removed huf_compress_impl.h

re-imported all functions inside huf_compress.c
for easier source editing.

Also updated a bunch of code comments
for clarification.

lib/decompress/huf_decompress.c

@@ -958,21 +958,22 @@ static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, qu
 };
 
 /** HUF_selectDecoder() :
-*   Tells which decoder is likely to decode faster,
-*   based on a set of pre-determined metrics.
-*   @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
-*   Assumption : 0 < cSrcSize, dstSize <= 128 KB */
+ *  Tells which decoder is likely to decode faster,
+ *  based on a set of pre-computed metrics.
+ * @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
+ *  Assumption : 0 < dstSize <= 128 KB */
 U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
 {
+    assert(dstSize > 0);
+    assert(dstSize <= 128 KB);
     /* decoder timing evaluation */
-    U32 const Q = cSrcSize >= dstSize ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
-    U32 const D256 = (U32)(dstSize >> 8);
-    U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
-    U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
-    DTime1 += DTime1 >> 3;  /* advantage to algorithm using less memory, for cache eviction */
-
-    return DTime1 < DTime0;
-}
+    {   U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
+        U32 const D256 = (U32)(dstSize >> 8);
+        U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
+        U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
+        DTime1 += DTime1 >> 3;  /* advantage to algorithm using less memory, to reduce cache eviction */
+        return DTime1 < DTime0;
+}   }
 
 
 typedef size_t (*decompressionAlgo)(void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);