version 1.34, 2002/04/18 23:33:17
|
version 1.98, 2005/02/05 22:59:24
|
|
|
//%///////////////////////////////////////////////////////////////////////////// |
//%2005//////////////////////////////////////////////////////////////////////// |
// | // |
// Copyright (c) 2000, 2001 The Open group, BMC Software, Tivoli Systems, IBM |
// Copyright (c) 2000, 2001, 2002 BMC Software; Hewlett-Packard Development |
|
// Company, L.P.; IBM Corp.; The Open Group; Tivoli Systems. |
|
// Copyright (c) 2003 BMC Software; Hewlett-Packard Development Company, L.P.; |
|
// IBM Corp.; EMC Corporation, The Open Group. |
|
// Copyright (c) 2004 BMC Software; Hewlett-Packard Development Company, L.P.; |
|
// IBM Corp.; EMC Corporation; VERITAS Software Corporation; The Open Group. |
|
// Copyright (c) 2005 Hewlett-Packard Development Company, L.P.; IBM Corp.; |
|
// EMC Corporation; VERITAS Software Corporation; The Open Group. |
// | // |
// Permission is hereby granted, free of charge, to any person obtaining a copy | // Permission is hereby granted, free of charge, to any person obtaining a copy |
// of this software and associated documentation files (the "Software"), to | // of this software and associated documentation files (the "Software"), to |
|
|
// | // |
// Author: Mike Brasher (mbrasher@bmc.com) | // Author: Mike Brasher (mbrasher@bmc.com) |
// | // |
// Modified By: |
// Modified By: Roger Kumpf, Hewlett-Packard Company (roger_kumpf@hp.com) |
// | // |
//%///////////////////////////////////////////////////////////////////////////// | //%///////////////////////////////////////////////////////////////////////////// |
| |
| |
#include <cctype> | #include <cctype> |
|
#include <cstring> |
#include "String.h" | #include "String.h" |
#include "Exception.h" |
#include "Array.h" |
#include "String.h" |
#include "InternalException.h" |
#include <iostream> | #include <iostream> |
|
#include <fstream> |
|
|
|
#include "CommonUTF.h" |
|
|
|
#ifdef PEGASUS_HAS_ICU |
|
#include <unicode/unistr.h> |
|
#endif |
| |
PEGASUS_USING_STD; | PEGASUS_USING_STD; |
| |
PEGASUS_NAMESPACE_BEGIN | PEGASUS_NAMESPACE_BEGIN |
| |
#define PEGASUS_ARRAY_T String |
/////////////////////////////////////////////////////////////////////////////// |
#include <Pegasus/Common/ArrayImpl.h> |
// |
#undef PEGASUS_ARRAY_T |
// CString |
|
// |
const String String::EMPTY; |
/////////////////////////////////////////////////////////////////////////////// |
| |
#if 0 // Apparently dead code |
CString::CString() |
static inline void _SkipWhitespace(const Char16*& p) |
: _rep(0) |
{ | { |
while (*p && isspace(*p)) |
|
p++; |
|
} | } |
#endif |
|
| |
inline Uint32 StrLen(const char* str) |
CString::CString(const CString& cstr) |
{ | { |
if (!str) |
_rep = 0; |
throw NullPointer(); |
|
| |
return strlen(str); |
if (cstr._rep) |
|
{ |
|
_rep = (void*)new char[strlen((char*)cstr._rep)+1]; |
|
strcpy((char*)_rep, (char*)cstr._rep); |
|
} |
} | } |
| |
inline Uint32 StrLen(const Char16* str) |
CString::CString(char* cstr) |
|
: _rep(cstr) |
{ | { |
if (!str) |
|
throw NullPointer(); |
|
|
|
Uint32 n = 0; |
|
|
|
while (*str++) |
|
n++; |
|
|
|
return n; |
|
} | } |
| |
String::String() |
CString::~CString() |
{ | { |
_rep.append('\0'); |
if (_rep) |
|
{ |
|
delete [] (char*)_rep; |
|
} |
} | } |
| |
String::String(const String& x) : _rep(x._rep) |
CString& CString::operator=(const CString& cstr) |
{ | { |
|
if (&cstr != this) |
|
{ |
|
if (_rep) |
|
{ |
|
delete [] (char*)_rep; |
|
_rep = 0; |
} | } |
