You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ctakes.apache.org by ch...@apache.org on 2013/06/14 20:43:36 UTC
svn commit: r1493198 - in /ctakes/trunk:
ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/
ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/
ctakes-core/desc/analysis_engine/ ctakes-core/src/main/j...
Author: chenpei
Date: Fri Jun 14 18:43:35 2013
New Revision: 1493198
URL: http://svn.apache.org/r1493198
Log:
CTAKES-209, CTAKES-210 - With the new SentenceDetector working with OpenNLP 1.5, we can simplify how models are loaded now.
- Deleted the SuffixMaxentModelResourceImpl and related classes. It's just a string to the model file now.
- Deleted duplicated SentenceDectector.xml descriptors that were scattered.
- Added util in FileLocator.java to read in resources from InputStream instead of physical path File. Updated the SD to use this mechanism.
Added:
ctakes/trunk/ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/sd-med-model.zip (with props)
Removed:
ctakes/trunk/ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/sd-med-model.bin
ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/MaxentModelResource.java
ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/SuffixMaxentModelResourceImpl.java
ctakes/trunk/ctakes-ne-contexts/desc/test/SentenceDetectorAnnotator.xml
ctakes/trunk/ctakes-pos-tagger/desc/SentenceDetectorAnnotator.xml
ctakes/trunk/ctakes-pos-tagger/desc/SimpleSegmentAnnotator.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/SentenceDetectorAnnotator.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/SimpleSegmentAnnotator.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/TokenizerAnnotator.xml
ctakes/trunk/ctakes-smoking-status/desc/analysis_engine/SentenceDetectorAnnotator.xml
Modified:
ctakes/trunk/ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/CommandLineParserUtil.java
ctakes/trunk/ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml
ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/SentenceDetector.java
ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ci/HyphenTextModifierImpl.java
ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/FileLocator.java
ctakes/trunk/ctakes-core/src/test/java/org/apache/ctakes/core/ci/HyphenTextModifierImplTests.java
ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserPlaintextAggregate.xml
ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPSRLPlaintextAggregate.xml
ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPDependencyParserAE.java
ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPSemanticRoleLabelerAE.java
ctakes/trunk/ctakes-ne-contexts/desc/test/SegmentTokenSentenceAggregate.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate2.xml
ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate3.xml
ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/eval/Evaluation_ImplBase.java
ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventAndTimeExtractionPipeline.java
ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/utils/CheckKnowtatorAnnotations.java
Modified: ctakes/trunk/ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/CommandLineParserUtil.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/CommandLineParserUtil.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/CommandLineParserUtil.java (original)
+++ ctakes/trunk/ctakes-constituency-parser/src/main/java/org/apache/ctakes/constituency/parser/util/CommandLineParserUtil.java Fri Jun 14 18:43:35 2013
@@ -25,7 +25,6 @@ import org.apache.ctakes.constituency.pa
import org.apache.ctakes.core.ae.SentenceDetector;
import org.apache.ctakes.core.ae.SimpleSegmentAnnotator;
import org.apache.ctakes.core.ae.TokenizerAnnotatorPTB;
-import org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl;
import org.apache.ctakes.typesystem.type.syntax.TopTreebankNode;
import org.apache.uima.UIMAException;
import org.apache.uima.analysis_engine.AnalysisEngine;
@@ -52,11 +51,10 @@ public class CommandLineParserUtil {
// AnalysisEngine ae = AnalysisEngineFactory.createAnalysisEngineFromPath("desc/analysis_engine/AggregateParsingProcessor.xml");
AggregateBuilder builder = new AggregateBuilder();
builder.add(AnalysisEngineFactory.createPrimitiveDescription(SimpleSegmentAnnotator.class));
- builder.add(AnalysisEngineFactory.createPrimitiveDescription(SentenceDetector.class,
- "MaxentModel",
- ExternalResourceFactory.createExternalResourceDescription(
- SuffixMaxentModelResourceImpl.class,
- SentenceDetector.class.getResource("../sentdetect/sdmed.mod"))));
+ builder.add(AnalysisEngineFactory.createPrimitiveDescription(
+ SentenceDetector.class,
+ SentenceDetector.SD_MODEL_FILE_PARAM,
+ "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
builder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
builder.add(AnalysisEngineFactory.createPrimitiveDescription(ConstituencyParser.class));
Added: ctakes/trunk/ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/sd-med-model.zip
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/sd-med-model.zip?rev=1493198&view=auto
==============================================================================
Binary file - no diff available.
Propchange: ctakes/trunk/ctakes-core-res/src/main/resources/org/apache/ctakes/core/sentdetect/sd-med-model.zip
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
Modified: ctakes/trunk/ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml (original)
+++ ctakes/trunk/ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml Fri Jun 14 18:43:35 2013
@@ -35,6 +35,13 @@
<multiValued>true</multiValued>
<mandatory>false</mandatory>
</configurationParameter>
+<configurationParameter>
+<name>SentenceModelFile</name>
+<description>The file that contains the MaxEnt model used by the Sentence Dectector</description>
+<type>String</type>
+<multiValued>false</multiValued>
+<mandatory>true</mandatory>
+</configurationParameter>
</configurationParameters>
<configurationParameterSettings>
<nameValuePair>
@@ -43,6 +50,12 @@
<array/>
</value>
</nameValuePair>
+<nameValuePair>
+<name>SentenceModelFile</name>
+<value>
+<string>org/apache/ctakes/core/sentdetect/sd-med-model.zip</string>
+</value>
+</nameValuePair>
</configurationParameterSettings>
<typeSystemDescription/>
<typePriorities/>
@@ -64,30 +77,4 @@
<outputsNewCASes>false</outputsNewCASes>
</operationalProperties>
</analysisEngineMetaData>
-<externalResourceDependencies>
-<externalResourceDependency>
-<key>MaxentModel</key>
-<description></description>
-<interfaceName>org.apache.ctakes.core.resource.MaxentModelResource</interfaceName>
-<optional>false</optional>
-</externalResourceDependency>
-</externalResourceDependencies>
-<resourceManagerConfiguration>
-<externalResources>
-<externalResource>
-<name>MaxentModelFile</name>
-<description></description>
-<fileResourceSpecifier>
-<fileUrl>file:org/apache/ctakes/core/sentdetect/sdmed.mod</fileUrl>
-</fileResourceSpecifier>
-<implementationName>org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl</implementationName>
-</externalResource>
-</externalResources>
-<externalResourceBindings>
-<externalResourceBinding>
-<key>MaxentModel</key>
-<resourceName>MaxentModelFile</resourceName>
-</externalResourceBinding>
-</externalResourceBindings>
-</resourceManagerConfiguration>
</taeDescription>
Modified: ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/SentenceDetector.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/SentenceDetector.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/SentenceDetector.java (original)
+++ ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ae/SentenceDetector.java Fri Jun 14 18:43:35 2013
@@ -20,15 +20,22 @@ package org.apache.ctakes.core.ae;
import java.io.File;
import java.io.IOException;
+import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.Set;
-import opennlp.maxent.GISModel;
-import opennlp.maxent.io.SuffixSensitiveGISModelWriter;
import opennlp.tools.sentdetect.DefaultSDContextGenerator;
-import opennlp.tools.sentdetect.SentenceDetectorME;
+import opennlp.tools.sentdetect.SentenceModel;
+import opennlp.tools.util.InvalidFormatException;
+import org.apache.ctakes.core.resource.FileLocator;
+import org.apache.ctakes.core.sentence.EndOfSentenceScannerImpl;
+import org.apache.ctakes.core.sentence.SentenceDetectorCtakes;
+import org.apache.ctakes.core.sentence.SentenceSpan;
+import org.apache.ctakes.core.util.ParamUtil;
+import org.apache.ctakes.typesystem.type.textspan.Segment;
+import org.apache.ctakes.typesystem.type.textspan.Sentence;
import org.apache.log4j.Logger;
import org.apache.uima.UimaContext;
import org.apache.uima.analysis_component.JCasAnnotator_ImplBase;
@@ -39,15 +46,6 @@ import org.apache.uima.jcas.JFSIndexRepo
import org.apache.uima.resource.ResourceAccessException;
import org.apache.uima.resource.ResourceInitializationException;
-
-import org.apache.ctakes.core.resource.MaxentModelResource;
-import org.apache.ctakes.core.sentence.EndOfSentenceScannerImpl;
-import org.apache.ctakes.core.sentence.SentenceDetectorCtakes;
-import org.apache.ctakes.core.sentence.SentenceSpan;
-import org.apache.ctakes.core.util.ParamUtil;
-import org.apache.ctakes.typesystem.type.textspan.Segment;
-import org.apache.ctakes.typesystem.type.textspan.Sentence;
-
/**
* Wraps the OpenNLP sentence detector in a UIMA annotator
*
@@ -64,7 +62,9 @@ public class SentenceDetector extends JC
// LOG4J logger based on class name
private Logger logger = Logger.getLogger(getClass().getName());
- private final String MAXENT_MODEL_RESRC_KEY = "MaxentModel";
+ public static final String SD_MODEL_FILE_PARAM = "SentenceModelFile";
+
+ private opennlp.tools.sentdetect.SentenceModel sdmodel;
private UimaContext context;
@@ -84,7 +84,7 @@ public class SentenceDetector extends JC
context = aContext;
try {
configInit();
- } catch (ResourceAccessException ace) {
+ } catch (Exception ace) {
throw new ResourceInitializationException(ace);
}
}
@@ -93,29 +93,26 @@ public class SentenceDetector extends JC
* Reads configuration parameters.
*
* @throws ResourceAccessException
+ * @throws IOException
+ * @throws InvalidFormatException
*/
- private void configInit() throws ResourceAccessException {
- MaxentModelResource mmResrc = (MaxentModelResource) context
- .getResourceObject(MAXENT_MODEL_RESRC_KEY);
- // <code>SuffixMaxentModelResourceImpl</code> will log the name of the
- // resource at load() time
- // logger.info("Sentence detector resource: " +
- // mmResrc.getModel().toString());
-
- if (mmResrc == null) {
- // TODO Consider throwing an exception here
- logger.warn("Unable to locate resource with key="
- + MAXENT_MODEL_RESRC_KEY + ".");
- } else {
+ private void configInit() throws ResourceAccessException, InvalidFormatException, IOException {
+
+ String sdModelPath = (String) context
+ .getConfigParameterValue(SD_MODEL_FILE_PARAM);
+ InputStream is = FileLocator.getAsStream(sdModelPath);
+ logger.info("POS tagger model file: " + sdModelPath);
+ sdmodel = new SentenceModel(is);
+ is.close();
EndOfSentenceScannerImpl eoss = new EndOfSentenceScannerImpl();
char[] eosc = eoss.getEndOfSentenceCharacters();
// SentenceDContextGenerator cg = new SentenceDContextGenerator();
DefaultSDContextGenerator cg = new DefaultSDContextGenerator(eosc);
- sentenceDetector = new SentenceDetectorCtakes(mmResrc.getModel(), cg, eoss);
- }
+ sentenceDetector = new SentenceDetectorCtakes(
+ sdmodel.getMaxentModel(), cg, eoss);
- skipSegmentsSet = ParamUtil.getStringParameterValuesSet(
- PARAM_SEGMENTS_TO_SKIP, context);
+ skipSegmentsSet = ParamUtil.getStringParameterValuesSet(
+ PARAM_SEGMENTS_TO_SKIP, context);
}
/**
@@ -172,7 +169,9 @@ public class SentenceDetector extends JC
// The sentence detector returns the offsets of the sentence-endings it
// detects
// within the string
- int[] sentenceBreaks = sentenceDetector.sentPosDetect(text.substring(b, e)); // OpenNLP tools 1.5 returns Spans rather than offsets that 1.4 did
+ int[] sentenceBreaks = sentenceDetector.sentPosDetect(text.substring(b,
+ e)); // OpenNLP tools 1.5 returns Spans rather than offsets that
+ // 1.4 did
int numSentences = sentenceBreaks.length;
// There might be text after the last sentence-ending found by detector,
// so +1
@@ -184,7 +183,9 @@ public class SentenceDetector extends JC
// Will trim leading or trailing whitespace when check for end-of-line
// characters
for (int i = 0; i < numSentences; i++) {
- sentEnd = sentenceBreaks[i] + b; // OpenNLP tools 1.5 returns Spans rather than offsets that 1.4 did
+ sentEnd = sentenceBreaks[i] + b; // OpenNLP tools 1.5 returns Spans
+ // rather than offsets that 1.4
+ // did
String coveredText = text.substring(sentStart, sentEnd);
potentialSentSpans[i] = new SentenceSpan(sentStart, sentEnd,
coveredText);
@@ -287,16 +288,17 @@ public class SentenceDetector extends JC
logger.info("Training new model from " + inFile.getAbsolutePath());
logger.info("Using " + numEosc + " end of sentence characters.");
-
- logger.error("----------------------------------------------------------------------------------");
- logger.error("Need to update yet for OpenNLP changes "); // TODO
- logger.error("Commented out code that no longer compiles due to OpenNLP API incompatible changes"); // TODO
- logger.error("----------------------------------------------------------------------------------");
- //GISModel mod = SentenceDetectorME.train(inFile, iters, cut, scanner);
- //SuffixSensitiveGISModelWriter ssgmw = new SuffixSensitiveGISModelWriter(
- // mod, outFile);
- //logger.info("Saving the model as: " + outFile.getAbsolutePath());
- //ssgmw.persist();
+
+ logger.error("----------------------------------------------------------------------------------");
+ logger.error("Need to update yet for OpenNLP changes "); // TODO
+ logger.error("Commented out code that no longer compiles due to OpenNLP API incompatible changes"); // TODO
+ logger.error("----------------------------------------------------------------------------------");
+ // GISModel mod = SentenceDetectorME.train(inFile, iters, cut, scanner);
+ // SuffixSensitiveGISModelWriter ssgmw = new
+ // SuffixSensitiveGISModelWriter(
+ // mod, outFile);
+ // logger.info("Saving the model as: " + outFile.getAbsolutePath());
+ // ssgmw.persist();
}
Modified: ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ci/HyphenTextModifierImpl.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ci/HyphenTextModifierImpl.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ci/HyphenTextModifierImpl.java (original)
+++ ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/ci/HyphenTextModifierImpl.java Fri Jun 14 18:43:35 2013
@@ -29,6 +29,8 @@ import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
@@ -49,6 +51,38 @@ public class HyphenTextModifierImpl impl
private int iv_windowSize = 3; // default lookahead window
private Tokenizer iv_tokenizer = null;
+ /*
+ * DECPRECATED: Uses InputSteam instead
