/* Find the best 'out_' histogram for each of the 'in' histograms.
* When called, clusters[0..num_clusters) contains the unique values from
* symbols[0..in_size), but this property is not preserved in this function.
* Note: we assume that out_[]->bit_cost_ is already up-to-date. */
public static void BrotliHistogramRemap(HistogramDistance *in_,
size_t in_size, uint *clusters, size_t num_clusters,
HistogramDistance *out_, uint *symbols)
{
size_t i;
for (i = 0; i < in_size; ++i)
{
uint best_out = i == 0 ? symbols[0] : symbols[i - 1];
double best_bits =
BrotliHistogramBitCostDistance(&in_[i], &out_[best_out]);
size_t j;
for (j = 0; j < num_clusters; ++j)
{
double cur_bits =
BrotliHistogramBitCostDistance(&in_[i], &out_[clusters[j]]);
if (cur_bits < best_bits)
{
best_bits = cur_bits;
best_out = clusters[j];
}
}
symbols[i] = best_out;
}
/* Recompute each out_ based on raw and symbols. */
for (i = 0; i < num_clusters; ++i)
{
HistogramDistance.HistogramClear(&out_[clusters[i]]);
}
for (i = 0; i < in_size; ++i)
{
HistogramDistance.HistogramAddHistogram(&out_[symbols[i]], &in_[i]);
}
}
/* What is the bit cost of moving histogram from cur_symbol to candidate. */
public static double BrotliHistogramBitCostDistance(
HistogramDistance *histogram, HistogramDistance *candidate)
{
if (histogram->total_count_ == 0)
{
return(0.0);
}
else
{
HistogramDistance tmp = *histogram;
HistogramDistance.HistogramAddHistogram(&tmp, candidate);
return(BitCostDistance.BrotliPopulationCost(&tmp) - candidate->bit_cost_);
}
}
static void BrotliCompareAndPushToQueue(
HistogramDistance *out_, uint *cluster_size, uint idx1,
uint idx2, size_t max_num_pairs, HistogramPair *pairs,
size_t *num_pairs)
{
bool is_good_pair = false;
HistogramPair p = new HistogramPair();
if (idx1 == idx2)
{
return;
}
if (idx2 < idx1)
{
uint t = idx2;
idx2 = idx1;
idx1 = t;
}
p.idx1 = idx1;
p.idx2 = idx2;
p.cost_diff = 0.5 * ClusterCostDiff(cluster_size[idx1], cluster_size[idx2]);
p.cost_diff -= out_[idx1].bit_cost_;
p.cost_diff -= out_[idx2].bit_cost_;
if (out_[idx1].total_count_ == 0)
{
p.cost_combo = out_[idx2].bit_cost_;
is_good_pair = true;
}
else if (out_[idx2].total_count_ == 0)
{
p.cost_combo = out_[idx1].bit_cost_;
is_good_pair = true;
}
else
{
double threshold = *num_pairs == 0 ? 1e99 : Math.Max(0.0, pairs[0].cost_diff);
HistogramDistance combo = out_[idx1];
double cost_combo;
HistogramDistance.HistogramAddHistogram(&combo, &out_[idx2]);
cost_combo = BitCostDistance.BrotliPopulationCost(&combo);
if (cost_combo < threshold - p.cost_diff)
{
p.cost_combo = cost_combo;
is_good_pair = true;
}
}
if (is_good_pair)
{
p.cost_diff += p.cost_combo;
if (*num_pairs > 0 && HistogramPairIsLess(&pairs[0], &p))
{
/* Replace the top of the queue if needed. */
if (*num_pairs < max_num_pairs)
{
pairs[*num_pairs] = pairs[0];
++(*num_pairs);
}
pairs[0] = p;
}
else if (*num_pairs < max_num_pairs)
{
pairs[*num_pairs] = p;
++(*num_pairs);
}
}
}
public static size_t BrotliHistogramCombine(HistogramDistance *out_,
uint *cluster_size,
uint *symbols,
uint *clusters,
HistogramPair *pairs,
size_t num_clusters,
size_t symbols_size,
size_t max_clusters,
size_t max_num_pairs)
{
double cost_diff_threshold = 0.0;
size_t min_cluster_size = 1;
size_t num_pairs = 0;
{
/* We maintain a vector of histogram pairs, with the property that the pair
* with the maximum bit cost reduction is the first. */
size_t idx1;
for (idx1 = 0; idx1 < num_clusters; ++idx1)
{
size_t idx2;
for (idx2 = idx1 + 1; idx2 < num_clusters; ++idx2)
{
BrotliCompareAndPushToQueue(out_, cluster_size, clusters[idx1],
clusters[idx2], max_num_pairs, &pairs[0], &num_pairs);
}
}
}
while (num_clusters > min_cluster_size)
{
uint best_idx1;
uint best_idx2;
size_t i;
if (pairs[0].cost_diff >= cost_diff_threshold)
{
cost_diff_threshold = 1e99;
min_cluster_size = max_clusters;
continue;
}
/* Take the best pair from the top of heap. */
best_idx1 = pairs[0].idx1;
best_idx2 = pairs[0].idx2;
HistogramDistance.HistogramAddHistogram(&out_[best_idx1], &out_[best_idx2]);
out_[best_idx1].bit_cost_ = pairs[0].cost_combo;
cluster_size[best_idx1] += cluster_size[best_idx2];
for (i = 0; i < symbols_size; ++i)
{
if (symbols[i] == best_idx2)
{
symbols[i] = best_idx1;
}
}
for (i = 0; i < num_clusters; ++i)
{
if (clusters[i] == best_idx2)
{
memmove(&clusters[i], &clusters[i + 1],
(num_clusters - i - 1) * sizeof(uint));
break;
}
}
--num_clusters;
{
/* Remove pairs intersecting the just combined best pair. */
size_t copy_to_idx = 0;
for (i = 0; i < num_pairs; ++i)
{
HistogramPair *p = &pairs[i];
if (p->idx1 == best_idx1 || p->idx2 == best_idx1 ||
p->idx1 == best_idx2 || p->idx2 == best_idx2)
{
/* Remove invalid pair from the queue. */
continue;
}
if (HistogramPairIsLess(&pairs[0], p))
{
/* Replace the top of the queue if needed. */
HistogramPair front = pairs[0];
pairs[0] = *p;
pairs[copy_to_idx] = front;
}
else
{
pairs[copy_to_idx] = *p;
}
++copy_to_idx;
}
num_pairs = copy_to_idx;
}
/* Push new pairs formed with the combined histogram to the heap. */
for (i = 0; i < num_clusters; ++i)
{
BrotliCompareAndPushToQueue(out_, cluster_size, best_idx1, clusters[i],
max_num_pairs, &pairs[0], &num_pairs);
}
}
return(num_clusters);
}
/* Does either of three things:
* (1) emits the current block with a new block type;
* (2) emits the current block with the type of the second last block;
* (3) merges the current block with the last block. */
public static unsafe void BlockSplitterFinishBlock(
BlockSplitterDistance *self, bool is_final)
{
BlockSplit * split = self->split_;
double * last_entropy = self->last_entropy_;
HistogramDistance *histograms = self->histograms_;
self->block_size_ =
Math.Max(self->block_size_, self->min_block_size_);
if (self->num_blocks_ == 0)
{
/* Create first block. */
split->lengths[0] = (uint)self->block_size_;
split->types[0] = 0;
last_entropy[0] =
BitsEntropy(histograms[0].data_, self->alphabet_size_);
last_entropy[1] = last_entropy[0];
++self->num_blocks_;
++split->num_types;
++self->curr_histogram_ix_;
if (self->curr_histogram_ix_ < *self->histograms_size_)
{
HistogramDistance.HistogramClear(&histograms[self->curr_histogram_ix_]);
}
self->block_size_ = 0;
}
else if (self->block_size_ > 0)
{
double entropy = BitsEntropy(histograms[self->curr_histogram_ix_].data_,
self->alphabet_size_);
HistogramDistance *combined_histo = stackalloc HistogramDistance[2];
double * combined_entropy = stackalloc double[2];
double * diff = stackalloc double[2];
size_t j;
for (j = 0; j < 2; ++j)
{
size_t last_histogram_ix = j == 0 ? self->last_histogram_ix_0 : self->last_histogram_ix_1;
combined_histo[j] = histograms[self->curr_histogram_ix_];
HistogramDistance.HistogramAddHistogram(&combined_histo[j],
&histograms[last_histogram_ix]);
combined_entropy[j] = BitsEntropy(
&combined_histo[j].data_[0], self->alphabet_size_);
diff[j] = combined_entropy[j] - entropy - last_entropy[j];
}
if (split->num_types < BROTLI_MAX_NUMBER_OF_BLOCK_TYPES &&
diff[0] > self->split_threshold_ &&
diff[1] > self->split_threshold_)
{
/* Create new block. */
split->lengths[self->num_blocks_] = (uint)self->block_size_;
split->types[self->num_blocks_] = (byte)split->num_types;
self->last_histogram_ix_1 = self->last_histogram_ix_0;
self->last_histogram_ix_0 = (byte)split->num_types;
last_entropy[1] = last_entropy[0];
last_entropy[0] = entropy;
++self->num_blocks_;
++split->num_types;
++self->curr_histogram_ix_;
if (self->curr_histogram_ix_ < *self->histograms_size_)
{
HistogramDistance.HistogramClear(&histograms[self->curr_histogram_ix_]);
}
self->block_size_ = 0;
self->merge_last_count_ = 0;
self->target_block_size_ = self->min_block_size_;
}
else if (diff[1] < diff[0] - 20.0)
{
/* Combine this block with second last block. */
split->lengths[self->num_blocks_] = (uint)self->block_size_;
split->types[self->num_blocks_] = split->types[self->num_blocks_ - 2];
size_t tmp = self->last_histogram_ix_0;
self->last_histogram_ix_0 = self->last_histogram_ix_1;
self->last_histogram_ix_1 = tmp;
histograms[self->last_histogram_ix_0] = combined_histo[1];
last_entropy[1] = last_entropy[0];
last_entropy[0] = combined_entropy[1];
++self->num_blocks_;
self->block_size_ = 0;
HistogramDistance.HistogramClear(&histograms[self->curr_histogram_ix_]);
self->merge_last_count_ = 0;
self->target_block_size_ = self->min_block_size_;
}
else
{
/* Combine this block with last block. */
split->lengths[self->num_blocks_ - 1] += (uint)self->block_size_;
histograms[self->last_histogram_ix_0] = combined_histo[0];
last_entropy[0] = combined_entropy[0];
if (split->num_types == 1)
{
last_entropy[1] = last_entropy[0];
}
self->block_size_ = 0;
HistogramDistance.HistogramClear(&histograms[self->curr_histogram_ix_]);
if (++self->merge_last_count_ > 1)
{
self->target_block_size_ += self->min_block_size_;
}
}
}
if (is_final)
{
*self->histograms_size_ = split->num_types;
split->num_blocks = self->num_blocks_;
}
}