isomorfeus-ferret 0.12.6 → 0.13.1

data/ext/isomorfeus_ferret_ext/brotli_enc_backward_references_hq.h

@@ -0,0 +1,95 @@
+/* Copyright 2013 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* Function to find backward reference copies. */
+
+#ifndef BROTLI_ENC_BACKWARD_REFERENCES_HQ_H_
+#define BROTLI_ENC_BACKWARD_REFERENCES_HQ_H_
+
+#include "brotli_common_constants.h"
+#include "brotli_common_context.h"
+#include "brotli_common_dictionary.h"
+#include "brotli_common_platform.h"
+#include "brotli_types.h"
+#include "brotli_enc_command.h"
+#include "brotli_enc_hash.h"
+#include "brotli_enc_memory.h"
+#include "brotli_enc_quality.h"
+
+#if defined(__cplusplus) || defined(c_plusplus)
+extern "C" {
+#endif
+
+BROTLI_INTERNAL void BrotliCreateZopfliBackwardReferences(MemoryManager* m,
+    size_t num_bytes,
+    size_t position, const uint8_t* ringbuffer, size_t ringbuffer_mask,
+    ContextLut literal_context_lut, const BrotliEncoderParams* params,
+    Hasher* hasher, int* dist_cache, size_t* last_insert_len,
+    Command* commands, size_t* num_commands, size_t* num_literals);
+
+BROTLI_INTERNAL void BrotliCreateHqZopfliBackwardReferences(MemoryManager* m,
+    size_t num_bytes,
+    size_t position, const uint8_t* ringbuffer, size_t ringbuffer_mask,
+    ContextLut literal_context_lut, const BrotliEncoderParams* params,
+    Hasher* hasher, int* dist_cache, size_t* last_insert_len,
+    Command* commands, size_t* num_commands, size_t* num_literals);
+
+typedef struct ZopfliNode {
+  /* Best length to get up to this byte (not including this byte itself)
+     highest 7 bit is used to reconstruct the length code. */
+  uint32_t length;
+  /* Distance associated with the length. */
+  uint32_t distance;
+  /* Number of literal inserts before this copy; highest 5 bits contain
+     distance short code + 1 (or zero if no short code). */
+  uint32_t dcode_insert_length;
+
+  /* This union holds information used by dynamic-programming. During forward
+     pass |cost| it used to store the goal function. When node is processed its
+     |cost| is invalidated in favor of |shortcut|. On path back-tracing pass
+     |next| is assigned the offset to next node on the path. */
+  union {
+    /* Smallest cost to get to this byte from the beginning, as found so far. */
+    float cost;
+    /* Offset to the next node on the path. Equals to command_length() of the
+       next node on the path. For last node equals to BROTLI_UINT32_MAX */
+    uint32_t next;
+    /* Node position that provides next distance for distance cache. */
+    uint32_t shortcut;
+  } u;
+} ZopfliNode;
+
+BROTLI_INTERNAL void BrotliInitZopfliNodes(ZopfliNode* array, size_t length);
+
+/* Computes the shortest path of commands from position to at most
+   position + num_bytes.
+
+   On return, path->size() is the number of commands found and path[i] is the
+   length of the i-th command (copy length plus insert length).
+   Note that the sum of the lengths of all commands can be less than num_bytes.
+
+   On return, the nodes[0..num_bytes] array will have the following
+   "ZopfliNode array invariant":
+   For each i in [1..num_bytes], if nodes[i].cost < kInfinity, then
+     (1) nodes[i].copy_length() >= 2
+     (2) nodes[i].command_length() <= i and
+     (3) nodes[i - nodes[i].command_length()].cost < kInfinity */
+BROTLI_INTERNAL size_t BrotliZopfliComputeShortestPath(
+    MemoryManager* m, size_t num_bytes,
+    size_t position, const uint8_t* ringbuffer, size_t ringbuffer_mask,
+    ContextLut literal_context_lut, const BrotliEncoderParams* params,
+    const int* dist_cache, Hasher* hasher, ZopfliNode* nodes);
+
+BROTLI_INTERNAL void BrotliZopfliCreateCommands(
+    const size_t num_bytes, const size_t block_start, const ZopfliNode* nodes,
+    int* dist_cache, size_t* last_insert_len, const BrotliEncoderParams* params,
+    Command* commands, size_t* num_literals);
+
+#if defined(__cplusplus) || defined(c_plusplus)
+}  /* extern "C" */
+#endif
+
+#endif  /* BROTLI_ENC_BACKWARD_REFERENCES_HQ_H_ */

