#define DEBG(x)
#define DEBG1(x)
/* inflate.c -- Not copyrighted 1992 by Mark Adler
   version c10p1, 10 January 1993 */

/* 
 * Adapted for booting Linux by Hannu Savolainen 1993
 * based on gzip-1.0.3 
 *
 * Nicolas Pitre <nico@cam.org>, 1999/04/14 :
 *   Little mods for all variable to reside either into rodata or bss segments
 *   by marking constant variables with 'const' and initializing all the others
 *   at run-time only.  This allows for the kernel uncompressor to run
 *   directly from Flash or ROM memory on embedded systems.
 */

/*
   Inflate deflated (PKZIP's method 8 compressed) data.  The compression
   method searches for as much of the current string of bytes (up to a
   length of 258) in the previous 32 K bytes.  If it doesn't find any
   matches (of at least length 3), it codes the next byte.  Otherwise, it
   codes the length of the matched string and its distance backwards from
   the current position.  There is a single Huffman code that codes both
   single bytes (called "literals") and match lengths.  A second Huffman
   code codes the distance information, which follows a length code.  Each
   length or distance code actually represents a base value and a number
   of "extra" (sometimes zero) bits to get to add to the base value.  At
   the end of each deflated block is a special end-of-block (EOB) literal/
   length code.  The decoding process is basically: get a literal/length
   code; if EOB then done; if a literal, emit the decoded byte; if a
   length then get the distance and emit the referred-to bytes from the
   sliding window of previously emitted data.

   There are (currently) three kinds of inflate blocks: stored, fixed, and
   dynamic.  The compressor deals with some chunk of data at a time, and
   decides which method to use on a chunk-by-chunk basis.  A chunk might
   typically be 32 K or 64 K.  If the chunk is incompressible, then the
   "stored" method is used.  In this case, the bytes are simply stored as
   is, eight bits per byte, with none of the above coding.  The bytes are
   preceded by a count, since there is no longer an EOB code.

   If the data is compressible, then either the fixed or dynamic methods
   are used.  In the dynamic method, the compressed data is preceded by
   an encoding of the literal/length and distance Huffman codes that are
   to be used to decode this block.  The representation is itself Huffman
   coded, and so is preceded by a description of that code.  These code
   descriptions take up a little space, and so for small blocks, there is
   a predefined set of codes, called the fixed codes.  The fixed method is
   used if the block codes up smaller that way (usually for quite small
   chunks), otherwise the dynamic method is used.  In the latter case, the
   codes are customized to the probabilities in the current block, and so
   can code it much better than the pre-determined fixed codes.
 
   The Huffman codes themselves are decoded using a multi-level table
   lookup, in order to maximize the speed of decoding plus the speed of
   building the decoding tables.  See the comments below that precede the
   lbits and dbits tuning parameters.
 */


/*
   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.  Similarly, 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.
 */

#ifdef RCSID
static char rcsid[] = "#Id: inflate.c,v 0.14 1993/06/10 13:27:04 jloup Exp #";
#endif

#ifndef STATIC

#if defined(STDC_HEADERS) || defined(HAVE_STDLIB_H)
#  include <sys/types.h>
#  include <stdlib.h>
#endif

#include "gzip.h"
#define STATIC
#endif /* !STATIC */
	
#define slide window

/* Huffman code lookup table entry--this entry is four bytes for machines
   that have 16-bit pointers (e.g. PC's in the small or medium model).
   Valid extra bits are 0..13.  e == 15 is EOB (end of block), e == 16
   means that v is a literal, 16 < e < 32 means that v is a pointer to
   the next table, which codes e - 16 bits, and lastly e == 99 indicates
   an unused code.  If a code with e == 99 is looked up, this implies an
   error in the data. */
struct huft {
  uch e;                /* number of extra bits or operation */
  uch b;                /* number of bits in this code or subcode */
  union {
    ush n;              /* literal, length base, or distance base */
    struct huft *t;     /* pointer to next level of table */
  } v;
};


/* Function prototypes */
STATIC int huft_build OF((unsigned *, unsigned, unsigned, 
		const ush *, const ush *, struct huft **, int *));
STATIC int huft_free OF((struct huft *));
STATIC int inflate_codes OF((struct huft *, struct huft *, int, int));
STATIC int inflate_stored OF((void));
STATIC int inflate_fixed OF((void));
STATIC int inflate_dynamic OF((void));
STATIC int inflate_block OF((int *));
STATIC int inflate OF((void));


