MapReduceIndexerTool Metadata

The MapReduceIndexerTool generates metadata fields for each input file when indexing. These fields can be used in morphline commands. These fields can also be stored in Solr, by adding definitions like the following to your Solr schema.xml file. After the MapReduce indexing process completes, the fields are searchable through Solr.
<!-- file metadata -->
<field name="file_download_url" type="string" indexed="false" stored="true" />
<field name="file_upload_url" type="string" indexed="false" stored="true" />
<field name="file_scheme" type="string" indexed="true" stored="true" />
<field name="file_host" type="string" indexed="true" stored="true" />
<field name="file_port" type="int" indexed="true" stored="true" />
<field name="file_path" type="string" indexed="true" stored="true" />
<field name="file_name" type="string" indexed="true" stored="true" />
<field name="file_length" type="tlong" indexed="true" stored="true" />
<field name="file_last_modified" type="tlong" indexed="true" stored="true" />
<field name="file_owner" type="string" indexed="true" stored="true" />
<field name="file_group" type="string" indexed="true" stored="true" />
<field name="file_permissions_user" type="string" indexed="true" stored="true" />
<field name="file_permissions_group" type="string" indexed="true" stored="true" />
<field name="file_permissions_other" type="string" indexed="true" stored="true" />
<field name="file_permissions_stickybit" type="boolean" indexed="true" stored="true" />

Example output:

"file_upload_url":"foo/test-documents/sample-statuses-20120906-141433.avro",
"file_download_url":"hdfs://host1.mycompany.com:8020/user/foo/ test-documents/sample-statuses-20120906-141433.avro",
"file_scheme":"hdfs",
"file_host":"host1.mycompany.com",
"file_port":8020,
"file_name":"sample-statuses-20120906-141433.avro",
"file_path":"/user/foo/test-documents/sample-statuses-20120906-141433.avro",
"file_last_modified":1357193447106,
"file_length":1512,
"file_owner":"foo",
"file_group":"foo",
"file_permissions_user":"rw-",
"file_permissions_group":"r--",
"file_permissions_other":"r--",
"file_permissions_stickybit":false,