core/org.eclipse.smila.processing.pipelets.xmlprocessing/SMILA-INF/XmlSplitterPipelet.json

{
	"class" : "org.eclipse.smila.processing.pipelets.xmlprocessing.XmlSplitterPipelet",
    "parameters": [
        {
            "name": "inputType",
            "type": "string",
            "values": ["ATTACHMENT", "ATTRIBUTE"],
            "description" : "Defines whether the XML input is found in an attachment or in an attribute of the record. An input attribute is not interpreted as to contain XML content itself but rather as a file path or an URL to the XML document."
        },
        {
            "name": "outputType",
            "type": "string",
            "values": ["ATTACHMENT", "ATTRIBUTE"],
            "description" : "Defines whether the XML snippet should be stored in an attachment or in an attribute of the newly created record."
        },
        {
            "name": "inputName",
            "type": "string",
            "description" : "The name of the input attachment or the path to the input attribute containing a path to an external data source, e.g. an xml file name"
        },
        {
            "name": "outputName",
            "type": "string",
            "description" : "The name of the output attachment or the path to the output attribute (store result as literals of attribute)."
        },
        {
            "name": "beginTagName",
            "type": "string",
            "description" : "The name of the tag to start the XML snippet with."
        },
        {
            "name": "beginTagNamespace",
            "type": "string",
            "optional": true,
            "description" : "The namespace of the start tag. Namespaces are not checked, if not given (in that case any namespace matches)."
        },
        {
            "name": "endTagName",
            "type": "string",
            "optional": true,
            "description" : "The name of the tag to end the xml snippet with, defaults to the value of beginTagName."
        },
        {
            "name": "endTagNamespace",
            "type": "string",
            "optional": true,
            "description" : "The namespace of the end tag, defaults to the value of beginTagNamespace."
        },
        {
            "name": "keyTagName",
            "type": "string",
            "description" : "The name of the tag used to create a record ID."
        },
        {
            "name": "maxBufferSize",
            "type": "long",
            "optional": true,
            "description" : "The maximum size of the internal record buffer (optional, default is 20)."
        },
        {
            "name": "idSeparator",
            "type": "string",
            "optional": true,
            "description" : "The separator used to create the record IDs of the split records (optional, default is \"#\")."
        },
        {
            "name": "xmlSnippetJobName",
            "type": "string",
            "description" : "The JobManager job name to submit the split records to. It must be running when the pipelet is executed."
        }
    ],
    "description": "This pipelet splits an XML stream into multiple XML snippets. For each snippet a new record is created where the XML snippet is stored in either an attribute or attachment. The created records are not returned as a PipeletResult (this is just the same as the incoming RecordIds) but are directly sent to the ConnectivityManager and are routed once more to the queue. On each created record the attribute \"__isXmlSnippet\" is set to \"true\". Incoming records with this attribute set are not split again, but returned as the pipelet result. This way it's possible to add further processing steps that should be done on the split records to the same pipeline that does the splitting."
}