From cc484e9e180e42e8483f65849a49fb45f1f3929d Mon Sep 17 00:00:00 2001 From: lxy264173 Date: Thu, 16 Jul 2026 16:22:26 +0800 Subject: [PATCH] fix(blob): support blob-only writes and reject nested blob fields --- src/paimon/common/data/blob_utils.cpp | 9 +- src/paimon/common/data/blob_utils.h | 3 +- src/paimon/common/data/blob_utils_test.cpp | 8 +- src/paimon/core/append/append_only_writer.cpp | 10 +- .../core/append/append_only_writer_test.cpp | 34 +++++++ .../core/io/rolling_blob_file_writer.cpp | 39 +++++--- src/paimon/core/io/rolling_blob_file_writer.h | 3 +- .../core/schema/arrow_schema_validator.cpp | 48 +++++++--- .../core/schema/arrow_schema_validator.h | 3 +- .../schema/arrow_schema_validator_test.cpp | 49 +++++++++- test/inte/blob_table_inte_test.cpp | 92 ++++++++++++++++--- 11 files changed, 239 insertions(+), 59 deletions(-) diff --git a/src/paimon/common/data/blob_utils.cpp b/src/paimon/common/data/blob_utils.cpp index 7bfeb9223..9f0e734f7 100644 --- a/src/paimon/common/data/blob_utils.cpp +++ b/src/paimon/common/data/blob_utils.cpp @@ -82,13 +82,12 @@ Result BlobUtils::SeparateBlobArray( return Status::Invalid( "SeparateBlobArray expects at least one non-inline blob field, but got none."); } - if (main_fields.empty()) { - return Status::Invalid("SeparateBlobArray expects at least one main field, but got none."); - } SeparatedStructArrays result; - PAIMON_ASSIGN_OR_RAISE_FROM_ARROW(result.main_array, - arrow::StructArray::Make(main_arrays, main_fields)); + if (!main_fields.empty()) { + PAIMON_ASSIGN_OR_RAISE_FROM_ARROW(result.main_array, + arrow::StructArray::Make(main_arrays, main_fields)); + } PAIMON_ASSIGN_OR_RAISE_FROM_ARROW(result.blob_array, arrow::StructArray::Make(blob_arrays, blob_fields)); return result; diff --git a/src/paimon/common/data/blob_utils.h b/src/paimon/common/data/blob_utils.h index 196355260..30a303899 100644 --- a/src/paimon/common/data/blob_utils.h +++ b/src/paimon/common/data/blob_utils.h @@ -51,7 +51,8 @@ class PAIMON_EXPORT BlobUtils { }; struct SeparatedStructArrays { - /// Non-blob fields (includes inline blob fields when inline_fields is provided) + /// Non-blob fields (includes inline blob fields when inline_fields is provided). + /// nullptr when all fields are stored in blob files. std::shared_ptr main_array; /// Blob fields that go to separate .blob files std::shared_ptr blob_array; diff --git a/src/paimon/common/data/blob_utils_test.cpp b/src/paimon/common/data/blob_utils_test.cpp index d42845f10..50557a2f3 100644 --- a/src/paimon/common/data/blob_utils_test.cpp +++ b/src/paimon/common/data/blob_utils_test.cpp @@ -182,11 +182,13 @@ TEST_F(BlobUtilsTest, SeparateBlobArray) { BlobUtils::SeparateBlobArray(struct_array, /*inline_fields=*/{"f2_blob"}), "SeparateBlobArray expects at least one non-inline blob field, but got none."); - // All fields are blob with no inline -> no main field -> should return error + // All fields are blob with no inline -> no main array is needed auto all_blob_struct = arrow::StructArray::Make({blob_array_data}, {blob_field}).ValueOrDie(); auto all_blob_sa = std::dynamic_pointer_cast(all_blob_struct); - ASSERT_NOK_WITH_MSG(BlobUtils::SeparateBlobArray(all_blob_sa, /*inline_fields=*/{}), - "SeparateBlobArray expects at least one main field, but got none."); + ASSERT_OK_AND_ASSIGN(auto all_blob_separated, + BlobUtils::SeparateBlobArray(all_blob_sa, /*inline_fields=*/{})); + ASSERT_EQ(nullptr, all_blob_separated.main_array); + ASSERT_TRUE(all_blob_separated.blob_array->Equals(*all_blob_sa)); } TEST_F(BlobUtilsTest, SeparateBlobArrayWithPartialInline) { diff --git a/src/paimon/core/append/append_only_writer.cpp b/src/paimon/core/append/append_only_writer.cpp index 21e543008..7890692ab 100644 --- a/src/paimon/core/append/append_only_writer.cpp +++ b/src/paimon/core/append/append_only_writer.cpp @@ -236,10 +236,14 @@ AppendOnlyWriter::RollingFileWriterResult AppendOnlyWriter::CreateRollingBlobWri options_.GetBlobTargetFileSize(), single_blob_file_writer_factory); }; + WriterFactory main_writer_factory; + if (schemas.main_schema->num_fields() > 0) { + main_writer_factory = + GetDataFileWriterFactory(schemas.main_schema, schemas.main_schema->field_names()); + } return std::make_unique( - options_.GetTargetFileSize(/*has_primary_key=*/false), - GetDataFileWriterFactory(schemas.main_schema, schemas.main_schema->field_names()), - blob_schema, blob_writer_creator, arrow::struct_(write_schema_->fields()), inline_fields); + options_.GetTargetFileSize(/*has_primary_key=*/false), main_writer_factory, blob_schema, + blob_writer_creator, arrow::struct_(write_schema_->fields()), inline_fields); } Status AppendOnlyWriter::Sync() { diff --git a/src/paimon/core/append/append_only_writer_test.cpp b/src/paimon/core/append/append_only_writer_test.cpp index 2d3d05427..df7d912aa 100644 --- a/src/paimon/core/append/append_only_writer_test.cpp +++ b/src/paimon/core/append/append_only_writer_test.cpp @@ -741,6 +741,40 @@ TEST_F(AppendOnlyWriterTest, TestWriteWithSingleBlobField) { ASSERT_OK(writer->Close()); } +TEST_F(AppendOnlyWriterTest, TestWriteWithOnlyBlobField) { + auto options = + CreateOptions({{Options::FILE_FORMAT, "orc"}, {Options::MANIFEST_FORMAT, "orc"}}); + auto dir = UniqueTestDirectory::Create(); + ASSERT_TRUE(dir); + auto path_factory = CreatePathFactory(dir->Str(), "orc", options); + + auto blob_field = BlobUtils::ToArrowField("blob", false); + auto schema = arrow::schema({blob_field}); + ASSERT_OK_AND_ASSIGN(auto writer, + CreateAppendOnlyWriter(options, /*schema_id=*/0, schema, + /*write_cols=*/std::vector{"blob"}, + /*max_sequence_number=*/-1, path_factory, + compact_manager_, memory_pool_)); + + arrow::LargeBinaryBuilder blob_builder; + ASSERT_TRUE(blob_builder.Append("a", 1).ok()); + ASSERT_TRUE(blob_builder.Append("bb", 2).ok()); + auto blob_array = blob_builder.Finish().ValueOrDie(); + + ASSERT_OK(writer->Write(CreateStructBatch(schema, {blob_array}))); + ASSERT_OK_AND_ASSIGN(CommitIncrement inc, writer->PrepareCommit(/*wait_compaction=*/true)); + + const auto& new_files = inc.GetNewFilesIncrement().NewFiles(); + ASSERT_EQ(new_files.size(), 1); + ASSERT_TRUE(BlobUtils::IsBlobFile(new_files[0]->file_name)); + ASSERT_EQ(new_files[0]->row_count, 2); + ASSERT_TRUE(new_files[0]->write_cols.has_value()); + ASSERT_EQ(new_files[0]->write_cols.value(), std::vector({"blob"})); + ASSERT_TRUE( + options.GetFileSystem()->Exists(path_factory->ToPath(new_files[0]->file_name)).value()); + ASSERT_OK(writer->Close()); +} + TEST_F(AppendOnlyWriterTest, TestWriteWithMultipleBlobFields) { auto options = CreateOptions({{Options::FILE_FORMAT, "orc"}, {Options::MANIFEST_FORMAT, "orc"}}); diff --git a/src/paimon/core/io/rolling_blob_file_writer.cpp b/src/paimon/core/io/rolling_blob_file_writer.cpp index c48a8bbeb..a8c9f4f8b 100644 --- a/src/paimon/core/io/rolling_blob_file_writer.cpp +++ b/src/paimon/core/io/rolling_blob_file_writer.cpp @@ -55,7 +55,7 @@ RollingBlobFileWriter::RollingBlobFileWriter( Status RollingBlobFileWriter::Write(::ArrowArray* record) { ScopeGuard guard([this]() -> void { this->Abort(); }); // Open the current writer if write the first record or roll over happen before. - if (PAIMON_UNLIKELY(current_writer_ == nullptr)) { + if (writer_factory_ != nullptr && PAIMON_UNLIKELY(current_writer_ == nullptr)) { PAIMON_RETURN_NOT_OK(OpenCurrentWriter()); } if (PAIMON_UNLIKELY(blob_writer_ == nullptr)) { @@ -69,12 +69,14 @@ Status RollingBlobFileWriter::Write(::ArrowArray* record) { PAIMON_ASSIGN_OR_RAISE(BlobUtils::SeparatedStructArrays separated_arrays, BlobUtils::SeparateBlobArray(struct_array, inline_fields_)); // Write main (non-blob) data - ::ArrowArray c_main_array; - PAIMON_RETURN_NOT_OK_FROM_ARROW( - arrow::ExportArray(*separated_arrays.main_array, &c_main_array)); - ScopeGuard