1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286
|
/* This file is part of the YAZ toolkit.
* Copyright (C) 1995-2012 Index Data
* See the file LICENSE for details.
*/
/**
* \file
* \brief MARC-8 decoding
*
* MARC-8 reference:
* http://www.loc.gov/marc/specifications/speccharmarc8.html
*/
#if HAVE_CONFIG_H
#include <config.h>
#endif
#include <assert.h>
#include <errno.h>
#include <string.h>
#include <yaz/xmalloc.h>
#include "iconv-p.h"
struct decoder_data {
int g0_mode;
int g1_mode;
int comb_offset;
int comb_size;
unsigned long comb_x[8];
size_t comb_no_read[8];
};
yaz_conv_func_t yaz_marc8_42_conv;
yaz_conv_func_t yaz_marc8_45_conv;
yaz_conv_func_t yaz_marc8_67_conv;
yaz_conv_func_t yaz_marc8_62_conv;
yaz_conv_func_t yaz_marc8_70_conv;
yaz_conv_func_t yaz_marc8_32_conv;
yaz_conv_func_t yaz_marc8_4E_conv;
yaz_conv_func_t yaz_marc8_51_conv;
yaz_conv_func_t yaz_marc8_33_conv;
yaz_conv_func_t yaz_marc8_34_conv;
yaz_conv_func_t yaz_marc8_53_conv;
yaz_conv_func_t yaz_marc8_31_conv;
static unsigned long yaz_read_marc8_comb(yaz_iconv_t cd,
struct decoder_data *data,
unsigned char *inp,
size_t inbytesleft, size_t *no_read,
int *comb);
static unsigned long read_marc8(yaz_iconv_t cd, yaz_iconv_decoder_t d,
unsigned char *inp,
size_t inbytesleft, size_t *no_read)
{
struct decoder_data *data = (struct decoder_data *) d->data;
unsigned long x;
if (data->comb_offset < data->comb_size)
{
*no_read = data->comb_no_read[data->comb_offset];
x = data->comb_x[data->comb_offset];
/* special case for double-diacritic combining characters,
INVERTED BREVE and DOUBLE TILDE.
We'll increment the no_read counter by 1, since we want to skip over
the processing of the closing ligature character
*/
/* this code is no longer necessary.. our handlers code in
yaz_marc8_?_conv (generated by charconv.tcl) now returns
0 and no_read=1 when a sequence does not match the input.
The SECOND HALFs in codetables.xml produces a non-existant
entry in the conversion trie.. Hence when met, the input byte is
skipped as it should (in yaz_iconv)
*/
#if 0
if (x == 0x0361 || x == 0x0360)
*no_read += 1;
#endif
data->comb_offset++;
return x;
}
data->comb_offset = 0;
for (data->comb_size = 0; data->comb_size < 8; data->comb_size++)
{
int comb = 0;
if (inbytesleft == 0 && data->comb_size)
{
yaz_iconv_set_errno(cd, YAZ_ICONV_EINVAL);
x = 0;
*no_read = 0;
break;
}
x = yaz_read_marc8_comb(cd, data, inp, inbytesleft, no_read, &comb);
if (!comb || !x)
break;
data->comb_x[data->comb_size] = x;
data->comb_no_read[data->comb_size] = *no_read;
inp += *no_read;
inbytesleft = inbytesleft - *no_read;
}
return x;
}
static unsigned long read_marc8s(yaz_iconv_t cd, yaz_iconv_decoder_t d,
unsigned char *inp,
size_t inbytesleft, size_t *no_read)
{
struct decoder_data *data = (struct decoder_data *) d->data;
unsigned long x = read_marc8(cd, d, inp, inbytesleft, no_read);
if (x && data->comb_size == 1)
{
if (yaz_iso_8859_1_lookup_x12(x, data->comb_x[0], &x))
{
*no_read += data->comb_no_read[0];
data->comb_size = 0;
}
}
return x;
}
static unsigned long yaz_read_marc8_comb(yaz_iconv_t cd,
struct decoder_data *data,
unsigned char *inp,
size_t inbytesleft, size_t *no_read,
int *comb)
{
*no_read = 0;
while (inbytesleft > 0 && *inp == 27)
{
int *modep = &data->g0_mode;
