296 lines
8.0 KiB
Plaintext
296 lines
8.0 KiB
Plaintext
|
* Sorting weight table for European Extended Latin Additions, default order.
|
||
|
|
* This covers Unicode block 46 LATIN EXTENDED ADDITIONAL (1E00 - 1EFF)
|
||
|
|
*
|
||
|
|
* The table is intended to be loaded after LATIN1-DEFAULT, LATINX-DEFAULT,
|
||
|
|
* and LATINX2-DEFAULT, which cover blocks 2, 4, 5 & 6. Note that all these
|
||
|
|
* block 46 characters are forced into block 4, so that all alphabetic
|
||
|
|
* characters in blocks 2, 4, 5, 6 & 46 sort together. This means that
|
||
|
|
* the control characters (blocks 1 and 3) sort before all of these, in
|
||
|
|
* Unicode value order.
|
||
|
|
*
|
||
|
|
* 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
|
||
|
|
* A-related
|
||
|
|
1EAE 4/1000 6 U * A WITH BREVE AND ACUTE
|
||
|
|
1EAF - 6 L
|
||
|
|
1EB0 - 7 U * A WITH BREVE AND GRAVE
|
||
|
|
1EB1 - 7 L
|
||
|
|
1EB2 - 8 U * A WITH BREVE AND HOOK ABOVE
|
||
|
|
1EB3 - 8 L
|
||
|
|
1EB4 - 9 U * A WITH BREVE AND TILDE
|
||
|
|
1EB5 - 9 L
|
||
|
|
1EB6 - 10 U * A WITH BREVE AND DOT BELOW
|
||
|
|
1EB7 - 10 L
|
||
|
|
1EA4 - 14 U * A WITH CIRCUMFLEX AND ACUTE
|
||
|
|
1EA5 - 14 L
|
||
|
|
1EA6 - 15 U * A WITH CIRCUMFLEX AND GRAVE
|
||
|
|
1EA7 - 15 L
|
||
|
|
1EA8 - 16 U * A WITH CIRCUMFLEX AND HOOK ABOVE
|
||
|
|
1EA9 - 16 L
|
||
|
|
1EAA - 17 U * A WITH CIRCUMFLEX AND TILDE
|
||
|
|
1EAB - 17 L
|
||
|
|
1EAC - 18 U * A WITH CIRCUMFLEX AND DOT BELOW
|
||
|
|
1EAD - 18 L
|
||
|
|
1E00 - 23 U * A WITH RING BELOW
|
||
|
|
1E01 - 23 L
|
||
|
|
1EA2 - 30 U * A WITH HOOK ABOVE
|
||
|
|
1EA3 - 30 L
|
||
|
|
1EA0 - 36 U * A WITH DOT BELOW
|
||
|
|
1EA1 - 36 L
|
||
|
|
* Next collates after A, not as accented form of A
|
||
|
|
1E9A 4/1001 - L * A WITH RIGHT HALF RING
|
||
|
|
* B-related
|
||
|
|
1E02 4/1020 35 U * B WITH DOT ABOVE
|
||
|
|
1E03 - 35 L
|
||
|
|
1E04 - 36 U * B WITH DOT BELOW
|
||
|
|
1E05 - 36 L
|
||
|
|
1E06 - 54 U * B WITH LINE BELOW
|
||
|
|
1E07 - 54 L
|
||
|
|
* C-related
|
||
|
|
1E08 4/1030 41 U * C WITH CEDILLA AND ACUTE
|
||
|
|
1E09 - 41 L
|
||
|
|
* D-related
|
||
|
|
1E0A 4/1040 35 U * D WITH DOT ABOVE
|
||
|
|
1E0B - 35 L
|
||
|
|
1E0C - 36 U * D WITH DOT BELOW
|
||
|
|
1E0D - 36 L
|
||
|
|
1E10 - 40 U * D WITH CEDILLA
|
||
|
|
1E11 - 40 L
|
||
|
|
1E12 - 53 U * D WITH CIRCUMFLEX BELOW
|
||
|
|
1E13 - 53 L
|
||
|
