pyxcp 0.21.9__cp312-cp312-win_amd64.whl → 0.22.23__cp312-cp312-win_amd64.whl

pyxcp/recorder/lz4.c

@@ -1,6 +1,6 @@
 /*
    LZ4 - Fast LZ compression algorithm
-   Copyright (C) 2011-2020, Yann Collet.
+   Copyright (C) 2011-2023, Yann Collet.
 
    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
 
@@ -79,7 +79,7 @@
   ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \
   || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
 #    define LZ4_FORCE_MEMORY_ACCESS 2
-#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
+#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) || defined(_MSC_VER)
 #    define LZ4_FORCE_MEMORY_ACCESS 1
 #  endif
 #endif
@@ -106,15 +106,13 @@
 #  define LZ4_SRC_INCLUDED 1
 #endif
 
-#ifndef LZ4_STATIC_LINKING_ONLY
-#define LZ4_STATIC_LINKING_ONLY
-#endif
-
 #ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
-#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
+#  define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
 #endif
 
-#define LZ4_STATIC_LINKING_ONLY  /* LZ4_DISTANCE_MAX */
+#ifndef LZ4_STATIC_LINKING_ONLY
+#  define LZ4_STATIC_LINKING_ONLY
+#endif
 #include "lz4.h"
 /* see also "memory routines" below */
 
@@ -126,14 +124,17 @@
 #  include <intrin.h>               /* only present in VS2005+ */
 #  pragma warning(disable : 4127)   /* disable: C4127: conditional expression is constant */
 #  pragma warning(disable : 6237)   /* disable: C6237: conditional expression is always 0 */
+#  pragma warning(disable : 6239)   /* disable: C6239: (<non-zero constant> && <expression>) always evaluates to the result of <expression> */
+#  pragma warning(disable : 6240)   /* disable: C6240: (<expression> && <non-zero constant>) always evaluates to the result of <expression> */
+#  pragma warning(disable : 6326)   /* disable: C6326: Potential comparison of a constant with another constant */
 #endif  /* _MSC_VER */
 
 #ifndef LZ4_FORCE_INLINE
-#  ifdef _MSC_VER    /* Visual Studio */
+#  if defined (_MSC_VER) && !defined (__clang__)    /* MSVC */
 #    define LZ4_FORCE_INLINE static __forceinline
 #  else
 #    if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
-#      ifdef __GNUC__
+#      if defined (__GNUC__) || defined (__clang__)
 #        define LZ4_FORCE_INLINE static inline __attribute__((always_inline))
 #      else
 #        define LZ4_FORCE_INLINE static inline
@@ -365,6 +366,11 @@ static unsigned LZ4_isLittleEndian(void)
     return one.c[0];
 }
 
+#if defined(__GNUC__) || defined(__INTEL_COMPILER)
+#define LZ4_PACK( __Declaration__ ) __Declaration__ __attribute__((__packed__))
+#elif defined(_MSC_VER)
+#define LZ4_PACK( __Declaration__ ) __pragma( pack(push, 1) ) __Declaration__ __pragma( pack(pop))
+#endif
 
 #if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)
 /* lie to the compiler about data alignment; use with caution */
@@ -380,9 +386,9 @@ static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
 
 /* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
 /* currently only defined for gcc and icc */
-typedef struct { U16 u16; } __attribute__((packed)) LZ4_unalign16;
-typedef struct { U32 u32; } __attribute__((packed)) LZ4_unalign32;
-typedef struct { reg_t uArch; } __attribute__((packed)) LZ4_unalignST;
+LZ4_PACK(typedef struct { U16 u16; }) LZ4_unalign16;
+LZ4_PACK(typedef struct { U32 u32; }) LZ4_unalign32;
+LZ4_PACK(typedef struct { reg_t uArch; }) LZ4_unalignST;
 
 static U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign16*)ptr)->u16; }
 static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign32*)ptr)->u32; }
@@ -427,10 +433,22 @@ static U16 LZ4_readLE16(const void* memPtr)
         return LZ4_read16(memPtr);
     } else {
         const BYTE* p = (const BYTE*)memPtr;
-        return (U16)((U16)p[0] + (p[1]<<8));
+        return (U16)((U16)p[0] | (p[1]<<8));
     }
 }
 
