Merge pull request #15015 from taosdata/fix/fixFst

fix:  fst bug

source/libs/index/src/indexFstDfa.c

@@ -19,8 +19,8 @@
 const static uint32_t STATE_LIMIT = 1000;
 
 static int dfaInstsEqual(const void *a, const void *b, size_t size) {
-  SArray *ar = (SArray *)a;
+  SArray *ar = *(SArray **)a;
-  SArray *br = (SArray *)b;
+  SArray *br = *(SArray **)b;
   size_t  al = ar != NULL ? taosArrayGetSize(ar) : 0;
   size_t  bl = br != NULL ? taosArrayGetSize(br) : 0;
   if (al != bl) {
@@ -71,8 +71,8 @@ FstDfa *dfaBuilderBuild(FstDfaBuilder *builder) {
 
   dfaAdd(builder->dfa, cur, 0);
 
-  SArray  *states = taosArrayInit(0, sizeof(uint32_t));
   uint32_t result;
+  SArray  *states = taosArrayInit(0, sizeof(uint32_t));
   if (dfaBuilderCacheState(builder, cur, &result)) {
     taosArrayPush(states, &result);
   }
@@ -146,10 +146,9 @@ bool dfaBuilderCacheState(FstDfaBuilder *builder, FstSparseSet *set, uint32_t *r
     *result = *v;
     taosArrayDestroy(tinsts);
   } else {
-    DfaState st;
+    DfaState st = {.insts = tinsts, .isMatch = isMatch};
-    st.insts = tinsts;
-    st.isMatch = isMatch;
     taosArrayPush(builder->dfa->states, &st);
+
     int32_t sz = taosArrayGetSize(builder->dfa->states) - 1;
     taosHashPut(builder->cache, &tinsts, sizeof(POINTER_BYTES), &sz, sizeof(sz));
     *result = sz;

source/libs/index/src/indexFstFile.c

@@ -85,11 +85,12 @@ static int idxFileCtxDoReadFrom(IFileCtx* ctx, uint8_t* buf, int len, int32_t of
       blk->blockId = blkId;
       blk->nread = taosPReadFile(ctx->file.pFile, blk->buf, kBlockSize, blkId * kBlockSize);
       assert(blk->nread <= kBlockSize);
-      nread = TMIN(blkLeft, len);
 
       if (blk->nread < kBlockSize && blk->nread < len) {
         break;
       }
+
+      nread = TMIN(blkLeft, len);
       memcpy(buf + total, blk->buf + blkOffset, nread);
 
       LRUStatus s = taosLRUCacheInsert(ctx->lru, key, strlen(key), blk, cacheMemSize, deleteDataBlockFromLRU, NULL,

source/libs/index/src/indexFstSparse.c

@@ -78,8 +78,8 @@ bool sparSetContains(FstSparseSet *ss, int32_t ip) {
   if (ip >= ss->cap || ip < 0) {
     return false;
   }
-  int32_t i = ss->sparse[ip];
 
+  int32_t i = ss->sparse[ip];
   if (i >= 0 && i < ss->cap && i < ss->size && ss->dense[i] == ip) {
     return true;
   } else {

tests/system-test/2-query/json_tag_large_tables.py

@@ -43,13 +43,48 @@ class TDTestCase:
         tdSql.execute('create database db vgroups 1')
         tdSql.execute('use db')
         print("============== STEP 1 ===== prepare data & validate json string")
+
+        i = 0
+        # add 100000 table
+        tdSql.execute("create table if not exists jsons1(ts timestamp, dataInt int, dataBool bool, dataStr nchar(50), dataStrBin binary(150)) tags(jtag json)")
+        while i <= 10 0000:
+            sql = """insert into jsons1_{%d} using jsons1 tags('{"tag1":{%d}}') values(1591060618000, 1, false, 'json1', '你是') (1591060608000, 23, true, '等等', 'json')"""%(i, i)
+            tdSql.execute(sql)
+            i = i + 1
+
+        // do query
+        i = 0        
+        while i <= 10 0000:
+            sql = """select count(*) from jsons1 where jtag->'tag1' = %d"""%(i)
+            tdSql.query(sql)
+            if 1 != tdSql.getRows():
+                print("err: %s"%(sql))
+        
+        while i <= 10000000
+            sql = """insert into jsons1_{%d} using jsons1 tags('{"tag1":{%d}}') values(1591060618000, 1, false, 'json1', '你是') (1591060608000, 23, true, '等等', 'json')"""%(i, i)
+            tdSql.execute(sql)
+            i = i + 1
+        
+        i = 0
+        # drop super table
+        tdSql.execute("create table if not exists jsons1(ts timestamp, dataInt int, dataBool bool, dataStr nchar(50), dataStrBin binary(150)) tags(jtag json)")
+        while i <= 100000:
+            sql = """insert into jsons1_{%d} using jsons1 tags('{"tag1":{%d}}') values(1591060618000, 1, false, 'json1', '你是') (1591060608000, 23, true, '等等', 'json')"""%(i, i)
+            tdSql.execute(sql)
+            i = i + 1
+
+        tdSql.execute('drop stable jsons1')
+
+
+        # drop database 
         i = 0
         tdSql.execute("create table if not exists jsons1(ts timestamp, dataInt int, dataBool bool, dataStr nchar(50), dataStrBin binary(150)) tags(jtag json)")
         while i <= 100000:
-            f = "insert into jsons1_{} using jsons1 tags('{\"tag1\":\"fff\",\"tag2\":{}, \"tag3\":true}') values(1591060618000, 1, false, 'json1', '你是') (1591060608000, 23, true, '等等', 'json')".format
+            sql = """insert into jsons1_{%d} using jsons1 tags('{"tag1":{%d}}') values(1591060618000, 1, false, 'json1', '你是') (1591060608000, 23, true, '等等', 'json')"""%(i, i)
-            sql = f(i, i) 
             tdSql.execute(sql)
             i = i + 1
+        tdSql.execute('drop database db')
+        
 
         # test duplicate key using the first one. elimate empty key
         #tdSql.execute("CREATE TABLE if not exists jsons1_8 using jsons1 tags('{\"tag1\":null, \"tag1\":true, \"tag1\":45, \"1tag$\":2, \" \":90, \"\":32}')") tdSql.query("select jtag from jsons1_8") tdSql.checkRows(0);