move Sequences definition to zstd_compress_internal.h

they should not be in common/zstd_internal.h,
since these definitions are not shared beyond lib/compress/.

build/single_file_libs/examples/zstd_errors.h

@@ -0,0 +1,106 @@
+/*
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ * 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.
+ */
+
+#ifndef ZSTD_ERRORS_H_398273423
+#define ZSTD_ERRORS_H_398273423
+
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+/* =====   ZSTDERRORLIB_API : control library symbols visibility   ===== */
+#ifndef ZSTDERRORLIB_VISIBLE
+   /* Backwards compatibility with old macro name */
+#  ifdef ZSTDERRORLIB_VISIBILITY
+#    define ZSTDERRORLIB_VISIBLE ZSTDERRORLIB_VISIBILITY
+#  elif defined(__GNUC__) && (__GNUC__ >= 4) && !defined(__MINGW32__)
+#    define ZSTDERRORLIB_VISIBLE __attribute__ ((visibility ("default")))
+#  else
+#    define ZSTDERRORLIB_VISIBLE
+#  endif
+#endif
+
+#ifndef ZSTDERRORLIB_HIDDEN
+#  if defined(__GNUC__) && (__GNUC__ >= 4) && !defined(__MINGW32__)
+#    define ZSTDERRORLIB_HIDDEN __attribute__ ((visibility ("hidden")))
+#  else
+#    define ZSTDERRORLIB_HIDDEN
+#  endif
+#endif
+
+#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
+#  define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBLE
+#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1)
+#  define ZSTDERRORLIB_API __declspec(dllimport) ZSTDERRORLIB_VISIBLE /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+#  define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBLE
+#endif
+
+/*-*********************************************
+ *  Error codes list
+ *-*********************************************
+ *  Error codes _values_ are pinned down since v1.3.1 only.
+ *  Therefore, don't rely on values if you may link to any version < v1.3.1.
+ *
+ *  Only values < 100 are considered stable.
+ *
+ *  note 1 : this API shall be used with static linking only.
+ *           dynamic linking is not yet officially supported.
+ *  note 2 : Prefer relying on the enum than on its value whenever possible
+ *           This is the only supported way to use the error list < v1.3.1
+ *  note 3 : ZSTD_isError() is always correct, whatever the library version.
+ **********************************************/
+typedef enum {
+  ZSTD_error_no_error = 0,
+  ZSTD_error_GENERIC  = 1,
+  ZSTD_error_prefix_unknown                = 10,
+  ZSTD_error_version_unsupported           = 12,
+  ZSTD_error_frameParameter_unsupported    = 14,
+  ZSTD_error_frameParameter_windowTooLarge = 16,
+  ZSTD_error_corruption_detected = 20,
+  ZSTD_error_checksum_wrong      = 22,
+  ZSTD_error_literals_headerWrong = 24,
+  ZSTD_error_dictionary_corrupted      = 30,
+  ZSTD_error_dictionary_wrong          = 32,
+  ZSTD_error_dictionaryCreation_failed = 34,
+  ZSTD_error_parameter_unsupported   = 40,
+  ZSTD_error_parameter_combination_unsupported = 41,
+  ZSTD_error_parameter_outOfBound    = 42,
+  ZSTD_error_tableLog_tooLarge       = 44,
+  ZSTD_error_maxSymbolValue_tooLarge = 46,
+  ZSTD_error_maxSymbolValue_tooSmall = 48,
+  ZSTD_error_stabilityCondition_notRespected = 50,
+  ZSTD_error_stage_wrong       = 60,
+  ZSTD_error_init_missing      = 62,
+  ZSTD_error_memory_allocation = 64,
+  ZSTD_error_workSpace_tooSmall= 66,
+  ZSTD_error_dstSize_tooSmall = 70,
+  ZSTD_error_srcSize_wrong    = 72,
+  ZSTD_error_dstBuffer_null   = 74,
+  ZSTD_error_noForwardProgress_destFull = 80,
+  ZSTD_error_noForwardProgress_inputEmpty = 82,
+  /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */
+  ZSTD_error_frameIndex_tooLarge = 100,
+  ZSTD_error_seekableIO          = 102,
+  ZSTD_error_dstBuffer_wrong     = 104,
+  ZSTD_error_srcBuffer_wrong     = 105,
+  ZSTD_error_sequenceProducer_failed = 106,
+  ZSTD_error_externalSequences_invalid = 107,
+  ZSTD_error_maxCode = 120  /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */
+} ZSTD_ErrorCode;
+
+ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code);   /**< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */
+
+
+#if defined (__cplusplus)
+}
+#endif
+
+#endif /* ZSTD_ERRORS_H_398273423 */

