cover.c in zstd-ruby-1.3.2.0

- old
+ new

@@ -3,10 +3,11 @@
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
  * LICENSE file in the root directory of this source tree) and the GPLv2 (found
  * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
  */
 
 /* *****************************************************************************
  * Constructs a dictionary using a heuristic based on the following paper:
  *
@@ -380,11 +381,11 @@
  * A segment is a range in the source as well as the score of the segment.
  */
 typedef struct {
   U32 begin;
   U32 end;
-  double score;
+  U32 score;
 } COVER_segment_t;
 
 /**
  * Selects the best segment in an epoch.
  * Segments of are scored according to the function:
@@ -477,15 +478,20 @@
 
 /**
  * Check the validity of the parameters.
  * Returns non-zero if the parameters are valid and 0 otherwise.
  */
-static int COVER_checkParameters(ZDICT_cover_params_t parameters) {
+static int COVER_checkParameters(ZDICT_cover_params_t parameters,
+                                 size_t maxDictSize) {
   /* k and d are required parameters */
   if (parameters.d == 0 || parameters.k == 0) {
     return 0;
   }
+  /* k <= maxDictSize */
+  if (parameters.k > maxDictSize) {
+    return 0;
+  }
   /* d <= k */
   if (parameters.d > parameters.k) {
     return 0;
   }
   return 1;
@@ -620,13 +626,17 @@
     const U32 epochEnd = epochBegin + epochSize;
     size_t segmentSize;
     /* Select a segment */
     COVER_segment_t segment = COVER_selectSegment(
         ctx, freqs, activeDmers, epochBegin, epochEnd, parameters);
-    /* Trim the segment if necessary and if it is empty then we are done */
+    /* If the segment covers no dmers, then we are out of content */
+    if (segment.score == 0) {
+      break;
+    }
+    /* Trim the segment if necessary and if it is too small then we are done */
     segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
-    if (segmentSize == 0) {
+    if (segmentSize < parameters.d) {
       break;
     }
     /* We fill the dictionary from the back to allow the best segments to be
      * referenced with the smallest offsets.
      */
@@ -646,11 +656,11 @@
     ZDICT_cover_params_t parameters) {
   BYTE *const dict = (BYTE *)dictBuffer;
   COVER_ctx_t ctx;
   COVER_map_t activeDmers;
   /* Checks */
-  if (!COVER_checkParameters(parameters)) {
+  if (!COVER_checkParameters(parameters, dictBufferCapacity)) {
     DISPLAYLEVEL(1, "Cover parameters incorrect\n");
     return ERROR(GENERIC);
   }
   if (nbSamples == 0) {
     DISPLAYLEVEL(1, "Cover must have at least one input file\n");
@@ -699,12 +709,12 @@
  *
  * All of the methods except COVER_best_init() are thread safe if zstd is
  * compiled with multithreaded support.
  */
 typedef struct COVER_best_s {
-  pthread_mutex_t mutex;
-  pthread_cond_t cond;
+  ZSTD_pthread_mutex_t mutex;
+  ZSTD_pthread_cond_t cond;
   size_t liveJobs;
   void *dict;
   size_t dictSize;
   ZDICT_cover_params_t parameters;
   size_t compressedSize;
@@ -713,12 +723,12 @@
 /**
  * Initialize the `COVER_best_t`.
  */
 static void COVER_best_init(COVER_best_t *best) {
   if (best==NULL) return; /* compatible with init on NULL */
-  (void)pthread_mutex_init(&best->mutex, NULL);
-  (void)pthread_cond_init(&best->cond, NULL);
+  (void)ZSTD_pthread_mutex_init(&best->mutex, NULL);
+  (void)ZSTD_pthread_cond_init(&best->cond, NULL);
   best->liveJobs = 0;
   best->dict = NULL;
   best->dictSize = 0;
   best->compressedSize = (size_t)-1;
   memset(&best->parameters, 0, sizeof(best->parameters));
@@ -729,15 +739,15 @@
  */
 static void COVER_best_wait(COVER_best_t *best) {
   if (!best) {
     return;
   }
-  pthread_mutex_lock(&best->mutex);
+  ZSTD_pthread_mutex_lock(&best->mutex);
   while (best->liveJobs != 0) {
-    pthread_cond_wait(&best->cond, &best->mutex);
+    ZSTD_pthread_cond_wait(&best->cond, &best->mutex);
   }
-  pthread_mutex_unlock(&best->mutex);
+  ZSTD_pthread_mutex_unlock(&best->mutex);
 }
 
