# gb2312.txt --
#
# GB2312 to Unicode table (modified)
#
# Copyright (c) 1998-1999 by Scriptics Corporation.
#
# See the file "license.terms" for information on usage and redistribution
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.
#
# RCS: @(#) $Id: gb2312.txt,v 1.2 1999/04/16 00:47:55 stanton Exp $
#
# NOTE: this table has been modified to include the 7-bit ASCII
# characters that are allowed in GB2312 files.
#
#
# Name: GB2312-80 to Unicode table (complete, hex format)
# Unicode version: 1.1
# Table version: 0.0d2
# Table format: Format A
# Date: 6 December 1993
# Author: Glenn Adams <glenn@metis.com>
# John H. Jenkins <John_Jenkins@taligent.com>
#
# Copyright (c) 1991-1994 Unicode, Inc. All Rights reserved.
#
# This file is provided as-is by Unicode, Inc. (The Unicode Consortium).
# No claims are made as to fitness for any particular purpose. No
# warranties of any kind are expressed or implied. The recipient
# agrees to determine applicability of information provided. If this
# file has been provided on magnetic media by Unicode, Inc., the sole
# remedy for any claim will be exchange of defective media within 90
# days of receipt.
#
# Recipient is granted the right to make copies in any form for
# internal distribution and to freely use the information supplied
# in the creation of products supporting Unicode. Unicode, Inc.
# specifically excludes the right to re-distribute this file directly
# to third parties or other organizations whether for profit or not.
#
# General notes:
#
# This table contains the data Metis and Taligent currently have on how
# GB2312-80 characters map into Unicode.
#
# Format: Three tab-separated columns
# Column #1 is the GB2312 code (in hex as 0xXXXX)
# Column #2 is the Unicode (in hex as 0xXXXX)
# Column #3 the Unicode name (follows a comment sign, '#')
# The official names for Unicode characters U+4E00
# to U+9FA5, inclusive, is "CJK UNIFIED IDEOGRAPH-XXXX",
# where XXXX is the code point. Including all these
# names in this file increases its size substantially
# and needlessly. The token "<CJK>" is used for the
# name of these characters. If necessary, it can be
# expanded algorithmically by a parser or editor.
#
# The entries are in GB2312 order
#
# The following algorithms can be used to change the hex form
# of GB2312 to other standard forms:
#
# To change hex to EUC form, add 0x8080
# To change hex to kuten form, first subtract 0x2020. Then
# the high and low bytes correspond to the ku and ten of
# the kuten form. For example, 0x2121 -> 0x0101 -> 0101;
# 0x777E -> 0x575E -> 8794
#
# Any comments or problems, contact <John_Jenkins@taligent.com>
#
#
0x2121 0x3000 # IDEOGRAPHIC SPACE
