258 lines
6.8 KiB
Plaintext
258 lines
6.8 KiB
Plaintext
|
* Sorting weight table for Latin 1, ISO8859/1 languages, default order.
|
||
|
|
* This covers Unicode blocks 2 BASIC LATIN (0020 - 007E)
|
||
|
|
* 4 LATIN-1 SUPPLEMENT (00A0 - 00FF)
|
||
|
|
* Note that all block 2 characters are forced into block 4, so that
|
||
|
|
* all alphabetic characters in both blocks sort together. This means that
|
||
|
|
* the control characters (blocks 1 and 3) sort before all of these,
|
||
|
|
* in Unicode value order. Also, the basic sort order of blocks 2 and
|
||
|
|
* 4 is : non-alphanumerics < numerics < alphabetics.
|
||
|
|
*
|
||
|
|
* SYNTAX:
|
||
|
|
* Each non-comment line gives one or more weights for a character,
|
||
|
|
* as follows (character value in hex, weights in decimal):
|
||
|
|
* Field 1 = Unicode character value
|
||
|
|
* Field 2 = Shared weight (characters that sort together if accents
|
||
|
|
* and case were to be disregarded should have the same SW)
|
||
|
|
* Or, Block Weight/Shared Weight. This form allows characters
|
||
|
|
* in different Unicode blocks to have equal SWs. If BW is
|
||
|
|
* omitted, only SWs for characters in the same block are equal.
|
||
|
|
* Field 3 = Accent weight, or '-' to omit or copy from previous.
|
||
|
|
* Please use values as defined in the file NLS.WT.LOOKUP.
|
||
|
|
* Field 4 = Case weight, or 'U' for upper and 'L' for lower case chars.
|
||
|
|
*
|
||
|
|
* HEX (BW/)SW AW CW
|
||
|
|
* Non-alphanumerics in block 2...
|
||
|
|
0020 4/100 - - * SPACE
|
||
|
|
0021 4/102 - - * EXCLAMATION MARK
|
||
|
|
0022 4/104 - - * QUOTATION MARK
|
||
|
|
0023 4/106 - - * NUMBER SIGN
|
||
|
|
0024 4/108 - - * DOLLAR SIGN
|
||
|
|
0025 4/110 - - * PERCENT SIGN
|
||
|
|
0026 4/112 - - * AMPERSAND
|
||
|
|
0027 4/114 - - * APOSTROPHE
|
||
|
|
0028 4/116 - - * LEFT PARENTHESIS
|
||
|
|
0029 4/118 - - * RIGHT PARENTHESIS
|
||
|
|
002A 4/120 - - * ASTERISK
|
||
|
|
002B 4/122 - - * PLUS SIGN
|
||
|
|
002C 4/124 - - * COMMA
|
||
|
|
002D 4/126 - - * HYPHEN-MINUS
|
||
|
|
002E 4/128 - - * FULL STOP
|
||
|
|
002F 4/130 - - * SOLIDUS
|
||
|
|
003A 4/132 - - * COLON
|
||
|
|
003B 4/134 - - * SEMICOLON
|
||
|
|
003C 4/136 - - * LESS-THAN SIGN
|
||
|
|
003D 4/138 - - * EQUALS SIGN
|
||
|
|
003E 4/140 - - * GREATER-THAN SIGN
|
||
|
|
003F 4/142 - - * QUESTION MARK
|
||
|
|
0040 4/144 - - * COMMERCIAL AT
|
||
|
|
005B 4/146 - - * LEFT SQUARE BRACKET
|
||
|
|
005C 4/148 - - * REVERSE SOLIDUS
|
||
|
|
005D 4/150 - - * RIGHT SQUARE BRACKET
|
||
|
|
005E 4/152 - - * CIRCUMFLEX ACCENT
|
||
|
|
005F 4/154 - - * LOW LINE
|
||
|
|
0060 4/156 - - * GRAVE ACCENT
|
||
|
|
007B 4/158 - - * LEFT CURLY BRACKET
|
||
|
|
007C 4/160 - - * VERTICAL LINE
|
||
|
|
007D 4/162 - - * RIGHT CURLY BRACKET
|
||
|
|
007E 4/164 - - * TILDE
|
||
|
|
* Next is DEL - should sort atfer other control chars really (e.g. sw = 1/32)
|
||
|
|
007F 4/166 - - * <control> (DEL)
|
||
|
|
* HEX (BW/)SW AW CW
|
||
|
|
* Non-alphanumerics from block 4...