array_lifecycle_guard( - [&c_main_array]() -> void { ArrowArrayRelease(&c_main_array); }); - PAIMON_RETURN_NOT_OK(current_writer_->Write(&c_main_array)); + if (current_writer_ != nullptr) { + ::ArrowArray c_main_array; + PAIMON_RETURN_NOT_OK_FROM_ARROW( + arrow::ExportArray(*separated_arrays.main_array, &c_main_array)); + ScopeGuard array_lifecycle_guard( + [&c_main_array]() -> void { ArrowArrayRelease(&c_main_array); }); + PAIMON_RETURN_NOT_OK(current_writer_->Write(&c_main_array)); + } // Write blob data via MultipleBlobFileWriter (each blob field independently) ::ArrowArray c_blob_array; @@ -84,28 +86,35 @@ Status RollingBlobFileWriter::Write(::ArrowArray* record) { PAIMON_RETURN_NOT_OK(blob_writer_->Write(&c_blob_array)); record_count_ += record_count; - PAIMON_ASSIGN_OR_RAISE(bool need_rolling_file, NeedRollingFile()); - if (need_rolling_file) { - PAIMON_RETURN_NOT_OK(CloseCurrentWriter()); + if (current_writer_ != nullptr) { + PAIMON_ASSIGN_OR_RAISE(bool need_rolling_file, NeedRollingFile()); + if (need_rolling_file) { + PAIMON_RETURN_NOT_OK(CloseCurrentWriter()); + } } guard.Release(); return Status::OK(); } Status RollingBlobFileWriter::CloseCurrentWriter() { - if (current_writer_ == nullptr) { + if (current_writer_ == nullptr && blob_writer_ == nullptr) { return Status::OK(); } if (blob_writer_ == nullptr) { return Status::OK(); } - PAIMON_ASSIGN_OR_RAISE(std::shared_ptr main_data_file_meta, CloseMainWriter()); + std::shared_ptr main_data_file_meta; + if (current_writer_ != nullptr) { + PAIMON_ASSIGN_OR_RAISE(main_data_file_meta, CloseMainWriter()); + } PAIMON_ASSIGN_OR_RAISE(std::vector> blob_metas, CloseBlobWriter()); - PAIMON_RETURN_NOT_OK( - ValidateFileConsistency(main_data_file_meta, blob_metas, blob_schema_->num_fields())); - results_.push_back(main_data_file_meta); + if (main_data_file_meta != nullptr) { + PAIMON_RETURN_NOT_OK( + ValidateFileConsistency(main_data_file_meta, blob_metas, blob_schema_->num_fields())); + results_.push_back(main_data_file_meta); + } results_.insert(results_.end(), blob_metas.begin(), blob_metas.end()); current_writer_.reset(); diff --git a/src/paimon/core/io/rolling_blob_file_writer.h b/src/paimon/core/io/rolling_blob_file_writer.h index 324772059..0aa998f3b 100644 --- a/src/paimon/core/io/rolling_blob_file_writer.h +++ b/src/paimon/core/io/rolling_blob_file_writer.h @@ -38,7 +38,8 @@ namespace paimon { /// between them. /// /// Multiple blob fields are supported. Each blob field is written to its own set of blob files -/// independently via MultipleBlobFileWriter. +/// independently via MultipleBlobFileWriter. For blob-only writes, the main writer factory may be +/// nullptr and only blob files are produced. /// /// 
 /// For example,
diff --git a/src/paimon/core/schema/arrow_schema_validator.cpp b/src/paimon/core/schema/arrow_schema_validator.cpp
index 117d468b2..ddd8ed820 100644
--- a/src/paimon/core/schema/arrow_schema_validator.cpp
+++ b/src/paimon/core/schema/arrow_schema_validator.cpp
@@ -53,10 +53,19 @@ Status ArrowSchemaValidator::ValidateSchema(const arrow::Schema& schema) {
 
 Status ArrowSchemaValidator::ValidateSchemaWithFieldId(const arrow::Schema& schema) {
     PAIMON_RETURN_NOT_OK(ValidateSchema(schema));
-    auto struct_type = arrow::struct_(schema.fields());
     std::set field_id_set;
-    PAIMON_RETURN_NOT_OK(
-        ValidateDataTypeWithFieldId(struct_type, /*key_value_metadata=*/nullptr, &field_id_set));
+    for (const auto& field : schema.fields()) {
+        PAIMON_ASSIGN_OR_RAISE(DataField data_field,
+                               DataField::ConvertArrowFieldToDataField(field));
+        auto iter = field_id_set.find(data_field.Id());
+        if (iter != field_id_set.end()) {
+            return Status::Invalid(
+                fmt::format("field id must be unique, duplicate field id {}", data_field.Id()));