|
if (cstr._rep) |
String::String(const String& x, Uint32 n) |
|
{ | { |
_rep.append('\0'); |
_rep = (char*)new char[strlen((char*)cstr._rep)+1]; |
append(x.getData(), n); |
strcpy((char*)_rep, (char*)cstr._rep); |
|
} |
|
} |
|
return *this; |
} | } |
| |
String::String(const Char16* x) : _rep(x, StrLen(x) + 1) |
CString::operator const char*() const |
{ | { |
|
return (char*)_rep; |
} | } |
| |
String::String(const Char16* x, Uint32 n) |
/////////////////////////////////////////////////////////////////////////////// |
|
// |
|
// String |
|
// |
|
/////////////////////////////////////////////////////////////////////////////// |
|
|
|
const String String::EMPTY = String(); |
|
|
|
Uint32 _strnlen(const char* str, Uint32 n) |
{ | { |
assign(x, n); |
if (!str) |
} |
throw NullPointer(); |
| |
String::String(const char* str) |
for (Uint32 i=0; i<n; i++) |
{ | { |
Uint32 n = ::strlen(str) + 1; |
if (!*str) |
reserve(n); |
{ |
|
return i; |
|
} |
|
} |
| |
while (n--) |
return n; |
_rep.append(*str++); |
|
} | } |
| |
String::String(const char* str, Uint32 n_) |
Uint32 _strnlen(const Char16* str, Uint32 n) |
{ | { |
Uint32 n = _pegasusMin(strlen(str), n_); |
if (!str) |
reserve(n + 1); |
throw NullPointer(); |
|
|
while (n--) |
|
_rep.append(*str++); |
|
| |
_rep.append('\0'); |
for (Uint32 i=0; i<n; i++) |
|
{ |
|
if (!*str) |
|
{ |
|
return i; |
|
} |
} | } |
| |
String& String::assign(const Char16* x) |
return n; |
{ |
|
_rep.clear(); |
|
_rep.append(x, StrLen(x) + 1); |
|
return *this; |
|
} | } |
| |
String& String::assign(const Char16* str, Uint32 n) |
inline Uint32 _StrLen(const char* str) |
{ | { |
_rep.clear(); |
if (!str) |
Uint32 m = _pegasusMin(StrLen(str), n); |
throw NullPointer(); |
_rep.append(str, m); |
|
_rep.append('\0'); |
return strlen(str); |
return *this; |
|
} | } |
| |
String& String::assign(const char* x) |
inline Uint32 _StrLen(const Char16* str) |
{ | { |
_rep.clear(); |
if (!str) |
Uint32 n = strlen(x); |
throw NullPointer(); |
_rep.reserve(n + 1); |
|
| |
while (n--) |
Uint32 n = 0; |
_rep.append(*x++); |
|
| |
_rep.append('\0'); |
while (*str++) |
|
n++; |
| |
return *this; |
return n; |
} | } |
| |
String& String::assign(const char* x, Uint32 n_) |
class StringRep |
{ | { |
_rep.clear(); |
public: |
|
StringRep() |
|
{} |
|
StringRep(const StringRep& r) |
|
: c16a(r.c16a) |
|
{} |
|
StringRep(const Char16* str) |
|
: c16a(str, _StrLen(str) + 1) |
|
{} |
| |
Uint32 n = _pegasusMin(strlen(x), n_); |
Array<Char16> c16a; |
_rep.reserve(n + 1); |
}; |
| |
while (n--) |
String::String() |
_rep.append(*x++); |
{ |
|
_rep = new StringRep; |
_rep.append('\0'); |
_rep->c16a.append('\0'); |
|
|
return *this; |
|
} | } |
| |
char* String::allocateCString(Uint32 extraBytes, Boolean noThrow) const |
String::String(const String& str) |
{ | { |
Uint32 n = size() + 1; |
if (str._rep != NULL) |
char* str = new char[n + extraBytes]; |
|
char* p = str; |
|
const Char16* q = getData(); |
|
|
|
for (Uint32 i = 0; i < n; i++) |
|
{ | { |
Uint16 c = *q++; |
_rep = new StringRep(*str._rep); |
*p++ = char(c); |
} |
|
else |
if ((c & 0xff00) && !noThrow) |
{ |
throw TruncatedCharacter(); |
_rep = new StringRep(); |
} | } |
|
|
return str; |
|
} | } |
| |
void String::appendToCString( |
|
char* str, |
|
Uint32 length, |
|
Boolean noThrow) const |
|
{ |
|
if (!str) |
|
throw NullPointer(); |
|
| |
Uint32 n = _pegasusMin(size(), length); |
String::String(const String& str, Uint32 n) |
|
{ |
|
_rep = new StringRep; |
|
assign(str.getChar16Data(), n); |
