fix: escape underscores when simplifying starts_with (#19076)

Author: willemv

datafusion/functions/src/string/starts_with.rs

@@ -132,15 +132,18 @@ impl ScalarUDFImpl for StartsWithFunc {
     ) -> Result<ExprSimplifyResult> {
         if let Expr::Literal(scalar_value, _) = &args[1] {
             // Convert starts_with(col, 'prefix') to col LIKE 'prefix%' with proper escaping
-            // Example: starts_with(col, 'ja%') -> col LIKE 'ja\%%'
-            //   1. 'ja%'         (input pattern)
-            //   2. 'ja\%'        (escape special char '%')
-            //   3. 'ja\%%'       (add suffix for starts_with)
+            // Escapes pattern characters: starts_with(col, 'j\_a%') -> col LIKE 'j\\\_a\%%'
+            //   1. 'j\_a%'         (input pattern)
+            //   2. 'j\\\_a\%'       (escape special chars '%', '_' and '\')
+            //   3. 'j\\\_a\%%'      (add unescaped % suffix for starts_with)
             let like_expr = match scalar_value {
                 ScalarValue::Utf8(Some(pattern))
                 | ScalarValue::LargeUtf8(Some(pattern))
                 | ScalarValue::Utf8View(Some(pattern)) => {
-                    let escaped_pattern = pattern.replace("%", "\\%");
+                    let escaped_pattern = pattern
+                        .replace("\\", "\\\\")
+                        .replace("%", "\\%")
+                        .replace("_", "\\_");
                     let like_pattern = format!("{escaped_pattern}%");
                     Expr::Literal(ScalarValue::Utf8(Some(like_pattern)), None)
                 }

datafusion/sqllogictest/test_files/string/string_literal.slt

@@ -207,6 +207,25 @@ SELECT ends_with('foobar', 'foo')
 ----
 false
 
+query B
+SELECT ends_with(a, '%bar') from (values ('foobar'), ('foo%bar')) as t(a);
+----
+false
+true
+
+query B
+SELECT ends_with(a, '_bar') from (values ('foobar'), ('foo_bar')) as t(a);
+----
+false
+true
+
+query B
+SELECT ends_with(a, '\_bar') from (values ('foobar'), ('foo\\bar'), ('foo\_bar')) as t(a);
+----
+false
+false
+true
+
 query I
 SELECT levenshtein('kitten', 'sitting')
 ----
@@ -846,6 +865,26 @@ SELECT starts_with('foobar', 'bar')
 ----
 false
 
+
+query B
+SELECT starts_with(a, 'foo%') from (values ('foobar'), ('foo%bar')) as t(a);
+----
+false
+true
+
+query B
+SELECT starts_with(a, 'foo\_') from (values ('foobar'), ('foo\\_bar'), ('foo\_bar')) as t(a);
+----
+false
+false
+true
+
+query B
+SELECT starts_with(a, 'foo_') from (values ('foobar'), ('foo_bar')) as t(a);
+----
+false
+true
+
 query TT
 select '   ', '|'
 ----

datafusion/sqllogictest/test_files/string/string_view.slt

@@ -370,7 +370,7 @@ EXPLAIN SELECT
 FROM test;
 ----
 logical_plan
-01)Projection: test.column1_utf8 LIKE Utf8("foo\%%") AS c1, test.column1_large_utf8 LIKE LargeUtf8("foo\%%") AS c2, test.column1_utf8view LIKE Utf8View("foo\%%") AS c3, test.column1_utf8 LIKE Utf8("f_o%") AS c4, test.column1_large_utf8 LIKE LargeUtf8("f_o%") AS c5, test.column1_utf8view LIKE Utf8View("f_o%") AS c6
+01)Projection: test.column1_utf8 LIKE Utf8("foo\%%") AS c1, test.column1_large_utf8 LIKE LargeUtf8("foo\%%") AS c2, test.column1_utf8view LIKE Utf8View("foo\%%") AS c3, test.column1_utf8 LIKE Utf8("f\_o%") AS c4, test.column1_large_utf8 LIKE LargeUtf8("f\_o%") AS c5, test.column1_utf8view LIKE Utf8View("f\_o%") AS c6
 02)--TableScan: test projection=[column1_utf8, column1_large_utf8, column1_utf8view]
 
 ## Test STARTS_WITH works with column arguments