From ca87fcd454e57a748ce6201f2853e9183a9bebae Mon Sep 17 00:00:00 2001
From: Stu Hood <stuhood@gmail.com>
Date: Mon, 1 Dec 2025 03:26:29 -0800
Subject: [PATCH] Implement `collect_block` for `Collector`s which wrap other
 `Collector`s (#2727)

* Implement `collect_block` for tuple Collectors, and for MultiCollector.

* Two more.
---
 src/collector/filter_collector_wrapper.rs | 32 +++++++++++++++++++++++
 src/collector/mod.rs                      | 24 +++++++++++++++++
 src/collector/multi_collector.rs          |  6 +++++
 3 files changed, 62 insertions(+)

diff --git a/src/collector/filter_collector_wrapper.rs b/src/collector/filter_collector_wrapper.rs
index 167ec980b..4e09b027c 100644
--- a/src/collector/filter_collector_wrapper.rs
+++ b/src/collector/filter_collector_wrapper.rs
@@ -120,6 +120,7 @@ where
             segment_collector,
             predicate: self.predicate.clone(),
             t_predicate_value: PhantomData,
+            filtered_docs: Vec::with_capacity(crate::COLLECT_BLOCK_BUFFER_LEN),
         })
     }
 
@@ -140,6 +141,7 @@ pub struct FilterSegmentCollector<TSegmentCollector, TPredicate, TPredicateValue
     segment_collector: TSegmentCollector,
     predicate: TPredicate,
     t_predicate_value: PhantomData<TPredicateValue>,
+    filtered_docs: Vec<DocId>,
 }
 
 impl<TSegmentCollector, TPredicate, TPredicateValue>
@@ -176,6 +178,20 @@ where
         }
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        self.filtered_docs.clear();
+        for &doc in docs {
+            // TODO: `accept_document` could be further optimized to do batch lookups of column
+            // values for single-valued columns.
+            if self.accept_document(doc) {
+                self.filtered_docs.push(doc);
+            }
+        }
+        if !self.filtered_docs.is_empty() {
+            self.segment_collector.collect_block(&self.filtered_docs);
+        }
+    }
+
     fn harvest(self) -> TSegmentCollector::Fruit {
         self.segment_collector.harvest()
     }
@@ -274,6 +290,7 @@ where
             segment_collector,
             predicate: self.predicate.clone(),
             buffer: Vec::new(),
+            filtered_docs: Vec::with_capacity(crate::COLLECT_BLOCK_BUFFER_LEN),
         })
     }
 
@@ -296,6 +313,7 @@ where TPredicate: 'static
     segment_collector: TSegmentCollector,
     predicate: TPredicate,
     buffer: Vec<u8>,
+    filtered_docs: Vec<DocId>,
 }
 
 impl<TSegmentCollector, TPredicate> BytesFilterSegmentCollector<TSegmentCollector, TPredicate>
@@ -334,6 +352,20 @@ where
         }
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        self.filtered_docs.clear();
+        for &doc in docs {
+            // TODO: `accept_document` could be further optimized to do batch lookups of column
+            // values for single-valued columns.
+            if self.accept_document(doc) {
+                self.filtered_docs.push(doc);
+            }
+        }
+        if !self.filtered_docs.is_empty() {
+            self.segment_collector.collect_block(&self.filtered_docs);
+        }
+    }
+
     fn harvest(self) -> TSegmentCollector::Fruit {
         self.segment_collector.harvest()
     }
diff --git a/src/collector/mod.rs b/src/collector/mod.rs
index a31754316..6c509fcfb 100644
--- a/src/collector/mod.rs
+++ b/src/collector/mod.rs
@@ -214,6 +214,12 @@ impl<TSegmentCollector: SegmentCollector> SegmentCollector for Option<TSegmentCo
         }
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        if let Some(segment_collector) = self {
+            segment_collector.collect_block(docs);
+        }
+    }
+
     fn harvest(self) -> Self::Fruit {
         self.map(|segment_collector| segment_collector.harvest())
     }
@@ -342,6 +348,11 @@ where
         self.1.collect(doc, score);
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        self.0.collect_block(docs);
+        self.1.collect_block(docs);
+    }
+
     fn harvest(self) -> <Self as SegmentCollector>::Fruit {
         (self.0.harvest(), self.1.harvest())
     }
@@ -407,6 +418,12 @@ where
         self.2.collect(doc, score);
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        self.0.collect_block(docs);
+        self.1.collect_block(docs);
+        self.2.collect_block(docs);
+    }
+
     fn harvest(self) -> <Self as SegmentCollector>::Fruit {
         (self.0.harvest(), self.1.harvest(), self.2.harvest())
     }
@@ -482,6 +499,13 @@ where
         self.3.collect(doc, score);
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        self.0.collect_block(docs);
+        self.1.collect_block(docs);
+        self.2.collect_block(docs);
+        self.3.collect_block(docs);
+    }
+
     fn harvest(self) -> <Self as SegmentCollector>::Fruit {
         (
             self.0.harvest(),
diff --git a/src/collector/multi_collector.rs b/src/collector/multi_collector.rs
index 8077577d2..7d2196e02 100644
--- a/src/collector/multi_collector.rs
+++ b/src/collector/multi_collector.rs
@@ -250,6 +250,12 @@ impl SegmentCollector for MultiCollectorChild {
         }
     }
 
+    fn collect_block(&mut self, docs: &[DocId]) {
+        for child in &mut self.children {
+            child.collect_block(docs);
+        }
+    }
+
     fn harvest(self) -> MultiFruit {
         MultiFruit {
             sub_fruits: self