2362N/A * Copyright (c) 2005, Oracle and/or its affiliates. All rights reserved. 0N/A * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 0N/A * This code is free software; you can redistribute it and/or modify it 0N/A * under the terms of the GNU General Public License version 2 only, as 2362N/A * published by the Free Software Foundation. Oracle designates this 0N/A * particular file as subject to the "Classpath" exception as provided 2362N/A * by Oracle in the LICENSE file that accompanied this code. 0N/A * This code is distributed in the hope that it will be useful, but WITHOUT 0N/A * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 0N/A * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 0N/A * version 2 for more details (a copy is included in the LICENSE file that 0N/A * accompanied this code). 0N/A * You should have received a copy of the GNU General Public License version 0N/A * 2 along with this work; if not, write to the Free Software Foundation, 0N/A * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 2362N/A * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 2362N/A * or visit www.oracle.com if you need additional information or have any 0N/A * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved 0N/A * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved 0N/A * The original version of this source code and documentation 0N/A * is copyrighted and owned by Taligent, Inc., a wholly-owned 0N/A * subsidiary of IBM. These materials are provided under terms 0N/A * of a License Agreement between Taligent and Sun. This technology 0N/A * is protected by multiple US and International patents. 0N/A * This notice and attribution to Taligent may not be removed. 0N/A * Taligent is a registered trademark of Taligent, Inc. 0N/A +
"& Z " // Put in all of the consonants, after Z 0N/A +
"< \u0E01 " // KO KAI 0N/A +
"< \u0E02 " // KHO KHAI 0N/A +
"< \u0E03 " // KHO KHUAT 0N/A +
"< \u0E04 " // KHO KHWAI 0N/A +
"< \u0E05 " // KHO KHON 0N/A +
"< \u0E06 " // KHO RAKHANG 0N/A +
"< \u0E07 " // NGO NGU 0N/A +
"< \u0E08 " // CHO CHAN 0N/A +
"< \u0E09 " // CHO CHING 0N/A +
"< \u0E0A " // CHO CHANG 0N/A +
"< \u0E0B " // SO SO 0N/A +
"< \u0E0C " // CHO CHOE 0N/A +
"< \u0E0D " // YO YING 0N/A +
"< \u0E0E " // DO CHADA 0N/A +
"< \u0E0F " // TO PATAK 0N/A +
"< \u0E10 " // THO THAN 0N/A +
"< \u0E11 " // THO NANGMONTHO 0N/A +
"< \u0E12 " // THO PHUTHAO 0N/A +
"< \u0E13 " // NO NEN 0N/A +
"< \u0E14 " // DO DEK 0N/A +
"< \u0E15 " // TO TAO 0N/A +
"< \u0E16 " // THO THUNG 0N/A +
"< \u0E17 " // THO THAHAN 0N/A +
"< \u0E18 " // THO THONG 0N/A +
"< \u0E19 " // NO NU 0N/A +
"< \u0E1A " // BO BAIMAI 0N/A +
"< \u0E1B " // PO PLA 0N/A +
"< \u0E1C " // PHO PHUNG 0N/A +
"< \u0E1D " // FO FA 0N/A +
"< \u0E1E " // PHO PHAN 0N/A +
"< \u0E1F " // FO FAN 0N/A +
"< \u0E20 " // PHO SAMPHAO 0N/A +
"< \u0E21 " // MO MA 0N/A +
"< \u0E22 " // YO YAK 0N/A +
"< \u0E23 " // RO RUA 0N/A +
