xzip.cpp

存C写的zip压缩、解压缩源代码。主要对文件操作

                tree[m].dl.len = (ush)bits;
            }
            n--;
        }
    }
}

/* ===========================================================================
 * Generate the codes for a given tree and bit counts (which need not be
 * optimal).
 * IN assertion: the array bl_count contains the bit length statistics for
 * the given tree and the field len is set for all tree elements.
 * OUT assertion: the field code is set for all tree elements of non
 *     zero code length.
 */
void gen_codes (TState &state, ct_data *tree, int max_code)
{
    ush next_code[MAX_BITS+1]; /* next code value for each bit length */
    ush code = 0;              /* running code value */
    int bits;                  /* bit index */
    int n;                     /* code index */

    /* The distribution counts are first used to generate the code values
     * without bit reversal.
     */
    for (bits = 1; bits <= MAX_BITS; bits++) {
        next_code[bits] = code = (ush)((code + state.ts.bl_count[bits-1]) << 1);
    }
    /* Check that the bit counts in bl_count are consistent. The last code
     * must be all ones.
     */
    Assert(state,code + state.ts.bl_count[MAX_BITS]-1 == (1<< ((ush) MAX_BITS)) - 1,
            "inconsistent bit counts");
    Trace("\ngen_codes: max_code %d ", max_code);

    for (n = 0;  n <= max_code; n++) {
        int len = tree[n].dl.len;
        if (len == 0) continue;
        /* Now reverse the bits */
        tree[n].fc.code = (ush)bi_reverse(next_code[len]++, len);

        //Tracec(tree != state.ts.static_ltree, "\nn %3d %c l %2d c %4x (%x) ", n, (isgraph(n) ? n : ' '), len, tree[n].fc.code, next_code[len]-1);
    }
}

/* ===========================================================================
 * Construct one Huffman tree and assigns the code bit strings and lengths.
 * Update the total bit length for the current block.
 * IN assertion: the field freq is set for all tree elements.
 * OUT assertions: the fields len and code are set to the optimal bit length
 *     and corresponding code. The length opt_len is updated; static_len is
 *     also updated if stree is not null. The field max_code is set.
 */
void build_tree(TState &state,tree_desc *desc)
{
    ct_data *tree   = desc->dyn_tree;
    ct_data *stree  = desc->static_tree;
    int elems            = desc->elems;
    int n, m;          /* iterate over heap elements */
    int max_code = -1; /* largest code with non zero frequency */
    int node = elems;  /* next internal node of the tree */

    /* Construct the initial heap, with least frequent element in
     * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1].
     * heap[0] is not used.
     */
    state.ts.heap_len = 0, state.ts.heap_max = HEAP_SIZE;

    for (n = 0; n < elems; n++) {
        if (tree[n].fc.freq != 0) {
            state.ts.heap[++state.ts.heap_len] = max_code = n;
            state.ts.depth[n] = 0;
        } else {
            tree[n].dl.len = 0;
        }
    }

    /* The pkzip format requires that at least one distance code exists,
     * and that at least one bit should be sent even if there is only one
     * possible code. So to avoid special checks later on we force at least
     * two codes of non zero frequency.
     */
    while (state.ts.heap_len < 2) {
        int newcp = state.ts.heap[++state.ts.heap_len] = (max_code < 2 ? ++max_code : 0);
        tree[newcp].fc.freq = 1;
        state.ts.depth[newcp] = 0;
        state.ts.opt_len--; if (stree) state.ts.static_len -= stree[newcp].dl.len;
        /* new is 0 or 1 so it does not have extra bits */
    }
    desc->max_code = max_code;

    /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree,
     * establish sub-heaps of increasing lengths:
     */
    for (n = state.ts.heap_len/2; n >= 1; n--) pqdownheap(state,tree, n);

    /* Construct the Huffman tree by repeatedly combining the least two
     * frequent nodes.
     */
    do {
        pqremove(tree, n);   /* n = node of least frequency */
        m = state.ts.heap[SMALLEST];  /* m = node of next least frequency */

        state.ts.heap[--state.ts.heap_max] = n; /* keep the nodes sorted by frequency */
        state.ts.heap[--state.ts.heap_max] = m;

        /* Create a new node father of n and m */
        tree[node].fc.freq = (ush)(tree[n].fc.freq + tree[m].fc.freq);
        state.ts.depth[node] = (uch) (Max(state.ts.depth[n], state.ts.depth[m]) + 1);
        tree[n].dl.dad = tree[m].dl.dad = (ush)node;
        /* and insert the new node in the heap */
        state.ts.heap[SMALLEST] = node++;
        pqdownheap(state,tree, SMALLEST);