|
} |
| |
char* p = str + strlen(str); |
String::String(const Char16* str) |
const Char16* q = getData(); |
{ |
|
_rep = new StringRep(str); |
|
} |
| |
for (Uint32 i = 0; i < n; i++) |
String::String(const Char16* str, Uint32 n) |
{ | { |
Uint16 c = *q++; |
_rep = new StringRep; |
*p++ = char(c); |
assign(str, n); |
|
} |
| |
if ((c & 0xff00) && !noThrow) |
String::String(const char* str) |
throw TruncatedCharacter(); |
{ |
|
_rep = new StringRep; |
|
assign(str); |
} | } |
| |
*p = '\0'; |
String::String(const char* str, Uint32 n) |
|
{ |
|
_rep = new StringRep; |
|
assign(str, n); |
} | } |
| |
Char16& String::operator[](Uint32 i) |
String::~String() |
{ | { |
if (i > size()) |
delete _rep; |
ThrowOutOfBounds(); |
} |
| |
return _rep[i]; |
String& String::operator=(const String& str) |
|
{ |
|
if (&str != this) |
|
{ |
|
assign(str); |
|
} |
|
return *this; |
} | } |
| |
const Char16 String::operator[](Uint32 i) const |
String& String::assign(const String& str) |
{ | { |
if (i > size()) |
_rep->c16a = str._rep->c16a; |
ThrowOutOfBounds(); |
return *this; |
|
} |
| |
return _rep[i]; |
String& String::assign(const Char16* str) |
|
{ |
|
_rep->c16a.clear(); |
|
_rep->c16a.append(str, _StrLen(str) + 1); |
|
return *this; |
} | } |
| |
String& String::append(const Char16* str, Uint32 n) |
String& String::assign(const Char16* str, Uint32 n) |
{ | { |
Uint32 m = _pegasusMin(StrLen(str), n); |
_rep->c16a.clear(); |
_rep.reserve(_rep.size() + m); |
Uint32 m = _strnlen(str, n); |
_rep.remove(_rep.size() - 1); |
_rep->c16a.append(str, m); |
_rep.append(str, m); |
_rep->c16a.append('\0'); |
_rep.append('\0'); |
|
return *this; | return *this; |
} | } |
| |
void String::remove(Uint32 pos, Uint32 size) |
String& String::assign(const char* str, Uint32 n) |
{ | { |
if (size == PEG_NOT_FOUND) |
char *tmpStr = new char[n+1]; |
size = this->size() - pos; |
memset(tmpStr,0x00,n+1); |
| |
if (pos + size > this->size()) |
strncpy(tmpStr,str,n); |
ThrowOutOfBounds(); |
assign(tmpStr); |
|
delete [] tmpStr; |
| |
if (size) |
return *this; |
_rep.remove(pos, size); |
|
} | } |
| |
int String::compare(const Char16* s1, const Char16* s2, Uint32 n) |
void String::clear() |
{ |
|
while (n--) |
|
{ | { |
int r = *s1++ - *s2++; |
_rep->c16a.clear(); |
|
_rep->c16a.append('\0'); |
if (r) |
|
return r; |
|
} | } |
| |
return 0; |
void String::reserveCapacity(Uint32 capacity) |
|
{ |
|
_rep->c16a.reserveCapacity(capacity + 1); |
} | } |
| |
int String::compareNoCase(const char* s1, const char* s2, Uint32 n) |
Uint32 String::size() const |
{ | { |
while (n--) |
return _rep->c16a.size() - 1; |
{ |
|
int r = tolower(*s1++) - tolower(*s2++); |
|
|
|
if (r) |
|
return r; |
|
} | } |
| |
return 0; |
const Char16* String::getChar16Data() const |
|
{ |
|
return _rep->c16a.getData(); |
} | } |
| |
Boolean String::equal(const String& x, const String& y) |
Char16& String::operator[](Uint32 index) |
{ | { |
if (x.size() != y.size()) |
if (index > size()) |
return false; |
throw IndexOutOfBoundsException(); |
| |
return String::compare(x.getData(), y.getData(), x.size()) == 0; |
return _rep->c16a[index]; |
} | } |
| |
Boolean String::equal(const String& x, const Char16* y) |
const Char16 String::operator[](Uint32 index) const |
{ | { |
if (x.size() != StrLen(y)) |
if (index > size()) |
return false; |
throw IndexOutOfBoundsException(); |
| |
return String::compare(x.getData(), y, x.size()) == 0; |
return _rep->c16a[index]; |
} | } |
| |
Boolean String::equal(const Char16* x, const String& y) |
