xunzip.cpp

压缩/解压缩类源码

    n = (uInt)(s->write - q);
    if (n > z->avail_out) n = z->avail_out;
    if (n && r == Z_BUF_ERROR) r = Z_OK;

    // update counters 
    z->avail_out -= n;
    z->total_out += n;

    // update check information 
    if (s->checkfn != Z_NULL)
      z->adler = s->check = (*s->checkfn)(s->check, q, n);

    // copy
    memcpy(p, q, n);
    p += n;
    q += n;
  }

  // update pointers
  z->next_out = p;
  s->read = q;

  // done
  return r;
}






// simplify the use of the inflate_huft type with some defines
#define exop word.what.Exop
#define bits word.what.Bits

typedef enum {        // waiting for "i:"=input, "o:"=output, "x:"=nothing 
      START,    // x: set up for LEN 
      LEN,      // i: get length/literal/eob next 
      LENEXT,   // i: getting length extra (have base) 
      DIST,     // i: get distance next 
      DISTEXT,  // i: getting distance extra 
      COPY,     // o: copying bytes in window, waiting for space
      LIT,      // o: got literal, waiting for output space 
      WASH,     // o: got eob, possibly still output waiting 
      END,      // x: got eob and all data flushed 
      BADCODE}  // x: got error 
inflate_codes_mode;

// inflate codes private state
struct inflate_codes_state {

  // mode 
  inflate_codes_mode mode;      // current inflate_codes mode 

  // mode dependent information 
  uInt len;
  union {
    struct {
      const inflate_huft *tree;       // pointer into tree 
      uInt need;                // bits needed 
    } code;             // if LEN or DIST, where in tree 
    uInt lit;           // if LIT, literal 
    struct {
      uInt get;                 // bits to get for extra 
      uInt dist;                // distance back to copy from 
    } copy;             // if EXT or COPY, where and how much 
  } sub;                // submode

  // mode independent information 
  Byte lbits;           // ltree bits decoded per branch 
  Byte dbits;           // dtree bits decoder per branch 
  const inflate_huft *ltree;          // literal/length/eob tree
  const inflate_huft *dtree;          // distance tree

};


inflate_codes_statef *inflate_codes_new(
uInt bl, uInt bd,
const inflate_huft *tl,
const inflate_huft *td, // need separate declaration for Borland C++
z_streamp z)
{
  inflate_codes_statef *c;

  if ((c = (inflate_codes_statef *)
       ZALLOC(z,1,sizeof(struct inflate_codes_state))) != Z_NULL)
  {
    c->mode = START;
    c->lbits = (Byte)bl;
    c->dbits = (Byte)bd;
    c->ltree = tl;
    c->dtree = td;
    Tracev((stderr, "inflate:       codes new\n"));
  }
  return c;
}


int inflate_codes(inflate_blocks_statef *s, z_streamp z, int r)
{
  uInt j;               // temporary storage
  const inflate_huft *t;      // temporary pointer
  uInt e;               // extra bits or operation
  uLong b;              // bit buffer
  uInt k;               // bits in bit buffer
  Byte *p;             // input data pointer
  uInt n;               // bytes available there
  Byte *q;             // output window write pointer
  uInt m;               // bytes to end of window or read pointer
  Byte *f;             // pointer to copy strings from
  inflate_codes_statef *c = s->sub.decode.codes;  // codes state

