fix sequence compression API in Explicit Delimiter mode

lib/common/error_private.c

@@ -27,7 +27,7 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(version_unsupported): return "Version not supported";
     case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
     case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
-    case PREFIX(corruption_detected): return "Corrupted block detected";
+    case PREFIX(corruption_detected): return "Input corruption detected";
     case PREFIX(checksum_wrong): return "Restored data doesn't match checksum";
     case PREFIX(parameter_unsupported): return "Unsupported parameter";
     case PREFIX(parameter_outOfBound): return "Parameter is out of bound";

lib/compress/zstd_compress.c

@@ -5752,9 +5752,9 @@ size_t ZSTD_compress2(ZSTD_CCtx* cctx,
 }
 
 typedef struct {
-    U32 idx;             /* Index in array of ZSTD_Sequence */
-    U32 posInSequence;   /* Position within sequence at idx */
-    size_t posInSrc;        /* Number of bytes given by sequences provided so far */
+    U32 idx;            /* Index in array of ZSTD_Sequence */
+    U32 posInSequence;  /* Position within sequence at idx */
+    size_t posInSrc;    /* Number of bytes given by sequences provided so far */
 } ZSTD_sequencePosition;
 
 /* ZSTD_validateSequence() :
@@ -5809,6 +5809,8 @@ ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx,
     repcodes_t updatedRepcodes;
     U32 dictSize;
 
+    DEBUGLOG(5, "ZSTD_copySequencesToSeqStoreExplicitBlockDelim (blockSize = %zu)", blockSize);
+
     if (cctx->cdict) {
         dictSize = (U32)cctx->cdict->dictContentSize;
     } else if (cctx->prefixDict.dict) {
@@ -5995,6 +5997,56 @@ static ZSTD_sequenceCopier ZSTD_selectSequenceCopier(ZSTD_sequenceFormat_e mode)
     return sequenceCopier;
 }
 
+/* Discover the size of next by searching for the block delimiter.
+ * Note that a block delimiter must exist in this mode,
+ * otherwise it's an input error.
+ * The value retrieved will be later compared to ensure it remains within bounds */
+static size_t
+blockSize_explicitDelimiter(const ZSTD_Sequence* inSeqs, size_t inSeqsSize, ZSTD_sequencePosition seqPos)
+{
+    int end = 0;
+    size_t blockSize = 0;
+    size_t spos = seqPos.idx;
+    assert(spos <= inSeqsSize);
+    while (spos < inSeqsSize) {
+        end = (inSeqs[spos].offset == 0);
+        blockSize += inSeqs[spos].litLength + inSeqs[spos].matchLength;
+        if (end) {
+            if (inSeqs[spos].matchLength != 0)
+                RETURN_ERROR(corruption_detected, "delimiter format error : both matchlength and offset must be == 0");
+            break;
+        }
+        spos++;
+    }
+    if (!end)
+        RETURN_ERROR(corruption_detected, "Reached end of sequences without finding a block delimiter");
+    return blockSize;
+}
+
+/* More a "target" block size */
+static size_t blockSize_noDelimiter(size_t blockSize, size_t remaining)
+{
+    int const lastBlock = (remaining <= blockSize);
+    return lastBlock ? remaining : blockSize;
+}
+
+static size_t determine_blockSize(ZSTD_sequenceFormat_e mode,
+                           size_t blockSize, size_t remaining,
+                     const ZSTD_Sequence* inSeqs, size_t inSeqsSize, ZSTD_sequencePosition seqPos)
+{
+    DEBUGLOG(6, "determine_blockSize : remainingSize = %zu", remaining);
+    if (mode == ZSTD_sf_noBlockDelimiters)
+        return blockSize_noDelimiter(blockSize, remaining);
+    {   size_t const explicitBlockSize = blockSize_explicitDelimiter(inSeqs, inSeqsSize, seqPos);
+        FORWARD_IF_ERROR(explicitBlockSize, "Error while determining block size with explicit delimiters");
+        if (explicitBlockSize > blockSize)
+            RETURN_ERROR(corruption_detected, "sequences incorrectly define a too large block");
+        if (explicitBlockSize > remaining)
+            RETURN_ERROR(srcSize_wrong, "sequences define a frame longer than source");
+        return explicitBlockSize;
+    }
+}
+
 /* Compress, block-by-block, all of the sequences given.
  *
  * Returns the cumulative size of all compressed blocks (including their headers),
@@ -6007,9 +6059,6 @@ ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
                           const void* src, size_t srcSize)
 {
     size_t cSize = 0;
-    U32 lastBlock;
-    size_t blockSize;
-    size_t compressedSeqsSize;
     size_t remaining = srcSize;
     ZSTD_sequencePosition seqPos = {0, 0, 0};
 
