version 1.69, 2003/08/12 17:48:38
|
version 1.80, 2003/09/26 17:52:18
|
|
|
#include "CommonUTF.h" | #include "CommonUTF.h" |
| |
#ifdef PEGASUS_HAS_ICU | #ifdef PEGASUS_HAS_ICU |
#include <unistr.h> |
#include <unicode/unistr.h> |
#endif | #endif |
| |
PEGASUS_USING_STD; | PEGASUS_USING_STD; |
|
|
} | } |
| |
// ATTN-RK-P3-20020509: Define case-sensitivity for non-English characters | // 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 | #ifdef PEGASUS_HAS_ICU |
Char16* utf16str; |
UnicodeString UniStr((const UChar *)_rep->c16a.getData()); |
UnicodeString UniStr((const UChar *)_rep->c16a.getData(), (int32_t)size()); |
UniStr.toLower(); |
UniStr = UniStr.toLower(); |
UniStr.append((UChar)'\0'); |
utf16str = (Char16 *)UniStr.getTerminatedBuffer(); |
|
assign(utf16str); |
assign((Char16*)UniStr.getBuffer()); |
delete utf16str; |
|
#else | #else |
for (Char16* p = &_rep->c16a[0]; *p; p++) | for (Char16* p = &_rep->c16a[0]; *p; p++) |
{ | { |
|
|
#ifdef PEGASUS_HAS_ICU | #ifdef PEGASUS_HAS_ICU |
UnicodeString UniStr1((const UChar *)s1.getChar16Data(), (int32_t)s1.size()); | UnicodeString UniStr1((const UChar *)s1.getChar16Data(), (int32_t)s1.size()); |
UnicodeString UniStr2((const UChar *)s2.getChar16Data(), (int32_t)s2.size()); | UnicodeString UniStr2((const UChar *)s2.getChar16Data(), (int32_t)s2.size()); |
UniStr1 = UniStr1.toLower(); |
UniStr1.toLower(); |
UniStr2 = UniStr2.toLower(); |
UniStr2.toLower(); |
return (UniStr2.compare(UniStr1)); | return (UniStr2.compare(UniStr1)); |
#else | #else |
const Char16* _s1 = s1.getChar16Data(); | const Char16* _s1 = s1.getChar16Data(); |
|
|
#ifdef PEGASUS_HAS_ICU | #ifdef PEGASUS_HAS_ICU |
UnicodeString UniStr1((const UChar *)str1.getChar16Data(), (int32_t)str1.size()); | UnicodeString UniStr1((const UChar *)str1.getChar16Data(), (int32_t)str1.size()); |
UnicodeString UniStr2((const UChar *)str2.getChar16Data(), (int32_t)str2.size()); | UnicodeString UniStr2((const UChar *)str2.getChar16Data(), (int32_t)str2.size()); |
UniStr1 = UniStr1.toLower(); |
UniStr1.toLower(); |
UniStr2 = UniStr2.toLower(); |
UniStr2.toLower(); |
return (UniStr1 == UniStr2); | return (UniStr1 == UniStr2); |
#else | #else |
if (str1.size() != str2.size()) | if (str1.size() != str2.size()) |
|
|
| |
CString String::getCStringUTF8() const | CString String::getCStringUTF8() const |
{ | { |
Uint32 n = size() + 1; |
Uint32 n = 3*size() + 1; |
char* str = new char[n]; | char* str = new char[n]; |
| |
const Char16* msg16 = getChar16Data(); | const Char16* msg16 = getChar16Data(); |
| |
const Uint16 *strsrc = (Uint16 *)msg16; | const Uint16 *strsrc = (Uint16 *)msg16; |
Uint16 *endsrc = (Uint16 *)&msg16[2*n]; |
Uint16 *endsrc = (Uint16 *)&msg16[size()+1]; |
| |
Uint8 *strtgt = (Uint8 *)str; | Uint8 *strtgt = (Uint8 *)str; |
Uint8 *endtgt = (Uint8 *)&str[n]; | Uint8 *endtgt = (Uint8 *)&str[n]; |
|
|
&strtgt, | &strtgt, |
endtgt); | endtgt); |
| |
return CString(str); |
char* str1 = new char[strlen(str)+1]; |
|
strcpy(str1,str); |
|
delete [] str; |
|
|
|
return CString(str1); |
} | } |
| |
Boolean String::isUTF8(const char *legal) | Boolean String::isUTF8(const char *legal) |
{ | { |
return (isValid_U8((const Uint8 *)legal, |
char numBytes = UTF_8_COUNT_TRAIL_BYTES(*legal)+1; |
trailingBytesForUTF8[*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 | #if 0 |
|
|
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. |
*/ | */ |
| |
|
|
| |
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) | #if defined(PEGASUS_OS_OS400) |
CString cstr = str.getCStringUTF8(); | CString cstr = str.getCStringUTF8(); |
const char* utf8str = cstr; | const char* utf8str = cstr; |
|
|
os << utf8str; | os << utf8str; |
| |
#elif defined(PEGASUS_HAS_ICU) | #elif defined(PEGASUS_HAS_ICU) |
*/ |
|
#if defined(PEGASUS_HAS_ICU) |
|
char *buf = NULL; | char *buf = NULL; |
|
const int size = str.size() * 6; |
UnicodeString UniStr((const UChar *)str.getChar16Data(), (int32_t)str.size()); | UnicodeString UniStr((const UChar *)str.getChar16Data(), (int32_t)str.size()); |
|
Uint32 bufsize = UniStr.extract(0,size,buf); |
| |
Uint32 bufsize = UniStr.extract(0,0,buf); |
|
buf = new char[bufsize+1]; | buf = new char[bufsize+1]; |
UniStr.extract(0,bufsize,buf); | UniStr.extract(0,bufsize,buf); |
|
|
os << buf; | os << buf; |
|
os.flush(); |
delete buf; |
delete [] buf; |
#else | #else |
| |
| |