!44019 format minddata log

Merge pull request !44019 from luoyang/err_struct

include/api/status.h

@@ -118,8 +118,10 @@ class MS_API Status {
   inline std::string ToString() const;
 
   int GetLineOfCode() const;
+  inline std::string GetFileName() const;
   inline std::string GetErrDescription() const;
   inline std::string SetErrDescription(const std::string &err_description);
+  inline void SetStatusMsg(const std::string &status_msg);
 
   MS_API friend std::ostream &operator<<(std::ostream &os, const Status &s);
 
@@ -144,8 +146,10 @@ class MS_API Status {
   Status(enum StatusCode status_code, const std::vector<char> &status_msg);
   Status(enum StatusCode code, int line_of_code, const char *file_name, const std::vector<char> &extra);
   std::vector<char> ToCString() const;
+  std::vector<char> GetFileNameChar() const;
   std::vector<char> GetErrDescriptionChar() const;
   std::vector<char> SetErrDescription(const std::vector<char> &err_description);
+  void SetStatusMsgChar(const std::vector<char> &status_msg);
   static std::vector<char> CodeAsCString(enum StatusCode c);
 
   struct Data;
@@ -157,10 +161,12 @@ Status::Status(enum StatusCode status_code, const std::string &status_msg)
 Status::Status(const enum StatusCode code, int line_of_code, const char *file_name, const std::string &extra)
     : Status(code, line_of_code, file_name, StringToChar(extra)) {}
 std::string Status::ToString() const { return CharToString(ToCString()); }
+std::string Status::GetFileName() const { return CharToString(GetFileNameChar()); }
 std::string Status::GetErrDescription() const { return CharToString(GetErrDescriptionChar()); }
 std::string Status::SetErrDescription(const std::string &err_description) {
   return CharToString(SetErrDescription(StringToChar(err_description)));
 }
+void Status::SetStatusMsg(const std::string &status_msg) { SetStatusMsgChar(StringToChar(status_msg)); }
 std::string Status::CodeAsString(enum StatusCode c) { return CharToString(CodeAsCString(c)); }
 }  // namespace mindspore
 #endif  // MINDSPORE_INCLUDE_API_STATUS_H

mindspore/ccsrc/minddata/dataset/CMakeLists.txt

@@ -76,6 +76,11 @@ else()
     endif()
 endif()
 
+set(MINDDATA_LOG_ADAPTER_SRC ${CMAKE_SOURCE_DIR}/mindspore/ccsrc/minddata/dataset/util/md_log_adapter.cc)
+add_library(md_log_adapter_obj OBJECT ${MINDDATA_LOG_ADAPTER_SRC})
+add_library(md_log_adapter STATIC $<TARGET_OBJECTS:md_log_adapter_obj>)
+target_link_libraries(md_log_adapter mindspore_core)
+
 ################## Include sub-modules ###############################
 add_subdirectory(util)
 add_subdirectory(core)
@@ -200,6 +205,8 @@ endif()
 
 set(dataengine_submodules ${dataengine_submodules} CACHE INTERNAL "_c_dataengine objects")
 add_library(_c_dataengine SHARED ${dataengine_submodules})
+add_dependencies(_c_dataengine md_log_adapter)
+target_link_libraries(_c_dataengine PRIVATE md_log_adapter)
 if(ENABLE_PYTHON)
 set_target_properties(_c_dataengine PROPERTIES
     PREFIX "${PYTHON_MODULE_PREFIX}"

mindspore/ccsrc/minddata/dataset/api/python/pybind_register.h

@@ -25,15 +25,16 @@
 
 #include "pybind11/pybind11.h"
 #include "pybind11/stl.h"
+#include "minddata/dataset/util/md_log_adapter.h"
 
 namespace py = pybind11;
 namespace mindspore {
 
 namespace dataset {
-#define THROW_IF_ERROR(s)                                      \
+#define THROW_IF_ERROR(s)                                                            \
-  do {                                                         \
+  do {                                                                               \
-    Status rc = std::move(s);                                  \
+    Status rc = std::move(s);                                                        \
-    if (rc.IsError()) throw std::runtime_error(rc.ToString()); \
+    if (rc.IsError()) throw std::runtime_error(MDLogAdapter::Apply(&rc).ToString()); \
   } while (false)
 
 using PybindDefineFunc = std::function<void(py::module *)>;

mindspore/ccsrc/minddata/dataset/engine/datasetops/map_op/cpu_map_job.cc

@@ -62,7 +62,7 @@ Status CpuMapJob::RebuildMapErrorMsg(const TensorRow &input_row, const size_t &i
   std::string abbr_op_name = op_name.substr(0, op_name.length() - 2);
   err_msg += "map operation: [" + abbr_op_name + "] failed. ";
   if (input_row.getPath().size() > 0 && !input_row.getPath()[0].empty()) {
-    err_msg += "The corresponding data files: " + input_row.getPath()[0];
+    err_msg += "The corresponding data file is: " + input_row.getPath()[0];
     if (input_row.getPath().size() > 1) {
       std::set<std::string> path_set;
       path_set.insert(input_row.getPath()[0]);
@@ -80,6 +80,9 @@ Status CpuMapJob::RebuildMapErrorMsg(const TensorRow &input_row, const size_t &i
     err_msg += "Error description:\n";
   }
   err_msg += tensor_err_msg;
+  if (abbr_op_name == "PyFunc") {
+    RETURN_STATUS_ERROR(StatusCode::kMDPyFuncException, err_msg);
+  }
   rc->SetErrDescription(err_msg);
   return *rc;
 }

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

@@ -201,12 +201,29 @@ Status GeneratorOp::operator()() {
         generator_counter_++;
       } catch (py::error_already_set &e) {
         eoe = e.matches(PyExc_StopIteration);
-        // Restore exception to python
-        e.restore();
         // Pop up non StopIteration Python Exception
         if (!eoe) {
-          RETURN_STATUS_ERROR(StatusCode::kMDPyFuncException, e.what());
+          std::string traceback;
+          try {
+            // Construct python-like traceback
+            py::list tb = py::module::import("traceback").attr("format_tb")(e.trace());
+            traceback = "Traceback (most recent call last):\n";
+            for (auto t : tb) {
+              traceback += py::reinterpret_borrow<py::str>(t);
+            }
+            traceback += e.what();
+          } catch (std::exception &) {
+            // Back to original exception
+            traceback = e.what();
+          }
+
+          // Restore exception to python
+          e.restore();
+          RETURN_STATUS_ERROR(StatusCode::kMDPyFuncException, traceback);
         }
+
+        // Restore exception to python
+        e.restore();
         if (num_rows_sampled != -1 && num_rows_sampled != generator_counter_) {
           if (generator_counter_ == 0) {
             std::string msg =

mindspore/ccsrc/minddata/dataset/util/CMakeLists.txt

@@ -1,3 +1,4 @@
 file(GLOB_RECURSE _CURRENT_SRC_FILES RELATIVE ${CMAKE_CURRENT_SOURCE_DIR} "*.cc")
+list(REMOVE_ITEM _CURRENT_SRC_FILES "md_log_adapter.cc")
 set_property(SOURCE ${_CURRENT_SRC_FILES} PROPERTY COMPILE_DEFINITIONS SUBMODULE_ID=mindspore::SubModuleId::SM_MD)
 add_library(utils OBJECT ${_CURRENT_SRC_FILES})

