File: clx.c

package info (click to toggle)
abiword 0.7.7-1
  • links: PTS
  • area: main
  • in suites: potato
  • size: 20,604 kB
  • ctags: 18,358
  • sloc: cpp: 88,791; ansic: 66,296; sh: 7,777; makefile: 3,397; xml: 687; perl: 361; awk: 273; sed: 36; csh: 28
file content (378 lines) | stat: -rw-r--r-- 8,032 bytes parent folder | download
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
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
#include <stdlib.h>
#include <stdio.h>
#include "wv.h"

void wvReleaseCLX(CLX *clx)
	{
	U16 i;
	for(i=0;i<clx->grpprl_count;i++)
		wvFree(clx->grpprl[i]);
	wvFree(clx->grpprl);
	wvFree(clx->cbGrpprl);
	wvReleasePCD_PLCF(clx->pcd,clx->pos);
	}

void wvBuildCLXForSimple6(CLX *clx,FIB *fib)
	{
	wvInitCLX(clx);
    clx->nopcd=1;;

	clx->pcd = (PCD *) malloc(clx->nopcd * sizeof(PCD));
	clx->pos = (U32 *) malloc( (clx->nopcd+1) * sizeof(U32));
	
    clx->pos[0] = 0;
    clx->pos[1] = fib->ccpText;

	wvInitPCD(&(clx->pcd[0]));			
	clx->pcd[0].fc = fib->fcMin;

	/* reverse the special encoding thing they do for word97 
	if we are using the usual 8 bit chars*/
	
	if (fib->fExtChar == 0)
		{
		clx->pcd[0].fc *= 2;
		clx->pcd[0].fc |= 0x40000000UL;
		}

	clx->pcd[0].prm.fComplex = 0;
	clx->pcd[0].prm.para.var1.isprm = 0;
	/*
	these set the ones that *I* use correctly, but may break for other wv
	users, though i doubt it, im just marking a possible firepoint for the
	future
	*/
	}
/*
The complex part of a file (CLX) is composed of a number of variable-sized
blocks of data. Recorded first are any grpprls that may be referenced by the
plcfpcd (if the plcfpcd has no grpprl references, no grpprls will be
recorded) followed by the plcfpcd. Each block in the complex part is
prefaced by a clxt (clx type), which is a 1-byte code, either 1 (meaning the
block contains a grpprl) or 2 (meaning this is the plcfpcd). A clxtGrpprl
(1) is followed by a 2-byte cb which is the count of bytes of the grpprl. A
clxtPlcfpcd (2) is followed by a 4-byte lcb which is the count of bytes of
the piece table. A full saved file will have no clxtGrpprl's.
*/
void wvGetCLX(version ver,CLX *clx,U32 offset,U32 len,U8 fExtChar,FILE *fd)
	{
	U8 clxt;
	U16 cb;
	U32 lcb,i,j=0;

	wvTrace(("offset %x len %d\n",offset,len));
	fseek(fd,offset,SEEK_SET);

	wvInitCLX(clx);

	while (j<len)
		{
		clxt = getc(fd);
		j++;
		if (clxt == 1)
			{
			cb = read_16ubit(fd);
			j+=2;
			clx->grpprl_count++;
			clx->cbGrpprl = (U16 *)realloc(clx->cbGrpprl,sizeof(U16)*clx->grpprl_count);
			clx->cbGrpprl[clx->grpprl_count-1] = cb;
			clx->grpprl = (U8 **)realloc(clx->grpprl,sizeof(U8 *)*(clx->grpprl_count));
			clx->grpprl[clx->grpprl_count-1] = (U8 *)malloc(cb);
			for(i=0;i<cb;i++)
				clx->grpprl[clx->grpprl_count-1][i] = getc(fd);
			j+=i;
			}
		else if (clxt == 2)
			{
			if (ver == WORD8)
				{
				lcb = read_32ubit(fd);
				j+=4;
				}
			else
				{
				wvTrace(("Here so far\n"));
#if 0
				lcb = read_16ubit(fd);		/* word 6 only has two bytes here */
				j+=2;
#endif

