(datafusion) branch main updated: fix: accept LargeUtf8 and Utf8View patterns in SIMILAR TO planning (#23735)

[gi...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

github-merge-queue[bot] pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git


The following commit(s) were added to refs/heads/main by this push:
     new 5f7feda66b fix: accept LargeUtf8 and Utf8View patterns in SIMILAR TO planning (#23735)
5f7feda66b is described below

commit 5f7feda66b1f460e9655ba33e749ae0fa8602553
Author: kid <19...@users.noreply.github.com>
AuthorDate: Wed Jul 29 19:39:45 2026 +0800

    fix: accept LargeUtf8 and Utf8View patterns in SIMILAR TO planning (#23735)
    
    ## Which issue does this PR close?
    
    - Closes #23732
    
    ## Rationale for this change
    
    Follow-up to #23704, which made the `TypeCoercion` analyzer coerce
    `SIMILAR TO` operands to a common string type. The SQL planner still
    rejects `LargeUtf8` and `Utf8View` **patterns** before the analyzer ever
    runs:
    
    ```sql
    SELECT s FROM test, patterns WHERE s SIMILAR TO arrow_cast(pat, 'Utf8View');
    -- error: Invalid pattern in SIMILAR TO expression
    ```
    
    Now that the analyzer coerces both operands, this planner restriction is
    unnecessary (and inconsistent with `LIKE`, whose planner path has no
    such check).
    
    ## What changes are included in this PR?
    
    - `datafusion/sql/src/expr/mod.rs`: the pattern-type check in
    `sql_similarto_to_expr` now accepts `Utf8` / `LargeUtf8` / `Utf8View` /
    `Null` instead of only `Utf8` / `Null`.
    - `datafusion/sqllogictest/test_files/type_coercion.slt`: regression
    tests with non-literal `Utf8View` and `LargeUtf8` patterns (plus a `NOT
    SIMILAR TO` case), next to the existing #22886 regression tests.
    
    The planner relaxation and tests were originally part of #22887; this PR
    lands the remaining piece of it.
    
    ## Are these changes tested?
    
    Yes — new sqllogictest cases in `type_coercion.slt`. The existing
    planner rejection of non-string patterns (`SELECT 'a' SIMILAR TO 1`)
    still errors as before.
    
    ## Are there any user-facing changes?
    
    Yes: `SIMILAR TO` queries with non-literal `LargeUtf8` / `Utf8View`
    patterns that previously failed during SQL planning with `Invalid
    pattern in SIMILAR TO expression` now plan and execute successfully. No
    breaking API changes.
---
 datafusion/sql/src/expr/mod.rs                     |  4 --
 .../sqllogictest/test_files/type_coercion.slt      | 46 ++++++++++++++++++++--
 2 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/datafusion/sql/src/expr/mod.rs b/datafusion/sql/src/expr/mod.rs
index c00dcb82ff..c2e4822f76 100644
--- a/datafusion/sql/src/expr/mod.rs
+++ b/datafusion/sql/src/expr/mod.rs
@@ -1008,10 +1008,6 @@ impl<S: ContextProvider> SqlToRel<'_, S> {
         planner_context: &mut PlannerContext,
     ) -> Result<Expr> {
         let pattern = self.sql_expr_to_logical_expr(pattern, schema, planner_context)?;
-        let pattern_type = pattern.get_type(schema)?;
-        if pattern_type != DataType::Utf8 && pattern_type != DataType::Null {
-            return plan_err!("Invalid pattern in SIMILAR TO expression");
-        }
         let escape_char = match escape_char.map(|v| v.value) {
             Some(Value::SingleQuotedString(char)) if char.len() == 1 => {
                 Some(char.chars().next().unwrap())
diff --git a/datafusion/sqllogictest/test_files/type_coercion.slt b/datafusion/sqllogictest/test_files/type_coercion.slt
index 7ec0f5f1db..6a56fc2407 100644
--- a/datafusion/sqllogictest/test_files/type_coercion.slt
+++ b/datafusion/sqllogictest/test_files/type_coercion.slt
@@ -304,7 +304,9 @@ query error does not support zero arguments
 SELECT * FROM (SELECT 1) WHERE TRY_CAST(STARTS_WITH() AS INT) = 1;
 
 ###################################################################
-## SIMILAR TO type coercion (https://github.com/apache/datafusion/issues/22886)
+## SIMILAR TO type coercion
+## https://github.com/apache/datafusion/issues/22886
+## https://github.com/apache/datafusion/issues/23732
 ###################################################################
 
 # NULL pattern is coerced to a typed NULL and evaluates to NULL instead of panicking
@@ -349,6 +351,44 @@ SELECT arrow_cast(t.s, 'Dictionary(Int32, Utf8)') SIMILAR TO p.pat FROM t CROSS
 ----
 true
 
+# non-scalar string-like patterns are coerced by the analyzer
+query B
+SELECT t.s SIMILAR TO arrow_cast(p.pat, 'Utf8View') FROM t CROSS JOIN p;
+----
+true
+
+query B
+SELECT t.s SIMILAR TO arrow_cast(p.pat, 'LargeUtf8') FROM t CROSS JOIN p;
+----
+true
+
+query B
+SELECT t.s NOT SIMILAR TO arrow_cast(p.pat, 'Utf8View') FROM t CROSS JOIN p;
+----
+false
+
+query B
+SELECT t.s SIMILAR TO arrow_cast(p.pat, 'Dictionary(Int32, Utf8)') FROM t CROSS JOIN p;
+----
+true
+
+# NULL patterns (literal or Null-typed non-scalar) evaluate to NULL
+query B
+SELECT t.s SIMILAR TO NULL FROM t;
+----
+NULL
+
+statement ok
+CREATE TABLE pn AS SELECT NULL AS pat;
+
+query B
+SELECT t.s SIMILAR TO pn.pat FROM t CROSS JOIN pn;
+----
+NULL
+
+statement ok
+DROP TABLE pn;
+
 statement ok
 DROP TABLE t;
 
@@ -359,6 +399,6 @@ DROP TABLE p;
 query error There isn't a common type to coerce Int64 and Utf8 in SIMILAR TO expression
 SELECT 1 SIMILAR TO 'a';
 
-# a non-string pattern is rejected even earlier, during SQL planning
-query error Invalid pattern in SIMILAR TO expression
+# a non-string pattern is rejected by the analyzer
+query error There isn't a common type to coerce Utf8 and Int64 in SIMILAR TO expression
 SELECT 'a' SIMILAR TO 1;


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@datafusion.apache.org
For additional commands, e-mail: commits-help@datafusion.apache.org