Fix format (#2852)

Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com>

Cargo.toml

@@ -47,7 +47,7 @@ rustc-hash = "2.0.0"
 thiserror = "2.0.1"
 htmlescape = "0.3.1"
 fail = { version = "0.5.0", optional = true }
-time = { version = "0.3.35", features = ["serde-well-known"] }
+time = { version = "0.3.47", features = ["serde-well-known"] }
 smallvec = "1.8.0"
 rayon = "1.5.2"
 lru = "0.16.3"
@@ -86,7 +86,7 @@ futures = "0.3.21"
 paste = "1.0.11"
 more-asserts = "0.3.1"
 rand_distr = "0.5"
-time = { version = "0.3.10", features = ["serde-well-known", "macros"] }
+time = { version = "0.3.47", features = ["serde-well-known", "macros"] }
 postcard = { version = "1.0.4", features = [
     "use-std",
 ], default-features = false }
@@ -201,4 +201,3 @@ harness = false
 [[bench]]
 name = "regex_all_terms"
 harness = false
-

common/Cargo.toml

@@ -15,11 +15,10 @@ repository = "https://github.com/quickwit-oss/tantivy"
 byteorder = "1.4.3"
 ownedbytes = { version= "0.9", path="../ownedbytes" }
 async-trait = "0.1"
-time = { version = "0.3.10", features = ["serde-well-known"] }
+time = { version = "0.3.47", features = ["serde-well-known"] }
 serde = { version = "1.0.136", features = ["derive"] }
 
 [dev-dependencies]
 binggan = "0.14.0"
 proptest = "1.0.0"
 rand = "0.9"
-

src/indexer/log_merge_policy.rs

@@ -94,7 +94,7 @@ impl MergePolicy for LogMergePolicy {
     fn compute_merge_candidates(&self, segments: &[SegmentMeta]) -> Vec<MergeCandidate> {
         let size_sorted_segments = segments
             .iter()
-            .filter(|seg| seg.num_docs() <= (self.max_docs_before_merge as u32))
+            .filter(|seg| (seg.num_docs() as usize) <= self.max_docs_before_merge)
             .sorted_by_key(|seg| std::cmp::Reverse(seg.max_doc()))
             .collect::<Vec<&SegmentMeta>>();
 
@@ -372,4 +372,21 @@ mod tests {
         assert_eq!(merge_candidates[0].0.len(), 1);
         assert_eq!(merge_candidates[0].0[0], test_input[1].id());
     }
+
+    #[test]
+    fn test_max_docs_before_merge_large_value() {
+        // Regression test: (max_docs_before_merge as u32) truncates values > u32::MAX.
+        // Casting num_docs() to usize instead avoids the truncation.
+        let mut policy = LogMergePolicy::default();
+        policy.set_min_num_segments(2);
+        policy.set_max_docs_before_merge(5_000_000_000usize);
+        let test_input = vec![
+            create_random_segment_meta(100_000),
+            create_random_segment_meta(100_000),
+        ];
+        let result = policy.compute_merge_candidates(&test_input);
+        // Both segments should be eligible (100_000 < 5_000_000_000)
+        assert_eq!(result.len(), 1);
+        assert_eq!(result[0].0.len(), 2);
+    }
 }

src/indexer/segment_updater.rs

@@ -403,7 +403,8 @@ impl SegmentUpdater {
             // from the different drives.
             //
             // Segment 1 from disk 1, Segment 1 from disk 2, etc.
-            committed_segment_metas.sort_by_key(|segment_meta| -(segment_meta.max_doc() as i32));
+            committed_segment_metas
+                .sort_by_key(|segment_meta| std::cmp::Reverse(segment_meta.max_doc()));
             let index_meta = IndexMeta {
                 index_settings: index.settings().clone(),
                 segments: committed_segment_metas,
@@ -705,6 +706,7 @@ mod tests {
     use crate::collector::TopDocs;
     use crate::directory::RamDirectory;
     use crate::fastfield::AliveBitSet;
+    use crate::index::{SegmentId, SegmentMetaInventory};
     use crate::indexer::merge_policy::tests::MergeWheneverPossible;
     use crate::indexer::merger::IndexMerger;
     use crate::indexer::segment_updater::merge_filtered_segments;
@@ -712,6 +714,22 @@ mod tests {
     use crate::schema::*;
     use crate::{Directory, DocAddress, Index, Segment};
 
+    #[test]
+    fn test_segment_sort_large_max_doc() {
+        // Regression test: -(max_doc as i32) overflows for max_doc >= 2^31.
+        // Using std::cmp::Reverse avoids this.
+        let inventory = SegmentMetaInventory::default();
+        let mut metas = vec![
+            inventory.new_segment_meta(SegmentId::generate_random(), 100),
+            inventory.new_segment_meta(SegmentId::generate_random(), (1u32 << 31) - 1),
+            inventory.new_segment_meta(SegmentId::generate_random(), 50_000),
+        ];
+        metas.sort_by_key(|m| std::cmp::Reverse(m.max_doc()));
+        assert_eq!(metas[0].max_doc(), (1u32 << 31) - 1);
+        assert_eq!(metas[1].max_doc(), 50_000);
+        assert_eq!(metas[2].max_doc(), 100);
+    }
+
     #[test]
     fn test_delete_during_merge() -> crate::Result<()> {
         let mut schema_builder = Schema::builder();

src/lib.rs

@@ -169,8 +169,10 @@ mod macros;
 mod future_result;
 
 // Re-exports
+pub use columnar;
 pub use common::{ByteCount, DateTime};
-pub use {columnar, query_grammar, time};
+pub use query_grammar;
+pub use time;
 
 pub use crate::error::TantivyError;
 pub use crate::future_result::FutureResult;