beg = s->pending;
                    if (s->pending == s->pending_buf_size) {
                        val = 1;
                        break;
                    }
                }
                val = s->gzhead->name[s->gzindex++];
                put_byte(s, val);
            } while (val != 0);
            if (s->gzhead->hcrc && s->pending > beg)
                strm->adler = crc32(strm->adler, s->pending_buf + beg,
                                    s->pending - beg);
            if (val == 0) {
                s->gzindex = 0;
                s->status = COMMENT_STATE;
            }
        }
        else
            s->status = COMMENT_STATE;
    }
    if (s->status == COMMENT_STATE) {
        if (s->gzhead->comment != NULL) {
            uInt beg = s->pending;  /* start of bytes to update crc */
            int val;

            do {
                if (s->pending == s->pending_buf_size) {
                    if (s->gzhead->hcrc && s->pending > beg)
                        strm->adler = crc32(strm->adler, s->pending_buf + beg,
                                            s->pending - beg);
                    flush_pending(strm);
                    beg = s->pending;
                    if (s->pending == s->pending_buf_size) {
                        val = 1;
                        break;
                    }
                }
                val = s->gzhead->comment[s->gzindex++];
                put_byte(s, val);
            } while (val != 0);
            if (s->gzhead->hcrc && s->pending > beg)
                strm->adler = crc32(strm->adler, s->pending_buf + beg,
                                    s->pending - beg);
            if (val == 0)
                s->status = HCRC_STATE;
        }
        else
            s->status = HCRC_STATE;
    }
    if (s->status == HCRC_STATE) {
        if (s->gzhead->hcrc) {
            if (s->pending + 2 > s->pending_buf_size)
                flush_pending(strm);
            if (s->pending + 2 <= s->pending_buf_size) {
                put_byte(s, (Byte)(strm->adler & 0xff));
                put_byte(s, (Byte)((strm->adler >> 8) & 0xff));
                strm->adler = crc32(0L, Z_NULL, 0);
                s->status = BUSY_STATE;
            }
        }
        else
            s->status = BUSY_STATE;
    }
#endif

    /* Flush as much pending output as possible */
    if (s->pending != 0) {
        flush_pending(strm);
        if (strm->avail_out == 0) {
            /* Since avail_out is 0, deflate will be called again with
             * more output space, but possibly with both pending and
             * avail_in equal to zero. There won't be anything to do,
             * but this is not an error situation so make sure we
             * return OK instead of BUF_ERROR at next call of deflate:
             */
            s->last_flush = -1;
            return Z_OK;
        }

    /* Make sure there is something to do and avoid duplicate consecutive
     * flushes. For repeated and useless calls with Z_FINISH, we keep
     * returning Z_STREAM_END instead of Z_BUF_ERROR.
     */
    } else if (strm->avail_in == 0 && flush <= old_flush &&
               flush != Z_FINISH) {
        ERR_RETURN(strm, Z_BUF_ERROR);
    }

    /* User must not provide more input after the first FINISH: */
    if (s->status == FINISH_STATE && strm->avail_in != 0) {
        ERR_RETURN(strm, Z_BUF_ERROR);
    }

    /* Start a new block or continue the current one.
     */
    if (strm->avail_in != 0 || s->lookahead != 0 ||
        (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) {
        block_state bstate;

        bstate = (*(configuration_table[s->level].func))(s, flush);