mindspore/ccsrc/minddata/dataset/util/md_log_adapter.cc

@@ -0,0 +1,78 @@
+/**
+ * Copyright 2022 Huawei Technologies Co., Ltd
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "minddata/dataset/util/md_log_adapter.h"
+#include "minddata/dataset/util/status.h"
+
+#include <sstream>
+
+namespace mindspore {
+namespace dataset {
+Status MDLogAdapter::Apply(Status *rc) {
+  std::string status_msg = ConstructMsg(rc->StatusCode(), rc->CodeAsString(rc->StatusCode()), "", rc->GetLineOfCode(),
+                                        rc->GetFileName(), rc->GetErrDescription());
+  rc->SetStatusMsg(status_msg);
+  return *rc;
+}
+
+std::string MDLogAdapter::ConstructMsg(const enum StatusCode &status_code, const std::string &code_as_string,
+                                       const std::string &status_msg, const int line_of_code,
+                                       const std::string &file_name, const std::string &err_description) {
+  std::ostringstream ss;
+  std::string kSplitLine = std::string(66, '-') + "\n";
+  std::string err_ori = err_description;
+
+  /// Python Runtime Error
+  ss << code_as_string << ". \n\n";
+
+  /// Python Stack
+  std::string user_err;
+  std::string user_stack;
+  if (status_code == StatusCode::kMDPyFuncException) {
+    std::string at_stack = "\n\nAt:\n";
+    if (err_ori.find(at_stack) != std::string::npos) {
+      user_stack = err_ori.substr(0, err_ori.find(at_stack));
+      user_err = "Execute user Python code failed, check 'Python Call Stack' above.";
+      ss << kSplitLine << "- Python Call Stack: \n" << kSplitLine;
+      ss << user_stack << "\n\n";
+    } else {
+      user_err = err_ori;
+    }
+  }
+
+  /// Summary Message
+  ss << kSplitLine << "- Dataset Pipeline Error Message: \n" << kSplitLine;
+  if (!user_err.empty()) {
+    ss << "[ERROR] " + user_err + "\n\n";
+  } else {
+    user_err = err_description;
+    if (*user_err.rbegin() != '.') {
+      user_err += '.';
+    }
+    ss << "[ERROR] " + user_err + "\n\n";
+  }
+
+  /// C++ Stack
+  if (!file_name.empty()) {
+    ss << kSplitLine << "- C++ Call Stack: (For framework developers) \n" << kSplitLine;
+    std::string cpp_trace = std::string(file_name) + "(" + std::to_string(line_of_code) + ").\n";
+    ss << cpp_trace << "\n\n";
+  }
+
+  return ss.str();
+}
+}  //  namespace dataset
+}  //  namespace mindspore

mindspore/ccsrc/minddata/dataset/util/md_log_adapter.h

@@ -0,0 +1,41 @@
+/**
+ * Copyright 2022 Huawei Technologies Co., Ltd
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+#ifndef MINDSPORE_CCSRC_MINDDATA_DATASET_MD_LOG_ADAPTER_H_
+#define MINDSPORE_CCSRC_MINDDATA_DATASET_MD_LOG_ADAPTER_H_
+
+#include <iostream>
+#include <string>
+#include <utility>
+
+#include "include/api/status.h"
+
+namespace mindspore {
+namespace dataset {
+class MDLogAdapter {
+ public:
+  MDLogAdapter() = default;
+
+  ~MDLogAdapter() = default;
+
+  static Status Apply(Status *rc);
+
+  static std::string ConstructMsg(const enum StatusCode &status_code, const std::string &code_as_string,
+                                  const std::string &status_msg, const int line_of_code, const std::string &file_name,
+                                  const std::string &err_description);
+};
+}  // namespace dataset
+}  // namespace mindspore
+#endif  // MINDSPORE_CCSRC_MINDDATA_DATASET_MD_LOG_ADAPTER_H

mindspore/ccsrc/minddata/dataset/util/task_manager.cc

@@ -218,8 +218,10 @@ void TaskManager::InterruptMaster(const Status &rc) {
     master->caught_severe_exception_ = true;
     // Move log error here for some scenarios didn't call GetMasterThreadRc
     if (master->rc_.StatusCode() != mindspore::StatusCode::kMDPyFuncException) {
+#ifndef ENABLE_PYTHON
       // use python operation, the error had been raised in python layer. So disable log prompt here.
       MS_LOG(ERROR) << "Task is terminated with err msg (more details are in info level logs): " << master->rc_;
+#endif
     }
   }
 }

mindspore/ccsrc/minddata/mindrecord/CMakeLists.txt

@@ -34,6 +34,7 @@ endif()
 set_property(SOURCE ${DIR_LIB_SRCS} PROPERTY COMPILE_DEFINITIONS SUBMODULE_ID=mindspore::SubModuleId::SM_MD)
 add_library(mindrecord_obj OBJECT ${DIR_LIB_SRCS})
 add_library(_c_mindrecord SHARED $<TARGET_OBJECTS:mindrecord_obj>)
+add_dependencies(_c_mindrecord md_log_adapter)
 
 set_target_properties(_c_mindrecord PROPERTIES
     PREFIX "${PYTHON_MODULE_PREFIX}"
@@ -48,6 +49,7 @@ else()
                                                 mindspore::protobuf)
 endif()
 target_link_libraries(_c_mindrecord PRIVATE mindspore_core)
+target_link_libraries(_c_mindrecord PRIVATE md_log_adapter)
 if(USE_GLOG)
     target_link_libraries(_c_mindrecord PRIVATE mindspore::glog)
 else()

mindspore/ccsrc/minddata/mindrecord/common/shard_pybind.cc

@@ -18,6 +18,7 @@
 #include <vector>
 
 #include "utils/ms_utils.h"
+#include "minddata/dataset/util/md_log_adapter.h"
 #include "minddata/mindrecord/include/common/log_adapter.h"
 #include "minddata/mindrecord/include/common/shard_utils.h"
 #include "minddata/mindrecord/include/shard_error.h"
@@ -30,13 +31,14 @@
 #include "pybind11/stl.h"
 
 namespace py = pybind11;
+using mindspore::dataset::MDLogAdapter;
 
 namespace mindspore {
 namespace mindrecord {
-#define THROW_IF_ERROR(s)                                      \
+#define THROW_IF_ERROR(s)                                                            \
-  do {                                                         \
+  do {                                                                               \
-    Status rc = std::move(s);                                  \
+    Status rc = std::move(s);                                                        \
-    if (rc.IsError()) throw std::runtime_error(rc.ToString()); \
+    if (rc.IsError()) throw std::runtime_error(MDLogAdapter::Apply(&rc).ToString()); \
   } while (false)
 
 void BindSchema(py::module *m) {

mindspore/core/utils/status.cc

@@ -26,6 +26,7 @@
 #endif
 #include <map>
 #include <sstream>
+#include <iostream>
 
 namespace mindspore {
 struct Status::Data {
@@ -45,7 +46,7 @@ static std::map<enum StatusCode, std::string> status_info_map = {
   {kMDShapeMisMatch, "Shape is incorrect"},
   {kMDInterrupted, "Interrupted system call"},
   {kMDNoSpace, "No space left on device"},
-  {kMDPyFuncException, "Exception thrown from PyFunc"},
+  {kMDPyFuncException, "Exception thrown from user defined Python function in dataset"},
   {kMDDuplicateKey, "Duplicate key"},
   {kMDPythonInterpreterFailure, ""},
   {kMDTDTPushFailure, "Unexpected error"},
@@ -58,7 +59,7 @@ static std::map<enum StatusCode, std::string> status_info_map = {
   {kMDBuddySpaceFull, "BuddySpace full"},
   {kMDNetWorkError, "Network error"},
   {kMDNotImplementedYet, "Unexpected error"},
-  {kMDUnexpectedError, "Unexpected error"},
+  {kMDUnexpectedError, "Exception thrown from dataset pipeline. Refer to 'Dataset Pipeline Error Message'"},
   // ME
   {kMEFailed, "Common error code."},
   {kMEInvalidInput, "Invalid input."},
@@ -157,6 +158,13 @@ int Status::GetLineOfCode() const {
   return data_->line_of_code;
 }
 
