/*
 * jdshuff.c
 *
 * This file was part of the Independent JPEG Group's software:
 * Copyright (C) 1991-1998, Thomas G. Lane.
 * Lossless JPEG Modifications:
 * Copyright (C) 1999, Ken Murchison.
 * For conditions of distribution and use, see the accompanying README file.
 *
 * This file contains Huffman entropy decoding routines for sequential JPEG.
 *
 * Much of the complexity here has to do with supporting input suspension.
 * If the data source module demands suspension, we want to be able to back
 * up to the start of the current MCU.  To do this, we copy state variables
 * into local working storage, and update them back to the permanent
 * storage only upon successful completion of an MCU.
 */

#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jlossy.h"		/* Private declarations for lossy codec */
#include "jdhuff.h"		/* Declarations shared with jd*huff.c */


/*
 * Private entropy decoder object for Huffman decoding.
 *
 * The savable_state subrecord contains fields that change within an MCU,
 * but must not be updated permanently until we complete the MCU.
 */

typedef struct {
  int last_dc_val[MAX_COMPS_IN_SCAN]; /* last DC coef for each component */
} savable_state;

/* This macro is to work around compilers with missing or broken
 * structure assignment.  You'll need to fix this code if you have
 * such a compiler and you change MAX_COMPS_IN_SCAN.
 */

#ifndef NO_STRUCT_ASSIGN
#define ASSIGN_STATE(dest,src)  ((dest) = (src))
#else
#if MAX_COMPS_IN_SCAN == 4
#define ASSIGN_STATE(dest,src)  \
	((dest).last_dc_val[0] = (src).last_dc_val[0], \
	 (dest).last_dc_val[1] = (src).last_dc_val[1], \
	 (dest).last_dc_val[2] = (src).last_dc_val[2], \
	 (dest).last_dc_val[3] = (src).last_dc_val[3])
#endif
#endif


typedef struct {
  huffd_common_fields;		/* Fields shared with other entropy decoders */

  /* These fields are loaded into local variables at start of each MCU.
   * In case of suspension, we exit WITHOUT updating them.
   */
  savable_state saved;		/* Other state at start of MCU */

  /* These fields are NOT loaded into local working state. */
  unsigned int restarts_to_go;	/* MCUs left in this restart interval */

  /* Pointers to derived tables (these workspaces have image lifespan) */
  d_derived_tbl * dc_derived_tbls[NUM_HUFF_TBLS];
  d_derived_tbl * ac_derived_tbls[NUM_HUFF_TBLS];

  /* Precalculated info set up by start_pass for use in decode_mcu: */

  /* Pointers to derived tables to be used for each block within an MCU */
  d_derived_tbl * dc_cur_tbls[D_MAX_DATA_UNITS_IN_MCU];
  d_derived_tbl * ac_cur_tbls[D_MAX_DATA_UNITS_IN_MCU];
  /* Whether we care about the DC and AC coefficient values for each block */
  boolean dc_needed[D_MAX_DATA_UNITS_IN_MCU];
  boolean ac_needed[D_MAX_DATA_UNITS_IN_MCU];
} shuff_entropy_decoder;

typedef shuff_entropy_decoder * shuff_entropy_ptr;


/*
 * Initialize for a Huffman-compressed scan.
 */

METHODDEF(void)
start_pass_huff_decoder (j_decompress_ptr cinfo)
{
  j_lossy_d_ptr lossyd = (j_lossy_d_ptr) cinfo->codec;
  shuff_entropy_ptr entropy = (shuff_entropy_ptr) lossyd->entropy_private;
  int ci, blkn, dctbl, actbl;
  jpeg_component_info * compptr;

  /* Check that the scan parameters Ss, Se, Ah/Al are OK for sequential JPEG.
   * This ought to be an error condition, but we make it a warning because
   * there are some baseline files out there with all zeroes in these bytes.
   */
  if (cinfo->Ss != 0 || cinfo->Se != DCTSIZE2-1 ||
      cinfo->Ah != 0 || cinfo->Al != 0)
    WARNMS(cinfo, JWRN_NOT_SEQUENTIAL);

  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    compptr = cinfo->cur_comp_info[ci];
    dctbl = compptr->dc_tbl_no;
    actbl = compptr->ac_tbl_no;
    /* Compute derived values for Huffman tables */
    /* We may do this more than once for a table, but it's not expensive */
    jpeg_make_d_derived_tbl(cinfo, TRUE, dctbl,
			    & entropy->dc_derived_tbls[dctbl]);
    jpeg_make_d_derived_tbl(cinfo, FALSE, actbl,
			    & entropy->ac_derived_tbls[actbl]);
    /* Initialize DC predictions to 0 */
    entropy->saved.last_dc_val[ci] = 0;
  }

