/**
*
*
* @param input
* @param filename
*/
void do_ppt(FILE *input,char *filename) {
int itemsread=1;
int rectype;
long reclen;
unsigned char recbuf[8];
while(itemsread) {
itemsread = catdoc_read(recbuf, 1, 8, input);
/* fprintf(stderr,"itemsread=%d: ",itemsread); */
/* for(i=0; i<8; i++) */
/* fprintf(stderr,"%02x ",recbuf[i]); */
/* fprintf(stderr,"\n"); */
if (catdoc_eof(input)) {
process_item(DOCUMENT_END,0,input);
return;
}
if(itemsread < 8)
break;
rectype=getshort(recbuf,2);
reclen=getulong(recbuf,4);
if (reclen < 0) {
return;
}
process_item(rectype,reclen,input);
}
}
void do_table(FILE *input,char *filename) {
long rectype;
long reclen,build_year=0,build_rel=0,offset=0;
int eof_flag=0;
int itemsread=1;
date_shift=25569.0; /* Windows 1900 date system */
CleanUpFormatIdxUsed();
while (itemsread) {
catdoc_read(rec,2,1,input);
biff_version=getshort(rec,0);
catdoc_read(rec,2,1,input);
reclen=getshort(rec,0);
if ( biff_version == 0x0809 || biff_version == 0x0409 ||
biff_version == 0x0209 || biff_version == 0x0009 ) {
if (reclen==8 || reclen==16) {
if (biff_version == 0x0809 ) {
itemsread=catdoc_read(rec,4,1,input);
if (itemsread == 0)
break;
build_year=getshort(rec+2,0);
build_rel=getshort(rec,0);
(void) build_rel;
if(build_year > 5 ) {
catdoc_read(rec,8,1,input);
biff_version=8;
offset=12;
}
else {
biff_version=7;
offset=4;
}
} else if (biff_version == 0x0209 ) {
biff_version=3;
offset=2;
} else if (biff_version == 0x0409 ) {
offset=2;
biff_version=4;
} else {
biff_version=2;
}
itemsread=catdoc_read(rec,reclen-offset,1,input);
break;
} else {
fprintf(stderr,"%s: Invalid BOF record\n",filename);
return;
}
} else {
itemsread=catdoc_read(rec,126,1,input);
}
}
if (catdoc_eof(input)) {
fprintf(stderr,"%s: No BOF record found\n",filename);
exit(1);
}
while(itemsread){
unsigned char buffer[2];
itemsread = catdoc_read(buffer, 2, 1, input);
if (catdoc_eof(input)) {
process_item(MSEOF,0,NULL);
return;
}
if(itemsread == 0)
break;
rectype=getshort(buffer,0);
itemsread = catdoc_read(buffer, 2, 1, input);
if(itemsread == 0)
break;
reclen=getshort(buffer,0);
if (reclen && reclen <MAX_MS_RECSIZE &&reclen >0){
itemsread = catdoc_read(rec, 1, reclen, input);
rec[reclen] = '\0';
}
if(eof_flag) {
if (rectype != BOF) {
break;
}
}
/* fprintf(stderr,"Rectype 0x%04X reclen=%d\n",rectype, reclen); */
process_item(rectype,reclen,rec);
if (rectype == MSEOF) {
eof_flag=1;
} else {
eof_flag=0;
}
}
return;
}
int process_file(FILE *f,long stop) {
int bufptr;
int tabmode=0;
long offset=0;
int hyperlink_mode = 0;
unsigned short c;
/* Now we are starting to read with get_unicode_char */
while (!catdoc_eof(f) && offset<stop) {
bufptr = -1;
do {
int unichar = get_unicode_char(f,&offset,stop);
if (unichar < 0)
continue;
c = unichar;
/* Following symbols below 32 are allowed inside paragraph:
0x0002 - footnote mark
0x0007 - table separator (converted to tabmode)
0x0009 - Horizontal tab ( printed as is)
0x000B - hard return
0x000C - page break
0x000D - return - marks an end of paragraph
0x001E - IS2 for some reason means short defis in Word.
