This is an automated email from the ASF dual-hosted git repository.
seanfinan pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/ctakes.git
The following commit(s) were added to refs/heads/main by this push:
new 679130e Got rid of compile warnings. The only reamining warnings are
for types (unchecked, etc.) in modules that use older untyped 3rd party code.
Updating dependencies in the future may help us get rid of these warnings.
679130e is described below
commit 679130e91efb46a03694abb382ee4b0d924f247a
Author: Sean Finan <[email protected]>
AuthorDate: Thu Dec 29 18:22:26 2022 -0500
Got rid of compile warnings. The only reamining warnings are for types
(unchecked, etc.) in modules that use older untyped 3rd party code. Updating
dependencies in the future may help us get rid of these warnings.
---
.../fsm/machines/elements/RangeStrengthFSM.java | 137 +++++++----------
.../sideeffect/ae/SESentenceFeatureAnnotator.java | 171 ++++++++++-----------
.../pipelines/EventExtractionPipeline.java | 6 +-
3 files changed, 147 insertions(+), 167 deletions(-)
diff --git
a/ctakes-drug-ner/src/main/java/org/apache/ctakes/drugner/fsm/machines/elements/RangeStrengthFSM.java
b/ctakes-drug-ner/src/main/java/org/apache/ctakes/drugner/fsm/machines/elements/RangeStrengthFSM.java
index 064a4a6..82ed38d 100644
---
a/ctakes-drug-ner/src/main/java/org/apache/ctakes/drugner/fsm/machines/elements/RangeStrengthFSM.java
+++
b/ctakes-drug-ner/src/main/java/org/apache/ctakes/drugner/fsm/machines/elements/RangeStrengthFSM.java
@@ -1,4 +1,4 @@
-/**
+/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
@@ -49,13 +49,13 @@ import net.openai.util.fsm.State;
public class RangeStrengthFSM
{
// text fractions
- Set iv_textNumberSet = new HashSet();
+ Set<String> iv_textNumberSet = new HashSet<>();
// range text
- Set iv_rangeSet = new HashSet();
+ Set<String> iv_rangeSet = new HashSet<>();
- Set iv_hyphenatedSet = new HashSet();
+ Set<String> iv_hyphenatedSet = new HashSet<>();
// contains the finite state machines
- private Set iv_machineSet = new HashSet();
+ final private Set<Machine> iv_machineSet = new HashSet<>();
/**
* Constructor
@@ -200,7 +200,7 @@ public class RangeStrengthFSM
* <li>25.4-30.4</li>
* <li>32.1-three</li>
* </ol>
- * @return
+ * @return -
*/
private Machine getDashDashMachine()
{
@@ -258,7 +258,7 @@ public class RangeStrengthFSM
* <li>25.4-30.4</li>
* <li>32.1-three</li>
* </ol>
- * @return
+ * @return -
*/
private Machine getDashMachine()
{
@@ -309,7 +309,7 @@ public class RangeStrengthFSM
* <li>two-three</li>
* <li>two-to-three</li>
* </ol>
- * @return
+ * @return -
*/
private Machine getDotDashMachine()
@@ -368,25 +368,25 @@ public class RangeStrengthFSM
/**
* Executes the finite state machines.
- * @param tokens
+ * @param tokens -
* @return Set of RangeToken objects.
- * @throws Exception
+ * @throws Exception -
*/
- public Set execute(List tokens, Set overrideSet) throws Exception
+ public Set<RangeStrengthToken> execute(List<BaseToken> tokens,
Set<BaseToken> overrideSet) throws Exception
{
- Set rangeSet = new HashSet();
+ Set<RangeStrengthToken> rangeSet = new HashSet<>();
// maps a fsm to a token start index
// key = fsm , value = token start index
- Map tokenStartMap = new HashMap();
+ Map<Machine,Integer> tokenStartMap = new HashMap<>();
- Iterator overrideTokenItr = overrideSet.iterator();
+ Iterator<BaseToken> overrideTokenItr = overrideSet.iterator();
// key = start offset, value = override BaseToken object
- Map overrideTokenMap = new HashMap();
+ Map<Integer,BaseToken> overrideTokenMap = new HashMap<>();
while (overrideTokenItr.hasNext())
{
- BaseToken t = (BaseToken)overrideTokenItr.next();
- Integer key = new Integer(t.getStartOffset());
+ BaseToken t = overrideTokenItr.next();
+ Integer key = t.getStartOffset();
overrideTokenMap.put(key, t);
}
@@ -394,9 +394,9 @@ public class RangeStrengthFSM
int overrideEndOffset = -1;
for (int i = 0; i < tokens.size(); i++)
{
- BaseToken token = (BaseToken) tokens.get(i);
+ BaseToken token = tokens.get(i);
- Integer key = new Integer(token.getStartOffset());
+ Integer key = token.getStartOffset();
if (overrideOn)
{
@@ -417,48 +417,37 @@ public class RangeStrengthFSM
{
// override one or more tokens until
the override
// token is complete
- token =
(BaseToken)overrideTokenMap.get(key);
+ token = overrideTokenMap.get(key);
overrideOn = true;
overrideEndOffset =
token.getEndOffset();
}
}
- Iterator machineItr = iv_machineSet.iterator();
- while (machineItr.hasNext())
- {
- Machine fsm = (Machine) machineItr.next();
-
- fsm.input(token);
+ for ( final Machine fsm : iv_machineSet ) {
+ fsm.input( token );
State currentState = fsm.getCurrentState();
- if (currentState.getStartStateFlag())
- {
- tokenStartMap.put(fsm, new Integer(i));
+ if ( currentState.getStartStateFlag() ) {
+ tokenStartMap.put( fsm, i );
}
- if (currentState.getEndStateFlag())
- {
- Object o = tokenStartMap.get(fsm);
+ if ( currentState.getEndStateFlag() ) {
+ Integer o = tokenStartMap.get( fsm );
int tokenStartIndex;
- if (o == null)
- {
+ if ( o == null ) {
// By default, all machines
start with
// token zero.
