version 1.39, 2002/05/06 20:13:08
|
version 1.109, 2005/05/18 20:34:36
|
|
|
//%///////////////////////////////////////////////////////////////////////////// |
//%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: Roger Kumpf, Hewlett-Packard Company (roger_kumpf@hp.com) | // Modified By: Roger Kumpf, Hewlett-Packard Company (roger_kumpf@hp.com) |
|
// Josephine Eskaline Joyce, IBM (jojustin@in.ibm.com) for Bug#3297 |
// | // |
//%///////////////////////////////////////////////////////////////////////////// | //%///////////////////////////////////////////////////////////////////////////// |
| |
| |
#include <cctype> | #include <cctype> |
|
#include <cstring> |
#include "String.h" | #include "String.h" |
#include "Exception.h" |
#include "Array.h" |
|
#include "AutoPtr.h" |
|
#include "InternalException.h" |
#include <iostream> | #include <iostream> |
|
#include <fstream> |
|
#include <Pegasus/Common/CommonUTF.h> |
|
|
|
#include "CommonUTF.h" |
|
|
|
#ifdef PEGASUS_HAS_ICU |
|
#include <unicode/ustring.h> |
|
#include <unicode/uchar.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 |
|
|
|
/////////////////////////////////////////////////////////////////////////////// | /////////////////////////////////////////////////////////////////////////////// |
// | // |
// String |
// CString |
// | // |
/////////////////////////////////////////////////////////////////////////////// | /////////////////////////////////////////////////////////////////////////////// |
| |
const String String::EMPTY = String(); |
CString::CString() |
|
: _rep(0) |
Uint32 _strnlen(const char* str, Uint32 n) |
|
{ | { |
if (!str) |
} |
throw NullPointer(); |
|
| |
for (Uint32 i=0; i<n; i++) |
CString::CString(const CString& cstr) |
{ | { |
if (!*str) |
_rep = 0; |
|
|
|
if (cstr._rep) |
{ | { |
return i; |
_rep = (void*)new char[strlen((char*)cstr._rep)+1]; |
|
strcpy((char*)_rep, (char*)cstr._rep); |
} | } |
} | } |
| |
return n; |
CString::CString(char* cstr) |
|
: _rep(cstr) |
|
{ |
} | } |
| |
Uint32 _strnlen(const Char16* str, Uint32 n) |
CString::~CString() |
{ | { |
if (!str) |
if (_rep) |
throw NullPointer(); |
{ |
|
delete [] (char*)_rep; |
|
} |
|
} |
| |
for (Uint32 i=0; i<n; i++) |
CString& CString::operator=(const CString& cstr) |
{ | { |
if (!*str) |
if (&cstr != this) |
{ | { |
return i; |
if (_rep) |
|
{ |
|
delete [] (char*)_rep; |
|
_rep = 0; |
} | } |
|
if (cstr._rep) |
|
{ |
|
_rep = (char*)new char[strlen((char*)cstr._rep)+1]; |
|
strcpy((char*)_rep, (char*)cstr._rep); |
} | } |
|
} |
return n; |
return *this; |
} | } |
| |
inline Uint32 _StrLen(const char* str) |
CString::operator const char*() const |
{ | { |
if (!str) |
return (char*)_rep; |
throw NullPointer(); |
|
|
|
return strlen(str); |
|
} | } |
| |
|
/////////////////////////////////////////////////////////////////////////////// |
|
// |
|
// String |
|
// |
|
/////////////////////////////////////////////////////////////////////////////// |
|
|
|
const String String::EMPTY = String(); |
|
|
inline Uint32 _StrLen(const Char16* str) | inline Uint32 _StrLen(const Char16* str) |
{ | { |
if (!str) | if (!str) |
|
|
return n; | return n; |
} | } |
| |
|
// |
|
// Converts a utf-8 char buffer to utf-16 and appends the utf-16 to the Array. |
|
// n is the length of the input char *, if stopAtTerm is 0 |
|
// A terminator character is appended to the end. |
|
// Note that each input char is converted individually, which gives |
|
// the fastest performance. |
|
// |
|
void _convertAndAppend(const char* str, Array<Char16>& c16a, Uint32 n, Uint8 stopAtTerm) |
|
{ |
|
Uint32 i = 0; |
|
while ((stopAtTerm && *str) || (!stopAtTerm && i < n)) |
|
{ |
|
if (*(Uint8*)str <= 0x7f) |
|
{ |
|
// Current byte sequence is in the us-ascii range. |
|
c16a.append(Uint8(*str++)); |
|
} |
|
else |
|
{ |
|
// |
|