+        }
+        field_id_set.insert(data_field.Id());
+        PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(field->type(), field->metadata(),
+                                                         /*allow_blob=*/true, &field_id_set));
+    }
     return Status::OK();
 }
 
@@ -91,7 +100,7 @@ Status ArrowSchemaValidator::ValidateNoWhitespaceOnlyFields(const arrow::FieldVe
 
 Status ArrowSchemaValidator::ValidateDataTypeWithFieldId(
     const std::shared_ptr& type,
-    const std::shared_ptr& key_value_metadata,
+    const std::shared_ptr& key_value_metadata, bool allow_blob,
     std::set* field_id_set) {
     const auto kind = type->id();
     switch (kind) {
@@ -112,7 +121,7 @@ Status ArrowSchemaValidator::ValidateDataTypeWithFieldId(
             const auto& value_field =
                 arrow::internal::checked_cast(type.get())->value_field();
             PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(
-                value_field->type(), value_field->metadata(), field_id_set));
+                value_field->type(), value_field->metadata(), /*allow_blob=*/false, field_id_set));
             break;
         }
         case arrow::Type::type::STRUCT: {
@@ -128,7 +137,7 @@ Status ArrowSchemaValidator::ValidateDataTypeWithFieldId(
                 }
                 field_id_set->insert(data_field.Id());
                 PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(
-                    sub_field->type(), sub_field->metadata(), field_id_set));
+                    sub_field->type(), sub_field->metadata(), /*allow_blob=*/false, field_id_set));
             }
             break;
         }
@@ -137,14 +146,17 @@ Status ArrowSchemaValidator::ValidateDataTypeWithFieldId(
                 arrow::internal::checked_cast(type.get())->key_field();
             const auto& item_field =
                 arrow::internal::checked_cast(type.get())->item_field();
-            PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(key_field->type(),
-                                                             key_field->metadata(), field_id_set));
-            PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(item_field->type(),
-                                                             item_field->metadata(), field_id_set));
+            PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(
+                key_field->type(), key_field->metadata(), /*allow_blob=*/false, field_id_set));
+            PAIMON_RETURN_NOT_OK(ValidateDataTypeWithFieldId(
+                item_field->type(), item_field->metadata(), /*allow_blob=*/false, field_id_set));
             break;
         }
         case arrow::Type::type::LARGE_BINARY: {
             if (BlobUtils::IsBlobMetadata(key_value_metadata)) {
+                if (!allow_blob) {
+                    return Status::Invalid("Blob field must be a top-level field.");
+                }
                 break;
             }
             [[fallthrough]];
@@ -157,6 +169,11 @@ Status ArrowSchemaValidator::ValidateDataTypeWithFieldId(
 }
 
 Status ArrowSchemaValidator::ValidateField(const std::shared_ptr& field) {
+    return ValidateField(field, /*allow_blob=*/true);
+}
+
+Status ArrowSchemaValidator::ValidateField(const std::shared_ptr& field,
+                                           bool allow_blob) {
     const auto kind = field->type()->id();
     switch (kind) {
         case arrow::Type::type::BOOL:
@@ -178,14 +195,14 @@ Status ArrowSchemaValidator::ValidateField(const std::shared_ptr&
             const auto& value_field =
                 arrow::internal::checked_cast(*field->type())
                     .value_field();
-            PAIMON_RETURN_NOT_OK(ValidateField(value_field));
+            PAIMON_RETURN_NOT_OK(ValidateField(value_field, /*allow_blob=*/false));
             break;
         }
