strlen(cstr._rep)+1];      _rep = (void*)new char[strlen((char*)cstr._rep)+1];
     _rep = strcpy(_rep, cstr._rep);      strcpy((char*)_rep, (char*)cstr._rep);
 } }
  
 CString::CString(char* cstr) CString::CString(char* cstr)
Line 63 
Line 74 
 CString::~CString() CString::~CString()
 { {
     if (_rep)     if (_rep)
         delete [] _rep;          delete [] (char*)_rep;
   }
   
   CString& CString::operator=(const CString& cstr)
   {
       if (_rep)
       {
           delete [] (char*)_rep;
           _rep = 0;
       }
       _rep = (char*)new char[strlen((char*)cstr._rep)+1];
       strcpy((char*)_rep, (char*)cstr._rep);
       return *this;
 } }
  
 CString::operator const char*() const CString::operator const char*() const
 { {
     return _rep;      return (char*)_rep;
 } }
  
 /////////////////////////////////////////////////////////////////////////////// ///////////////////////////////////////////////////////////////////////////////
Line 155 
Line 178 
  
 String::String(const String& str) String::String(const String& str)
 { {
     if (str._rep != NULL)
     {
     _rep = new StringRep(*str._rep);     _rep = new StringRep(*str._rep);
 } }
     else
     {
       _rep = new StringRep();
     }
   }
   
  
 String::String(const String& str, Uint32 n) String::String(const String& str, Uint32 n)
 { {
Line 181 
Line 212 
     assign(str);     assign(str);
 } }
  
   String::String(const char* str, const char* utfFlag)
   {
       _rep = new StringRep;
   
       if(!memcmp(utfFlag,STRING_FLAG_UTF8,sizeof(STRING_FLAG_UTF8)))
       {
           assignUTF8(str);
       }
       else
       {
           assign(str);
       }
   }
   
 String::String(const char* str, Uint32 n) String::String(const char* str, Uint32 n)
 { {
     _rep = new StringRep;     _rep = new StringRep;
Line 227 
Line 272 
     _rep->c16a.reserveCapacity(n);     _rep->c16a.reserveCapacity(n);
  
     while (n--)     while (n--)
         _rep->c16a.append(*str++);          _rep->c16a.append(Uint8(*str++));
  
     return *this;     return *this;
 } }
Line 240 
Line 285 
     _rep->c16a.reserveCapacity(_n + 1);     _rep->c16a.reserveCapacity(_n + 1);
  
     while (_n--)     while (_n--)
         _rep->c16a.append(*str++);          _rep->c16a.append(Uint8(*str++));
  
     _rep->c16a.append('\0');     _rep->c16a.append('\0');
  
Line 340 
Line 385 
 { {
     if (index < size())     if (index < size())
     {     {
         if (length == PEG_NOT_FOUND)          if ((length == PEG_NOT_FOUND) || (length > size() - index))
             length = size() - index;             length = size() - index;
  
         return String(getChar16Data() + index, length);         return String(getChar16Data() + index, length);
Line 422 
Line 467 
     return PEG_NOT_FOUND;     return PEG_NOT_FOUND;
 } }
  
   // ATTN-RK-P3-20020509: Define case-sensitivity for non-English characters
   // ATTN-CEC-20030913: ICU code added, but uses the server's locale.  Look at adding
   // a toLower( ) with Locale parameter - like ICU's toLower( )
 void String::toLower() void String::toLower()
 { {
   #ifdef PEGASUS_HAS_ICU
       UnicodeString UniStr((const UChar *)_rep->c16a.getData());
       UniStr.toLower();
       UniStr.append((UChar)'\0');
   
       assign((Char16*)UniStr.getBuffer());
   #else
     for (Char16* p = &_rep->c16a[0]; *p; p++)     for (Char16* p = &_rep->c16a[0]; *p; p++)
     {     {
         if (*p <= PEGASUS_MAX_PRINTABLE_CHAR)         if (*p <= PEGASUS_MAX_PRINTABLE_CHAR)
             *p = tolower(*p);             *p = tolower(*p);
     }     }
   #endif
 } }
  
 int String::compare(const String& s1, const String& s2, Uint32 n) int String::compare(const String& s1, const String& s2, Uint32 n)
Line 470 
Line 526 
  
 int String::compareNoCase(const String& s1, const String& s2) int String::compareNoCase(const String& s1, const String& s2)
 { {
   #ifdef PEGASUS_HAS_ICU
       UnicodeString UniStr1((const UChar *)s1.getChar16Data(), (int32_t)s1.size());
       UnicodeString UniStr2((const UChar *)s2.getChar16Data(), (int32_t)s2.size());
       UniStr1.toLower();
       UniStr2.toLower();
       return (UniStr2.compare(UniStr1));
   #else
     const Char16* _s1 = s1.getChar16Data();     const Char16* _s1 = s1.getChar16Data();
     const Char16* _s2 = s2.getChar16Data();     const Char16* _s2 = s2.getChar16Data();
  