+#ifdef LZ4_STATIC_LINKING_ONLY_ENDIANNESS_INDEPENDENT_OUTPUT
+static U32 LZ4_readLE32(const void* memPtr)
+{
+    if (LZ4_isLittleEndian()) {
+        return LZ4_read32(memPtr);
+    } else {
+        const BYTE* p = (const BYTE*)memPtr;
+        return (U32)p[0] | (p[1]<<8) | (p[2]<<16) | (p[3]<<24);
+    }
+}
+#endif
+
 static void LZ4_writeLE16(void* memPtr, U16 value)
 {
     if (LZ4_isLittleEndian()) {
@@ -512,7 +530,7 @@ LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
 
 /* LZ4_memcpy_using_offset()  presumes :
  * - dstEnd >= dstPtr + MINMATCH
- * - there is at least 8 bytes available to write after dstEnd */
+ * - there is at least 12 bytes available to write after dstEnd */
 LZ4_FORCE_INLINE void
 LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
 {
@@ -527,12 +545,12 @@ LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const si
     case 2:
         LZ4_memcpy(v, srcPtr, 2);
         LZ4_memcpy(&v[2], srcPtr, 2);
-#if defined(_MSC_VER) && (_MSC_VER <= 1936) /* MSVC 2022 ver 17.6 or earlier */
+#if defined(_MSC_VER) && (_MSC_VER <= 1937) /* MSVC 2022 ver 17.7 or earlier */
 #  pragma warning(push)
 #  pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */
 #endif
         LZ4_memcpy(&v[4], v, 4);
-#if defined(_MSC_VER) && (_MSC_VER <= 1936) /* MSVC 2022 ver 17.6 or earlier */
+#if defined(_MSC_VER) && (_MSC_VER <= 1937) /* MSVC 2022 ver 17.7 or earlier */
 #  pragma warning(pop)
 #endif
         break;
@@ -779,7 +797,12 @@ LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
 LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
 {
     if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
+
+#ifdef LZ4_STATIC_LINKING_ONLY_ENDIANNESS_INDEPENDENT_OUTPUT
+    return LZ4_hash4(LZ4_readLE32(p), tableType);
+#else
     return LZ4_hash4(LZ4_read32(p), tableType);
+#endif
 }
 
 LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
@@ -898,7 +921,7 @@ LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
     cctx->dictSize = 0;
 }
 
-/** LZ4_compress_generic() :
+/** LZ4_compress_generic_validated() :
  *  inlined, to ensure branches are decided at compilation time.
  *  The following conditions are presumed already validated:
  *  - source != NULL
@@ -1080,7 +1103,10 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
 
         /* Catch up */
         filledIp = ip;
-        while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
+        assert(ip > anchor); /* this is always true as ip has been advanced before entering the main loop */
+        if ((match > lowLimit) && unlikely(ip[-1] == match[-1])) {
+            do { ip--; match--; } while (((ip > anchor) & (match > lowLimit)) && (unlikely(ip[-1] == match[-1])));
+        }
 
         /* Encode Literals */
         {   unsigned const litLength = (unsigned)(ip - anchor);
@@ -1095,7 +1121,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
                 goto _last_literals;
             }
             if (litLength >= RUN_MASK) {
-                int len = (int)(litLength - RUN_MASK);
+                unsigned len = litLength - RUN_MASK;
                 *token = (RUN_MASK<<ML_BITS);
                 for(; len >= 255 ; len-=255) *op++ = 255;
                 *op++ = (BYTE)len;
@@ -1452,22 +1478,30 @@ int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacit
 /* Note!: This function leaves the stream in an unclean/broken state!
  * It is not safe to subsequently use the same state with a _fastReset() or
  * _continue() call without resetting it. */
-static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+static int LZ4_compress_destSize_extState_internal(LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize, int acceleration)
 {
     void* const s = LZ4_initStream(state, sizeof (*state));
     assert(s != NULL); (void)s;
 
     if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {  /* compression success is guaranteed */
-        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
+        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, acceleration);
     } else {
         if (*srcSizePtr < LZ4_64Klimit) {
-            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1);
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, acceleration);
         } else {
             tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
-            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1);
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, acceleration);
     }   }
 }
 
+int LZ4_compress_destSize_extState(void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize, int acceleration)
+{
+    int const r = LZ4_compress_destSize_extState_internal((LZ4_stream_t*)state, src, dst, srcSizePtr, targetDstSize, acceleration);
+    /* clean the state on exit */
+    LZ4_initStream(state, sizeof (LZ4_stream_t));
+    return r;
+}
+
 
 int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
 {
@@ -1479,7 +1513,7 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe
     LZ4_stream_t* const ctx = &ctxBody;
 #endif
 
