Merge pull request #41131 from JackyWoo/add_function_java_int_hash

Support Java integers hashing in `javaHash`

docs/en/sql-reference/functions/hash-functions.md

@@ -296,7 +296,14 @@ SELECT farmHash64(array('e','x','a'), 'mple', 10, toDateTime('2019-06-15 23:00:0
 
 ## javaHash
 
-Calculates [JavaHash](http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/String.java#l1452) from a string. This hash function is neither fast nor having a good quality. The only reason to use it is when this algorithm is already used in another system and you have to calculate exactly the same result.
+Calculates JavaHash from a [string](http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/String.java#l1452), 
+[Byte](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Byte.java#l405), 
+[Short](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Short.java#l410), 
+[Integer](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Integer.java#l959), 
+[Long](https://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/Long.java#l1060). 
+This hash function is neither fast nor having a good quality. The only reason to use it is when this algorithm is already used in another system and you have to calculate exactly the same result.
+
+Note that Java only support calculating signed integers hash, so if you want to calculate unsigned integers hash you must cast it to proper signed ClickHouse types.
 
 **Syntax**
 
@@ -312,6 +319,20 @@ A `Int32` data type hash value.
 
 Query:
 
+```sql
+SELECT javaHash(toInt32(123));
+```
+
+Result:
+
+```response
+┌─javaHash(toInt32(123))─┐
+│               123      │
+└────────────────────────┘
+```
+
+Query:
+
 ```sql
 SELECT javaHash('Hello, world!');
 ```

src/Functions/FunctionsHashing.h

@@ -82,6 +82,7 @@ namespace ErrorCodes
   *
   */
 
+
 struct IntHash32Impl
 {
     using ReturnType = UInt32;
@@ -413,7 +414,6 @@ struct MurmurHash3Impl128
     static constexpr bool use_int_hash_for_pods = false;
 };
 
-/// http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/478a4add975b/src/share/classes/java/lang/String.java#l1452
 /// Care should be taken to do all calculation in unsigned integers (to avoid undefined behaviour on overflow)
 ///  but obtain the same result as it is done in signed integers with two's complement arithmetic.
 struct JavaHashImpl
@@ -421,7 +421,34 @@ struct JavaHashImpl
     static constexpr auto name = "javaHash";
     using ReturnType = Int32;
 
-    static Int32 apply(const char * data, const size_t size)
+    static ReturnType apply(int64_t x)
+    {
+        return static_cast<ReturnType>(
+            static_cast<uint32_t>(x) ^ static_cast<uint32_t>(static_cast<uint64_t>(x) >> 32));
+    }
+
+    template <class T, typename std::enable_if<std::is_same_v<T, int8_t>
+                                                   || std::is_same_v<T, int16_t>
+                                                   || std::is_same_v<T, int32_t>, T>::type * = nullptr>
+    static ReturnType apply(T x)
+    {
+        return x;
+    }
+
+    template <typename T, typename std::enable_if<!std::is_same_v<T, int8_t>
+                                                      && !std::is_same_v<T, int16_t>
+                                                      && !std::is_same_v<T, int32_t>
+                                                      && !std::is_same_v<T, int64_t>, T>::type * = nullptr>
+    static ReturnType apply(T x)
+    {
+        if (std::is_unsigned_v<T>)
+            throw Exception("Unsigned types are not supported", ErrorCodes::NOT_IMPLEMENTED);
+        const size_t size = sizeof(T);
+        const char * data = reinterpret_cast<const char *>(&x);
+        return apply(data, size);
+    }
+
+    static ReturnType apply(const char * data, const size_t size)
     {
         UInt32 h = 0;
         for (size_t i = 0; i < size; ++i)
@@ -429,7 +456,7 @@ struct JavaHashImpl
         return static_cast<Int32>(h);
     }
 
-    static Int32 combineHashes(Int32, Int32)
+    static ReturnType combineHashes(Int32, Int32)
     {
         throw Exception("Java hash is not combineable for multiple arguments", ErrorCodes::NOT_IMPLEMENTED);
     }
@@ -824,7 +851,10 @@ private:
                 }
                 else
                 {
-                    h = Impl::apply(reinterpret_cast<const char *>(&vec_from[i]), sizeof(vec_from[i]));
+                    if (std::is_same_v<Impl, JavaHashImpl>)
+                        h = JavaHashImpl::apply(vec_from[i]);
+                    else
+                        h = Impl::apply(reinterpret_cast<const char *>(&vec_from[i]), sizeof(vec_from[i]));
                 }
 
                 if constexpr (first)

tests/queries/0_stateless/00800_function_java_hash.reference

@@ -1,3 +1,13 @@
+123
+-123
+123
+-123
+123
+-123
+123
+122
+-539222985
+-539222986
 96354
 -676697544
 138768

tests/queries/0_stateless/00800_function_java_hash.sql

@@ -1,5 +1,15 @@
 -- Tags: no-fasttest
 
+select javaHash(toInt8(123));
+select javaHash(toInt8(-123));
+select javaHash(toInt16(123));
+select javaHash(toInt16(-123));
+select javaHash(toInt32(123));
+select javaHash(toInt32(-123));
+select javaHash(toInt64(123));
+select javaHash(toInt64(-123));
+select javaHash(toInt64(12345678901));
+select javaHash(toInt64(-12345678901));
 select javaHash('abc');
 select javaHash('874293087');
 select javaHashUTF16LE(convertCharset('a1가', 'utf-8', 'utf-16le'));

tests/queries/0_stateless/00800_function_java_hash_with_unsigined_types.reference

@@ -0,0 +1,4 @@
+Not supported
+Not supported
+Not supported
+Not supported

tests/queries/0_stateless/00800_function_java_hash_with_unsigined_types.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+# Tags: no-fasttest
+
+CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CURDIR"/../shell_config.sh
+
+exception_pattern='DB::Exception:'
+
+function check()
+{
+  ${CLICKHOUSE_CLIENT} -q "$1" |& {
+      if [[ `grep -F  $exception_pattern  | wc -l` -gt 0 ]]
+      then
+        echo 'Not supported'
+      fi
+  }
+}
+
+check "SELECT javaHash(toUInt8(1))"
+check "SELECT javaHash(toUInt16(1))"
+check "SELECT javaHash(toUInt32(1))"
+check "SELECT javaHash(toUInt64(1))"