String& String::append(const Char16& c) |
{ | { |
return equal(y, x); |
_rep->c16a.insert(_rep->c16a.size() - 1, c); |
|
return *this; |
} | } |
| |
Boolean String::equal(const String& x, const char* y) |
String& String::append(const Char16* str, Uint32 n) |
{ | { |
return equal(x, String(y)); |
Uint32 m = _strnlen(str, n); |
|
_rep->c16a.reserveCapacity(_rep->c16a.size() + m); |
|
_rep->c16a.remove(_rep->c16a.size() - 1); |
|
_rep->c16a.append(str, m); |
|
_rep->c16a.append('\0'); |
|
return *this; |
} | } |
| |
Boolean String::equal(const char* x, const String& y) |
String& String::append(const String& str) |
{ | { |
return equal(String(x), y); |
return append(str.getChar16Data(), str.size()); |
} | } |
| |
Boolean String::equalNoCase(const String& x, const String& y) |
void String::remove(Uint32 index, Uint32 size) |
{ | { |
if (x.size() != y.size()) |
if (size == PEG_NOT_FOUND) |
return false; |
size = this->size() - index; |
|
|
const Char16* p = x.getData(); |
|
const Char16* q = y.getData(); |
|
| |
Uint32 n = x.size(); |
if (index + size > this->size()) |
|
throw IndexOutOfBoundsException(); |
| |
while (n--) |
if (size) |
{ |
_rep->c16a.remove(index, size); |
#ifdef PEGASUS_HAS_EBCDIC |
|
if (*p <= 255 && *q <= 255) |
|
#else |
|
if (*p <= 127 && *q <= 127) |
|
#endif |
|
{ |
|
if (tolower(*p++) != tolower(*q++)) |
|
return false; |
|
} |
|
else if (*p++ != *q++) |
|
return false; |
|
} |
|
|
|
return true; |
|
} | } |
| |
String String::subString(Uint32 pos, Uint32 length) const |
String String::subString(Uint32 index, Uint32 length) const |
{ | { |
if (pos < size()) |
if (index < size()) |
{ | { |
if (length == PEG_NOT_FOUND) |
if ((length == PEG_NOT_FOUND) || (length > size() - index)) |
length = size() - pos; |
length = size() - index; |
| |
return String(getData() + pos, length); |
return String(getChar16Data() + index, length); |
} | } |
else | else |
return String(); | return String(); |
|
|
| |
Uint32 String::find(Char16 c) const | Uint32 String::find(Char16 c) const |
{ | { |
const Char16* first = getData(); |
const Char16* first = getChar16Data(); |
| |
for (const Char16* p = first; *p; p++) | for (const Char16* p = first; *p; p++) |
{ | { |
|
|
return PEG_NOT_FOUND; | return PEG_NOT_FOUND; |
} | } |
| |
Uint32 String::find(Uint32 pos, Char16 c) const |
Uint32 String::find(Uint32 index, Char16 c) const |
{ | { |
const Char16* data = getData(); |
const Char16* data = getChar16Data(); |
| |
for (Uint32 i = pos, n = size(); i < n; i++) |
for (Uint32 i = index, n = size(); i < n; i++) |
{ | { |
if (data[i] == c) | if (data[i] == c) |
return i; | return i; |
|
|
| |
Uint32 String::find(const String& s) const | Uint32 String::find(const String& s) const |
{ | { |
const Char16* pSubStr = s.getData(); |
const Char16* pSubStr = s.getChar16Data(); |
const Char16* pStr = getData(); |
const Char16* pStr = getChar16Data(); |
Uint32 subStrLen = s.size(); | Uint32 subStrLen = s.size(); |
Uint32 strLen = size(); | Uint32 strLen = size(); |
| |
|
|
Uint32 i = 1; | Uint32 i = 1; |
for (; i < subStrLen; i++) | for (; i < subStrLen; i++) |
if (*pStr++ != *p++ ) | if (*pStr++ != *p++ ) |
{pStr--; break;} // break from loop |
{pStr-=i; break;} // break from loop |
if (i == subStrLen) | if (i == subStrLen) |
return loc; | return loc; |
} | } |
|
|
return PEG_NOT_FOUND; | return PEG_NOT_FOUND; |
} | } |
| |
Uint32 String::find(const char* s) const |
|
{ |
|
return find(String(s)); |
|
} |
|
|
|
Uint32 String::find(const Char16* s) const |
