jdpipe.c

EVM板JPEG实现,Texas Instruments TMS320C54x EVM JPEG

/*
 * jdpipe.c
 *
 * Copyright (C) 1991, 1992, Thomas G. Lane.
 * This file is part of the Independent JPEG Group's software.
 * For conditions of distribution and use, see the accompanying README file.
 *
 * This file contains decompression pipeline controllers.
 * These routines are invoked via the d_pipeline_controller method.
 *
 * There are two basic pipeline controllers.  The simpler one handles a
 * single-scan JPEG file (single component or fully interleaved) with no
 * color quantization or 1-pass quantization.  In this case, the file can
 * be processed in one top-to-bottom pass.  The more complex controller is
 * used when 2-pass color quantization is requested and/or the JPEG file
 * has multiple scans (noninterleaved or partially interleaved).  In this
 * case, the entire image must be buffered up in a "big" array.
 *
 * If you need to make a minimal implementation, the more complex controller
 * can be compiled out by disabling the appropriate configuration options.
 * We don't recommend this, since then you can't handle all legal JPEG files.
 */

#include "jinclude.h"


#ifdef D_MULTISCAN_FILES_SUPPORTED /* wish we could assume ANSI's defined() */
#define NEED_COMPLEX_CONTROLLER
#else
#ifdef QUANT_2PASS_SUPPORTED
#define NEED_COMPLEX_CONTROLLER
#endif
#endif


/*
 * About the data structures:
 *
 * The processing chunk size for upsampling is referred to in this file as
 * a "row group": a row group is defined as Vk (v_samp_factor) sample rows of
 * any component while downsampled, or Vmax (max_v_samp_factor) unsubsampled
 * rows.  In an interleaved scan each MCU row contains exactly DCTSIZE row
 * groups of each component in the scan.  In a noninterleaved scan an MCU row
 * is one row of blocks, which might not be an integral number of row groups;
 * therefore, we read in Vk MCU rows to obtain the same amount of data as we'd
 * have in an interleaved scan.
 * To provide context for the upsampling step, we have to retain the last
 * two row groups of the previous MCU row while reading in the next MCU row
 * (or set of Vk MCU rows).  To do this without copying data about, we create
 * a rather strange data structure.  Exactly DCTSIZE+2 row groups of samples
 * are allocated, but we create two different sets of pointers to this array.
 * The second set swaps the last two pairs of row groups.  By working
 * alternately with the two sets of pointers, we can access the data in the
 * desired order.
 *
 * Cross-block smoothing also needs context above and below the "current" row.
 * Since this is an optional feature, I've implemented it in a way that is
 * much simpler but requires more than the minimum amount of memory.  We
 * simply allocate three extra MCU rows worth of coefficient blocks and use
 * them to "read ahead" one MCU row in the file.  For a typical 1000-pixel-wide
 * image with 2x2,1x1,1x1 sampling, each MCU row is about 50Kb; an 80x86
 * machine may be unable to apply cross-block smoothing to wider images.
 */


/*
 * These variables are logically local to the pipeline controller,
 * but we make them static so that scan_big_image can use them
 * without having to pass them through the quantization routines.
 */

static int rows_in_mem;		/* # of sample rows in full-size buffers */
/* Work buffer for data being passed to output module. */
/* This has color_out_comps components if not quantizing, */
/* but only one component when quantizing. */
static JSAMPIMAGE output_workspace;

#ifdef NEED_COMPLEX_CONTROLLER
/* Full-size image array holding upsampled, but not color-processed data. */
static big_sarray_ptr *fullsize_image;
static JSAMPIMAGE fullsize_ptrs; /* workspace for access_big_sarray() result */
#endif


/*
 * Utility routines: common code for pipeline controllers
 */

LOCAL void
interleaved_scan_setup (decompress_info_ptr cinfo)
/* Compute all derived info for an interleaved (multi-component) scan */
/* On entry, cinfo->comps_in_scan and cinfo->cur_comp_info[] are set up */
{
  short ci, mcublks;
  jpeg_component_info *compptr;

  if (cinfo->comps_in_scan > MAX_COMPS_IN_SCAN)
  {
/*    ERREXIT(cinfo->emethods, "Too many components for interleaved scan"); */
      send_command(ERR7);
      receive_command();
      exit();
  }

  cinfo->MCUs_per_row = (cinfo->image_width
			 + cinfo->max_h_samp_factor*DCTSIZE - 1)
			/ (cinfo->max_h_samp_factor*DCTSIZE);

  cinfo->MCU_rows_in_scan = (cinfo->image_height
			     + cinfo->max_v_samp_factor*DCTSIZE - 1)
			    / (cinfo->max_v_samp_factor*DCTSIZE);
  
  cinfo->blocks_in_MCU = 0;