+ */
+ public HyphenTextModifierImpl(String hyphenfilename, int windowSize) {
+ iv_windowSize = windowSize;
+ iv_tokenizer = new Tokenizer();
+ BufferedReader br;
+ try {
+ br = new BufferedReader(new FileReader(new File(hyphenfilename)));
+
+ String line = "";
+
+ iv_shouldbeHyphenMap = new HashMap<String, Integer>();
+ while ((line = br.readLine()) != null) {
+ String[] toks = line.split("\\|");
+ String[] unh = toks[0].split("\\-");
+ String shouldbehyphen = "";
+ for (int i = 0; i < unh.length; i++) {
+ shouldbehyphen += " " + unh[i];
+ }
+ shouldbehyphen = shouldbehyphen.trim().toLowerCase();
+ iv_shouldbeHyphenMap.put(shouldbehyphen, new Integer(1));
+ }
+ } catch (FileNotFoundException e) {
+ System.err.println("Cannot find the hyphenation file:" + hyphenfilename);
+ e.printStackTrace();
+ } catch (IOException e) {
+ System.err.println("IOException accessing the hyphenation file:" + hyphenfilename);
+ e.printStackTrace();
+ }
+
+ }
/**
* Default constructor takes a name of the file containing hyphenated
* phrases, with their frequency.
@@ -58,13 +92,12 @@ public class HyphenTextModifierImpl impl
* The file is delimited with "|" and has two fields:<br>
* hyphen-term|frequency
*/
- public HyphenTextModifierImpl(String hyphenfilename, int windowSize) {
+ public HyphenTextModifierImpl(InputStream hyphenfilename, int windowSize) {
iv_windowSize = windowSize;
iv_tokenizer = new Tokenizer();
BufferedReader br;
try {
- br = new BufferedReader(new FileReader(new File(hyphenfilename)));
-
+ br = new BufferedReader(new InputStreamReader(hyphenfilename));
String line = "";
iv_shouldbeHyphenMap = new HashMap<String, Integer>();
@@ -86,7 +119,7 @@ public class HyphenTextModifierImpl impl
e.printStackTrace();
}
- }
+ }
/**
* Filters out unwanted tokens - newlines.
Modified: ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/FileLocator.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/FileLocator.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/FileLocator.java (original)
+++ ctakes/trunk/ctakes-core/src/main/java/org/apache/ctakes/core/resource/FileLocator.java Fri Jun 14 18:43:35 2013
@@ -19,7 +19,9 @@
package org.apache.ctakes.core.resource;
import java.io.File;
+import java.io.FileInputStream;
import java.io.FileNotFoundException;
+import java.io.InputStream;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URL;
@@ -31,6 +33,25 @@ import java.net.URL;
*/
public class FileLocator
{
+ public static InputStream getAsStream(String location) throws FileNotFoundException
+ {
+ try
+ {
+ //Get from classpath
+ return FileLocator.class.getClassLoader().getResourceAsStream(location);
+ }
+ catch (Exception e)
+ {
+ //Try to get from filestream
+ File f = new File(location);
+ FileInputStream fs = new FileInputStream(f);
+ return fs;
+ }
+ }
+
+ /**
+ * @deprecated As of release 3.1, replaced by {@link #getAsStream()}
+ */
public static File locateFile(String location)
throws FileNotFoundException
{
Modified: ctakes/trunk/ctakes-core/src/test/java/org/apache/ctakes/core/ci/HyphenTextModifierImplTests.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-core/src/test/java/org/apache/ctakes/core/ci/HyphenTextModifierImplTests.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-core/src/test/java/org/apache/ctakes/core/ci/HyphenTextModifierImplTests.java (original)
+++ ctakes/trunk/ctakes-core/src/test/java/org/apache/ctakes/core/ci/HyphenTextModifierImplTests.java Fri Jun 14 18:43:35 2013
@@ -23,12 +23,14 @@ package org.apache.ctakes.core.ci;
import static org.junit.Assert.assertArrayEquals;
+import java.io.InputStream;
import java.net.URISyntaxException;
import java.util.ArrayList;
import org.junit.Test;
import org.apache.ctakes.core.ci.HyphenTextModifierImpl;
+import org.apache.ctakes.core.resource.FileLocator;
/**
* @author Mayo Clinic
@@ -92,10 +94,10 @@ public class HyphenTextModifierImplTests
System.out.println(s);
}
- String filename = null;
+ InputStream filename = null;
try {
- filename = this.getClass().getClassLoader().getResource("org/apache/ctakes/core/tokenizer/hyphenated.txt").toURI().getRawPath();
- } catch (URISyntaxException e) {
+ filename = FileLocator.getAsStream("org/apache/ctakes/core/tokenizer/hyphenated.txt");
+ } catch (Exception e) {
e.printStackTrace();
}
HyphenTextModifierImpl tm = new HyphenTextModifierImpl(filename, 7);
Modified: ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserPlaintextAggregate.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserPlaintextAggregate.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserPlaintextAggregate.xml (original)
+++ ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserPlaintextAggregate.xml Fri Jun 14 18:43:35 2013
@@ -405,6 +405,13 @@
<multiValued>true</multiValued>
<mandatory>false</mandatory>
</configurationParameter>
+ <configurationParameter>
+ <name>SentenceModelFile</name>