         case arrow::Type::type::STRUCT: {
             arrow::FieldVector arrow_fields =
                 arrow::internal::checked_cast(*field->type()).fields();
             for (const auto& sub_field : arrow_fields) {
-                PAIMON_RETURN_NOT_OK(ValidateField(sub_field));
+                PAIMON_RETURN_NOT_OK(ValidateField(sub_field, /*allow_blob=*/false));
             }
             break;
         }
@@ -194,12 +211,15 @@ Status ArrowSchemaValidator::ValidateField(const std::shared_ptr&
                 arrow::internal::checked_cast(*field->type()).key_field();
             const auto& item_field =
                 arrow::internal::checked_cast(*field->type()).item_field();
-            PAIMON_RETURN_NOT_OK(ValidateField(key_field));
-            PAIMON_RETURN_NOT_OK(ValidateField(item_field));
+            PAIMON_RETURN_NOT_OK(ValidateField(key_field, /*allow_blob=*/false));
+            PAIMON_RETURN_NOT_OK(ValidateField(item_field, /*allow_blob=*/false));
             break;
         }
         case arrow::Type::type::LARGE_BINARY: {
             if (BlobUtils::IsBlobField(field)) {
+                if (!allow_blob) {
+                    return Status::Invalid("Blob field must be a top-level field.");
+                }
                 break;
             }
             [[fallthrough]];
diff --git a/src/paimon/core/schema/arrow_schema_validator.h b/src/paimon/core/schema/arrow_schema_validator.h
index 39c6ef77c..940f2ab80 100644
--- a/src/paimon/core/schema/arrow_schema_validator.h
+++ b/src/paimon/core/schema/arrow_schema_validator.h
@@ -55,7 +55,8 @@ class PAIMON_EXPORT ArrowSchemaValidator {
  private:
     static Status ValidateDataTypeWithFieldId(
         const std::shared_ptr& type,
-        const std::shared_ptr& key_value_metadata,
+        const std::shared_ptr& key_value_metadata, bool allow_blob,
         std::set* field_id_set);
+    static Status ValidateField(const std::shared_ptr& field, bool allow_blob);
 };
 }  // namespace paimon
diff --git a/src/paimon/core/schema/arrow_schema_validator_test.cpp b/src/paimon/core/schema/arrow_schema_validator_test.cpp
index 1d4057450..1154cb877 100644
--- a/src/paimon/core/schema/arrow_schema_validator_test.cpp
+++ b/src/paimon/core/schema/arrow_schema_validator_test.cpp
@@ -21,6 +21,7 @@
 
 #include "arrow/type.h"
 #include "gtest/gtest.h"
+#include "paimon/common/data/blob_utils.h"
 #include "paimon/common/types/data_field.h"
 #include "paimon/common/utils/date_time_utils.h"
 #include "paimon/testing/utils/testharness.h"
@@ -148,6 +149,51 @@ TEST(ArrowSchemaValidatorTest, TestInvalidDataType) {
     }
 }
 
+TEST(ArrowSchemaValidatorTest, TestBlobFieldMustBeTopLevel) {
+    {
+        auto arrow_schema =
+            arrow::schema(arrow::FieldVector({BlobUtils::ToArrowField("blob", true)}));
+        ASSERT_OK(ArrowSchemaValidator::ValidateSchema(*arrow_schema));
+    }
+    {
+        std::vector fields = {DataField(0, BlobUtils::ToArrowField("blob", true))};
+        auto arrow_schema = DataField::ConvertDataFieldsToArrowSchema(fields);
+        ASSERT_OK(ArrowSchemaValidator::ValidateSchemaWithFieldId(*arrow_schema));
+    }
+    {
+        auto nested_blob_field =
+            arrow::field("nested", arrow::struct_({BlobUtils::ToArrowField("blob", true)}));
+        auto arrow_schema = arrow::schema(arrow::FieldVector({nested_blob_field}));
+        ASSERT_NOK_WITH_MSG(ArrowSchemaValidator::ValidateSchema(*arrow_schema),
+                            "Blob field must be a top-level field.");
+    }
+    {
+        auto array_blob_field =
+            arrow::field("array_blob", arrow::list(BlobUtils::ToArrowField("item", true)));
+        auto arrow_schema = arrow::schema(arrow::FieldVector({array_blob_field}));
+        ASSERT_NOK_WITH_MSG(ArrowSchemaValidator::ValidateSchema(*arrow_schema),
+                            "Blob field must be a top-level field.");