|
{ |
|
return find(String(s)); |
|
} |
|
|
|
Uint32 String::reverseFind(Char16 c) const | Uint32 String::reverseFind(Char16 c) const |
{ | { |
const Char16* first = getData(); |
const Char16* first = getChar16Data(); |
const Char16* last = getData() + size(); |
const Char16* last = getChar16Data() + size(); |
| |
while (last != first) | while (last != first) |
{ | { |
|
|
| |
void String::toLower() | void String::toLower() |
{ | { |
for (Char16* p = &_rep[0]; *p; p++) |
const char * noLocale = NULL; |
|
String::toLower(noLocale); |
|
} |
|
void String::toLower(const char * strLocale) |
{ | { |
#ifdef PEGASUS_HAS_EBCDIC |
#ifdef PEGASUS_HAS_ICU |
if (*p <= 255) |
UnicodeString UniStr((const UChar *)_rep->c16a.getData()); |
|
if(strLocale == NULL) |
|
{ |
|
UniStr.toLower(); |
|
} |
|
else |
|
{ |
|
Locale loc(strLocale); |
|
if(loc.isBogus()) |
|
{ |
|
throw InvalidNameException(String(strLocale)); |
|
} |
|
UniStr.toLower(loc); |
|
} |
|
UniStr.append((UChar)'\0'); |
|
|
|
assign((Char16*)UniStr.getBuffer()); |
#else | #else |
if (*p <= 127) |
for (Char16* p = &_rep->c16a[0]; *p; p++) |
#endif |
{ |
|
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR) |
*p = tolower(*p); | *p = tolower(*p); |
} | } |
|
#endif |
} | } |
| |
void String::translate(Char16 fromChar, Char16 toChar) |
void String::toUpper(const char * strLocale) |
|
{ |
|
#ifdef PEGASUS_HAS_ICU |
|
UnicodeString UniStr((const UChar *)_rep->c16a.getData()); |
|
if(strLocale == NULL) |
|
{ |
|
UniStr.toUpper(); |
|
} |
|
else |
{ | { |
for (Char16* p = &_rep[0]; *p; p++) |
Locale loc(strLocale); |
|
if(loc.isBogus()) |
{ | { |
if (*p == fromChar) |
throw InvalidNameException(String(strLocale)); |
*p = toChar; |
|
} | } |
|
UniStr.toUpper(loc); |
} | } |
|
UniStr.append((UChar)'\0'); |
| |
int String::compare(const Char16* s1, const Char16* s2) |
assign((Char16*)UniStr.getBuffer()); |
|
#else |
|
for (Char16* p = &_rep->c16a[0]; *p; p++) |
{ | { |
while (*s1 && *s2) |
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
*p = toupper(*p); |
|
} |
|
#endif |
|
} |
|
|
|
int String::compare(const String& s1, const String& s2, Uint32 n) |
{ | { |
int r = *s1++ - *s2++; |
const Char16* s1c16 = s1.getChar16Data(); |
|
const Char16* s2c16 = s2.getChar16Data(); |
|
|
|
while (n--) |
|
{ |
|
int r = *s1c16++ - *s2c16++; |
| |
if (r) | if (r) |
return r; | return r; |
} | } |
| |
if (*s2) |
return 0; |
|
} |
|
|
|
int String::compare(const String& s1, const String& s2) |
|
{ |
|
const Char16* s1c16 = s1.getChar16Data(); |
|
const Char16* s2c16 = s2.getChar16Data(); |
|
|
|
while (*s1c16 && *s2c16) |
|
{ |
|
int r = *s1c16++ - *s2c16++; |
|
|
|
if (r) |
|
return r; |
|
} |
|
|
|
if (*s2c16) |
return -1; | return -1; |
else if (*s1) |
else if (*s1c16) |
return 1; | return 1; |
| |
return 0; | return 0; |
} | } |
| |
int String::compareNoCase(const char* s1, const char* s2) |
int String::compareNoCase(const String& s1, const String& s2) |
{ | { |
while (*s1 && *s2) |
const char * noLocale = NULL; |
|
return String::compareNoCase(s1, s2, noLocale); |
|
} |
|
|
|
int String::compareNoCase(const String& s1, const String& s2,const char * strLocale) |
{ | { |
int r = tolower(*s1++) - tolower(*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()); |
|
if(strLocale == NULL) |
|
{ |
|
UniStr1.toLower(); |
|
UniStr2.toLower(); |
|
} |
|
else |
|
{ |
|
Locale loc(strLocale); |
|
if(loc.isBogus()) |
|
{ |
|
throw InvalidNameException(String(strLocale)); |
|
} |
|
UniStr1.toLower(loc); |