+std::vector<char> Status::GetFileNameChar() const {
+  if (data_ == nullptr) {
+    return std::vector<char>();
+  }
+  return StringToChar(data_->file_name);
+}
+
 std::vector<char> Status::GetErrDescriptionChar() const {
   if (data_ == nullptr) {
     return std::vector<char>();
@@ -204,6 +212,13 @@ std::vector<char> Status::SetErrDescription(const std::vector<char> &err_descrip
   return StringToChar(data_->status_msg);
 }
 
+void Status::SetStatusMsgChar(const std::vector<char> &status_msg) {
+  if (data_ == nullptr) {
+    return;
+  }
+  data_->status_msg = CharToString(status_msg);
+}
+
 bool Status::operator==(const Status &other) const {
   if (data_ == nullptr && other.data_ == nullptr) {
     return true;

mindspore/lite/test/config_level0/cropped_size.cfg

@@ -1,2 +1,2 @@
 Note: This is the mindspore Lite inference framework size threshold. Offline review is required before modify this value!!!
-1097000
+1100096

mindspore/lite/test/config_level1/cropped_size.cfg

@@ -1,2 +1,2 @@
 Note: This is the mindspore Lite inference framework size threshold. Modifying this threshold requires meeting review.
-1097000
+1100096

mindspore/python/mindspore/dataset/core/py_util_helpers.py

@@ -53,9 +53,10 @@ class ExceptionHandler:
 
     def reraise(self):
         """Reraise the caught exception in the main thread/process"""
-        # Error message like: "Caught ValueError in GeneratorDataset worker process. Original Traceback:".
+        # Find the last traceback which is more useful to user.
-        err_msg = "Caught {} {}.\nOriginal {}".format(
+        index = [i for i in range(len(self.except_msg)) if self.except_msg.startswith('Traceback', i)]
-            self.except_type.__name__, self.where, self.except_msg)
+        err_msg = "{}".format(self.except_msg[index[-1]:]).strip()
+
         if self.except_type == KeyError:
             # As KeyError will call its repr() function automatically, which makes stack info hard to read.
             err_msg = KeyErrorParse(err_msg)

mindspore/python/mindspore/dataset/core/validator_helpers.py

@@ -760,7 +760,7 @@ def check_tensor_op(param, param_name):
 def check_c_tensor_op(param, param_name):
     """check whether param is a tensor op or a callable Python function but not a py_transform"""
     if callable(param) and str(param).find("py_transform") >= 0:
-        raise TypeError("{0} is a py_transform op which is not allow to use.".format(param_name))
+        raise TypeError("{0} is a py_transform op which is not allowed to use.".format(param_name))
     if not isinstance(param, cde.TensorOp) and not callable(param) and not getattr(param, 'parse', None):
         raise TypeError("{0} is neither a c_transform op (TensorOperation) nor a callable pyfunc.".format(param_name))
 

mindspore/python/mindspore/mindrecord/filewriter.py

@@ -266,7 +266,7 @@ class FileWriter:
         if not isinstance(raw_data, list):
             raise ParamTypeError('raw_data', 'list')
         if self._flush and not self._append:
-            raise RuntimeError("Unexpected error. Not allow to call `write_raw_data` on flushed MindRecord files." \
+            raise RuntimeError("Not allowed to call `write_raw_data` on flushed MindRecord files." \
                                "When creating new Mindrecord files, please remove `commit` before `write_raw_data`." \
                                "In other cases, when appending to existing MindRecord files, " \
                                "please call `open_for_append` first and then `write_raw_data`.")

tests/ut/cpp/CMakeLists.txt

@@ -283,7 +283,8 @@ set(ut_objects ${CORE_OBJECT_LIST} $<TARGET_OBJECTS:_ut_ut_obj> $<TARGET_OBJECTS
         $<TARGET_OBJECTS:_mindspore_common_obj>)
 
 if(ENABLE_MINDDATA)
-    set(ut_objects ${ut_objects} ${dataengine_submodules} $<TARGET_OBJECTS:mindrecord_obj>)
+    set(ut_objects ${ut_objects} ${dataengine_submodules} $<TARGET_OBJECTS:mindrecord_obj>
+        $<TARGET_OBJECTS:md_log_adapter_obj>)
 endif()
 add_executable(ut_tests ${ut_objects})
 

tests/ut/python/dataset/test_autotune.py

@@ -184,7 +184,7 @@ class TestAutotuneWithProfiler:
         with pytest.raises(RuntimeError) as excinfo:
             md_profiler.init()
 
-        assert "Unexpected error. Stop MD Autotune before initializing the MD Profiler." in str(excinfo.value)
+        assert "Stop MD Autotune before initializing the MD Profiler." in str(excinfo.value)
 
     @staticmethod
     def test_autotune_simple_pipeline():

tests/ut/python/dataset/test_cache_map.py

@@ -648,7 +648,7 @@ def test_cache_map_failure11():
         num_iter = 0
         for _ in ds1.create_dict_iterator(num_epochs=1):
             num_iter += 1
-    assert "Unexpected error. Server is not set up with spill support" in str(
+    assert "Server is not set up with spill support" in str(
         e.value)
 
     assert num_iter == 0

tests/ut/python/dataset/test_datasets_ag_news.py

@@ -131,7 +131,7 @@ def test_ag_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.AGNewsDataset(FILE_DIR, usage='test', shuffle=False)
@@ -140,7 +140,7 @@ def test_ag_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.AGNewsDataset(FILE_DIR, usage='test', shuffle=False)
@@ -149,7 +149,7 @@ def test_ag_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_amazon_review.py

@@ -165,7 +165,7 @@ def test_amazon_review_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.AmazonReviewDataset(FULL_DIR, usage='test', shuffle=False)
@@ -174,7 +174,7 @@ def test_amazon_review_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.AmazonReviewDataset(FULL_DIR, usage='test', shuffle=False)
@@ -183,7 +183,7 @@ def test_amazon_review_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_amazon_review_dataset_pipeline():

tests/ut/python/dataset/test_datasets_celeba.py

@@ -158,7 +158,7 @@ def test_celeba_dataset_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CelebADataset(DATA_DIR, shuffle=False)
@@ -168,7 +168,7 @@ def test_celeba_dataset_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CelebADataset(DATA_DIR, shuffle=False)
@@ -177,7 +177,7 @@ def test_celeba_dataset_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_celeba_sampler_exception():

tests/ut/python/dataset/test_datasets_cifarop.py

@@ -487,7 +487,7 @@ def test_cifar_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.Cifar10Dataset(DATA_DIR_10)
@@ -497,7 +497,7 @@ def test_cifar_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.Cifar100Dataset(DATA_DIR_100)
@@ -507,7 +507,7 @@ def test_cifar_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.Cifar100Dataset(DATA_DIR_100)
@@ -517,7 +517,7 @@ def test_cifar_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.Cifar100Dataset(DATA_DIR_100)
@@ -527,7 +527,7 @@ def test_cifar_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_cifar10_pk_sampler_get_dataset_size():

tests/ut/python/dataset/test_datasets_cityscapes.py

@@ -236,7 +236,7 @@ def test_cityscapes_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files:" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is:" in str(e)
 
     try:
         data = ds.CityscapesDataset(DATASET_DIR, usage=usage, quality_mode=quality_mode, task=task)
@@ -246,7 +246,7 @@ def test_cityscapes_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files:" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is:" in str(e)
 
 
 def test_cityscapes_param():

tests/ut/python/dataset/test_datasets_clue.py

@@ -409,7 +409,7 @@ def test_clue_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CLUEDataset(train_file, task='AFQMC', usage='train')
@@ -418,7 +418,7 @@ def test_clue_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CLUEDataset(train_file, task='AFQMC', usage='train')
@@ -427,7 +427,7 @@ def test_clue_exception_file_path():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_cmu_arctic.py