// Current byte sequence is not in the us-ascii range. |
|
// |
|
|
|
// Check if the byte sequence is valid utf-8, and if so, |
|
// call the converter to utf-16 |
|
Uint16 tgt[3]; |
|
tgt[1] = 0; |
|
Uint8 c = UTF_8_COUNT_TRAIL_BYTES(*str); |
|
if ( (!stopAtTerm && i + c >= n) || |
|
(!isValid_U8((const Uint8 *)str, c+1)) ) |
|
{ |
|
// Note about error conditions. |
|
// It is possible that the last utf-8 char before the |
|
// end of input string extends past the end of the input string. |
|
// This is caught in both cases - |
|
// If counting up to n, then the test above catches it. |
|
// If converting until terminator found, then a terminator |
|
// in the middle of a multi-byte utf-8 char is invalid. |
|
MessageLoaderParms parms("Common.String.BAD_UTF8", |
|
"The byte sequence starting at index $0 is not valid UTF-8 encoding.", |
|
i); |
|
throw Exception(parms); |
|
} |
|
else |
|
{ |
|
// str is incremented by this call to the start of the next char |
|
Uint16 * tgtBuf = tgt; |
|
UTF8toUTF16((const Uint8 **)&str, (Uint8 *)&str[c+1], &tgtBuf, &tgtBuf[2]); |
|
c16a.append(tgt[0]); |
|
if (tgt[1]) |
|
{ |
|
// Its a utf-16 surrogate pair (uses 2 Char16's) |
|
c16a.append(tgt[1]); |
|
} |
|
|
|
// bump by the trailing byte count |
|
i += c; |
|
} |
|
} |
|
|
|
i++; |
|
} // end while |
|
|
|
c16a.append('\0'); |
|
} |
|
|
|
class StringRep |
|
{ |
|
public: |
|
StringRep() |
|
{} |
|
StringRep(const StringRep& r) |
|
: c16a(r.c16a) |
|
{} |
|
StringRep(const Char16* str) |
|
: c16a(str, _StrLen(str) + 1) |
|
{} |
|
|
|
Array<Char16> c16a; |
|
}; |
|
|
String::String() | String::String() |
{ | { |
_rep.append('\0'); |
_rep = new StringRep; |
|
_rep->c16a.append('\0'); |
} | } |
| |
String::String(const String& str) | String::String(const String& str) |
: _rep(str._rep) |
|
{ | { |
|
if (str._rep != NULL) |
|
{ |
|
_rep = new StringRep(*str._rep); |
|
} |
|
else |
|
{ |
|
_rep = new StringRep(); |
|
} |
} | } |
| |
|
|
String::String(const String& str, Uint32 n) | String::String(const String& str, Uint32 n) |
{ | { |
assign(str.getData(), n); |
_rep = new StringRep; |
|
assign(str.getChar16Data(), n); |
} | } |
| |
String::String(const Char16* str) | String::String(const Char16* str) |
: _rep(str, _StrLen(str) + 1) |
|
{ | { |
|
if ( str == 0 ) |
|
{ |
|
throw NullPointer(); |
|
} |
|
|
|
_rep = new StringRep(str); |
} | } |
| |
String::String(const Char16* str, Uint32 n) | String::String(const Char16* str, Uint32 n) |
{ | { |
|
if ( str == 0 ) |
|
{ |
|
throw NullPointer(); |
|
} |
|
|
|
_rep = new StringRep; |
assign(str, n); | assign(str, n); |
} | } |
| |
String::String(const char* str) | String::String(const char* str) |
{ | { |
assign(str); |
if ( str == 0 ) |
|
{ |
|
throw NullPointer(); |
|
} |
|
|
|
_rep = new StringRep; |
|
AutoPtr<StringRep> tempRep(_rep); |
|
// An exception can be thrown, so use a temp AutoPtr. |
|
_convertAndAppend(str, _rep->c16a, 0, 1); |
|
tempRep.release(); |
} | } |
| |
String::String(const char* str, Uint32 n) | String::String(const char* str, Uint32 n) |
{ | { |
assign(str, n); |
if ( str == 0 ) |
|
{ |
|
throw NullPointer(); |
|
} |
|
|
|
_rep = new StringRep; |
|
AutoPtr<StringRep> tempRep(_rep); |
|
// An exception can be thrown, so use a temp AutoPtr. |
|
_convertAndAppend(str, _rep->c16a, n, 0); |
|
tempRep.release(); |
} | } |
| |
String::~String() | String::~String() |
{ | { |
|
delete _rep; |
} | } |
| |
String& String::operator=(const String& str) | String& String::operator=(const String& str) |
{ | { |
return assign(str); |
if (&str != this) |
} |
|
|
|
String& String::operator=(const Char16* str) |
|
{ | { |
return assign(str); |
assign(str); |
|
} |
|
return *this; |
} | } |
| |
String& String::assign(const String& str) | String& String::assign(const String& str) |
{ | { |
_rep = str._rep; |
_rep->c16a = str._rep->c16a; |
