Making Solr import XML files

data-config.xml

<dataConfig>
    <dataSource name="fds" encoding="ISO-8859-1" type="FileDataSource"/>
    <document>

        <entity name="files"
                dataSource="null"
                rootEntity="false"
                processor="FileListEntityProcessor"
                baseDir="/tmp/provision/import"
                fileName=".*\.xml"
                onError="abort"
                recursive="true">
            <entity name="file"
                    processor="XPathEntityProcessor"
                    pk="title"
                    dataSource="files"
                    stream="true"
                    forEach="/SVVZ/Modules/Module"
                    onError="abort"
                    transformer="RegexTransformer"
                    url="${files.fileAbsolutePath}">
                <field column="title" xpath="/SVVZ/Modules/Module/CAMO_TITLEGER" />
            </entity>
        </entity>
    </document>
</dataConfig>

result.json

{
  "responseHeader": {
    "status": 0,
    "QTime": 63
  },
  "initArgs": [
    "defaults",
    [
      "config",
      "/usr/local/src/solr_core/test/conf/data-config.xml"
    ]
  ],
  "command": "full-import",
  "mode": "debug",
  "documents": [],
  "verbose-output": [
    "entity:files",
    [
      null,
      "----------- row #1-------------",
      "fileSize",
      403,
      "fileLastModified",
      "2014-02-18T11:06:09Z",
      "fileAbsolutePath",
      "/tmp/provision/import/sample.xml",
      "fileDir",
      "/tmp/provision/import",
      "file",
      "sample.xml",
      null,
      "---------------------------------------------",
      "entity:file",
      [
        "query",
        "/tmp/provision/import/sample.xml",
        "time-taken",
        "0:0:0.1",
        null,
        "----------- row #1-------------",
        "titel",
        [
          "I want this to be my field value"
        ],
        "$forEach",
        "/SVVZ/Modules/Module",
        null,
        "---------------------------------------------",
        "transformer:RegexTransformer",
        [
          null,
          "---------------------------------------------",
          "titel",
          [
            "I want this to be my field value"
          ],
          "$forEach",
          "/SVVZ/Modules/Module",
          null,
          "---------------------------------------------"
        ],
        null,
        "----------- row #2-------------",
        "titel",
        [
          "A second title"
        ],
        "$forEach",
        "/SVVZ/Modules/Module",
        null,
        "---------------------------------------------",
        "transformer:RegexTransformer",
        [
          null,
          "---------------------------------------------",
          "titel",
          [
            "A second title"
          ],
          "$forEach",
          "/SVVZ/Modules/Module",
          null,
          "---------------------------------------------"
        ]
      ]
    ]
  ],
  "status": "idle",
  "importResponse": "",
  "statusMessages": {
    "Total Requests made to DataSource": "0",
    "Total Rows Fetched": "3",
    "Total Documents Skipped": "0",
    "Full Dump Started": "2014-02-18 11:15:47",
    "": "Indexing completed. Added/Updated: 0 documents. Deleted 0 documents.",
    "Committed": "2014-02-18 11:15:47",
    "Total Documents Processed": "0",
    "Time taken": "0:0:0.49"
  },
  "WARNING": "This response format is experimental.  It is likely to change in the future."
}

sample.xml

<?xml version="1.0" encoding="ISO-8859-1"?>
<?xml-stylesheet type="text/xsl" href="http://localhost/svvz_default.xsl" ?>
<SVVZ>
    <SVVZTerm>WS 13/14</SVVZTerm>
    <Modules>
        <Module>
            <CAMO_TITLEGER>I want this to be my field value</CAMO_TITLEGER>
        </Module>
        <Module>
            <CAMO_TITLEGER>A second title</CAMO_TITLEGER>
        </Module>
    </Modules>
</SVVZ>

schema.xml

<?xml version="1.0" ?>
<schema name="simple" version="1.1">

        <types>
                <fieldtype name="string" class="solr.StrField" />
                <fieldType name="long" class="solr.TrieLongField" />
                <fieldtype name='text' class='solr.TextField'>
                      <analyzer>
                          <tokenizer class='solr.WhitespaceTokenizerFactory' />
                          <filter class='solr.LowerCaseFilterFactory' />
                      </analyzer>
                </fieldtype>
        </types>

        <fields>
           <dynamicField name='*' type='string' multiValued='true' indexed='true' stored='true' />
           <copyField source='*' dest='fulltext' />
           <field name='fullText' type='string' multiValued='true' />
        </fields>

    <defaultSearchField>fullText</defaultSearchField>
    <solrQueryParser defaultOperator='OR' />

</schema>

solrconfig.xml

<?xml version="1.0" encoding="UTF-8" ?>
<config>

        <luceneMatchVersion>4.6</luceneMatchVersion>

        <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />

        <requestHandler name="/update" class="solr.UpdateRequestHandler" />

        <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />

        <admin>
                <defaultQuery>*:*</defaultQuery>
        </admin>
        <lib dir="/usr/local/src/solr-4.6.1/dist/" regex="solr-dataimporthandler-.*\.jar" />

        <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
           <lst name="defaults">
               <str name="config">/usr/local/src/dbm_solr_core/dbm/conf/data-config.xml</str>
           </lst>
        </requestHandler>

</config>

The updated files appear to work nicely. Thanks for all the great help!

I tried working this code but i keep getting the error "missing content stream"!! Can you please help if you have any idea? I am using Sol 6.5.0