|
||
|
|
00A0 4/170 - - * NO-BREAK SPACE
|
||
|
|
00A1 4/172 - - * INVERTED EXCLAMATION MARK
|
||
|
|
00A2 4/174 - - * CENT SIGN
|
||
|
|
00A3 4/176 - - * POUND SIGN
|
||
|
|
00A4 4/178 - - * CURRENCY SIGN
|
||
|
|
00A5 4/180 - - * YEN SIGN
|
||
|
|
00A6 4/182 - - * BROKEN BAR
|
||
|
|
00A7 4/184 - - * SECTION SIGN
|
||
|
|
00A8 4/186 - - * DIAERESIS
|
||
|
|
00A9 4/188 - - * COPYRIGHT SIGN
|
||
|
|
00AA 4/190 - - * FEMININE ORDINAL INDICATOR
|
||
|
|
00AB 4/192 - - * LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||
|
|
00AC 4/194 - - * NOT SIGN
|
||
|
|
00AD 4/196 - - * SOFT HYPHEN
|
||
|
|
00AE 4/198 - - * REGISTERED SIGN
|
||
|
|
00AF 4/200 - - * MACRON
|
||
|
|
00B0 4/202 - - * DEGREE SIGN
|
||
|
|
00B1 4/204 - - * PLUS-MINUS SIGN
|
||
|
|
00B2 4/206 - - * SUPERSCRIPT TWO
|
||
|
|
00B3 4/208 - - * SUPERSCRIPT THREE
|
||
|
|
00B4 4/210 - - * ACUTE ACCENT
|
||
|
|
00B5 4/212 - - * MICRO SIGN
|
||
|
|
00B6 4/214 - - * PILCROW SIGN
|
||
|
|
00B7 4/216 - - * MIDDLE DOT
|
||
|
|
00B8 4/218 - - * CEDILLA
|
||
|
|
00B9 4/220 - - * SUPERSCRIPT ONE
|
||
|
|
00BA 4/222 - - * MASCULINE ORDINAL INDICATOR
|
||
|
|
00BB 4/224 - - * RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||
|
|
00BC 4/226 - - * VULGAR FRACTION ONE QUARTER
|
||
|
|
00BD 4/228 - - * VULGAR FRACTION ONE HALF
|
||
|
|
00BE 4/230 - - * VULGAR FRACTION THREE QUARTERS
|
||
|
|
00BF 4/232 - - * INVERTED QUESTION MARK
|
||
|
|
00D7 4/234 - - * MULTIPLICATION SIGN
|
||
|
|
00F7 4/236 - - * DIVISION SIGN
|
||
|
|
* HEX (BW/)SW AW CW
|
||
|
|
* Numerics from block 2...
|
||
|
|
0030 4/400 - - * DIGIT ZERO
|
||
|
|
0031 4/401 - - * DIGIT ONE
|
||
|
|
0032 4/402 - - * DIGIT TWO
|
||
|
|
0033 4/403 - - * DIGIT THREE
|
||
|
|
0034 4/404 - - * DIGIT FOUR
|
||
|
|
0035 4/405 - - * DIGIT FIVE
|
||
|
|
0036 4/406 - - * DIGIT SIX
|
||
|
|
0037 4/407 - - * DIGIT SEVEN
|
||
|
|
0038 4/408 - - * DIGIT EIGHT
|
||
|
|
0039 4/409 - - * DIGIT NINE
|
||
|
|
* NOTE: Space left here for alphabetics from other blocks
|
||
|
|
* to be collated before Latin A if necessary (e.g. Greek)
|
||
|
|
*
|
||
|
|
* HEX (BW/)SW AW CW
|
||
|
|
* Alphabetics from both blocks 2 & 4...
|
||
|
|
* A
|
||
|
|
0041 4/1000 - U * A
|
||
|
|
0061 - - L
|
||
|
|
00C1 - 1 U * A WITH ACUTE
|
||
|
|
00E1 - 1 L
|
||
|
|
00C0 - 3 U * A WITH GRAVE
|
||
|
|
00E0 - 3 L
|
||
|
|
00C2 - 13 U * A WITH CIRCUMFLEX
|
||
|
|
00E2 - 13 L
|
||
|
|
00C5 - 21 U * A WITH RING ABOVE
|
||
|
|
00E5 - 21 L
|
||
|
|
00C4 - 24 U * A WITH DIAERESIS
|
||
|
|
00E4 - 24 L
|
||
|
|
00C3 - 31 U * A WITH TILDE
|
||
|
|
00E3 - 31 L
|
||
|
|
* AE
|
||
|
|
00C6 4/1010 - U * LIGATURE AE
|
||
|
|
00E6 - - L
|
||
|
|
* B
|
||
|
|
0042 4/1020 - U * B
|
||
|
|
0062 - - L
|
||
|
|
* C
|
||
|
|
0043 4/1030 - U * C
|
||
|
|
0063 - - L
|
||
|
|
00C7 - 40 U * C WITH CEDILLA
|
||
|
|
00E7 - 40 L
|
