auto qbarrier = rewriter.create<QuantizeCastOp>(op.getLoc(), quantizedType,
                                                    op.getInputs());
    rewriter.replaceOpWithNewOp<DequantizeCastOp>(op, converter.input_type,
                                                  qbarrier.getResult());

    return false;
  }
};

class ConstFakeQuantRewrite
    : public FakeQuantRewrite<ConstFakeQuantRewrite, ConstFakeQuant> {

}
var file_pkg_test_config_mock_config_proto_depIdxs = []int32{
	1, // 0: config.MockConfig.pairs:type_name -> config.ConfigPair
	1, // [1:1] is the sub-list for method output_type
	1, // [1:1] is the sub-list for method input_type
	1, // [1:1] is the sub-list for extension type_name
	1, // [1:1] is the sub-list for extension extendee
	0, // [0:1] is the sub-list for field type_name
}

    private List<Object> getInputValues(List<Class<?>> inputTypes, MetadataProvider metadataProvider) {
        if (inputTypes.size() == 0) {
            return Collections.emptyList();
        }

        if (!metadataProvider.isUsable()) {
            return null;
        }

        List<Object> inputs = new ArrayList<>(inputTypes.size());
        for (Class<?> inputType : inputTypes) {
            if (inputType == ComponentMetadata.class) {

        return action(modelPath, inputType, inputType.toString(), action);
    }

    public <I> ModelAction action(String modelPath, ModelType<I> inputType, BiAction<? super T, ? super I> action) {
        return action(modelPath, inputType, modelPath, action);
    }

    private void validateInputTypes(RuleAction<?> ruleAction) {
        for (Class<?> inputType : ruleAction.getInputTypes()) {
            if (!validInputType.contains(inputType)) {
                throw new RuleActionValidationException(invalidParameterMessage(inputType));
            }
        }
    }

    private String invalidParameterMessage(Class<?> inputType) {
        if (validInputType.isEmpty()) {

    for (int index : dynamic_shape_arg_index) {
      BlockArgument arg = func.getArgument(index);
      auto inputType = mlir::dyn_cast<RankedTensorType>(arg.getType());
      // Only rank 1 tensor is supported for now.
      if (!inputType || inputType.getRank() != 1) continue;
      auto shape = llvm::to_vector<4>(inputType.getShape());
      llvm::SmallVector<int64_t, 4> bounds(shape.begin(), shape.end());
      // Mark the dim as dynamic dim.

        File input = getInput().get().getAsFile();
        InstrumentationInputType inputType = getInputType(input);
        switch (inputType) {
            case DEPENDENCY_ANALYSIS_DATA:
                doOutputTransformedFile(input, outputs);
                return;
            case ORIGINAL_ARTIFACT:

        ruleAction.execute("string", [])

        then:
        ruleAction.inputTypes == []
        closureCalled == "string"

        when:
        ruleAction = ruleActionAdapter.createFromClosure(String, { s -> closureCalled = s })
        ruleAction.execute("object", [])

        then:
        ruleAction.inputTypes == []
        closureCalled == "object"

        when:

    private final List<Class<?>> inputTypes;

    public ClosureBackedRuleAction(Class<T> subjectType, Closure<?> closure) {
        this.subjectType = subjectType;
        this.closure = closure;
        this.inputTypes = parseInputTypes(closure);
    }

    @Override
    public List<Class<?>> getInputTypes() {
        return inputTypes;
    }

    @Override

        File input = getInput().get().getAsFile();
        InstrumentationInputType inputType = getInputType(input);
        switch (inputType) {
            case DEPENDENCY_ANALYSIS_DATA:
                doMergeAndOutputAnalysis(input, outputs);
                return;
            case ORIGINAL_ARTIFACT: