Merge pull request #2965 from facebook/offbase

Converge sumtype (offset | repcode) numeric representation towards offBase

Author: Cyan4973

contrib/seekable_format/zstdseek_decompress.c

@@ -23,13 +23,64 @@
 #  endif
 #endif
 
+/* ************************************************************
+*  Detect POSIX version
+*  PLATFORM_POSIX_VERSION = 0 for non-Unix e.g. Windows
+*  PLATFORM_POSIX_VERSION = 1 for Unix-like but non-POSIX
+*  PLATFORM_POSIX_VERSION > 1 is equal to found _POSIX_VERSION
+*  Value of PLATFORM_POSIX_VERSION can be forced on command line
+***************************************************************/
+#ifndef PLATFORM_POSIX_VERSION
+
+#  if (defined(__APPLE__) && defined(__MACH__)) || defined(__SVR4) || defined(_AIX) || defined(__hpux) /* POSIX.1-2001 (SUSv3) conformant */ \
+     || defined(__DragonFly__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__)  /* BSD distros */
+     /* exception rule : force posix version to 200112L,
+      * note: it's better to use unistd.h's _POSIX_VERSION whenever possible */
+#    define PLATFORM_POSIX_VERSION 200112L
+
+/* try to determine posix version through official unistd.h's _POSIX_VERSION (http://pubs.opengroup.org/onlinepubs/7908799/xsh/unistd.h.html).
+ * note : there is no simple way to know in advance if <unistd.h> is present or not on target system,
+ * Posix specification mandates its presence and its content, but target system must respect this spec.
+ * It's necessary to _not_ #include <unistd.h> whenever target OS is not unix-like
+ * otherwise it will block preprocessing stage.
+ * The following list of build macros tries to "guess" if target OS is likely unix-like, and therefore can #include <unistd.h>
+ */
+#  elif !defined(_WIN32) \
+     && ( defined(__unix__) || defined(__unix) \
+       || defined(__midipix__) || defined(__VMS) || defined(__HAIKU__) )
+
+#    if defined(__linux__) || defined(__linux) || defined(__CYGWIN__)
+#      ifndef _POSIX_C_SOURCE
+#        define _POSIX_C_SOURCE 200809L  /* feature test macro : https://www.gnu.org/software/libc/manual/html_node/Feature-Test-Macros.html */
+#      endif
+#    endif
+#    include <unistd.h>  /* declares _POSIX_VERSION */
+#    if defined(_POSIX_VERSION)  /* POSIX compliant */
+#      define PLATFORM_POSIX_VERSION _POSIX_VERSION
+#    else
+#      define PLATFORM_POSIX_VERSION 1
+#    endif
+
+#    ifdef __UCLIBC__
+#     ifndef __USE_MISC
+#      define __USE_MISC /* enable st_mtim on uclibc */
+#     endif
+#    endif
+
+#  else  /* non-unix target platform (like Windows) */
+#    define PLATFORM_POSIX_VERSION 0
+#  endif
+
+#endif   /* PLATFORM_POSIX_VERSION */
+
+
 /* ************************************************************
 * Avoid fseek()'s 2GiB barrier with MSVC, macOS, *BSD, MinGW
 ***************************************************************/
 #if defined(_MSC_VER) && _MSC_VER >= 1400
 #   define LONG_SEEK _fseeki64
 #elif !defined(__64BIT__) && (PLATFORM_POSIX_VERSION >= 200112L) /* No point defining Large file for 64 bit */
-#  define LONG_SEEK fseeko
+#   define LONG_SEEK fseeko
 #elif defined(__MINGW32__) && !defined(__STRICT_ANSI__) && !defined(__NO_MINGW_LFS) && defined(__MSVCRT__)
 #   define LONG_SEEK fseeko64
 #elif defined(_WIN32) && !defined(__DJGPP__)

lib/compress/zstd_compress.c

@@ -2940,7 +2940,7 @@ static void ZSTD_copyBlockSequences(ZSTD_CCtx* zc)
         /* seqStoreSeqs[i].offset == offCode+1, and ZSTD_updateRep() expects offCode
            so we provide seqStoreSeqs[i].offset - 1 */
         ZSTD_updateRep(updatedRepcodes.rep,
-                       seqStoreSeqs[i].offBase - 1,
+                       seqStoreSeqs[i].offBase,
                        seqStoreSeqs[i].litLength == 0);
         literalsRead += outSeqs[i].litLength;
     }
@@ -3433,20 +3433,22 @@ static void ZSTD_deriveSeqStoreChunk(seqStore_t* resultSeqStore,
 }
 
 /**
- * Returns the raw offset represented by the combination of offCode, ll0, and repcode history.
- * offCode must represent a repcode in the numeric representation of ZSTD_storeSeq().
+ * Returns the raw offset represented by the combination of offBase, ll0, and repcode history.
+ * offBase must represent a repcode in the numeric representation of ZSTD_storeSeq().
  */
 static U32
-ZSTD_resolveRepcodeToRawOffset(const U32 rep[ZSTD_REP_NUM], const U32 offCode, const U32 ll0)
+ZSTD_resolveRepcodeToRawOffset(const U32 rep[ZSTD_REP_NUM], const U32 offBase, const U32 ll0)
 {
-    U32 const adjustedOffCode = STORED_REPCODE(offCode) - 1 + ll0;  /* [ 0 - 3 ] */
-    assert(STORED_IS_REPCODE(offCode));
-    if (adjustedOffCode == ZSTD_REP_NUM) {
-        /* litlength == 0 and offCode == 2 implies selection of first repcode - 1 */
-        assert(rep[0] > 0);
+    U32 const adjustedRepCode = OFFBASE_TO_REPCODE(offBase) - 1 + ll0;  /* [ 0 - 3 ] */
+    assert(OFFBASE_IS_REPCODE(offBase));
+    if (adjustedRepCode == ZSTD_REP_NUM) {
+        /* litlength == 0 and offCode == 2 implies selection of first repcode - 1
+         * This is only valid if it results in a valid offset value, aka > 0.
+         */
+        assert(rep[0] > 1);
         return rep[0] - 1;
     }
-    return rep[adjustedOffCode];
+    return rep[adjustedRepCode];
 }
 
 /**
@@ -3468,11 +3470,11 @@ static void ZSTD_seqStore_resolveOffCodes(repcodes_t* const dRepcodes, repcodes_
     for (; idx < nbSeq; ++idx) {
         seqDef* const seq = seqStore->sequencesStart + idx;
         U32 const ll0 = (seq->litLength == 0);
-        U32 const offCode = OFFBASE_TO_STORED(seq->offBase);
+        U32 const offBase = seq->offBase;
         assert(seq->offBase > 0);
-        if (STORED_IS_REPCODE(offCode)) {
-            U32 const dRawOffset = ZSTD_resolveRepcodeToRawOffset(dRepcodes->rep, offCode, ll0);
-            U32 const cRawOffset = ZSTD_resolveRepcodeToRawOffset(cRepcodes->rep, offCode, ll0);
+        if (OFFBASE_IS_REPCODE(offBase)) {
+            U32 const dRawOffset = ZSTD_resolveRepcodeToRawOffset(dRepcodes->rep, offBase, ll0);
+            U32 const cRawOffset = ZSTD_resolveRepcodeToRawOffset(cRepcodes->rep, offBase, ll0);
             /* Adjust simulated decompression repcode history if we come across a mismatch. Replace
              * the repcode with the offset it actually references, determined by the compression
              * repcode history.
@@ -3484,8 +3486,8 @@ static void ZSTD_seqStore_resolveOffCodes(repcodes_t* const dRepcodes, repcodes_
         /* Compression repcode history is always updated with values directly from the unmodified seqStore.
          * Decompression repcode history may use modified seq->offset value taken from compression repcode history.
          */
-        ZSTD_updateRep(dRepcodes->rep, OFFBASE_TO_STORED(seq->offBase), ll0);
-        ZSTD_updateRep(cRepcodes->rep, offCode, ll0);
+        ZSTD_updateRep(dRepcodes->rep, seq->offBase, ll0);
+        ZSTD_updateRep(cRepcodes->rep, offBase, ll0);
     }
 }
 