+    }
+    {
+        auto map_blob_field = arrow::field(
+            "map_blob",
+            arrow::map(arrow::utf8(), arrow::struct_({BlobUtils::ToArrowField("blob", true)})));
+        auto arrow_schema = arrow::schema(arrow::FieldVector({map_blob_field}));
+        ASSERT_NOK_WITH_MSG(ArrowSchemaValidator::ValidateSchema(*arrow_schema),
+                            "Blob field must be a top-level field.");
+    }
+    {
+        std::vector nested_fields = {
+            DataField(1, BlobUtils::ToArrowField("blob", true))};
+        std::vector fields = {DataField(
+            0,
+            arrow::field("nested", DataField::ConvertDataFieldsToArrowStructType(nested_fields)))};
+        auto arrow_schema = DataField::ConvertDataFieldsToArrowSchema(fields);
+        ASSERT_NOK_WITH_MSG(ArrowSchemaValidator::ValidateSchemaWithFieldId(*arrow_schema),
+                            "Blob field must be a top-level field.");
+    }
+}
+
 TEST(ArrowSchemaValidatorTest, ValidateDataTypeWithFieldId) {
     {
         std::vector fields = {DataField(3, arrow::field("f3", arrow::float64())),
@@ -265,7 +311,8 @@ TEST(ArrowSchemaValidatorTest, ValidateDataTypeWithFieldId) {
         auto struct_type = DataField::ConvertDataFieldsToArrowStructType(fields);
         std::set field_id_set;
         ASSERT_NOK_WITH_MSG(ArrowSchemaValidator::ValidateDataTypeWithFieldId(
-                                struct_type, /*key_value_metadata=*/nullptr, &field_id_set),
+                                struct_type, /*key_value_metadata=*/nullptr,
+                                /*allow_blob=*/true, &field_id_set),
                             "Unknown or unsupported arrow type: large_string");
     }
 }
diff --git a/test/inte/blob_table_inte_test.cpp b/test/inte/blob_table_inte_test.cpp
index 75fee6ef3..e51e398f8 100644
--- a/test/inte/blob_table_inte_test.cpp
+++ b/test/inte/blob_table_inte_test.cpp
@@ -730,30 +730,92 @@ TEST_P(BlobTableInteTest, TestMultipleAppends) {
     }
 }
 
-TEST_P(BlobTableInteTest, TestOnlySomeColumns) {
-    CreateTable();
+TEST_P(BlobTableInteTest, TestDataEvolutionBlobOnlyWriteWithFirstRowId) {
+    arrow::FieldVector fields = {arrow::field("f0", arrow::int32()),
+                                 arrow::field("f1", arrow::utf8()), BlobUtils::ToArrowField("b0")};
+    std::map options = {{Options::MANIFEST_FORMAT, "orc"},
+                                                  {Options::FILE_FORMAT, GetParam()},
+                                                  {Options::FILE_SYSTEM, "local"},
+                                                  {Options::ROW_TRACKING_ENABLED, "true"},
+                                                  {Options::DATA_EVOLUTION_ENABLED, "true"}};
+    CreateTable(fields, /*partition_keys=*/{}, options);
     std::string table_path = PathUtil::JoinPath(dir_->Str(), "foo.db/bar");
-    auto schema = arrow::schema(fields_);
+    auto schema = arrow::schema(fields);
 
-    // write field: f0
-    std::vector write_cols0 = {"f0"};
+    // Initial full-row write assigns row ids 0 and 1.
     auto src_array0 = std::dynamic_pointer_cast(
-        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_({fields_[0]}), R"([
-        [1]
+        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_(fields), R"([
+        [1, "a", "old_blob_0"],
+        [2, "b", "old_blob_1"]
     ])")
             .ValueOrDie());
-    ASSERT_OK_AND_ASSIGN(auto commit_msgs, WriteArray(table_path, {}, write_cols0, {src_array0}));
-    ASSERT_OK(Commit(table_path, commit_msgs));
+    ASSERT_OK_AND_ASSIGN(auto commit_msgs0,
+                         WriteArray(table_path, {}, schema->field_names(), {src_array0}));
+    ASSERT_OK(Commit(table_path, commit_msgs0));
 
-    // write field: f1
-    std::vector write_cols1 = {"f1"};
+    // Update only b0 and align it with the existing row ids.