0x2122 0x3001 # IDEOGRAPHIC COMMA
0x2123 0x3002 # IDEOGRAPHIC FULL STOP
0x2124 0x30FB # KATAKANA MIDDLE DOT
0x2125 0x02C9 # MODIFIER LETTER MACRON (Mandarin Chinese first tone)
0x2126 0x02C7 # CARON (Mandarin Chinese third tone)
0x2127 0x00A8 # DIAERESIS
0x2128 0x3003 # DITTO MARK
0x2129 0x3005 # IDEOGRAPHIC ITERATION MARK
0x212A 0x2015 # HORIZONTAL BAR
0x212B 0xFF5E # FULLWIDTH TILDE
0x212C 0x2225 # PARALLEL TO
0x212D 0x2026 # HORIZONTAL ELLIPSIS
0x212E 0x2018 # LEFT SINGLE QUOTATION MARK
0x212F 0x2019 # RIGHT SINGLE QUOTATION MARK
0x2130 0x201C # LEFT DOUBLE QUOTATION MARK
0x2131 0x201D # RIGHT DOUBLE QUOTATION MARK
0x2132 0x3014 # LEFT TORTOISE SHELL BRACKET
0x2133 0x3015 # RIGHT TORTOISE SHELL BRACKET
0x2134 0x3008 # LEFT ANGLE BRACKET
0x2135 0x3009 # RIGHT ANGLE BRACKET
0x2136 0x300A # LEFT DOUBLE ANGLE BRACKET
0x2137 0x300B # RIGHT DOUBLE ANGLE BRACKET
0x2138 0x300C # LEFT CORNER BRACKET
0x2139 0x300D # RIGHT CORNER BRACKET
0x213A 0x300E # LEFT WHITE CORNER BRACKET
0x213B 0x300F # RIGHT WHITE CORNER BRACKET
0x213C 0x3016 # LEFT WHITE LENTICULAR BRACKET
0x213D 0x3017 # RIGHT WHITE LENTICULAR BRACKET
0x213E 0x3010 # LEFT BLACK LENTICULAR BRACKET
0x213F 0x3011 # RIGHT BLACK LENTICULAR BRACKET
0x2140 0x00B1 # PLUS-MINUS SIGN
0x2141 0x00D7 # MULTIPLICATION SIGN
0x2142 0x00F7 # DIVISION SIGN
0x2143 0x2236 # RATIO
0x2144 0x2227 # LOGICAL AND
0x2145 0x2228 # LOGICAL OR
0x2146 0x2211 # N-ARY SUMMATION
0x2147 0x220F # N-ARY PRODUCT
0x2148 0x222A # UNION
0x2149 0x2229 # INTERSECTION
0x214A 0x2208 # ELEMENT OF
0x214B 0x2237 # PROPORTION
0x214C 0x221A # SQUARE ROOT
0x214D 0x22A5 # UP TACK
0x214E 0x2225 # PARALLEL TO
0x214F 0x2220 # ANGLE
0x2150 0x2312 # ARC
0x2151 0x2299 # CIRCLED DOT OPERATOR
0x2152 0x222B # INTEGRAL
0x2153 0x222E # CONTOUR INTEGRAL
0x2154 0x2261 # IDENTICAL TO
0x2155 0x224C # ALL EQUAL TO
0x2156 0x2248 # ALMOST EQUAL TO
0x2157 0x223D # REVERSED TILDE
0x2158 0x221D # PROPORTIONAL TO
0x2159 0x2260 # NOT EQUAL TO
0x215A 0x226E # NOT LESS-THAN
0x215B 0x226F # NOT GREATER-THAN
0x215C 0x2264 # LESS-THAN OR EQUAL TO
0x215D 0x2265 # GREATER-THAN OR EQUAL TO
0x215E 0x221E # INFINITY
0x215F 0x2235 # BECAUSE
0x2160 0x2234 # THEREFORE
0x2161 0x2642 # MALE SIGN
0x2162 0x2640 # FEMALE SIGN
0x2163 0x00B0 # DEGREE SIGN
0x2164 0x2032 # PRIME
0x2165 0x2033 # DOUBLE PRIME
0x2166 0x2103 # DEGREE CELSIUS
0x2167 0xFF04 # FULLWIDTH DOLLAR SIGN
0x2168 0x00A4 # CURRENCY SIGN
0x2169 0xFFE0 # FULLWIDTH CENT SIGN
0x216A 0xFFE1 # FULLWIDTH POUND SIGN
0x216B 0x2030 # PER MILLE SIGN
0x216C 0x00A7 # SECTION SIGN
0x216D 0x2116 # NUMERO SIGN
0x216E 0x2606 # WHITE STAR
0x216F 0x2605 # BLACK STAR
0x2170 0x25CB # WHITE CIRCLE
0x2171 0x25CF # BLACK CIRCLE
0x2172 0x25CE # BULLSEYE
0x2173 0x25C7 # WHITE DIAMOND
0x2174 0x25C6 # BLACK DIAMOND
0x2175 0x25A1 # WHITE SQUARE
0x2176 0x25A0 # BLACK SQUARE
0x2177 0x25B3 # WHITE UP-POINTING TRIANGLE
0x2178 0x25B2 # BLACK UP-POINTING TRIANGLE
0x2179 0x203B # REFERENCE MARK
0x217A 0x2192 # RIGHTWARDS ARROW
0x217B 0x2190 # LEFTWARDS ARROW
0x217C 0x2191 # UPWARDS ARROW
0x217D 0x2193 # DOWNWARDS ARROW
0x217E 0x3013 # GETA MARK
0x2231 0x2488 # DIGIT ONE FULL STOP
0x2232 0x2489 # DIGIT TWO FULL STOP
0x2233 0x248A # DIGIT THREE FULL STOP
0x2234 0x248B # DIGIT FOUR FULL STOP
0x2235 0x248C # DIGIT FIVE FULL STOP
0x2236 0x248D # DIGIT SIX FULL STOP
0x2237 0x248E # DIGIT SEVEN FULL STOP
0x2238 0x248F # DIGIT EIGHT FULL STOP
0x2239 0x2490 # DIGIT NINE FULL STOP
0x223A 0x2491 # NUMBER TEN FULL STOP
0x223B 0x2492 # NUMBER ELEVEN FULL STOP
0x223C 0x2493 # NUMBER TWELVE FULL STOP
0x223D 0x2494 # NUMBER THIRTEEN FULL STOP
0x223E 0x2495 # NUMBER FOURTEEN FULL STOP
0x223F 0x2496 # NUMBER FIFTEEN FULL STOP
0x2240 0x2497 # NUMBER SIXTEEN FULL STOP
0x2241 0x2498 # NUMBER SEVENTEEN FULL STOP
0x2242 0x2499 # NUMBER EIGHTEEN FULL STOP
0x2243 0x249A # NUMBER NINETEEN FULL STOP
0x2244 0x249B # NUMBER TWENTY FULL STOP
0x2245 0x2474 # PARENTHESIZED DIGIT ONE
0x2246 0x2475 # PARENTHESIZED DIGIT TWO
0x2247 0x2476 # PARENTHESIZED DIGIT THREE
0x2248 0x2477 # PARENTHESIZED DIGIT FOUR
0x2249 0x2478 # PARENTHESIZED DIGIT FIVE
0x224A 0x2479 # PARENTHESIZED DIGIT SIX
0x224B 0x247A # PARENTHESIZED DIGIT SEVEN
0x224C 0x247B # PARENTHESIZED DIGIT EIGHT
0x224D 0x247C # PARENTHESIZED DIGIT NINE
0x224E 0x247D # PARENTHESIZED NUMBER TEN
0x224F 0x247E # PARENTHESIZED NUMBER ELEVEN
0x2250 0x247F # PARENTHESIZED NUMBER TWELVE
0x2251 0x2480 # PARENTHESIZED NUMBER THIRTEEN
0x2252 0x2481 # PARENTHESIZED NUMBER FOURTEEN
0x2253 0x2482 # PARENTHESIZED NUMBER FIFTEEN
0x2254 0x2483 # PARENTHESIZED NUMBER SIXTEEN
0x2255 0x2484 # PARENTHESIZED NUMBER SEVENTEEN
0x2256 0x2485 # PARENTHESIZED NUMBER EIGHTEEN
0x2257 0x2486 # PARENTHESIZED NUMBER NINETEEN
0x2258 0x2487 # PARENTHESIZED NUMBER TWENTY
0x2259 0x2460 # CIRCLED DIGIT ONE
0x225A 0x2461 # CIRCLED DIGIT TWO
0x225B 0x2462 # CIRCLED DIGIT THREE
0x225C 0x2463 # CIRCLED DIGIT FOUR
0x225D 0x2464 # CIRCLED DIGIT FIVE
0x225E 0x2465 # CIRCLED DIGIT SIX
0x225F 0x2466 # CIRCLED DIGIT SEVEN
0x2260 0x2467 # CIRCLED DIGIT EIGHT
0x2261 0x2468 # CIRCLED DIGIT NINE
0x2262 0x2469 # CIRCLED NUMBER TEN
0x2265 0x3220 # PARENTHESIZED IDEOGRAPH ONE
0x2266 0x3221 # PARENTHESIZED IDEOGRAPH TWO
0x2267 0x3222 # PARENTHE