0x001F - soft hyphen in Word
0x0013 - start embedded hyperlink
0x0014 - separate hyperlink URL from text
0x0015 - end embedded hyperlink
*/
if (tabmode) {
tabmode=0;
if (c==0x007) {
buffer[++bufptr]=0x1E;
continue;
} else {
buffer[++bufptr]=0x1C;
}
}
if (c<32) {
switch (c) {
case 0x007:
tabmode = 1;
break;
case 0x000D:
case 0x000B:
buffer[++bufptr]=0x000A;
break;
case 0x000C:
buffer[++bufptr]=c;
break;
case 0x001E:
buffer[++bufptr]='-';
break;
case 0x0002: break;
case 0x001F:
buffer[++bufptr]=0xAD;/* translate to Unicode
soft hyphen */
break;
case 0x0009:
buffer[++bufptr]=c;
break;
case 0x0013:
hyperlink_mode=1;
buffer[++bufptr]=' ';
break;
case 0x0014:
hyperlink_mode = 0;
/*fall through */
case 0x0015:
/* just treat hyperlink separators as
* space */
buffer[++bufptr]=' ';
break;
case 0x0001: if (hyperlink_mode)
break;
/* else fall through */
default:
bufptr=-1; /* Any other control char - discard para*/
}
} else if (c != 0xfeff) {
/* skip ZERO-WIDTH-UNBREAKABLE-SPACE. Output anything
* else*/
buffer[++bufptr]=c;
}
} while (bufptr >=0 && bufptr<PARAGRAPH_BUFFER-2 && !catdoc_eof(f) && buffer[bufptr]!=0x000a);
if (bufptr>0) {
buffer[++bufptr]=0;
output_paragraph(buffer);
}
}
return 0;
}
void copy_out (FILE *f,char *header) {
char *buf=(char *)buffer;
int count,i;
long offset;
if (get_unicode_char == get_word8_char) {
/* non-word file and -u specified. Trying to guess which kind of
* unicode is used
*/
if ((unsigned char)header[0]==0xFE && (unsigned char)header[1]==0xFF) {
get_unicode_char = get_utf16msb;
fputs(convert_char(header[2]<<8|header[3]),output_file);
fputs(convert_char(header[4]<<8|header[5]),output_file);
fputs(convert_char(header[6]<<8|header[7]),output_file);
} else if ((unsigned char)header[0]!=0xFF ||
(unsigned char)header[1]!=0xFE) {
int c,j,d;
/* if it is not utf16, assume it is UTF8. We are told -u,
* aren't we */
get_unicode_char = get_utf8;
i=0;
while (i<8) {
c=(unsigned char)header[i++];
if (c >=0x80) {
if ( c<0xE0) {
c=(c & 0x1F);
count =1;
} else {
c=(c & 0xF);
count = 2;
}
for (j=0;j<count;j++) {
if (i<7) {
d=(unsigned char) header[i++];
} else {
d=fgetc(f);
}
c=c<<6 | (d & 0x3F);
}
}
fputs (convert_char(c),output_file);
}
} else {
get_unicode_char = get_utf16lsb;
fputs(convert_char(header[3]<<8|header[2]),output_file);
fputs(convert_char(header[5]<<8|header[4]),output_file);
fputs(convert_char(header[7]<<8|header[6]),output_file);
}
while (!catdoc_eof(f)) {
i=get_unicode_char(f,&offset,0x7FFFFFFF);
if (i!=EOF) fputs(convert_char(i),output_file);
}
} else {
for (i=0;i<8;i++) {
fputs(convert_char(to_unicode(source_charset,(unsigned char)header[i])),output_file);
}
/* Assuming 8-bit input text */
while ((count = catdoc_read(buf,1,PARAGRAPH_BUFFER,f))) {
for (i=0;i<count;i++) {
fputs(convert_char(to_unicode(source_charset,
(unsigned char)buf[i])),output_file);
}
}
}
}