THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
...
Code Block | ||||
---|---|---|---|---|
| ||||
<?xml version="1.0" encoding="UTF-8"?> <properties> <metadataFilters> <metadataFilter class="org.apache.tika.metadata.filter.ClearByMimeMetadataFilter"> <params> <!-- this will remove metadata objects for jpegs and pdfs; more seriously, this may be useful for image files or this may be useful for image files or emf or wmf depending on your use case --> <mimes> <mime>image/jpeg</mime> <mime>application/pdf</mime> </mimes> </params> </metadataFilter> </metaFilters> </properties |
...
Code Block | ||||
---|---|---|---|---|
| ||||
<?xml version="1.0" encoding="UTF-8"?> <properties> <autoDetectParserConfig> <metadataWriteFilterFactory class="org.apache.tika.metadata.writefilter.StandardWriteFilterFactory"> <params> <!-- all measurements are in UTF-16 bytes. If any values are truncated, TikaCoreProperties.TRUNCATED_METADATA is set to true in the metadata object --> <!-- the maximum size for a metadata key. --> <maxKeySize>1000</maxKeySize> <!-- max total size for a field in UTF-16 bytes. If a field has multiple values, their lengths are summed to calculate the field size. --> <maxFieldSize>10000</maxFieldSize> <!-- max total estimated byte is a sum of the key sizes and values --> <maxTotalEstimatedBytes>100000</maxTotalEstimatedBytes> <!-- limit the count of values for multi-valued fields --> <maxValuesPerField>100</maxValuesPerField> <!-- include only these fields. NOTE, however that there a several fields that are important to the parse process and these fields are always allowed in addition (see ALWAYS_SET_FIELDS and ALWAYS_ADD_FIELDS in the StandardWriteFilter --> <includeFields> <field>dc:creator</field> <field>dc:title</field> </includeFields> </params> </metadataWriteFilterFactory> </autoDetectParserConfig> </properties> |
...
Code Block | ||||
---|---|---|---|---|
| ||||
<?xml version="1.0" encoding="UTF-8"?> <properties> <autoDetectParserConfig> <params> <!-- if the incoming metadata object has a ContentLength entry and it is larger than this value, spool the file to disk; this is useful for some file formats that are more efficiently processed via a file instead of an InputStream --> <spoolToDisk>100000</spoolToDisk> <!-- the next four are parameters for the SecureContentHandler --> <!-- threshold used in zip bomb detection. This many characters must be written before the maximum compression ratio is calculated --> <outputThreshold>10000</outputThreshold> <!-- maximum compression ratio between output characters and input bytes --> <maximumCompressionRation>100</maximumCompressionRatio> <!-- maximum XML element nesting level --> <maximumDepth>100</maximumDepth> <!-- maximum embedded file depth --> <maximumPackageEntryDepth>100</maximumPackageEntryDepth> </params> </autoDetectParserConfig> </properties> |
TODO: add an example of the EmbeddedDocumentExtractorFactory
TODO: add a 5th? section for writelimiting