assert this.classifier == classifier
    }

    IvyDescriptorArtifact hasConf(def conf) {
        assert this.conf == conf
        return this
    }

    IvyDescriptorArtifact hasType(def type) {
        assert this.type == type
        return this
    }

    String getClassifier() {
        this.mavenAttributes.get("classifier")
    }

    }

    @Override
    public T hasPackaging(String packaging) {
        backingModule.hasPackaging(packaging);
        return t();
    }

    @Override
    public T hasType(String type) {
        backingModule.hasType(type);
        return t();
    }

    @Override
    public T variant(String variant, Map<String, String> attributes) {
        backingModule.variant(variant, attributes);

            Value<? extends V> value = providerOfValue.calculateValue(consumer);
            if (value.isMissing()) {
                return value.asType();
            }
            collector.add(key, value.getWithoutSideEffect(), dest);
            return Value.present().withSideEffect(SideEffect.fixedFrom(value));
        }

        @Override

            low=-1.0, high=1.0, size=(4, 3)
        ).astype('f4')
        self.bias_0 = np.random.uniform(low=-1.0, high=1.0, size=(3,)).astype(
            'f4'
        )

        self.filters_1 = np.random.uniform(
            low=-1.0, high=1.0, size=(4, 3)
        ).astype('f4')
        self.bias_1 = np.random.uniform(low=-1.0, high=1.0, size=(3,)).astype(
            'f4'
        )

}

// request is an injectable interface representing a netlink request.
type request interface {
	Serialize() []byte
	AddData(data nl.NetlinkRequestData)
	AddRawData(data []byte)
	Execute(sockType int, resType uint16) ([][]byte, error)
}

// netlinkHandler is an implementation of the handler interface. It maintains a netlink socket
// for communication with the NFAcct subsystem.
type netlinkHandler struct {

              np.random.uniform(size=bias_shape), dtype=dtypes.float32
          )

        self._kernel = np.random.uniform(size=y_shape).astype('f4')
        self._min = (-0.8, -0.8, -0.9)
        self._max = (0.9, 0.9, 1.0)

      @def_function.function(
          input_signature=[
              tensor_spec.TensorSpec(
                  name='x', shape=x_signature, dtype=dtypes.float32
              )
          ]

		buf.WriteString(" (")
	}

	// <untyped kind>
	hasType := false
	switch x.mode {
	case invalid, novalue, builtin, typexpr:
		// no type
	default:
		// should have a type, but be cautious (don't crash during printing)
		if x.typ != nil {
			if isUntyped(x.typ) {
				buf.WriteString(x.typ.(*Basic).name)
				buf.WriteByte(' ')
				break
			}
			hasType = true
		}
	}

	// <mode>

              np.random.uniform(size=bias_shape), dtype=dtypes.float32
          )

        self._kernel = np.random.uniform(size=y_shape).astype('f4')
        self._min = (-0.8, -0.8, -0.9)
        self._max = (0.9, 0.9, 1.0)

      @def_function.function(
          input_signature=[
              tensor_spec.TensorSpec(
                  name='x', shape=x_signature, dtype=dtypes.float32
              )
          ]

		buf.WriteString(" (")
	}

	// <untyped kind>
	hasType := false
	switch x.mode {
	case invalid, novalue, builtin, typexpr:
		// no type
	default:
		// should have a type, but be cautious (don't crash during printing)
		if x.typ != nil {
			if isUntyped(x.typ) {
				buf.WriteString(x.typ.(*Basic).name)
				buf.WriteByte(' ')
				break
			}
			hasType = true
		}
	}

	// <mode>

        error("type $type used in a function is not in schema scope")
    }
}


private
fun KClassifier.isInScope(typeScope: DataSchemaBuilder.PreIndex) =
    isBuiltInType || this is KClass<*> && typeScope.hasType(this)


private
val KClassifier.isBuiltInType: Boolean
    get() = when (this) {
        Int::class, String::class, Boolean::class, Long::class, Unit::class -> true
        else -> false
    }