1 /*
2 * Copyright (c) 2005, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 /*
27 */
28
29 /*
30 * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved
31 * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved
32 *
33 * The original version of this source code and documentation
34 * is copyrighted and owned by Taligent, Inc., a wholly-owned
35 * subsidiary of IBM. These materials are provided under terms
36 * of a License Agreement between Taligent and Sun. This technology
37 * is protected by multiple US and International patents.
38 *
39 * This notice and attribution to Taligent may not be removed.
40 * Taligent is a registered trademark of Taligent, Inc.
41 *
42 */
43
44 package sun.text.resources;
45
46 import java.util.ListResourceBundle;
47
48 public class CollationData_th extends ListResourceBundle {
49
50 protected final Object[][] getContents() {
51 return new Object[][] {
52 { "Rule",
53 "! " // First turn on the SE Asian Vowel/Consonant
54 // swapping rule
55 + "& Z " // Put in all of the consonants, after Z
56 + "< \u0E01 " // KO KAI
57 + "< \u0E02 " // KHO KHAI
58 + "< \u0E03 " // KHO KHUAT
59 + "< \u0E04 " // KHO KHWAI
60 + "< \u0E05 " // KHO KHON
61 + "< \u0E06 " // KHO RAKHANG
62 + "< \u0E07 " // NGO NGU
63 + "< \u0E08 " // CHO CHAN
64 + "< \u0E09 " // CHO CHING
65 + "< \u0E0A " // CHO CHANG
66 + "< \u0E0B " // SO SO
67 + "< \u0E0C " // CHO CHOE
68 + "< \u0E0D " // YO YING
69 + "< \u0E0E " // DO CHADA
70 + "< \u0E0F " // TO PATAK
71 + "< \u0E10 " // THO THAN
72 + "< \u0E11 " // THO NANGMONTHO
73 + "< \u0E12 " // THO PHUTHAO
74 + "< \u0E13 " // NO NEN
75 + "< \u0E14 " // DO DEK
76 + "< \u0E15 " // TO TAO
77 + "< \u0E16 " // THO THUNG
78 + "< \u0E17 " // THO THAHAN
79 + "< \u0E18 " // THO THONG
80 + "< \u0E19 " // NO NU
81 + "< \u0E1A " // BO BAIMAI
82 + "< \u0E1B " // PO PLA
83 + "< \u0E1C " // PHO PHUNG
84 + "< \u0E1D " // FO FA
85 + "< \u0E1E " // PHO PHAN
86 + "< \u0E1F " // FO FAN
87 + "< \u0E20 " // PHO SAMPHAO
88 + "< \u0E21 " // MO MA
89 + "< \u0E22 " // YO YAK
90 + "< \u0E23 " // RO RUA
91 + "< \u0E24 " // RU
92 + "< \u0E25 " // LO LING
93 + "< \u0E26 " // LU
94 + "< \u0E27 " // WO WAEN
95 + "< \u0E28 " // SO SALA
96 + "< \u0E29 " // SO RUSI
97 + "< \u0E2A " // SO SUA
98 + "< \u0E2B " // HO HIP
99 + "< \u0E2C " // LO CHULA
100 + "< \u0E2D " // O ANG
101 + "< \u0E2E " // HO NOKHUK
102
103 //
104 // Normal vowels
105 //
106 + "< \u0E30 " // SARA A
107 + "< \u0E31 " // MAI HAN-AKAT
108 + "< \u0E32 " // SARA AA
109
110 // Normalizer will decompose this character to \u0e4d\u0e32. This is
111 // a Bad Thing, because we want the separate characters to sort
112 // differently than this individual one. Since there's no public way to
113 // set the decomposition to be used when creating a collator, there's
114 // no way around this right now.
115 // It's best to go ahead and leave the character in, because it occurs
116 // this way a lot more often than it occurs as separate characters.
117 + "< \u0E33 " // SARA AM
118
119 + "< \u0E34 " // SARA I
120
121 + "< \u0E35 " // SARA II
122 + "< \u0E36 " // SARA UE
123 + "< \u0E37 " // SARA UEE
124 + "< \u0E38 " // SARA U
125 + "< \u0E39 " // SARA UU
126
127 //
128 // Preceding vowels
129 //
130 + "< \u0E40 " // SARA E
131 + "< \u0E41 " // SARA AE
132 + "< \u0E42 " // SARA O
133 + "< \u0E43 " // SARA AI MAIMUAN
134 + "< \u0E44 " // SARA AI MAIMALAI
135
136 //
137 // Digits
138 //
139 + "< \u0E50 " // DIGIT ZERO
140 + "< \u0E51 " // DIGIT ONE
141 + "< \u0E52 " // DIGIT TWO
142 + "< \u0E53 " // DIGIT THREE
143 + "< \u0E54 " // DIGIT FOUR
144 + "< \u0E55 " // DIGIT FIVE
145 + "< \u0E56 " // DIGIT SIX
146 + "< \u0E57 " // DIGIT SEVEN
147 + "< \u0E58 " // DIGIT EIGHT
148 + "< \u0E59 " // DIGIT NINE
149
150 // Sorta tonal marks, but maybe not really
151 + "< \u0E4D " // NIKHAHIT
152
153 //
154 // Thai symbols are supposed to sort "after white space".
155 // I'm treating this as making them sort just after the normal Latin-1
156 // symbols, which are in turn after the white space.
157 //
158 + "&'\u007d'" // right-brace
159 + "< \u0E2F " // PAIYANNOI (ellipsis, abbreviation)
160 + "< \u0E46 " // MAIYAMOK
161 + "< \u0E4F " // FONGMAN
162 + "< \u0E5A " // ANGKHANKHU
163 + "< \u0E5B " // KHOMUT
164 + "< \u0E3F " // CURRENCY SYMBOL BAHT
165
166 // These symbols are supposed to be "after all characters"
167 + "< \u0E4E " // YAMAKKAN
168
169 // This rare symbol also comes after all characters. But when it is
170 // used in combination with RU and LU, the combination is treated as
171 // a separate letter, ala "CH" sorting after "C" in traditional Spanish.
172 + "< \u0E45 " // LAKKHANGYAO
173 + "& \u0E24 < \u0E24\u0E45 "
174 + "& \u0E26 < \u0E26\u0E45 "
175
176 // Tonal marks are primary ignorables but are treated as secondary
177 // differences
178 + "& \u0301 " // acute accent
179 + "; \u0E47 " // MAITAIKHU
180 + "; \u0E48 " // MAI EK
181 + "; \u0E49 " // MAI THO
182 + "; \u0E4A " // MAI TRI
183 + "; \u0E4B " // MAI CHATTAWA
184 + "; \u0E4C " // THANTHAKHAT
185
186
187 // These are supposed to be ignored, so I'm treating them as controls
188 + "& \u0001 "
189 + "= \u0E3A " // PHINTHU
190 + "= '.' " // period
191 }
192 };
193 }
194 }