|
1E0E - 54 U * D WITH LINE BELOW
|
||
|
|
1E0F - 54 L
|
||
|
|
* E-related
|
||
|
|
1EBE 4/1060 14 U * E WITH CIRCUMFLEX AND ACUTE
|
||
|
|
1EBF - 14 L
|
||
|
|
1EC0 - 15 U * E WITH CIRCUMFLEX AND GRAVE
|
||
|
|
1EC1 - 15 L
|
||
|
|
1EC2 - 16 U * E WITH CIRCUMFLEX AND HOOK ABOVE
|
||
|
|
1EC3 - 16 L
|
||
|
|
1EC4 - 17 U * E WITH CIRCUMFLEX AND TILDE
|
||
|
|
1EC5 - 17 L
|
||
|
|
1EC6 - 18 U * E WITH CIRCUMFLEX AND DOT BELOW
|
||
|
|
1EC7 - 18 L
|
||
|
|
1EBA - 30 U * E WITH HOOK ABOVE
|
||
|
|
1EBB - 30 L
|
||
|
|
1EBC - 31 U * E WITH TILDE
|
||
|
|
1EBD - 31 L
|
||
|
|
1E1A - 34 U * E WITH TILDE BELOW
|
||
|
|
1E1B - 34 L
|
||
|
|
1EB8 - 36 U * E WITH DOT BELOW
|
||
|
|
1EB9 - 36 L
|
||
|
|
1E1C - 43 U * E WITH CEDILLA AND BREVE
|
||
|
|
1E1D - 43 L
|
||
|
|
1E16 - 47 U * E WITH MACRON AND ACUTE
|
||
|
|
1E17 - 47 L
|
||
|
|
1E14 - 48 U * E WITH MACRON AND GRAVE
|
||
|
|
1E15 - 48 L
|
||
|
|
1E18 - 53 U * E WITH CIRCUMFLEX BELOW
|
||
|
|
1E19 - 53 L
|
||
|
|
* F-related
|
||
|
|
1E1E 4/1070 35 U * F WITH DOT ABOVE
|
||
|
|
1E1F - 35 L
|
||
|
|
* G-related
|
||
|
|
1E20 4/1090 46 U * G WITH MACRON
|
||
|
|
1E21 - 46 L
|
||
|
|
* H-related
|
||
|
|
1E2A 4/1100 11 U * H WITH BREVE BELOW
|
||
|
|
1E2B - 11 L
|
||
|
|
1E26 - 24 U * H WITH DIAERESIS
|
||
|
|
1E27 - 24 L
|
||
|
|
1E22 - 35 U * H WITH DOT ABOVE
|
||
|
|
1E23 - 35 L
|
||
|
|
1E24 - 36 U * H WITH DOT BELOW
|
||
|
|
1E25 - 36 L
|
||
|
|
1E28 - 40 U * H WITH CEDILLA
|
||
|
|
1E29 - 40 L
|
||
|
|
1E96 - 54 L * H WITH LINE BELOW
|
||
|
|
* I-related
|
||
|
|
1E2E 4/1110 26 U * I WITH DIAERESIS AND ACUTE
|
||
|
|
1E2F - 26 L
|
||
|
|
1EC8 - 30 U * I WITH HOOK ABOVE
|
||
|
|
1EC9 - 30 L
|
||
|
|
1E2C - 34 U * I WITH TILDE BELOW
|
||
|
|
1E2D - 34 L
|
||
|
|
1ECA - 36 U * I WITH DOT BELOW
|
||
|
|
1ECB - 36 L
|
||
|
|
* K-related
|
||
|
|
1E30 4/1130 1 U * K WITH ACUTE
|
||
|
|
1E31 - 1 L
|
||
|
|
1E32 - 36 U * K WITH DOT BELOW
|
||
|
|
1E33 - 36 L
|
||
|
|
1E34 - 54 U * K WITH LINE BELOW
|
||
|
|
1E35 - 54 L
|
||
|
|
* L-related
|
||
|
|
1E36 4/1140 36 U * L WITH DOT BELOW
|
||
|
|
1E37 - 36 L
|
||
|
|
1E38 - 52 U * L WITH DOT BELOW AND MACRON
|
||
|
|
1E39 - 52 L
|
||
|
|
1E3C - 53 U * L WITH CIRCUMFLEX BELOW
|
||
|
|
1E3D - 53 L
|
||
|
|
1E3A - 54 U * L WITH LINE BELOW
|
||
|
|
1E3B - 54 L
|
||
|
|
* M-related
|
||
|
|
1E3E 4/1150 1 U * M WITH ACUTE
|
||
|
|