@@ -6029,10 +6078,15 @@ ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
     }
 
     while (remaining) {
+        size_t compressedSeqsSize;
         size_t cBlockSize;
         size_t additionalByteAdjustment;
-        lastBlock = remaining <= cctx->blockSize;
-        blockSize = lastBlock ? (U32)remaining : (U32)cctx->blockSize;
+        size_t blockSize = determine_blockSize(cctx->appliedParams.blockDelimiters,
+                                        cctx->blockSize, remaining,
+                                        inSeqs, inSeqsSize, seqPos);
+        U32 const lastBlock = (blockSize == remaining);
+        assert(blockSize <= remaining);
+        FORWARD_IF_ERROR(blockSize, "Error while trying to determine block size");
         ZSTD_resetSeqStore(&cctx->seqStore);
         DEBUGLOG(4, "Working on new block. Blocksize: %zu", blockSize);
 
@@ -6113,7 +6167,8 @@ ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
     return cSize;
 }
 
-size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstCapacity,
+size_t ZSTD_compressSequences(ZSTD_CCtx* cctx,
+                              void* dst, size_t dstCapacity,
                               const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
                               const void* src, size_t srcSize)
 {

lib/zstd.h

@@ -1375,23 +1375,25 @@ typedef enum {
 } ZSTD_sequenceFormat_e;
 
 /*! ZSTD_generateSequences() :
- * Generate sequences using ZSTD_compress2, given a source buffer.
+ * Generate sequences using ZSTD_compress2(), given a source buffer.
  *
  * Each block will end with a dummy sequence
  * with offset == 0, matchLength == 0, and litLength == length of last literals.
  * litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0)
  * simply acts as a block delimiter.
  *
- * zc can be used to insert custom compression params.
- * This function invokes ZSTD_compress2
+ * @zc can be used to insert custom compression params.
+ * This function invokes ZSTD_compress2().
  *
  * The output of this function can be fed into ZSTD_compressSequences() with CCtx
  * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters
  * @return : number of sequences generated
  */
 
-ZSTDLIB_STATIC_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs,
-                                          size_t outSeqsSize, const void* src, size_t srcSize);
+ZSTDLIB_STATIC_API size_t
+ZSTD_generateSequences( ZSTD_CCtx* zc,
+                        ZSTD_Sequence* outSeqs, size_t outSeqsSize,
+                        const void* src, size_t srcSize);
 
 /*! ZSTD_mergeBlockDelimiters() :
  * Given an array of ZSTD_Sequence, remove all sequences that represent block delimiters/last literals
@@ -1432,11 +1434,12 @@ ZSTDLIB_STATIC_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, si
  * Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused.
  * Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly,
  *         and cannot emit an RLE block that disagrees with the repcode history
- * @return : final compressed size or a ZSTD error.
+ * @return : final compressed size, or a ZSTD error code.
  */
-ZSTDLIB_STATIC_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstSize,
-                                  const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
-                                  const void* src, size_t srcSize);
+ZSTDLIB_STATIC_API size_t
+ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
+                        const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+                        const void* src, size_t srcSize);
 
 
 /*! ZSTD_writeSkippableFrame() :