  // copy input/output information to locals (UPDATE macro restores)
  LOAD

  // process input and output based on current state
  for(;;) switch (c->mode)
  {             // waiting for "i:"=input, "o:"=output, "x:"=nothing
    case START:         // x: set up for LEN
#ifndef SLOW
      if (m >= 258 && n >= 10)
      {
        UPDATE
        r = inflate_fast(c->lbits, c->dbits, c->ltree, c->dtree, s, z);
        LOAD
        if (r != Z_OK)
        {
          c->mode = r == Z_STREAM_END ? WASH : BADCODE;
          break;
        }
      }
#endif // !SLOW
      c->sub.code.need = c->lbits;
      c->sub.code.tree = c->ltree;
      c->mode = LEN;
    case LEN:           // i: get length/literal/eob next
      j = c->sub.code.need;
      NEEDBITS(j)
      t = c->sub.code.tree + ((uInt)b & inflate_mask[j]);
      DUMPBITS(t->bits)
      e = (uInt)(t->exop);
      if (e == 0)               // literal 
      {
        c->sub.lit = t->base;
        Tracevv((stderr, t->base >= 0x20 && t->base < 0x7f ?
                 "inflate:         literal '%c'\n" :
                 "inflate:         literal 0x%02x\n", t->base));
        c->mode = LIT;
        break;
      }
      if (e & 16)               // length 
      {
        c->sub.copy.get = e & 15;
        c->len = t->base;
        c->mode = LENEXT;
        break;
      }
      if ((e & 64) == 0)        // next table 
      {
        c->sub.code.need = e;
        c->sub.code.tree = t + t->base;
        break;
      }
      if (e & 32)               // end of block 
      {
        Tracevv((stderr, "inflate:         end of block\n"));
        c->mode = WASH;
        break;
      }
      c->mode = BADCODE;        // invalid code 
      z->msg = (char*)"invalid literal/length code";
      r = Z_DATA_ERROR;
      LEAVE
    case LENEXT:        // i: getting length extra (have base) 
      j = c->sub.copy.get;
      NEEDBITS(j)
      c->len += (uInt)b & inflate_mask[j];
      DUMPBITS(j)
      c->sub.code.need = c->dbits;
      c->sub.code.tree = c->dtree;
      Tracevv((stderr, "inflate:         length %u\n", c->len));
      c->mode = DIST;
    case DIST:          // i: get distance next 
      j = c->sub.code.need;
      NEEDBITS(j)
      t = c->sub.code.tree + ((uInt)b & inflate_mask[j]);
      DUMPBITS(t->bits)
      e = (uInt)(t->exop);
      if (e & 16)               // distance 
      {
        c->sub.copy.get = e & 15;
        c->sub.copy.dist = t->base;
        c->mode = DISTEXT;
        break;
      }
      if ((e & 64) == 0)        // next table 
      {
        c->sub.code.need = e;
        c->sub.code.tree = t + t->base;
        break;
      }
      c->mode = BADCODE;        // invalid code 
      z->msg = (char*)"invalid distance code";
      r = Z_DATA_ERROR;
      LEAVE
    case DISTEXT:       // i: getting distance extra 
      j = c->sub.copy.get;
      NEEDBITS(j)
      c->sub.copy.dist += (uInt)b & inflate_mask[j];
      DUMPBITS(j)
      Tracevv((stderr, "inflate:         distance %u\n", c->sub.copy.dist));
      c->mode = COPY;
    case COPY:          // o: copying bytes in window, waiting for space 
      f = (uInt)(q - s->window) < c->sub.copy.dist ?
          s->end - (c->sub.copy.dist - (q - s->window)) :
          q - c->sub.copy.dist;
      while (c->len)
      {
        NEEDOUT
        OUTBYTE(*f++)
        if (f == s->end)
          f = s->window;
        c->len--;
      }
      c->mode = START;
      break;
    case LIT:           // o: got literal, waiting for output space 
      NEEDOUT
      OUTBYTE(c->sub.lit)
      c->mode = START;
      break;
    case WASH:          // o: got eob, possibly more output 
      if (k > 7)        // return unused byte, if any 
      {
        Assert(k < 16, "inflate_codes grabbed too many bytes")
        k -= 8;
        n++;
        p--;            // can always return one 
      }
      FLUSH
      if (s->read != s->write)
        LEAVE
      c->mode = END;
    case END:
      r = Z_STREAM_END;
      LEAVE
    case BADCODE:       // x: got error
      r = Z_DATA_ERROR;
      LEAVE
    default:
      r = Z_STREAM_ERROR;
      LEAVE
  }
}


void inflate_codes_free(inflate_codes_statef *c,z_streamp z)
{ ZFREE(z, c);
  Tracev((stderr, "inflate:       codes free\n"));
}



