[bug] Fix dictContentType when reprocessing cdict

Conditions to trigger:
* CDict is loaded as raw content.
* CDict starts with the zstd dictionary magic number.
* The CDict is reprocessed (not attached or copied).
* The new API is used (streaming or `ZSTD_compress2()`).

Bug: The dictionary is loaded as a zstd dictionary, not a raw content
dictionary, because the dict content type is set to `ZSTD_dct_auto`.

Fix: Pass in the dictionary content type from cdict creation to the call
to `ZSTD_compress_insertDictionary()`.

Test: Added a test case that exposes the bug, and fixed the raw
content tests to not modify the `dictBuffer`, which makes all future
tests with the `dictBuffer` raw content, which doesn't seem intentional.
This commit is contained in:
Nick Terrell
2020-10-12 12:46:10 -07:00
parent b951ad20a2
commit 7083f79008
2 changed files with 45 additions and 24 deletions
+3 -1
View File
@@ -64,6 +64,7 @@ size_t ZSTD_compressBound(size_t srcSize) {
struct ZSTD_CDict_s {
const void* dictContent;
size_t dictContentSize;
ZSTD_dictContentType_e dictContentType; /* The dictContentType the CDict was created with */
U32* entropyWorkspace; /* entropy workspace of HUF_WORKSPACE_SIZE bytes */
ZSTD_cwksp workspace;
ZSTD_matchState_t matchState;
@@ -3188,7 +3189,7 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
ZSTD_compress_insertDictionary(
cctx->blockState.prevCBlock, &cctx->blockState.matchState,
&cctx->ldmState, &cctx->workspace, &cctx->appliedParams, cdict->dictContent,
cdict->dictContentSize, dictContentType, dtlm,
cdict->dictContentSize, cdict->dictContentType, dtlm,
cctx->entropyWorkspace)
: ZSTD_compress_insertDictionary(
cctx->blockState.prevCBlock, &cctx->blockState.matchState,
@@ -3460,6 +3461,7 @@ static size_t ZSTD_initCDict_internal(
ZSTD_memcpy(internalBuffer, dictBuffer, dictSize);
}
cdict->dictContentSize = dictSize;
cdict->dictContentType = dictContentType;
cdict->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cdict->workspace, HUF_WORKSPACE_SIZE);