|
UniStr2.toLower(loc); |
|
} |
|
// Note: the ICU 2.6.1 documentation for UnicodeString::compare( ) is |
|
// backwards! The API actually returns +1 if this is greater than text. |
|
// This is why the line below appears wrong based on the 2.6.1 docs. |
|
// (ref. bugzilla 1207) |
|
return (UniStr1.compare(UniStr2)); |
|
#else |
|
const Char16* _s1 = s1.getChar16Data(); |
|
const Char16* _s2 = s2.getChar16Data(); |
|
|
|
while (*_s1 && *_s2) |
|
{ |
|
int r; |
|
|
|
if (*_s1 <= PEGASUS_MAX_PRINTABLE_CHAR && |
|
*_s2 <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
{ |
|
r = tolower(*_s1++) - tolower(*_s2++); |
|
} |
|
else |
|
{ |
|
r = *_s1++ - *_s2++; |
|
} |
| |
if (r) | if (r) |
return r; | return r; |
} | } |
| |
if (*s2) |
if (*_s2) |
return -1; | return -1; |
else if (*s1) |
else if (*_s1) |
return 1; | return 1; |
| |
return 0; | return 0; |
|
#endif |
} | } |
| |
PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& x) |
Boolean String::equal(const String& str1, const String& str2) |
{ | { |
for (Uint32 i = 0, n = x.size(); i < n; i++) |
return String::compare(str1, str2) == 0; |
os << x[i]; |
|
|
|
return os; |
|
} | } |
| |
void String::toLower(char* str) |
Boolean String::equalNoCase(const String& str1, const String& str2) |
{ | { |
while (*str) |
const char * noLocale = NULL; |
tolower(*str++); |
return String::equalNoCase(str1, str2, noLocale); |
} | } |
| |
String ToLower(const String& str) |
Boolean String::equalNoCase(const String& str1, const String& str2,const char * strLocale) |
|
{ |
|
#ifdef PEGASUS_HAS_ICU |
|
UnicodeString UniStr1((const UChar *)str1.getChar16Data(), (int32_t)str1.size()); |
|
UnicodeString UniStr2((const UChar *)str2.getChar16Data(), (int32_t)str2.size()); |
|
if(strLocale == NULL) |
{ | { |
String tmp(str); |
UniStr1.toLower(); |
|
UniStr2.toLower(); |
|
} |
|
else |
|
{ |
|
Locale loc(strLocale); |
|
if(loc.isBogus()) |
|
{ |
|
throw InvalidNameException(String(strLocale)); |
|
} |
|
UniStr1.toLower(loc); |
|
UniStr2.toLower(loc); |
|
} |
|
return (UniStr1 == UniStr2); |
|
#else |
|
if (str1.size() != str2.size()) |
|
return false; |
|
|
|
const Char16* p = str1.getChar16Data(); |
|
const Char16* q = str2.getChar16Data(); |
| |
for (Uint32 i = 0, n = tmp.size(); i < n; i++) |
Uint32 n = str1.size(); |
|
|
|
while (n--) |
|
{ |
|
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR && |
|
*q <= PEGASUS_MAX_PRINTABLE_CHAR) |
{ | { |
Char16 c = tmp[i]; |
if (tolower(*p++) != tolower(*q++)) |
|
return false; |
|
} |
|
else if (*p++ != *q++) |
|
return false; |
|
} |
| |
#ifdef PEGASUS_HAS_EBCDIC |
return true; |
if (c <= 255) |
|
#else |
|
if (c <= 127) |
|
#endif | #endif |
tmp[i] = tolower(c); |
|
} | } |
| |
return tmp; |
// UTF8 specific code: |
|
String& String::assign(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 - 1)); ++count); |
|
|
|
_rep->c16a.append(msg16, count); |
|
|
|
_rep->c16a.append('\0'); |
|
|
|
delete [] msg16; |
|
|
|
return *this; |
} | } |
| |
int CompareNoCase(const char* s1, const char* s2) |
CString String::getCString() const |
{ | { |
while (*s1 && *s2) |
Uint32 n = 3*size() + 1; |
{ |
char* str = new char[n]; |
int r = tolower(*s1++) - tolower(*s2++); |
|
| |
if (r) |
const Char16* msg16 = getChar16Data(); |
return r; |
|
|
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); |
} | } |
| |
if (*s2) |
#if 0 |
return -1; |
// ATTN-RK-P3-20020603: This code is not completely correct |
else if (*s1) |
// Wildcard String matching function that may be useful in the future |
