fix: optimize after crash recovery without opening wal (#600)

Author: feihongxu0824

src/db/index/segment/segment.cc

@@ -4224,8 +4224,6 @@ Status SegmentImpl::recover() {
               wal_file_path.c_str());
     return Status::OK();
   }
-  AILEGO_DEFER([&]() { recover_wal_file->close(); });
-
   std::array<uint64_t, static_cast<size_t>(Operator::DELETE) + 1>
       recovered_doc_count{};
   uint64_t total_recovered_doc_count{0};
@@ -4309,7 +4307,17 @@ Status SegmentImpl::recover() {
       (size_t)recovered_doc_count[3]   // DELETE
   );
 
-  return Status::OK();
+  if (recover_wal_file->close() != 0) {
+    return Status::InternalError("Failed to close recovered wal file: ",
+                                 wal_file_path);
+  }
+  recover_wal_file.reset();
+
+  // Keep the recovered WAL attached to the segment. Operations such as
+  // optimize() flush the writing segment before sealing it; without an open
+  // member WAL, flush() treats the recovered memory components as empty and
+  // returns without persisting them.
+  return open_wal_file();
 }
 
 Status SegmentImpl::open_wal_file() {

tests/db/crash_recovery/write_recovery_test.cc

@@ -218,6 +218,39 @@ TEST_F(CrashRecoveryTest, CrashRecoveryDuringInsertion) {
 }
 
 
+TEST_F(CrashRecoveryTest, OptimizeAfterCrashRecoveryPersistsReplayedData) {
+  {
+    auto schema = CreateTestSchema(collection_name_);
+    auto result = Collection::CreateAndOpen(dir_path_, *schema, options_);
+    ASSERT_TRUE(result.has_value()) << result.error().message();
+  }
+
+  RunGeneratorAndCrash("0", "10000", "insert", "0", 1);
+
+  uint64_t recovered_doc_count = 0;
+  {
+    auto result = Collection::Open(dir_path_, options_);
+    ASSERT_TRUE(result.has_value())
+        << "Failed to reopen collection after crash recovery";
+    auto collection = result.value();
+
+    recovered_doc_count = collection->Stats().value().doc_count;
+    ASSERT_GT(recovered_doc_count, 0)
+        << "No documents were recovered from the WAL";
+
+    auto status = collection->Optimize();
+    ASSERT_TRUE(status.ok()) << status.message();
+    ASSERT_EQ(collection->Stats().value().doc_count, recovered_doc_count);
+  }
+
+  auto result = Collection::Open(dir_path_, options_);
+  ASSERT_TRUE(result.has_value())
+      << "Failed to reopen collection after optimizing recovered data";
+  ASSERT_EQ(result.value()->Stats().value().doc_count, recovered_doc_count)
+      << "Optimize discarded documents restored from the WAL";
+}
+
+
 TEST_F(CrashRecoveryTest, CrashRecoveryDuringUpsert) {
   {
     auto schema = CreateTestSchema(collection_name_);