diff --git a/lib/dictBuilder/cover.c b/lib/dictBuilder/cover.c index cc4b1337..117acbf7 100644 --- a/lib/dictBuilder/cover.c +++ b/lib/dictBuilder/cover.c @@ -382,7 +382,7 @@ static void COVER_group(COVER_ctx_t *ctx, const void *group, typedef struct { U32 begin; U32 end; - double score; + U32 score; } COVER_segment_t; /** @@ -627,9 +627,13 @@ static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs, /* 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 @@ -889,7 +893,7 @@ static void COVER_tryParameters(void *opaque) { 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], @@ -999,6 +1003,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( 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, dictBufferCapacity)) { DISPLAYLEVEL(1, "Cover parameters incorrect\n");