return 1; |
// The following code was provided by Bob Blair. |
| |
return 0; |
/* _StringMatch Match input MatchString against a GLOB style pattern |
|
Note that MatchChar is the char type so that this source |
|
in portable to different string types. This is an internal function |
|
|
|
Results: The return value is 1 if string matches pattern, and |
|
0 otherwise. The matching operation permits the following |
|
special characters in the pattern: *?\[] (see the manual |
|
entry for details on what these mean). |
|
|
|
|
|
Side effects: None. |
|
*/ |
|
|
|
/* MatchChar defined as a separate entity because this function source used |
|
elsewhere was an unsigned char *. Here we use Uint16 to maintain 16 bit |
|
size. |
|
*/ |
|
typedef Uint16 MatchChar; |
|
|
|
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; |
} | } |
| |
Boolean GetLine(PEGASUS_STD(istream)& is, String& line) |
inline Boolean _Equal(MatchChar ch1, MatchChar ch2, int nocase) |
{ | { |
line.clear(); |
// ICU_TODO: If ICU is available we should do this the correct way. |
|
if (nocase) |
|
return _ToLower(ch1) == _ToLower(ch2); |
|
else |
|
return ch1 == ch2; |
|
} |
| |
Boolean gotChar = false; |
|
char c; |
|
| |
while (is.get(c)) |
static const MatchChar * |
|
_matchrange(const MatchChar *range, MatchChar c, int nocase) |
|
{ |
|
const MatchChar *p = range; |
|
const MatchChar *rstart = range + 1; |
|
const MatchChar *rend = 0; |
|
MatchChar compchar; |
|
|
|
for (rend = rstart; *rend && *rend != ']'; rend++); |
|
if (*rend == ']') { // if there is an end to this pattern |
|
for (compchar = *rstart; rstart != rend; rstart++) { |
|
if (_Equal(*rstart, c, nocase)) |
|
return ++rend; |
|
if (*rstart == '-') { |
|
rstart++; |
|
if (c >= compchar && c <= *rstart) |
|
return ++rend; |
|
} |
|
} |
|
} |
|
return (const MatchChar *)0; |
|
} |
|
|
|
static int |
|
_StringMatch( |
|
const MatchChar *testString, |
|
const MatchChar *pattern, |
|
int nocase ) /* Ignore case if this is true */ |
|
{ |
|
const MatchChar *pat = pattern; |
|
const MatchChar *str = testString; |
|
unsigned int done = 0; |
|
unsigned int res = 0; // the result: 1 == match |
|
|
|
while (!done) { // main loop walks through pattern and test string |
|
//cerr << "Comparing <" << *pat << "> and <" << *str << ">" << endl; |
|
if (!*pat) { //end of pattern |
|
done = 1; // we're done |
|
if (!*str) //end of test, too? |
|
res = 1; // then we matched |
|
} else { //Not end of pattern |
|
if (!*str) { // but end of test |
|
done = 1; // We're done |
|
if (*pat == '*') // If pattern openends |
|
res = 1; // then we matched |
|
} else { //Not end of test |
|
if (*pat == '*') { //Ambiguuity found |
|
if (!*++pat) { //and it ends pattern |
|
done = 1; // then we're done |
|
res = 1; // and match |
|
} else { //if it doesn't end |
|
while (!done) { // until we're done |
|
if (_StringMatch(str, pat, nocase)) { // we recurse |
|
done = 1; //if it recurses true |
|
res = 1; // we done and match |
|
} else { //it recurses false |
|
if (!*str) // see if test is done |
|
done = 1; // yes: we done |
|
else // not done: |
|
str++; // keep testing |
|
} // end test on recursive call |
|
} // end looping on recursive calls |
|
} // end logic when pattern is ambiguous |
|
} else { //pattern not ambiguus |
|
if (*pat == '?') { //pattern is 'any' |
|
pat++, str++; // so move along |
|
} else if (*pat == '[') { //see if it's a range |
|
pat = _matchrange(pat, *str, nocase); // and is a match |
|
