# -*- mode: conf; coding: utf-8; -*- LANGCODE:hu_HU CHARSET: utf-8 BUILD_FLAGS:ALLOWS_DUPLICATES LANGFILTER: tr -d '\r' LANGFILTER: | tr [aábcdeéfghiíjklmnnyoóöőprtuúüűvzs] [AÁBCDEÉFGHIÍJKLMNNYOÓÖŐPRTUÚÜŰVZS] LANGFILTER: | sed -e 's,^\(.*\)CS\(.*\)$,\11\2\n\1CS\2,g' LANGFILTER: | sed -e 's,GY,2,g' LANGFILTER: | sed -e 's,LY,3,g' LANGFILTER: | sed -e 's,NY,4,g' LANGFILTER: | sed -e 's,^\(.*\)SZ\(.*\)$,\15\2\n\1SZ\2,g' LANGFILTER: | sed -e 's,TY,6,g' LANGFILTER: | sed -e 's,^\(.*\)ZS\(.*\)$,\17\2\n\1ZS\2,g' LANGFILTER: | grep '^[1-7AÁBCDEÉFGHIÍJKLMNOÓÖŐPRSTUÚÜŰVZ]\{2,15\}$' LANGFILTER: | tr '1234567' '\001\002\003\004\005\006\007' # High bit means "official". Next 7 bits are an enum where # Hungarian==0x14. Low byte is padding XLOC_HEADER:0x9400 2 0 {"_"} 6 1 'A|a' 4 1 'Á|á' 3 2 'B|b' 1 5 'C|c' 1 7 {"CS|cs"} 3 2 'D|d' 6 1 'E|e' 3 3 'É|é' 2 4 'F|f' 3 2 'G|g' 2 4 {"GY|gy"} 2 3 'H|h' 3 1 'I|i' 1 5 'Í|í' 2 4 'J|j' 6 1 'K|k' 4 1 'L|l' 1 8 {"LY|ly"} 3 1 'M|m' 4 1 'N|n' 1 5 {"NY|ny"} 3 1 'O|o' 3 2 'Ó|ó' 2 4 'Ö|ö' 1 7 'Ő|ö' 2 4 'P|p' 4 1 'R|r' 3 1 'S|s' 2 3 {"SZ|sz"} 5 1 'T|t' 1 10 {"TY|ty"} 2 4 'U|u' 1 7 'Ú|ú' 2 4 'Ü|ü' 1 7 'Ű|ű' 2 3 'V|v' 2 4 'Z|z' 1 8 {"ZS|zs"}