data/ext/isomorfeus_ferret_ext/brotli_enc_backward_references_inc.h

@@ -0,0 +1,163 @@
+/* NOLINT(build/header_guard) */
+/* Copyright 2013 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* template parameters: EXPORT_FN, FN */
+
+static BROTLI_NOINLINE void EXPORT_FN(CreateBackwardReferences)(
+    size_t num_bytes, size_t position,
+    const uint8_t* ringbuffer, size_t ringbuffer_mask,
+    ContextLut literal_context_lut, const BrotliEncoderParams* params,
+    Hasher* hasher, int* dist_cache, size_t* last_insert_len,
+    Command* commands, size_t* num_commands, size_t* num_literals) {
+  HASHER()* privat = &hasher->privat.FN(_);
+  /* Set maximum distance, see section 9.1. of the spec. */
+  const size_t max_backward_limit = BROTLI_MAX_BACKWARD_LIMIT(params->lgwin);
+  const size_t position_offset = params->stream_offset;
+
+  const Command* const orig_commands = commands;
+  size_t insert_length = *last_insert_len;
+  const size_t pos_end = position + num_bytes;
+  const size_t store_end = num_bytes >= FN(StoreLookahead)() ?
+      position + num_bytes - FN(StoreLookahead)() + 1 : position;
+
+  /* For speed up heuristics for random data. */
+  const size_t random_heuristics_window_size =
+      LiteralSpreeLengthForSparseSearch(params);
+  size_t apply_random_heuristics = position + random_heuristics_window_size;
+  const size_t gap = 0;
+
+  /* Minimum score to accept a backward reference. */
+  const score_t kMinScore = BROTLI_SCORE_BASE + 100;
+
+  BROTLI_UNUSED(literal_context_lut);
+
+  FN(PrepareDistanceCache)(privat, dist_cache);
+
+  while (position + FN(HashTypeLength)() < pos_end) {
+    size_t max_length = pos_end - position;
+    size_t max_distance = BROTLI_MIN(size_t, position, max_backward_limit);
+    size_t dictionary_start = BROTLI_MIN(size_t,
+        position + position_offset, max_backward_limit);
+    HasherSearchResult sr;
+    sr.len = 0;
+    sr.len_code_delta = 0;
+    sr.distance = 0;
+    sr.score = kMinScore;
+    FN(FindLongestMatch)(privat, &params->dictionary,
+        ringbuffer, ringbuffer_mask, dist_cache, position, max_length,
+        max_distance, dictionary_start + gap, params->dist.max_distance, &sr);
+    if (sr.score > kMinScore) {
+      /* Found a match. Let's look for something even better ahead. */
+      int delayed_backward_references_in_row = 0;
+      --max_length;
+      for (;; --max_length) {
+        const score_t cost_diff_lazy = 175;
+        HasherSearchResult sr2;
+        sr2.len = params->quality < MIN_QUALITY_FOR_EXTENSIVE_REFERENCE_SEARCH ?
+            BROTLI_MIN(size_t, sr.len - 1, max_length) : 0;
+        sr2.len_code_delta = 0;
+        sr2.distance = 0;
+        sr2.score = kMinScore;
+        max_distance = BROTLI_MIN(size_t, position + 1, max_backward_limit);
+        dictionary_start = BROTLI_MIN(size_t,
+            position + 1 + position_offset, max_backward_limit);
+        FN(FindLongestMatch)(privat,
+            &params->dictionary,
+            ringbuffer, ringbuffer_mask, dist_cache, position + 1, max_length,
+            max_distance, dictionary_start + gap, params->dist.max_distance,
+            &sr2);
+        if (sr2.score >= sr.score + cost_diff_lazy) {
+          /* Ok, let's just write one byte for now and start a match from the
+             next byte. */
+          ++position;
+          ++insert_length;
+          sr = sr2;
+          if (++delayed_backward_references_in_row < 4 &&
+              position + FN(HashTypeLength)() < pos_end) {
+            continue;
+          }
+        }
+        break;
+      }
+      apply_random_heuristics =
+          position + 2 * sr.len + random_heuristics_window_size;
+      dictionary_start = BROTLI_MIN(size_t,
+          position + position_offset, max_backward_limit);
+      {
+        /* The first 16 codes are special short-codes,
+           and the minimum offset is 1. */
+        size_t distance_code = ComputeDistanceCode(
+            sr.distance, dictionary_start + gap, dist_cache);
+        if ((sr.distance <= (dictionary_start + gap)) && distance_code > 0) {
+          dist_cache[3] = dist_cache[2];
+          dist_cache[2] = dist_cache[1];
+          dist_cache[1] = dist_cache[0];
+          dist_cache[0] = (int)sr.distance;
+          FN(PrepareDistanceCache)(privat, dist_cache);
+        }
+        InitCommand(commands++, &params->dist, insert_length,
+            sr.len, sr.len_code_delta, distance_code);
+      }
+      *num_literals += insert_length;
+      insert_length = 0;
+      /* Put the hash keys into the table, if there are enough bytes left.
+         Depending on the hasher implementation, it can push all positions
+         in the given range or only a subset of them.
+         Avoid hash poisoning with RLE data. */
+      {
+        size_t range_start = position + 2;
+        size_t range_end = BROTLI_MIN(size_t, position + sr.len, store_end);
+        if (sr.distance < (sr.len >> 2)) {
+          range_start = BROTLI_MIN(size_t, range_end, BROTLI_MAX(size_t,
+              range_start, position + sr.len - (sr.distance << 2)));
+        }
+        FN(StoreRange)(privat, ringbuffer, ringbuffer_mask, range_start,
+                       range_end);
+      }
+      position += sr.len;
+    } else {
+      ++insert_length;
+      ++position;
+      /* If we have not seen matches for a long time, we can skip some
+         match lookups. Unsuccessful match lookups are very very expensive
+         and this kind of a heuristic speeds up compression quite
+         a lot. */
+      if (position > apply_random_heuristics) {
+        /* Going through uncompressible data, jump. */
+        if (position >
+            apply_random_heuristics + 4 * random_heuristics_window_size) {
+          /* It is quite a long time since we saw a copy, so we assume
+             that this data is not compressible, and store hashes less
+             often. Hashes of non compressible data are less likely to
+             turn out to be useful in the future, too, so we store less of
+             them to not to flood out the hash table of good compressible
+             data. */
+          const size_t kMargin =
+              BROTLI_MAX(size_t, FN(StoreLookahead)() - 1, 4);
+          size_t pos_jump =
+              BROTLI_MIN(size_t, position + 16, pos_end - kMargin);
+          for (; position < pos_jump; position += 4) {
+            FN(Store)(privat, ringbuffer, ringbuffer_mask, position);
+            insert_length += 4;
+          }
+        } else {
+          const size_t kMargin =
+              BROTLI_MAX(size_t, FN(StoreLookahead)() - 1, 2);
+          size_t pos_jump =
+              BROTLI_MIN(size_t, position + 8, pos_end - kMargin);
+          for (; position < pos_jump; position += 2) {
+            FN(Store)(privat, ringbuffer, ringbuffer_mask, position);
+            insert_length += 2;
+          }
+        }
+      }
+    }
+  }
+  insert_length += pos_end - position;
+  *last_insert_len = insert_length;
+  *num_commands += (size_t)(commands - orig_commands);
+}