"< \u0E25 " // LO LING 0N/A +
"< \u0E27 " // WO WAEN 0N/A +
"< \u0E28 " // SO SALA 0N/A +
"< \u0E29 " // SO RUSI 0N/A +
"< \u0E2A " // SO SUA 0N/A +
"< \u0E2B " // HO HIP 0N/A +
"< \u0E2C " // LO CHULA 0N/A +
"< \u0E2D " // O ANG 0N/A +
"< \u0E2E " // HO NOKHUK 0N/A +
"< \u0E30 " // SARA A 0N/A +
"< \u0E31 " // MAI HAN-AKAT 0N/A +
"< \u0E32 " // SARA AA 0N/A // Normalizer will decompose this character to \u0e4d\u0e32. This is 0N/A // a Bad Thing, because we want the separate characters to sort 0N/A // differently than this individual one. Since there's no public way to 0N/A // set the decomposition to be used when creating a collator, there's 0N/A // no way around this right now. 0N/A // It's best to go ahead and leave the character in, because it occurs 0N/A // this way a lot more often than it occurs as separate characters. 0N/A +
"< \u0E33 " // SARA AM 0N/A +
"< \u0E34 " // SARA I 0N/A +
"< \u0E35 " // SARA II 0N/A +
"< \u0E36 " // SARA UE 0N/A +
"< \u0E37 " // SARA UEE 0N/A +
"< \u0E38 " // SARA U 0N/A +
"< \u0E39 " // SARA UU 0N/A +
"< \u0E40 " // SARA E 0N/A +
"< \u0E41 " // SARA AE 0N/A +
"< \u0E42 " // SARA O 0N/A +
"< \u0E43 " // SARA AI MAIMUAN 0N/A +
"< \u0E44 " // SARA AI MAIMALAI 0N/A +
"< \u0E50 " // DIGIT ZERO 0N/A +
"< \u0E51 " // DIGIT ONE 0N/A +
"< \u0E52 " // DIGIT TWO 0N/A +
"< \u0E53 " // DIGIT THREE 0N/A +
"< \u0E54 " // DIGIT FOUR 0N/A +
"< \u0E55 " // DIGIT FIVE 0N/A +
"< \u0E56 " // DIGIT SIX 0N/A +
"< \u0E57 " // DIGIT SEVEN 0N/A +
"< \u0E58 " // DIGIT EIGHT 0N/A +
"< \u0E59 " // DIGIT NINE 0N/A // Sorta tonal marks, but maybe not really 0N/A +
"< \u0E4D " // NIKHAHIT 0N/A // Thai symbols are supposed to sort "after white space". 0N/A // I'm treating this as making them sort just after the normal Latin-1 0N/A // symbols, which are in turn after the white space. 0N/A +
"&'\u007d'" // right-brace 0N/A +
"< \u0E2F " // PAIYANNOI (ellipsis, abbreviation) 0N/A +
"< \u0E46 " // MAIYAMOK 0N/A +
"< \u0E4F " // FONGMAN 0N/A +
"< \u0E5A " // ANGKHANKHU 0N/A +
"< \u0E5B " // KHOMUT 0N/A +
"< \u0E3F " // CURRENCY SYMBOL BAHT 0N/A // These symbols are supposed to be "after all characters" 0N/A +
"< \u0E4E " // YAMAKKAN 0N/A // This rare symbol also comes after all characters. But when it is 0N/A // used in combination with RU and LU, the combination is treated as 0N/A // a separate letter, ala "CH" sorting after "C" in traditional Spanish. 0N/A +
"< \u0E45 " // LAKKHANGYAO 0N/A +
"& \u0E24 < \u0E24\u0E45 " 0N/A +
"& \u0E26 < \u0E26\u0E45 " 0N/A // Tonal marks are primary ignorables but are treated as secondary 0N/A +
"& \u0301 " // acute accent 0N/A +
"; \u0E47 " // MAITAIKHU 0N/A +
"; \u0E48 " // MAI EK 0N/A +
"; \u0E49 " // MAI THO 0N/A +
"; \u0E4A " // MAI TRI 0N/A +
"; \u0E4B " // MAI CHATTAWA 0N/A +
"; \u0E4C " // THANTHAKHAT 0N/A // These are supposed to be ignored, so I'm treating them as controls 0N/A +
"= \u0E3A " // PHINTHU 0N/A +
"= '.' " // period