+ <description>The file that contains the MaxEnt model used by the Sentence Dectector</description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
</configurationParameters>
<configurationParameterSettings>
<nameValuePair>
@@ -413,6 +420,12 @@
<array/>
</value>
</nameValuePair>
+ <nameValuePair>
+ <name>SentenceModelFile</name>
+ <value>
+ <string>org/apache/ctakes/core/sentdetect/sd-med-model.zip</string>
+ </value>
+ </nameValuePair>
</configurationParameterSettings>
<typeSystemDescription/>
<typePriorities/>
@@ -434,32 +447,6 @@
<outputsNewCASes>false</outputsNewCASes>
</operationalProperties>
</analysisEngineMetaData>
- <externalResourceDependencies>
- <externalResourceDependency>
- <key>MaxentModel</key>
- <description/>
- <interfaceName>org.apache.ctakes.core.resource.MaxentModelResource</interfaceName>
- <optional>false</optional>
- </externalResourceDependency>
- </externalResourceDependencies>
- <resourceManagerConfiguration>
- <externalResources>
- <externalResource>
- <name>MaxentModelFile</name>
- <description/>
- <fileResourceSpecifier>
- <fileUrl>file:org/apache/ctakes/core/sentdetect/sdmed.mod</fileUrl>
- </fileResourceSpecifier>
- <implementationName>org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl</implementationName>
- </externalResource>
- </externalResources>
- <externalResourceBindings>
- <externalResourceBinding>
- <key>MaxentModel</key>
- <resourceName>MaxentModelFile</resourceName>
- </externalResourceBinding>
- </externalResourceBindings>
- </resourceManagerConfiguration>
</taeDescription>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SimpleSegmentAnnotator">
Modified: ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPSRLPlaintextAggregate.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPSRLPlaintextAggregate.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPSRLPlaintextAggregate.xml (original)
+++ ctakes/trunk/ctakes-dependency-parser/desc/analysis_engine/ClearNLPSRLPlaintextAggregate.xml Fri Jun 14 18:43:35 2013
@@ -466,6 +466,13 @@
<multiValued>true</multiValued>
<mandatory>false</mandatory>
</configurationParameter>
+ <configurationParameter>
+ <name>SentenceModelFile</name>
+ <description>The file that contains the MaxEnt model used by the Sentence Dectector</description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
</configurationParameters>
<configurationParameterSettings>
<nameValuePair>
@@ -474,6 +481,12 @@
<array/>
</value>
</nameValuePair>
+ <nameValuePair>
+ <name>SentenceModelFile</name>
+ <value>
+ <string>org/apache/ctakes/core/sentdetect/sd-med-model.zip</string>
+ </value>
+ </nameValuePair>
</configurationParameterSettings>
<typeSystemDescription/>
<typePriorities/>
@@ -495,32 +508,6 @@
<outputsNewCASes>false</outputsNewCASes>
</operationalProperties>
</analysisEngineMetaData>
- <externalResourceDependencies>
- <externalResourceDependency>
- <key>MaxentModel</key>
- <description/>
- <interfaceName>org.apache.ctakes.core.resource.MaxentModelResource</interfaceName>
- <optional>false</optional>
- </externalResourceDependency>
- </externalResourceDependencies>
- <resourceManagerConfiguration>
- <externalResources>
- <externalResource>
- <name>MaxentModelFile</name>
- <description/>
- <fileResourceSpecifier>
- <fileUrl>file:org/apache/ctakes/core/sentdetect/sdmed.mod</fileUrl>
- </fileResourceSpecifier>
- <implementationName>org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl</implementationName>
- </externalResource>
- </externalResources>
- <externalResourceBindings>
- <externalResourceBinding>
- <key>MaxentModel</key>
- <resourceName>MaxentModelFile</resourceName>
- </externalResourceBinding>
- </externalResourceBindings>
- </resourceManagerConfiguration>
</taeDescription>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SimpleSegmentAnnotator">
Modified: ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPDependencyParserAE.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPDependencyParserAE.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPDependencyParserAE.java (original)
+++ ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPDependencyParserAE.java Fri Jun 14 18:43:35 2013
@@ -21,6 +21,7 @@ package org.apache.ctakes.dependency.par
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
+import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URI;
import java.net.URL;
@@ -28,6 +29,7 @@ import java.util.ArrayList;
import java.util.List;
import java.util.zip.ZipInputStream;
+import org.apache.ctakes.core.resource.FileLocator;
import org.apache.ctakes.dependency.parser.util.ClearDependencyUtility;
import org.apache.ctakes.typesystem.type.syntax.BaseToken;
import org.apache.ctakes.typesystem.type.syntax.ConllDependencyNode;
@@ -125,17 +127,17 @@ public class ClearNLPDependencyParserAE
// Note: If lemmatizer data file is not specified, then use lemmas from the BaseToken normalizedToken field.
