1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
{
This is a test program for LazUnicode unit.
Works with UTF-8 and UTF-16 encodings by switching UseUTF16 define.
Works also in Delphi where String=UnicodeString. Just rename this file as *.dpr.
For Delphi you must copy units LazUnicode and LazUTF16, both part of LazUtils package.
}
program LazUnicodeConsole;
{$IFDEF FPC}
{$mode objfpc}{$H+}
{$ENDIF}
{$APPTYPE CONSOLE} // Mostly for Delphi
// For testing the UTF16 version.
{$IF DEFINED(FPC) and DEFINED(UseUTF16)}
{$ModeSwitch UnicodeStrings} // Sets also FPC_UNICODESTRINGS.
{$ENDIF}
{$IF DEFINED(FPC_UNICODESTRINGS) or not DEFINED(FPC)}
{$DEFINE ReallyUseUTF16} // FPC with UTF-16 or Delphi
{$ENDIF}
uses
LazUnicode;
const
Eyes = '👀';
Thai = 'ฃ'; // No idea what it means.
WineGlass = '🍷';
Heart = '💓'; // or '♡';
// Accents in combining codepoints. Last one has 2 consecutive combining marks.
Combining = 'ÓÓỐỐỚỚÒÒỒỒỎỎỔỔỞỞỌỌBあC'#$CC#$81#$CC#$B2;
//ArEnStr1 = 'مAرBحCبDاE';
var
s_UTF8: {$IFDEF FPC}AnsiString{$ELSE}String{$ENDIF};
s, ch: String;
//CodeUnit: Char;
i: NativeInt;
cpIter: TCodePointEnumerator;
ucIter: TUnicodeCharacterEnumerator;
begin
s_UTF8 := 'Pöö ' + Eyes + Thai + '. Have ' + WineGlass + ' for FPC' + Heart + 'Lazarus';
s := s_UTF8; // Converts encoding when needed.
{$IFDEF ReallyUseUTF16}
writeln('Using UnicodeString + UTF-16');
{$ELSE}
writeln('Using AnsiString + UTF-8');
{$ENDIF}
writeln('Sizeof(Char) = ', Sizeof(Char));
writeln('Testing with string: ', s);
writeln('');
ch := CodePointCopy(s, 14, 1); // Should return the wine glass.
writeln('Testing CodePointCopy. SubString = "', ch + '"');
i := CodePointLength(s); // Should return 30.
writeln('Testing CodePointLength. Result = ', i);
// Constant must be assigned to AnsiString when using the UTF-8 system.
s_UTF8 := WineGlass;
i := CodePointPos(s_UTF8, s); // Should return 14.
writeln('Testing CodePointPos. Result = ', i);
s_UTF8 := '☐';
i := CodePointPos(s_UTF8, s); // Should return 0.
writeln('Testing CodePointPos for non-existent char. Result = ', i);
// Use CodePoint enumerator explicitly
writeln('');
writeln('*** Using CodePoint enumerator explicitly: ***');
cpIter := TCodePointEnumerator.Create(s);
while cpIter.MoveNext do
writeln('ch=', cpIter.Current, ' has ', cpIter.CurrentCodeUnitCount, ' codeunits.');
cpIter.Free;
s_UTF8 := Combining;
s := s_UTF8; // Converts encoding when needed.
writeln('');
writeln('Testing with string: ', s);
// Use UnicodeCharacter enumerator explicitly
writeln('');
writeln('*** Using UnicodeCharacter enumerator explicitly: ***');
ucIter := TUnicodeCharacterEnumerator.Create(s);
while ucIter.MoveNext do
writeln('ch=', ucIter.Current, ' has ', ucIter.CurrentCodePointCount, ' codepoints and ', ucIter.CurrentCodeUnitCount, ' codeunits.');
ucIter.Free;
{$IFDEF FPC}
// Use for-in loop for Unicode Characters.
writeln('');
writeln('*** Using for-in loop for Unicode Characters : ***');
for ch in s do
writeln('ch=',ch);
{$ENDIF}
// for-in loop for codeunits using a Char variable still works.
{ Uncomment to test.
writeln('');
writeln('*** Using for-in loop for codeunits: ***');
for CodeUnit in s do
writeln('CodeUnit=',CodeUnit); // The output makes no sense obviously.
}
end.
|
