Update to libjpeg_turbo 1.4.90

(Duplicate of https://codereview.chromium.org/1939823002/ for landing.)

TBR=noel@chromium.org,thakis@chromium.org
BUG=608347, 398235, 591927

Review URL: https://codereview.chromium.org/1953443002 .

1 files changed, 197 insertions, 161 deletions

diff --git a/jchuff.c b/jchuff.c
index 68e4e0e..58acd70 100644
--- a/jchuff.c
+++ b/jchuff.c
@@ -4,8 +4,10 @@
  * This file was part of the Independent JPEG Group's software:
  * Copyright (C) 1991-1997, Thomas G. Lane.
  * libjpeg-turbo Modifications:
- * Copyright (C) 2009-2011, D. R. Commander.
- * For conditions of distribution and use, see the accompanying README file.
+ * Copyright (C) 2009-2011, 2014-2016 D. R. Commander.
+ * Copyright (C) 2015 Matthieu Darbois.
+ * For conditions of distribution and use, see the accompanying README.ijg
+ * file.
  *
  * This file contains Huffman entropy encoding routines.
  *
@@ -19,7 +21,8 @@
 #define JPEG_INTERNALS
 #include "jinclude.h"
 #include "jpeglib.h"
-#include "jchuff.h"		/* Declarations shared with jcphuff.c */
+#include "jsimd.h"
+#include "jconfigint.h"
 #include <limits.h>
 
 /*
@@ -37,7 +40,7 @@
  */
 
 /* NOTE: Both GCC and Clang define __GNUC__ */
-#if defined __GNUC__ && defined __arm__
+#if defined __GNUC__ && (defined __arm__ || defined __aarch64__)
 #if !defined __thumb__ || defined __thumb2__
 #define USE_CLZ_INTRINSIC
 #endif
@@ -47,8 +50,7 @@
 #define JPEG_NBITS_NONZERO(x) (32 - __builtin_clz(x))
 #define JPEG_NBITS(x) (x ? JPEG_NBITS_NONZERO(x) : 0)
 #else
-static unsigned char jpeg_nbits_table[65536];
-static int jpeg_nbits_table_init = 0;
+#include "jpeg_nbits_table.h"
 #define JPEG_NBITS(x) (jpeg_nbits_table[x])
 #define JPEG_NBITS_NONZERO(x) JPEG_NBITS(x)
 #endif
@@ -65,8 +67,8 @@ static int jpeg_nbits_table_init = 0;
  */
 
 typedef struct {
-  size_t put_buffer;		/* current bit-accumulation buffer */
-  int put_bits;			/* # of bits now in it */
+  size_t put_buffer;            /* current bit-accumulation buffer */
+  int put_bits;                 /* # of bits now in it */
   int last_dc_val[MAX_COMPS_IN_SCAN]; /* last DC coef for each component */
 } savable_state;
 
@@ -80,12 +82,12 @@ typedef struct {
 #else
 #if MAX_COMPS_IN_SCAN == 4
 #define ASSIGN_STATE(dest,src)  \
-	((dest).put_buffer = (src).put_buffer, \
-	 (dest).put_bits = (src).put_bits, \
-	 (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])
+        ((dest).put_buffer = (src).put_buffer, \
+         (dest).put_bits = (src).put_bits, \
+         (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
 
@@ -93,44 +95,45 @@ typedef struct {
 typedef struct {
   struct jpeg_entropy_encoder pub; /* public fields */
 
-  savable_state saved;		/* Bit buffer & DC state at start of MCU */
+  savable_state saved;          /* Bit buffer & DC 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 */
-  int next_restart_num;		/* next restart number to write (0-7) */
+  unsigned int restarts_to_go;  /* MCUs left in this restart interval */
+  int next_restart_num;         /* next restart number to write (0-7) */
 
   /* Pointers to derived tables (these workspaces have image lifespan) */
-  c_derived_tbl * dc_derived_tbls[NUM_HUFF_TBLS];
-  c_derived_tbl * ac_derived_tbls[NUM_HUFF_TBLS];
+  c_derived_tbl *dc_derived_tbls[NUM_HUFF_TBLS];
+  c_derived_tbl *ac_derived_tbls[NUM_HUFF_TBLS];
 