// Initialize lemmatizer
- URL lemmatizerModelURL = (this.lemmatizerDataFile == null)
- ? this.getClass().getClassLoader().getResource(ENG_LEMMATIZER_DATA_FILE).toURI().toURL()
- : this.lemmatizerDataFile.toURL();
+ InputStream lemmatizerModel = (this.lemmatizerDataFile == null)
+ ? FileLocator.getAsStream(ENG_LEMMATIZER_DATA_FILE)
+ : FileLocator.getAsStream(this.lemmatizerDataFile.getPath());
- this.lemmatizer = EngineGetter.getMPAnalyzer(language, lemmatizerModelURL.openStream());
+ this.lemmatizer = EngineGetter.getMPAnalyzer(language, lemmatizerModel);
}
- URL parserModelURL = (this.parserModelUri == null)
- ? this.getClass().getClassLoader().getResource(DEFAULT_MODEL_FILE_NAME).toURI().toURL()
- : this.parserModelUri.toURL();
+ InputStream parserModel = (this.parserModelUri == null)
+ ? FileLocator.getAsStream(DEFAULT_MODEL_FILE_NAME)
+ : FileLocator.getAsStream(this.parserModelUri.getPath());
- this.parser = EngineGetter.getComponent(parserModelURL.openStream(), this.language, NLPLib.MODE_DEP);
+ this.parser = EngineGetter.getComponent(parserModel, this.language, NLPLib.MODE_DEP);
} catch (Exception e) {
throw new ResourceInitializationException(e);
Modified: ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPSemanticRoleLabelerAE.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPSemanticRoleLabelerAE.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPSemanticRoleLabelerAE.java (original)
+++ ctakes/trunk/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/ae/ClearNLPSemanticRoleLabelerAE.java Fri Jun 14 18:43:35 2013
@@ -18,6 +18,7 @@
*/
package org.apache.ctakes.dependency.parser.ae;
+import java.io.InputStream;
import java.net.URI;
import java.net.URL;
import java.util.ArrayList;
@@ -25,6 +26,7 @@ import java.util.HashMap;
import java.util.List;
import java.util.Map;
+import org.apache.ctakes.core.resource.FileLocator;
import org.apache.ctakes.core.util.ListFactory;
import org.apache.ctakes.typesystem.type.syntax.BaseToken;
import org.apache.ctakes.typesystem.type.syntax.ConllDependencyNode;
@@ -123,20 +125,20 @@ final String language = AbstractReader.L
try {
- URL srlPredURL = (this.srlPredUri == null)
- ? this.getClass().getClassLoader().getResource(DEFAULT_PRED_MODEL_FILE_NAME).toURI().toURL()
- : this.srlPredUri.toURL();
- this.identifier = EngineGetter.getComponent(srlPredURL.openStream(), this.language, NLPLib.MODE_PRED);
+ InputStream srlPred = (this.srlPredUri == null)
+ ? FileLocator.getAsStream(DEFAULT_PRED_MODEL_FILE_NAME)
+ : FileLocator.getAsStream(this.srlPredUri.getPath());
+ this.identifier = EngineGetter.getComponent(srlPred, this.language, NLPLib.MODE_PRED);
- URL srlRoleURL = (this.srlRoleUri == null)
- ? this.getClass().getClassLoader().getResource(DEFAULT_ROLE_MODEL_FILE_NAME).toURI().toURL()
- : this.srlRoleUri.toURL();
- this.classifier = EngineGetter.getComponent(srlRoleURL.openStream(), this.language, NLPLib.MODE_ROLE);
+ InputStream srlRole = (this.srlRoleUri == null)
+ ? FileLocator.getAsStream(DEFAULT_ROLE_MODEL_FILE_NAME)
+ : FileLocator.getAsStream(this.srlRoleUri.getPath());
+ this.classifier = EngineGetter.getComponent(srlRole, this.language, NLPLib.MODE_ROLE);
- URL srlModelURL = (this.srlModelUri == null)
- ? this.getClass().getClassLoader().getResource(DEFAULT_SRL_MODEL_FILE_NAME).toURI().toURL()
- : this.srlModelUri.toURL();
- this.srlabeler = EngineGetter.getComponent(srlModelURL.openStream(), this.language, NLPLib.MODE_SRL);
+ InputStream srlModel = (this.srlModelUri == null)
+ ? FileLocator.getAsStream(DEFAULT_SRL_MODEL_FILE_NAME)
+ : FileLocator.getAsStream(this.srlModelUri.getPath());
+ this.srlabeler = EngineGetter.getComponent(srlModel, this.language, NLPLib.MODE_SRL);
} catch (Exception e) {
throw new ResourceInitializationException(e);
Modified: ctakes/trunk/ctakes-ne-contexts/desc/test/SegmentTokenSentenceAggregate.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-ne-contexts/desc/test/SegmentTokenSentenceAggregate.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-ne-contexts/desc/test/SegmentTokenSentenceAggregate.xml (original)
+++ ctakes/trunk/ctakes-ne-contexts/desc/test/SegmentTokenSentenceAggregate.xml Fri Jun 14 18:43:35 2013
@@ -27,7 +27,7 @@
<import location="TokenizerAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SentenceDetectorAnnotator">
