first implementation of small window size for btopt

noticeably improves compression ratio
when window size is small (< 18).

enwik7	level 19

windowLog	`dev`	`smallwlog`	improvement
23	3.577	3.577	0.02%
22	3.536	3.538	0.06%
21	3.462	3.467	0.14%
20	3.364	3.377	0.39%
19	3.244	3.272	0.86%
18	3.110	3.166	1.80%
17	2.843	3.057	7.53%
16	2.724	2.943	8.04%
15	2.594	2.822	8.79%
14	2.456	2.686	9.36%
13	2.312	2.523	9.13%
12	2.162	2.361	9.20%
11	2.003	2.182	8.94%

lib/compress/zstd_compress.c

@@ -1387,7 +1387,7 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms,
     note : `params` are assumed fully validated at this stage */
 static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
                                       ZSTD_CCtx_params params,
-                                      U64 pledgedSrcSize,
+                                      U64 const pledgedSrcSize,
                                       ZSTD_compResetPolicy_e const crp,
                                       ZSTD_buffered_policy_e const zbuff)
 {
@@ -2868,7 +2868,8 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
             ms->dictMatchState = NULL;
         }
 
-        ZSTD_window_enforceMaxDist(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
+        //ZSTD_window_enforceMaxDist(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
+        ZSTD_checkDictValidity(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
         /* Ensure hash/chain table insertion resumes no sooner than lowlimit */
         if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit;
 
@@ -3296,12 +3297,11 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
 
     FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
                                      ZSTDcrp_continue, zbuff) );
-    {
+    {   size_t const dictID = ZSTD_compress_insertDictionary(
-        size_t const dictID = ZSTD_compress_insertDictionary(
                 cctx->blockState.prevCBlock, &cctx->blockState.matchState,
                 &params, dict, dictSize, dictContentType, dtlm, cctx->entropyWorkspace);
         FORWARD_IF_ERROR(dictID);
-        assert(dictID <= (size_t)(U32)-1);
+        assert(dictID <= UINT32_MAX);
         cctx->dictID = (U32)dictID;
     }
     return 0;

lib/compress/zstd_compress_internal.h

@@ -141,7 +141,7 @@ struct ZSTD_matchState_t {
     U32* hashTable3;
     U32* chainTable;
     optState_t opt;         /* optimal parser state */
-    const ZSTD_matchState_t * dictMatchState;
+    const ZSTD_matchState_t* dictMatchState;
     ZSTD_compressionParameters cParams;
 };
 
@@ -731,6 +731,38 @@ ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
     }
 }
 
+MEM_STATIC void
+ZSTD_checkDictValidity(ZSTD_window_t* window,
+                       const void* blockEnd,
+                             U32   maxDist,
+                             U32*  loadedDictEndPtr,
+                       const ZSTD_matchState_t** dictMatchStatePtr)
+{
+    U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+    U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
+    DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+
+    /* - When there is no dictionary : loadedDictEnd == 0.
+         In which case, the test (blockEndIdx > maxDist) is merely to avoid
+         overflowing next operation `newLowLimit = blockEndIdx - maxDist`.
+       - When there is a standard dictionary :
+         Index referential is copied from the dictionary,
+         which means it starts from 0.
+         In which case, loadedDictEnd == dictSize,
+         and it makes sense to compare `blockEndIdx > maxDist + dictSize`
+         since `blockEndIdx` also starts from zero.
+       - When there is an attached dictionary :
+         loadedDictEnd is expressed within the referential of the context,
+         so it can be directly compared against blockEndIdx.
+    */
+    if (loadedDictEnd && (blockEndIdx > maxDist + loadedDictEnd)) {
+        /* On reaching window size, dictionaries are invalidated */
+        if (loadedDictEndPtr) *loadedDictEndPtr = 0;
+        if (dictMatchStatePtr) *dictMatchStatePtr = NULL;
+    }
+}
+
 /**
  * ZSTD_window_update():
  * Updates the window by appending [src, src + srcSize) to the window.

lib/compress/zstd_opt.c

@@ -545,6 +545,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
     U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
+    U32 const maxDistance = 1U << cParams->windowLog;
     const BYTE* const base = ms->window.base;
     U32 const current = (U32)(ip-base);
     U32 const hashLog = cParams->hashLog;
@@ -560,8 +561,9 @@ U32 ZSTD_insertBtAndGetAllMatches (
     U32 const dictLimit = ms->window.dictLimit;
     const BYTE* const dictEnd = dictBase + dictLimit;
     const BYTE* const prefixStart = base + dictLimit;
-    U32 const btLow = btMask >= current ? 0 : current - btMask;
+    U32 const btLow = (btMask >= current) ? 0 : current - btMask;
-    U32 const windowLow = ms->window.lowLimit;
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const windowLow = ((current - windowValid) > maxDistance) ? current - maxDistance : windowValid;
     U32 const matchLow = windowLow ? windowLow : 1;
     U32* smallerPtr = bt + 2*(current&btMask);
     U32* largerPtr  = bt + 2*(current&btMask) + 1;