/* The inflate algorithm uses a sliding 32 K byte window on the uncompressed
   stream to find repeated byte strings.  This is implemented here as a
   circular buffer.  The index is updated simply by incrementing and then
   ANDing with 0x7fff (32K-1). */
/* It is left to other modules to supply the 32 K area.  It is assumed
   to be usable as if it were declared "uch slide[32768];" or as just
   "uch *slide;" and then malloc'ed in the latter case.  The definition
   must be in unzip.h, included above. */
/* unsigned wp;             current position in slide */
#define wp outcnt
#define flush_output(w) (wp=(w),flush_window())

/* Tables for deflate from PKZIP's appnote.txt. */
static const unsigned 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};
static const ush cplens[] = {         /* Copy lengths for literal codes 257..285 */
        3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
        35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
        /* note: see note #13 above about the 258 in this list. */
static const ush cplext[] = {         /* Extra bits for literal codes 257..285 */
        0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2,
        3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */
static const ush cpdist[] = {         /* Copy offsets for distance codes 0..29 */
        1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
        257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
        8193, 12289, 16385, 24577};
static const ush cpdext[] = {         /* Extra bits for distance codes */
        0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6,
        7, 7, 8, 8, 9, 9, 10, 10, 11, 11,
        12, 12, 13, 13};



/* Macros for inflate() bit peeking and grabbing.
   The usage is:
   
        NEEDBITS(j)
        x = b & mask_bits[j];
        DUMPBITS(j)

   where NEEDBITS makes sure that b has at least j bits in it, and
   DUMPBITS removes the bits from b.  The macros use the variable k
   for the number of bits in b.  Normally, b and k are register
   variables for speed, and are initialized at the beginning of a
   routine that uses these macros from a global bit buffer and count.

   If we assume that EOB will be the longest code, then we will never
   ask for bits with NEEDBITS that are beyond the end of the stream.
   So, NEEDBITS should not read any more bytes than are needed to
   meet the request.  Then no bytes need to be "returned" to the buffer
   at the end of the last block.

   However, this assumption is not true for fixed blocks--the EOB code
   is 7 bits, but the other literal/length codes can be 8 or 9 bits.
   (The EOB code is shorter than other codes because fixed blocks are
   generally short.  So, while a block always has an EOB, many other
   literal/length codes have a significantly lower probability of
   showing up at all.)  However, by making the first table have a
   lookup of seven bits, the EOB code will be found in that first
   lookup, and so will not require that too many bits be pulled from
   the stream.
 */

STATIC ulg bb;                         /* bit buffer */
STATIC unsigned bk;                    /* bits in bit buffer */

STATIC const ush mask_bits[] = {
    0x0000,
    0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff,
    0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff
};

#define NEXTBYTE()  (uch)get_byte()
#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}}
#define DUMPBITS(n) {b>>=(n);k-=(n);}


/*
   Huffman code decoding is performed using a multi-level table lookup.
   The fastest way to decode is to simply build a lookup table whose
   size is determined by the longest code.  However, the time it takes
   to build this table can also be a factor if the data being decoded
   is not very long.  The most common codes are necessarily the
   shortest codes, so those codes dominate the decoding time, and hence
   the speed.  The idea is you can have a shorter table that decodes the
   shorter, more probable codes, and then point to subsidiary tables for
   the longer codes.  The time it costs to decode the longer codes is
   then traded against the time it takes to make longer tables.

   This results of this trade are in the variables lbits and dbits
   below.  lbits is the number of bits the first level table for literal/
   length codes can decode in one step, and dbits is the same thing for
   the distance codes.  Subsequent tables are also less than or equal to
   those sizes.  These values may be adjusted either when all of the
   codes are shorter than that, in which case the longest code length in
   bits is used, or when the shortest code is *longer* than the requested
   table size, in which case the length of the shortest code in bits is
   used.