data/ext/isomorfeus_ferret_ext/brotli_enc_bit_cost.c

@@ -0,0 +1,35 @@
+/* Copyright 2013 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* Functions to estimate the bit cost of Huffman trees. */
+
+#include "brotli_enc_bit_cost.h"
+
+#include "brotli_common_constants.h"
+#include "brotli_common_platform.h"
+#include "brotli_types.h"
+#include "brotli_enc_fast_log.h"
+#include "brotli_enc_histogram.h"
+
+#if defined(__cplusplus) || defined(c_plusplus)
+extern "C" {
+#endif
+
+#define FN(X) X ## Literal
+#include "brotli_enc_bit_cost_inc.h"  /* NOLINT(build/include) */
+#undef FN
+
+#define FN(X) X ## Command
+#include "brotli_enc_bit_cost_inc.h"  /* NOLINT(build/include) */
+#undef FN
+
+#define FN(X) X ## Distance
+#include "brotli_enc_bit_cost_inc.h"  /* NOLINT(build/include) */
+#undef FN
+
+#if defined(__cplusplus) || defined(c_plusplus)
+}  /* extern "C" */
+#endif

data/ext/isomorfeus_ferret_ext/brotli_enc_bit_cost.h

@@ -0,0 +1,63 @@
+/* Copyright 2013 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* Functions to estimate the bit cost of Huffman trees. */
+
+#ifndef BROTLI_ENC_BIT_COST_H_
+#define BROTLI_ENC_BIT_COST_H_
+
+#include "brotli_common_platform.h"
+#include "brotli_types.h"
+#include "brotli_enc_fast_log.h"
+#include "brotli_enc_histogram.h"
+
+#if defined(__cplusplus) || defined(c_plusplus)
+extern "C" {
+#endif
+
+static BROTLI_INLINE double ShannonEntropy(
+    const uint32_t* population, size_t size, size_t* total) {
+  size_t sum = 0;
+  double retval = 0;
+  const uint32_t* population_end = population + size;
+  size_t p;
+  if (size & 1) {
+    goto odd_number_of_elements_left;
+  }
+  while (population < population_end) {
+    p = *population++;
+    sum += p;
+    retval -= (double)p * FastLog2(p);
+ odd_number_of_elements_left:
+    p = *population++;
+    sum += p;
+    retval -= (double)p * FastLog2(p);
+  }
+  if (sum) retval += (double)sum * FastLog2(sum);
+  *total = sum;
+  return retval;
+}
+
+static BROTLI_INLINE double BitsEntropy(
+    const uint32_t* population, size_t size) {
+  size_t sum;
+  double retval = ShannonEntropy(population, size, &sum);
+  if (retval < sum) {
+    /* At least one bit per literal is needed. */
+    retval = (double)sum;
+  }
+  return retval;
+}
+
+BROTLI_INTERNAL double BrotliPopulationCostLiteral(const HistogramLiteral*);
+BROTLI_INTERNAL double BrotliPopulationCostCommand(const HistogramCommand*);
+BROTLI_INTERNAL double BrotliPopulationCostDistance(const HistogramDistance*);
+
+#if defined(__cplusplus) || defined(c_plusplus)
+}  /* extern "C" */
+#endif
+
+#endif  /* BROTLI_ENC_BIT_COST_H_ */