				lcb = read_32ubit(fd);		/* word 6 specs appeared to have lied ! */
				j+=4;
				}
			wvGetPCD_PLCF(&clx->pcd,&clx->pos,&clx->nopcd,ftell(fd),lcb,fd);
			j+=lcb;

			if (ver == WORD7)
				{
#if 0
				/* DANGER !!, this is a completely mad attempt to differenciate 
				between word 95 files that use 16 and 8 bit characters. It may
				not work, it attempt to err on the side of 8 bit characters.
				*/
				if (!(wvGuess16bit(clx->pcd,clx->pos,clx->nopcd)))
#else
				/* I think that this is the correct reason for this behaviour */
				if (fExtChar == 0)
#endif
					for (i=0;i<clx->nopcd;i++)
						{
						clx->pcd[i].fc *= 2;
						clx->pcd[i].fc |= 0x40000000UL;
						}
				}
			}
		else
			{
			wvError(("clxt is not 1 or 2, it is %d\n",clxt));
			return;
			}
		}
	}


void wvInitCLX(CLX *item)
	{
    item->pcd=NULL;
	item->pos=NULL;
	item->nopcd=0;

    item->grpprl_count=0;
    item->cbGrpprl=NULL;
    item->grpprl=NULL;
    }


int wvGetPieceBoundsFC(U32 *begin,U32 *end,CLX *clx,U32 piececount)
	{
    int type;
    if ( (piececount+1) > clx->nopcd)
		{
		wvTrace(("piececount is > nopcd, i.e.%d > %d\n", piececount+1,clx->nopcd));
        return(-1);
		}
    *begin = wvNormFC(clx->pcd[piececount].fc,&type);

	if (type)
	    *end = *begin+(clx->pos[piececount+1]-clx->pos[piececount]);
	else
	    *end = *begin+((clx->pos[piececount+1]-clx->pos[piececount])*2);

    return(type);
    }

int wvGetPieceBoundsCP(U32 *begin,U32 *end,CLX *clx,U32 piececount)
	{
    if ( (piececount+1) > clx->nopcd)
        return(-1);
    *begin = clx->pos[piececount];
    *end = clx->pos[piececount+1];
    return(0);
    }


char *wvAutoCharset(wvParseStruct *ps)
	{
	U16 i=0;
	int flag;
	char *ret;
	ret="iso-8859-15";

	/* 
	If any of the pieces use unicode then we have to assume the
	worst and use utf-8
	*/
	while(i<ps->clx.nopcd)
        {
		wvNormFC(ps->clx.pcd[i].fc,&flag);
		if (flag==0)
			{
			ret="UTF-8";
			break;
			}
        i++;
        }

	/* 
	Also if the document fib is not codepage 1252 we also have to 
	assume the worst 
	*/
	if (strcmp(ret,"UTF-8"))
		{
		if (
			(ps->fib.lid != 0x407) &&
			(ps->fib.lid != 0x807) &&
			(ps->fib.lid != 0x409) &&
			(ps->fib.lid != 0x807) &&
			(ps->fib.lid != 0xC09)
			)
		ret="UTF-8";
		}
	return(ret);
	}



int wvQuerySamePiece(U32 fcTest,CLX *clx,U32 piece)
	{
	/*
	wvTrace(("Same Piece, %x %x %x\n",fcTest,wvNormFC(clx->pcd[piece].fc,NULL),wvNormFC(clx->pcd[piece+1].fc,NULL)));
    if ( (fcTest >= wvNormFC(clx->pcd[piece].fc,NULL)) && (fcTest < wvNormFC(clx->pcd[piece+1].fc,NULL)) )
	*/
	wvTrace(("Same Piece, %x %x %x\n",fcTest,clx->pcd[piece].fc,wvGetEndFCPiece(piece,clx)));
    if ( (fcTest >= wvNormFC(clx->pcd[piece].fc,NULL)) && (fcTest < wvGetEndFCPiece(piece,clx)) )
		return(1);
    return(0);
	}