@@ -5770,26 +5772,26 @@ ZSTD_validateSequence(U32 offCode, U32 matchLength,
      * window size. After output surpasses windowSize, we're limited to windowSize offsets again.
      */
     size_t const offsetBound = posInSrc > windowSize ? (size_t)windowSize : posInSrc + (size_t)dictSize;
-    RETURN_ERROR_IF(offCode > STORE_OFFSET(offsetBound), corruption_detected, "Offset too large!");
+    RETURN_ERROR_IF(offCode > OFFSET_TO_OFFBASE(offsetBound), corruption_detected, "Offset too large!");
     RETURN_ERROR_IF(matchLength < MINMATCH, corruption_detected, "Matchlength too small");
     return 0;
 }
 
 /* Returns an offset code, given a sequence's raw offset, the ongoing repcode array, and whether litLength == 0 */
-static U32 ZSTD_finalizeOffCode(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0)
+static U32 ZSTD_finalizeOffBase(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0)
 {
-    U32 offCode = STORE_OFFSET(rawOffset);
+    U32 offBase = OFFSET_TO_OFFBASE(rawOffset);
 
     if (!ll0 && rawOffset == rep[0]) {
-        offCode = STORE_REPCODE_1;
+        offBase = REPCODE1_TO_OFFBASE;
     } else if (rawOffset == rep[1]) {
-        offCode = STORE_REPCODE(2 - ll0);
+        offBase = REPCODE_TO_OFFBASE(2 - ll0);
     } else if (rawOffset == rep[2]) {
-        offCode = STORE_REPCODE(3 - ll0);
+        offBase = REPCODE_TO_OFFBASE(3 - ll0);
     } else if (ll0 && rawOffset == rep[0] - 1) {
-        offCode = STORE_REPCODE_3;
+        offBase = REPCODE3_TO_OFFBASE;
     }
-    return offCode;
+    return offBase;
 }
 
 /* Returns 0 on success, and a ZSTD_error otherwise. This function scans through an array of
@@ -5819,19 +5821,19 @@ ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx,
         U32 const litLength = inSeqs[idx].litLength;
         U32 const ll0 = (litLength == 0);
         U32 const matchLength = inSeqs[idx].matchLength;
-        U32 const offCode = ZSTD_finalizeOffCode(inSeqs[idx].offset, updatedRepcodes.rep, ll0);
-        ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0);
+        U32 const offBase = ZSTD_finalizeOffBase(inSeqs[idx].offset, updatedRepcodes.rep, ll0);
+        ZSTD_updateRep(updatedRepcodes.rep, offBase, ll0);
 
-        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength);
+        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offBase, matchLength, litLength);
         if (cctx->appliedParams.validateSequences) {
             seqPos->posInSrc += litLength + matchLength;
-            FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc,
+            FORWARD_IF_ERROR(ZSTD_validateSequence(offBase, matchLength, seqPos->posInSrc,
                                                 cctx->appliedParams.cParams.windowLog, dictSize),
                                                 "Sequence validation failed");
         }
         RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation,
                         "Not enough memory allocated. Try adjusting ZSTD_c_minMatch.");
-        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength);
+        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offBase, matchLength);
         ip += matchLength + litLength;
     }
     ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(repcodes_t));
@@ -5888,7 +5890,7 @@ ZSTD_copySequencesToSeqStoreNoBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition*
         U32 litLength = currSeq.litLength;
         U32 matchLength = currSeq.matchLength;
         U32 const rawOffset = currSeq.offset;
-        U32 offCode;
+        U32 offBase;
 