  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    compptr = cinfo->cur_comp_info[ci];
    /* for interleaved scan, sampling factors give # of blocks per component */
    compptr->MCU_width = compptr->h_samp_factor;
    compptr->MCU_height = compptr->v_samp_factor;
    compptr->MCU_blocks = compptr->MCU_width * compptr->MCU_height;
    /* compute physical dimensions of component */
    compptr->downsampled_width = jround_up(compptr->true_comp_width,
					   (long) (compptr->MCU_width*DCTSIZE));
    compptr->downsampled_height = jround_up(compptr->true_comp_height,
					    (long) (compptr->MCU_height*DCTSIZE));
    /* Sanity check */
    if (compptr->downsampled_width !=
	(cinfo->MCUs_per_row * (compptr->MCU_width*DCTSIZE)))
   {
/*      ERREXIT(cinfo->emethods, "I'm confused about the image width"); */
      send_command(ERR7);
      receive_command();
      exit();
   }
    /* Prepare array describing MCU composition */
    mcublks = compptr->MCU_blocks;
    if (cinfo->blocks_in_MCU + mcublks > MAX_BLOCKS_IN_MCU)
    {
/*      ERREXIT(cinfo->emethods, "Sampling factors too large for interleaved scan"); */
      send_command(ERR7);
      receive_command();
      exit();
    }
    while (mcublks-- > 0) {
      cinfo->MCU_membership[cinfo->blocks_in_MCU++] = ci;
    }
  }

  (*cinfo->methods->d_per_scan_method_selection) (cinfo);
}


LOCAL void
noninterleaved_scan_setup (decompress_info_ptr cinfo)
/* Compute all derived info for a noninterleaved (single-component) scan */
/* On entry, cinfo->comps_in_scan = 1 and cinfo->cur_comp_info[0] is set up */
{
  jpeg_component_info *compptr = cinfo->cur_comp_info[0];

  /* for noninterleaved scan, always one block per MCU */
  compptr->MCU_width = 1;
  compptr->MCU_height = 1;
  compptr->MCU_blocks = 1;
  /* compute physical dimensions of component */
  compptr->downsampled_width = jround_up(compptr->true_comp_width,
					 (long) DCTSIZE);
  compptr->downsampled_height = jround_up(compptr->true_comp_height,
					  (long) DCTSIZE);

  cinfo->MCUs_per_row = compptr->downsampled_width / DCTSIZE;
  cinfo->MCU_rows_in_scan = compptr->downsampled_height / DCTSIZE;

  /* Prepare array describing MCU composition */
  cinfo->blocks_in_MCU = 1;
  cinfo->MCU_membership[0] = 0;

  (*cinfo->methods->d_per_scan_method_selection) (cinfo);
}



LOCAL JSAMPIMAGE
alloc_sampimage (decompress_info_ptr cinfo,
		 int num_comps, long num_rows, long num_cols)
/* Allocate an in-memory sample image (all components same size) */
{
  JSAMPIMAGE image;
  int ci;

  image = (JSAMPIMAGE) (*cinfo->emethods->alloc_small)
				(num_comps * SIZEOF(JSAMPARRAY));
  for (ci = 0; ci < num_comps; ci++) {
    image[ci] = (*cinfo->emethods->alloc_small_sarray) (num_cols, num_rows);
  }
  return image;
}


#if 0				/* this routine not currently needed */

LOCAL void
free_sampimage (decompress_info_ptr cinfo, JSAMPIMAGE image, int num_comps)
/* Release a sample image created by alloc_sampimage */
{
  int ci;

  for (ci = 0; ci < num_comps; ci++) {
      (*cinfo->emethods->free_small_sarray) (image[ci]);
  }
  (*cinfo->emethods->free_small) ((void *) image);
}

#endif


LOCAL JBLOCKIMAGE
alloc_MCU_row (decompress_info_ptr cinfo)
/* Allocate one MCU row's worth of coefficient blocks */
{
  JBLOCKIMAGE image;
  int ci;

  image = (JBLOCKIMAGE) (*cinfo->emethods->alloc_small)
				(cinfo->comps_in_scan * SIZEOF(JBLOCKARRAY));
  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    image[ci] = (*cinfo->emethods->alloc_small_barray)
			(cinfo->cur_comp_info[ci]->downsampled_width / DCTSIZE,
			 (long) cinfo->cur_comp_info[ci]->MCU_height);
  }
  return image;
}


#ifdef NEED_COMPLEX_CONTROLLER	/* not used by simple controller */

LOCAL void
free_MCU_row (decompress_info_ptr cinfo, JBLOCKIMAGE image)
/* Release a coefficient block array created by alloc_MCU_row */
{
  int ci;

  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    (*cinfo->emethods->free_small_barray) (image[ci]);
  }
  (*cinfo->emethods->free_small) ((void *) image);
}

