HLL support default value

be/src/exprs/hll_function.cpp

@@ -48,6 +48,9 @@ void HllFunctions::hll_init(FunctionContext *, StringVal* dst) {
     dst->len = sizeof(HyperLogLog);
     dst->ptr = (uint8_t*)new HyperLogLog();
 }
+StringVal HllFunctions::empty_hll(FunctionContext* ctx) {
+    return AnyValUtil::from_string_temp(ctx, HyperLogLog::empty());
+}
 
 template <typename T>
 void HllFunctions::hll_update(FunctionContext *, const T &src, StringVal* dst) {

be/src/exprs/hll_function.h

@@ -26,6 +26,7 @@ class HllFunctions {
 public:
     static void init();
     static StringVal hll_hash(FunctionContext* ctx, const StringVal& dest_base);
+    static StringVal empty_hll(FunctionContext* ctx);
     static void hll_init(FunctionContext*, StringVal* dst);
 
     template <typename T>

be/src/olap/hll.h

@@ -103,6 +103,14 @@ class HyperLogLog {
 
     int64_t estimate_cardinality();
 
+    static std::string empty() {
+        static HyperLogLog hll;
+        std::string buf;
+        buf.resize(HLL_EMPTY_SIZE);
+        hll.serialize((uint8_t*)buf.c_str());
+        return buf;
+    }
+
     // only for debug
     std::string to_string() {
         switch (_type) {

docs/documentation/cn/sql-reference/sql-statements/Data Definition/HLL.md

@@ -18,6 +18,9 @@
 
       HLL_HASH(column_name)
       生成HLL列类型，用于insert或导入的时候，导入的使用见相关说明
+
+      EMPTY_HLL()
+      生成空HLL列，用于insert或导入的时候补充默认值，导入的使用见相关说明
 
 ## example
     1. 首先创建一张含有hll列的表

docs/documentation/cn/sql-reference/sql-statements/Data Manipulation/BROKER LOAD.md

@@ -286,8 +286,8 @@
 
     7. 导入数据到含有HLL列的表，可以是表中的列或者数据里面的列
 
-        如果表中有三列分别是（id,v1,v2）。其中v1和v2列是hll列。导入的源文件有3列。则（column_list）中声明第一列为id，第二三列为一个临时命名的k1,k2。
-        在SET中必须给表中的hll列特殊声明 hll_hash。表中的v1列等于原始数据中的hll_hash(k1)列。
+        如果表中有三列分别是（id,v1,v2,v3）。其中v1和v2列是hll列。导入的源文件有3列。则（column_list）中声明第一列为id，第二三列为一个临时命名的k1,k2。
+        在SET中必须给表中的hll列特殊声明 hll_hash。表中的v1列等于原始数据中的hll_hash(k1)列, 表中的v3列在原始数据中并没有对应的值，使用empty_hll补充默认值。
         LOAD LABEL example_db.label7
         (
         DATA INFILE("hdfs://hdfs_host:hdfs_port/user/palo/data/input/file")
@@ -297,7 +297,8 @@
         (id, k1, k2)
         SET (
           v1 = hll_hash(k1),
-          v2 = hll_hash(k2)
+          v2 = hll_hash(k2),
+          v3 = empty_hll()
         )
         )
         WITH BROKER hdfs ("username"="hdfs_user", "password"="hdfs_password");

docs/documentation/cn/sql-reference/sql-statements/Data Manipulation/STREAM LOAD.md

@@ -90,8 +90,8 @@
     6. 使用streaming方式导入（用户是defalut_cluster中的）
         seq 1 10 | awk '{OFS="\t"}{print $1, $1 * 10}' | curl --location-trusted -u root -T - http://host:port/api/testDb/testTbl/_stream_load
 
-    7. 导入含有HLL列的表，可以是表中的列或者数据中的列用于生成HLL列
-        curl --location-trusted -u root -H "columns: k1, k2, v1=hll_hash(k1)" -T testData http://host:port/api/testDb/testTbl/_stream_load
+    7. 导入含有HLL列的表，可以是表中的列或者数据中的列用于生成HLL列，也可使用empty_hll补充数据中没有的列
+        curl --location-trusted -u root -H "columns: k1, k2, v1=hll_hash(k1), v2=empty_hll()" -T testData http://host:port/api/testDb/testTbl/_stream_load
 
     8. 导入数据进行严格模式过滤，并设置时区为 Africa/Abidjan
         curl --location-trusted -u root -H "strict_mode: true" -H "timezone: Africa/Abidjan" -T testData http://host:port/api/testDb/testTbl/_stream_load

docs/documentation/en/sql-reference/sql-statements/Data Definition/HLL_EN.md

@@ -19,6 +19,9 @@ This function is used to estimate the cardinality of a single HLL sequence
 HLL_HASH(column_name)
 Generate HLL column types for insert or import, see the instructions for the use of imports
 
+EMPTY_HLL()
+Generate empty HLL column types for insert or import, see the instructions for the use of imports
+
 ## example
 1. First create a table with HLL columns
 create table test(

docs/documentation/en/sql-reference/sql-statements/Data Manipulation/BROKER LOAD_EN.md

@@ -302,9 +302,9 @@
 
     7. Load data into tables containing HLL columns, which can be columns in tables or columns in data
 
-        If there are three columns in the table (id, v1, v2). The V1 and V2 columns are HLL columns. The imported source file has three columns. Then (column_list) declares that the first column is id, and the second and third columns are temporarily named k1, k2.
+        If there are three columns in the table (id, v1, v2, v3). The V1 and V2 columns are HLL columns. The imported source file has three columns. Then (column_list) declares that the first column is id, and the second and third columns are temporarily named k1, k2.
 