return *this; | return *this; |
} | } |
| |
String& String::assign(const Char16* str) | String& String::assign(const Char16* str) |
{ | { |
_rep.clear(); |
if ( str == 0 ) |
_rep.append(str, _StrLen(str) + 1); |
{ |
|
throw NullPointer(); |
|
} |
|
|
|
_rep->c16a.clear(); |
|
_rep->c16a.append(str, _StrLen(str) + 1); |
return *this; | return *this; |
} | } |
| |
String& String::assign(const Char16* str, Uint32 n) | String& String::assign(const Char16* str, Uint32 n) |
{ | { |
_rep.clear(); |
if ( str == 0 ) |
Uint32 m = _strnlen(str, n); |
{ |
_rep.append(str, m); |
throw NullPointer(); |
_rep.append('\0'); |
} |
|
|
|
_rep->c16a.clear(); |
|
_rep->c16a.append(str, n); |
|
_rep->c16a.append('\0'); |
return *this; | return *this; |
} | } |
| |
String& String::assign(const char* str) | String& String::assign(const char* str) |
{ | { |
_rep.clear(); |
if ( str == 0 ) |
|
{ |
Uint32 n = strlen(str) + 1; |
throw NullPointer(); |
_rep.reserve(n); |
} |
|
|
while (n--) |
|
_rep.append(*str++); |
|
| |
|
_rep->c16a.clear(); |
|
_convertAndAppend(str, _rep->c16a, 0, 1); |
return *this; | return *this; |
} | } |
| |
String& String::assign(const char* str, Uint32 n) | String& String::assign(const char* str, Uint32 n) |
{ | { |
_rep.clear(); |
if ( str == 0 ) |
|
{ |
Uint32 _n = _strnlen(str, n); |
throw NullPointer(); |
_rep.reserve(_n + 1); |
} |
|
|
while (_n--) |
|
_rep.append(*str++); |
|
|
|
_rep.append('\0'); |
|
| |
|
_rep->c16a.clear(); |
|
_convertAndAppend(str, _rep->c16a, n, 0); |
return *this; | return *this; |
} | } |
| |
void String::clear() | void String::clear() |
{ | { |
_rep.clear(); |
_rep->c16a.clear(); |
_rep.append('\0'); |
_rep->c16a.append('\0'); |
} | } |
| |
void String::reserve(Uint32 capacity) |
void String::reserveCapacity(Uint32 capacity) |
{ | { |
_rep.reserve(capacity + 1); |
_rep->c16a.reserveCapacity(capacity + 1); |
} | } |
| |
Uint32 String::size() const | Uint32 String::size() const |
{ | { |
return _rep.size() - 1; |
//#if defined (PEGASUS_OS_VMS) |
} |
// |
|
// This prevents returning a minus number. |
const Char16* String::getData() const |
// |
{ |
// Seems as though the first time through |
return _rep.getData(); |
// the XML parser something doesn't get |
} |
// initialized and there is no check for |
|
// a negative number in the parser! |
char* String::allocateCString(Uint32 extraBytes, Boolean noThrow) const |
// |
{ |
// Uint32 foo; |
Uint32 n = size() + 1; |
// foo = _rep->c16a.size(); |
char* str = new char[n + extraBytes]; |
// if (foo == 0) |
char* p = str; |
// { |
const Char16* q = getData(); |
// return 0; |
|
// } |
for (Uint32 i = 0; i < n; i++) |
// else |
{ |
// { |
Uint16 c = *q++; |
// return (foo -1); |
*p++ = char(c); |
// } |
|
//#else |
if ((c & 0xff00) && !noThrow) |
return _rep->c16a.size() - 1; |
throw TruncatedCharacter(); |
//#endif |
} |
|
|
|
return str; |
|
} | } |
| |
void String::appendToCString( |
const Char16* String::getChar16Data() const |
char* str, |
|
Uint32 length, |
|
Boolean noThrow) const |
|
{ |
|
if (!str) |
|
throw NullPointer(); |
|
|
|
Uint32 n = (size() < length)? size() : length; |
|
|
|
char* p = str + strlen(str); |
|
const Char16* q = getData(); |
|
|
|
for (Uint32 i = 0; i < n; i++) |
|
{ | { |
Uint16 c = *q++; |
return _rep->c16a.getData(); |
*p++ = char(c); |
|
|
|
if ((c & 0xff00) && !noThrow) |
|
throw TruncatedCharacter(); |
|
} |
|
|
|
*p = '\0'; |
|
} | } |
| |
Char16& String::operator[](Uint32 i) |
Char16& String::operator[](Uint32 index) |
{ | { |
if (i > size()) |
if (index > size()) |
ThrowOutOfBounds(); |
throw IndexOutOfBoundsException(); |
| |
return _rep[i]; |
return _rep->c16a[index]; |
} | } |
| |
const Char16 String::operator[](Uint32 i) const |
const Char16 String::operator[](Uint32 index) const |
{ | { |
if (i > size()) |
if (index > size()) |
ThrowOutOfBounds(); |
throw IndexOutOfBoundsException(); |
| |
return _rep[i]; |
return _rep->c16a[index]; |
} | } |
| |
String& String::append(const Char16& c) | String& String::append(const Char16& c) |
{ | { |
_rep.insert(_rep.size() - 1, c); |
_rep->c16a.insert(_rep->c16a.size() - 1, c); |
return *this; | return *this; |
} | } |
| |
String& String::append(const Char16* str, Uint32 n) | String& String::append(const Char16* str, Uint32 n) |
{ | { |
Uint32 m = _strnlen(str, n); |
if (str == 0) |
_rep.reserve(_rep.size() + m); |
|
_rep.remove(_rep.size() - 1); |
|
_rep.append(str, m); |
|
_rep.append('\0'); |
|
return *this; |
|
} |
|
|
|
String& String::append(const String& str) |
|
{ |
|
return append(str.getData(), str.size()); |
|
} |
|
|
|
String& String::operator+=(const String& str) |
|
{ | { |
return append(str); |
throw NullPointer(); |
} | } |
| |
String& String::operator+=(Char16 c) |
_rep->c16a.reserveCapacity(_rep->c16a.size() + n); |
{ |
_rep->c16a.remove(_rep->c16a.size() - 1); |
return append(c); |
_rep->c16a.append(str, n); |
|
_rep->c16a.append('\0'); |
|
return *this; |
} | } |
| |
String& String::operator+=(char c) |
String& String::append(const String& str) |
{ | { |
return append(Char16(c)); |
return append(str.getChar16Data(), str.size()); |
} | } |
| |
void String::remove(Uint32 pos, Uint32 size) |
void String::remove(Uint32 index, Uint32 size) |
{ | { |
if (size == PEG_NOT_FOUND) | if (size == PEG_NOT_FOUND) |
size = this->size() - pos; |
size = this->size() - index; |
| |
if (pos + size > this->size()) |
if (index + size > this->size()) |
ThrowOutOfBounds(); |
throw IndexOutOfBoundsException(); |
| |
if (size) | if (size) |
_rep.remove(pos, size); |
_rep->c16a.remove(index, size); |
} | } |
| |
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 |
|
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 Char16* s) const |
|
{ |
|
return find(String(s)); |
|
} |
|
|
|
Uint32 String::find(const char* 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++) |
#ifdef PEGASUS_HAS_ICU |
|
if (InitializeICU::initICUSuccessful()) |
{ | { |
#ifdef PEGASUS_HAS_EBCDIC |
// This will do a locale-insensitive, but context-sensitive convert. |
if (*p <= 255) |
// Context-sensitive prevents any optimizations that try to |
#else |
// convert just the ascii before calling ICU. |
if (*p <= 127) |
// The string may shrink or expand after the convert. |
#endif |
|
*p = tolower(*p); |
|
} |
|
} |
|
| |
void String::toLower(char* str) |
int32_t sz = size(); |
|
UChar* destbuf = new UChar[sz + 1]; |
|
const UChar* srcbuf = (const UChar *)getChar16Data(); |
|
UErrorCode err = U_ZERO_ERROR; |
|
|
|
int32_t needed = u_strToLower(destbuf, sz + 1 , srcbuf, sz, NULL, &err); |
|
if (err == U_BUFFER_OVERFLOW_ERROR) |
|
{ |
|
delete [] destbuf; |
|
destbuf = new UChar[needed + 1]; |
|
err = U_ZERO_ERROR; |
|
u_strToLower(destbuf, needed + 1 , srcbuf, sz, NULL, &err); |
|
} |
|
if (U_FAILURE(err)) |
{ | { |
while (*str) |
delete [] destbuf; |
tolower(*str++); |
throw Exception(u_errorName(err)); |
} | } |
| |
void String::translate(Char16 fromChar, Char16 toChar) |
if (needed == sz) |
{ | { |
for (Char16* p = &_rep[0]; *p; p++) |
Char16* from = (Char16*)destbuf; |
|
for (Char16* to = &_rep->c16a[0]; *to; to++, from++) |
{ | { |
if (*p == fromChar) |
*to = *from; |
*p = toChar; |
|
} | } |
} | } |
|
else |
void String::print() const |
|
{ | { |
cout << *this << endl; |
assign((Char16 *)destbuf, needed); |
} | } |
| |
int String::compare(const Char16* s1, const Char16* s2, Uint32 n) |
delete [] destbuf; |
|
} |
|
else |
|
#endif |
{ | { |
while (n--) |
for (Char16* p = &_rep->c16a[0]; *p; p++) |
{ | { |
int r = *s1++ - *s2++; |
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
*p = tolower(*p); |
if (r) |
} |
return r; |
|
} | } |
|
|
return 0; |
|
} | } |
| |
int String::compare(const Char16* s1, const Char16* s2) |
