This is an automated email from the ASF dual-hosted git repository.
airborne12 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 7c2f99b1bc0 [refactor](index) Move collection similarity to shared
index code (#68602)
7c2f99b1bc0 is described below
commit 7c2f99b1bc03c0b43a877fe90837172f4de637c3
Author: Jack <[email protected]>
AuthorDate: Tue Sep 29 22:23:53 2026 +0800
[refactor](index) Move collection similarity to shared index code (#68602)
### What problem does this PR solve?
Problem Summary:
`CollectionSimilarity` is used by both inverted-index and SNII query
paths, but its source and header live under `storage/compaction`. Move
the implementation and its unit test to the shared `storage/index`
directory and update direct includes. No scoring logic changes.
---
be/src/storage/{compaction => index}/collection_similarity.cpp | 4 ++--
be/src/storage/{compaction => index}/collection_similarity.h | 0
be/src/storage/index/index_query_context.h | 2 +-
be/src/storage/index/inverted/query_v2/collect/doc_set_collector.h | 2 +-
be/src/storage/index/inverted/query_v2/collect/top_k_collector.h | 2 +-
.../inverted/query_v2/scored_bit_set_query/scored_bit_set_scorer.h | 2 +-
be/src/storage/segment/segment_iterator.cpp | 2 +-
.../storage/{compaction => index}/collection_similarity_test.cpp | 6 +++---
.../index/inverted/inverted_index_reader_analysis_purpose_test.cpp | 2 +-
be/test/storage/index/inverted/query/phrase_prefix_query_test.cpp | 2 +-
be/test/storage/index/inverted/query/query_helper_test.cpp | 4 ++--
be/test/storage/index/snii/snii_index_reader_candidate_test.cpp | 2 +-
12 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/be/src/storage/compaction/collection_similarity.cpp
b/be/src/storage/index/collection_similarity.cpp
similarity index 98%
rename from be/src/storage/compaction/collection_similarity.cpp
rename to be/src/storage/index/collection_similarity.cpp
index 9c4f2a35873..7afed5ded24 100644
--- a/be/src/storage/compaction/collection_similarity.cpp
+++ b/be/src/storage/index/collection_similarity.cpp
@@ -15,7 +15,7 @@
// specific language governing permissions and limitations
// under the License.
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "core/column/column_nullable.h"
#include "core/column/column_vector.h"
@@ -165,4 +165,4 @@ void CollectionSimilarity::find_top_k_scores(const
roaring::Roaring* row_bitmap,
}
}
-} // namespace doris
\ No newline at end of file
+} // namespace doris
diff --git a/be/src/storage/compaction/collection_similarity.h
b/be/src/storage/index/collection_similarity.h
similarity index 100%
rename from be/src/storage/compaction/collection_similarity.h
rename to be/src/storage/index/collection_similarity.h
diff --git a/be/src/storage/index/index_query_context.h
b/be/src/storage/index/index_query_context.h
index 159ff30746a..49a197c877e 100644
--- a/be/src/storage/index/index_query_context.h
+++ b/be/src/storage/index/index_query_context.h
@@ -20,7 +20,7 @@
#include <memory>
#include <roaring/roaring.hh>
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/inverted/similarity/collection_statistics.h"
namespace doris::segment_v2 {
diff --git a/be/src/storage/index/inverted/query_v2/collect/doc_set_collector.h
b/be/src/storage/index/inverted/query_v2/collect/doc_set_collector.h
index bad94d724bc..4cc0f09c9a7 100644
--- a/be/src/storage/index/inverted/query_v2/collect/doc_set_collector.h
+++ b/be/src/storage/index/inverted/query_v2/collect/doc_set_collector.h
@@ -20,7 +20,7 @@
#include <memory>
#include <roaring/roaring.hh>
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/inverted/query_v2/weight.h"
namespace doris::segment_v2::inverted_index::query_v2 {
diff --git a/be/src/storage/index/inverted/query_v2/collect/top_k_collector.h
b/be/src/storage/index/inverted/query_v2/collect/top_k_collector.h
index 8dbc564f13f..254d83f69ba 100644
--- a/be/src/storage/index/inverted/query_v2/collect/top_k_collector.h
+++ b/be/src/storage/index/inverted/query_v2/collect/top_k_collector.h
@@ -26,7 +26,7 @@
#include <string>
#include <vector>
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/inverted/query_v2/weight.h"
namespace doris::segment_v2::inverted_index::query_v2 {
diff --git
a/be/src/storage/index/inverted/query_v2/scored_bit_set_query/scored_bit_set_scorer.h
b/be/src/storage/index/inverted/query_v2/scored_bit_set_query/scored_bit_set_scorer.h
index 59aae9a09f1..503606d91a8 100644
---
a/be/src/storage/index/inverted/query_v2/scored_bit_set_query/scored_bit_set_scorer.h
+++
b/be/src/storage/index/inverted/query_v2/scored_bit_set_query/scored_bit_set_scorer.h
@@ -21,7 +21,7 @@
#include <utility>
#include "roaring/roaring.hh"
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/inverted/query_v2/bit_set_query/bit_set_scorer.h"
#include "storage/index/inverted/query_v2/scorer.h"
diff --git a/be/src/storage/segment/segment_iterator.cpp
b/be/src/storage/segment/segment_iterator.cpp
index ce02946b342..dabab3bfdaf 100644
--- a/be/src/storage/segment/segment_iterator.cpp
+++ b/be/src/storage/segment/segment_iterator.cpp
@@ -77,12 +77,12 @@
#include "runtime/thread_context.h"
#include "service/backend_options.h"
#include "storage/binlog.h"
-#include "storage/compaction/collection_similarity.h"
#include "storage/id_manager.h"
#include "storage/index/ann/ann_index.h"
#include "storage/index/ann/ann_index_iterator.h"
#include "storage/index/ann/ann_index_reader.h"
#include "storage/index/ann/ann_topn_runtime.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/index_file_reader.h"
#include "storage/index/index_iterator.h"
#include "storage/index/index_query_context.h"
diff --git a/be/test/storage/compaction/collection_similarity_test.cpp
b/be/test/storage/index/collection_similarity_test.cpp
similarity index 99%
rename from be/test/storage/compaction/collection_similarity_test.cpp
rename to be/test/storage/index/collection_similarity_test.cpp
index 7b5bf796353..3657b7089a0 100644
--- a/be/test/storage/compaction/collection_similarity_test.cpp
+++ b/be/test/storage/index/collection_similarity_test.cpp
@@ -15,7 +15,7 @@
// specific language governing permissions and limitations
// under the License.