data/ext/isomorfeus_ferret_ext/brotli_enc_bit_cost_inc.h

@@ -0,0 +1,127 @@
+/* NOLINT(build/header_guard) */
+/* Copyright 2013 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* template parameters: FN */
+
+#define HistogramType FN(Histogram)
+
+double FN(BrotliPopulationCost)(const HistogramType* histogram) {
+  static const double kOneSymbolHistogramCost = 12;
+  static const double kTwoSymbolHistogramCost = 20;
+  static const double kThreeSymbolHistogramCost = 28;
+  static const double kFourSymbolHistogramCost = 37;
+  const size_t data_size = FN(HistogramDataSize)();
+  int count = 0;
+  size_t s[5];
+  double bits = 0.0;
+  size_t i;
+  if (histogram->total_count_ == 0) {
+    return kOneSymbolHistogramCost;
+  }
+  for (i = 0; i < data_size; ++i) {
+    if (histogram->data_[i] > 0) {
+      s[count] = i;
+      ++count;
+      if (count > 4) break;
+    }
+  }
+  if (count == 1) {
+    return kOneSymbolHistogramCost;
+  }
+  if (count == 2) {
+    return (kTwoSymbolHistogramCost + (double)histogram->total_count_);
+  }
+  if (count == 3) {
+    const uint32_t histo0 = histogram->data_[s[0]];
+    const uint32_t histo1 = histogram->data_[s[1]];
+    const uint32_t histo2 = histogram->data_[s[2]];
+    const uint32_t histomax =
+        BROTLI_MAX(uint32_t, histo0, BROTLI_MAX(uint32_t, histo1, histo2));
+    return (kThreeSymbolHistogramCost +
+            2 * (histo0 + histo1 + histo2) - histomax);
+  }
+  if (count == 4) {
+    uint32_t histo[4];
+    uint32_t h23;
+    uint32_t histomax;
+    for (i = 0; i < 4; ++i) {
+      histo[i] = histogram->data_[s[i]];
+    }
+    /* Sort */
+    for (i = 0; i < 4; ++i) {
+      size_t j;
+      for (j = i + 1; j < 4; ++j) {
+        if (histo[j] > histo[i]) {
+          BROTLI_SWAP(uint32_t, histo, j, i);
+        }
+      }
+    }
+    h23 = histo[2] + histo[3];
+    histomax = BROTLI_MAX(uint32_t, h23, histo[0]);
+    return (kFourSymbolHistogramCost +
+            3 * h23 + 2 * (histo[0] + histo[1]) - histomax);
+  }
+
+  {
+    /* In this loop we compute the entropy of the histogram and simultaneously
+       build a simplified histogram of the code length codes where we use the
+       zero repeat code 17, but we don't use the non-zero repeat code 16. */
+    size_t max_depth = 1;
+    uint32_t depth_histo[BROTLI_CODE_LENGTH_CODES] = { 0 };
+    const double log2total = FastLog2(histogram->total_count_);
+    for (i = 0; i < data_size;) {
+      if (histogram->data_[i] > 0) {
+        /* Compute -log2(P(symbol)) = -log2(count(symbol)/total_count) =
+                                    = log2(total_count) - log2(count(symbol)) */
+        double log2p = log2total - FastLog2(histogram->data_[i]);
+        /* Approximate the bit depth by round(-log2(P(symbol))) */
+        size_t depth = (size_t)(log2p + 0.5);
+        bits += histogram->data_[i] * log2p;
+        if (depth > 15) {
+          depth = 15;
+        }
+        if (depth > max_depth) {
+          max_depth = depth;
+        }
+        ++depth_histo[depth];
+        ++i;
+      } else {
+        /* Compute the run length of zeros and add the appropriate number of 0
+           and 17 code length codes to the code length code histogram. */
+        uint32_t reps = 1;
+        size_t k;
+        for (k = i + 1; k < data_size && histogram->data_[k] == 0; ++k) {
+          ++reps;
+        }
+        i += reps;
+        if (i == data_size) {
+          /* Don't add any cost for the last zero run, since these are encoded
+             only implicitly. */
+          break;
+        }
+        if (reps < 3) {
+          depth_histo[0] += reps;
+        } else {
+          reps -= 2;
+          while (reps > 0) {
+            ++depth_histo[BROTLI_REPEAT_ZERO_CODE_LENGTH];
+            /* Add the 3 extra bits for the 17 code length code. */
+            bits += 3;
+            reps >>= 3;
+          }
+        }
+      }
+    }
+    /* Add the estimated encoding cost of the code length code histogram. */
+    bits += (double)(18 + 2 * max_depth);
+    /* Add the entropy of the code length code histogram. */
+    bits += BitsEntropy(depth_histo, BROTLI_CODE_LENGTH_CODES);
+  }
+  return bits;
+}
+
+#undef HistogramType

data/ext/isomorfeus_ferret_ext/brotli_enc_block_encoder_inc.h

@@ -0,0 +1,34 @@
+/* NOLINT(build/header_guard) */
+/* Copyright 2014 Google Inc. All Rights Reserved.
+
+   Distributed under MIT license.
+   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
+*/
+
+/* template parameters: FN */
+
+#define HistogramType FN(Histogram)
+
+/* Creates entropy codes for all block types and stores them to the bit
+   stream. */
+static void FN(BuildAndStoreEntropyCodes)(MemoryManager* m, BlockEncoder* self,
+    const HistogramType* histograms, const size_t histograms_size,
+    const size_t alphabet_size, HuffmanTree* tree,
+    size_t* storage_ix, uint8_t* storage) {
+  const size_t table_size = histograms_size * self->histogram_length_;
+  self->depths_ = BROTLI_ALLOC(m, uint8_t, table_size);
+  self->bits_ = BROTLI_ALLOC(m, uint16_t, table_size);
+  if (BROTLI_IS_OOM(m)) return;
+
+  {
+    size_t i;
+    for (i = 0; i < histograms_size; ++i) {
+      size_t ix = i * self->histogram_length_;
+      BuildAndStoreHuffmanTree(&histograms[i].data_[0], self->histogram_length_,
+          alphabet_size, tree, &self->depths_[ix], &self->bits_[ix],
+          storage_ix, storage);
+    }
+  }
+}
+
+#undef HistogramType