Line 497 
Line 560 
         return 1;         return 1;
  
     return 0;     return 0;
   #endif
 } }
  
 Boolean String::equal(const String& str1, const String& str2) Boolean String::equal(const String& str1, const String& str2)
Line 506 
Line 570 
  
 Boolean String::equalNoCase(const String& str1, const String& str2) Boolean String::equalNoCase(const String& str1, const String& str2)
 { {
   #ifdef PEGASUS_HAS_ICU
       UnicodeString UniStr1((const UChar *)str1.getChar16Data(), (int32_t)str1.size());
       UnicodeString UniStr2((const UChar *)str2.getChar16Data(), (int32_t)str2.size());
       UniStr1.toLower();
       UniStr2.toLower();
       return (UniStr1 == UniStr2);
   #else
     if (str1.size() != str2.size())     if (str1.size() != str2.size())
         return false;         return false;
  
Line 527 
Line 598 
     }     }
  
     return true;     return true;
   #endif
 } }
  
   // UTF8 specific code:
   String& String::assignUTF8(const char* str)
   {
       _rep->c16a.clear();
       Uint32 n = strlen(str) + 1;
   
       const Uint8 *strsrc = (Uint8 *)str;
       Uint8 *endsrc = (Uint8 *)&str[n-1];
   
       Char16 *msg16 = new Char16[n];
       Uint16 *strtgt = (Uint16 *)msg16;
       Uint16 *endtgt = (Uint16 *)&msg16[n];
   
       UTF8toUTF16(&strsrc,
                   endsrc,
                   &strtgt,
                   endtgt);
   
       Uint32 count;
   
       for(count = 0; ((msg16[count]) != Char16(0x00)) && (count <= n); ++count);
   
       _rep->c16a.append(msg16, count);
   
       _rep->c16a.append('\0');
   
       delete [] msg16;
   
       return *this;
   }
  
   CString String::getCStringUTF8() const
   {
       Uint32 n = 3*size() + 1;
       char* str = new char[n];
   
       const Char16* msg16 = getChar16Data();
   
       const Uint16 *strsrc = (Uint16 *)msg16;
       Uint16 *endsrc = (Uint16 *)&msg16[size()+1];
   
       Uint8 *strtgt = (Uint8 *)str;
       Uint8 *endtgt = (Uint8 *)&str[n];
   
       UTF16toUTF8 (&strsrc,
                    endsrc,
                    &strtgt,
                    endtgt);
   
           char* str1 = new char[strlen(str)+1];
           strcpy(str1,str);
           delete [] str;
   
       return CString(str1);
   }
   
   Boolean String::isUTF8(const char *legal)
   {
       char numBytes = UTF_8_COUNT_TRAIL_BYTES(*legal)+1;
   
       // Validate that the string is long enough to hold all the expected bytes.
       // Note that if legal[0] == 0, numBytes will be 1.
       for (char i=1; i<numBytes; i++)
       {
           if (legal[i] == 0)
           {
               return false;
           }
       }
   
       return (isValid_U8((const Uint8 *)legal, numBytes));
   }
   
   #if 0
 // ATTN-RK-P3-20020603: This code is not completely correct // ATTN-RK-P3-20020603: This code is not completely correct
  // Wildcard String matching function that may be useful in the future  // Wildcard String matching function that may be useful in the future
 // The following code was provided by Bob Blair. // The following code was provided by Bob Blair.
Line 543 
Line 688 
         special characters in the pattern: *?\[] (see the manual         special characters in the pattern: *?\[] (see the manual
         entry for details on what these mean).         entry for details on what these mean).
  