size_t inbytesleft0 = inbytesleft;
inbytesleft--;
inp++;
if (inbytesleft == 0)
goto incomplete;
if (*inp == '$') /* set with multiple bytes */
{
inbytesleft--;
inp++;
}
if (inbytesleft == 0)
goto incomplete;
if (*inp == '(' || *inp == ',') /* G0 */
{
inbytesleft--;
inp++;
}
else if (*inp == ')' || *inp == '-') /* G1 */
{
inbytesleft--;
inp++;
modep = &data->g1_mode;
}
if (inbytesleft == 0)
goto incomplete;
if (*inp == '!') /* ANSEL is a special case */
{
inbytesleft--;
inp++;
}
if (inbytesleft == 0)
goto incomplete;
*modep = *inp++; /* Final character */
inbytesleft--;
(*no_read) += inbytesleft0 - inbytesleft;
}
if (inbytesleft == 0)
return 0;
else if (*inp == ' ')
{
*no_read += 1;
return ' ';
}
else
{
unsigned long x;
size_t no_read_sub = 0;
int mode = *inp < 128 ? data->g0_mode : data->g1_mode;
*comb = 0;
switch(mode)
{
case 'B': /* Basic ASCII */
case 's': /* ASCII */
x = yaz_marc8_42_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'E': /* ANSEL */
x = yaz_marc8_45_conv(inp, inbytesleft, &no_read_sub, comb, 127, 128);
break;
case 'g': /* Greek */
x = yaz_marc8_67_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'b': /* Subscripts */
x = yaz_marc8_62_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'p': /* Superscripts */
x = yaz_marc8_70_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case '2': /* Basic Hebrew */
x = yaz_marc8_32_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'N': /* Basic Cyrillic */
x = yaz_marc8_4E_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'Q': /* Extended Cyrillic */
x = yaz_marc8_51_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case '3': /* Basic Arabic */
x = yaz_marc8_33_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case '4': /* Extended Arabic */
x = yaz_marc8_34_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case 'S': /* Greek */
x = yaz_marc8_53_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
case '1': /* Chinese, Japanese, Korean (EACC) */
x = yaz_marc8_31_conv(inp, inbytesleft, &no_read_sub, comb, 127, 0);
break;
default:
*no_read = 0;
yaz_iconv_set_errno(cd, YAZ_ICONV_EILSEQ);
return 0;
}
*no_read += no_read_sub;
return x;
}
incomplete:
*no_read = 0;
yaz_iconv_set_errno(cd, YAZ_ICONV_EINVAL);
return 0;
}
static size_t init_marc8(yaz_iconv_t cd, yaz_iconv_decoder_t d,
unsigned char *inp,
size_t inbytesleft, size_t *no_read)
{
struct decoder_data *data = (struct decoder_data *) d->data;
data->g0_mode = 'B';
data->g1_mode = 'E';
data->comb_offset = data->comb_size = 0;
return 0;
}
void destroy_marc8(yaz_iconv_decoder_t d)
{
struct decoder_data *data = (struct decoder_data *) d->data;
xfree(data);
}
yaz_iconv_decoder_t yaz_marc8_decoder(const char *fromcode,
yaz_iconv_decoder_t d)
{
if (!yaz_matchstr(fromcode, "MARC8") || !yaz_matchstr(fromcode, "ANSEL"))
d->read_handle = read_marc8;
else if (!yaz_matchstr(fromcode, "MARC8s"))
d->read_handle = read_marc8s;
else
return 0;
{
struct decoder_data *data = (struct decoder_data *)
xmalloc(sizeof(*data));
d->data = data;
d->init_handle = init_marc8;
d->destroy_handle = destroy_marc8;
}
return d;
}
/*
* Local variables:
* c-basic-offset: 4
* c-file-style: "Stroustrup"
* indent-tabs-mode: nil
* End:
* vim: shiftwidth=4 tabstop=8 expandtab
*/
|