@@ -147,7 +147,7 @@ def test_cmu_arctic_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.CMUArcticDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["waveform"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_coco.py

@@ -429,7 +429,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Detection")
@@ -439,7 +439,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Detection")
@@ -448,7 +448,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Detection")
@@ -457,7 +457,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Stuff")
@@ -466,7 +466,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Stuff")
@@ -476,7 +476,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Stuff")
@@ -485,7 +485,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=ANNOTATION_FILE, task="Stuff")
@@ -494,7 +494,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=KEYPOINT_FILE, task="Keypoint")
@@ -503,7 +503,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=KEYPOINT_FILE, task="Keypoint")
@@ -513,7 +513,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=KEYPOINT_FILE, task="Keypoint")
@@ -522,7 +522,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=KEYPOINT_FILE, task="Keypoint")
@@ -531,7 +531,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=PANOPTIC_FILE, task="Panoptic")
@@ -540,7 +540,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=PANOPTIC_FILE, task="Panoptic")
@@ -550,7 +550,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=PANOPTIC_FILE, task="Panoptic")
@@ -559,7 +559,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=PANOPTIC_FILE, task="Panoptic")
@@ -568,7 +568,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=PANOPTIC_FILE, task="Panoptic")
@@ -577,7 +577,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=CAPTIONS_FILE, task="Captioning")
@@ -586,7 +586,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data1 = ds.CocoDataset(DATA_DIR, annotation_file=CAPTIONS_FILE, task="Captioning")
@@ -595,7 +595,7 @@ def test_coco_case_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == '__main__':

tests/ut/python/dataset/test_datasets_conll2000.py

@@ -324,7 +324,7 @@ def test_conll2000_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["word"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_csv.py

@@ -325,7 +325,7 @@ def test_csv_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CSVDataset(
@@ -338,7 +338,7 @@ def test_csv_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CSVDataset(
@@ -351,7 +351,7 @@ def test_csv_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.CSVDataset(
@@ -364,7 +364,7 @@ def test_csv_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_csv_dataset_duplicate_columns():

tests/ut/python/dataset/test_datasets_dbpedia.py

@@ -114,7 +114,7 @@ def test_dbpedia_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
     try:
         data = ds.DBpediaDataset(DATA_DIR, usage="test", shuffle=False)
         data = data.map(operations=exception_func, input_columns=["content"], num_parallel_workers=1)
@@ -122,7 +122,7 @@ def test_dbpedia_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_div2k.py

@@ -232,7 +232,7 @@ def test_div2k_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files:" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is:" in str(e)
 
     try:
         data = ds.DIV2KDataset(DATASET_DIR, usage=usage, downgrade=downgrade, scale=scale)
@@ -242,7 +242,7 @@ def test_div2k_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files:" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is:" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_emnist.py

@@ -359,7 +359,7 @@ def test_emnist_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.EMnistDataset(DATA_DIR, "mnist", "train")
         data = data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_enwik9.py

@@ -279,7 +279,7 @@ def test_enwik9_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["text"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_fashion_mnist.py

@@ -228,7 +228,7 @@ def test_fashion_mnist_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.FashionMnistDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_flickr.py

@@ -153,7 +153,7 @@ def test_flickr30k_dataset_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.FlickrDataset(FLICKR30K_DATASET_DIR, FLICKR30K_ANNOTATION_FILE_1, decode=True)
@@ -163,7 +163,7 @@ def test_flickr30k_dataset_exception():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_gtzan.py

@@ -150,7 +150,7 @@ def test_gtzan_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
 
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.GTZANDataset(DATA_DIR)

tests/ut/python/dataset/test_datasets_imagefolder.py

@@ -876,7 +876,7 @@ def test_imagefolder_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.ImageFolderDataset(DATA_DIR)
@@ -887,7 +887,7 @@ def test_imagefolder_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.ImageFolderDataset(DATA_DIR)
@@ -897,7 +897,7 @@ def test_imagefolder_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     data_dir_invalid = "../data/dataset/testPK"
     try:

tests/ut/python/dataset/test_datasets_imdb.py

@@ -686,7 +686,7 @@ def test_imdb_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.IMDBDataset(DATA_DIR)
@@ -697,7 +697,7 @@ def test_imdb_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     data_dir_invalid = "../data/dataset/IMDBDATASET"
     try:

tests/ut/python/dataset/test_datasets_iwslt.py

@@ -119,7 +119,7 @@ def test_iwslt2016_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.IWSLT2016Dataset(DATA_IWSLT2016_DIR, usage='train', language_pair=["de", "en"], shuffle=False)
@@ -128,7 +128,7 @@ def test_iwslt2016_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_iwslt2017_dataset_basic():
@@ -231,7 +231,7 @@ def test_iwslt2017_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.IWSLT2017Dataset(DATA_IWSLT2017_DIR, usage='train', language_pair=["de", "en"], shuffle=False)
@@ -240,7 +240,7 @@ def test_iwslt2017_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_kmnist.py

@@ -236,7 +236,7 @@ def test_kmnist_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.KMnistDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_libri_tts.py

@@ -149,7 +149,7 @@ def test_libri_tts_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.LibriTTSDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["waveform"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_lj_speech.py

@@ -124,7 +124,7 @@ def test_lj_speech_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.LJSpeechDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["waveform"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_lsun.py

@@ -561,7 +561,7 @@ def test_lsun_exception_map():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.LSUNDataset(DATA_DIR)
@@ -573,7 +573,7 @@ def test_lsun_exception_map():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.LSUNDataset(DATA_DIR)
@@ -583,7 +583,7 @@ def test_lsun_exception_map():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == '__main__':

tests/ut/python/dataset/test_datasets_manifestop.py

@@ -179,7 +179,7 @@ def test_manifest_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.ManifestDataset(DATA_FILE)
@@ -189,7 +189,7 @@ def test_manifest_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.ManifestDataset(DATA_FILE)
@@ -198,7 +198,7 @@ def test_manifest_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     NO_SOURCE_DATA_FILE = "../data/dataset/testManifestData/invalidNoSource.manifest"
     try:

tests/ut/python/dataset/test_datasets_mnist.py

@@ -217,7 +217,7 @@ def test_mnist_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.MnistDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_omniglot.py

@@ -453,7 +453,7 @@ def test_omniglot_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(
             e)
 
     try:
@@ -466,7 +466,7 @@ def test_omniglot_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.OmniglotDataset(DATA_DIR)
@@ -476,7 +476,7 @@ def test_omniglot_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == '__main__':

tests/ut/python/dataset/test_datasets_penn_treebank.py

@@ -361,7 +361,7 @@ def test_penn_treebank_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["text"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_qmnist.py

@@ -273,7 +273,7 @@ def test_qmnist_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.QMnistDataset(DATA_DIR, "train", True)
         data = data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_sbu.py

@@ -232,7 +232,7 @@ def test_sbu_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         dataset = ds.SBUDataset(DATA_DIR, decode=True)
         dataset = dataset.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_semeion.py