  /* Precalculate decoding info for each block in an MCU of this scan */
  for (blkn = 0; blkn < cinfo->data_units_in_MCU; blkn++) {
    ci = cinfo->MCU_membership[blkn];
    compptr = cinfo->cur_comp_info[ci];
    /* Precalculate which table to use for each block */
    entropy->dc_cur_tbls[blkn] = entropy->dc_derived_tbls[compptr->dc_tbl_no];
    entropy->ac_cur_tbls[blkn] = entropy->ac_derived_tbls[compptr->ac_tbl_no];
    /* Decide whether we really care about the coefficient values */
    if (compptr->component_needed) {
      entropy->dc_needed[blkn] = TRUE;
      /* we don't need the ACs if producing a 1/8th-size image */
      entropy->ac_needed[blkn] = (compptr->codec_data_unit > 1);
    } else {
      entropy->dc_needed[blkn] = entropy->ac_needed[blkn] = FALSE;
    }
  }

  /* Initialize bitread state variables */
  entropy->bitstate.bits_left = 0;
  entropy->bitstate.get_buffer = 0; /* unnecessary, but keeps Purify quiet */
  entropy->insufficient_data = FALSE;

  /* Initialize restart counter */
  entropy->restarts_to_go = cinfo->restart_interval;
}


/*
 * Figure F.12: extend sign bit.
 * On some machines, a shift and add will be faster than a table lookup.
 */

#ifdef AVOID_TABLES

#define HUFF_EXTEND(x,s)  ((x) < (1<<((s)-1)) ? (x) + (((-1)<<(s)) + 1) : (x))

#else

#define HUFF_EXTEND(x,s)  ((x) < extend_test[s] ? (x) + extend_offset[s] : (x))

static const int extend_test[16] =   /* entry n is 2**(n-1) */
  { 0, 0x0001, 0x0002, 0x0004, 0x0008, 0x0010, 0x0020, 0x0040, 0x0080,
    0x0100, 0x0200, 0x0400, 0x0800, 0x1000, 0x2000, 0x4000 };

static const int extend_offset[16] = /* entry n is (-1 << n) + 1 */
  { 0, ((-1)<<1) + 1, ((-1)<<2) + 1, ((-1)<<3) + 1, ((-1)<<4) + 1,
    ((-1)<<5) + 1, ((-1)<<6) + 1, ((-1)<<7) + 1, ((-1)<<8) + 1,
    ((-1)<<9) + 1, ((-1)<<10) + 1, ((-1)<<11) + 1, ((-1)<<12) + 1,
    ((-1)<<13) + 1, ((-1)<<14) + 1, ((-1)<<15) + 1 };

#endif /* AVOID_TABLES */


/*
 * Check for a restart marker & resynchronize decoder.
 * Returns FALSE if must suspend.
 */

LOCAL(boolean)
process_restart (j_decompress_ptr cinfo)
{
  j_lossy_d_ptr lossyd = (j_lossy_d_ptr) cinfo->codec;
  shuff_entropy_ptr entropy = (shuff_entropy_ptr) lossyd->entropy_private;
  int ci;

  /* Throw away any unused bits remaining in bit buffer; */
  /* include any full bytes in next_marker's count of discarded bytes */
  cinfo->marker->discarded_bytes += entropy->bitstate.bits_left / 8;
  entropy->bitstate.bits_left = 0;

  /* Advance past the RSTn marker */
  if (! (*cinfo->marker->read_restart_marker) (cinfo))
    return FALSE;

  /* Re-initialize DC predictions to 0 */
  for (ci = 0; ci < cinfo->comps_in_scan; ci++)
    entropy->saved.last_dc_val[ci] = 0;

  /* Reset restart counter */
  entropy->restarts_to_go = cinfo->restart_interval;

  /* Reset out-of-data flag, unless read_restart_marker left us smack up
   * against a marker.  In that case we will end up treating the next data
   * segment as empty, and we can avoid producing bogus output pixels by
   * leaving the flag set.
   */
  if (cinfo->unread_marker == 0)
    entropy->insufficient_data = FALSE;

  return TRUE;
}


/*
 * Decode and return one MCU's worth of Huffman-compressed coefficients.
 * The coefficients are reordered from zigzag order into natural array order,
 * but are not dequantized.
 *
 * The i'th block of the MCU is stored into the block pointed to by
 * MCU_data[i].  WE ASSUME THIS AREA HAS BEEN ZEROED BY THE CALLER.
 * (Wholesale zeroing is usually a little faster than retail...)
 *
 * Returns FALSE if data source requested suspension.  In that case no
 * changes have been made to permanent state.  (Exception: some output
 * coefficients may already have been assigned.  This is harmless for
 * this module, since we'll just re-assign them on the next call.)
 */