-    int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);
+    int result = LZ4_compress_destSize_extState_internal(ctx, src, dst, srcSizePtr, targetDstSize, 1);
 
 #if (LZ4_HEAPMODE)
     FREEMEM(ctx);
@@ -1548,8 +1582,11 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 #endif
 
 
+typedef enum { _ld_fast, _ld_slow } LoadDict_mode_e;
 #define HASH_UNIT sizeof(reg_t)
-int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
+int LZ4_loadDict_internal(LZ4_stream_t* LZ4_dict,
+                    const char* dictionary, int dictSize,
+                    LoadDict_mode_e _ld)
 {
     LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
     const tableType_t tableType = byU32;
@@ -1585,13 +1622,39 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
 
     while (p <= dictEnd-HASH_UNIT) {
         U32 const h = LZ4_hashPosition(p, tableType);
+        /* Note: overwriting => favors positions end of dictionary */
         LZ4_putIndexOnHash(idx32, h, dict->hashTable, tableType);
         p+=3; idx32+=3;
     }
 
+    if (_ld == _ld_slow) {
+        /* Fill hash table with additional references, to improve compression capability */
+        p = dict->dictionary;
+        idx32 = dict->currentOffset - dict->dictSize;
+        while (p <= dictEnd-HASH_UNIT) {
+            U32 const h = LZ4_hashPosition(p, tableType);
+            U32 const limit = dict->currentOffset - 64 KB;
+            if (LZ4_getIndexOnHash(h, dict->hashTable, tableType) <= limit) {
+                /* Note: not overwriting => favors positions beginning of dictionary */
+                LZ4_putIndexOnHash(idx32, h, dict->hashTable, tableType);
+            }
+            p++; idx32++;
+        }
+    }
+
     return (int)dict->dictSize;
 }
 
+int LZ4_loadDict(LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
+{
+    return LZ4_loadDict_internal(LZ4_dict, dictionary, dictSize, _ld_fast);
+}
+
+int LZ4_loadDictSlow(LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
+{
+    return LZ4_loadDict_internal(LZ4_dict, dictionary, dictSize, _ld_slow);
+}
+
 void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream)
 {
     const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL :
@@ -1923,6 +1986,17 @@ read_variable_length(const BYTE** ip, const BYTE* ilimit,
     if (initial_check && unlikely((*ip) >= ilimit)) {    /* read limit reached */
         return rvl_error;
     }
+    s = **ip;
+    (*ip)++;
+    length += s;
+    if (unlikely((*ip) > ilimit)) {    /* read limit reached */
+        return rvl_error;
+    }
+    /* accumulator overflow detection (32-bit mode only) */
+    if ((sizeof(length) < 8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
+        return rvl_error;
+    }
+    if (likely(s != 255)) return length;
     do {
         s = **ip;
         (*ip)++;
@@ -1931,10 +2005,10 @@ read_variable_length(const BYTE** ip, const BYTE* ilimit,
             return rvl_error;
         }
         /* accumulator overflow detection (32-bit mode only) */
-        if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
+        if ((sizeof(length) < 8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
             return rvl_error;
         }
-    } while (s==255);
+    } while (s == 255);
 
     return length;
 }
@@ -2000,7 +2074,7 @@ LZ4_decompress_generic(
      * note : fast loop may show a regression for some client arm chips. */
 #if LZ4_FAST_DEC_LOOP
         if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
-            DEBUGLOG(6, "skip fast decode loop");
+            DEBUGLOG(6, "move to safe decode loop");
             goto safe_decode;
         }
 
@@ -2012,6 +2086,7 @@ LZ4_decompress_generic(
             assert(ip < iend);
             token = *ip++;
             length = token >> ML_BITS;  /* literal length */
+            DEBUGLOG(7, "blockPos%6u: litLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)length);
 
             /* decode literal length */
             if (length == RUN_MASK) {
@@ -2025,49 +2100,47 @@ LZ4_decompress_generic(
                 if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
 
                 /* copy literals */
-                cpy = op+length;
                 LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
-                if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
-                LZ4_wildCopy32(op, ip, cpy);
-                ip += length; op = cpy;
-            } else {
-                cpy = op+length;
-                DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
+                if ((op+length>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
+                LZ4_wildCopy32(op, ip, op+length);
+                ip += length; op += length;
+            } else if (ip <= iend-(16 + 1/*max lit + offset + nextToken*/)) {
                 /* We don't need to check oend, since we check it once for each loop below */
-                if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
+                DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
                 /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */
                 LZ4_memcpy(op, ip, 16);
-                ip += length; op = cpy;
+                ip += length; op += length;
+            } else {
+                goto safe_literal_copy;
             }
 
