1 # CASED.awk -- awk script to generate CASED.tab
3 # National Institute of Advanced Industrial Science and Technology (AIST)
4 # Registration Number H15PRO112
6 # This file is part of the m17n database; a sub-part of the m17n
9 # The m17n library is free software; you can redistribute it and/or
10 # modify it under the terms of the GNU Lesser General Public License
11 # as published by the Free Software Foundation; either version 2.1 of
12 # the License, or (at your option) any later version.
14 # The m17n library is distributed in the hope that it will be useful,
15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 # Lesser General Public License for more details.
19 # You should have received a copy of the GNU Lesser General Public
20 # License along with the m17n library; if not, write to the Free
21 # Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
52 function decode_hex(str, idx) {
55 for (i = idx; i <= len; i++)
57 c = tohex[substr (str, i, 1)];
65 function single (str, bit) {
66 i = decode_hex (str, 1);
71 function range (str, bit) {
72 end = decode_hex (str, index (str, "..") + 2);
73 for (i = decode_hex (str, 1); i <= end; i++)
78 FILE == 1 && /^[^#]/ {
79 if ($3 ~ /L[ltu]/) single ($1, 1);
80 else if ($3 ~ /Mn|Me|Cf|Lm|Sk/) range ($1, 2);
83 /^# PropList-.+\.txt/ {
87 FILE == 2 && /^[^#;]+; *Other_(Upp|Low)ercase/ {
88 if (index ($1, ".")) range ($1, 1);
92 /^# WordBreakProperty-.+\.txt/ {
96 FILE == 3 && /^[^#;]+; *MidLetter/ {
97 if (index ($1, ".")) range ($1, 2);
103 printf ("0x%X %d\n", i, cased[i]);