- <import location="SentenceDetectorAnnotator.xml"/>
+ <import location="../../../ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SimpleSegmentAnnotator">
<import location="SimpleSegmentAnnotator.xml"/>
Modified: ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate.xml (original)
+++ ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate.xml Fri Jun 14 18:43:35 2013
@@ -27,10 +27,10 @@
<import location="SimpleSegmentAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SentenceDetectorAnnotator">
-<import location="SentenceDetectorAnnotator.xml"/>
+<import location="../../../ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="TokenizerAnnotator">
-<import location="TokenizerAnnotator.xml"/>
+<import location="../../../ctakes-core/desc/analysis_engine/TokenizerAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="POSTagger">
<import location="POSTagger.xml"/>
Modified: ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate2.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate2.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate2.xml (original)
+++ ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate2.xml Fri Jun 14 18:43:35 2013
@@ -27,10 +27,10 @@
<import location="SimpleSegmentAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SentenceDetectorAnnotator">
-<import location="SentenceDetectorAnnotator.xml"/>
+<import location="../../../ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="TokenizerAnnotator">
-<import location="TokenizerAnnotator.xml"/>
+<import location="../../../ctakes-core/desc/analysis_engine/TokenizerAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="POSTagger">
<import location="POSTagger.xml"/>
Modified: ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate3.xml
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate3.xml?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate3.xml (original)
+++ ctakes/trunk/ctakes-pos-tagger/desc/test/POSTaggerAggregate3.xml Fri Jun 14 18:43:35 2013
@@ -27,10 +27,10 @@
<import location="TokenizerAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SentenceDetectorAnnotator">
- <import location="SentenceDetectorAnnotator.xml"/>
+ <import location="../../../ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="SimpleSegmentAnnotator">
- <import location="SimpleSegmentAnnotator.xml"/>
+ <import location="../../../ctakes-core/desc/analysis_engine/SimpleSegmentAnnotator.xml"/>
</delegateAnalysisEngine>
<delegateAnalysisEngine key="POSTagger">
<import location="POSTagger.xml"/>
Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/eval/Evaluation_ImplBase.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/eval/Evaluation_ImplBase.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/eval/Evaluation_ImplBase.java (original)
+++ ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/eval/Evaluation_ImplBase.java Fri Jun 14 18:43:35 2013
@@ -41,7 +41,6 @@ import org.apache.ctakes.core.resource.F
import org.apache.ctakes.core.resource.FileResourceImpl;
import org.apache.ctakes.core.resource.JdbcConnectionResourceImpl;
import org.apache.ctakes.core.resource.LuceneIndexReaderResourceImpl;
-import org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl;
import org.apache.ctakes.dependency.parser.ae.ClearNLPDependencyParserAE;
import org.apache.ctakes.dependency.parser.ae.ClearNLPSemanticRoleLabelerAE;
import org.apache.ctakes.dictionary.lookup.ae.UmlsDictionaryLookupAnnotator;
@@ -239,10 +238,8 @@ public abstract class Evaluation_ImplBas
// identify sentences
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
SentenceDetector.class,
- "MaxentModel",
- ExternalResourceFactory.createExternalResourceDescription(
- SuffixMaxentModelResourceImpl.class,
- FileLocator.locateFile("org/apache/ctakes/core/sentdetect/sdmed.mod").toURI().toURL())));
+ SentenceDetector.SD_MODEL_FILE_PARAM,
+ "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
// identify tokens
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
// merge some tokens
Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventAndTimeExtractionPipeline.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventAndTimeExtractionPipeline.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventAndTimeExtractionPipeline.java (original)
+++ ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventAndTimeExtractionPipeline.java Fri Jun 14 18:43:35 2013