void String::toUpper() |
{ | { |
while (*s1 && *s2) |
#ifdef PEGASUS_HAS_ICU |
|
if (InitializeICU::initICUSuccessful()) |
{ | { |
int r = *s1++ - *s2++; |
// This will do a locale-insensitive, but context-sensitive convert. |
|
// Context-sensitive prevents any optimizations that try to |
|
// convert just the ascii before calling ICU. |
|
// The string may shrink or expand after the convert. |
| |
if (r) |
int32_t sz = size(); |
return r; |
UChar* destbuf = new UChar[sz + 1]; |
|
const UChar* srcbuf = (const UChar *)getChar16Data(); |
|
UErrorCode err = U_ZERO_ERROR; |
|
|
|
int32_t needed = u_strToUpper(destbuf, sz + 1 , srcbuf, sz, NULL, &err); |
|
if (err == U_BUFFER_OVERFLOW_ERROR) |
|
{ |
|
delete [] destbuf; |
|
destbuf = new UChar[needed + 1]; |
|
err = U_ZERO_ERROR; |
|
u_strToUpper(destbuf, needed + 1 , srcbuf, sz, NULL, &err); |
|
} |
|
if (U_FAILURE(err)) |
|
{ |
|
delete [] destbuf; |
|
throw Exception(u_errorName(err)); |
} | } |
| |
if (*s2) |
if (needed == sz) |
return -1; |
{ |
else if (*s1) |
Char16* from = (Char16*)destbuf; |
return 1; |
for (Char16* to = &_rep->c16a[0]; *to; to++, from++) |
|
{ |
|
*to = *from; |
|
} |
|
} |
|
else |
|
{ |
|
assign((Char16 *)destbuf, needed); |
|
} |
| |
return 0; |
delete [] destbuf; |
|
} |
|
else |
|
#endif |
|
{ |
|
for (Char16* p = &_rep->c16a[0]; *p; p++) |
|
{ |
|
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
*p = toupper(*p); |
|
} |
|
} |
} | } |
| |
int String::compareNoCase(const char* s1, const char* s2, Uint32 n) |
int String::compare(const String& s1, const String& s2, Uint32 n) |
{ | { |
|
const Char16* s1c16 = s1.getChar16Data(); |
|
const Char16* s2c16 = s2.getChar16Data(); |
|
|
while (n--) | while (n--) |
{ | { |
int r = tolower(*s1++) - tolower(*s2++); |
int r = *s1c16++ - *s2c16++; |
| |
if (r) | if (r) |
return r; | return r; |
|
|
return 0; | return 0; |
} | } |
| |
int String::compareNoCase(const char* s1, const char* s2) |
int String::compare(const String& s1, const String& s2) |
{ | { |
while (*s1 && *s2) |
const Char16* s1c16 = s1.getChar16Data(); |
|
const Char16* s2c16 = s2.getChar16Data(); |
|
|
|
while (*s1c16 && *s2c16) |
{ | { |
int r = tolower(*s1++) - tolower(*s2++); |
int r = *s1c16++ - *s2c16++; |
| |
if (r) | if (r) |
return r; | return r; |
} | } |
| |
if (*s2) |
if (*s2c16) |
return -1; | return -1; |
else if (*s1) |
else if (*s1c16) |
return 1; | return 1; |
| |
return 0; | return 0; |
} | } |
| |
Boolean String::equal(const String& str1, const String& str2) |
int String::compareNoCase(const String& s1, const String& s2) |
{ | { |
if (str1.size() != str2.size()) |
#ifdef PEGASUS_HAS_ICU |
return false; |
if (InitializeICU::initICUSuccessful()) |
|
{ |
return String::compare(str1.getData(), str2.getData(), str1.size()) == 0; |
return u_strcasecmp((const UChar*)s1.getChar16Data(), |
|
(const UChar*)s2.getChar16Data(), |
|
U_FOLD_CASE_DEFAULT); |
} | } |
|
#endif |
|
const Char16* _s1 = s1.getChar16Data(); |
|
const Char16* _s2 = s2.getChar16Data(); |
| |
Boolean String::equal(const String& str1, const Char16* str2) |
while (*_s1 && *_s2) |
{ | { |
if (str1.size() != _StrLen(str2)) |
int r; |
return false; |
|
| |
return String::compare(str1.getData(), str2, str1.size()) == 0; |
if (*_s1 <= PEGASUS_MAX_PRINTABLE_CHAR && |
|
*_s2 <= PEGASUS_MAX_PRINTABLE_CHAR) |
|
{ |
|
r = tolower(*_s1++) - tolower(*_s2++); |
} | } |
|
else |
Boolean String::equal(const Char16* str1, const String& str2) |
|
{ | { |
return equal(str2, str1); |
r = *_s1++ - *_s2++; |
} | } |
| |
Boolean String::equal(const String& str1, const char* str2) |
if (r) |
{ |
return r; |
return equal(str1, String(str2)); |
} |
|
|
|
if (*_s2) |
|
return -1; |
|
else if (*_s1) |
|
return 1; |
|
|
|
return 0; |
} | } |
| |
Boolean String::equal(const char* str1, const String& str2) |
Boolean String::equal(const String& str1, const String& str2) |
{ | { |
return equal(String(str1), str2); |
return String::compare(str1, str2) == 0; |
} | } |
| |
Boolean String::equalNoCase(const String& str1, const String& str2) | Boolean String::equalNoCase(const String& str1, const String& str2) |
{ | { |
|
#ifdef PEGASUS_HAS_ICU |
|
return compareNoCase(str1, str2) == 0; |
|
#else |
if (str1.size() != str2.size()) | if (str1.size() != str2.size()) |
return false; | return false; |
| |
const Char16* p = str1.getData(); |
const Char16* p = str1.getChar16Data(); |
const Char16* q = str2.getData(); |
const Char16* q = str2.getChar16Data(); |
| |
Uint32 n = str1.size(); | Uint32 n = str1.size(); |
| |
while (n--) | while (n--) |
{ | { |
#ifdef PEGASUS_HAS_EBCDIC |
if (*p <= PEGASUS_MAX_PRINTABLE_CHAR && |
if (*p <= 255 && *q <= 255) |
*q <= PEGASUS_MAX_PRINTABLE_CHAR) |
#else |
|
if (*p <= 127 && *q <= 127) |
|
#endif |
|
{ | { |
if (tolower(*p++) != tolower(*q++)) | if (tolower(*p++) != tolower(*q++)) |
return false; | return false; |
|
|
} | } |
| |
return true; | return true; |
|
#endif |
|
} |
|
|
|
|
|
CString String::getCString() 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); |
} | } |
| |
//#define NEWMATCHFUNCTION |
#if 0 |
#if defined NEWMATCHFUNCTION |
// 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. |
| |
|
|
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. |
*/ | */ |
| |
|
|
| |
inline Uint16 _ToLower(Uint16 ch) | inline Uint16 _ToLower(Uint16 ch) |
{ | { |
#ifdef PEGASUS_HAS_EBCDIC |
// ICU_TODO: If ICU is available we should do this the correct way. |
return ch <= 255 ? tolower(char(ch)) : ch; |
return ch <= PEGASUS_MAX_PRINTABLE_CHAR ? tolower(char(ch)) : ch; |
#else |
|
return ch <= 127 ? tolower(char(ch)) : ch; |
|
#endif |
|
} | } |
| |
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 |
|
return ch1 == ch2; | return ch1 == ch2; |
} | } |
| |
|
|
pat = _matchrange(pat, *str, nocase); // and is a match | pat = _matchrange(pat, *str, nocase); // and is a match |
if (!pat) { //It is not a match | if (!pat) { //It is not a match |
done = 1; // we're done | done = 1; // we're done |
res = 1; // no match |
res = 0; // no match |
} else { //Range matches | } else { //Range matches |
str++, pat++; // keep going | str++, pat++; // keep going |
} | } |
|
|
return res; | return res; |
} | } |
| |
#else |
|
//////////////////////////////////////////////////////////////////////////////// |
|
// |
|
// String matching routines borrowed from Tcl 8.0: |
|
// |
|
//////////////////////////////////////////////////////////////////////////////// |
|
|
|
//////////////////////////////////////////////////////////////////////////////// |
|
// |
|
// This software is copyrighted by the Regents of the University of |
|
// California, Sun Microsystems, Inc., and other parties. The following |
|
// terms apply to all files associated with the software unless explicitly |
|
// disclaimed in individual files. |
|
// |
|
// The authors hereby grant permission to use, copy, modify, distribute, |
|
// and license this software and its documentation for any purpose, provided |
|
// that existing copyright notices are retained in all copies and that this |
|
// notice is included verbatim in any distributions. No written agreement, |
|
// license, or royalty fee is required for any of the authorized uses. |
|
// Modifications to this software may be copyrighted by their authors |
|
// and need not follow the licensing terms described here, provided that |
|
// the new terms are clearly indicated on the first page of each file where |
|
// they apply. |
|
// |
|
// IN NO EVENT SHALL THE AUTHORS OR DISTRIBUTORS BE LIABLE TO ANY PARTY |
|
// FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES |
|
// ARISING OUT OF THE USE OF THIS SOFTWARE, ITS DOCUMENTATION, OR ANY |
|
// DERIVATIVES THEREOF, EVEN IF THE AUTHORS HAVE BEEN ADVISED OF THE |
|
// POSSIBILITY OF SUCH DAMAGE. |
|
// |
|
// THE AUTHORS AND DISTRIBUTORS SPECIFICALLY DISCLAIM ANY WARRANTIES, |
|
// INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY, |
|
// FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. THIS SOFTWARE |
|
// IS PROVIDED ON AN "AS IS" BASIS, AND THE AUTHORS AND DISTRIBUTORS HAVE |
|
// NO OBLIGATION TO PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR |
|
// MODIFICATIONS. |
|
// |
|
// GOVERNMENT USE: If you are acquiring this software on behalf of the |
|
// U.S. government, the Government shall have only "Restricted Rights" |
|
// in the software and related documentation as defined in the Federal |
|
// Acquisition Regulations (FARs) in Clause 52.227.19 (c) (2). If you |
|
// are acquiring the software on behalf of the Department of Defense, the |
|
// software shall be classified as "Commercial Computer Software" and the |
|
// Government shall have only "Restricted Rights" as defined in Clause |
|
// 252.227-7013 (c) (1) of DFARs. Notwithstanding the foregoing, the |
|
// authors grant the U.S. Government and others acting in its behalf |
|
// permission to use and distribute the software in accordance with the |
|
// terms specified in this license. |
|
// |
|
//////////////////////////////////////////////////////////////////////////////// |
|
|
|
|
|
/* |
|
*---------------------------------------------------------------------- |
|
* |
|
* Tcl_StringMatch -- |
|
* |
|
* See if a particular string matches a particular pattern. |
|
* |
|
* 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. |
|
* |
|
*---------------------------------------------------------------------- |
|
*/ |
|
|
|
typedef Uint16 MatchChar; |
|
|
|
inline Uint16 _ToLower(Uint16 ch) |
|
{ |
|
#ifdef PEGASUS_HAS_EBCDIC |
|
return ch <= 255 ? tolower(char(ch)) : ch; |
|
#else |
|
return ch <= 127 ? tolower(char(ch)) : ch; |
|
#endif |
|
} |
|
|
|
inline Boolean _Equal(Uint16 ch1, Uint16 ch2, int nocase) |
|
{ |
|
if (nocase) |
|
return _ToLower(ch1) == _ToLower(ch2); |
|
else |
|
return ch1 == ch2; |
|
} |
|
|
|
int _StringMatch( |
|
MatchChar *string, /* String. */ |
|
MatchChar *pattern, /* Pattern, which may contain special |
|
* characters. */ |
|
int nocase) /* Ignore case if this is true */ |
|
{ |
|
MatchChar c2; |
|
|
|
while (1) { |
|
/* See if we're at the end of both the pattern and the string. |
|
* If so, we succeeded. If we're at the end of the pattern |
|
* but not at the end of the string, we failed. |
|
*/ |
|
|
|
if (*pattern == 0) { |
|
if (*string == 0) { |
|
return 1; |
|
} else { |
|
return 0; |
|
} |
|
} |
|
if ((*string == 0) && (*pattern != '*')) { |
|
return 0; |
|
} |
|
|
|
/* Check for a "*" as the next pattern character. It matches |
|
* any substring. We handle this by calling ourselves |
|
* recursively for each postfix of string, until either we |
|
* match or we reach the end of the string. |
|
*/ |
|
|
|
if (*pattern == '*') { |
|
pattern += 1; |
|
if (*pattern == 0) { |
|
return 1; |
|
} |
|
while (1) { |
|
if (_StringMatch(string, pattern, nocase)) { |
|
return 1; |
|
} |
|
if (*string == 0) { |
|
return 0; |
|
} |
|
string += 1; |
|
} |
|
} |
|
|
|
/* Check for a "?" as the next pattern character. It matches |
|
* any single character. |
|
*/ |
|
|
|
if (*pattern == '?') { |
|
goto thisCharOK; |
|
} |
|
|
|
/* Check for a "[" as the next pattern character. It is followed |
|
* by a list of characters that are acceptable, or by a range |
|
* (two characters separated by "-"). |
|
*/ |
|
|
|
if (*pattern == '[') { |
|
pattern += 1; |
|
while (1) { |
|
if ((*pattern == ']') || (*pattern == 0)) { |
|
return 0; |
|
} |
|
if (_Equal(*pattern, *string, nocase)) { |
|
break; |
|
} |
|
if (pattern[1] == '-') { |
|