+    std::vector blob_write_cols = {"b0"};
     auto src_array1 = std::dynamic_pointer_cast(
-        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_({fields_[1]}), R"([
-        ["a"]
+        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_({fields[2]}), R"([
+        ["new_blob_0"],
+        ["new_blob_1"]
+    ])")
+            .ValueOrDie());
+    ASSERT_OK_AND_ASSIGN(auto commit_msgs1,
+                         WriteArray(table_path, {}, blob_write_cols, {src_array1}));
+    SetFirstRowId(/*reset_first_row_id=*/0, commit_msgs1);
+    ASSERT_OK(Commit(table_path, commit_msgs1));
+
+    auto expected_array = std::dynamic_pointer_cast(
+        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_(fields), R"([
+        [1, "a", "new_blob_0"],
+        [2, "b", "new_blob_1"]
+    ])")
+            .ValueOrDie());
+    ASSERT_OK(ScanAndRead(table_path, schema->field_names(), expected_array));
+
+    if (GetParam() != "lance") {
+        auto expected_with_row_id = std::dynamic_pointer_cast(
+            arrow::ipc::internal::json::ArrayFromJSON(
+                arrow::struct_({fields[0], fields[1], fields[2], SpecialFields::RowId().field_}),
+                R"([
+        [1, "a", "new_blob_0", 0],
+        [2, "b", "new_blob_1", 1]
+    ])")
+                .ValueOrDie());
+        ASSERT_OK(ScanAndRead(table_path, {"f0", "f1", "b0", "_ROW_ID"}, expected_with_row_id));
+    }
+}
+
+TEST_P(BlobTableInteTest, TestDataEvolutionBlobOnlyFirstCommitFailsWithoutFirstRowId) {
+    arrow::FieldVector fields = {arrow::field("f0", arrow::int32()),
+                                 arrow::field("f1", arrow::utf8()), BlobUtils::ToArrowField("b0")};
+    std::map options = {{Options::MANIFEST_FORMAT, "orc"},
+                                                  {Options::FILE_FORMAT, GetParam()},
+                                                  {Options::FILE_SYSTEM, "local"},
+                                                  {Options::ROW_TRACKING_ENABLED, "true"},
+                                                  {Options::DATA_EVOLUTION_ENABLED, "true"}};
+    CreateTable(fields, /*partition_keys=*/{}, options);
+    std::string table_path = PathUtil::JoinPath(dir_->Str(), "foo.db/bar");
+
+    auto blob_array = std::dynamic_pointer_cast(
+        arrow::ipc::internal::json::ArrayFromJSON(arrow::struct_({fields[2]}), R"([
+        ["blob_0"]
     ])")
             .ValueOrDie());
-    ASSERT_NOK_WITH_MSG(WriteArray(table_path, {}, write_cols1, {src_array1}),
-                        "SeparateBlobArray expects at least one main field, but got none.");
+    std::vector blob_write_cols = {"b0"};
+    ASSERT_OK_AND_ASSIGN(auto commit_msgs,
+                         WriteArray(table_path, {}, blob_write_cols, {blob_array}));
+
+    ASSERT_EQ(commit_msgs.size(), 1);
+    auto commit_msg = std::dynamic_pointer_cast(commit_msgs[0]);
+    ASSERT_TRUE(commit_msg);
+    ASSERT_EQ(commit_msg->data_increment_.new_files_.size(), 1);
+    const auto& blob_file = commit_msg->data_increment_.new_files_[0];
+    ASSERT_TRUE(BlobUtils::IsBlobFile(blob_file->file_name));
+    ASSERT_FALSE(blob_file->first_row_id.has_value());
+
+    ASSERT_NOK_WITH_MSG(Commit(table_path, commit_msgs), "blobStart 0 should be less than start 0");
 }
 
 TEST_P(BlobTableInteTest, TestMultipleAppendsDifferentFirstRowIds) {