/*
* calculate_huffman_codes turns pSF into an array
* with a single entry that is the root of the
* huffman tree. The return value is a SymbolEncoder,
* which is an array of huffman codes index by symbol value.
*/
static SymbolEncoder*
calculate_huffman_codes(SymbolFrequencies * pSF)
{
unsigned int i = 0;
unsigned int n = 0;
huffman_node *m1 = NULL, *m2 = NULL;
SymbolEncoder *pSE = NULL;
#if 0
printf("BEFORE SORT\n");
print_freqs(pSF);
#endif
/* Sort the symbol frequency array by ascending frequency. */
qsort((*pSF), MAX_SYMBOLS, sizeof((*pSF)[0]), SFComp);
#if 0
printf("AFTER SORT\n");
print_freqs(pSF);
#endif
/* Get the number of symbols. */
for(n = 0; n < MAX_SYMBOLS && (*pSF)[n]; ++n)
;
/*
* Construct a Huffman tree. This code is based
* on the algorithm given in Managing Gigabytes
* by Ian Witten et al, 2nd edition, page 34.
* Note that this implementation uses a simple
* count instead of probability.
*/
for(i = 0; i < n - 1; ++i)
{
/* Set m1 and m2 to the two subsets of least probability. */
m1 = (*pSF)[0];
m2 = (*pSF)[1];
/* Replace m1 and m2 with a set {m1, m2} whose probability
* is the sum of that of m1 and m2. */
(*pSF)[0] = m1->parent = m2->parent =
new_nonleaf_node(m1->count + m2->count, m1, m2);
(*pSF)[1] = NULL;
/* Put newSet into the correct count position in pSF. */
qsort((*pSF), n, sizeof((*pSF)[0]), SFComp);
}
/* Build the SymbolEncoder array from the tree. */
pSE = (SymbolEncoder*)malloc(sizeof(SymbolEncoder));
memset(pSE, 0, sizeof(SymbolEncoder));
build_symbol_encoder((*pSF)[0], pSE);
return pSE;
}
static huffman_node*
read_code_table_from_memory(const unsigned char* bufin,
unsigned int bufinlen,
unsigned int *pindex,
uint32_t *pDataBytes)
{
huffman_node *root = new_nonleaf_node(0, NULL, NULL);
uint32_t count;
/* Read the number of entries.
(it is stored in network byte order). */
if(memread(bufin, bufinlen, pindex, &count, sizeof(count)))
{
free_huffman_tree(root);
return NULL;
}
count = ntohl(count);
/* Read the number of data bytes this encoding represents. */
if(memread(bufin, bufinlen, pindex, pDataBytes, sizeof(*pDataBytes)))
{
free_huffman_tree(root);
return NULL;
}
*pDataBytes = ntohl(*pDataBytes);
/* Read the entries. */
while(count-- > 0)
{
unsigned int curbit;
unsigned char symbol;
unsigned char numbits;
unsigned char numbytes;
unsigned char *bytes;
huffman_node *p = root;
if(memread(bufin, bufinlen, pindex, &symbol, sizeof(symbol)))
{
free_huffman_tree(root);
return NULL;
}
if(memread(bufin, bufinlen, pindex, &numbits, sizeof(numbits)))
{
free_huffman_tree(root);
return NULL;
}
numbytes = (unsigned char)numbytes_from_numbits(numbits);
bytes = (unsigned char*)malloc(numbytes);
if(memread(bufin, bufinlen, pindex, bytes, numbytes))
{
free(bytes);
free_huffman_tree(root);
return NULL;
}
/*
* Add the entry to the Huffman tree. The value
* of the current bit is used switch between
* zero and one child nodes in the tree. New nodes
* are added as needed in the tree.
*/
for(curbit = 0; curbit < numbits; ++curbit)
{
if(get_bit(bytes, curbit))
{
if(p->one == NULL)
{
p->one = curbit == (unsigned char)(numbits - 1)
? new_leaf_node(symbol)
: new_nonleaf_node(0, NULL, NULL);
p->one->parent = p;
}
p = p->one;
}
else
{
if(p->zero == NULL)
{
p->zero = curbit == (unsigned char)(numbits - 1)
? new_leaf_node(symbol)
: new_nonleaf_node(0, NULL, NULL);
p->zero->parent = p;
}
p = p->zero;
}
}
free(bytes);
}
return root;
}
/*
* read_code_table builds a Huffman tree from the code
* in the in file. This function returns NULL on error.
* The returned value should be freed with free_huffman_tree.
*/
static huffman_node*
read_code_table(FILE* in, unsigned int *pDataBytes)
{
huffman_node *root = new_nonleaf_node(0, NULL, NULL);
unsigned int count;
/* Read the number of entries.
(it is stored in network byte order). */
if(fread(&count, sizeof(count), 1, in) != 1)
{
free_huffman_tree(root);
return NULL;
}
count = ntohl(count);
/* Read the number of data bytes this encoding represents. */
if(fread(pDataBytes, sizeof(*pDataBytes), 1, in) != 1)
{
free_huffman_tree(root);
return NULL;
}
*pDataBytes = ntohl(*pDataBytes);
/* Read the entries. */
while(count-- > 0)
{
int c;
unsigned int curbit;
unsigned char symbol;
unsigned char numbits;
unsigned char numbytes;
unsigned char *bytes;
huffman_node *p = root;
if((c = fgetc(in)) == EOF)
{
free_huffman_tree(root);
return NULL;
}
symbol = (unsigned char)c;
if((c = fgetc(in)) == EOF)
{
free_huffman_tree(root);
return NULL;
}
numbits = (unsigned char)c;
numbytes = (unsigned char)numbytes_from_numbits(numbits);
bytes = (unsigned char*)malloc(numbytes);
if(fread(bytes, 1, numbytes, in) != numbytes)
{
free(bytes);
free_huffman_tree(root);
return NULL;
}
/*
* Add the entry to the Huffman tree. The value
* of the current bit is used switch between
* zero and one child nodes in the tree. New nodes
* are added as needed in the tree.
*/
for(curbit = 0; curbit < numbits; ++curbit)
{
if(get_bit(bytes, curbit))
{
if(p->one == NULL)
{
p->one = curbit == (unsigned char)(numbits - 1)
? new_leaf_node(symbol)
: new_nonleaf_node(0, NULL, NULL);
p->one->parent = p;
}
p = p->one;
}
else
{
if(p->zero == NULL)
{
p->zero = curbit == (unsigned char)(numbits - 1)
? new_leaf_node(symbol)
: new_nonleaf_node(0, NULL, NULL);
p->zero->parent = p;
}
p = p->zero;
}
}
free(bytes);
}
return root;
}