1E3F - 1 L
|
||
|
|
1E40 - 35 U * M WITH DOT ABOVE
|
||
|
|
1E41 - 35 L
|
||
|
|
1E42 - 36 U * M WITH DOT BELOW
|
||
|
|
1E43 - 36 L
|
||
|
|
* N-related
|
||
|
|
1E44 4/1160 35 U * N WITH DOT ABOVE
|
||
|
|
1E45 - 35 L
|
||
|
|
1E46 - 36 U * N WITH DOT BELOW
|
||
|
|
1E47 - 36 L
|
||
|
|
1E4A - 53 U * N WITH CIRCUMFLEX BELOW
|
||
|
|
1E4B - 53 L
|
||
|
|
1E48 - 54 U * N WITH LINE BELOW
|
||
|
|
1E49 - 54 L
|
||
|
|
* O-related
|
||
|
|
1ED0 4/1170 14 U * O WITH CIRCUMFLEX AND ACUTE
|
||
|
|
1ED1 - 14 L
|
||
|
|
1ED2 - 15 U * O WITH CIRCUMFLEX AND GRAVE
|
||
|
|
1ED3 - 15 L
|
||
|
|
1ED4 - 16 U * O WITH CIRCUMFLEX AND HOOK ABOVE
|
||
|
|
1ED5 - 16 L
|
||
|
|
1ED6 - 17 U * O WITH CIRCUMFLEX AND TILDE
|
||
|
|
1ED7 - 17 L
|
||
|
|
1ED8 - 18 U * O WITH CIRCUMFLEX AND DOT BELOW
|
||
|
|
1ED9 - 18 L
|
||
|
|
1ECE - 30 U * O WITH HOOK ABOVE
|
||
|
|
1ECF - 30 L
|
||
|
|
1E4C - 32 U * O WITH TILDE AND ACUTE
|
||
|
|
1E4D - 32 L
|
||
|
|
1E4E - 33 U * O WITH TILDE AND DIAERESIS
|
||
|
|
1E4F - 33 L
|
||
|
|
1ECC - 36 U * O WITH DOT BELOW
|
||
|
|
1ECD - 36 L
|
||
|
|
1E52 - 47 U * O WITH MACRON AND ACUTE
|
||
|
|
1E53 - 47 L
|
||
|
|
1E50 - 48 U * O WITH MACRON AND GRAVE
|
||
|
|
1E51 - 48 L
|
||
|
|
1EDA - 56 U * O WITH HORN AND ACUTE
|
||
|
|
1EDB - 56 L
|
||
|
|
1EDC - 57 U * O WITH HORN AND GRAVE
|
||
|
|
1EDD - 57 L
|
||
|
|
1EDE - 58 U * O WITH HORN AND HOOK ABOVE
|
||
|
|
1EDF - 58 L
|
||
|
|
1EE0 - 59 U * O WITH HORN AND TILDE
|
||
|
|
1EE1 - 59 L
|
||
|
|
1EE2 - 62 U * O WITH HORN AND DOT BELOW
|
||
|
|
1EE3 - 62 L
|
||
|
|
* P-related
|
||
|
|
1E54 4/1190 1 U * P WITH ACUTE
|
||
|
|
1E55 - 1 L
|
||
|
|
1E56 - 35 U * P WITH DOT ABOVE
|
||
|
|
1E57 - 35 L
|
||
|
|
* R-related
|
||
|
|
1E58 4/1210 35 U * R WITH DOT ABOVE
|
||
|
|
1E59 - 35 L
|
||
|
|
1E5A - 36 U * R WITH DOT BELOW
|
||
|
|
1E5B - 36 L
|
||
|
|
1E5C - 52 U * R WITH DOT BELOW AND MACRON
|
||
|
|
1E5D - 52 L
|
||
|
|
1E5E - 54 U * R WITH LINE BELOW
|
||
|
|
1E5F - 54 L
|
||
|
|
* S-related
|
||
|
|
1E64 4/1220 2 U * S WITH ACUTE AND DOT ABOVE
|
||
|
|
1E65 - 2 L
|
||
|
|
1E66 - 20 U * S WITH CARON AND DOT ABOVE
|
||
|
|
1E67 - 20 L
|
||
|
|
1E60 - 35 U * S WITH DOT ABOVE
|
||
|
|
1E61 - 35 L
|
||
|
|
1E62 - 36 U * S WITH DOT BELOW
|
||
|
|
1E63 - 36 L
|
||
|
|
1E68 - 37 U * S WITH DOT BELOW AND DOT ABOVE
|
||
|
|
1E69 - 37 L
|
||
|
|
* T-related
|
||
