!9339 Disable getter optimization pass

From: @ezphlow
Reviewed-by: @robingrosman,@nsyca
Signed-off-by: @nsyca

mindspore/ccsrc/minddata/dataset/engine/datasetops/dataset_op.cc

@@ -323,6 +323,7 @@ Status DatasetOp::GetNumClasses(int64_t *num_classes) {
     return child_[child_.size() - 1]->GetNumClasses(num_classes);
   } else {
     // when num classes isn't found, the default behavior is to return -1
+    MS_LOG(WARNING) << "Num classes not defined for : " << Name();
     *num_classes = -1;
     return Status::OK();
   }

mindspore/ccsrc/minddata/dataset/engine/opt/pre/getter_pass.cc

@@ -54,15 +54,7 @@ Status GetterPass::GetterNodes::RunOnNode(std::shared_ptr<FilterOp> node, bool *
 Status GetterPass::RunOnTree(ExecutionTree *tree, bool *modified) {
   RETURN_IF_NOT_OK(pass_.Run(tree, modified));
 
-  // nested private class variables can be directly accessed by its outer class
-  for (auto node : pass_.nodes_to_remove_) {
-    DatasetOp *parent;
-    node->Parent(&parent, 0);
-    // only remove node whose is a single child of its parent
-    if (parent != nullptr && parent->Children().size() == 1) {
-      RETURN_IF_NOT_OK(node->Remove());
-    }
-  }
+  // currently the getter pass only disables call_back from the execution tree
 
   // clear the callback for selected ops (map when its GetOutputType/Shape)
   for (auto node : pass_.nodes_to_clear_callback_) node->ClearCallbacks();

mindspore/ccsrc/minddata/dataset/text/kernels/basic_tokenizer_op.cc

@@ -131,7 +131,7 @@ Status BasicTokenizerOp::CaseFoldWithoutUnusedWords(const std::string_view &text
 Status BasicTokenizerOp::CaseFoldWithoutUnusedWords(const std::shared_ptr<Tensor> &input,
                                                     std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string");
+  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string.");
   std::vector<std::string> strs(input->Size());
   int i = 0;
   for (auto iter = input->begin<std::string_view>(); iter != input->end<std::string_view>(); iter++) {

mindspore/ccsrc/minddata/dataset/text/kernels/case_fold_op.cc

@@ -29,7 +29,7 @@ namespace dataset {
 
 Status CaseFoldOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string");
+  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string.");
   icu::ErrorCode error;
   const icu::Normalizer2 *nfkc_case_fold = icu::Normalizer2::getNFKCCasefoldInstance(error);
   CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFKCCasefoldInstance failed.");

mindspore/ccsrc/minddata/dataset/text/kernels/jieba_tokenizer_op.cc

@@ -33,11 +33,11 @@ JiebaTokenizerOp::JiebaTokenizerOp(const std::string &hmm_path, const std::strin
 
 Status JiebaTokenizerOp::Compute(const TensorRow &input, TensorRow *output) {
   IO_CHECK_VECTOR(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor");
+  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor.");
   RETURN_UNEXPECTED_IF_NULL(jieba_parser_);
 
   if (input[0]->Rank() != 0 || input[0]->type() != DataType::DE_STRING) {
-    RETURN_STATUS_UNEXPECTED("the input tensor should be scalar string tensor");
+    RETURN_STATUS_UNEXPECTED("the input tensor should be scalar string tensor.");
   }
 
   std::string_view sentence_v;

mindspore/ccsrc/minddata/dataset/text/kernels/ngram_op.cc

@@ -35,7 +35,7 @@ NgramOp::NgramOp(const std::vector<int32_t> &ngrams, int32_t l_len, int32_t r_le
 
 Status NgramOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING && input->Rank() == 1, "Not a 1-D str Tensor");
+  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING && input->Rank() == 1, "Not a 1-D str Tensor.");
   std::vector<int32_t> offsets;                 // offsets for each str
   std::vector<std::string> res;                 // holds the result of ngrams
   std::string str_buffer;                       // concat all pad tokens with string interleaved with separators
@@ -60,7 +60,7 @@ Status NgramOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Te
     if (end_ind - start_ind <= n) {
       res.emplace_back(std::string());  // push back empty string
     } else {
-      CHECK_FAIL_RETURN_UNEXPECTED(end_ind - n >= 0, "Incorrect loop condition");
+      CHECK_FAIL_RETURN_UNEXPECTED(end_ind - n >= 0, "Incorrect loop condition.");
 
       for (int i = start_ind; i < end_ind - n; i++) {
         res.emplace_back(str_buffer.substr(offsets[i], offsets[i + n] - offsets[i] - separator_.size()));

mindspore/ccsrc/minddata/dataset/text/kernels/normalize_utf8_op.cc

@@ -29,7 +29,7 @@ namespace dataset {
 const NormalizeForm NormalizeUTF8Op::kDefNormalizeForm = NormalizeForm::kNfkc;
 Status NormalizeUTF8Op::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string");
+  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string.");
 
   icu::ErrorCode error;
   const icu::Normalizer2 *normalize = nullptr;
@@ -40,26 +40,26 @@ Status NormalizeUTF8Op::Compute(const std::shared_ptr<Tensor> &input, std::share
     }
     case NormalizeForm::kNfc: {
       normalize = icu::Normalizer2::getNFCInstance(error);
-      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFCInstance failed");
+      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFCInstance failed.");
       break;
     }
     case NormalizeForm::kNfkc: {
       normalize = icu::Normalizer2::getNFKCInstance(error);
-      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFKCInstance failed");
+      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFKCInstance failed.");
       break;
     }
     case NormalizeForm::kNfd: {
       normalize = icu::Normalizer2::getNFDInstance(error);
-      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFDInstance failed");
+      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFDInstance failed.");
       break;
     }
     case NormalizeForm::kNfkd: {
       normalize = icu::Normalizer2::getNFKDInstance(error);
-      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFKDInstance failed");
+      CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "getNFKDInstance failed.");
       break;
     }
     default: {
-      RETURN_STATUS_UNEXPECTED("unexpected normalize form");
+      RETURN_STATUS_UNEXPECTED("Unexpected normalize form.");
       break;
     }
   }
@@ -68,7 +68,7 @@ Status NormalizeUTF8Op::Compute(const std::shared_ptr<Tensor> &input, std::share
   for (auto iter = input->begin<std::string_view>(); iter != input->end<std::string_view>(); iter++) {
     icu::StringByteSink<std::string> sink(&strs[i++]);
     normalize->normalizeUTF8(0, icu::StringPiece((*iter).data(), (*iter).size()), sink, nullptr, error);
-    CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "normalizeUTF8 failed.");
+    CHECK_FAIL_RETURN_UNEXPECTED(error.isSuccess(), "NormalizeUTF8 failed.");
   }
   return Tensor::CreateFromVector(strs, input->shape(), output);
 }

mindspore/ccsrc/minddata/dataset/text/kernels/regex_replace_op.cc

@@ -25,7 +25,7 @@ namespace dataset {
 
 Status RegexReplaceOp::RegexReplace(icu::RegexMatcher *const matcher, const std::string_view &text,
                                     std::string *out) const {
-  CHECK_FAIL_RETURN_UNEXPECTED((matcher != nullptr && out != nullptr), "Input is null");
+  CHECK_FAIL_RETURN_UNEXPECTED((matcher != nullptr && out != nullptr), "Input is null.");
   UErrorCode icu_error = U_ZERO_ERROR;
   icu::UnicodeString unicode_text = icu::UnicodeString::fromUTF8(text);
   matcher->reset(unicode_text);
@@ -35,17 +35,18 @@ Status RegexReplaceOp::RegexReplace(icu::RegexMatcher *const matcher, const std:
   } else {
     unicode_out = matcher->replaceFirst(replace_, icu_error);
   }
-  CHECK_FAIL_RETURN_UNEXPECTED(U_SUCCESS(icu_error), "RegexReplace failed");
+  CHECK_FAIL_RETURN_UNEXPECTED(U_SUCCESS(icu_error), "RegexReplace failed.");
   unicode_out.toUTF8String(*out);
   return Status::OK();
 }
 
 Status RegexReplaceOp::Compute(const std::shared_ptr<Tensor> &input, std::shared_ptr<Tensor> *output) {
   IO_CHECK(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string");
+  CHECK_FAIL_RETURN_UNEXPECTED(input->type() == DataType::DE_STRING, "Input tensor not of type string.");
   UErrorCode icu_error = U_ZERO_ERROR;
   icu::RegexMatcher matcher(pattern_, 0, icu_error);
-  CHECK_FAIL_RETURN_UNEXPECTED(U_SUCCESS(icu_error), "Create icu RegexMatcher failed, you may input one error pattern");
+  CHECK_FAIL_RETURN_UNEXPECTED(U_SUCCESS(icu_error),
+                               "Create icu RegexMatcher failed, you may input one error pattern.");
   std::vector<std::string> strs(input->Size());
   int i = 0;
   for (auto iter = input->begin<std::string_view>(); iter != input->end<std::string_view>(); iter++) {

mindspore/ccsrc/minddata/dataset/text/kernels/sentence_piece_tokenizer_op.cc

@@ -56,7 +56,7 @@ Status SentencePieceTokenizerOp::Compute(const std::shared_ptr<Tensor> &input, s
   }
 
   if (input->Rank() != 0 || input->type() != DataType::DE_STRING) {
-    RETURN_STATUS_UNEXPECTED("the input tensor should be scalar string tensor");
+    RETURN_STATUS_UNEXPECTED("Input tensor should be scalar string tensor.");
   }
 
   std::string_view sentence_v;
@@ -67,14 +67,14 @@ Status SentencePieceTokenizerOp::Compute(const std::shared_ptr<Tensor> &input, s
     std::vector<std::string> pieces;
     auto status = processor_.Encode(sentence, &pieces);
     if (!status.ok()) {
-      RETURN_STATUS_UNEXPECTED("sentence piece tokenizer error");
+      RETURN_STATUS_UNEXPECTED("Sentence piece tokenizer error.");
     }
     RETURN_IF_NOT_OK(Tensor::CreateFromVector(pieces, output));
   } else {
     std::vector<int> ids;
     auto status = processor_.Encode(sentence, &ids);
     if (!status.ok()) {
-      RETURN_STATUS_UNEXPECTED("sentence piece tokenizer error");
+      RETURN_STATUS_UNEXPECTED("Sentence piece tokenizer error.");
     }
     RETURN_IF_NOT_OK(Tensor::CreateFromVector(ids, output));
   }
@@ -84,15 +84,15 @@ Status SentencePieceTokenizerOp::Compute(const std::shared_ptr<Tensor> &input, s
 Status SentencePieceTokenizerOp::GetModelRealPath(const std::string &model_path, const std::string &filename) {
   char real_path[PATH_MAX] = {0};
   if (file_path_.size() >= PATH_MAX) {
-    RETURN_STATUS_UNEXPECTED("sentence piece model path is invalid.");
+    RETURN_STATUS_UNEXPECTED("Sentence piece model path is invalid.");
   }
 #if defined(_WIN32) || defined(_WIN64)
   if (_fullpath(real_path, common::SafeCStr(model_path), PATH_MAX) == nullptr) {
-    RETURN_STATUS_UNEXPECTED("sentence piece model path is invalid.");
+    RETURN_STATUS_UNEXPECTED("Sentence piece model path is invalid.");
   }
 #else
   if (realpath(common::SafeCStr(model_path), real_path) == nullptr) {
-    RETURN_STATUS_UNEXPECTED("sentence piece model path  is invalid.");
+    RETURN_STATUS_UNEXPECTED("Sentence piece model path  is invalid.");
   }
 #endif
   std::string abs_path = real_path;

mindspore/ccsrc/minddata/dataset/text/kernels/truncate_sequence_pair_op.cc

@@ -29,7 +29,7 @@ Status TruncateSequencePairOp::Compute(const TensorRow &input, TensorRow *output
   std::shared_ptr<Tensor> seq1 = input[0];
   std::shared_ptr<Tensor> seq2 = input[1];
   CHECK_FAIL_RETURN_UNEXPECTED(seq1->shape().Rank() == 1 && seq2->shape().Rank() == 1,
-                               "Both sequences should be of rank 1");
+                               "Both sequences should be of rank 1.");
   dsize_t length1 = seq1->shape()[0];
   dsize_t length2 = seq2->shape()[0];
   dsize_t outLength1 = length1;

mindspore/ccsrc/minddata/dataset/text/kernels/unicode_char_tokenizer_op.cc

@@ -31,9 +31,9 @@ const bool UnicodeCharTokenizerOp::kDefWithOffsets = false;
 
 Status UnicodeCharTokenizerOp::Compute(const TensorRow &input, TensorRow *output) {
   IO_CHECK_VECTOR(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor");
+  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor.");
   if (input[0]->Rank() != 0 || input[0]->type() != DataType::DE_STRING) {
-    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar string tensor");
+    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar string tensor.");
   }
   std::string_view str;
   RETURN_IF_NOT_OK(input[0]->GetItemAt(&str, {}));

mindspore/ccsrc/minddata/dataset/text/kernels/whitespace_tokenizer_op.cc

@@ -35,9 +35,9 @@ const bool WhitespaceTokenizerOp::kDefWithOffsets = false;
 
 Status WhitespaceTokenizerOp::Compute(const TensorRow &input, TensorRow *output) {
   IO_CHECK_VECTOR(input, output);
-  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor");
+  CHECK_FAIL_RETURN_UNEXPECTED(input.size() == 1, "Input should be one tensor.");
   if (input[0]->Rank() != 0 || input[0]->type() != DataType::DE_STRING) {
-    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar string tensor");
+    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar string tensor.");
   }
   std::string_view str;
   RETURN_IF_NOT_OK(input[0]->GetItemAt(&str, {}));

mindspore/ccsrc/minddata/dataset/text/kernels/wordpiece_tokenizer_op.cc

@@ -117,7 +117,7 @@ Status WordpieceTokenizerOp::GetTokens(const std::string &input_token, const uin
 Status WordpieceTokenizerOp::Compute(const TensorRow &input, TensorRow *output) {
   IO_CHECK_VECTOR(input, output);
   if (input[0]->Rank() > 1 || input[0]->type() != DataType::DE_STRING) {
-    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar or 1-D string tensor");
+    RETURN_STATUS_UNEXPECTED("The input tensor should be scalar or 1-D string tensor.");
   }
   dsize_t count = 0;
   std::vector<std::string> out_tokens;

tests/ut/cpp/dataset/optimization_pass_test.cc

@@ -95,9 +95,9 @@ TEST_F(MindDataTestOptimizationPass, MindDataTestOutputShapeAndTypePass) {
   //        +- ( 4) <RandomDataOp>: [workers: 4] [total rows: 44]
   //
 
-  // verify that Shuffle and RepeatOp are removed, but Batch and ProjectOp are not
-  EXPECT_EQ(ss_str.find("ShuffleOp"), ss_str.npos);
-  EXPECT_EQ(ss_str.find("RepeatOp"), ss_str.npos);
+  // verify that no ops are removed, but Batch and ProjectOp are not
+  EXPECT_NE(ss_str.find("ShuffleOp"), ss_str.npos);
+  EXPECT_NE(ss_str.find("RepeatOp"), ss_str.npos);
   EXPECT_NE(ss_str.find("ProjectOp"), ss_str.npos);
   EXPECT_NE(ss_str.find("BatchOp"), ss_str.npos);
 }
@@ -129,8 +129,8 @@ TEST_F(MindDataTestOptimizationPass, MindDataTestDatasetSizePass) {
   exe_tree->Print(ss);
   std::string ss_str = ss.str();
 
-  // verify that Shuffle and RepeatOp are removed, but Batch and ProjectOp are not
-  EXPECT_EQ(ss_str.find("ShuffleOp"), ss_str.npos);
+  // verify that no ops are removed, but Batch and ProjectOp are not
+  EXPECT_NE(ss_str.find("ShuffleOp"), ss_str.npos);
   EXPECT_NE(ss_str.find("RepeatOp"), ss_str.npos);
   EXPECT_NE(ss_str.find("ProjectOp"), ss_str.npos);
   EXPECT_NE(ss_str.find("BatchOp"), ss_str.npos);