ostosys.1.3.0.source-code.defaultConfiguration.xml Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of costosys Show documentation

A utility for managing documents stored in a PostgreSQL database. The documents are imported into a PostgreSQL DB as full texts with the goal to be able to retrieve the documents by their PubMedID efficiently. For more sophisticated tasks, a user configuration file can be delivered which can take control of the table schema to use, the PostgreSQL schema to use and the actual database server to connect to as well as the concrete database.

There is a newer version: 1.6.2

Show newest version

<?xml version="1.0" encoding="UTF-8"?>
<!-- no Doctype, XML Schema used instead -->
<databaseConnectorConfiguration
		xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
        xmlns="http://julielab.de"
		xsi:schemaLocation="http://julielab.de https://raw.githubusercontent.com/JULIELab/costosys/v1.0.1/src/main/resources/configuration.xsd">
	<DBSchemaInformation>
		<activePostgresSchema>public</activePostgresSchema>
		<activeTableSchema/>
		<activeDataPostgresSchema>_data</activeDataPostgresSchema>
		<dataTable>_data</dataTable>
		<tableSchemas>
			<tableSchema name="medline_2017"
				forEach="/PubmedArticleSet/PubmedArticle/MedlineCitation">
				<field name="pmid" type="text" xpath="PMID" primaryKey="true"
					retrieve="true"/>
				<field name="xml" type="bytea" xpath="." returnXMLFragment="true"
					retrieve="true" gzip="true"/>
			</tableSchema>
			<tableSchema name="medline_2016" forEach="/MedlineCitationSet/MedlineCitation">
				<field name="pmid" type="text" xpath="PMID" primaryKey="true"
					retrieve="true"/>
				<field name="xml" type="bytea" xpath="." returnXMLFragment="true"
					retrieve="true" gzip="true"/>
			</tableSchema>
			<tableSchema name="pubmed_gzip"
				forEach="/PubmedArticleSet/PubmedArticle/MedlineCitation">
				<field name="pmid" type="text" xpath="PMID" primaryKey="true"
					retrieve="true"/>
				<field name="xml" type="bytea" xpath="." returnXMLFragment="true"
					retrieve="true" gzip="true"/>
			</tableSchema>
			<tableSchema name="xmi_complete_cas" forEach=".">
				<field name="docid" type="text" primaryKey="true"  retrieve="true"/>
				<field name="xmi" type="xml" retrieve="true"/>
			</tableSchema>
			<tableSchema name="xmi_complete_cas_gzip" forEach=".">
				<field name="docid" type="text" primaryKey="true" retrieve="true"/>
				<field name="xmi" type="bytea" retrieve="true" gzip="true"/>
			</tableSchema>
			<tableSchema name="xmi_text" forEach=".">
				<field name="docid" type="text" primaryKey="true" retrieve="true"/>
				<field name="xmi" type="xml" retrieve="true"/>
				<field name="max_xmi_id" type="integer" xpath="." retrieve="true"/>
				<field name="sofa_mapping" type="text" xpath="." retrieve="true"/>
			</tableSchema>
			<tableSchema name="xmi_annotation" forEach=".">
				<field name="docid" type="xml" primaryKey="true" retrieve="false"/>
				<field name="xmi" type="xml" retrieve="true"/>
			</tableSchema>
			<tableSchema name="xmi_text_gzip" forEach=".">
				<field name="docid" type="text" primaryKey="true" retrieve="true"/>
				<field name="xmi" type="bytea" 	retrieve="true" gzip="true"/>
				<field name="max_xmi_id" type="integer" xpath="." retrieve="true"/>
				<field name="sofa_mapping" type="text" xpath="." retrieve="true"/>
			</tableSchema>
			<!-- This schema is supposed to only get the max_xmi_id field value of
				the xmi_text_gzip schema. -->
			<tableSchema name="max_id_addition" forEach=".">
				<field name="docid" type="text" primaryKey="true" retrieve="false"/>
				<field name="xmi" type="bytea" retrieve="false" gzip="true"/>
				<field name="max_xmi_id" type="integer" retrieve="true"/>
			</tableSchema>
			<tableSchema name="xmi_annotation_gzip" forEach=".">
				<field name="docid" type="text" primaryKey="true" retrieve="false"/>
				<field name="xmi" type="bytea" retrieve="true" gzip="true"/>
			</tableSchema>
			<tableSchema name="dbc_junit_gzip" forEach="/MedlineCitationSet/MedlineCitation">
				<field name="pmid" type="text" xpath="PMID" primaryKey="true"
					retrieve="true"/>
				<field name="xml" type="bytea" xpath="." returnXMLFragment="true"
					retrieve="true" gzip="true"/>
			</tableSchema>
		</tableSchemas>
	</DBSchemaInformation>
	<DBConnectionInformation>
		<activeDBConnection></activeDBConnection>
		<maxActiveDBConnections>1</maxActiveDBConnections>
		<DBConnections>
			<DBConnection url="" name="" />
		</DBConnections>
	</DBConnectionInformation>
</databaseConnectorConfiguration>