UBarney commented on code in PR #14567:
URL: https://github.com/apache/datafusion/pull/14567#discussion_r1954594478
##########
datafusion/physical-optimizer/src/pruning.rs:
##########
@@ -4061,6 +4132,106 @@ mod tests {
prune_with_expr(expr, &schema, &statistics, expected_ret);
}
+ #[test]
+ fn prune_utf8_not_like_one() {
+ let (schema, statistics) = utf8_setup();
+
+ let expr = col("s1").not_like(lit("A\u{10ffff}_"));
+ #[rustfmt::skip]
+ let expected_ret = &[
+ // s1 ["A", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["A", "L"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["N", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["M", "M"] ==> some rows could pass (must keep)
+ true,
+ // s1 [NULL, NULL] ==> unknown (must keep)
+ true,
+ // s1 ["A", NULL] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", "A"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", ""] ==> some rows could pass (must keep)
+ true,
+ // s1 ["AB", "A\u{10ffff}\u{10ffff}\u{10ffff}"] ==> some rows
could pass (must keep)
+ true,
+ // s1 ["A\u{10ffff}\u{10ffff}", "A\u{10ffff}\u{10ffff}"] ==> no
row match. (min, max) maybe truncate
+ // orignal (min, max) maybe ("A\u{10ffff}\u{10ffff}\u{10ffff}",
"A\u{10ffff}\u{10ffff}\u{10ffff}\u{10ffff}")
+ true,
+ ];
+ prune_with_expr(expr, &schema, &statistics, expected_ret);
+ }
+
+ #[test]
+ fn prune_utf8_not_like_many() {
+ let (schema, statistics) = utf8_setup();
+
+ let expr = col("s1").not_like(lit("A\u{10ffff}%"));
+ #[rustfmt::skip]
+ let expected_ret = &[
+ // s1 ["A", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["A", "L"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["N", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["M", "M"] ==> some rows could pass (must keep)
+ true,
+ // s1 [NULL, NULL] ==> unknown (must keep)
+ true,
+ // s1 ["A", NULL] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", "A"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", ""] ==> some rows could pass (must keep)
+ true,
+ // s1 ["AB", "A\u{10ffff}\u{10ffff}\u{10ffff}"] ==> some rows
could pass (must keep)
+ true,
+ // s1 ["A\u{10ffff}\u{10ffff}", "A\u{10ffff}\u{10ffff}"] ==> no
row match
+ false,
+ ];
+ prune_with_expr(expr, &schema, &statistics, expected_ret);
+
+ let expr = col("s1").not_like(lit("A\u{10ffff}%\u{10ffff}"));
+ #[rustfmt::skip]
+ let expected_ret = &[
+ // s1 ["A", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["A", "L"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["N", "Z"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["M", "M"] ==> some rows could pass (must keep)
+ true,
+ // s1 [NULL, NULL] ==> unknown (must keep)
+ true,
+ // s1 ["A", NULL] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", "A"] ==> some rows could pass (must keep)
+ true,
+ // s1 ["", ""] ==> some rows could pass (must keep)
+ true,
+ // s1 ["AB", "A\u{10ffff}\u{10ffff}\u{10ffff}"] ==> some rows
could pass (must keep)
+ true,
+ // s1 ["A\u{10ffff}\u{10ffff}", "A\u{10ffff}\u{10ffff}"] ==> some
rows could pass (must keep)
+ true,
+ ];
+ prune_with_expr(expr, &schema, &statistics, expected_ret);
+
+ let expr = col("s1").not_like(lit("A\\%%"));
Review Comment:
add `not like A\u{10ffff}%\u{10ffff}_`. I think existing testcase
`col("s1").not_like(lit("A\u{10ffff}%\u{10ffff}"))` is equivalent to `NOT LIKE
'foo%bar'`
--
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...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
