[MINOR] Clarify that xxhash64 seed is 42

### What changes were proposed in this pull request? State that the hash seed used for xxhash64 is 42 in docs. ### Why are the changes needed? It's somewhat non-standard not seed to 0. Users would have to know this seed to reproduce the hash value. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? N/A Closes apache#38010 from srowen/Hash42. Authored-by: Sean Owen <[email protected]> Signed-off-by: Ruifeng Zheng <[email protected]>
saileshbaidya · Sep 27, 2022 · 311a855 · 311a855
1 parent f2ba6b5
commit 311a855
Show file tree

Hide file tree

Showing 4 changed files with 5 additions and 4 deletions.
diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R
@@ -974,7 +974,7 @@ setMethod("hash",
 #' @details
 #' \code{xxhash64}: Calculates the hash code of given columns using the 64-bit
 #' variant of the xxHash algorithm, and returns the result as a long
-#' column.
+#' column. The hash computation uses an initial seed of 42.
 #'
 #' @rdname column_misc_functions
 #' @aliases xxhash64 xxhash64,Column-method

diff --git a/python/pyspark/sql/functions.py b/python/pyspark/sql/functions.py
@@ -5092,7 +5092,7 @@ def hash(*cols: "ColumnOrName") -> Column:
 
 def xxhash64(*cols: "ColumnOrName") -> Column:
     """Calculates the hash code of given columns using the 64-bit variant of the xxHash algorithm,
-    and returns the result as a long column.
+    and returns the result as a long column. The hash computation uses an initial seed of 42.
 
     .. versionadded:: 3.0.0
 

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala
@@ -643,7 +643,8 @@ object Murmur3HashFunction extends InterpretedHashFunction {
  * A xxHash64 64-bit hash expression.
  */
 @ExpressionDescription(
-  usage = "_FUNC_(expr1, expr2, ...) - Returns a 64-bit hash value of the arguments.",
+  usage = "_FUNC_(expr1, expr2, ...) - Returns a 64-bit hash value of the arguments. " +
+    "Hash seed is 42.",
   examples = """
     Examples:
       > SELECT _FUNC_('Spark', array(123), 2);

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -2569,7 +2569,7 @@ object functions {
   /**
    * Calculates the hash code of given columns using the 64-bit
    * variant of the xxHash algorithm, and returns the result as a long
-   * column.
+   * column. The hash computation uses an initial seed of 42.
    *
    * @group misc_funcs
    * @since 3.0.0