@@ -207,7 +207,7 @@ def test_semeion_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.SemeionDataset(DATA_DIR_SEMEION)
@@ -217,7 +217,7 @@ def test_semeion_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_semeion_pipeline():

tests/ut/python/dataset/test_datasets_sogou_news.py

@@ -153,7 +153,7 @@ def test_sogou_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.SogouNewsDataset(DATA_SOGOU_NEWS_DIR, usage='test', shuffle=False)
@@ -162,7 +162,7 @@ def test_sogou_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.SogouNewsDataset(DATA_SOGOU_NEWS_DIR, usage='test', shuffle=False)
@@ -171,7 +171,7 @@ def test_sogou_news_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_speech_commands.py

@@ -124,7 +124,7 @@ def test_speech_commands_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files."
+    error_msg_8 = "The corresponding data file is."
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.SpeechCommandsDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=["waveform"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_squad.py

@@ -205,7 +205,7 @@ def test_squad_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" \
+        assert "map operation: [PyFunc] failed. The corresponding data file is" \
             in str(e)
 
     try:
@@ -216,7 +216,7 @@ def test_squad_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" \
+        assert "map operation: [PyFunc] failed. The corresponding data file is" \
             in str(e)
 
     try:
@@ -227,7 +227,7 @@ def test_squad_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" \
+        assert "map operation: [PyFunc] failed. The corresponding data file is" \
             in str(e)
 
     try:
@@ -238,7 +238,7 @@ def test_squad_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" \
+        assert "map operation: [PyFunc] failed. The corresponding data file is" \
             in str(e)
 
 

tests/ut/python/dataset/test_datasets_stl10.py

@@ -305,7 +305,7 @@ def test_stl10_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         all_data = ds.STL10Dataset(DATA_DIR, "all")
         all_data = all_data.map(operations=exception_func, input_columns=["image"], num_parallel_workers=1)

tests/ut/python/dataset/test_datasets_tedlium.py

@@ -195,7 +195,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.TedliumDataset(DATA_DIR_TEDLIUM_RELEASE12, RELEASE1)
@@ -205,7 +205,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.TedliumDataset(DATA_DIR_TEDLIUM_RELEASE12, RELEASE2)
@@ -215,7 +215,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.TedliumDataset(DATA_DIR_TEDLIUM_RELEASE12, RELEASE2)
@@ -225,7 +225,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.TedliumDataset(DATA_DIR_TEDLIUM_RELEASE3, RELEASE3)
@@ -235,7 +235,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.TedliumDataset(DATA_DIR_TEDLIUM_RELEASE3, RELEASE3)
@@ -245,7 +245,7 @@ def test_tedlium_exception_file_path():
             num_rows += 1
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_tedlium_extensions():

tests/ut/python/dataset/test_datasets_textfileop.py

@@ -327,7 +327,7 @@ def test_textline_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["text"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_tfrecord.py

@@ -437,7 +437,7 @@ def test_tfrecord_exception():
         data = data.map(operations=exception_func, input_columns=["col_1d"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(info.value)
 
     with pytest.raises(RuntimeError) as info:
         schema = ds.Schema()
@@ -448,7 +448,7 @@ def test_tfrecord_exception():
         data = data.map(operations=exception_func, input_columns=["col_2d"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(info.value)
 
     with pytest.raises(RuntimeError) as info:
         schema = ds.Schema()
@@ -459,7 +459,7 @@ def test_tfrecord_exception():
         data = data.map(operations=exception_func, input_columns=["col_3d"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(info.value)
 
 
 if __name__ == '__main__':

tests/ut/python/dataset/test_datasets_udposop.py

@@ -311,7 +311,7 @@ def test_udpos_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["word"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_voc.py

@@ -296,7 +296,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False)
@@ -306,7 +306,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False)
@@ -315,7 +315,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False)
@@ -324,7 +324,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Detection", usage="train", shuffle=False)
@@ -333,7 +333,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Segmentation", usage="train", shuffle=False)
@@ -342,7 +342,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Segmentation", usage="train", shuffle=False)
@@ -352,7 +352,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Segmentation", usage="train", shuffle=False)
@@ -361,7 +361,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.VOCDataset(DATA_DIR, task="Segmentation", usage="train", shuffle=False)
@@ -371,7 +371,7 @@ def test_voc_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 def test_voc_num_classes():

tests/ut/python/dataset/test_datasets_wider_face.py

@@ -205,7 +205,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     # usage = all
     try:
@@ -215,7 +215,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -224,7 +224,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -233,7 +233,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -242,7 +242,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -251,7 +251,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -260,7 +260,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -269,7 +269,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.WIDERFaceDataset(DATA_DIR, shuffle=False)
@@ -278,7 +278,7 @@ def test_wider_face_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == '__main__':

tests/ut/python/dataset/test_datasets_wiki_text.py

@@ -370,7 +370,7 @@ def test_wiki_text_dataset_exceptions():
         data = data.map(operations=exception_func, input_columns=["text"], num_parallel_workers=1)
         for _ in data.__iter__():
             pass
-    assert "map operation: [PyFunc] failed. The corresponding data files" in str(error_info.value)
+    assert "map operation: [PyFunc] failed. The corresponding data file is" in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_yahoo_answers.py

@@ -122,7 +122,7 @@ def test_yahoo_answers_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
     try:
         data = ds.YahooAnswersDataset(DATA_DIR, usage="test", shuffle=False)
         data = data.map(operations=exception_func, input_columns=["content"], num_parallel_workers=1)
@@ -130,7 +130,7 @@ def test_yahoo_answers_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_yelp_review.py

@@ -129,7 +129,7 @@ def test_yelp_review_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
     try:
         data = ds.YelpReviewDataset(DATA_POLARITY_DIR, usage='test', shuffle=False)
@@ -138,7 +138,7 @@ def test_yelp_review_dataset_exception():
             pass
         assert False
     except RuntimeError as e:
-        assert "map operation: [PyFunc] failed. The corresponding data files" in str(e)
+        assert "map operation: [PyFunc] failed. The corresponding data file is" in str(e)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_datasets_yes_no.py

@@ -143,7 +143,7 @@ def test_yes_no_exception():
     def exception_func(item):
         raise Exception("Error occur!")
 
-    error_msg_8 = "The corresponding data files"
+    error_msg_8 = "The corresponding data file is"
     with pytest.raises(RuntimeError, match=error_msg_8):
         data = ds.YesNoDataset(DATA_DIR)
         data = data.map(operations=exception_func, input_columns=[

tests/ut/python/dataset/test_eager_vision.py

@@ -540,7 +540,7 @@ def test_eager_invalid_image_cutout():
         assert error_msg in str(error_info.value)
 
     my_input = np.random.randn(60, 50)
-    test_config(my_input, RuntimeError, "Unexpected error. CutOut: shape is invalid.")
+    test_config(my_input, RuntimeError, "CutOut: shape is invalid.")
 
     test_config(1, TypeError, "Input should be NumPy or PIL image, got <class 'int'>.")
     test_config(1.0, TypeError, "Input should be NumPy or PIL image, got <class 'float'>.")

tests/ut/python/dataset/test_five_crop.py

@@ -98,7 +98,7 @@ def test_five_crop_error_msg():
         for _ in data:
             pass
     error_msg = \
-        "Unexpected error. map operation: [ToTensor] failed. The op is OneToOne, can only accept one tensor as input."
+        "map operation: [ToTensor] failed. The op is OneToOne, can only accept one tensor as input."
     assert error_msg in str(info.value)
 