         /* Modify the sequence depending on where endPosInSequence lies */
         if (endPosInSequence >= currSeq.litLength + currSeq.matchLength) {
@@ -5942,20 +5944,20 @@ ZSTD_copySequencesToSeqStoreNoBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition*
         }
         /* Check if this offset can be represented with a repcode */
         {   U32 const ll0 = (litLength == 0);
-            offCode = ZSTD_finalizeOffCode(rawOffset, updatedRepcodes.rep, ll0);
-            ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0);
+            offBase = ZSTD_finalizeOffBase(rawOffset, updatedRepcodes.rep, ll0);
+            ZSTD_updateRep(updatedRepcodes.rep, offBase, ll0);
         }
 
         if (cctx->appliedParams.validateSequences) {
             seqPos->posInSrc += litLength + matchLength;
-            FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc,
+            FORWARD_IF_ERROR(ZSTD_validateSequence(offBase, matchLength, seqPos->posInSrc,
                                                    cctx->appliedParams.cParams.windowLog, dictSize),
                                                    "Sequence validation failed");
         }
-        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength);
+        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offBase, matchLength, litLength);
         RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation,
                         "Not enough memory allocated. Try adjusting ZSTD_c_minMatch.");
-        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength);
+        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offBase, matchLength);
         ip += matchLength + litLength;
     }
     DEBUGLOG(5, "Ending seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength);

lib/compress/zstd_compress_internal.h

@@ -577,29 +577,27 @@ ZSTD_safecopyLiterals(BYTE* op, BYTE const* ip, BYTE const* const iend, BYTE con
     while (ip < iend) *op++ = *ip++;
 }
 
-#define ZSTD_REP_MOVE     (ZSTD_REP_NUM-1)
-#define STORE_REPCODE_1 STORE_REPCODE(1)
-#define STORE_REPCODE_2 STORE_REPCODE(2)
-#define STORE_REPCODE_3 STORE_REPCODE(3)
-#define STORE_REPCODE(r) (assert((r)>=1), assert((r)<=3), (r)-1)
-#define STORE_OFFSET(o)  (assert((o)>0), o + ZSTD_REP_MOVE)
-#define STORED_IS_OFFSET(o)  ((o) > ZSTD_REP_MOVE)
-#define STORED_IS_REPCODE(o) ((o) <= ZSTD_REP_MOVE)
-#define STORED_OFFSET(o)  (assert(STORED_IS_OFFSET(o)), (o)-ZSTD_REP_MOVE)
-#define STORED_REPCODE(o) (assert(STORED_IS_REPCODE(o)), (o)+1)  /* returns ID 1,2,3 */
-#define STORED_TO_OFFBASE(o) ((o)+1)
-#define OFFBASE_TO_STORED(o) ((o)-1)
+
+#define REPCODE1_TO_OFFBASE REPCODE_TO_OFFBASE(1)
+#define REPCODE2_TO_OFFBASE REPCODE_TO_OFFBASE(2)
+#define REPCODE3_TO_OFFBASE REPCODE_TO_OFFBASE(3)
+#define REPCODE_TO_OFFBASE(r) (assert((r)>=1), assert((r)<=ZSTD_REP_NUM), (r)) /* accepts IDs 1,2,3 */
+#define OFFSET_TO_OFFBASE(o)  (assert((o)>0), o + ZSTD_REP_NUM)
+#define OFFBASE_IS_OFFSET(o)  ((o) > ZSTD_REP_NUM)
+#define OFFBASE_IS_REPCODE(o) ( 1 <= (o) && (o) <= ZSTD_REP_NUM)
+#define OFFBASE_TO_OFFSET(o)  (assert(OFFBASE_IS_OFFSET(o)), (o) - ZSTD_REP_NUM)
+#define OFFBASE_TO_REPCODE(o) (assert(OFFBASE_IS_REPCODE(o)), (o))  /* returns ID 1,2,3 */
 
 /*! ZSTD_storeSeq() :
- *  Store a sequence (litlen, litPtr, offCode and matchLength) into seqStore_t.
- *  @offBase_minus1 : Users should use employ macros STORE_REPCODE_X and STORE_OFFSET().
+ *  Store a sequence (litlen, litPtr, offBase and matchLength) into seqStore_t.
+ *  @offBase : Users should employ macros REPCODE_TO_OFFBASE() and OFFSET_TO_OFFBASE().
  *  @matchLength : must be >= MINMATCH
- *  Allowed to overread literals up to litLimit.
+ *  Allowed to over-read literals up to litLimit.
 */
 HINT_INLINE UNUSED_ATTR void
 ZSTD_storeSeq(seqStore_t* seqStorePtr,
               size_t litLength, const BYTE* literals, const BYTE* litLimit,
-              U32 offBase_minus1,
+              U32 offBase,
               size_t matchLength)
 {
     BYTE const* const litLimit_w = litLimit - WILDCOPY_OVERLENGTH;
@@ -608,8 +606,8 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr,
     static const BYTE* g_start = NULL;
     if (g_start==NULL) g_start = (const BYTE*)literals;  /* note : index only works for compression within a single segment */
     {   U32 const pos = (U32)((const BYTE*)literals - g_start);
-        DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offCode%7u",
-               pos, (U32)litLength, (U32)matchLength, (U32)offBase_minus1);
+        DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offBase%7u",
+               pos, (U32)litLength, (U32)matchLength, (U32)offBase);
     }
 #endif
     assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq);
@@ -619,9 +617,9 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr,
     assert(literals + litLength <= litLimit);
     if (litEnd <= litLimit_w) {
         /* Common case we can use wildcopy.
-	 * First copy 16 bytes, because literals are likely short.
-	 */
-        assert(WILDCOPY_OVERLENGTH >= 16);
+         * First copy 16 bytes, because literals are likely short.
+         */
+        ZSTD_STATIC_ASSERT(WILDCOPY_OVERLENGTH >= 16);
         ZSTD_copy16(seqStorePtr->lit, literals);
         if (litLength > 16) {
             ZSTD_wildcopy(seqStorePtr->lit+16, literals+16, (ptrdiff_t)litLength-16, ZSTD_no_overlap);
@@ -640,7 +638,7 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr,
     seqStorePtr->sequences[0].litLength = (U16)litLength;
 
     /* match offset */
-    seqStorePtr->sequences[0].offBase = STORED_TO_OFFBASE(offBase_minus1);
+    seqStorePtr->sequences[0].offBase = offBase;
 
     /* match Length */
     assert(matchLength >= MINMATCH);
@@ -658,17 +656,17 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr,
 
 /* ZSTD_updateRep() :
  * updates in-place @rep (array of repeat offsets)
- * @offBase_minus1 : sum-type, with same numeric representation as ZSTD_storeSeq()
+ * @offBase : sum-type, using numeric representation of ZSTD_storeSeq()
  */
 MEM_STATIC void
-ZSTD_updateRep(U32 rep[ZSTD_REP_NUM], U32 const offBase_minus1, U32 const ll0)
+ZSTD_updateRep(U32 rep[ZSTD_REP_NUM], U32 const offBase, U32 const ll0)
 {
-    if (STORED_IS_OFFSET(offBase_minus1)) {  /* full offset */
+    if (OFFBASE_IS_OFFSET(offBase)) {  /* full offset */
         rep[2] = rep[1];
         rep[1] = rep[0];
-        rep[0] = STORED_OFFSET(offBase_minus1);
+        rep[0] = OFFBASE_TO_OFFSET(offBase);
     } else {   /* repcode */
-        U32 const repCode = STORED_REPCODE(offBase_minus1) - 1 + ll0;
+        U32 const repCode = OFFBASE_TO_REPCODE(offBase) - 1 + ll0;
         if (repCode > 0) {  /* note : if repCode==0, no change */
             U32 const currentOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode];
             rep[2] = (repCode >= 2) ? rep[1] : rep[2];
@@ -685,11 +683,11 @@ typedef struct repcodes_s {
 } repcodes_t;
 
 MEM_STATIC repcodes_t
-ZSTD_newRep(U32 const rep[ZSTD_REP_NUM], U32 const offBase_minus1, U32 const ll0)
+ZSTD_newRep(U32 const rep[ZSTD_REP_NUM], U32 const offBase, U32 const ll0)
 {
     repcodes_t newReps;
     ZSTD_memcpy(&newReps, rep, sizeof(newReps));
-    ZSTD_updateRep(newReps.rep, offBase_minus1, ll0);
+    ZSTD_updateRep(newReps.rep, offBase, ll0);
     return newReps;
 }