   
   Side effects: None.   Side effects: None.
  */  */
  
Line 554 
Line 700 
  
 inline Uint16 _ToLower(Uint16 ch) inline Uint16 _ToLower(Uint16 ch)
 { {
       // ICU_TODO:  If ICU is available we should do this the correct way.
     return ch <= PEGASUS_MAX_PRINTABLE_CHAR ? tolower(char(ch)) : ch;     return ch <= PEGASUS_MAX_PRINTABLE_CHAR ? tolower(char(ch)) : ch;
 } }
  
 inline Boolean _Equal(MatchChar ch1, MatchChar ch2, int nocase) inline Boolean _Equal(MatchChar ch1, MatchChar ch2, int nocase)
 { {
       // ICU_TODO:  If ICU is available we should do this the correct way.
     if (nocase)     if (nocase)
         return _ToLower(ch1) == _ToLower(ch2);         return _ToLower(ch1) == _ToLower(ch2);
     else     else
Line 652 
Line 800 
 } }
  
  
       /** match matches a string against a GLOB style pattern.
           Return trues if the String parameter matches the pattern. C-Shell style
           glob matching is used.
           @param str String to be matched against the pattern
           @param pattern Pattern to use in the match
           @return Boolean true if str matches pattern
           The pattern definition is as follows:
           <pre>
           *             Matches any number of any characters
           ?             Match exactly one character
           [chars]       Match any character in chars
           [chara-charb] Match any character in the range between chara and charb
           </pre>
           The literal characters *, ?, [, ] can be included in a string by
           escaping them with backslash "\".  Ranges of characters can be concatenated.
           <pre>
           examples:
           Boolean result = String::match("This is a test", "*is*");
           Boolean works =  String::match("abcdef123", "*[0-9]");
           </pre>
       */
 Boolean String::match(const String& str, const String& pattern) Boolean String::match(const String& str, const String& pattern)
 { {
     return _StringMatch(     return _StringMatch(
         (Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 0) != 0;         (Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 0) != 0;
 } }
  
       /** matchNoCase Matches a String against a GLOB style pattern independent
           of case.
           Returns true if the str parameter matches the pattern. C-Shell style
           glob matching is used. Ignore case in all comparisons. Case is
           ignored in the match.
           @parm str String containing the string to be matched\
           @parm pattern GLOB style patterh to use in the match.
           @return Boolean true if str matches patterh
           @SeeAlso match
       */
 Boolean String::matchNoCase(const String& str, const String& pattern) Boolean String::matchNoCase(const String& str, const String& pattern)
 { {
     return _StringMatch(     return _StringMatch(
         (Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 1) != 0;         (Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 1) != 0;
 } }
   #endif
  
  
 /////////////////////////////////////////////////////////////////////////////// ///////////////////////////////////////////////////////////////////////////////
Line 693 
Line 873 
  
 PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& str) PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& str)
 { {
   
   #if defined(PEGASUS_OS_OS400)
       CString cstr = str.getCStringUTF8();
       const char* utf8str = cstr;
   
       os << utf8str;
   
   #elif defined(PEGASUS_HAS_ICU)
   
       char *buf = NULL;
       const int size = str.size() * 6;
       UnicodeString UniStr((const UChar *)str.getChar16Data(), (int32_t)str.size());
       Uint32 bufsize = UniStr.extract(0,size,buf);
   
       buf = new char[bufsize+1];
       UniStr.extract(0,bufsize,buf);
       os << buf;
       os.flush();
       delete [] buf;
   #else
   
   
     for (Uint32 i = 0, n = str.size(); i < n; i++)     for (Uint32 i = 0, n = str.size(); i < n; i++)
     {     {
         Uint16 code = str[i];         Uint16 code = str[i];
Line 709 
Line 911 
             os << buffer;             os << buffer;
         }         }
     }     }
   #endif // End of PEGASUS_HAS_ICU #else leg.
  
     return os;     return os;
 } }
Line 738 
Line 941 
     return String::compare(str1, str2) >= 0;     return String::compare(str1, str2) >= 0;
 } }
  
   #ifndef PEGASUS_REMOVE_DEPRECATED
 int CompareNoCase(const char* s1, const char* s2) int CompareNoCase(const char* s1, const char* s2)
 { {
     while (*s1 && *s2)      return System::strcasecmp(s1, s2);
     {  
         int r = tolower(*s1++) - tolower(*s2++);  
   
         if (r)  
             return r;  
     }  
   
     if (*s2)  
         return -1;  
     else if (*s1)  
         return 1;  
   
     return 0;  
 }  
   
 int EqualNoCase(const char* s1, const char* s2)  
 {  
     return CompareNoCase(s1, s2) == 0;  
 } }
   #endif
  
 PEGASUS_NAMESPACE_END PEGASUS_NAMESPACE_END

Legend:
Removed from v.1.55  
changed lines
  Added in v.1.81
No CVS admin address has been configured
 Powered by
ViewCVS 0.9.2