 

tests/ut/python/dataset/test_formatted_exception.py

@@ -0,0 +1,239 @@
+# Copyright 2022 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+import numpy as np
+import mindspore.dataset as ds
+import mindspore.dataset.vision as vision
+
+
+def test_generator_single_worker_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in GeneratorDataset scenario with one worker.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    class Gen():
+        def __init__(self):
+            self.data = [1, 2, 3, 4]
+        def __getitem__(self, index):
+            data = self.data[index]
+            return data/0
+        def __len__(self):
+            return 4
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False, num_parallel_workers=1)
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from user defined Python function in dataset" in str(e)
+        assert "Python Call Stack" in str(e)
+        assert "Traceback (most recent call last):" in str(e)
+        assert "ZeroDivisionError: division by zero" in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)
+
+
+def test_generator_multi_workers_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in GeneratorDataset scenario with multi-workers.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    def pyfunc(image):
+        return image
+
+    class Gen():
+        def __init__(self):
+            self.data = [[1], [2], [3], [4]]
+        def __getitem__(self, index):
+            image = Image.open(index)
+            return image
+        def __len__(self):
+            return 4
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False, num_parallel_workers=2)
+    dataset = dataset.map(operations=pyfunc, input_columns=["image"])
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from user defined Python function in dataset" in str(e)
+        assert "Python Call Stack" in str(e)
+        assert "Traceback (most recent call last):" in str(e)
+        assert "NameError: name 'Image' is not defined" in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)
+
+
+def test_batch_operator_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in batch operator scenario.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    class Gen():
+        def __init__(self):
+            self.data = [np.ones((2)), np.ones((2)), np.ones((2)), np.ones((2, 3))]
+        def __getitem__(self, index):
+            return self.data[index]
+        def __len__(self):
+            return 4
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False)
+    dataset = dataset.batch(2)
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from dataset pipeline. Refer to 'Dataset Pipeline Error Message'" in str(e)
+        assert "Python Call Stack" not in str(e)
+        assert "C++ Call Stack: (For framework developers)" in str(e)
+
+
+def test_batch_operator_with_pyfunc_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in batch operator with pyfunc scenario.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    class Gen():
+        def __init__(self):
+            self.data = [np.ones((2)), np.ones((2)), np.ones((2)), np.ones((2))]
+        def __getitem__(self, index):
+            return self.data[index]
+        def __len__(self):
+            return 4
+
+    def batch_func(col, batch_info):
+        zero = 0
+        fake_data = 1/zero
+        return np.ones((3)), np.array(fake_data)
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False)
+    dataset = dataset.batch(2, per_batch_map=batch_func, input_columns=["image"])
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from user defined Python function in dataset" in str(e)
+        assert "Python Call Stack" in str(e)
+        assert "Traceback (most recent call last):" in str(e)
+        assert "in batch_func" in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)
+
+
+def test_map_operator_with_c_ops_and_multiprocessing_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in map operator with c ops scenario.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    class Gen():
+        def __init__(self):
+            self.data = [np.ones((10, 10, 3)),
+                         np.ones((15, 15, 3)),
+                         np.ones((5, 5, 3))]
+        def __getitem__(self, index):
+            return self.data[index]
+        def __len__(self):
+            return 3
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False, num_parallel_workers=2)
+    dataset = dataset.map(operations=vision.RandomCrop((8, 8)), input_columns=["image"], num_parallel_workers=2)
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Shape is incorrect" in str(e)
+        assert "Python Call Stack" not in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)
+
+
+def test_map_operator_with_pyfunc_and_multithreading_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in map operator with pyfunc scenario.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    def pyfunc(image):
+        a = 1
+        b = 0
+        c = a/b
+        return c
+
+    class Gen():
+        def __init__(self):
+            self.data = [[1], [2], [3], [4]]
+        def __getitem__(self, index):
+            return self.data[index]
+        def __len__(self):
+            return 4
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False, num_parallel_workers=2)
+    dataset = dataset.map(operations=pyfunc, input_columns=["image"], num_parallel_workers=2)
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from user defined Python function in dataset" in str(e)
+        assert "Python Call Stack" in str(e)
+        assert "Traceback (most recent call last):" in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)
+
+
+def test_map_operator_with_pyfunc_and_multiprocessing_exception():
+    """
+    Feature: Formatted exception.
+    Description: Test formatted exception in map operator with pyfunc scenario.
+    Expectation: Python stack and summary message can be found in exception log.
+    """
+    def pyfunc(image):
+        a = 1
+        b = 0
+        c = a/b
+        return c
+
+    class Gen():
+        def __init__(self):
+            self.data = [[1], [2], [3], [4]]
+        def __getitem__(self, index):
+            return self.data[index]
+        def __len__(self):
+            return 4
+
+    dataset = ds.GeneratorDataset(Gen(), ["image"], shuffle=False, num_parallel_workers=1)
+    dataset = dataset.map(operations=pyfunc, input_columns=["image"], num_parallel_workers=2,
+                          python_multiprocessing=True)
+
+    try:
+        for data in dataset.create_dict_iterator(output_numpy=True, num_epochs=1):
+            print(data["image"].shape)
+        assert False
+    except RuntimeError as e:
+        assert "Exception thrown from user defined Python function in dataset" in str(e)
+        assert "Python Call Stack" in str(e)
+        assert "Traceback (most recent call last):" in str(e)
+        assert "in pyfunc" in str(e)
+        assert "Dataset Pipeline Error Message:" in str(e)

tests/ut/python/dataset/test_griffinlim.py

@@ -154,7 +154,7 @@ def test_griffin_lim_pipeline_invalid_param_constraint():
     data1 = ds.NumpySlicesDataset(in_data, column_names=["multi_dimensional_data"], shuffle=False)
 
     with pytest.raises(RuntimeError,
-                       match=r"Unexpected error. map operation: \[GriffinLim\] failed. " +
+                       match=r"map operation: \[GriffinLim\] failed. " +
                        r"GriffinLim: the frequency of the input should equal to n_fft / 2 \+ 1"):
         transforms = [c_audio.GriffinLim(n_fft=100)]
         data1 = data1.map(operations=transforms, input_columns=["multi_dimensional_data"])
@@ -162,7 +162,7 @@ def test_griffin_lim_pipeline_invalid_param_constraint():
             _ = item["multi_dimensional_data"]
 
     with pytest.raises(RuntimeError,
-                       match=r"Unexpected error. map operation: \[GriffinLim\] failed. " +
+                       match=r"map operation: \[GriffinLim\] failed. " +
                        r"GriffinLim: the frequency of the input should equal to n_fft / 2 \+ 1"):
         transforms = [c_audio.GriffinLim(n_fft=300, n_iter=10, win_length=0, hop_length=120)]
         data1 = data1.map(operations=transforms, input_columns=["multi_dimensional_data"])
@@ -170,7 +170,7 @@ def test_griffin_lim_pipeline_invalid_param_constraint():
             _ = item["multi_dimensional_data"]
 
     with pytest.raises(RuntimeError,
-                       match=r"Syntax error. GriffinLim: momentum equal to or greater than 1 can be unstable, " +
+                       match=r"GriffinLim: momentum equal to or greater than 1 can be unstable, " +
                        "but got: 1.000000"):
         transforms = [c_audio.GriffinLim(n_fft=300, n_iter=10, win_length=0, hop_length=0, power=2, momentum=1)]
         data1 = data1.map(operations=transforms, input_columns=["multi_dimensional_data"])

tests/ut/python/dataset/test_melscale_fbanks.py

@@ -115,7 +115,6 @@ def test_melscale_fbanks_invalid_input():
         logger.info("Test melscale_fbanks with bad input: {0}".format(test_name))
         with pytest.raises(error) as error_info:
             audio.melscale_fbanks(n_freqs, f_min, f_max, n_mels, sample_rate, norm, mel_type)
-        print(error_info)
         assert error_msg in str(error_info.value)
 
