pcollinsg.c (5094B)
1 #include <u.h> 2 #include <libc.h> 3 #include <bio.h> 4 #include "dict.h" 5 6 /* 7 * Routines for handling dictionaries in the "Paperback Collins" 8 * `German' format (with tags surrounded by \5⋯\6 and \xba⋯\xba) 9 */ 10 11 /* 12 * \5...\6 escapes (fonts, mostly) 13 * 14 * h headword (helvetica 7 pt) 15 * c clause (helvetica 7 pt) 16 * 3 helvetica 7 pt 17 * 4 helvetica 6.5 pt 18 * s helvetica 8 pt 19 * x helvetica 8 pt 20 * y helvetica 5 pt 21 * m helvetica 30 pt 22 * 1 roman 6 pt 23 * 9 roman 4.5 pt 24 * p roman 7 pt 25 * q roman 4.5 pt 26 * 2 italic 6 pt 27 * 7 italic 4.5 pt 28 * b bold 6 pt 29 * a `indent 0:4 left' 30 * k `keep 9' 31 * l `size 12' 32 */ 33 34 enum { 35 IBASE=0x69, /* dotless i */ 36 Taglen=32 37 }; 38 39 static Rune intab[256] = { 40 /*0*/ /*1*/ /*2*/ /*3*/ /*4*/ /*5*/ /*6*/ /*7*/ 41 /*00*/ NONE, NONE, NONE, NONE, NONE, TAGS, TAGE, NONE, 42 NONE, NONE, NONE, NONE, NONE, 0x20, NONE, NONE, 43 /*10*/ NONE, 0x2d, 0x20, 0x20, NONE, NONE, NONE, NONE, 44 0x20, NONE, NONE, NONE, 0x20, NONE, NONE, 0x2d, 45 /*20*/ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, '\'', 46 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 47 /*30*/ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 48 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 49 /*40*/ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 50 0x48, 0x49, 0x4a, 0x4b,'L', 0x4d, 0x4e, 0x4f, 51 /*50*/ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 52 0x58, 0x59, 0x5a, 0x5b,'\\', 0x5d, 0x5e, 0x5f, 53 /*60*/ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 54 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, 55 /*70*/ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 56 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, NONE, 57 /*80*/ NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 58 NONE, NONE, 0x20, NONE, NONE, NONE, NONE, NONE, 59 /*90*/ 0xdf, 0xe6, NONE, MOE, NONE, NONE, NONE, 0xf8, 60 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 61 /*A0*/ NONE, NONE, 0x22, 0xa3, NONE, NONE, NONE, NONE, 62 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 63 /*B0*/ NONE, NONE, NONE, NONE, NONE, NONE, NONE, 0x7e, 64 NONE, IBASE, SPCS, NONE, NONE, NONE, NONE, NONE, 65 /*C0*/ NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 66 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 67 /*D0*/ NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 68 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 69 /*E0*/ NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 70 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE, 71 /*F0*/ 0x20, 0x20, NONE, NONE, NONE, NONE, NONE, NONE, 72 NONE, NONE, NONE, NONE, NONE, NONE, NONE, NONE 73 }; 74 75 static Nassoc numtab[] = { 76 {1, 0x2b}, 77 {4, 0x3d}, 78 {7, 0xb0}, 79 {11, 0x2248}, 80 {69, 0x2666}, 81 {114, 0xae}, 82 {340, 0x25b}, 83 {341, 0x254}, 84 {342, 0x28c}, 85 {343, 0x259}, 86 {345, 0x292}, 87 {346, 0x283}, 88 {347, 0x275}, 89 {348, 0x28a}, 90 {349, 0x2c8}, 91 {351, 0x26a}, 92 {352, 0x25c}, 93 {354, 0x251}, 94 {355, 0x7e}, 95 {356, 0x252}, 96 {384, 0x273}, 97 {445, 0xf0}, /* BUG -- should be script eth */ 98 }; 99 100 static Nassoc overtab[] = { 101 {0x2c, LCED}, 102 {0x2f, LACU}, 103 {0x3a, LUML}, 104 {'\\', LGRV}, 105 {0x5e, LFRN}, 106 {0x7e, LTIL} 107 }; 108 109 static uchar *reach(uchar*, int); 110 111 static Entry curentry; 112 static char tag[Taglen]; 113 114 void 115 pcollgprintentry(Entry e, int cmd) 116 { 117 uchar *p, *pe; 118 int r, rprev = NONE, rx, over = 0, font; 119 char buf[16]; 120 121 p = (uchar *)e.start; 122 pe = (uchar *)e.end; 123 curentry = e; 124 if(cmd == 'h') 125 outinhibit = 1; 126 while(p < pe){ 127 if(cmd == 'r'){ 128 outchar(*p++); 129 continue; 130 } 131 switch(r = intab[*p++]){ /* assign = */ 132 case TAGS: 133 if(rprev != NONE){ 134 outrune(rprev); 135 rprev = NONE; 136 } 137 p = reach(p, 0x06); 138 font = tag[0]; 139 if(cmd == 'h') 140 outinhibit = (font != 'h'); 141 break; 142 143 case TAGE: /* an extra one */ 144 break; 145 146 case SPCS: 147 p = reach(p, 0xba); 148 r = looknassoc(numtab, asize(numtab), strtol(tag,0,0)); 149 if(r < 0){ 150 if(rprev != NONE){ 151 outrune(rprev); 152 rprev = NONE; 153 } 154 sprint(buf, "\\N'%s'", tag); 155 outchars(buf); 156 break; 157 } 158 /* else fall through */ 159 160 default: 161 if(over){ 162 rx = looknassoc(overtab, asize(overtab), r); 163 if(rx > 0) 164 rx = liglookup(rx, rprev); 165 if(rx > 0 && rx != NONE) 166 outrune(rx); 167 else{ 168 outrune(rprev); 169 if(r == ':') 170 outrune(0xa8); 171 else{ 172 outrune(0x5e); 173 outrune(r); 174 } 175 } 176 over = 0; 177 rprev = NONE; 178 }else if(r == '^'){ 179 over = 1; 180 }else{ 181 if(rprev != NONE) 182 outrune(rprev); 183 rprev = r; 184 } 185 } 186 187 } 188 if(rprev != NONE) 189 outrune(rprev); 190 if(cmd == 'h') 191 outinhibit = 0; 192 outnl(0); 193 } 194 195 long 196 pcollgnextoff(long fromoff) 197 { 198 int c, state = 0, defoff = -1; 199 200 if(Bseek(bdict, fromoff, 0) < 0) 201 return -1; 202 while((c = Bgetc(bdict)) >= 0){ 203 if(c == '\r') 204 defoff = Boffset(bdict); 205 switch(state){ 206 case 0: 207 if(c == 0x05) 208 state = 1; 209 break; 210 case 1: 211 if(c == 'h') 212 state = 2; 213 else 214 state = 0; 215 break; 216 case 2: 217 if(c == 0x06) 218 return (Boffset(bdict)-3); 219 else 220 state = 0; 221 break; 222 } 223 } 224 return defoff; 225 } 226 227 void 228 pcollgprintkey(void) 229 { 230 Bprint(bout, "No pronunciation key yet\n"); 231 } 232 233 static uchar * 234 reach(uchar *p, int tagchar) 235 { 236 int c; char *q=tag; 237 238 while(p < (uchar *)curentry.end){ 239 c = *p++; 240 if(c == tagchar) 241 break; 242 *q++ = c; 243 if(q >= &tag[sizeof tag-1]) 244 break; 245 } 246 *q = 0; 247 return p; 248 }