-#ifdef ENTROPY_OPT_SUPPORTED	/* Statistics tables for optimization */
-  long * dc_count_ptrs[NUM_HUFF_TBLS];
-  long * ac_count_ptrs[NUM_HUFF_TBLS];
+#ifdef ENTROPY_OPT_SUPPORTED    /* Statistics tables for optimization */
+  long *dc_count_ptrs[NUM_HUFF_TBLS];
+  long *ac_count_ptrs[NUM_HUFF_TBLS];
 #endif
+
+  int simd;
 } huff_entropy_encoder;
 
-typedef huff_entropy_encoder * huff_entropy_ptr;
+typedef huff_entropy_encoder *huff_entropy_ptr;
 
 /* Working state while writing an MCU.
  * This struct contains all the fields that are needed by subroutines.
  */
 
 typedef struct {
-  JOCTET * next_output_byte;	/* => next byte to write in buffer */
-  size_t free_in_buffer;	/* # of byte spaces remaining in buffer */
-  savable_state cur;		/* Current bit buffer & DC state */
-  j_compress_ptr cinfo;		/* dump_buffer needs access to this */
+  JOCTET *next_output_byte;     /* => next byte to write in buffer */
+  size_t free_in_buffer;        /* # of byte spaces remaining in buffer */
+  savable_state cur;            /* Current bit buffer & DC state */
+  j_compress_ptr cinfo;         /* dump_buffer needs access to this */
 } working_state;
 
 
 /* Forward declarations */
-METHODDEF(boolean) encode_mcu_huff JPP((j_compress_ptr cinfo,
-					JBLOCKROW *MCU_data));
-METHODDEF(void) finish_pass_huff JPP((j_compress_ptr cinfo));
+METHODDEF(boolean) encode_mcu_huff (j_compress_ptr cinfo, JBLOCKROW *MCU_data);
+METHODDEF(void) finish_pass_huff (j_compress_ptr cinfo);
 #ifdef ENTROPY_OPT_SUPPORTED
-METHODDEF(boolean) encode_mcu_gather JPP((j_compress_ptr cinfo,
-					  JBLOCKROW *MCU_data));
-METHODDEF(void) finish_pass_gather JPP((j_compress_ptr cinfo));
+METHODDEF(boolean) encode_mcu_gather (j_compress_ptr cinfo,
+                                      JBLOCKROW *MCU_data);
+METHODDEF(void) finish_pass_gather (j_compress_ptr cinfo);
 #endif
 
 
@@ -145,7 +148,7 @@ start_pass_huff (j_compress_ptr cinfo, boolean gather_statistics)
 {
   huff_entropy_ptr entropy = (huff_entropy_ptr) cinfo->entropy;
   int ci, dctbl, actbl;
-  jpeg_component_info * compptr;
+  jpeg_component_info *compptr;
 
   if (gather_statistics) {
 #ifdef ENTROPY_OPT_SUPPORTED
@@ -159,6 +162,8 @@ start_pass_huff (j_compress_ptr cinfo, boolean gather_statistics)
     entropy->pub.finish_pass = finish_pass_huff;
   }
 
+  entropy->simd = jsimd_can_huff_encode_one_block();
+
   for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
     compptr = cinfo->cur_comp_info[ci];
     dctbl = compptr->dc_tbl_no;
@@ -168,29 +173,29 @@ start_pass_huff (j_compress_ptr cinfo, boolean gather_statistics)
       /* Check for invalid table indexes */
       /* (make_c_derived_tbl does this in the other path) */
       if (dctbl < 0 || dctbl >= NUM_HUFF_TBLS)
-	ERREXIT1(cinfo, JERR_NO_HUFF_TABLE, dctbl);
+        ERREXIT1(cinfo, JERR_NO_HUFF_TABLE, dctbl);
       if (actbl < 0 || actbl >= NUM_HUFF_TBLS)
-	ERREXIT1(cinfo, JERR_NO_HUFF_TABLE, actbl);
+        ERREXIT1(cinfo, JERR_NO_HUFF_TABLE, actbl);
       /* Allocate and zero the statistics tables */
       /* Note that jpeg_gen_optimal_table expects 257 entries in each table! */
       if (entropy->dc_count_ptrs[dctbl] == NULL)
-	entropy->dc_count_ptrs[dctbl] = (long *)
-	  (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
-				      257 * SIZEOF(long));
-      MEMZERO(entropy->dc_count_ptrs[dctbl], 257 * SIZEOF(long));
+        entropy->dc_count_ptrs[dctbl] = (long *)
+          (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
+                                      257 * sizeof(long));
+      MEMZERO(entropy->dc_count_ptrs[dctbl], 257 * sizeof(long));
       if (entropy->ac_count_ptrs[actbl] == NULL)
-	entropy->ac_count_ptrs[actbl] = (long *)
-	  (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
-				      257 * SIZEOF(long));
-      MEMZERO(entropy->ac_count_ptrs[actbl], 257 * SIZEOF(long));
+        entropy->ac_count_ptrs[actbl] = (long *)
+          (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
+                                      257 * sizeof(long));
+      MEMZERO(entropy->ac_count_ptrs[actbl], 257 * sizeof(long));
 #endif
     } else {
       /* Compute derived values for Huffman tables */
       /* We may do this more than once for a table, but it's not expensive */
       jpeg_make_c_derived_tbl(cinfo, TRUE, dctbl,
-			      & entropy->dc_derived_tbls[dctbl]);
+                              & entropy->dc_derived_tbls[dctbl]);
       jpeg_make_c_derived_tbl(cinfo, FALSE, actbl,
-			      & entropy->ac_derived_tbls[actbl]);
+                              & entropy->ac_derived_tbls[actbl]);
     }
     /* Initialize DC predictions to 0 */
     entropy->saved.last_dc_val[ci] = 0;
@@ -215,7 +220,7 @@ start_pass_huff (j_compress_ptr cinfo, boolean gather_statistics)
 
 GLOBAL(void)
 jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
-			 c_derived_tbl ** pdtbl)
+                         c_derived_tbl **pdtbl)
 {
   JHUFF_TBL *htbl;
   c_derived_tbl *dtbl;
@@ -240,22 +245,22 @@ jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
   if (*pdtbl == NULL)
     *pdtbl = (c_derived_tbl *)
       (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
-				  SIZEOF(c_derived_tbl));
+                                  sizeof(c_derived_tbl));
   dtbl = *pdtbl;
-  
+
   /* Figure C.1: make table of Huffman code length for each symbol */
 
   p = 0;
   for (l = 1; l <= 16; l++) {
     i = (int) htbl->bits[l];
-    if (i < 0 || p + i > 256)	/* protect against table overrun */
+    if (i < 0 || p + i > 256)   /* protect against table overrun */
       ERREXIT(cinfo, JERR_BAD_HUFF_TABLE);
     while (i--)
       huffsize[p++] = (char) l;
   }
   huffsize[p] = 0;
   lastp = p;
-  
+
   /* Figure C.2: generate the codes themselves */
   /* We also validate that the counts represent a legal Huffman code tree. */
 
@@ -270,12 +275,12 @@ jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
     /* code is now 1 more than the last code used for codelength si; but
      * it must still fit in si bits, since no code is allowed to be all ones.
      */
-    if (((INT32) code) >= (((INT32) 1) << si))
+    if (((JLONG) code) >= (((JLONG) 1) << si))
       ERREXIT(cinfo, JERR_BAD_HUFF_TABLE);
     code <<= 1;
     si++;
   }
-  
+
   /* Figure C.3: generate encoding tables */
   /* These are code and size indexed by symbol value */
 
@@ -283,7 +288,7 @@ jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
    * this lets us detect duplicate VAL entries here, and later
    * allows emit_bits to detect any attempt to emit such symbols.
    */
-  MEMZERO(dtbl->ehufsi, SIZEOF(dtbl->ehufsi));
+  MEMZERO(dtbl->ehufsi, sizeof(dtbl->ehufsi));
 
   /* This is also a convenient place to check for out-of-range
    * and duplicated VAL entries.  We allow 0..255 for AC symbols
@@ -299,17 +304,6 @@ jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
     dtbl->ehufco[i] = huffcode[p];
     dtbl->ehufsi[i] = huffsize[p];
   }
-
-#ifndef USE_CLZ_INTRINSIC
-  if(!jpeg_nbits_table_init) {
-    for(i = 0; i < 65536; i++) {
-      int nbits = 0, temp = i;
-      while (temp) {temp >>= 1;  nbits++;}
-      jpeg_nbits_table[i] = nbits;
-    }
-    jpeg_nbits_table_init = 1;
-  }
-#endif
 }
 
 
@@ -317,17 +311,17 @@ jpeg_make_c_derived_tbl (j_compress_ptr cinfo, boolean isDC, int tblno,
 
 /* Emit a byte, taking 'action' if must suspend. */
 #define emit_byte(state,val,action)  \
-	{ *(state)->next_output_byte++ = (JOCTET) (val);  \
-	  if (--(state)->free_in_buffer == 0)  \
-	    if (! dump_buffer(state))  \
-	      { action; } }
+        { *(state)->next_output_byte++ = (JOCTET) (val);  \
+          if (--(state)->free_in_buffer == 0)  \
+            if (! dump_buffer(state))  \
+              { action; } }
 
 
 LOCAL(boolean)
-dump_buffer (working_state * state)
+dump_buffer (working_state *state)
 /* Empty the output buffer; return TRUE if successful, FALSE if must suspend */
 {
-  struct jpeg_destination_mgr * dest = state->cinfo->dest;
+  struct jpeg_destination_mgr *dest = state->cinfo->dest;
 
   if (! (*dest->empty_output_buffer) (state->cinfo))
     return FALSE;
@@ -389,7 +383,11 @@ dump_buffer (working_state * state)
   } \
 }
 
-#if __WORDSIZE==64 || defined(_WIN64)
+#if !defined(_WIN32) && !defined(SIZEOF_SIZE_T)
+#error Cannot determine word size
+#endif
+
+#if SIZEOF_SIZE_T==8 || defined(_WIN64)
 
 #define EMIT_BITS(code, size) { \
   CHECKBUF47() \
@@ -397,7 +395,7 @@ dump_buffer (working_state * state)
 }
 
 #define EMIT_CODE(code, size) { \
-  temp2 &= (((INT32) 1)<<nbits) - 1; \
+  temp2 &= (((JLONG) 1)<<nbits) - 1; \
   CHECKBUF31() \
   PUT_BITS(code, size) \
   PUT_BITS(temp2, nbits) \
@@ -411,7 +409,7 @@ dump_buffer (working_state * state)
 }
 
 #define EMIT_CODE(code, size) { \
-  temp2 &= (((INT32) 1)<<nbits) - 1; \
+  temp2 &= (((JLONG) 1)<<nbits) - 1; \
   PUT_BITS(code, size) \
   CHECKBUF15() \
   PUT_BITS(temp2, nbits) \
@@ -421,7 +419,16 @@ dump_buffer (working_state * state)
 #endif
 
 
-#define BUFSIZE (DCTSIZE2 * 2)
+/* Although it is exceedingly rare, it is possible for a Huffman-encoded
+ * coefficient block to be larger than the 128-byte unencoded block.  For each
+ * of the 64 coefficients, PUT_BITS is invoked twice, and each invocation can
+ * theoretically store 16 bits (for a maximum of 2048 bits or 256 bytes per
+ * encoded block.)  If, for instance, one artificially sets the AC
+ * coefficients to alternating values of 32767 and -32768 (using the JPEG
+ * scanning order-- 1, 8, 16, etc.), then this will produce an encoded block
+ * larger than 200 bytes.
+ */
+#define BUFSIZE (DCTSIZE2 * 4)
 
 #define LOAD_BUFFER() { \
   if (state->free_in_buffer < BUFSIZE) { \
@@ -454,7 +461,7 @@ dump_buffer (working_state * state)
 
 
 LOCAL(boolean)
-flush_bits (working_state * state)
+flush_bits (working_state *state)
 {
   JOCTET _buffer[BUFSIZE], *buffer;
   size_t put_buffer;  int put_bits;
@@ -468,7 +475,7 @@ flush_bits (working_state * state)
   PUT_BITS(0x7F, 7)
   while (put_bits >= 8) EMIT_BYTE()
 
-  state->cur.put_buffer = 0;	/* and reset bit-buffer to empty */
+  state->cur.put_buffer = 0;    /* and reset bit-buffer to empty */
   state->cur.put_bits = 0;
   STORE_BUFFER()
 
@@ -479,8 +486,25 @@ flush_bits (working_state * state)
 /* Encode a single block's worth of coefficients */
 
 LOCAL(boolean)
-encode_one_block (working_state * state, JCOEFPTR block, int last_dc_val,
-		  c_derived_tbl *dctbl, c_derived_tbl *actbl)
+encode_one_block_simd (working_state *state, JCOEFPTR block, int last_dc_val,
+                       c_derived_tbl *dctbl, c_derived_tbl *actbl)
+{
+  JOCTET _buffer[BUFSIZE], *buffer;
+  size_t bytes, bytestocopy;  int localbuf = 0;
+
+  LOAD_BUFFER()
+
+  buffer = jsimd_huff_encode_one_block(state, buffer, block, last_dc_val,
+                                       dctbl, actbl);
+
+  STORE_BUFFER()
+
+  return TRUE;
+}
+
+LOCAL(boolean)
+encode_one_block (working_state *state, JCOEFPTR block, int last_dc_val,
+                  c_derived_tbl *dctbl, c_derived_tbl *actbl)
 {
   int temp, temp2, temp3;
   int nbits;
@@ -495,7 +519,7 @@ encode_one_block (working_state * state, JCOEFPTR block, int last_dc_val,
   LOAD_BUFFER()
 
   /* Encode the DC coefficient difference per section F.1.2.1 */
-  
+
   temp = temp2 = block[0] - last_dc_val;
 
  /* This is a well-known technique for obtaining the absolute value without a
@@ -517,20 +541,18 @@ encode_one_block (working_state * state, JCOEFPTR block, int last_dc_val,
   /* Emit the Huffman-coded symbol for the number of bits */
   code = dctbl->ehufco[nbits];
   size = dctbl->ehufsi[nbits];
-  PUT_BITS(code, size)
-  CHECKBUF15()
+  EMIT_BITS(code, size)
 
   /* Mask off any extra bits in code */
-  temp2 &= (((INT32) 1)<<nbits) - 1;
+  temp2 &= (((JLONG) 1)<<nbits) - 1;
 
   /* Emit that number of bits of the value, if positive, */
   /* or the complement of its magnitude, if negative. */
-  PUT_BITS(temp2, nbits)
-  CHECKBUF15()
+  EMIT_BITS(temp2, nbits)
 
   /* Encode the AC coefficients per section F.1.2.2 */
-  
-  r = 0;			/* r = run length of zeros */
+
+  r = 0;                        /* r = run length of zeros */
 
 /* Manually unroll the k loop to eliminate the counter variable.  This
  * improves performance greatly on systems with a limited number of
@@ -594,7 +616,7 @@ encode_one_block (working_state * state, JCOEFPTR block, int last_dc_val,
  */
 
 LOCAL(boolean)
-emit_restart (working_state * state, int restart_num)
+emit_restart (working_state *state, int restart_num)
 {
   int ci;
 
@@ -624,7 +646,7 @@ encode_mcu_huff (j_compress_ptr cinfo, JBLOCKROW *MCU_data)
   huff_entropy_ptr entropy = (huff_entropy_ptr) cinfo->entropy;
   working_state state;
   int blkn, ci;
-  jpeg_component_info * compptr;
+  jpeg_component_info *compptr;
 
   /* Load up working state */
   state.next_output_byte = cinfo->dest->next_output_byte;
@@ -636,20 +658,34 @@ encode_mcu_huff (j_compress_ptr cinfo, JBLOCKROW *MCU_data)
   if (cinfo->restart_interval) {
     if (entropy->restarts_to_go == 0)
       if (! emit_restart(&state, entropy->next_restart_num))
-	return FALSE;
+        return FALSE;
   }
 
   /* Encode the MCU data blocks */
-  for (blkn = 0; blkn < cinfo->blocks_in_MCU; blkn++) {
-    ci = cinfo->MCU_membership[blkn];
-    compptr = cinfo->cur_comp_info[ci];
-    if (! encode_one_block(&state,
-			   MCU_data[blkn][0], state.cur.last_dc_val[ci],
-			   entropy->dc_derived_tbls[compptr->dc_tbl_no],
-			   entropy->ac_derived_tbls[compptr->ac_tbl_no]))
-      return FALSE;
-    /* Update last_dc_val */
-    state.cur.last_dc_val[ci] = MCU_data[blkn][0][0];
+  if (entropy->simd) {
+    for (blkn = 0; blkn < cinfo->blocks_in_MCU; blkn++) {
+      ci = cinfo->MCU_membership[blkn];
+      compptr = cinfo->cur_comp_info[ci];
+      if (! encode_one_block_simd(&state,
+                                  MCU_data[blkn][0], state.cur.last_dc_val[ci],
+                                  entropy->dc_derived_tbls[compptr->dc_tbl_no],
+                                  entropy->ac_derived_tbls[compptr->ac_tbl_no]))
+        return FALSE;
+      /* Update last_dc_val */
+      state.cur.last_dc_val[ci] = MCU_data[blkn][0][0];
+    }
+  } else {
+    for (blkn = 0; blkn < cinfo->blocks_in_MCU; blkn++) {
+      ci = cinfo->MCU_membership[blkn];
+      compptr = cinfo->cur_comp_info[ci];
+      if (! encode_one_block(&state,
+                             MCU_data[blkn][0], state.cur.last_dc_val[ci],
+                             entropy->dc_derived_tbls[compptr->dc_tbl_no],
+                             entropy->ac_derived_tbls[compptr->ac_tbl_no]))
+        return FALSE;
+      /* Update last_dc_val */
+      state.cur.last_dc_val[ci] = MCU_data[blkn][0][0];
+    }
   }
 
   /* Completed MCU, so update state */
@@ -716,18 +752,18 @@ finish_pass_huff (j_compress_ptr cinfo)
 
 LOCAL(void)
 htest_one_block (j_compress_ptr cinfo, JCOEFPTR block, int last_dc_val,
-		 long dc_counts[], long ac_counts[])
+                 long dc_counts[], long ac_counts[])
 {
   register int temp;
   register int nbits;
   register int k, r;
-  
+
   /* Encode the DC coefficient difference per section F.1.2.1 */
-  
+
   temp = block[0] - last_dc_val;
   if (temp < 0)
     temp = -temp;
-  
+
   /* Find the number of bits needed for the magnitude of the coefficient */
   nbits = 0;
   while (temp) {
@@ -742,36 +778,36 @@ htest_one_block (j_compress_ptr cinfo, JCOEFPTR block, int last_dc_val,
 
   /* Count the Huffman symbol for the number of bits */
   dc_counts[nbits]++;
-  
+
   /* Encode the AC coefficients per section F.1.2.2 */
-  
-  r = 0;			/* r = run length of zeros */
-  
+
+  r = 0;                        /* r = run length of zeros */
+
   for (k = 1; k < DCTSIZE2; k++) {
     if ((temp = block[jpeg_natural_order[k]]) == 0) {
       r++;
     } else {
       /* if run length > 15, must emit special run-length-16 codes (0xF0) */
       while (r > 15) {
-	ac_counts[0xF0]++;
-	r -= 16;
+        ac_counts[0xF0]++;
+        r -= 16;
       }
-      
+
       /* Find the number of bits needed for the magnitude of the coefficient */
       if (temp < 0)
-	temp = -temp;
-      
+        temp = -temp;
+
       /* Find the number of bits needed for the magnitude of the coefficient */
-      nbits = 1;		/* there must be at least one 1 bit */
+      nbits = 1;                /* there must be at least one 1 bit */
       while ((temp >>= 1))
-	nbits++;
+        nbits++;
       /* Check for out-of-range coefficient values */
       if (nbits > MAX_COEF_BITS)
-	ERREXIT(cinfo, JERR_BAD_DCT_COEF);
-      
+        ERREXIT(cinfo, JERR_BAD_DCT_COEF);
+
       /* Count Huffman symbol for run length / number of bits */
       ac_counts[(r << 4) + nbits]++;
-      
+
       r = 0;
     }
   }
@@ -792,14 +828,14 @@ encode_mcu_gather (j_compress_ptr cinfo, JBLOCKROW *MCU_data)
 {
   huff_entropy_ptr entropy = (huff_entropy_ptr) cinfo->entropy;
   int blkn, ci;
-  jpeg_component_info * compptr;
+  jpeg_component_info *compptr;
 
   /* Take care of restart intervals if needed */
   if (cinfo->restart_interval) {
     if (entropy->restarts_to_go == 0) {
       /* Re-initialize DC predictions to 0 */
       for (ci = 0; ci < cinfo->comps_in_scan; ci++)
-	entropy->saved.last_dc_val[ci] = 0;
+        entropy->saved.last_dc_val[ci] = 0;
       /* Update restart state */
       entropy->restarts_to_go = cinfo->restart_interval;
     }
@@ -810,8 +846,8 @@ encode_mcu_gather (j_compress_ptr cinfo, JBLOCKROW *MCU_data)
     ci = cinfo->MCU_membership[blkn];
     compptr = cinfo->cur_comp_info[ci];
     htest_one_block(cinfo, MCU_data[blkn][0], entropy->saved.last_dc_val[ci],
-		    entropy->dc_count_ptrs[compptr->dc_tbl_no],
-		    entropy->ac_count_ptrs[compptr->ac_tbl_no]);
+                    entropy->dc_count_ptrs[compptr->dc_tbl_no],
+                    entropy->ac_count_ptrs[compptr->ac_tbl_no]);
     entropy->saved.last_dc_val[ci] = MCU_data[blkn][0][0];
   }
 
@@ -848,24 +884,24 @@ encode_mcu_gather (j_compress_ptr cinfo, JBLOCKROW *MCU_data)
  */
 
 GLOBAL(void)
-jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
+jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL *htbl, long freq[])
 {
-#define MAX_CLEN 32		/* assumed maximum initial code length */
-  UINT8 bits[MAX_CLEN+1];	/* bits[k] = # of symbols with code length k */
-  int codesize[257];		/* codesize[k] = code length of symbol k */
-  int others[257];		/* next symbol in current branch of tree */
+#define MAX_CLEN 32             /* assumed maximum initial code length */
+  UINT8 bits[MAX_CLEN+1];       /* bits[k] = # of symbols with code length k */
+  int codesize[257];            /* codesize[k] = code length of symbol k */
+  int others[257];              /* next symbol in current branch of tree */
   int c1, c2;
   int p, i, j;
   long v;
 
   /* This algorithm is explained in section K.2 of the JPEG standard */
 
-  MEMZERO(bits, SIZEOF(bits));
-  MEMZERO(codesize, SIZEOF(codesize));
+  MEMZERO(bits, sizeof(bits));
+  MEMZERO(codesize, sizeof(codesize));
   for (i = 0; i < 257; i++)
-    others[i] = -1;		/* init links to empty */
-  
-  freq[256] = 1;		/* make sure 256 has a nonzero count */
+    others[i] = -1;             /* init links to empty */
+
+  freq[256] = 1;                /* make sure 256 has a nonzero count */
   /* Including the pseudo-symbol 256 in the Huffman procedure guarantees
    * that no real symbol is given code-value of all ones, because 256
    * will be placed last in the largest codeword category.
@@ -880,8 +916,8 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
     v = 1000000000L;
     for (i = 0; i <= 256; i++) {
       if (freq[i] && freq[i] <= v) {
-	v = freq[i];
-	c1 = i;
+        v = freq[i];
+        c1 = i;
       }
     }
 
@@ -891,15 +927,15 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
     v = 1000000000L;
     for (i = 0; i <= 256; i++) {
       if (freq[i] && freq[i] <= v && i != c1) {
-	v = freq[i];
-	c2 = i;
+        v = freq[i];
+        c2 = i;
       }
     }
 
     /* Done if we've merged everything into one frequency */
     if (c2 < 0)
       break;
-    
+
     /* Else merge the two counts/trees */
     freq[c1] += freq[c2];
     freq[c2] = 0;
@@ -910,9 +946,9 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
       c1 = others[c1];
       codesize[c1]++;
     }
-    
-    others[c1] = c2;		/* chain c2 onto c1's tree branch */
-    
+
+    others[c1] = c2;            /* chain c2 onto c1's tree branch */
+
     /* Increment the codesize of everything in c2's tree branch */
     codesize[c2]++;
     while (others[c2] >= 0) {
@@ -927,7 +963,7 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
       /* The JPEG standard seems to think that this can't happen, */
       /* but I'm paranoid... */
       if (codesize[i] > MAX_CLEN)
-	ERREXIT(cinfo, JERR_HUFF_CLEN_OVERFLOW);
+        ERREXIT(cinfo, JERR_HUFF_CLEN_OVERFLOW);
 
       bits[codesize[i]]++;
     }
@@ -943,28 +979,28 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
    * shortest nonzero BITS entry is converted into a prefix for two code words
    * one bit longer.
    */
-  
+
   for (i = MAX_CLEN; i > 16; i--) {
     while (bits[i] > 0) {
-      j = i - 2;		/* find length of new prefix to be used */
+      j = i - 2;                /* find length of new prefix to be used */
       while (bits[j] == 0)
-	j--;
-      
-      bits[i] -= 2;		/* remove two symbols */
-      bits[i-1]++;		/* one goes in this length */
-      bits[j+1] += 2;		/* two new symbols in this length */
-      bits[j]--;		/* symbol of this length is now a prefix */
+        j--;
+
+      bits[i] -= 2;             /* remove two symbols */
+      bits[i-1]++;              /* one goes in this length */
+      bits[j+1] += 2;           /* two new symbols in this length */
+      bits[j]--;                /* symbol of this length is now a prefix */
     }
   }
 