   There are two different values for the two tables, since they code a
   different number of possibilities each.  The literal/length table
   codes 286 possible values, or in a flat code, a little over eight
   bits.  The distance table codes 30 possible values, or a little less
   than five bits, flat.  The optimum values for speed end up being
   about one bit more than those, so lbits is 8+1 and dbits is 5+1.
   The optimum values may differ though from machine to machine, and
   possibly even between compilers.  Your mileage may vary.
 */


STATIC const int lbits = 9;          /* bits in base literal/length lookup table */
STATIC const int dbits = 6;          /* bits in base distance lookup table */


/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */
#define BMAX 16         /* maximum bit length of any code (16 for explode) */
#define N_MAX 288       /* maximum number of codes in any set */


STATIC unsigned hufts;         /* track memory usage */


STATIC int huft_build(b, n, s, d, e, t, m)
unsigned *b;            /* code lengths in bits (all assumed <= BMAX) */
unsigned n;             /* number of codes (assumed <= N_MAX) */
unsigned s;             /* number of simple-valued codes (0..s-1) */
const ush *d;                 /* list of base values for non-simple codes */
const ush *e;                 /* list of extra bits for non-simple codes */
struct huft **t;        /* result: starting table */
int *m;                 /* maximum lookup bits, returns actual */
/* Given a list of code lengths and a maximum table size, make a set of
   tables to decode that set of codes.  Return zero on success, one if
   the given code set is incomplete (the tables are still built in this
   case), two if the input is invalid (all zero length codes or an
   oversubscribed set of lengths), and three if not enough memory. */
{
  unsigned a;                   /* counter for codes of length k */
  unsigned c[BMAX+1];           /* bit length count table */
  unsigned f;                   /* i repeats in table every f entries */
  int g;                        /* maximum code length */
  int h;                        /* table level */
  register unsigned i;          /* counter, current code */
  register unsigned j;          /* counter */
  register int k;               /* number of bits in current code */
  int l;                        /* bits per table (returned in m) */
  register unsigned *p;         /* pointer into c[], b[], or v[] */
  register struct huft *q;      /* points to current table */
  struct huft r;                /* table entry for structure assignment */
  struct huft *u[BMAX];         /* table stack */
  unsigned v[N_MAX];            /* values in order of bit length */
  register int w;               /* bits before this table == (l * h) */
  unsigned x[BMAX+1];           /* bit offsets, then code stack */
  unsigned *xp;                 /* pointer into x */
  int y;                        /* number of dummy codes added */
  unsigned z;                   /* number of entries in current table */

DEBG("huft1 ");

  /* Generate counts for each bit length */
  memzero(c, sizeof(c));
  p = b;  i = n;
  do {
    Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), 
	    n-i, *p));
    c[*p]++;                    /* assume all entries <= BMAX */
    p++;                      /* Can't combine with above line (Solaris bug) */
  } while (--i);
  if (c[0] == n)                /* null input--all zero length codes */
  {
    *t = (struct huft *)NULL;
    *m = 0;
    return 0;
  }

DEBG("huft2 ");

  /* Find minimum and maximum length, bound *m by those */
  l = *m;
  for (j = 1; j <= BMAX; j++)
    if (c[j])
      break;
  k = j;                        /* minimum code length */
  if ((unsigned)l < j)
    l = j;
  for (i = BMAX; i; i--)
    if (c[i])
      break;
  g = i;                        /* maximum code length */
  if ((unsigned)l > i)
    l = i;
  *m = l;

DEBG("huft3 ");

  /* Adjust last length count to fill out codes, if needed */
  for (y = 1 << j; j < i; j++, y <<= 1)
    if ((y -= c[j]) < 0)
      return 2;                 /* bad input: more codes than bits */
  if ((y -= c[i]) < 0)
    return 2;
  c[i] += y;

DEBG("huft4 ");

  /* Generate starting offsets into the value table for each length */
  x[1] = j = 0;
  p = c + 1;  xp = x + 2;
  while (--i) {                 /* note that i == g from above */
    *xp++ = (j += *p++);
  }

DEBG("huft5 ");

  /* Make a table of values in order of bit lengths */
  p = b;  i = 0;
  do {
    if ((j = *p++) != 0)
      v[x[j]++] = i;
  } while (++i < n);

DEBG("h6 ");

  /* Generate the Huffman codes and for each, make the table entries */
  x[0] = i = 0;                 /* first Huffman code is zero */
  p = v;                        /* grab values in bit order */
  h = -1;                       /* no tables yet--level -1 */
  w = -l;                       /* bits decoded == (l * h) */
  u[0] = (struct huft *)NULL;   /* just to keep compilers happy */
  q = (struct huft *)NULL;      /* ditto */
  z = 0;                        /* ditto */
DEBG("h6a ");

  /* go through the bit lengths (k already is bits in shortest code) */
  for (; k <= g; k++)
  {
DEBG("h6b ");
    a = c[k];
    while (a--)
    {
DEBG("h6b1 ");
      /* here i is the Huffman code of length k bits for value *p */
      /* make tables up to required level */