adriangb commented on code in PR #12978:
URL: https://github.com/apache/datafusion/pull/12978#discussion_r1898531783
##########
datafusion/physical-optimizer/src/pruning.rs:
##########
@@ -1607,6 +1629,127 @@ fn build_statistics_expr(
Ok(statistics_expr)
}
+/// Convert `column LIKE literal` where P is a constant prefix of the literal
+/// to a range check on the column: `P <= column && column < P'`, where P' is
the
+/// lowest string after all P* strings.
+fn build_like_match(
+ expr_builder: &mut PruningExpressionBuilder,
+) -> Option<Arc<dyn PhysicalExpr>> {
+ // column LIKE literal => (min, max) LIKE literal split at % => min <=
split literal && split literal <= max
+ // column LIKE 'foo%' => min <= 'foo' && 'foo' <= max
+ // column LIKE '%foo' => min <= '' && '' <= max => true
+ // column LIKE '%foo%' => min <= '' && '' <= max => true
+ // column LIKE 'foo' => min <= 'foo' && 'foo' <= max
+
+ fn unpack_string(s: &ScalarValue) -> Option<&String> {
+ match s {
+ ScalarValue::Utf8(Some(s)) => Some(s),
+ ScalarValue::LargeUtf8(Some(s)) => Some(s),
+ ScalarValue::Utf8View(Some(s)) => Some(s),
+ ScalarValue::Dictionary(_, value) => unpack_string(value),
+ _ => None,
+ }
+ }
+
+ fn extract_string_literal(expr: &Arc<dyn PhysicalExpr>) -> Option<&String>
{
+ if let Some(lit) = expr.as_any().downcast_ref::<phys_expr::Literal>() {
+ let s = unpack_string(lit.value())?;
+ return Some(s);
+ }
+ None
+ }
+
+ // TODO Handle ILIKE perhaps by making the min lowercase and max uppercase
+ // this may involve building the physical expressions that call lower()
and upper()
+ let min_column_expr = expr_builder.min_column_expr().ok()?;
+ let max_column_expr = expr_builder.max_column_expr().ok()?;
+ let scalar_expr = expr_builder.scalar_expr();
+ // check that the scalar is a string literal
+ let s = extract_string_literal(scalar_expr)?;
+ // ANSI SQL specifies two wildcards: % and _. % matches zero or more
characters, _ matches exactly one character.
+ let first_wildcard_index = s.find(['%', '_']);
+ if first_wildcard_index == Some(0) {
+ // there's no filtering we could possibly do, return an error and have
this be handled by the unhandled hook
+ return None;
+ }
+ let (lower_bound, upper_bound) = if let Some(wildcard_index) =
first_wildcard_index {
+ let prefix = &s[..wildcard_index];
+ let lower_bound_lit =
Arc::new(phys_expr::Literal::new(ScalarValue::Utf8(Some(
+ prefix.to_string(),
+ ))));
+ let upper_bound_lit =
Arc::new(phys_expr::Literal::new(ScalarValue::Utf8(Some(
+ increment_utf8(prefix)?,
+ ))));
+ (lower_bound_lit, upper_bound_lit)
+ } else {
+ // the like expression is a literal and can be converted into a
comparison
+ let bound =
Arc::new(phys_expr::Literal::new(ScalarValue::Utf8(Some(s.clone()))));
+ (Arc::clone(&bound), bound)
+ };
+ let lower_bound_expr = Arc::new(phys_expr::BinaryExpr::new(
+ lower_bound,
+ Operator::LtEq,
+ Arc::clone(&max_column_expr),
+ ));
+ let upper_bound_expr = Arc::new(phys_expr::BinaryExpr::new(
+ Arc::clone(&min_column_expr),
+ Operator::LtEq,
+ upper_bound,
+ ));
+ let combined = Arc::new(phys_expr::BinaryExpr::new(
+ upper_bound_expr,
+ Operator::And,
+ lower_bound_expr,
+ ));
+ Some(combined)
+}
+
+/// Increment a UTF8 string by one, returning `None` if it can't be
incremented.
+/// This makes it so that the returned string will always compare greater than
the input string
+/// or any other string with the same prefix.
+/// This is necessary since the statistics may have been truncated: if we have
a min statistic
+/// of "fo" that may have originally been "foz" or anything else with the
prefix "fo".
+/// E.g. `increment_utf8("foo") >= "foo"` and `increment_utf8("foo") >= "fooz"`
+/// In this example `increment_utf8("foo") == "fop"
+fn increment_utf8(data: &str) -> Option<String> {
Review Comment:
I haven't reviewed that implementation but yes I think we should consider it!
--
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
