You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by jo...@apache.org on 2011/09/27 11:01:02 UTC
svn commit: r1176285 -
/incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml
Author: joern
Date: Tue Sep 27 09:01:01 2011
New Revision: 1176285
URL: http://svn.apache.org/viewvc?rev=1176285&view=rev
Log:
OPENNLP-261 Adapted stump collection reader xml to work with CScollectionReader class.
Modified:
incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml
Modified: incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml
URL: http://svn.apache.org/viewvc/incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml?rev=1176285&r1=1176284&r2=1176285&view=diff
==============================================================================
--- incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml (original)
+++ incubator/opennlp/sandbox/corpus-server-connector/desc/CSQueueCollectionReader.xml Tue Sep 27 09:01:01 2011
@@ -21,79 +21,47 @@
***************************************************************
-->
-<!-- A simple collection reader that reads text files from a directory in the
- filesystem. The Java class for this collection reader is in uima_core.jar. -->
-
<collectionReaderDescription xmlns="http://uima.apache.org/resourceSpecifier">
<frameworkImplementation>org.apache.uima.java</frameworkImplementation>
- <implementationName>org.apache.uima.examples.cpe.FileSystemCollectionReader</implementationName>
+ <implementationName>org.apache.opennlp.corpus_server.connector.CSCollectionReader</implementationName>
<processingResourceMetaData>
- <name>File System Collection Reader</name>
- <description>Reads files from the filesystem. This CollectionReader may be used
- with or without a CAS Initializer. If a CAS Initializer is supplied, it will
- be passed an InputStream to the file and must populate the CAS from that
- InputStream. If no CAS Initializer is supplied, this CollectionReader will
- read the file itself and set treat the entire contents of the file as the
- document to be inserted into the CAS.</description>
+ <name>Corpus Server Collection Reader</name>
+ <description>Reads CASes from a Corpus Server Queue.</description>
<version>1.0</version>
<vendor>The Apache Software Foundation</vendor>
<configurationParameters>
<configurationParameter>
- <name>InputDirectory</name>
+ <name>CorpusAddress</name>
<description>Directory containing input files</description>
<type>String</type>
<multiValued>false</multiValued>
<mandatory>true</mandatory>
</configurationParameter>
<configurationParameter>
- <name>Encoding</name>
- <description>Character encoding for the documents. If not specified,
- the default system encoding will be used. Note that this parameter
- only applies if there is no CAS Initializer provided; otherwise,
- it is the CAS Initializer's responsibility to deal with character
- encoding issues. </description>
- <type>String</type>
- <multiValued>false</multiValued>
- <mandatory>false</mandatory>
- </configurationParameter>
- <configurationParameter>
- <name>Language</name>
- <description>ISO language code for the documents</description>
+ <name>QueueAddress</name>
+ <description>Directory containing input files</description>
<type>String</type>
<multiValued>false</multiValued>
- <mandatory>false</mandatory>
- </configurationParameter>
- <configurationParameter>
- <name>BrowseSubdirectories</name>
- <description>True means include files of subdirectories, recursively, of the input directory.</description>
- <type>Boolean</type>
- <multiValued>false</multiValued>
- <mandatory>false</mandatory>
+ <mandatory>true</mandatory>
</configurationParameter>
</configurationParameters>
<configurationParameterSettings>
<nameValuePair>
- <name>InputDirectory</name>
+ <name>CorpusAddress</name>
<value>
<string>C:/Program Files/apache-uima/examples/data</string>
</value>
</nameValuePair>
<nameValuePair>
- <name>BrowseSubdirectories</name>
+ <name>QueueAddress</name>
<value>
- <boolean>false</boolean>
+ <string>false</string>
</value>
</nameValuePair>
- <nameValuePair>
- <name>Language</name>
- <value>
- <string>en</string>
- </value>
- </nameValuePair>
</configurationParameterSettings>
<!-- Type System of CASes returned by this Collection Reader -->
-
+ <!-- TODO: Can TS be imported via http?! Otherwise it must be downloaded by the user! -->
<typeSystemDescription>
<imports>
<import name="org.apache.uima.examples.SourceDocumentInformation"/>
@@ -103,9 +71,7 @@
<capabilities>
<capability>
<inputs/>
- <outputs>
- <type allAnnotatorFeatures="true">org.apache.uima.examples.SourceDocumentInformation</type>
- </outputs>
+ <outputs/>
</capability>
</capabilities>
<operationalProperties>