   /* Remove the count for the pseudo-symbol 256 from the largest codelength */
-  while (bits[i] == 0)		/* find largest codelength still in use */
+  while (bits[i] == 0)          /* find largest codelength still in use */
     i--;
   bits[i]--;
-  
+
   /* Return final symbol counts (only for lengths 0..16) */
-  MEMCOPY(htbl->bits, bits, SIZEOF(htbl->bits));
-  
+  MEMCOPY(htbl->bits, bits, sizeof(htbl->bits));
+
   /* Return a list of the symbols sorted by code length */
   /* It's not real clear to me why we don't need to consider the codelength
    * changes made above, but the JPEG spec seems to think this works.
@@ -973,8 +1009,8 @@ jpeg_gen_optimal_table (j_compress_ptr cinfo, JHUFF_TBL * htbl, long freq[])
   for (i = 1; i <= MAX_CLEN; i++) {
     for (j = 0; j <= 255; j++) {
       if (codesize[j] == i) {
-	htbl->huffval[p] = (UINT8) j;
-	p++;
+        htbl->huffval[p] = (UINT8) j;
+        p++;
       }
     }
   }
@@ -993,7 +1029,7 @@ finish_pass_gather (j_compress_ptr cinfo)
 {
   huff_entropy_ptr entropy = (huff_entropy_ptr) cinfo->entropy;
   int ci, dctbl, actbl;
-  jpeg_component_info * compptr;
+  jpeg_component_info *compptr;
   JHUFF_TBL **htblptr;
   boolean did_dc[NUM_HUFF_TBLS];
   boolean did_ac[NUM_HUFF_TBLS];
@@ -1001,8 +1037,8 @@ finish_pass_gather (j_compress_ptr cinfo)
   /* It's important not to apply jpeg_gen_optimal_table more than once
    * per table, because it clobbers the input frequency counts!
    */
-  MEMZERO(did_dc, SIZEOF(did_dc));
-  MEMZERO(did_ac, SIZEOF(did_ac));
+  MEMZERO(did_dc, sizeof(did_dc));
+  MEMZERO(did_ac, sizeof(did_ac));
 
   for (ci = 0; ci < cinfo->comps_in_scan; ci++) {
     compptr = cinfo->cur_comp_info[ci];
@@ -1011,14 +1047,14 @@ finish_pass_gather (j_compress_ptr cinfo)
     if (! did_dc[dctbl]) {
       htblptr = & cinfo->dc_huff_tbl_ptrs[dctbl];
       if (*htblptr == NULL)
-	*htblptr = jpeg_alloc_huff_table((j_common_ptr) cinfo);
+        *htblptr = jpeg_alloc_huff_table((j_common_ptr) cinfo);
       jpeg_gen_optimal_table(cinfo, *htblptr, entropy->dc_count_ptrs[dctbl]);
       did_dc[dctbl] = TRUE;
     }
     if (! did_ac[actbl]) {
       htblptr = & cinfo->ac_huff_tbl_ptrs[actbl];
       if (*htblptr == NULL)
-	*htblptr = jpeg_alloc_huff_table((j_common_ptr) cinfo);
+        *htblptr = jpeg_alloc_huff_table((j_common_ptr) cinfo);
       jpeg_gen_optimal_table(cinfo, *htblptr, entropy->ac_count_ptrs[actbl]);
       did_ac[actbl] = TRUE;
     }
@@ -1041,7 +1077,7 @@ jinit_huff_encoder (j_compress_ptr cinfo)
 
   entropy = (huff_entropy_ptr)
     (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
-				SIZEOF(huff_entropy_encoder));
+                                sizeof(huff_entropy_encoder));
   cinfo->entropy = (struct jpeg_entropy_encoder *) entropy;
   entropy->pub.start_pass = start_pass_huff;