c2 = pattern[2]; |
|
if (c2 == 0) { |
|
return 0; |
|
} |
|
if ((*pattern <= *string) && (c2 >= *string)) { |
|
break; |
|
} |
|
if ((*pattern >= *string) && (c2 <= *string)) { |
|
break; |
|
} |
|
pattern += 2; |
|
} |
|
pattern += 1; |
|
} |
|
while (*pattern != ']') { |
|
if (*pattern == 0) { |
|
pattern--; |
|
break; |
|
} |
|
pattern += 1; |
|
} |
|
goto thisCharOK; |
|
} |
|
|
|
/* If the next pattern character is '/', just strip off the '/' |
|
* so we do exact matching on the character that follows. |
|
*/ |
|
|
|
if (*pattern == '\\') { |
|
pattern += 1; |
|
if (*pattern == 0) { |
|
return 0; |
|
} |
|
} |
|
| |
/* There's no special character. Just make sure that the next |
/** match matches a string against a GLOB style pattern. |
* characters of each string match. |
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> |
*/ | */ |
|
|
if (!_Equal(*pattern, *string, nocase)) { |
|
return 0; |
|
} |
|
|
|
thisCharOK: pattern += 1; |
|
string += 1; |
|
} |
|
} |
|
#endif |
|
|
|
Boolean String::match(const String& str, const String& pattern) | Boolean String::match(const String& str, const String& pattern) |
{ | { |
return _StringMatch( | return _StringMatch( |
(Uint16*)str.getData(), (Uint16*)pattern.getData(), 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 |
|
@see 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.getData(), (Uint16*)pattern.getData(), 1) != 0; |
(Uint16*)str.getChar16Data(), (Uint16*)pattern.getChar16Data(), 1) != 0; |
} | } |
|
#endif |
| |
| |
/////////////////////////////////////////////////////////////////////////////// | /////////////////////////////////////////////////////////////////////////////// |
|
|
return !String::equal(str1, str2); | return !String::equal(str1, str2); |
} | } |
| |
PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& str1) |
PEGASUS_STD(ostream)& operator<<(PEGASUS_STD(ostream)& os, const String& str) |
|
{ |
|
|
|
#if defined(PEGASUS_OS_OS400) |
|
CString cstr = str.getCString(); |
|
const char* utf8str = cstr; |
|
|
|
os << utf8str; |
|
|
|
#elif defined(PEGASUS_HAS_ICU) |
|
if (InitializeICU::initICUSuccessful()) |
|
{ |
|
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 |
|
#endif // End of PEGASUS_HAS_ICU #else leg. |
|
{ |
|
for (Uint32 i = 0, n = str.size(); i < n; i++) |
|
{ |
|
Uint16 code = str[i]; |
|
|
|
if (code > 0 && code <= PEGASUS_MAX_PRINTABLE_CHAR) |
{ | { |
for (Uint32 i = 0, n = str1.size(); i < n; i++) |
os << char(code); |
os << str1[i]; |
} |
|
else |
|
{ |
|
// Print in hex format: |
|
char buffer[8]; |
|
sprintf(buffer, "\\x%04X", code); |
|
os << buffer; |
|
} |
|
} |
|
} |
| |
return os; | return os; |
} | } |
|
|
| |
Boolean operator<(const String& str1, const String& str2) | Boolean operator<(const String& str1, const String& str2) |
{ | { |
return String::compare(str1.getData(), str2.getData()) < 0; |
return String::compare(str1, str2) < 0; |
} | } |
| |
Boolean operator<=(const String& str1, const String& str2) | Boolean operator<=(const String& str1, const String& str2) |
{ | { |
return String::compare(str1.getData(), str2.getData()) <= 0; |
return String::compare(str1, str2) <= 0; |
} | } |
| |
Boolean operator>(const String& str1, const String& str2) | Boolean operator>(const String& str1, const String& str2) |
{ | { |
return String::compare(str1.getData(), str2.getData()) > 0; |
return String::compare(str1, str2) > 0; |
} | } |
| |
Boolean operator>=(const String& str1, const String& str2) | Boolean operator>=(const String& str1, const String& str2) |
{ | { |
return String::compare(str1.getData(), str2.getData()) >= 0; |
return String::compare(str1, str2) >= 0; |
} |
|
|
|
int CompareNoCase(const char* s1, const char* s2) |
|
{ |
|
while (*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; |
|
} | } |
| |
PEGASUS_NAMESPACE_END | PEGASUS_NAMESPACE_END |