paweld/lazarus
1
0
Fork 0
mirror of https://gitlab.com/freepascal.org/lazarus/lazarus.git synced 2025-06-13 13:28:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

LCL: improved UTF8FindNearestCharStart

Browse Source 
git-svn-id: trunk@27831 -
This commit is contained in:
mattias 2010-10-24 17:44:33 +00:00
parent b3b03bfaea
commit af460b1644
1 changed files with 33 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
lcl/lclproc.pas
View File

@ -3316,27 +3316,48 @@ begin
end; end;
end; end;
{ Find the start of the UTF8 character which contains BytePos,
Len is length in byte, BytePos starts at 0 }
function UTF8FindNearestCharStart(UTF8Str: PChar; Len: integer; function UTF8FindNearestCharStart(UTF8Str: PChar; Len: integer;
BytePos: integer): integer; BytePos: integer): integer;
var
CharLen: LongInt;
begin begin
Result:=0; Result:=0;
if UTF8Str<>nil then begin if (UTF8Str<>nil) and (Len>0) and (BytePos>=0) then begin
if BytePos>Len then BytePos:=Len; Result:=BytePos;
while (BytePos>0) do begin if Result>Len then Result:=Len-1;
CharLen:=UTF8CharacterLength(UTF8Str); if (Result>0) and (ord(UTF8Str[Result]) and %11000000=%10000000) then begin
dec(BytePos,CharLen); dec(Result);
if (BytePos<0) then exit; if (Result>0) and (ord(UTF8Str[Result]) and %11000000=%10000000) then begin
inc(Result,CharLen); dec(Result);
if (BytePos=0) then exit; if (Result>0) and (ord(UTF8Str[Result]) and %11000000=%10000000) then begin
inc(UTF8Str,CharLen); dec(Result);
// should be four byte character
if (ord(UTF8Str[Result]) and %11111000<>%11110000) then begin
// broken UTF8 character
inc(Result,3);
end else begin
// is four byte character
end;
end else if (ord(UTF8Str[Result]) and %11110000<>%11100000) then begin
// broken UTF8 character, should be three byte
inc(Result,2);
end else
begin
// is three byte character
end;
end else if (ord(UTF8Str[Result]) and %11100000<>%11000000) then begin
// broken UTF8 character, should be two byte
inc(Result);
end else
begin
// is two byte character
end;
end; end;
end; end;
end; end;
{ Len is the length in bytes of UTF8Str { Len is the length in bytes of UTF8Str
CharIndex is the position of the desired char, in chars CharIndex is the position of the desired char (starting at 0), in chars
This function is similar to UTF8FindNearestCharStart This function is similar to UTF8FindNearestCharStart
} }