add length_bytes

Eventual-Inc · Sep 26, 2024 · 69c09b1 · 69c09b1
1 parent 6cb363e
commit 69c09b1
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/src/daft-sql/src/modules/utf8.rs b/src/daft-sql/src/modules/utf8.rs
@@ -38,6 +38,7 @@ impl SQLModule for SQLModuleUtf8 {
         // TODO add replace variants
         // parent.add("replace", f(Replace(false)));
         parent.add_fn("length", Length);
+        parent.add_fn("length_bytes", LengthBytes);
         parent.add_fn("lower", Lower);
         parent.add_fn("upper", Upper);
         parent.add_fn("lstrip", Lstrip);

diff --git a/tests/sql/test_utf8_exprs.py b/tests/sql/test_utf8_exprs.py
@@ -38,6 +38,7 @@ def test_utf8_exprs():
         regexp_replace(a, 'ba.', 'foo') as replace_a,
         regexp_split(a, '\\s+') as regexp_split_a,
         length(a) as length_a,
+        length_bytes(a) as length_bytes_a,
         lower(a) as lower_a,
         lstrip(a) as lstrip_a,
         rstrip(a) as rstrip_a,
@@ -77,6 +78,7 @@ def test_utf8_exprs():
             col("a").str.split(r"\s+", regex=True).alias("regexp_split_a"),
             col("a").str.replace("ba.", "foo").alias("replace_a"),
             col("a").str.length().alias("length_a"),
+            col("a").str.length_bytes().alias("length_bytes_a"),
             col("a").str.lower().alias("lower_a"),
             col("a").str.lstrip().alias("lstrip_a"),
             col("a").str.rstrip().alias("rstrip_a"),