        if (bstate == finish_started || bstate == finish_done) {
            s->status = FINISH_STATE;
        }
        if (bstate == need_more || bstate == finish_started) {
            if (strm->avail_out == 0) {
                s->last_flush = -1; /* avoid BUF_ERROR next call, see above */
            }
            return Z_OK;
            /* If flush != Z_NO_FLUSH && avail_out == 0, the next call
             * of deflate should use the same flush parameter to make sure
             * that the flush is complete. So we don't have to output an
             * empty block here, this will be done at next call. This also
             * ensures that for a very small output buffer, we emit at most
             * one empty block.
             */
        }
        if (bstate == block_done) {
            if (flush == Z_PARTIAL_FLUSH) {
                _tr_align(s);
            } else { /* FULL_FLUSH or SYNC_FLUSH */
                _tr_stored_block(s, (char*)0, 0L, 0);
                /* For a full flush, this empty block will be recognized
                 * as a special marker by inflate_sync().
                 */
                if (flush == Z_FULL_FLUSH) {
                    CLEAR_HASH(s);             /* forget history */
                }
            }
            flush_pending(strm);
            if (strm->avail_out == 0) {
              s->last_flush = -1; /* avoid BUF_ERROR at next call, see above */
              return Z_OK;
            }
        }
    }
    Assert(strm->avail_out > 0, "bug2");

    if (flush != Z_FINISH) return Z_OK;
    if (s->wrap <= 0) return Z_STREAM_END;

    /* Write the trailer */
#ifdef GZIP
    if (s->wrap == 2) {
        put_byte(s, (Byte)(strm->adler & 0xff));
        put_byte(s, (Byte)((strm->adler >> 8) & 0xff));
        put_byte(s, (Byte)((strm->adler >> 16) & 0xff));
        put_byte(s, (Byte)((strm->adler >> 24) & 0xff));
        put_byte(s, (Byte)(strm->total_in & 0xff));
        put_byte(s, (Byte)((strm->total_in >> 8) & 0xff));
        put_byte(s, (Byte)((strm->total_in >> 16) & 0xff));
        put_byte(s, (Byte)((strm->total_in >> 24) & 0xff));
    }
    else
#endif
    {
        putShortMSB(s, (uInt)(strm->adler >> 16));
        putShortMSB(s, (uInt)(strm->adler & 0xffff));
    }
    flush_pending(strm);
    /* If avail_out is zero, the application will call deflate again
     * to flush the rest.
     */
    if (s->wrap > 0) s->wrap = -s->wrap; /* write the trailer only once! */
    return s->pending != 0 ? Z_OK : Z_STREAM_END;
}

/* ========================================================================= */
int ZEXPORT deflateEnd (strm)
    z_streamp strm;
{
    int status;

    if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR;

    status = strm->state->status;
    if (status != INIT_STATE &&
        status != EXTRA_STATE &&
        status != NAME_STATE &&
        status != COMMENT_STATE &&
        status != HCRC_STATE &&
        status != BUSY_STATE &&
        status != FINISH_STATE) {
      return Z_STREAM_ERROR;
    }

    /* Deallocate in reverse order of allocations: */
    TRY_FREE(strm, strm->state->pending_buf);
    TRY_FREE(strm, strm->state->head);
    TRY_FREE(strm, strm->state->prev);
    TRY_FREE(strm, strm->state->window);

    ZFREE(strm, strm->state);
    strm->state = Z_NULL;

    return status == BUSY_STATE ? Z_DATA_ERROR : Z_OK;
}

/* =========================================================================
 * Copy the source state to the destination state.
 * To simplify the source, this is not supported for 16-bit MSDOS (which
 * doesn't have enough memory anyway to duplicate compression states).
 */
int ZEXPORT deflateCopy (dest, source)
    z_streamp dest;
    z_streamp source;
{
#ifdef MAXSEG_64K
    return Z_STREAM_ERROR;
#else
    deflate_state *ds;
    deflate_state *ss;
    ushf *overlay;


    if (source == Z_NULL || dest == Z_NULL || source->state == Z_NULL) {
        return Z_STREAM_ERROR;
    }

    ss = source->state;

    zmemcpy(dest, source, sizeof(z_stream));

    ds = (deflate_state *) ZALLOC(dest, 1, sizeof(deflate_state));
    if (ds == Z_NULL) return Z_MEM_ERROR;
    dest->state = (struct internal_state FAR *) ds;
    zmemcpy(ds, ss, sizeof(deflate_state));
    ds->strm = dest;

    ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte));
    ds->prev   = (Posf *)  ZALLOC(dest, ds->w_size, sizeof(Pos));
    ds->head   = (Posf *)  ZALLOC(dest, ds->hash_size, sizeof(Pos));
    overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2);
    ds->pending_buf = (uchf *) overlay;

    if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL ||
        ds->pending_buf == Z_NULL) {
        deflateEnd (dest);
        return Z_MEM_ERROR;
    }
    /* following zmemcpy do not work for 16-bit MSDOS */
    zmemcpy(ds->window, ss->window, ds->w_size * 2 * sizeof(Byte));
    zmemcpy(ds->prev, ss->prev, ds->w_size * sizeof(Pos));
    zmemcpy(ds->head, ss->head, ds->hash_size * sizeof(Pos));
    zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size);

    ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf);
    ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush);
    ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize;

    ds->l_desc.dyn_tree = ds->dyn_ltree;
    ds->d_desc.dyn_tree = ds->dyn_dtree;
    ds->bl_desc.dyn_tree = ds->bl_tree;

    return Z_OK;
#endif /* MAXSEG_64K */
}

/* ===========================================================================
 * Read a new buffer from the current input stream, update the adler32
 * and total number of bytes read.  All deflate() input goes through
 * this function so some applications may wish to modify it to avoid
 * allocating a large strm->next_in buffer and copying from it.
 * (See also flush_pending()).
 */
local int read_buf(strm, buf, size)
    z_streamp strm;
    Bytef *buf;
    unsigned size;
{
    unsigned len = strm->avail_in;

    if (len > size) len = size;
    if (len == 0) return 0;

    strm->avail_in  -= len;

    if (strm->state->wrap == 1) {
        strm->adler = adler32(strm->adler, strm->next_in, len);
    }
#ifdef GZIP
    else if (strm->state->wrap == 2) {
        strm->adler = crc32(strm->adler, strm->next_in, len);
    }
#endif
    zmemcpy(buf, strm->next_in, len);
    strm->next_in  += len;
    strm->total_in += len;

    return (int)len;
}

/* ===========================================================================
 * Initialize the "longest match" routines for a new zlib stream
 */
local void lm_init (s)
    deflate_state *s;
{
    s->window_size = (ulg)2L*s->w_size;

    CLEAR_HASH(s);

    /* Set the default configuration parameters:
     */
    s->max_lazy_match   = configuration_table[s->level].max_lazy;
    s->good_match       = configuration_table[s->level].good_length;
    s->nice_match       = configuration_table[s->level].nice_length;
    s->max_chain_length = configuration_table[s->level].max_chain;

    s->strstart = 0;
    s->block_start = 0L;
    s->lookahead = 0;
    s->match_length = s->prev_length = MIN_MATCH-1;
    s->match_available = 0;
    s->ins_h = 0;
#ifndef FASTEST
#ifdef ASMV
    match_init(); /* initialize the asm code */
#endif
#endif
}

#ifndef FASTEST
/* ===========================================================================
 * Set match_start to the longest match starting at the given string and
 * return its length. Matches shorter or equal to prev_length are discarded,
 * in which case the result is equal to prev_length and match_start is
 * garbage.
 * IN assertions: cur_match is the head of the hash chain for the current
 *   string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1
 * OUT assertion: the match length is not greater than s->lookahead.
 */
#ifndef ASMV
/* For 80x86 and 680x0, an optimized version will be provided in match.asm or
 * match.S. The code will be functionally equivalent.
 */
local uInt longest_match(s, cur_match)
    deflate_state *s;
    IPos cur_match;                             /* current match */
{
    unsigned chain_length = s->max_chain_length;/* max hash chain length */
    register Bytef *scan = s->window + s->strstart; /* current string */
    register Bytef *match;                       /* matched string */
    register int len;                           /* length of current match */
    int best_len = s->prev_length;              /* best match length so far */