-        In SET, the HLL column in the table must be specifically declared hll_hash. The V1 column in the table is equal to the hll_hash (k1) column in the original data.        
+        In SET, the HLL column in the table must be specifically declared hll_hash. The V1 column in the table is equal to the hll_hash (k1) column in the original data.The v3 column in the table does not have a corresponding value in the original data, and empty_hll is used to supplement the default value.
 
         LOAD LABEL example_db.label7
         (
@@ -315,7 +315,8 @@
         (id, k1, k2)
         SET (
           v1 = hll_hash(k1),
-          v2 = hll_hash(k2)
+          v2 = hll_hash(k2),
+          v3 = empty_hll()
         )
         )
         WITH BROKER hdfs ("username"="hdfs_user", "password"="hdfs_password");

docs/documentation/en/sql-reference/sql-statements/Data Manipulation/STREAM LOAD_EN.md

@@ -145,9 +145,9 @@ Where url is the url given by ErrorURL.
 
     ```Seq 1 10 | awk '{OFS="\t"}{print $1, $1 * 10}' | curl --location-trusted -u root -T - http://host:port/api/testDb/testTbl/_stream_load```
 
-7. load a table with HLL columns, which can be columns in the table or columns in the data used to generate HLL columns
+7. load a table with HLL columns, which can be columns in the table or columns in the data used to generate HLL columns,you can also use empty_hll to supplement columns that are not in the data
 
-    ```Curl --location-trusted -u root -H "columns: k1, k2, v1=hll_hash(k1)" -T testData http://host:port/api/testDb/testTbl/_stream_load```
+    ```Curl --location-trusted -u root -H "columns: k1, k2, v1=hll_hash(k1), v2=empty_hll()" -T testData http://host:port/api/testDb/testTbl/_stream_load```
 
 8. load data for strict mode filtering and set the time zone to Africa/Abidjan
 

fe/src/main/java/org/apache/doris/planner/BrokerScanNode.java

@@ -277,9 +277,9 @@ private void finalizeParams(ParamCreateContext context) throws UserException, An
                             + destSlotDesc.getColumn().getName() + "=hll_hash(xxx)");
                 }
                 FunctionCallExpr fn = (FunctionCallExpr) expr;
-                if (!fn.getFnName().getFunction().equalsIgnoreCase("hll_hash")) {
+                if (!fn.getFnName().getFunction().equalsIgnoreCase("hll_hash") && !fn.getFnName().getFunction().equalsIgnoreCase("empty_hll")) {
                     throw new AnalysisException("HLL column must use hll_hash function, like "
-                            + destSlotDesc.getColumn().getName() + "=hll_hash(xxx)");
+                            + destSlotDesc.getColumn().getName() + "=hll_hash(xxx) or " + destSlotDesc.getColumn().getName() + "=empty_hll()");
                 }
                 expr.setType(Type.HLL);
             }

fe/src/main/java/org/apache/doris/planner/StreamLoadScanNode.java

@@ -179,16 +179,17 @@ private void finalizeParams() throws UserException {
                     }
                 }
             }
+
             // check hll_hash
             if (dstSlotDesc.getType().getPrimitiveType() == PrimitiveType.HLL) {
                 if (!(expr instanceof FunctionCallExpr)) {
                     throw new AnalysisException("HLL column must use hll_hash function, like "
                             + dstSlotDesc.getColumn().getName() + "=hll_hash(xxx)");
                 }
                 FunctionCallExpr fn = (FunctionCallExpr) expr;
-                if (!fn.getFnName().getFunction().equalsIgnoreCase("hll_hash")) {
+                if (!fn.getFnName().getFunction().equalsIgnoreCase("hll_hash") && !fn.getFnName().getFunction().equalsIgnoreCase("empty_hll")) {
                     throw new AnalysisException("HLL column must use hll_hash function, like "
-                            + dstSlotDesc.getColumn().getName() + "=hll_hash(xxx)");
+                            + dstSlotDesc.getColumn().getName() + "=hll_hash(xxx) or " + dstSlotDesc.getColumn().getName() + "=empty_hll()");
                 }
                 expr.setType(Type.HLL);
             }

gensrc/script/doris_builtins_functions.py

@@ -587,6 +587,8 @@
         '_ZN5doris12HllFunctions15hll_cardinalityEPN9doris_udf15FunctionContextERKNS1_9StringValE'],
     [['hll_hash'], 'VARCHAR', ['VARCHAR'],
         '_ZN5doris12HllFunctions8hll_hashEPN9doris_udf15FunctionContextERKNS1_9StringValE'],
+    [['empty_hll'], 'VARCHAR', [],
+        '_ZN5doris12HllFunctions9empty_hllEPN9doris_udf15FunctionContextE'],
 
     #bitmap function