mirror of
https://gitlab.com/freepascal.org/fpc/source.git
synced 2025-05-01 09:33:40 +02:00
aee5380ae0
o support for the new codepage-aware ansistrings in the jvm branch
o empty ansistrings are now always represented by a nil pointer rather than
by an empty string, because an empty string also has a code page which
can confuse code (although this will make ansistrings harder to use
in Java code)
o more string helpers code shared between the general and jvm rtl
o support for indexbyte/word in the jvm rtl (warning: first parameter
is an open array rather than an untyped parameter there, so
indexchar(pcharvar^,10,0) will be equivalent to
indexchar[pcharvar^],10,0) there, which is different from what is
intended; changing it to an untyped parameter wouldn't help though)
o default() support is not yet complete
o calling fpcres is currently broken due to limitations in
sysutils.executeprocess() regarding handling unix quoting and
the compiler using the same command lines for scripts and directly
calling external programs
o compiling the Java compiler currently requires adding ALLOW_WARNINGS=1
to the make command line
git-svn-id: branches/jvmbackend@20887 -
147 lines
8.1 KiB
PHP
147 lines
8.1 KiB
PHP
{
|
|
This file is part of the Free Pascal run time library.
|
|
Copyright (c) 1999-2005 by Florian Klaempfl,
|
|
member of the Free Pascal development team.
|
|
|
|
This file implements support routines for UnicodeStrings with FPC
|
|
|
|
See the file COPYING.FPC, included in this distribution,
|
|
for details about the copyright.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
|
|
**********************************************************************}
|
|
|
|
|
|
Procedure UniqueString (Var S : UnicodeString);external name 'FPC_UNICODESTR_UNIQUE';
|
|
Function Pos (Const Substr : UnicodeString; Const Source : UnicodeString) : SizeInt;
|
|
Function Pos (c : Char; Const s : UnicodeString) : SizeInt;
|
|
Function Pos (c : UnicodeChar; Const s : UnicodeString) : SizeInt;
|
|
Function Pos (const c : RawByteString; Const s : UnicodeString) : SizeInt;
|
|
Function Pos (const c : UnicodeString; Const s : RawByteString) : SizeInt;
|
|
Function Pos (const c : ShortString; Const s : UnicodeString) : SizeInt;
|
|
|
|
Function UpCase(const s : UnicodeString) : UnicodeString;
|
|
Function UpCase(c:UnicodeChar):UnicodeChar;
|
|
Function LowerCase(const s : UnicodeString) : UnicodeString;
|
|
Function LowerCase(c:UnicodeChar):UnicodeChar;
|
|
|
|
Procedure Insert (Const Source : UnicodeString; Var S : UnicodeString; Index : SizeInt);
|
|
Procedure Delete (Var S : UnicodeString; Index,Size: SizeInt);
|
|
Procedure SetString (Out S : UnicodeString; Buf : PUnicodeChar; Len : SizeInt);
|
|
Procedure SetString (Out S : UnicodeString; Buf : PChar; Len : SizeInt);
|
|
|
|
function WideCharToString(S : PWideChar) : UnicodeString;
|
|
function StringToWideChar(const Src : RawByteString;Dest : PWideChar;DestSize : SizeInt) : PWideChar;
|
|
function WideCharLenToString(S : PWideChar;Len : SizeInt) : UnicodeString;
|
|
procedure WideCharLenToStrVar(Src : PWideChar;Len : SizeInt;out Dest : UnicodeString);
|
|
procedure WideCharLenToStrVar(Src : PWideChar;Len : SizeInt;out Dest : AnsiString);
|
|
procedure WideCharToStrVar(S : PWideChar;out Dest : UnicodeString);
|
|
procedure WideCharToStrVar(S : PWideChar;out Dest : AnsiString);
|
|
|
|
function UnicodeCharToString(S : PUnicodeChar) : UnicodeString;
|
|
function StringToUnicodeChar(const Src : RawByteString;Dest : PUnicodeChar;DestSize : SizeInt) : PUnicodeChar;
|
|
function UnicodeCharLenToString(S : PUnicodeChar;Len : SizeInt) : UnicodeString;
|
|
procedure UnicodeCharLenToStrVar(Src : PUnicodeChar;Len : SizeInt;out Dest : UnicodeString);
|
|
procedure UnicodeCharLenToStrVar(Src : PUnicodeChar;Len : SizeInt;out Dest : AnsiString);
|
|
procedure UnicodeCharToStrVar(S : PUnicodeChar;out Dest : AnsiString);
|
|
|
|
procedure DefaultUnicode2AnsiMove(source:punicodechar;var dest:RawByteString;cp : TSystemCodePage;len:SizeInt);
|
|
procedure DefaultAnsi2UnicodeMove(source:pchar;cp : TSystemCodePage;var dest:unicodestring;len:SizeInt);
|
|
|
|
Type
|
|
TStandardCodePageEnum = (
|
|
scpAnsi, // system Ansi code page (GetACP on windows)
|
|
scpConsoleInput, // system console input code page (GetConsoleCP on windows)
|
|
scpConsoleOutput // system console output code page (GetConsoleOutputCP on windows)
|
|
);
|
|
|
|
{$ifndef FPC_HAS_BUILTIN_WIDESTR_MANAGER}
|
|
{ hooks for internationalization
|
|
please add new procedures at the end, it makes it easier to detect new procedures }
|
|
TUnicodeStringManager = record
|
|
Wide2AnsiMoveProc : procedure(source:pwidechar;var dest:RawByteString;cp : TSystemCodePage;len:SizeInt);
|
|
Ansi2WideMoveProc : procedure(source:pchar;cp : TSystemCodePage;var dest:widestring;len:SizeInt);
|
|
|
|
// UpperUTF8 : procedure(p:PUTF8String);
|
|
|
|
UpperWideStringProc : function(const S: WideString): WideString;
|
|
// UpperUCS4 : procedure(p:PUCS4Char);
|
|
// LowerUTF8 : procedure(p:PUTF8String);
|
|
LowerWideStringProc : function(const S: WideString): WideString;
|
|
// LowerUCS4 : procedure(p:PUCS4Char);
|
|
{
|
|
CompUTF8 : function(p1,p2:PUTF8String) : shortint;
|
|
CompUCS2 : function(p1,p2:PUCS2Char) : shortint;
|
|
CompUCS4 : function(p1,p2:PUC42Char) : shortint;
|
|
}
|
|
CompareWideStringProc : function(const s1, s2 : WideString) : PtrInt;
|
|
CompareTextWideStringProc : function(const s1, s2 : WideString): PtrInt;
|
|
{ return value: number of code points in the string. Whenever an invalid
|
|
code point is encountered, all characters part of this invalid code point
|
|
are considered to form one "character" and the next character is
|
|
considered to be the start of a new (possibly also invalid) code point }
|
|
CharLengthPCharProc : function(const Str: PChar): PtrInt;
|
|
{ return value:
|
|
-1 if incomplete or invalid code point
|
|
0 if NULL character,
|
|
> 0 if that's the length in bytes of the code point }
|
|
CodePointLengthProc : function(const Str: PChar; MaxLookAead: PtrInt): Ptrint;
|
|
|
|
UpperAnsiStringProc : function(const s : ansistring) : ansistring;
|
|
LowerAnsiStringProc : function(const s : ansistring) : ansistring;
|
|
CompareStrAnsiStringProc : function(const S1, S2: ansistring): PtrInt;
|
|
CompareTextAnsiStringProc : function(const S1, S2: ansistring): PtrInt;
|
|
StrCompAnsiStringProc : function(S1, S2: PChar): PtrInt;
|
|
StrICompAnsiStringProc : function(S1, S2: PChar): PtrInt;
|
|
StrLCompAnsiStringProc : function(S1, S2: PChar; MaxLen: PtrUInt): PtrInt;
|
|
StrLICompAnsiStringProc : function(S1, S2: PChar; MaxLen: PtrUInt): PtrInt;
|
|
StrLowerAnsiStringProc : function(Str: PChar): PChar;
|
|
StrUpperAnsiStringProc : function(Str: PChar): PChar;
|
|
ThreadInitProc : procedure;
|
|
ThreadFiniProc : procedure;
|
|
|
|
{ this is only different on windows }
|
|
Unicode2AnsiMoveProc : procedure(source:punicodechar;var dest:RawByteString;cp : TSystemCodePage;len:SizeInt);
|
|
Ansi2UnicodeMoveProc : procedure(source:pchar;cp : TSystemCodePage;var dest:unicodestring;len:SizeInt);
|
|
UpperUnicodeStringProc : function(const S: UnicodeString): UnicodeString;
|
|
LowerUnicodeStringProc : function(const S: UnicodeString): UnicodeString;
|
|
CompareUnicodeStringProc : function(const s1, s2 : UnicodeString) : PtrInt;
|
|
CompareTextUnicodeStringProc : function(const s1, s2 : UnicodeString): PtrInt;
|
|
|
|
{ codepage retrieve function }
|
|
GetStandardCodePageProc: function(const stdcp: TStandardCodePageEnum): TSystemCodePage;
|
|
end;
|
|
{$endif FPC_HAS_BUILTIN_WIDESTR_MANAGER}
|
|
|
|
var
|
|
widestringmanager : TUnicodeStringManager;
|
|
|
|
function UnicodeToUtf8(Dest: PChar; Source: PUnicodeChar; MaxBytes: SizeInt): SizeInt;{$ifdef SYSTEMINLINE}inline;{$endif}
|
|
function UnicodeToUtf8(Dest: PChar; MaxDestBytes: SizeUInt; Source: PUnicodeChar; SourceChars: SizeUInt): SizeUInt;
|
|
function Utf8ToUnicode(Dest: PUnicodeChar; Source: PChar; MaxChars: SizeInt): SizeInt;{$ifdef SYSTEMINLINE}inline;{$endif}
|
|
function Utf8ToUnicode(Dest: PUnicodeChar; MaxDestChars: SizeUInt; Source: PChar; SourceBytes: SizeUInt): SizeUInt;
|
|
function UTF8Encode(const s : RawByteString) : RawByteString; inline;
|
|
function UTF8Encode(const s : UnicodeString) : RawByteString;
|
|
function UTF8Decode(const s : RawByteString): UnicodeString;
|
|
function AnsiToUtf8(const s : RawByteString): RawByteString;{$ifdef SYSTEMINLINE}inline;{$endif}
|
|
function Utf8ToAnsi(const s : RawByteString) : RawByteString;{$ifdef SYSTEMINLINE}inline;{$endif}
|
|
function UnicodeStringToUCS4String(const s : UnicodeString) : UCS4String;
|
|
function UCS4StringToUnicodeString(const s : UCS4String) : UnicodeString;
|
|
function WideStringToUCS4String(const s : WideString) : UCS4String;
|
|
function UCS4StringToWideString(const s : UCS4String) : WideString;
|
|
|
|
Procedure GetWideStringManager (Var Manager : TUnicodeStringManager);
|
|
Procedure SetWideStringManager (Const New : TUnicodeStringManager);
|
|
Procedure SetWideStringManager (Const New : TUnicodeStringManager; Var Old: TUnicodeStringManager);
|
|
|
|
Procedure GetUnicodeStringManager (Var Manager : TUnicodeStringManager);
|
|
Procedure SetUnicodeStringManager (Const New : TUnicodeStringManager);
|
|
Procedure SetUnicodeStringManager (Const New : TUnicodeStringManager; Var Old: TUnicodeStringManager);
|
|
|
|
function StringElementSize(const S : UnicodeString): Word; overload;
|
|
function StringRefCount(const S : UnicodeString): SizeInt; overload;
|
|
function StringCodePage(const S : UnicodeString): TSystemCodePage; overload;
|