U32 wvGetPieceFromCP(U32 currentcp,CLX *clx)
	{
	U32 i=0;
	while(i<clx->nopcd)
		{
		wvTrace(("i %d: currentcp is %d, clx->pos[i] is %d, clx->pos[i+1] is %d\n",i,currentcp,clx->pos[i],clx->pos[i+1]));
		if ( (currentcp >= clx->pos[i]) && (currentcp < clx->pos[i+1]) )
			return(i);
		i++;
		}
	wvTrace(("cp was not in any piece ! \n",currentcp));
	return(0xffffffffL);
	}

U32 wvGetEndFCPiece(U32 piece,CLX *clx)
	{
	int flag;
	U32 fc;
	U32 offset = clx->pos[piece+1] - clx->pos[piece];

	wvTrace(("offset is %x, befc is %x\n",offset,clx->pcd[piece].fc));
	fc = wvNormFC(clx->pcd[piece].fc,&flag);
	wvTrace(("fc is %x, flag %d\n",fc,flag));
	if (flag) fc+=offset;
	else fc+=offset*2;
	wvTrace(("fc is finally %x\n",fc));
	return(fc);
	}

/*
1) search for the piece containing the character in the piece table.

2) Then calculate the FC in the file that stores the character from the piece
    table information.
*/
U32 wvConvertCPToFC(U32 currentcp,CLX *clx)
	{
	U32 currentfc=0xffffffffL;
	U32 i=0;
	int flag;

	while(i<clx->nopcd)
        {
        if ( (currentcp >= clx->pos[i]) && (currentcp < clx->pos[i+1]) )
            {
            currentfc = wvNormFC(clx->pcd[i].fc,&flag);
			if (flag) currentfc+=(currentcp-clx->pos[i]);
			else currentfc+=((currentcp-clx->pos[i])*2);
            break;
            }
        i++;
        }

	if (currentfc == 0xffffffffL)
		{
		i--;
		currentfc = wvNormFC(clx->pcd[i].fc,&flag);
		if (flag) currentfc+=(currentcp-clx->pos[i]);
		else currentfc+=((currentcp-clx->pos[i])*2);
		wvTrace(("flaky cp to fc conversion underway\n"));
		}

	return(currentfc);
	}

struct test
	{
	U32 fc;
	U32 offset;
	};

int compar(const void *a, const void *b)
	{
	struct test *one,*two;
	one = (struct test *)a;
	two = (struct test *)b;
	
	if (one->fc < two->fc)
		return(-1);
	else if (one->fc == two->fc)
		return(0);
	return(1);
	}

/* 
In word 95 files there is no flag attached to each
offset as there is in word 97 to tell you that we are
talking about 16 bit chars, so I attempt here to make
an educated guess based on overlapping offsets to
figure it out, If I had some actual information as
the how word 95 actually stores it it would help.
*/

int wvGuess16bit(PCD *pcd,U32 *pos,U32 nopcd)
	{
	struct test *fcs;
	U32 i;
	int ret=1;
	fcs = (struct test *)malloc(sizeof(struct test) * nopcd);
	for(i=0;i<nopcd;i++)
		{
		fcs[i].fc = pcd[i].fc;
		fcs[i].offset = (pos[i+1]-pos[i])*2;
		}

	qsort(fcs, nopcd, sizeof(struct test), compar);

	for(i=0;i<nopcd-1;i++)
		{
		if (fcs[i].fc+fcs[i].offset > fcs[i+1].fc)
			{
			wvTrace(("overlap, my guess is 8 bit\n"));
			ret = 0;
			break;
			}
		}

	wvFree(fcs);
	return(ret);
	}