feat(pyspark, duckdb): add hexdigest support

ibis/backends/duckdb/registry.py

@@ -397,6 +397,16 @@ def _array_remove(t, op):
     )
 
 
+def _hexdigest(translator, op):
+    how = op.how
+
+    arg_formatted = translator.translate(op.arg)
+    if how in ("md5", "sha256"):
+        return getattr(sa.func, how)(arg_formatted)
+    else:
+        raise NotImplementedError(how)
+
+
 operation_registry.update(
     {
         ops.Array: (
@@ -533,6 +543,7 @@ def _array_remove(t, op):
         ops.MapValues: unary(sa.func.map_values),
         ops.MapMerge: fixed_arity(sa.func.map_concat, 2),
         ops.Hash: unary(sa.func.hash),
+        ops.HashHexDigest: _hexdigest,
         ops.Median: reduction(sa.func.median),
         ops.First: reduction(sa.func.first),
         ops.Last: reduction(sa.func.last),

ibis/backends/pyspark/compiler.py

@@ -2065,6 +2065,21 @@ def compile_hash_column(t, op, **kwargs):
     return F.hash(t.translate(op.arg, **kwargs))
 
 
+@compiles(ops.HashHexDigest)
+def compile_hexdigest_column(t, op, **kwargs):
+    how = op.how
+    arg = t.translate(op.arg, **kwargs)
+
+    if how == "md5":
+        return F.md5(arg)
+    elif how == "sha1":
+        return F.sha1(arg)
+    elif how in ("sha256", "sha512"):
+        return F.sha2(arg, int(how[-3:]))
+    else:
+        raise NotImplementedError(how)
+
+
 @compiles(ops.ArrayZip)
 def compile_zip(t, op, **kwargs):
     return F.arrays_zip(*map(partial(t.translate, **kwargs), op.arg))