if (!pat) { //It is not a match |
|
done = 1; // we're done |
|
res = 0; // no match |
|
} else { //Range matches |
|
str++, pat++; // keep going |
|
} |
|
} else { // only case left is individual characters |
|
if (!_Equal(*pat++, *str++, nocase)) // if they don't match |
|
done = 1; // bail. |
|
} |
|
} // end ("pattern is not ambiguous (*)" logic |
|
} // end logic when pattern and string still have data |
|
} // end logic when pattern still has data |
|
} // end main loop |
|
return res; |
|
} |
|
|
|
|
|
/** 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) |
|
{ |
|
return _StringMatch( |
|
(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) |
{ | { |
gotChar = true; |
return _StringMatch( |
|
(Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 1) != 0; |
|
} |
|
#endif |
|
|
| |
if (c == '\n') |
/////////////////////////////////////////////////////////////////////////////// |
break; |
// |
|
// String-related functions |
|
// |
|
/////////////////////////////////////////////////////////////////////////////// |
| |
line.append(c); |
Boolean operator==(const String& str1, const String& str2) |
|
{ |
|
return String::equal(str1, str2); |
} | } |
| |
return gotChar; |
Boolean operator==(const String& str1, const char* str2) |
|
{ |
|
return String::equal(str1, str2); |
} | } |
| |
String::~String() |
Boolean operator==(const char* str1, const String& str2) |
{ | { |
|
return String::equal(str1, str2); |
} | } |
| |
String& String::assign(const String& x) |
Boolean operator!=(const String& str1, const String& str2) |
{ | { |
_rep = x._rep; |
return !String::equal(str1, str2); |
return *this; |
|
} | } |
| |
String& String::append(const Char16& c) |
PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& str) |
{ | { |
_rep.insert(_rep.size() - 1, c); |
|
return *this; |
#if defined(PEGASUS_OS_OS400) |
|
CString cstr = str.getCString(); |
|
const char* utf8str = cstr; |
|
|
|
os << utf8str; |
|
|
|
#elif defined(PEGASUS_HAS_ICU) |
|
if(os == cout || os == cerr){ |
|
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{ |
|
CString cstr = str.getCString(); |
|
const char* utf8str = cstr; |
|
os << utf8str; |
} | } |
| |
void String::clear() |
#else |
|
for (Uint32 i = 0, n = str.size(); i < n; i++) |
|
{ |
|
Uint16 code = str[i]; |
|
|
|
if (code > 0 && code <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
{ |
|
os << char(code); |
|
} |
|
else |
|
{ |
|
// Print in hex format: |
|
char buffer[8]; |
|
sprintf(buffer, "\\x%04X", code); |
|
os << buffer; |
|
} |
|
} |
|
#endif // End of PEGASUS_HAS_ICU #else leg. |
|
|
|
return os; |
|
} |
|
|
|
String operator+(const String& str1, const String& str2) |
|
{ |
|
return String(str1).append(str2); |
|
} |
|
|
|
Boolean operator<(const String& str1, const String& str2) |
{ | { |
_rep.clear(); |
return String::compare(str1, str2) < 0; |
_rep.append('\0'); |
|
} | } |
| |
void String::print() const |
Boolean operator<=(const String& str1, const String& str2) |
{ | { |
cout << *this << endl; |
return String::compare(str1, str2) <= 0; |
} | } |
| |
void String::reserve(Uint32 capacity) |
Boolean operator>(const String& str1, const String& str2) |
{ | { |
_rep.reserve(capacity + 1); |
return String::compare(str1, str2) > 0; |
} | } |
| |
const Array<String>& EmptyStringArray() |
Boolean operator>=(const String& str1, const String& str2) |
{ | { |
static Array<String> tmp; |
return String::compare(str1, str2) >= 0; |
return tmp; |
|
} | } |
| |
PEGASUS_NAMESPACE_END | PEGASUS_NAMESPACE_END |