How to turn a JSON file into a stream of Java 8 objects?

Question

I have a very large> 1GB JSON file containing an array (it's confidential, but it's a proxy :)

 [
        {
            "date": "August 17, 2015",
            "hours": 7,
            "minutes": 10
        },
        {
            "date": "August 19, 2015",
            "hours": 4,
            "minutes": 46
        },
        {
            "date": "August 19, 2015",
            "hours": 7,
            "minutes": 22
        },
        {
            "date": "August 21, 2015",
            "hours": 4,
            "minutes": 48
        },
        {
            "date": "August 21, 2015",
            "hours": 6,
            "minutes": 1
        }
    ]

I used JSON2POJO to create a definition for the Sleep object.

Now you can use Jackson Mapper only to convert to an array, and then use Arrayys.stream (ARRAY). Also, this is a failure (yes, this is a BIG file).

The obvious one is to use the Jackson Streaming API. But this is super low. In particular, I still want Sleep Objects.

How to use Jackson Streaming JSON reader and my Sleep.java class to generate a stream of sleep Java 8 objects?

Answer 1

, : 1 JSON ( JSON , ), Jackson Java.

, Jackson Streaming API, , , , , ( ) Java 8 Streaming API.

GitHub

:

 //Use the JSON File included as a resource
 ClassLoader classLoader = SleepReader.class.getClassLoader();
 File dataFile = new File(classLoader.getResource("example.json").getFile());

 //Simple example of getting the Sleep Objects from that JSON
 new JsonArrayStreamDataSupplier<>(dataFile, Sleep.class) //Got the Stream
                .forEachRemaining(nightsRest -> {
                    System.out.println(nightsRest.toString());
                });

JSON example.json

   [
    {
        "date": "August 17, 2015",
        "hours": 7,
        "minutes": 10
    },
    {
        "date": "August 19, 2015",
        "hours": 4,
        "minutes": 46
    },
    {
        "date": "August 19, 2015",
        "hours": 7,
        "minutes": 22
    },
    {
        "date": "August 21, 2015",
        "hours": 4,
        "minutes": 48
    },
    {
        "date": "August 21, 2015",
        "hours": 6,
        "minutes": 1
    }
]

, GitHub ( ), :

    /**
 * @license APACHE LICENSE, VERSION 2.0 http://www.apache.org/licenses/LICENSE-2.0
 * @author Michael Witbrock
 */
package com.michaelwitbrock.jacksonstream;

import com.fasterxml.jackson.core.JsonFactory;
import com.fasterxml.jackson.core.JsonParser;
import com.fasterxml.jackson.core.JsonToken;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
import java.io.File;
import java.io.IOException;
import java.util.Iterator;
import java.util.Spliterators;
import java.util.stream.Stream;
import java.util.stream.StreamSupport;

public class JsonArrayStreamDataSupplier<T> implements Iterator<T> {
    /*
    * This class wraps the Jackson streaming API for arrays (a common kind of 
    * large JSON file) in a Java 8 Stream. The initial motivation was that 
    * use of a default objectmapper to a Java array was crashing for me on
    * a very large JSON file (> 1GB).  And there didn't seem to be good example 
    * code for handling Jackson streams as Java 8 streams, which seems natural.
    */

    static ObjectMapper mapper = new ObjectMapper();
    JsonParser parser;
    boolean maybeHasNext = false;
    int count = 0;
    JsonFactory factory = new JsonFactory();
    private Class<T> type;

    public JsonArrayStreamDataSupplier(File dataFile, Class<T> type) {
        this.type = type;
        try {
            // Setup and get into a state to start iterating
            parser = factory.createParser(dataFile);
            parser.setCodec(mapper);
            JsonToken token = parser.nextToken();
            if (token == null) {
                throw new RuntimeException("Can't get any JSON Token from "
                        + dataFile.getAbsolutePath());
            }

            // the first token is supposed to be the start of array '['
            if (!JsonToken.START_ARRAY.equals(token)) {
                // return or throw exception
                maybeHasNext = false;
                throw new RuntimeException("Can't get any JSON Token fro array start from "
                        + dataFile.getAbsolutePath());
            }
        } catch (Exception e) {
            maybeHasNext = false;
        }
        maybeHasNext = true;
    }

    /*
    This method returns the stream, and is the only method other 
    than the constructor that should be used.
    */
    public Stream<T> getStream() {
        return StreamSupport.stream(Spliterators.spliteratorUnknownSize(this, 0), false);
    }

    /* The remaining methods are what enables this to be passed to the spliterator generator, 
       since they make it Iterable.
    */
    @Override
    public boolean hasNext() {
        if (!maybeHasNext) {
            return false; // didn't get started
        }
        try {
            return (parser.nextToken() == JsonToken.START_OBJECT);
        } catch (Exception e) {
            System.out.println("Ex" + e);
            return false;
        }
    }

    @Override
    public T next() {
        try {
            JsonNode n = parser.readValueAsTree();
            //Because we can't send T as a parameter to the mapper
            T node = mapper.convertValue(n, type);
            return node;
        } catch (IOException | IllegalArgumentException e) {
            System.out.println("Ex" + e);
            return null;
        }

    }


}

Answer 2

Iterator

, Iterator, Jackson API.

22 , readValueAs , , , - , JSON Array, Jackson .

public class InputStreamJsonArrayStreamDataSupplier<T> implements Supplier<Stream<T>> {


private ObjectMapper mapper = new ObjectMapper();
private JsonParser jsonParser;
private Class<T> type;



public InputStreamJsonArrayStreamDataSupplier(Class<T> type) throws IOException {
    this.type = type;

    // Setup and get into a state to start iterating
    jsonParser = mapper.getFactory().createParser(data);
    jsonParser.setCodec(mapper);
    JsonToken token = jsonParser.nextToken();
    if (JsonToken.START_ARRAY.equals(token)) {
        // if it is started with START_ARRAY it ok
        token = jsonParser.nextToken();
    }
    if (!JsonToken.START_OBJECT.equals(token)) {
        throw new RuntimeException("Can't get any JSON object from input " + data);
    }
}


public Stream<T> get() {
    try {
        return StreamSupport.stream(Spliterators.spliteratorUnknownSize((Iterator<T>) jsonParser.readValuesAs(type), 0), false);
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}
}