de.julielab.xml.JulieXMLConstants Maven / Gradle / Ivy
Show all versions of julie-xml-tools Show documentation
package de.julielab.xml;
public abstract class JulieXMLConstants {
/**
* Constant for the name of a definition attribute in the configuration file for the {@link DataBaseConnector}. The
* value of the FOR_EACH attribute is the XPath expression which determines the XML elements for each
* of which particular fields with values within these elements should be constructed.
*
* Example:
*
* Assume we have a file with the following structure:
*
*
* <MedlineCitationSet>
* <MedlineCitation>
* <PMID>123456</PMID>
* ...more content...
* </MedlineCitation>
* ...
* <MedlineCitation>
* ...some content...
* </MedlineCitation>
* ...
* </MedlineCitationSet>
*
*
* We want to traverse each of the <MedlineCitation> elements and extract information from their inner
* elements, e.g. their PMID. For this purpose we set the FOR_EACH attribute (or the corresponding
* method parameters in the Java code) to the XPath "/MedlineCitationSet/MedlineCitation".
*
*/
public static final String FOR_EACH = "forEach";
/**
* Constant for the name of a field attribute.
*
* If set to true, the database table column corresponding to the field definition with the PRIMARY_KEY
* attribute will be part of the primary key.
*/
public static final String PRIMARY_KEY = "primaryKey";
/**
* Constant for the name of a field attribute.
*
* If set to true, the value of the database table column corresponding to the field definition with the
* RETRIEVE attribute will be retrieved by the {@link DataBaseConnector}'s query methods.
*/
public static final String RETRIEVE = "retrieve";
/**
* Constant for the name of a field attribute. The XPATH attribute is holding the XPath expression that
* determines which XML element holds the desired information for the field.
*/
public static final String XPATH = "xpath";
/**
* Constant for the name of a field. Will correspond to the name of the database-field which holds the information
* retrieved by the field Map.
*/
public static final String NAME = "name";
/**
* Constant for the name of a field attribute.
*
* The RETURN_XML_FRAGMENT attribute determines whether the complete XML code pointed to by the
* XPATH attribute should be returned (RETURN_XML_FRAGMENT set to true).
*
* Example:
*
* A field with the following attribute-value-pairs
*
*
* <field name="xml" xpath="/MedlineCitationSet/MedlineCitation" returnXMLFragment="true">
*
* returns the complete XML fragment for a MedlineCitation node, including opening and closing tags.
*/
public static final String RETURN_XML_FRAGMENT = "returnXMLFragment";
/**
* Constant for the name of a field attribute.
*
* If a field's XPath expression has several hits (e.g. an XPath pointing to an author in a Medline document will
* most probably find multiple matches), RETURN_ARRAY determines whether the extracted values should be
* returned as a String array. If set to false, multiple values will be concatenated using the String given by
* CONCAT_STRING or, if missing, the default (',').
*/
public static final String RETURN_ARRAY = "returnValuesAsArray";
public static final Object GZIP = "gzip";
/**
* Constant for the name of a field attribute.
*
* Determines the String to be used when concatenating multiple hits of an XPath. Multiple hits can also be returned
* as an array. See the RETURN_ARRAY constant for more information.
*/
public static final String CONCAT_STRING = "concatString";
/**
* Constant for the name of a field attribute.
*
* If set to true, the file name - if the XML document is read from file - is used to extract values. This is done
* on a 'match with regular expression and replace with' fashion. Therefore, using this attribute requires to
* deliver values for the attributes {@link #REGEX} and {@link #REPLACE_WITH} as well.
*/
public static final String EXTRACT_FROM_FILENAME = "extractFromFileName";
/**
* Constant for the name of a field attribute.
*
* If set to true, extracted XML text passages will be XML entity resolved. That is, special characters will be substituted by their human readable counterpart.
*
*
* Example:
*
* The text
*
The population of butterflies \& bees represents < 30% of all insects
* contains the XML entities '&' and '<' in an escaped fashion so not to collide with the XML parsing process. Switching RESOLVE_ENTITIES to true will
* result in the string
* The population of butterflies & bees represents < 30% of all insects
*
*/
public static final String RESOLVE_ENTITIES = "resolveEntities";
/**
* Constant for the name of a field attribute. Fields which have set the TIMESTAMP attribute to "true"
* will be given the time stamp of the last update for the corresponding record. This is required for delta-updates.
*/
public static final String TIMESTAMP = "timestamp";
/**
* Constant for the name of a field attribute.
*
* Used together with EXTRACT_FROM_FILENAME and REPLACE_WITH attributes. Determines the
* regular expression whose matches on the XML document file name are substituted by the value given by
* REPLACE_WITH.
*/
public static final String REGEX = "regex";
/**
* Constant for the name of a field attribute.
*
* Used together with EXTRACT_FROM_FILENAME and REGEX attributes. Determines the
* substitute expression to replace characters of the XML document filename which match the regular expression given
* by the REGEX attribute.
*/
public static final String REPLACE_WITH = "replaceWith";
/**
* Constant for the name of a field attribute.
*
* Used to set the type of a parsed value, e.g. String
*/
public static final String TYPE = "type";
/**
* Constant for the name of a field attribute>
*
* The value of this attribute will always be the value of the field that specifies the attribute.
*
*/
public static final String CONSTANT_VALUE = "constantValue";
}