    } while (state.ts.heap_len >= 2);

    state.ts.heap[--state.ts.heap_max] = state.ts.heap[SMALLEST];

    /* At this point, the fields freq and dad are set. We can now
     * generate the bit lengths.
     */
    gen_bitlen(state,(tree_desc *)desc);

    /* The field len is now set, we can generate the bit codes */
    gen_codes (state,(ct_data *)tree, max_code);
}

/* ===========================================================================
 * Scan a literal or distance tree to determine the frequencies of the codes
 * in the bit length tree. Updates opt_len to take into account the repeat
 * counts. (The contribution of the bit length codes will be added later
 * during the construction of bl_tree.)
 */
void scan_tree (TState &state,ct_data *tree, int max_code)
{
    int n;                     /* iterates over all tree elements */
    int prevlen = -1;          /* last emitted length */
    int curlen;                /* length of current code */
    int nextlen = tree[0].dl.len; /* length of next code */
    int count = 0;             /* repeat count of the current code */
    int max_count = 7;         /* max repeat count */
    int min_count = 4;         /* min repeat count */

    if (nextlen == 0) max_count = 138, min_count = 3;
    tree[max_code+1].dl.len = (ush)-1; /* guard */

    for (n = 0; n <= max_code; n++) {
        curlen = nextlen; nextlen = tree[n+1].dl.len;
        if (++count < max_count && curlen == nextlen) {
            continue;
        } else if (count < min_count) {
            state.ts.bl_tree[curlen].fc.freq = (ush)(state.ts.bl_tree[curlen].fc.freq + count);
        } else if (curlen != 0) {
            if (curlen != prevlen) state.ts.bl_tree[curlen].fc.freq++;
            state.ts.bl_tree[REP_3_6].fc.freq++;
        } else if (count <= 10) {
            state.ts.bl_tree[REPZ_3_10].fc.freq++;
        } else {
            state.ts.bl_tree[REPZ_11_138].fc.freq++;
        }
        count = 0; prevlen = curlen;
        if (nextlen == 0) {
            max_count = 138, min_count = 3;
        } else if (curlen == nextlen) {
            max_count = 6, min_count = 3;
        } else {
            max_count = 7, min_count = 4;
        }
    }
}

/* ===========================================================================
 * Send a literal or distance tree in compressed form, using the codes in
 * bl_tree.
 */
void send_tree (TState &state, ct_data *tree, int max_code)
{
    int n;                     /* iterates over all tree elements */
    int prevlen = -1;          /* last emitted length */
    int curlen;                /* length of current code */
    int nextlen = tree[0].dl.len; /* length of next code */
    int count = 0;             /* repeat count of the current code */
    int max_count = 7;         /* max repeat count */
    int min_count = 4;         /* min repeat count */

    /* tree[max_code+1].dl.len = -1; */  /* guard already set */
    if (nextlen == 0) max_count = 138, min_count = 3;

    for (n = 0; n <= max_code; n++) {
        curlen = nextlen; nextlen = tree[n+1].dl.len;
        if (++count < max_count && curlen == nextlen) {
            continue;
        } else if (count < min_count) {
            do { send_code(state, curlen, state.ts.bl_tree); } while (--count != 0);

        } else if (curlen != 0) {
            if (curlen != prevlen) {
                send_code(state, curlen, state.ts.bl_tree); count--;
            }
            Assert(state,count >= 3 && count <= 6, " 3_6?");
            send_code(state,REP_3_6, state.ts.bl_tree); send_bits(state,count-3, 2);

        } else if (count <= 10) {
            send_code(state,REPZ_3_10, state.ts.bl_tree); send_bits(state,count-3, 3);

        } else {
            send_code(state,REPZ_11_138, state.ts.bl_tree); send_bits(state,count-11, 7);
        }
        count = 0; prevlen = curlen;
        if (nextlen == 0) {
            max_count = 138, min_count = 3;
        } else if (curlen == nextlen) {
            max_count = 6, min_count = 3;
        } else {
            max_count = 7, min_count = 4;
        }
    }
}

/* ===========================================================================
 * Construct the Huffman tree for the bit lengths and return the index in
 * bl_order of the last bit length code to send.
 */
int build_bl_tree(TState &state)
{
    int max_blindex;  /* index of last bit length code of non zero freq */

    /* Determine the bit length frequencies for literal and distance trees */
    scan_tree(state,(ct_data *)state.ts.dyn_ltree, state.ts.l_desc.max_code);
    scan_tree(state,(ct_data *)state.ts.dyn_dtree, state.ts.d_desc.max_code);

    /* Build the bit length tree: */
    build_tree(state,(tree_desc *)(&state.ts.bl_desc));
    /* opt_len now includes the length of the tree representations, except
     * the lengths of the bit lengths codes and the 5+5+4 bits for the counts.
     */

    /* Determine the number of bit length codes to send. The pkzip format
     * requires that at least 4 bit length codes be sent. (appnote.txt says
     * 3 but the actual value used is 4.)
     */
    for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) {
        if (state.ts.bl_tree[bl_order[max_blindex]].dl.len != 0) break;
    }
    /* Update opt_len to include the bit length tree and counts */
    state.ts.opt_len += 3*(max_blindex+1) + 5+5+4;
    Trace("\ndyn trees: dyn %ld, stat %ld", state.ts.opt_len, state.ts.static_len);

    return max_blindex;
}

/* ===========================================================================
 * Send the header for a block using dynamic Huffman trees: the counts, the
 * lengths of the bit length codes, the literal tree and the distance tree.
 * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4.
 */
void send_all_trees(TState &state,int lcodes, int dcodes, int blcodes)
{
    int rank;                    /* index in bl_order */

    Assert(state,lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes");
    Assert(state,lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES,
            "too many codes");
    Trace("\nbl counts: ");
    send_bits(state,lcodes-257, 5);
    /* not +255 as stated in appnote.txt 1.93a or -256 in 2.04c */
    send_bits(state,dcodes-1,   5);
    send_bits(state,blcodes-4,  4); /* not -3 as stated in appnote.txt */
    for (rank = 0; rank < blcodes; rank++) {
        Trace("\nbl code %2d ", bl_order[rank]);
        send_bits(state,state.ts.bl_tree[bl_order[rank]].dl.len, 3);
    }    
    Trace("\nbl tree: sent %ld", state.bs.bits_sent);

    send_tree(state,(ct_data *)state.ts.dyn_ltree, lcodes-1); /* send the literal tree */
    Trace("\nlit tree: sent %ld", state.bs.bits_sent);

    send_tree(state,(ct_data *)state.ts.dyn_dtree, dcodes-1); /* send the distance tree */
    Trace("\ndist tree: sent %ld", state.bs.bits_sent);
}

/* ===========================================================================
 * Determine the best encoding for the current block: dynamic trees, static
 * trees or store, and output the encoded block to the zip file. This function
 * returns the total compressed length (in bytes) for the file so far.
 */
ulg flush_block(TState &state,char *buf, ulg stored_len, int eof)
{
    ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */
    int max_blindex;  /* index of last bit length code of non zero freq */

    state.ts.flag_buf[state.ts.last_flags] = state.ts.flags; /* Save the flags for the last 8 items */

     /* Check if the file is ascii or binary */
    if (*state.ts.file_type == (ush)UNKNOWN) set_file_type(state);

    /* Construct the literal and distance trees */
    build_tree(state,(tree_desc *)(&state.ts.l_desc));
    Trace("\nlit data: dyn %ld, stat %ld", state.ts.opt_len, state.ts.static_len);

    build_tree(state,(tree_desc *)(&state.ts.d_desc));
    Trace("\ndist data: dyn %ld, stat %ld", state.ts.opt_len, state.ts.static_len);
    /* At this point, opt_len and static_len are the total bit lengths of
     * the compressed block data, excluding the tree representations.
     */

    /* Build the bit length tree for the above two trees, and get the index
     * in bl_order of the last bit length code to send.
     */
    max_blindex = build_bl_tree(state);

    /* Determine the best encoding. Compute first the block length in bytes */
    opt_lenb = (state.ts.opt_len+3+7)>>3;
    static_lenb = (state.ts.static_len+3+7)>>3;
    state.ts.input_len += stored_len; /* for debugging only */

    Trace("\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u dist %u ",
            opt_lenb, state.ts.opt_len, static_lenb, state.ts.static_len, stored_len,
            state.ts.last_lit, state.ts.last_dist);

    if (static_lenb <= opt_lenb) opt_lenb = static_lenb;

    // Originally, zip allowed the file to be transformed from a compressed
    // into a stored file in the case where compression failed, there
    // was only one block, and it was allowed to change. I've removed this
    // possibility since the code's cleaner if no changes are allowed.
    //if (stored_len <= opt_lenb && eof && state.ts.cmpr_bytelen == 0L
    //   && state.ts.cmpr_len_bits == 0L && state.seekable)
    //{   // && state.ts.file_method != NULL
    //    // Since LIT_BUFSIZE <= 2*WSIZE, the input data must be there: