Export documents from Solr core to XML format

SolrExporter.groovy

#!/usr/bin/env groovy

/**
 * Usage: ./SolrExporter.groovy query url [url]
 *
 * ./SolrExporter.groovy "id:12345" "http://your.solr.host:8983/solr/core/"
 * 
 * ./SolrExporter.groovy "id:12345" "http://old.solr.host:8983/solr/core/" "http://new.solr.host:8983/solr/core/"
 * 
 * 
 * You can also use this expoorter to reindex Solr (e.g. after incompatible schema change):
 * 
 * ./SolrExporter.groovy "*:*" "http://localhost:8983/solr/core/" "http://localhost:8983/solr/core/"
 */

import org.apache.solr.client.solrj.SolrQuery
import org.apache.solr.client.solrj.SolrServer
import org.apache.solr.client.solrj.impl.CommonsHttpSolrServer
import org.apache.solr.client.solrj.util.ClientUtils
import org.apache.solr.common.SolrDocument
import org.apache.solr.common.SolrInputDocument

@Grapes([
    @Grab(group = 'org.apache.solr', module = 'solr-solrj', version = '1.4.1'),
    @Grab(group = 'org.slf4j', module = 'slf4j-simple', version = '1.6.4')
])
class SolrDocumentExporter {

    private SolrServer sourceServer
    private SolrServer targetServer
    private SolrQuery query


    SolrDocumentExporter(q, source) {
        this(q, source, null)
    }

    SolrDocumentExporter(q, source, target) {
        query = solrQuery(q)
        sourceServer = new CommonsHttpSolrServer(source)
        if (target) targetServer = new CommonsHttpSolrServer(target)
    }

    void exportDocuments() {
        List<SolrDocument> resultDocuments = executeQuery(sourceServer, query)
        List<SolrInputDocument> inputDocuments = inputDocuments(resultDocuments)
        if (targetServer) updateDocuments(targetServer, inputDocuments)
        else printDocuments(inputDocuments)
    }

    private SolrQuery solrQuery(String q) {
        new SolrQuery(query:q, start:0, rows:Integer.MAX_VALUE)
    }

    private List<SolrDocument> executeQuery(server, query) {
        server.query(query).response.get("response")
    }

    private List<SolrInputDocument> inputDocuments(documents) {
        documents.collect { ClientUtils.toSolrInputDocument(it) }
    }

    private void updateDocuments(server, documents) {
        server.add(documents)
        server.commit()
    }

    private void printDocuments(documents) {
        documents.each { println(ClientUtils.toXML(it)) }
    }
}

target = (args.length > 2) ? args[2] : null
new SolrDocumentExporter(args[0], args[1], target).exportDocuments()

Hi!

Was trying to use this script and noticed that since it is loading the whole core into memory, it does not work for large cores - so I did couple of changes so it would use deep pagination feature in solr - https://gist.github.com/amalinovskiy/743ca7ef2548a28e68b085200f87bde8

Thanks a lot for sharing this!