Migrate to new stats falsification rules

.github/workflows/ci.yml

@@ -376,6 +376,10 @@ jobs:
         with:
           sccache: s3
       - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6
+      - uses: actions/setup-java@be666c2fcd27ec809703dec50e508c2fdc7f6654  # v5
+        with:
+          distribution: "corretto"
+          java-version: "17"
       - uses: ./.github/actions/setup-prebuild
       - run: ./gradlew javadoc
         working-directory: ./java

vortex-array/src/expr/expression.rs

@@ -15,9 +15,7 @@ use vortex_error::vortex_ensure;
 use vortex_session::VortexSession;
 
 use crate::dtype::DType;
-use crate::expr::StatsCatalog;
 use crate::expr::display::DisplayTreeExpr;
-use crate::expr::stats::Stat;
 use crate::scalar_fn::ScalarFnRef;
 use crate::scalar_fn::fns::root::Root;
 
@@ -114,28 +112,6 @@ impl Expression {
         self.scalar_fn.validity(self)
     }
 
-    /// An expression over zone-statistics which implies all records in the zone evaluate to false.
-    ///
-    /// Given an expression, `e`, if `e.stat_falsification(..)` evaluates to true, it is guaranteed
-    /// that `e` evaluates to false on all records in the zone. However, the inverse is not
-    /// necessarily true: even if the falsification evaluates to false, `e` need not evaluate to
-    /// true on all records.
-    ///
-    /// The [`StatsCatalog`] can be used to constrain or rename stats used in the final expr.
-    ///
-    /// # Examples
-    ///
-    /// - An expression over one variable: `x > 0` is false for all records in a zone if the maximum
-    ///   value of the column `x` in that zone is less than or equal to zero: `max(x) <= 0`.
-    /// - An expression over two variables: `x > y` becomes `max(x) <= min(y)`.
-    /// - A conjunctive expression: `x > y AND z < x` becomes `max(x) <= min(y) OR min(z) >= max(x).
-    ///
-    /// Some expressions, in theory, have falsifications but this function does not support them
-    /// such as `x < (y < z)` or `x LIKE "needle%"`.
-    pub fn stat_falsification(&self, catalog: &dyn StatsCatalog) -> Option<Expression> {
-        self.scalar_fn().stat_falsification(self, catalog)
-    }
-
     /// Returns an expression that proves this predicate is definitely false from stats.
     ///
     /// `scope` is the dtype of the row this expression evaluates over.
@@ -164,28 +140,6 @@ impl Expression {
         crate::stats::rewrite::StatsRewriteCtx::new(session, scope).satisfy(self)
     }
 
-    /// Returns an expression representing the zoned statistic for the given stat, if available.
-    ///
-    /// The [`StatsCatalog`] returns expressions that can be evaluated using the zone map as a
-    /// scope. Expressions can implement this function to propagate such statistics through the
-    /// expression tree. For example, the `a + 10` expression could propagate `min: min(a) + 10`.
-    ///
-    /// NOTE(gatesn): we currently cannot represent statistics over nested fields. Please file an
-    /// issue to discuss a solution to this.
-    pub fn stat_expression(&self, stat: Stat, catalog: &dyn StatsCatalog) -> Option<Expression> {
-        self.scalar_fn().stat_expression(self, stat, catalog)
-    }
-
-    /// Returns an expression representing the zoned maximum statistic, if available.
-    pub fn stat_min(&self, catalog: &dyn StatsCatalog) -> Option<Expression> {
-        self.stat_expression(Stat::Min, catalog)
-    }
-
-    /// Returns an expression representing the zoned maximum statistic, if available.
-    pub fn stat_max(&self, catalog: &dyn StatsCatalog) -> Option<Expression> {
-        self.stat_expression(Stat::Max, catalog)
-    }
-
     /// Format the expression as a compact string.
     ///
     /// Since this is a recursive formatter, it is exposed on the public Expression type.

vortex-array/src/expr/mod.rs

@@ -42,7 +42,6 @@ pub mod traversal;
 pub use analysis::*;
 pub use expression::*;
 pub use exprs::*;
-pub use pruning::StatsCatalog;
 
 pub trait VortexExprExt {
     /// Accumulate all field references from this expression and its children in a set

vortex-array/src/expr/pruning/mod.rs

@@ -8,20 +8,3 @@ pub use pruning_expr::RequiredStats;
 pub use pruning_expr::checked_pruning_expr;
 pub use pruning_expr::field_path_stat_field_name;
 pub use relation::Relation;
-
-use crate::dtype::FieldPath;
-use crate::expr::Expression;
-use crate::expr::stats::Stat;
-
-/// A catalog of available stats that are associated with field paths.
-pub trait StatsCatalog {
-    /// Given a field path and statistic, return an expression that when evaluated over the catalog
-    /// will return that stat for the referenced field.
-    ///
-    /// This is likely to be a column expression, or a literal.
-    ///
-    /// Returns `None` if the stat is not available for the field path.
-    fn stats_ref(&self, _field_path: &FieldPath, _stat: Stat) -> Option<Expression> {
-        None
-    }
-}