     test_invalid_input("invalid n_freqs parameter Value", 99999999999, 0, 50, 5, 100, audio.NormType.NONE,

tests/ut/python/dataset/test_minddataset_exception.py

@@ -113,7 +113,7 @@ def test_invalid_mindrecord():
         f.write('just for test')
     columns_list = ["data", "file_name", "label"]
     num_readers = 4
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid file, the size of mindrecord file header "
+    with pytest.raises(RuntimeError, match="Invalid file, the size of mindrecord file header "
                                            "is larger than the upper limit."):
         data_set = ds.MindDataset(file_name, columns_list, num_readers)
         for _ in data_set.create_dict_iterator(num_epochs=1, output_numpy=True):
@@ -375,21 +375,21 @@ def test_mindrecord_exception():
     file_name = os.environ.get('PYTEST_CURRENT_TEST').split(':')[-1].split(' ')[0]
     create_cv_mindrecord(file_name, 1)
     columns_list = ["data", "file_name", "label"]
-    with pytest.raises(RuntimeError, match="The corresponding data files"):
+    with pytest.raises(RuntimeError, match="The corresponding data file is"):
         data_set = ds.MindDataset(file_name, columns_list, shuffle=False)
         data_set = data_set.map(operations=exception_func, input_columns=["data"],
                                 num_parallel_workers=1)
         num_iter = 0
         for _ in data_set.create_dict_iterator(num_epochs=1, output_numpy=True):
             num_iter += 1
-    with pytest.raises(RuntimeError, match="The corresponding data files"):
+    with pytest.raises(RuntimeError, match="The corresponding data file is"):
         data_set = ds.MindDataset(file_name, columns_list, shuffle=False)
         data_set = data_set.map(operations=exception_func, input_columns=["file_name"],
                                 num_parallel_workers=1)
         num_iter = 0
         for _ in data_set.create_dict_iterator(num_epochs=1, output_numpy=True):
             num_iter += 1
-    with pytest.raises(RuntimeError, match="The corresponding data files"):
+    with pytest.raises(RuntimeError, match="The corresponding data file is"):
         data_set = ds.MindDataset(file_name, columns_list, shuffle=False)
         data_set = data_set.map(operations=exception_func, input_columns=["label"],
                                 num_parallel_workers=1)

tests/ut/python/dataset/test_profiling_startstop.py

@@ -252,7 +252,7 @@ class TestMindDataProfilingStartStop:
             # Reissue Start MindData Profiling
             self.md_profiler.start()
 
-        assert "MD ProfilingManager is already running." in str(info)
+        assert "MD ProfilingManager is already running." in str(info.value)
 
         # Stop MindData Profiling
         self.md_profiler.stop()
@@ -290,7 +290,7 @@ class TestMindDataProfilingStartStop:
             # Stop MindData Profiling - without prior Start()
             self.md_profiler.stop()
 
-        assert "MD ProfilingManager has not started yet." in str(info)
+        assert "MD ProfilingManager has not started yet." in str(info.value)
 
         # Start MindData Profiling
         self.md_profiler.start()

tests/ut/python/dataset/test_serdes_dataset.py

@@ -1028,19 +1028,19 @@ def test_serdes_not_implemented_op_exception():
                      vision.Perspective(start_points=[[0, 63], [63, 63], [63, 0], [0, 0]],
                                         end_points=[[0, 63], [63, 63], [63, 0], [0, 0]],
                                         interpolation=Inter.BILINEAR)])
-    assert "Unexpected error. Invalid data, unsupported operation: Perspective" in str(error_info.value)
+    assert "Invalid data, unsupported operation: Perspective" in str(error_info.value)
 
     # Proper to_json and from_json support has not yet been added for AdjustBrightness op
     with pytest.raises(RuntimeError) as error_info:
         test_config([vision.Decode(),
                      vision.AdjustBrightness(brightness_factor=2.0)])
-    assert "Unexpected error. Invalid data, unsupported operation: AdjustBrightness" in str(error_info.value)
+    assert "Invalid data, unsupported operation: AdjustBrightness" in str(error_info.value)
 
     # Proper to_json and from_json support has not yet been added for AdjustContrast op
     with pytest.raises(RuntimeError) as error_info:
         test_config([vision.Decode(),
                      vision.AdjustContrast(contrast_factor=2.0)])
-    assert "Unexpected error. Invalid data, unsupported operation: AdjustContrast" in str(error_info.value)
+    assert "Invalid data, unsupported operation: AdjustContrast" in str(error_info.value)
 
     # Restore configuration
     ds.config.set_seed(original_seed)

tests/ut/python/dataset/test_spectrogram.py

@@ -413,7 +413,7 @@ def test_spectrogram_param():
         _ = audio.Spectrogram(n_fft=100, center=False)(wav)
     except RuntimeError as error:
         logger.info("Got an exception in Spectrogram: {}".format(str(error)))
-        assert "Unexpected error. Spectrogram: n_fft should be more than 0 and less than 30," \
+        assert "Spectrogram: n_fft should be more than 0 and less than 30," \
                " but got n_fft: 100." in str(error)
 
 

tests/ut/python/dataset/test_ten_crop.py

@@ -191,7 +191,7 @@ def test_ten_crop_wrong_img_error_msg():
     with pytest.raises(RuntimeError) as info:
         data.create_tuple_iterator(num_epochs=1).__next__()
     error_msg = \
-        "Unexpected error. map operation: [ToTensor] failed. The op is OneToOne, can only accept one tensor as input."
+        "map operation: [ToTensor] failed. The op is OneToOne, can only accept one tensor as input."
     assert error_msg in str(info.value)
 
 

tests/ut/python/dataset/test_two_level_pipeline.py

@@ -124,7 +124,7 @@ def test_minddtaset_generatordataset_exception_01(add_and_remove_cv_file):
         for _ in range(num_epochs):
             for _ in iter_:
                 num_iter += 1
-    assert 'Unexpected error. Invalid data, column name:' in str(error_info.value)
+    assert 'Invalid data, column name:' in str(error_info.value)
 
 
 # pylint: disable=redefined-outer-name
@@ -187,7 +187,7 @@ def test_minddtaset_generatordataset_exception_02(add_and_remove_file):
             for item in iter_:
                 print("item: ", item)
                 num_iter += 1
-    assert 'Unexpected error. Invalid data, column name:' in str(error_info.value)
+    assert 'Invalid data, column name:' in str(error_info.value)
 
 
 def test_two_level_pipeline_with_multiprocessing():

tests/ut/python/dataset/test_uniform_augment.py

@@ -386,7 +386,7 @@ def test_cpp_uniform_augment_random_crop_badinput(num_ops=1):
     with pytest.raises(RuntimeError) as error_info:
         for _ in ds1.create_dict_iterator(num_epochs=1, output_numpy=True):
             num_batches += 1
-    assert "Shape is incorrect. map operation: [UniformAugment] failed." in str(error_info)
+    assert "map operation: [UniformAugment] failed." in str(error_info.value)
 
 
 if __name__ == "__main__":

tests/ut/python/dataset/test_vectors.py

@@ -195,7 +195,7 @@ def test_vectors_invalid_input():
                        error=RuntimeError, error_msg="invalid file, file is empty.")
     test_invalid_input("the count of `unknown_init`'s element is different with word vector.",
                        DATASET_ROOT_PATH + "vectors.txt",
-                       error=RuntimeError, error_msg="Unexpected error. ToVectors: " +
+                       error=RuntimeError, error_msg="ToVectors: " +
                        "unk_init must be the same length as vectors, but got unk_init: 2 and vectors: 6",
                        unk_init=[-1, -1])
     test_invalid_input("The file not exist", DATASET_ROOT_PATH + "not_exist.txt", error=RuntimeError,

tests/ut/python/dataset_deprecated/test_eager_vision.py

@@ -561,7 +561,7 @@ def test_eager_invalid_image_cutout_c():
         assert error_msg in str(error_info.value)
 
     my_input = np.random.randn(60, 50)
-    test_config(my_input, RuntimeError, "Unexpected error. CutOut: shape is invalid.")
+    test_config(my_input, RuntimeError, "CutOut: shape is invalid.")
 
