!7538 Add empty string tensor support for Album

Merge pull request !7538 from EricZ/album_empty_string

mindspore/ccsrc/minddata/dataset/core/tensor.h

@@ -301,7 +301,7 @@ class Tensor {
   const TensorShape &shape() const { return shape_; }
 
   /// Check if tensor has data
-  /// \return bool - true if tensor is empty
+  /// \return bool - true if tensor is not empty
   bool HasData() const { return data_ != nullptr; }
 
   /// Reshape the tensor. The given shape should have the same number of elements in the Tensor

mindspore/ccsrc/minddata/dataset/engine/datasetops/source/album_op.cc

@@ -380,7 +380,7 @@ Status AlbumOp::LoadIDTensor(const std::string &file, uint32_t col_num, TensorRo
 Status AlbumOp::LoadEmptyTensor(uint32_t col_num, TensorRow *row) {
   // hack to get the file name without extension, the 1 is to get rid of the backslash character
   TensorPtr empty_tensor;
-  RETURN_IF_NOT_OK(Tensor::CreateEmpty(TensorShape({}), data_schema_->column(col_num).type(), &empty_tensor));
+  RETURN_IF_NOT_OK(Tensor::CreateEmpty(TensorShape({0}), data_schema_->column(col_num).type(), &empty_tensor));
   row->push_back(std::move(empty_tensor));
   return Status::OK();
 }

tests/ut/cpp/dataset/schema_test.cc

@@ -62,7 +62,7 @@ TEST_F(MindDataTestSchema, TestAlbumSchema) {
   } else {
     int32_t num_cols = schema->NumColumns();
     MS_LOG(INFO) << "num_cols: " << num_cols << ".";
-    EXPECT_TRUE(num_cols == 7);
+    EXPECT_TRUE(num_cols == 8);
   }
 }
 

tests/ut/cpp/dataset/tensor_string_test.cc

@@ -117,6 +117,17 @@ TEST_F(MindDataTestStringTensorDE, Empty) {
   }
 }
 
+TEST_F(MindDataTestStringTensorDE, EmptyData) {
+  std::shared_ptr<Tensor> t;
+  Tensor::CreateScalar<std::string>("", &t);
+  // empty string has 1 element 
+  ASSERT_TRUE(t->HasData());
+
+  std::shared_ptr<Tensor> t1;
+  Tensor::CreateEmpty(TensorShape({0}), DataType(DataType::DE_STRING), &t1);
+  ASSERT_TRUE(!t1->HasData());
+}
+
 TEST_F(MindDataTestStringTensorDE, SetItem) {
   std::vector<std::string> strings{"abc", "defg", "hi", "klmno", "123", "789"};
   std::shared_ptr<Tensor> t3;
@@ -159,4 +170,4 @@ TEST_F(MindDataTestStringTensorDE, Iterator) {
     ASSERT_TRUE(*itr == strings[index]);
     index += 2;
   }
-}
+}

tests/ut/data/dataset/testAlbum/fullSchema.json

@@ -8,6 +8,10 @@
       "type": "string",
       "rank": 1
     },
+    "optional" : {
+      "type": "string",
+      "rank": 1
+    },
     "id" : {
       "type": "int64",
       "rank": 0