// infblock.c -- interpret and process block types to last block
// Copyright (C) 1995-1998 Mark Adler
// For conditions of distribution and use, see copyright notice in zlib.h

//struct inflate_codes_state {int dummy;}; // for buggy compilers 



// Table for deflate from PKZIP's appnote.txt.
const uInt border[] = { // Order of the bit length code lengths
        16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15};

//
// Notes beyond the 1.93a appnote.txt:
//
// 1. Distance pointers never point before the beginning of the output stream.
// 2. Distance pointers can point back across blocks, up to 32k away.
// 3. There is an implied maximum of 7 bits for the bit length table and
//    15 bits for the actual data.
// 4. If only one code exists, then it is encoded using one bit.  (Zero
//    would be more efficient, but perhaps a little confusing.)  If two
//    codes exist, they are coded using one bit each (0 and 1).
// 5. There is no way of sending zero distance codes--a dummy must be
//    sent if there are none.  (History: a pre 2.0 version of PKZIP would
//    store blocks with no distance codes, but this was discovered to be
//    too harsh a criterion.)  Valid only for 1.93a.  2.04c does allow
//    zero distance codes, which is sent as one code of zero bits in
//    length.
// 6. There are up to 286 literal/length codes.  Code 256 represents the
//    end-of-block.  Note however that the static length tree defines
//    288 codes just to fill out the Huffman codes.  Codes 286 and 287
//    cannot be used though, since there is no length base or extra bits
//    defined for them.  Similarily, there are up to 30 distance codes.
//    However, static trees define 32 codes (all 5 bits) to fill out the
//    Huffman codes, but the last two had better not show up in the data.
// 7. Unzip can check dynamic Huffman blocks for complete code sets.
//    The exception is that a single code would not be complete (see #4).
// 8. The five bits following the block type is really the number of
//    literal codes sent minus 257.
// 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits
//    (1+6+6).  Therefore, to output three times the length, you output
//    three codes (1+1+1), whereas to output four times the same length,
//    you only need two codes (1+3).  Hmm.
//10. In the tree reconstruction algorithm, Code = Code + Increment
//    only if BitLength(i) is not zero.  (Pretty obvious.)
//11. Correction: 4 Bits: # of Bit Length codes - 4     (4 - 19)
//12. Note: length code 284 can represent 227-258, but length code 285
//    really is 258.  The last length deserves its own, short code
//    since it gets used a lot in very redundant files.  The length
//    258 is special since 258 - 3 (the min match length) is 255.
//13. The literal/length and distance code bit lengths are read as a
//    single stream of lengths.  It is possible (and advantageous) for
//    a repeat code (16, 17, or 18) to go across the boundary between
//    the two sets of lengths.


void inflate_blocks_reset(inflate_blocks_statef *s, z_streamp z, uLong *c)
{
  if (c != Z_NULL)
    *c = s->check;
  if (s->mode == IBM_BTREE || s->mode == IBM_DTREE)
    ZFREE(z, s->sub.trees.blens);
  if (s->mode == IBM_CODES)
    inflate_codes_free(s->sub.decode.codes, z);
  s->mode = IBM_TYPE;
  s->bitk = 0;
  s->bitb = 0;
  s->read = s->write = s->window;
  if (s->checkfn != Z_NULL)
    z->adler = s->check = (*s->checkfn)(0L, (const Byte *)Z_NULL, 0);
  Tracev((stderr, "inflate:   blocks reset\n"));
}


inflate_blocks_statef *inflate_blocks_new(z_streamp z, check_func c, uInt w)
{
  inflate_blocks_statef *s;

  if ((s = (inflate_blocks_statef *)ZALLOC
       (z,1,sizeof(struct inflate_blocks_state))) == Z_NULL)