crepererum commented on code in PR #4646:
URL: https://github.com/apache/arrow-datafusion/pull/4646#discussion_r1059877878
##########
datafusion/optimizer/src/simplify_expressions/expr_simplifier.rs:
##########
@@ -1576,17 +1589,166 @@ mod tests {
assert_eq!(simplify(expr), expected)
}
+ #[test]
+ fn test_simplify_regex() {
+ // malformed regex
+ assert_contains!(
+ try_simplify(regex_match(col("c1"), lit("foo{")))
+ .unwrap_err()
+ .to_string(),
+ "regex parse error"
+ );
+
+ // unsupported cases
+ assert_no_change(regex_match(col("c1"), lit("foo.*")));
+ assert_no_change(regex_match(col("c1"), lit("(foo)")));
+ assert_no_change(regex_match(col("c1"), lit("^foo")));
+ assert_no_change(regex_match(col("c1"), lit("foo$")));
+ assert_no_change(regex_match(col("c1"), lit("%")));
+ assert_no_change(regex_match(col("c1"), lit("_")));
+ assert_no_change(regex_match(col("c1"), lit("f%o")));
+ assert_no_change(regex_match(col("c1"), lit("f_o")));
+
+ // empty cases
+ assert_change(regex_match(col("c1"), lit("")), like(col("c1"), "%"));
+ assert_change(
+ regex_not_match(col("c1"), lit("")),
+ not_like(col("c1"), "%"),
+ );
+ assert_change(regex_imatch(col("c1"), lit("")), ilike(col("c1"), "%"));
+ assert_change(
+ regex_not_imatch(col("c1"), lit("")),
+ not_ilike(col("c1"), "%"),
+ );
+
+ // single character
+ assert_change(regex_match(col("c1"), lit("x")), like(col("c1"),
"%x%"));
+
+ // single word
+ assert_change(regex_match(col("c1"), lit("foo")), like(col("c1"),
"%foo%"));
+
+ // OR-chain
+ assert_change(
+ regex_match(col("c1"), lit("foo|bar|baz")),
Review Comment:
We can extend the rewrite logic at one point to spot fully anchored regex
expressions (i.e. the ones that span the whole string, not any substring). In
this case we could emit EQ/NEQ/IN.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