doc/zstd_manual.html

@@ -154,7 +154,7 @@ size_t ZSTD_compressBound(size_t srcSize); </b>/*!< maximum compressed size in w
  it's recommended to provide @dstCapacity >= ZSTD_compressBound(srcSize)
  as it eliminates one potential failure scenario,
  aka not enough room in dst buffer to write the compressed frame.
- Note : ZSTD_compressBound() itself can fail, if @srcSize > ZSTD_MAX_INPUT_SIZE .
+ Note : ZSTD_compressBound() itself can fail, if @srcSize >= ZSTD_MAX_INPUT_SIZE .
         In which case, ZSTD_compressBound() will return an error code
         which can be tested using ZSTD_isError().
 
@@ -1410,6 +1410,20 @@ ZSTD_compressSequences( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
  
 </p></pre><BR>
 
+<pre><b>ZSTDLIB_STATIC_API size_t
+ZSTD_compressSequencesAndLiterals( ZSTD_CCtx* cctx, void* dst, size_t dstSize,
+            const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+            const void* literals, size_t litSize);
+</b><p> This is a variant of ZSTD_compressSequences() which,
+ instead of receiving (src,srcSize) as input parameter, receives (literals,litSize),
+ aka all literals already extracted and grouped into a single continuous buffer.
+ This can be useful if the process generating the sequences also happens to generate the buffer of literals,
+ thus skipping an extraction + caching stage.
+ To be valid, `litSize` must be equal to the sum of all @.litLength fields in @inSeqs.
+ @return : final compressed size, or a ZSTD error code.
+ 
+</p></pre><BR>
+
 <pre><b>ZSTDLIB_STATIC_API size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity,
                                 const void* src, size_t srcSize, unsigned magicVariant);
 </b><p> Generates a zstd skippable frame containing data given by src, and writes it to dst buffer.

lib/common/zstd_internal.h

@@ -278,62 +278,6 @@ typedef enum {
 /*-*******************************************
 *  Private declarations
 *********************************************/
-typedef struct seqDef_s {
-    U32 offBase;   /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */
-    U16 litLength;
-    U16 mlBase;    /* mlBase == matchLength - MINMATCH */
-} seqDef;
-
-/* Controls whether seqStore has a single "long" litLength or matchLength. See seqStore_t. */
-typedef enum {
-    ZSTD_llt_none = 0,             /* no longLengthType */
-    ZSTD_llt_literalLength = 1,    /* represents a long literal */
-    ZSTD_llt_matchLength = 2       /* represents a long match */
-} ZSTD_longLengthType_e;
-
-typedef struct {
-    seqDef* sequencesStart;
-    seqDef* sequences;      /* ptr to end of sequences */
-    BYTE*  litStart;
-    BYTE*  lit;             /* ptr to end of literals */
-    BYTE*  llCode;
-    BYTE*  mlCode;
-    BYTE*  ofCode;
-    size_t maxNbSeq;
-    size_t maxNbLit;
-
-    /* longLengthPos and longLengthType to allow us to represent either a single litLength or matchLength
-     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
-     * the existing value of the litLength or matchLength by 0x10000.
-     */
-    ZSTD_longLengthType_e longLengthType;
-    U32                   longLengthPos;  /* Index of the sequence to apply long length modification to */
-} seqStore_t;
-
-typedef struct {
-    U32 litLength;
-    U32 matchLength;
-} ZSTD_sequenceLength;
-
-/**
- * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences
- * indicated by longLengthPos and longLengthType, and adds MINMATCH back to matchLength.
- */
-MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq)
-{
-    ZSTD_sequenceLength seqLen;
-    seqLen.litLength = seq->litLength;
-    seqLen.matchLength = seq->mlBase + MINMATCH;
-    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
-        if (seqStore->longLengthType == ZSTD_llt_literalLength) {
-            seqLen.litLength += 0x10000;
-        }
-        if (seqStore->longLengthType == ZSTD_llt_matchLength) {
-            seqLen.matchLength += 0x10000;
-        }
-    }
-    return seqLen;
-}
 