#endif


LOCAL void
alloc_sampling_buffer (decompress_info_ptr cinfo, JSAMPIMAGE sampled_data[2])
/* Create a downsampled-data buffer having the desired structure */
/* (see comments at head of file) */
{
  short ci, vs, i;

  /* Get top-level space for array pointers */
  sampled_data[0] = (JSAMPIMAGE) (*cinfo->emethods->alloc_small)
				(cinfo->comps_in_scan * SIZEOF(JSAMPARRAY));
  sampled_data[1] = (JSAMPIMAGE) (*cinfo->emethods->alloc_small)
				(cinfo->comps_in_scan * SIZEOF(JSAMPARRAY));

  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    vs = cinfo->cur_comp_info[ci]->v_samp_factor; /* row group height */
    /* Allocate the real storage */
    sampled_data[0][ci] = (*cinfo->emethods->alloc_small_sarray)
				(cinfo->cur_comp_info[ci]->downsampled_width,
				(long) (vs * (DCTSIZE+2)));
    /* Create space for the scrambled-order pointers */
    sampled_data[1][ci] = (JSAMPARRAY) (*cinfo->emethods->alloc_small)
				(vs * (DCTSIZE+2) * SIZEOF(JSAMPROW));
    /* Duplicate the first DCTSIZE-2 row groups */
    for (i = 0; i < vs * (DCTSIZE-2); i++) {
      sampled_data[1][ci][i] = sampled_data[0][ci][i];
    }
    /* Copy the last four row groups in swapped order */
    for (i = 0; i < vs * 2; i++) {
      sampled_data[1][ci][vs*DCTSIZE + i] = sampled_data[0][ci][vs*(DCTSIZE-2) + i];
      sampled_data[1][ci][vs*(DCTSIZE-2) + i] = sampled_data[0][ci][vs*DCTSIZE + i];
    }
  }
}


#ifdef NEED_COMPLEX_CONTROLLER	/* not used by simple controller */

LOCAL void
free_sampling_buffer (decompress_info_ptr cinfo, JSAMPIMAGE sampled_data[2])
/* Release a sampling buffer created by alloc_sampling_buffer */
{
  short ci;

  for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
    /* Free the real storage */
    (*cinfo->emethods->free_small_sarray) (sampled_data[0][ci]);
    /* Free the scrambled-order pointers */
    (*cinfo->emethods->free_small) ((void *) sampled_data[1][ci]);
  }

  /* Free the top-level space */
  (*cinfo->emethods->free_small) ((void *) sampled_data[0]);
  (*cinfo->emethods->free_small) ((void *) sampled_data[1]);
}

#endif


/*
 * Several decompression processes need to range-limit values to the range
 * 0..MAXJSAMPLE; the input value may fall somewhat outside this range
 * due to noise introduced by quantization, roundoff error, etc.  These
 * processes are inner loops and need to be as fast as possible.  On most
 * machines, particularly CPUs with pipelines or instruction prefetch,
 * a (range-check-less) C table lookup
 *		x = sample_range_limit[x];
 * is faster than explicit tests
 *		if (x < 0)  x = 0;
 *		else if (x > MAXJSAMPLE)  x = MAXJSAMPLE;
 * These processes all use a common table prepared by the routine below.
 *
 * The table will work correctly for x within MAXJSAMPLE+1 of the legal
 * range.  This is a much wider range than is needed for most cases,
 * but the wide range is handy for color quantization.
 * Note that the table is allocated in near data space on PCs; it's small
 * enough and used often enough to justify this.
 */

LOCAL void
prepare_range_limit_table (decompress_info_ptr cinfo)
/* Allocate and fill in the sample_range_limit table */
{
  JSAMPLE * table;
  int i;

  table = (JSAMPLE *) (*cinfo->emethods->alloc_small)
			(3 * (MAXJSAMPLE+1) * SIZEOF(JSAMPLE));
  cinfo->sample_range_limit = table + (MAXJSAMPLE+1);
  for (i = 0; i <= MAXJSAMPLE; i++) {
    table[i] = 0;			/* sample_range_limit[x] = 0 for x<0 */
    table[i+(MAXJSAMPLE+1)] = (JSAMPLE) i;	/* sample_range_limit[x] = x */
    table[i+(MAXJSAMPLE+1)*2] = MAXJSAMPLE;	/* x beyond MAXJSAMPLE */
  }
}


LOCAL void
duplicate_row (JSAMPARRAY image_data,
	       long num_cols, int source_row, int num_rows)
/* Duplicate the source_row at source_row+1 .. source_row+num_rows */
/* This happens only at the bottom of the image, */
/* so it needn't be super-efficient */
{
  register int row;

  for (row = 1; row <= num_rows; row++) {
    jcopy_sample_rows(image_data, source_row, image_data, source_row + row,
		      1, num_cols);