Add sort_and_merge_tests, update exception to be more consistent, upd…

…ate docs to reflect new behavior

cpp/arcticdb/column_store/memory_segment_impl.cpp

@@ -650,7 +650,7 @@ size_t SegmentInMemoryImpl::num_bytes() const {
 void SegmentInMemoryImpl::sort(const std::string& column_name) {
     init_column_map();
     auto idx = column_index(std::string_view(column_name));
-    user_input::check<ErrorCode::E_COLUMN_NOT_FOUND>(static_cast<bool>(idx), "Column {} not found in sort", column_name);
+    schema::check<ErrorCode::E_COLUMN_DOESNT_EXIST>(static_cast<bool>(idx), "Column {} not found in sort", column_name);
     sort(static_cast<position_t>(idx.value()));
 }
 
@@ -659,7 +659,7 @@ void SegmentInMemoryImpl::sort(const std::vector<std::string>& column_names) {
     std::vector<position_t> positions;
     for(const auto& column_name : column_names) {
         auto idx = column_index(std::string_view(column_name));
-        user_input::check<ErrorCode::E_COLUMN_NOT_FOUND>(static_cast<bool>(idx), "Column {} not found in multi-sort", column_name);
+        schema::check<ErrorCode::E_COLUMN_DOESNT_EXIST>(static_cast<bool>(idx), "Column {} not found in multi-sort", column_name);
         positions.emplace_back(static_cast<position_t>(*idx));
     }
     sort(positions);

python/arcticdb/version_store/library.py

@@ -1241,6 +1241,7 @@ def finalize_staged_data(
                 is not the same as the schema of the existing data
             - If dynamic schema is used and different segments have the same column names but their dtypes don't have a
                 common type (e.g string and any numeric type)
+            - If a different index name is encountered in the staged data, regardless of the schema mode
 
         See Also
         --------
@@ -1351,6 +1352,7 @@ def sort_and_finalize_staged_data(
                 staged segment is not the same as the schema of the existing data
             - If dynamic schema is used and different segments have the same column names but their dtypes don't have a
                 common type (e.g string and any numeric type)
+            - If a different index name is encountered in the staged data, regardless of the schema mode
 
         See Also
         --------

python/tests/unit/arcticdb/version_store/test_sort_merge.py

@@ -868,3 +868,56 @@ def test_writing_wide_segment_over_sliced_data(self, lmdb_storage, lib_name):
         lib.sort_and_finalize_staged_data("sym", mode=StagedDataFinalizeMethod.WRITE)
 
         assert_frame_equal(lib.read("sym").data, df_1)
+
+
+@pytest.mark.parametrize("delete_staged_data_on_failure", [True, False])
+def test_sort_and_finalize_staged_data_write_dynamic_schema_named_index(
+    lmdb_library_static_dynamic, delete_staged_data_on_failure
+):
+    lib = lmdb_library_static_dynamic
+    sym = "test_sort_and_finalize_staged_data_append_dynamic_schema_named_index"
+    df_0 = pd.DataFrame(
+        {"col_0": [0], "col_1": [0.5]}, index=pd.date_range("2024-01-01", periods=1)
+    )
+    df_0.index.name = "date"
+    df_1 = pd.DataFrame({"col_0": [1]}, index=pd.date_range("2024-01-02", periods=1))
+    lib.write(sym, df_0, staged=True)
+    lib.write(sym, df_1, staged=True)
+
+    with pytest.raises(SchemaException) as exception_info:
+        lib.sort_and_finalize_staged_data(
+            sym,
+            mode=StagedDataFinalizeMethod.WRITE,
+            delete_staged_data_on_failure=delete_staged_data_on_failure,
+        )
+
+    # Make sure that name of the problematic index column
+    assert "date" in str(exception_info.value)
+    expected_key_count = 0 if delete_staged_data_on_failure else 2
+    assert len(get_append_keys(lib, sym)) == expected_key_count
+
+
+@pytest.mark.parametrize("delete_staged_data_on_failure", [True, False])
+def test_sort_and_finalize_staged_data_append_dynamic_schema_named_index(
+    lmdb_library_static_dynamic, delete_staged_data_on_failure
+):
+    lib = lmdb_library_static_dynamic
+    sym = "test_sort_and_finalize_staged_data_append_dynamic_schema_named_index"
+    df_0 = pd.DataFrame(
+        {"col_0": [0], "col_1": [0.5]}, index=pd.date_range("2024-01-01", periods=1)
+    )
+    df_0.index.name = "date"
+    df_1 = pd.DataFrame({"col_0": [1]}, index=pd.date_range("2024-01-02", periods=1))
+    lib.write(sym, df_0)
+    lib.write(sym, df_1, staged=True)
+    with pytest.raises(SchemaException) as exception_info:
+        lib.sort_and_finalize_staged_data(
+            sym,
+            mode=StagedDataFinalizeMethod.APPEND,
+            delete_staged_data_on_failure=delete_staged_data_on_failure,
+        )
+
+    # Make sure that name of the problematic index column
+    assert "date" in str(exception_info.value)
+    expected_key_count = 0 if delete_staged_data_on_failure else 1
+    assert len(get_append_keys(lib, sym)) == expected_key_count