@@ -34,7 +34,6 @@ import org.apache.ctakes.core.resource.F
import org.apache.ctakes.core.resource.FileResourceImpl;
import org.apache.ctakes.core.resource.JdbcConnectionResourceImpl;
import org.apache.ctakes.core.resource.LuceneIndexReaderResourceImpl;
-import org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl;
import org.apache.ctakes.dependency.parser.ae.ClearNLPDependencyParserAE;
import org.apache.ctakes.dependency.parser.ae.ClearNLPSemanticRoleLabelerAE;
import org.apache.ctakes.dictionary.lookup.ae.UmlsDictionaryLookupAnnotator;
@@ -135,11 +134,9 @@ public class EventAndTimeExtractionPipel
// identify sentences
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
- SentenceDetector.class,
- "MaxentModel",
- ExternalResourceFactory.createExternalResourceDescription(
- SuffixMaxentModelResourceImpl.class,
- FileLocator.locateFile("org/apache/ctakes/core/sentdetect/sdmed.mod").toURI().toURL())));
+ SentenceDetector.class,
+ SentenceDetector.SD_MODEL_FILE_PARAM,
+ "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
// identify tokens
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
// merge some tokens
Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java (original)
+++ ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java Fri Jun 14 18:43:35 2013
@@ -34,7 +34,6 @@ import org.apache.ctakes.core.resource.F
import org.apache.ctakes.core.resource.FileResourceImpl;
import org.apache.ctakes.core.resource.JdbcConnectionResourceImpl;
import org.apache.ctakes.core.resource.LuceneIndexReaderResourceImpl;
-import org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl;
import org.apache.ctakes.dependency.parser.ae.ClearNLPDependencyParserAE;
import org.apache.ctakes.dependency.parser.ae.ClearNLPSemanticRoleLabelerAE;
import org.apache.ctakes.dictionary.lookup.ae.UmlsDictionaryLookupAnnotator;
@@ -127,11 +126,10 @@ public class EventExtractionPipeline {
// identify sentences
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(
- SentenceDetector.class,
- "MaxentModel",
- ExternalResourceFactory.createExternalResourceDescription(
- SuffixMaxentModelResourceImpl.class,
- FileLocator.locateFile("org/apache/ctakes/core/sentdetect/sdmed.mod").toURI().toURL())));
+ SentenceDetector.class,
+ SentenceDetector.SD_MODEL_FILE_PARAM,
+ "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
+
// identify tokens
aggregateBuilder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
// merge some tokens
Modified: ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/utils/CheckKnowtatorAnnotations.java
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/utils/CheckKnowtatorAnnotations.java?rev=1493198&r1=1493197&r2=1493198&view=diff
==============================================================================
--- ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/utils/CheckKnowtatorAnnotations.java (original)
+++ ctakes/trunk/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/utils/CheckKnowtatorAnnotations.java Fri Jun 14 18:43:35 2013
@@ -24,7 +24,6 @@ import java.util.List;
import org.apache.ctakes.core.ae.SentenceDetector;
import org.apache.ctakes.core.ae.TokenizerAnnotatorPTB;
-import org.apache.ctakes.core.resource.SuffixMaxentModelResourceImpl;
import org.apache.ctakes.temporal.ae.THYMEKnowtatorXMLReader;
import org.apache.ctakes.temporal.eval.CommandLine;
import org.apache.ctakes.temporal.eval.Evaluation_ImplBase.SegmentsFromBracketedSectionTagsAnnotator;
@@ -79,11 +78,9 @@ public class CheckKnowtatorAnnotations {
options.getKnowtatorXMLDirectory()));
builder.add(AnalysisEngineFactory.createPrimitiveDescription(SegmentsFromBracketedSectionTagsAnnotator.class));
builder.add(AnalysisEngineFactory.createPrimitiveDescription(
- SentenceDetector.class,
- "MaxentModel",
- ExternalResourceFactory.createExternalResourceDescription(
- SuffixMaxentModelResourceImpl.class,
- SentenceDetector.class.getResource("../sentdetect/sdmed.mod"))));
+ SentenceDetector.class,
+ SentenceDetector.SD_MODEL_FILE_PARAM,
+ "org/apache/ctakes/core/sentdetect/sd-med-model.zip"));
builder.add(AnalysisEngineFactory.createPrimitiveDescription(TokenizerAnnotatorPTB.class));
for (JCas jCas : new JCasIterable(reader, builder.createAggregate())) {
for (EventMention event : JCasUtil.select(jCas, EventMention.class)) {