             /* get offset */
             offset = LZ4_readLE16(ip); ip+=2;
-            DEBUGLOG(6, " offset = %zu", offset);
+            DEBUGLOG(6, "blockPos%6u: offset = %u", (unsigned)(op-(BYTE*)dst), (unsigned)offset);
             match = op - offset;
             assert(match <= op);  /* overflow check */
 
             /* get matchlength */
             length = token & ML_MASK;
+            DEBUGLOG(7, "  match length token = %u (len==%u)", (unsigned)length, (unsigned)length+MINMATCH);
 
             if (length == ML_MASK) {
                 size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
                 if (addl == rvl_error) {
-                    DEBUGLOG(6, "error reading long match length");
+                    DEBUGLOG(5, "error reading long match length");
                     goto _output_error;
                 }
                 length += addl;
                 length += MINMATCH;
+                DEBUGLOG(7, "  long match length == %u", (unsigned)length);
                 if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
-                if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) {
-                    DEBUGLOG(6, "Error : offset outside buffers");
-                    goto _output_error;
-                }
                 if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
                     goto safe_match_copy;
                 }
             } else {
                 length += MINMATCH;
                 if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+                    DEBUGLOG(7, "moving to safe_match_copy (ml==%u)", (unsigned)length);
                     goto safe_match_copy;
                 }
 
@@ -2086,7 +2159,7 @@ LZ4_decompress_generic(
             }   }   }
 
             if ( checkOffset && (unlikely(match + dictSize < lowPrefix)) ) {
-                DEBUGLOG(6, "Error : pos=%zi, offset=%zi => outside buffers", op-lowPrefix, op-match);
+                DEBUGLOG(5, "Error : pos=%zi, offset=%zi => outside buffers", op-lowPrefix, op-match);
                 goto _output_error;
             }
             /* match starting within external dictionary */
@@ -2143,6 +2216,7 @@ LZ4_decompress_generic(
             assert(ip < iend);
             token = *ip++;
             length = token >> ML_BITS;  /* literal length */
+            DEBUGLOG(7, "blockPos%6u: litLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)length);
 
             /* A two-stage shortcut for the most common case:
              * 1) If the literal length is 0..14, and there is enough space,
@@ -2163,6 +2237,7 @@ LZ4_decompress_generic(
                 /* The second stage: prepare for match copying, decode full info.
                  * If it doesn't work out, the info won't be wasted. */
                 length = token & ML_MASK; /* match length */
+                DEBUGLOG(7, "blockPos%6u: matchLength token = %u (len=%u)", (unsigned)(op-(BYTE*)dst), (unsigned)length, (unsigned)length + 4);
                 offset = LZ4_readLE16(ip); ip += 2;
                 match = op - offset;
                 assert(match <= op); /* check overflow */
@@ -2194,11 +2269,12 @@ LZ4_decompress_generic(
                 if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
             }
 
-            /* copy literals */
-            cpy = op+length;
 #if LZ4_FAST_DEC_LOOP
         safe_literal_copy:
 #endif
+            /* copy literals */
+            cpy = op+length;
+
             LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
             if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) {
                 /* We've either hit the input parsing restriction or the output parsing restriction.
@@ -2234,9 +2310,10 @@ LZ4_decompress_generic(
                       * so check that we exactly consume the input and don't overrun the output buffer.
                       */
                     if ((ip+length != iend) || (cpy > oend)) {
-                        DEBUGLOG(6, "should have been last run of literals")
-                        DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
-                        DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend);
+                        DEBUGLOG(5, "should have been last run of literals")
+                        DEBUGLOG(5, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
+                        DEBUGLOG(5, "or cpy(%p) > (oend-MFLIMIT)(%p)", cpy, oend-MFLIMIT);
+                        DEBUGLOG(5, "after writing %u bytes / %i bytes available", (unsigned)(op-(BYTE*)dst), outputSize);
                         goto _output_error;
                     }
                 }
@@ -2262,6 +2339,7 @@ LZ4_decompress_generic(
 
             /* get matchlength */
             length = token & ML_MASK;
+            DEBUGLOG(7, "blockPos%6u: matchLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)length);
 
     _copy_match:
             if (length == ML_MASK) {
@@ -2351,7 +2429,7 @@ LZ4_decompress_generic(
                 while (op < cpy) { *op++ = *match++; }
             } else {
                 LZ4_memcpy(op, match, 8);
-                if (length > 16)  { LZ4_wildCopy8(op+8, match+8, cpy); }
+                if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); }
             }
             op = cpy;   /* wildcopy correction */
         }

pyxcp/recorder/lz4.h

@@ -1,7 +1,7 @@
 /*
  *  LZ4 - Fast LZ compression algorithm
  *  Header File
- *  Copyright (C) 2011-2020, Yann Collet.
+ *  Copyright (C) 2011-2023, Yann Collet.
 
    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
 
@@ -130,7 +130,7 @@ extern "C" {
 /*------   Version   ------*/
 #define LZ4_VERSION_MAJOR    1    /* for breaking interface changes  */
 #define LZ4_VERSION_MINOR    9    /* for new (non-breaking) interface capabilities */
-#define LZ4_VERSION_RELEASE  4    /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_RELEASE  5    /* for tweaks, bug-fixes, or development */
 
 #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
 
@@ -144,23 +144,25 @@ LZ4LIB_API const char* LZ4_versionString (void);   /**< library version string;
 
 
 /*-************************************
-*  Tuning parameter
+*  Tuning memory usage
 **************************************/
-#define LZ4_MEMORY_USAGE_MIN 10
-#define LZ4_MEMORY_USAGE_DEFAULT 14
-#define LZ4_MEMORY_USAGE_MAX 20
-
 /*!
  * LZ4_MEMORY_USAGE :
- * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; )
- * Increasing memory usage improves compression ratio, at the cost of speed.
+ * Can be selected at compile time, by setting LZ4_MEMORY_USAGE.
+ * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB)
+ * Increasing memory usage improves compression ratio, generally at the cost of speed.
  * Reduced memory usage may improve speed at the cost of ratio, thanks to better cache locality.
- * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ * Default value is 14, for 16KB, which nicely fits into most L1 caches.
  */
 #ifndef LZ4_MEMORY_USAGE
 # define LZ4_MEMORY_USAGE LZ4_MEMORY_USAGE_DEFAULT
 #endif
 
+/* These are absolute limits, they should not be changed by users */
+#define LZ4_MEMORY_USAGE_MIN 10
+#define LZ4_MEMORY_USAGE_DEFAULT 14
+#define LZ4_MEMORY_USAGE_MAX 20
+
 #if (LZ4_MEMORY_USAGE < LZ4_MEMORY_USAGE_MIN)
 #  error "LZ4_MEMORY_USAGE is too small !"
 #endif
@@ -191,7 +193,7 @@ LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int
 /*! LZ4_decompress_safe() :
  * @compressedSize : is the exact complete size of the compressed block.
  * @dstCapacity : is the size of destination buffer (which must be already allocated),
- *                is an upper bound of decompressed size.
+ *                presumed an upper bound of decompressed size.
  * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
  *           If destination buffer is not large enough, decoding will stop and output an error code (negative value).
  *           If the source stream is detected malformed, the function will stop decoding and return a negative result.
@@ -243,17 +245,17 @@ LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int d
 LZ4LIB_API int LZ4_sizeofState(void);
 LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
 
-
 /*! LZ4_compress_destSize() :
  *  Reverse the logic : compresses as much data as possible from 'src' buffer
- *  into already allocated buffer 'dst', of size >= 'targetDestSize'.
+ *  into already allocated buffer 'dst', of size >= 'dstCapacity'.
  *  This function either compresses the entire 'src' content into 'dst' if it's large enough,
  *  or fill 'dst' buffer completely with as much data as possible from 'src'.
  *  note: acceleration parameter is fixed to "default".
  *
- * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
+ * *srcSizePtr : in+out parameter. Initially contains size of input.
+ *               Will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
  *               New value is necessarily <= input value.
- * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
+ * @return : Nb bytes written into 'dst' (necessarily <= dstCapacity)
  *           or 0 if compression fails.
  *
  * Note : from v1.8.2 to v1.9.1, this function had a bug (fixed in v1.9.2+):
@@ -267,8 +269,7 @@ LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* d
  *        a dstCapacity which is > decompressedSize, by at least 1 byte.
  *        See https://github.com/lz4/lz4/issues/859 for details
  */
-LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
-
+LZ4LIB_API int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize);
 
 /*! LZ4_decompress_safe_partial() :
  *  Decompress an LZ4 compressed block, of size 'srcSize' at position 'src',
@@ -312,7 +313,7 @@ LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcS
 ***********************************************/
 typedef union LZ4_stream_u LZ4_stream_t;  /* incomplete type (defined later) */
 
-/**
+/*!
  Note about RC_INVOKED
 
  - RC_INVOKED is predefined symbol of rc.exe (the resource compiler which is part of MSVC/Visual Studio).
@@ -362,13 +363,22 @@ LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
  *  LZ4_loadDict() triggers a reset, so any previous data will be forgotten.
  *  The same dictionary will have to be loaded on decompression side for successful decoding.
  *  Dictionary are useful for better compression of small data (KB range).
- *  While LZ4 accept any input as dictionary,
- *  results are generally better when using Zstandard's Dictionary Builder.
+ *  While LZ4 itself accepts any input as dictionary, dictionary efficiency is also a topic.
+ *  When in doubt, employ the Zstandard's Dictionary Builder.
  *  Loading a size of 0 is allowed, and is the same as reset.
- * @return : loaded dictionary size, in bytes (necessarily <= 64 KB)
+ * @return : loaded dictionary size, in bytes (note: only the last 64 KB are loaded)
  */
 LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
 
+/*! LZ4_loadDictSlow() : v1.9.5+
+ *  Same as LZ4_loadDict(),
+ *  but uses a bit more cpu to reference the dictionary content more thoroughly.
+ *  This is expected to slightly improve compression ratio.
+ *  The extra-cpu cost is likely worth it if the dictionary is re-used across multiple sessions.
+ * @return : loaded dictionary size, in bytes (note: only the last 64 KB are loaded)
+ */
+LZ4LIB_API int LZ4_loadDictSlow(LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
+
 /*! LZ4_compress_fast_continue() :
  *  Compress 'src' content using data from previously compressed blocks, for better compression ratio.
  * 'dst' buffer must be already allocated.
@@ -546,9 +556,9 @@ LZ4_decompress_safe_partial_usingDict(const char* src, char* dst,
 #define LZ4_STATIC_3504398509
 
 #ifdef LZ4_PUBLISH_STATIC_FUNCTIONS
-#define LZ4LIB_STATIC_API LZ4LIB_API
+# define LZ4LIB_STATIC_API LZ4LIB_API
 #else
-#define LZ4LIB_STATIC_API
+# define LZ4LIB_STATIC_API
 #endif
 
 
@@ -564,6 +574,12 @@ LZ4_decompress_safe_partial_usingDict(const char* src, char* dst,
  */
 LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
 
+/*! LZ4_compress_destSize_extState() :
+ *  Same as LZ4_compress_destSize(), but using an externally allocated state.
+ *  Also: exposes @acceleration
+ */
+int LZ4_compress_destSize_extState(void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize, int acceleration);
+
 /*! LZ4_attach_dictionary() :
  *  This is an experimental API that allows
  *  efficient use of a static dictionary many times.
@@ -705,7 +721,7 @@ struct LZ4_stream_t_internal {
     /* Implicit padding to ensure structure is aligned */
 };
 
-#define LZ4_STREAM_MINSIZE  ((1UL << LZ4_MEMORY_USAGE) + 32)  /* static size, for inter-version compatibility */
+#define LZ4_STREAM_MINSIZE  ((1UL << (LZ4_MEMORY_USAGE)) + 32)  /* static size, for inter-version compatibility */
 union LZ4_stream_u {
     char minStateSize[LZ4_STREAM_MINSIZE];
     LZ4_stream_t_internal internal_donotuse;
@@ -726,7 +742,7 @@ union LZ4_stream_u {
  *  Note2: An LZ4_stream_t structure guarantees correct alignment and size.
  *  Note3: Before v1.9.0, use LZ4_resetStream() instead
 **/
-LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
+LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* stateBuffer, size_t size);
 
 
 /*! LZ4_streamDecode_t :
@@ -838,11 +854,12 @@ LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4
  *         But they may happen if input data is invalid (error or intentional tampering).
  *         As a consequence, use these functions in trusted environments with trusted data **only**.
  */
-LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead")
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_partial() instead")
 LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
-LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead")
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider migrating towards LZ4_decompress_safe_continue() instead. "
+               "Note that the contract will change (requires block's compressed size, instead of decompressed size)")
 LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
-LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead")
+LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_partial_usingDict() instead")
 LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
 
 /*! LZ4_resetStream() :