||
|
|
* D
|
||
|
|
0044 4/1040 - U * D
|
||
|
|
0064 - - L
|
||
|
|
* ETH
|
||
|
|
00D0 4/1050 - U * ETH
|
||
|
|
00F0 - - L
|
||
|
|
* E
|
||
|
|
0045 4/1060 - U * E
|
||
|
|
0065 - - L
|
||
|
|
00C9 - 1 U * E WITH ACUTE
|
||
|
|
00E9 - 1 L
|
||
|
|
00C8 - 3 U * E WITH GRAVE
|
||
|
|
00E8 - 3 L
|
||
|
|
00CA - 13 U * E WITH CIRCUMFLEX
|
||
|
|
00EA - 13 L
|
||
|
|
00CB - 24 U * E WITH DIAERESIS
|
||
|
|
00EB - 24 L
|
||
|
|
* F
|
||
|
|
0046 4/1070 - U * F
|
||
|
|
0066 - - L
|
||
|
|
* THORN
|
||
|
|
00DE 4/1080 - U * THORN
|
||
|
|
00FE - - L
|
||
|
|
* G
|
||
|
|
0047 4/1090 - U * G
|
||
|
|
0067 - - L
|
||
|
|
* H
|
||
|
|
0048 4/1100 - U * H
|
||
|
|
0068 - - L
|
||
|
|
* I
|
||
|
|
0049 4/1110 - U * I
|
||
|
|
0069 - - L
|
||
|
|
00CD - 1 U * I WITH ACUTE
|
||
|
|
00ED - 1 L
|
||
|
|
00CC - 3 U * I WITH GRAVE
|
||
|
|
00EC - 3 L
|
||
|
|
00CE - 13 U * I WITH CIRCUMFLEX
|
||
|
|
00EE - 13 L
|
||
|
|
00CF - 24 U * I WITH DIAERESIS
|
||
|
|
00EF - 24 L
|
||
|
|
* J
|
||
|
|
004A 4/1120 - U * J
|
||
|
|
006A - - L
|
||
|
|
* K
|
||
|
|
004B 4/1130 - U * K
|
||
|
|
006B - - L
|
||
|
|
* L
|
||
|
|
004C 4/1140 - U * L
|
||
|
|
006C - - L
|
||
|
|
* M
|
||
|
|
004D 4/1150 - U * M
|
||
|
|
006D - - L
|
||
|
|
* N
|
||
|
|
004E 4/1160 - U * N
|
||
|
|
006E - - L
|
||
|
|
00D1 - 31 U * N WITH TILDE
|
||
|
|
00F1 - 31 L
|
||
|
|
* O
|
||
|
|
004F 4/1170 - U * O
|
||
|
|
006F - - L
|
||
|
|
00D3 - 1 U * O WITH ACUTE
|
||
|
|
00F3 - 1 L
|
||
|
|
00D2 - 3 U * O WITH GRAVE
|
||
|
|
00F2 - 3 L
|
||
|
|
00D4 - 13 U * O WITH CIRCUMFLEX
|
||
|
|
00F4 - 13 L
|
||
|
|
00D6 - 24 U * O WITH DIAERESIS
|
||
|
|
00F6 - 24 L
|
||
|
|
00D5 - 31 U * O WITH TILDE
|
||
|
|
00F5 - 31 L
|
||
|
|
00D8 - 38 U * O WITH STROKE
|
||
|
|
00F8 - 38 L
|
||
|
|
* P
|
||
|
|
0050 4/1190 - U * P
|
||
|
|
0070 - - L
|
||
|
|
* Q
|
||
|
|
0051 4/1200 - U * Q
|
||
|
|
0071 - - L
|
||
|
|
* R
|
||
|
|
0052 4/1210 - U * R
|
||
|
|
0072 - - L
|
||
|
|
* S
|
||
|
|
0053 4/1220 - U * S
|
||
|
|
0073 - - L
|
||
|
|
* SHARP S
|
||
|
|
00DF 4/1230 - L * SHARP S
|
||
|
|
* T
|
||
|
|
0054 4/1240 - U * T
|
||
|
|
0074 - - L
|
||
|
|
* U
|
||
|
|
0055 4/1250 - U * U
|
||
|
|
0075 - - L
|
||
|
|
00DA - 1 U * U WITH ACUTE
|
||
|
|
00FA - 1 L
|
||
|
|
00D9 - 3 U * U WITH GRAVE
|
||
|
|
00F9 - 3 L
|
||
|
|
00DB - 13 U * U WITH CIRCUMFLEX
|
||
|
|
00FB - 13 L
|
||
|
|
00DC - 24 U * U WITH DIAERESIS
|
||
|
|
00FC - 24 L
|
||
|
|
* V
|
||
|
|
0056 4/1260 - U * V
|
||
|
|
0076 - - L
|
||
|
|
* W
|
||
|
|
0057 4/1270 - U * W
|
||
|
|
0077 - - L
|
||
|
|
* X
|
||
|
|
0058 4/1280 - U * X
|
||
|
|
0078 - - L
|
||
|
|
* Y
|
||
|
|
0059 4/1290 - U * Y
|
||
|
|
0079 - - L
|
||
|
|
00DD - 1 U * Y WITH ACUTE
|
||
|
|
00FD - 1 L
|
||
|
|
00FF - 24 L * Y WITH DIAERESIS
|
||
|
|
* Z
|
||
|
|
005A 4/1300 - U * Z
|
||
|
|
007A - - L
|
||
|
|
* END
|