 /**
  * Contains the compressed frame size and an upper-bound for the decompressed frame size.
@@ -347,10 +291,6 @@ typedef struct {
     unsigned long long decompressedBound;
 } ZSTD_frameSizeInfo;   /* decompress & legacy */
 
-const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
-int ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
-
-
 /* ZSTD_invalidateRepCodes() :
  * ensures next compression will not use repcodes from previous block.
  * Note : only works with regular variant;

lib/compress/zstd_compress.c

@@ -6909,7 +6909,7 @@ ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
         if (blockSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1+1) {
             cBlockSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
             FORWARD_IF_ERROR(cBlockSize, "Nocompress block failed");
-            DEBUGLOG(5, "Block too small, writing out nocompress block: cSize: %zu", cBlockSize);
+            DEBUGLOG(5, "Block too small (%zu): data remains uncompressed: cSize=%zu", blockSize, cBlockSize);
             cSize += cBlockSize;
             ip += blockSize;
             op += cBlockSize;

lib/compress/zstd_compress_internal.h

@@ -83,6 +83,70 @@ typedef struct {
     ZSTD_fseCTables_t fse;
 } ZSTD_entropyCTables_t;
 
+/***********************************************
+*  Sequences *
+***********************************************/
+typedef struct seqDef_s {
+    U32 offBase;   /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */
+    U16 litLength;
+    U16 mlBase;    /* mlBase == matchLength - MINMATCH */
+} seqDef;
+
+/* Controls whether seqStore has a single "long" litLength or matchLength. See seqStore_t. */
+typedef enum {
+    ZSTD_llt_none = 0,             /* no longLengthType */
+    ZSTD_llt_literalLength = 1,    /* represents a long literal */
+    ZSTD_llt_matchLength = 2       /* represents a long match */
+} ZSTD_longLengthType_e;
+
+typedef struct {
+    seqDef* sequencesStart;
+    seqDef* sequences;      /* ptr to end of sequences */
+    BYTE*  litStart;
+    BYTE*  lit;             /* ptr to end of literals */
+    BYTE*  llCode;
+    BYTE*  mlCode;
+    BYTE*  ofCode;
+    size_t maxNbSeq;
+    size_t maxNbLit;
+
+    /* longLengthPos and longLengthType to allow us to represent either a single litLength or matchLength
+     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
+     * the existing value of the litLength or matchLength by 0x10000.
+     */
+    ZSTD_longLengthType_e longLengthType;
+    U32                   longLengthPos;  /* Index of the sequence to apply long length modification to */
+} seqStore_t;
+
+typedef struct {
+    U32 litLength;
+    U32 matchLength;
+} ZSTD_sequenceLength;
+
+/**
+ * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences
+ * indicated by longLengthPos and longLengthType, and adds MINMATCH back to matchLength.
+ */
+MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq)
+{
+    ZSTD_sequenceLength seqLen;
+    seqLen.litLength = seq->litLength;
+    seqLen.matchLength = seq->mlBase + MINMATCH;
+    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
+        if (seqStore->longLengthType == ZSTD_llt_literalLength) {
+            seqLen.litLength += 0x10000;
+        }
+        if (seqStore->longLengthType == ZSTD_llt_matchLength) {
+            seqLen.matchLength += 0x10000;
+        }
+    }
+    return seqLen;
+}
+
+const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
+int ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
+
+
 /***********************************************
 *  Entropy buffer statistics structs and funcs *
 ***********************************************/

lib/compress/zstd_compress_sequences.h

@@ -11,6 +11,7 @@
 #ifndef ZSTD_COMPRESS_SEQUENCES_H
 #define ZSTD_COMPRESS_SEQUENCES_H
 
+#include "zstd_compress_internal.h" /* seqDef */
 #include "../common/fse.h" /* FSE_repeat, FSE_CTable */
 #include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */