Graphlytic 5.2.0

Table of Contents

1. Description

Executes arbitrary groovy script

2. Connection

2.1. Attributes

There are no special attributes supported for this driver.

2.2. Parameters

The only parameter is “language”:

language=groovy

3. Query

Executes the Groovy query. Used for the read statements.

The entire code should be enclosed in <![CDATA[ ]]> element.

In order to proceed to the next query processor use:

query.next()

You can use any <script> in the body of the query to process every record returned by the query one by one. The easiest way to return/forward current entry into another subquery/script is to use etl.globals object, for example:

etl.globals['my_value'] = "some value"

In order to use results from the previous <query> element, use:

etl.getParameter('name_of_property')

4. Script

Executes any read or write statements. Used mainly for "write" statements.

5. Examples

Query example: Reads a Graphson document, parses each vertex into a HashMap, and processes the entries one by one. After that, it parses each edge into a HashMap and processes the entries one by one.

<!DOCTYPE etl SYSTEM "https://scriptella.org/dtd/etl.dtd">
 <etl>
    <description>Graphlytic job</description>
                
    <properties>
        job_name=Graphlytic job
    </properties>
 
    <!-- CONNECTIONS -->
    <connection id="graphdb" driver="graphConnection">
        project_id=1
    </connection>
    
    <connection id="groovy" driver="script">language=groovy</connection>
            
    <connection id="logInfo" driver="log">
        level=INFO
    </connection>
                
    <!-- JOB STEPS -->
    <script connection-id="logInfo">
        STARTING JOB "$job_name"
    </script>
 
    <!-- CLEAR DB PRIOR TO IMPORT -->
    <script connection-id="graphdb">
        MATCH (n) DETACH DELETE n
    </script>
            
    <query connection-id="groovy">
        <![CDATA[
            import com.fasterxml.jackson.databind.JsonNode
            import com.fasterxml.jackson.databind.ObjectMapper
            import com.fasterxml.jackson.core.type.TypeReference
            import java.nio.file.Files
            import java.nio.file.Paths
 
            java.nio.file.Path path = java.nio.file.Paths.get("C:/path/to/data/dataset.graphson")
            String jsonData = new String(Files.readAllBytes(path), "UTF-8")
 
            ObjectMapper mapper = new ObjectMapper();
            JsonNode tree = mapper.readTree(jsonData);
            if (tree.has("vertices")) {
                tree.get("vertices").elements().forEachRemaining((entity)-> {
                    etl.globals['isEdge'] = false;
                    etl.globals['entity'] = mapper.convertValue(
                      entity, 
                      new TypeReference<Map<String, Object>>(){}
                    );
                    query.next()
                });
            }
            if (tree.has("edges")) {
                tree.get("edges").elements().forEachRemaining((entity)-> {
                    etl.globals['isEdge'] = true;
                    etl.globals['entity'] = mapper.convertValue(
                      entity, 
                      new TypeReference<Map<String, Object>>(){}
                    );
                    query.next();
                });
            }
        ]]>
 
        <script connection-id="logInfo" if="etl.globals['isEdge'] == false">
            Importing VERTEX ${etl.globals['entity']};
        </script>
        
        <script connection-id="graphdb" if="etl.globals['isEdge'] == false">
            CREATE (n:IMPORTED {
              name: '${etl.globals['entity']['name']}', 
              age: ${etl.globals['entity']['age']}, 
              uid: '${etl.globals['entity']['_id']}'
            }) RETURN n
        </script>
        
        <script connection-id="logInfo" if="etl.globals['isEdge'] == true">
            Importing EDGE ${etl.globals['entity']};
        </script>
        
        <script connection-id="graphdb" if="etl.globals['isEdge'] == true">
            MATCH (n), (m) 
            WHERE 
              n.uid='${etl.globals['entity']['_outV']}' and 
              m.uid='${etl.globals['entity']['_inV']}'
            CREATE (m)-[r:${etl.globals['entity']['_label']}]->(n)
            RETURN n,r,m
        </script>
    </query>
</etl>