METHODDEF(boolean)
decode_mcu (j_decompress_ptr cinfo, JBLOCKROW *MCU_data)
{
  j_lossy_d_ptr lossyd = (j_lossy_d_ptr) cinfo->codec;
  shuff_entropy_ptr entropy = (shuff_entropy_ptr) lossyd->entropy_private;
  int blkn;
  BITREAD_STATE_VARS;
  savable_state state;

  /* Process restart marker if needed; may have to suspend */
  if (cinfo->restart_interval) {
    if (entropy->restarts_to_go == 0)
      if (! process_restart(cinfo))
	return FALSE;
  }

  /* If we've run out of data, just leave the MCU set to zeroes.
   * This way, we return uniform gray for the remainder of the segment.
   */
  if (! entropy->insufficient_data) {

    /* Load up working state */
    BITREAD_LOAD_STATE(cinfo,entropy->bitstate);
    ASSIGN_STATE(state, entropy->saved);

    /* Outer loop handles each block in the MCU */

    for (blkn = 0; blkn < cinfo->data_units_in_MCU; blkn++) {
      JBLOCKROW block = MCU_data[blkn];
      d_derived_tbl * dctbl = entropy->dc_cur_tbls[blkn];
      d_derived_tbl * actbl = entropy->ac_cur_tbls[blkn];
      register int s, k, r;

      /* Decode a single block's worth of coefficients */

      /* Section F.2.2.1: decode the DC coefficient difference */
      HUFF_DECODE(s, br_state, dctbl, return FALSE, label1);
      if (s) {
	CHECK_BIT_BUFFER(br_state, s, return FALSE);
	r = GET_BITS(s);
	s = HUFF_EXTEND(r, s);
      }

      if (entropy->dc_needed[blkn]) {
	/* Convert DC difference to actual value, update last_dc_val */
	int ci = cinfo->MCU_membership[blkn];
	s += state.last_dc_val[ci];
	state.last_dc_val[ci] = s;
	/* Output the DC coefficient (assumes jpeg_natural_order[0] = 0) */
	(*block)[0] = (JCOEF) s;
      }

      if (entropy->ac_needed[blkn]) {

	/* Section F.2.2.2: decode the AC coefficients */
	/* Since zeroes are skipped, output area must be cleared beforehand */
	for (k = 1; k < DCTSIZE2; k++) {
	  HUFF_DECODE(s, br_state, actbl, return FALSE, label2);
      
	  r = s >> 4;
	  s &= 15;
      
	  if (s) {
	    k += r;
	    CHECK_BIT_BUFFER(br_state, s, return FALSE);
	    r = GET_BITS(s);
	    s = HUFF_EXTEND(r, s);
	    /* Output coefficient in natural (dezigzagged) order.
	     * Note: the extra entries in jpeg_natural_order[] will save us
	     * if k >= DCTSIZE2, which could happen if the data is corrupted.
	     */
	    (*block)[jpeg_natural_order[k]] = (JCOEF) s;
	  } else {
	    if (r != 15)
	      break;
	    k += 15;
	  }
	}

      } else {

	/* Section F.2.2.2: decode the AC coefficients */
	/* In this path we just discard the values */
	for (k = 1; k < DCTSIZE2; k++) {
	  HUFF_DECODE(s, br_state, actbl, return FALSE, label3);
      
	  r = s >> 4;
	  s &= 15;
      
	  if (s) {
	    k += r;
	    CHECK_BIT_BUFFER(br_state, s, return FALSE);
	    DROP_BITS(s);
	  } else {
	    if (r != 15)
	      break;
	    k += 15;
	  }
	}

      }
    }

    /* Completed MCU, so update state */
    BITREAD_SAVE_STATE(cinfo,entropy->bitstate);
    ASSIGN_STATE(entropy->saved, state);
  }

  /* Account for restart interval (no-op if not using restarts) */
  entropy->restarts_to_go--;

  return TRUE;
}


/*
 * Module initialization routine for Huffman entropy decoding.
 */

GLOBAL(void)
jinit_shuff_decoder (j_decompress_ptr cinfo)
{
  j_lossy_d_ptr lossyd = (j_lossy_d_ptr) cinfo->codec;
  shuff_entropy_ptr entropy;
  int i;

  entropy = (shuff_entropy_ptr)
    (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
				SIZEOF(shuff_entropy_decoder));
  lossyd->entropy_private = (void *) entropy;
  lossyd->entropy_start_pass = start_pass_huff_decoder;
  lossyd->entropy_decode_mcu = decode_mcu;

  /* Mark tables unallocated */
  for (i = 0; i < NUM_HUFF_TBLS; i++) {
    entropy->dc_derived_tbls[i] = entropy->ac_derived_tbls[i] = NULL;
  }
}