static void
init_frequencies(SymbolFrequencies *pSF)
{
memset(*pSF, 0, sizeof(SymbolFrequencies));
#if 0
unsigned int i;
for(i = 0; i < MAX_SYMBOLS; ++i)
{
unsigned char uc = (unsigned char)i;
(*pSF)[i] = new_leaf_node(uc);
}
#endif
}
static unsigned int get_symfreq(symfreq *sf, FILE *in)
{
int c;
unsigned int tot = 0;
/* 初始化频率表 */
init_freq(sf);
/* 计算文件中每个符号的出现次数 */
while ((c = fgetc(in)) != EOF) {
unsigned char uc = c;
if (!(*sf)[uc])
(*sf)[uc] = new_leaf_node(uc);
++(*sf)[uc]->count;
++tot;
}
return tot;
}
static unsigned int
get_symbol_frequencies(SymbolFrequencies *pSF, FILE *in)
{
int c;
unsigned int total_count = 0;
/* Set all frequencies to 0. */
init_frequencies(pSF);
/* Count the frequency of each symbol in the input file. */
while((c = fgetc(in)) != EOF)
{
unsigned char uc = c;
if(!(*pSF)[uc])
(*pSF)[uc] = new_leaf_node(uc);
++(*pSF)[uc]->count;
++total_count;
}
return total_count;
}
static unsigned int
get_symbol_frequencies_from_memory(SymbolFrequencies *pSF,
const unsigned char *bufin,
unsigned int bufinlen)
{
unsigned int i;
unsigned int total_count = 0;
/* Set all frequencies to 0. */
init_frequencies(pSF);
/* Count the frequency of each symbol in the input file. */
for(i = 0; i < bufinlen; ++i)
{
unsigned char uc = bufin[i];
if(!(*pSF)[uc])
(*pSF)[uc] = new_leaf_node(uc);
++(*pSF)[uc]->count;
++total_count;
}
return total_count;
}
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;
}
/* 读入编码表，返回构建的 Huffman 树 */
static node *read_code_table(FILE *in, unsigned int *pdb)
{
node *root = new_node(0, NULL, NULL);
uint32_t count;
/* 读入符号数 */
if (fread(&count, sizeof(count), 1, in) != 1) {
free_tree(root);
return NULL;
}
count = ntohl(count);
/* 读入当前分支编码数 */
if (fread(pdb, sizeof(*pdb), 1, in) != 1) {
free_tree(root);
return NULL;
}
*pdb = ntohl(*pdb);
/* 读入符号表 */
while (count-- > 0) {
int c;
unsigned int c_bit;
unsigned char symbol;
unsigned char len;
unsigned char lbytes;
unsigned char *bytes;
node *p = root;
if ((c = fgetc(in)) == EOF) {
free_tree(root);
return NULL;
}
symbol = (unsigned char) c;
if ((c = fgetc(in)) == EOF) {
free_tree(root);
return NULL;
}
len = (unsigned char) c;
lbytes = (unsigned char) bit_len_byte(len);
bytes = (unsigned char *) malloc(lbytes);
if (fread(bytes, 1, lbytes, in) != lbytes) {
free(bytes);
free_tree(root);
return NULL;
}
/* 依据当前位加入 Huffman 树 */
for (c_bit = 0; c_bit < len; ++c_bit) {
if (get_bit(bytes, c_bit)) {
if (p->one == NULL) {
p->one = c_bit == (unsigned char) (len - 1)
? new_leaf_node(symbol)
: new_node(0, NULL, NULL);
p->one->parent = p;
}
p = p->one;
} else {
if (p->zero == NULL) {
p->zero = c_bit == (unsigned char) (len - 1)
? new_leaf_node(symbol)
: new_node(0, NULL, NULL);
p->zero->parent = p;
}
p = p->zero;
}
}
free(bytes);
}
return root;
}