I am trying to create a utility for generating palmdoc/mobipocket format ebook files, it is said that mobi uses LZ77 compression technique to compress their records, but I found that there is quite a deviation from standard LZ77, My main source of reference is Calibre ebook creator with C implementation for palmdoc
In this file, uncompress works well, but I have not been able to compress a mobi record identically similar either using other implementation or this (Calibre code doent decompress the same).
I found some differences like, (<-- my comments follow in code)
static Py_ssize_t <-- can replaced with size_t
cpalmdoc_do_compress(buffer *b, char *output) {
Py_ssize_t i = 0, j, chunk_len, dist;
unsigned int compound;
Byte c, n;
bool found;
char *head;
buffer temp;
head = output;
temp.data = (Byte *)PyMem_Malloc(sizeof(Byte)*8); temp.len = 0;
if (temp.data == NULL) return 0;
while (i < b->len) {
c = b->data[i];
//do repeats
if ( i > 10 && (b->len - i) > 10) { <-- ignores any match outside this range
found = false;
for (chunk_len = 10; chunk_len > 2; chunk_len--) {
j = cpalmdoc_rfind(b->data, i, chunk_len);
dist = i - j;
if (j < i && dist <= 2047) { <-- 2048 window size instead of 4096
found = true;
compound = (unsigned int)((dist << 3) + chunk_len-3);
*(output++) = CHAR(0x80 + (compound >> 8 ));
*(output++) = CHAR(compound & 0xFF);
i += chunk_len;
break;
}
}
if (found) continue;
}
//write single character
i++;
if (c == 32 && i < b->len) { <-- if space is encountered skip char & check for next sequence for match otherwise do this, due to this code had wrong result.
n = b->data[i];
if ( n >= 0x40 && n <= 0x7F) {
*(output++) = CHAR(n^0x80); i++; continue;
}
}
if (c == 0 || (c > 8 && c < 0x80))
*(output++) = CHAR(c);
else { // Write binary data <-- why binary data? LZ is for text encoding
j = i;
temp.data[0] = c; temp.len = 1;
while (j < b->len && temp.len < 8) {
c = b->data[j];
if (c == 0 || (c > 8 && c < 0x80)) break;
temp.data[temp.len++] = c; j++;
}
i += temp.len - 1;
*(output++) = (char)temp.len;
for (j=0; j < temp.len; j++) *(output++) = (char)temp.data[j];
}
}
PyMem_Free(temp.data);
return output - head;
}
is this implementation correct?