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include <gtest/gtest.h>
@@ -643,7 +643,7 @@ TEST_F(CollectionSimilarityTest, LargeDataSparseBitmapTest)
{
for (size_t i = 0; i < NUM_SCORED_ROWS; ++i) {
float score = static_cast<float>(i + 1) /
static_cast<float>(NUM_SCORED_ROWS);
- similarity->collect(static_cast<uint32_t>(i * 100), score); // 稀疏分布
+ similarity->collect(static_cast<uint32_t>(i * 100), score);
}
std::vector<uint32_t> all_ids;
@@ -763,4 +763,4 @@ TEST_F(CollectionSimilarityTest,
LargeDataBoundaryThresholdTest) {
}
}
-} // namespace doris
\ No newline at end of file
+} // namespace doris
diff --git
a/be/test/storage/index/inverted/inverted_index_reader_analysis_purpose_test.cpp
b/be/test/storage/index/inverted/inverted_index_reader_analysis_purpose_test.cpp
index 7889b37dfe5..8407f4d6950 100644
---
a/be/test/storage/index/inverted/inverted_index_reader_analysis_purpose_test.cpp
+++
b/be/test/storage/index/inverted/inverted_index_reader_analysis_purpose_test.cpp
@@ -29,7 +29,7 @@
#include "io/fs/local_file_system.h"
#include "runtime/exec_env.h"
#include "runtime/runtime_state.h"
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/index_file_reader.h"
#include "storage/index/inverted/analyzer/analyzer.h"
#include "storage/index/inverted/analyzer/analyzer_provider.h"
diff --git a/be/test/storage/index/inverted/query/phrase_prefix_query_test.cpp
b/be/test/storage/index/inverted/query/phrase_prefix_query_test.cpp
index 94b0eca42b3..07863f708a8 100644
--- a/be/test/storage/index/inverted/query/phrase_prefix_query_test.cpp
+++ b/be/test/storage/index/inverted/query/phrase_prefix_query_test.cpp
@@ -23,7 +23,7 @@
#include "io/fs/local_file_system.h"
#include "runtime/exec_env.h"
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/index_file_reader.h"
#include "storage/index/index_file_writer.h"
#include "storage/index/inverted/inverted_index_cache.h"
diff --git a/be/test/storage/index/inverted/query/query_helper_test.cpp
b/be/test/storage/index/inverted/query/query_helper_test.cpp
index 95c1a3a6fad..51a47bdcbd9 100644
--- a/be/test/storage/index/inverted/query/query_helper_test.cpp
+++ b/be/test/storage/index/inverted/query/query_helper_test.cpp
@@ -22,7 +22,7 @@
#include <memory>
#include "common/be_mock_util.h"
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/index_query_context.h"
#include "storage/index/inverted/similarity/similarity.h"
#include "storage/index/inverted/util/mock_iterator.h"
@@ -276,4 +276,4 @@ TEST_F(QueryHelperTest, CollectMixedScenario) {
ASSERT_TRUE(_context->collection_similarity->_bm25_scores.count(1002) > 0);
ASSERT_TRUE(_context->collection_similarity->_bm25_scores.count(2000) > 0);
ASSERT_TRUE(_context->collection_similarity->_bm25_scores.count(2001) > 0);
-}
\ No newline at end of file
+}
diff --git a/be/test/storage/index/snii/snii_index_reader_candidate_test.cpp
b/be/test/storage/index/snii/snii_index_reader_candidate_test.cpp
index a1f4f71c36d..d58512f82b8 100644
--- a/be/test/storage/index/snii/snii_index_reader_candidate_test.cpp
+++ b/be/test/storage/index/snii/snii_index_reader_candidate_test.cpp
@@ -31,7 +31,7 @@
#include "io/fs/local_file_system.h"
#include "runtime/exec_env.h"
#include "runtime/runtime_state.h"
-#include "storage/compaction/collection_similarity.h"
+#include "storage/index/collection_similarity.h"
#include "storage/index/index_file_reader.h"
#include "storage/index/index_query_context.h"
#include "storage/index/inverted/analyzer/custom_analyzer.h"
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]