 /**
  * Call COVER_best_wait() and then destroy the COVER_best_t.
  */
@@ -747,25 +757,25 @@
   }
   COVER_best_wait(best);
   if (best->dict) {
     free(best->dict);
   }
-  pthread_mutex_destroy(&best->mutex);
-  pthread_cond_destroy(&best->cond);
+  ZSTD_pthread_mutex_destroy(&best->mutex);
+  ZSTD_pthread_cond_destroy(&best->cond);
 }
 
 /**
  * Called when a thread is about to be launched.
  * Increments liveJobs.
  */
 static void COVER_best_start(COVER_best_t *best) {
   if (!best) {
     return;
   }
-  pthread_mutex_lock(&best->mutex);
+  ZSTD_pthread_mutex_lock(&best->mutex);
   ++best->liveJobs;
-  pthread_mutex_unlock(&best->mutex);
+  ZSTD_pthread_mutex_unlock(&best->mutex);
 }
 
 /**
  * Called when a thread finishes executing, both on error or success.
  * Decrements liveJobs and signals any waiting threads if liveJobs == 0.
@@ -777,11 +787,11 @@
   if (!best) {
     return;
   }
   {
     size_t liveJobs;
-    pthread_mutex_lock(&best->mutex);
+    ZSTD_pthread_mutex_lock(&best->mutex);
     --best->liveJobs;
     liveJobs = best->liveJobs;
     /* If the new dictionary is better */
     if (compressedSize < best->compressedSize) {
       /* Allocate space if necessary */
@@ -800,13 +810,13 @@
       memcpy(best->dict, dict, dictSize);
       best->dictSize = dictSize;
       best->parameters = parameters;
       best->compressedSize = compressedSize;
     }
-    pthread_mutex_unlock(&best->mutex);
+    ZSTD_pthread_mutex_unlock(&best->mutex);
     if (liveJobs == 0) {
-      pthread_cond_broadcast(&best->cond);
+      ZSTD_pthread_cond_broadcast(&best->cond);
     }
   }
 }
 
 /**
@@ -882,11 +892,11 @@
                              parameters.zParams.compressionLevel);
     if (!dst || !cctx || !cdict) {
       goto _compressCleanup;
     }
     /* Compress each sample and sum their sizes (or error) */
-    totalCompressedSize = 0;
+    totalCompressedSize = dictBufferCapacity;
     for (i = 0; i < ctx->nbSamples; ++i) {
       const size_t size = ZSTD_compress_usingCDict(
           cctx, dst, dstCapacity, ctx->samples + ctx->offsets[i],
           ctx->samplesSizes[i], cdict);
       if (ZSTD_isError(size)) {
@@ -958,11 +968,11 @@
     }
   }
   /* Initialization */
   COVER_best_init(&best);
   /* Turn down global display level to clean up display at level 2 and below */
-  g_displayLevel = parameters->zParams.notificationLevel - 1;
+  g_displayLevel = displayLevel == 0 ? 0 : displayLevel - 1;
   /* Loop through d first because each new value needs a new context */
   LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n",
                     kIterations);
   for (d = kMinD; d <= kMaxD; d += 2) {
     /* Initialize the context for this value of d */
@@ -992,11 +1002,12 @@
       data->dictBufferCapacity = dictBufferCapacity;
       data->parameters = *parameters;
       data->parameters.k = k;
       data->parameters.d = d;
       data->parameters.steps = kSteps;
+      data->parameters.zParams.notificationLevel = g_displayLevel;
       /* Check the parameters */
-      if (!COVER_checkParameters(data->parameters)) {
+      if (!COVER_checkParameters(data->parameters, dictBufferCapacity)) {
         DISPLAYLEVEL(1, "Cover parameters incorrect\n");
         free(data);
         continue;
       }
       /* Call the function and pass ownership of data to it */