|
|
1E97 4/1240 24 L * T WITH DIAERESIS
|
||
|
|
1E6A - 35 U * T WITH DOT ABOVE
|
||
|
|
1E6B - 35 L
|
||
|
|
1E6C - 36 U * T WITH DOT BELOW
|
||
|
|
1E6D - 36 L
|
||
|
|
1E70 - 53 U * T WITH CIRCUMFLEX BELOW
|
||
|
|
1E71 - 53 L
|
||
|
|
1E6E - 54 U * T WITH LINE BELOW
|
||
|
|
1E6F - 54 L
|
||
|
|
|
||
|
|
* U-related
|
||
|
|
1EE6 4/1250 30 U * U WITH HOOK ABOVE
|
||
|
|
1EE7 - 30 L
|
||
|
|
1E78 - 32 U * U WITH TILDE AND ACUTE
|
||
|
|
1E79 - 32 L
|
||
|
|
1E74 - 34 U * U WITH TILDE BELOW
|
||
|
|
1E75 - 34 L
|
||
|
|
1EE4 - 36 U * U WITH DOT BELOW
|
||
|
|
1EE5 - 36 L
|
||
|
|
1E7A - 49 U * U WITH MACRON AND DIAERESIS
|
||
|
|
1E7B - 49 L
|
||
|
|
1E72 - 50 U * U WITH DIAERESIS BELOW
|
||
|
|
1E73 - 50 L
|
||
|
|
1E76 - 53 U * U WITH CIRCUMFLEX BELOW
|
||
|
|
1E77 - 53 L
|
||
|
|
1EE8 - 56 U * U WITH HORN AND ACUTE
|
||
|
|
1EE9 - 56 L
|
||
|
|
1EEA - 57 U * U WITH HORN AND GRAVE
|
||
|
|
1EEB - 57 L
|
||
|
|
1EEC - 58 U * U WITH HORN AND HOOK ABOVE
|
||
|
|
1EED - 58 L
|
||
|
|
1EEE - 59 U * U WITH HORN AND TILDE
|
||
|
|
1EEF - 59 L
|
||
|
|
1EF0 - 62 U * U WITH HORN AND DOT BELOW
|
||
|
|
1EF1 - 62 L
|
||
|
|
* V-related
|
||
|
|
1E7C 4/1260 31 U * V WITH TILDE
|
||
|
|
1E7D - 31 L
|
||
|
|
1E7E - 36 U * V WITH DOT BELOW
|
||
|
|
1E7F - 36 L
|
||
|
|
* W-related
|
||
|
|
1E82 4/1270 1 U * W WITH ACUTE
|
||
|
|
1E83 - 1 L
|
||
|
|
1E80 - 3 U * W WITH GRAVE
|
||
|
|
1E81 - 3 L
|
||
|
|
1E98 - 21 L * W WITH RING ABOVE
|
||
|
|
1E84 - 24 U * W WITH DIAERESIS
|
||
|
|
1E85 - 24 L
|
||
|
|
1E86 - 35 U * W WITH DOT ABOVE
|
||
|
|
1E87 - 35 L
|
||
|
|
1E88 - 36 U * W WITH DOT BELOW
|
||
|
|
1E89 - 36 L
|
||
|
|
* X-related
|
||
|
|
1E8C 4/1280 24 U * X WITH DIAERESIS
|
||
|
|
1E8D - 24 L
|
||
|
|
1E8A - 35 U * X WITH DOT ABOVE
|
||
|
|
1E8B - 35 L
|
||
|
|
* Y-related
|
||
|
|
1EF2 4/1290 3 U * Y WITH GRAVE
|
||
|
|
1EF3 - 3 L
|
||
|
|
1E99 - 21 L * Y WITH RING ABOVE
|
||
|
|
1EF6 - 30 U * Y WITH HOOK ABOVE
|
||
|
|
1EF7 - 30 L
|
||
|
|
1EF8 - 31 U * Y WITH TILDE
|
||
|
|
1EF9 - 31 L
|
||
|
|
1E8E - 35 U * Y WITH DOT ABOVE
|
||
|
|
1E8F - 35 L
|
||
|
|
1EF4 - 36 U * Y WITH DOT BELOW
|
||
|
|
1EF5 - 36 L
|
||
|
|
* Z-related
|
||
|
|
1E90 4/1300 13 U * Z WITH CIRCUMFLEX
|
||
|
|
1E91 - 13 L
|
||
|
|
1E92 - 36 U * Z WITH DOT BELOW
|
||
|
|
1E93 - 36 L
|
||
|
|
1E94 - 54 U * Z WITH LINE BELOW
|
||
|
|
1E95 - 54 L
|