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
|
/******************************************************************************
* Copyright (c) 2000-2016 Ericsson Telecom AB
* All rights reserved. This program and the accompanying materials
* are made available under the terms of the Eclipse Public License v1.0
* which accompanies this distribution, and is available at
* http://www.eclipse.org/legal/epl-v10.html
*
* Contributors:
* Balasko, Jeno
* Raduly, Csaba
*
******************************************************************************/
module UTF8 {
/*
Unicode code points and UTF-8 encodings for accented Latin letters.
The code points below 0xFF match the encoding in codepage 1252
(a.k.a. Windows Latin1) which is almost, but not quite, the same as ISO-8859-1.
There are no differences for these characters.
The names correspond to the HTML entitiy names (case sensitive).
The first (simple) is the Unicode code point (which, even at 1 byte,
doesn't fit into a charstring because the value is more than 127).
The entries with octetstring type and suffix of 8 are the UTF8 encoding.
*/
const universal charstring Aacute := char(0,0,0,193); // 0xC1
const octetstring Aacute8 := 'C381'O;
// Although the Unicode name is LATIN CAPITAL LETTER A WITH DIAERESIS,
// the HTML entity name is Auml. Same for the other umlaut characters.
const universal charstring Auml := char(0,0,0,196); // 0xC4
const octetstring Auml8 := 'C384'O
const universal charstring Eacute := char(0,0,0,201); // 0xC9
const octetstring Eacute8 := 'C389'O
const universal charstring Euml := char(0,0,0,203); // 0xCB
const octetstring Euml8 := 'C38B'O
const universal charstring Iacute := char(0,0,0,205); // 0xCD
const octetstring Iacute8 := 'C38D'O
const universal charstring Iuml := char(0,0,0,207); // 0xCF
const octetstring Iuml8 := 'C38F'O
const universal charstring Oacute := char(0,0,0,211); // 0xD3
const octetstring Oacute8 := 'C393'O
const universal charstring Ouml := char(0,0,0,214); // 0xD6
const octetstring Ouml8 := 'C396'O
const universal charstring Uacute := char(0,0,0,218); // 0xDA
const octetstring Uacute8 := 'C39A'O
const universal charstring Uuml := char(0,0,0,220); // 0xDC
const octetstring Uuml8 := 'C39C'O
const universal charstring aacute := char(0,0,0,225); // 0xE1
const octetstring aacute8 := 'C3A1'O
const universal charstring auml := char(0,0,0,228); // 0xE4
const octetstring auml8 := 'C3A4'O
const universal charstring eacute := char(0,0,0,233); // 0xE9
const octetstring eacute8 := 'C3A9'O
const universal charstring euml := char(0,0,0,235); // 0xEB
const octetstring euml8 := 'C3AB'O
const universal charstring iacute := char(0,0,0,237); // 0xED
const octetstring iacute8 := 'C3AD'O
const universal charstring iuml := char(0,0,0,239); // 0xEF
const octetstring iuml8 := 'C3AF'O
const universal charstring oacute := char(0,0,0,243); // 0xF3
const octetstring oacute8 := 'C3B3'O
const universal charstring ouml := char(0,0,0,246); // 0xF6
const octetstring ouml8 := 'C3B6'O
const universal charstring uacute := char(0,0,0,250); // 0xFA
const octetstring uacute8 := 'C3BA'O
const universal charstring uuml := char(0,0,0,252); // 0xFC
const octetstring uuml8 := 'C3BC'O
// Latin Extended-A, not in Latin-1
const universal charstring Odouble := char(0,0,1,80); // 0x150
const octetstring Odouble8 := 'C590'O
const universal charstring odouble := char(0,0,1,81); // 0x151
const octetstring odouble8 := 'C591'O
const universal charstring Udouble := char(0,0,1,112); // 0x170
const octetstring Udouble8 := 'C5B0'O
const universal charstring udouble := char(0,0,1,113); // 0x171
const octetstring udouble8 := 'C5B1'O
}
|