     test_config(1, TypeError, "Input should be NumPy or PIL image, got <class 'int'>.")
     test_config(1.0, TypeError, "Input should be NumPy or PIL image, got <class 'float'>.")

tests/ut/python/dataset_deprecated/test_map.py

@@ -266,8 +266,8 @@ def test_map_with_exact_log():
         for data in dataset.create_dict_iterator():
             print(data["data"], data["label"])
     print("-----{}++++".format(info.value), flush=True)
-    assert str(info.value).count("Exception thrown from PyFunc") == 1
+    assert str(info.value).count("Exception thrown from user defined Python function") == 1
-    assert str(info.value).count("Caught TypeError in map") == 1
+    assert str(info.value).count("map operation") == 1
     assert str(info.value).count("img should be PIL image") == 1
 
 

tests/ut/python/dataset_deprecated/test_to_type.py

@@ -261,7 +261,7 @@ def test_to_type_05():
         data = data.map(operations=transform, input_columns=["image"])
         for _ in enumerate(data):
             pass
-    assert "data type" in str(error_info.value)
+    assert "datatype" in str(error_info.value)
 
 
 def test_to_type_invalid_arg():

tests/ut/python/mindrecord/test_cifar10_to_mindrecord.py

@@ -135,7 +135,7 @@ def test_cifar10_to_mindrecord_directory(fixture_file):
     when destination path is directory.
     """
     with pytest.raises(RuntimeError,
-                       match="Unexpected error. Invalid file, mindrecord files already exist. Please check file path:"):
+                       match="Invalid file, mindrecord files already exist. Please check file path:"):
         cifar10_transformer = Cifar10ToMR(CIFAR10_DIR, CIFAR10_DIR)
         cifar10_transformer.transform()
 
@@ -146,7 +146,7 @@ def test_cifar10_to_mindrecord_filename_equals_cifar10():
     when destination path equals source path.
     """
     with pytest.raises(RuntimeError,
-                       match="Unexpected error. Invalid file, mindrecord files already exist. Please check file path:"):
+                       match="Invalid file, mindrecord files already exist. Please check file path:"):
         cifar10_transformer = Cifar10ToMR(CIFAR10_DIR,
                                           CIFAR10_DIR + "/data_batch_0")
         cifar10_transformer.transform()

tests/ut/python/mindrecord/test_mindrecord_base.py

@@ -1229,7 +1229,7 @@ def test_mindrecord_commit_exception_01():
         writer.commit()
         writer.write_raw_data(data[5:10])
 
-    assert 'Unexpected error. Not allow to call `write_raw_data` on flushed MindRecord files.' in str(err.value)
+    assert 'Not allowed to call `write_raw_data` on flushed MindRecord files.' in str(err.value)
     remove_multi_files(mindrecord_file_name, 4)
 
 
@@ -1249,7 +1249,7 @@ def test_cv_file_overwrite_exception_01():
                           "label": {"type": "int64"}, "data": {"type": "bytes"}}
         writer.add_schema(cv_schema_json, "img_schema")
         writer.write_raw_data(data)
-    assert 'Unexpected error. Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
+    assert 'Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
     remove_multi_files(mindrecord_file_name, FILES_NUM)
 
 def test_cv_file_overwrite_exception_02():
@@ -1268,5 +1268,5 @@ def test_cv_file_overwrite_exception_02():
                           "label": {"type": "int64"}, "data": {"type": "bytes"}}
         writer.add_schema(cv_schema_json, "img_schema")
         writer.write_raw_data(data)
-    assert 'Unexpected error. Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
+    assert 'Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
     remove_multi_files(mindrecord_file_name, FILES_NUM)

tests/ut/python/mindrecord/test_mindrecord_exception.py

@@ -256,7 +256,7 @@ def test_invalid_db():
         f.write('just for test')
     with pytest.raises(RuntimeError) as err:
         FileReader(file_name)
-    assert "Unexpected error. Failed to execute the sql [ SELECT NAME from SHARD_NAME; ] " \
+    assert "Failed to execute the sql [ SELECT NAME from SHARD_NAME; ] " \
            "while verifying meta file" in str(err.value)
     remove_file(file_name)
 
@@ -271,7 +271,7 @@ def test_overwrite_invalid_mindrecord():
         f.write('just for test')
     with pytest.raises(RuntimeError) as err:
         create_cv_mindrecord(1, file_name)
-    assert 'Unexpected error. Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
+    assert 'Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
     remove_file(file_name)
 
 def test_overwrite_invalid_db():
@@ -285,7 +285,7 @@ def test_overwrite_invalid_db():
         f.write('just for test')
     with pytest.raises(RuntimeError) as err:
         create_cv_mindrecord(1, file_name)
-    assert 'Unexpected error. Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
+    assert 'Invalid file, mindrecord files already exist. Please check file path:' in str(err.value)
     remove_file(file_name)
 
 def test_read_after_close():
@@ -382,7 +382,7 @@ def test_mindpage_pageno_pagesize_not_int():
     with pytest.raises(ParamValueError):
         reader.read_at_page_by_name("822", 0, "qwer")
 
-    with pytest.raises(RuntimeError, match=r"Unexpected error. Invalid data, "
+    with pytest.raises(RuntimeError, match=r"Invalid data, "
                        r"category_id: 99999 must be in the range \[0, 10\]."):
         reader.read_at_page_by_id(99999, 0, 1)
     remove_file(file_name)
@@ -407,11 +407,11 @@ def test_mindpage_filename_not_exist():
     info = reader.read_category_info()
     logger.info("category info: {}".format(info))
 
-    with pytest.raises(RuntimeError, match=r"Unexpected error. Invalid data, "
+    with pytest.raises(RuntimeError, match=r"Invalid data, "
                        r"category_id: 9999 must be in the range \[0, 10\]."):
         reader.read_at_page_by_id(9999, 0, 1)
 
-    with pytest.raises(RuntimeError, match="Unexpected error. category_name: abc.jpg could not found."):
+    with pytest.raises(RuntimeError, match="category_name: abc.jpg could not found."):
         reader.read_at_page_by_name("abc.jpg", 0, 1)
 
     with pytest.raises(ParamValueError):
@@ -567,7 +567,7 @@ def test_write_with_invalid_data():
     mindrecord_file_name = os.environ.get('PYTEST_CURRENT_TEST').split(':')[-1].split(' ')[0]
 
     # field: file_name  =>  filename
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -603,7 +603,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # field: data  =>  image
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -639,7 +639,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # string type with int value
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -675,7 +675,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # field with int64 type, but the real data is string
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -711,7 +711,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # bytes field is string
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -747,7 +747,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # field is not numpy type
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")
@@ -783,7 +783,7 @@ def test_write_with_invalid_data():
         writer.commit()
 
     # not enough field
-    with pytest.raises(RuntimeError, match="Unexpected error. Invalid data, " \
+    with pytest.raises(RuntimeError, match="Invalid data, " \
                                            "the number of schema should be positive but got:"):
         remove_one_file(mindrecord_file_name)
         remove_one_file(mindrecord_file_name + ".db")