tokenStartIndex = 0;
- }
- else
- {
- tokenStartIndex = ((Integer)
o).intValue();
+ } else {
+ tokenStartIndex = o;
// skip ahead over single token
we don't want
- tokenStartIndex++;
+ tokenStartIndex++;
}
- BaseToken startToken =
- (BaseToken)
tokens.get(tokenStartIndex);
- BaseToken endToken = token;
+ BaseToken startToken = tokens.get(
tokenStartIndex );
RangeStrengthToken segmentToken =
- new RangeStrengthToken(
-
startToken.getStartOffset(),
-
endToken.getEndOffset());
- rangeSet.add(segmentToken);
+ new RangeStrengthToken(
+
startToken.getStartOffset(),
+
token.getEndOffset() );
+ rangeSet.add( segmentToken );
fsm.reset();
}
}
@@ -468,10 +457,7 @@ public class RangeStrengthFSM
tokenStartMap.clear();
// reset machines
- Iterator itr = iv_machineSet.iterator();
- while (itr.hasNext())
- {
- Machine fsm = (Machine) itr.next();
+ for ( final Machine fsm : iv_machineSet ) {
fsm.reset();
}
@@ -480,48 +466,45 @@ public class RangeStrengthFSM
/**
* Executes the finite state machines.
- * @param tokens
+ * @param tokens -
* @return Set of FractionToken objects.
- * @throws Exception
+ * @throws Exception -
*/
- public Set execute(List tokens) throws Exception {
- Set fractionSet = new HashSet();
+ public Set<RangeStrengthToken> execute(List<BaseToken> tokens) throws
Exception {
+ Set<RangeStrengthToken> fractionSet = new HashSet<>();
// maps a fsm to a token start index
// key = fsm , value = token start index
- Map tokenStartMap = new HashMap();
+ Map<Machine,Integer> tokenStartMap = new HashMap<>();
for (int i = 0; i < tokens.size(); i++) {
- BaseToken token = (BaseToken) tokens.get(i);
-
- Iterator machineItr = iv_machineSet.iterator();
- while (machineItr.hasNext()) {
- Machine fsm = (Machine) machineItr.next();
-
- fsm.input(token);
-
+ BaseToken token = tokens.get(i);
+
+ for ( final Machine fsm : iv_machineSet ) {
+ fsm.input( token );
+
State currentState = fsm.getCurrentState();
- if (currentState.getStartStateFlag()) {
- tokenStartMap.put(fsm, new Integer(i));
+ if ( currentState.getStartStateFlag() ) {
+ tokenStartMap.put( fsm, i );
}
- if (currentState.getEndStateFlag()) {
- Object o = tokenStartMap.get(fsm);
+ if ( currentState.getEndStateFlag() ) {
+ Integer o = tokenStartMap.get( fsm );
int tokenStartIndex;
- if (o == null) {
+ if ( o == null ) {
// By default, all machines
start with
// token zero.
tokenStartIndex = 0;
} else {
- tokenStartIndex = ((Integer)
o).intValue();
+ tokenStartIndex = o;
// skip ahead over single token
we don't want
tokenStartIndex++;
}
- BaseToken startToken = (BaseToken)
tokens
- .get(tokenStartIndex);
- BaseToken endToken = token;
- RangeStrengthToken fractionToken = new
RangeStrengthToken(startToken
- .getStartOffset(),
endToken.getEndOffset());
- fractionSet.add(fractionToken);
+ BaseToken startToken = tokens
+ .get( tokenStartIndex );
+ RangeStrengthToken fractionToken = new
RangeStrengthToken( startToken
+
.getStartOffset(),
+
token.getEndOffset() );
+ fractionSet.add( fractionToken );
fsm.reset();
}
}
@@ -531,9 +514,7 @@ public class RangeStrengthFSM
tokenStartMap.clear();
// reset machines
- Iterator itr = iv_machineSet.iterator();
- while (itr.hasNext()) {
- Machine fsm = (Machine) itr.next();
+ for ( final Machine fsm : iv_machineSet ) {
fsm.reset();
}
diff --git
a/ctakes-side-effect/src/main/java/org/apache/ctakes/sideeffect/ae/SESentenceFeatureAnnotator.java
b/ctakes-side-effect/src/main/java/org/apache/ctakes/sideeffect/ae/SESentenceFeatureAnnotator.java
index c779ff9..8384457 100644
---
a/ctakes-side-effect/src/main/java/org/apache/ctakes/sideeffect/ae/SESentenceFeatureAnnotator.java
+++
b/ctakes-side-effect/src/main/java/org/apache/ctakes/sideeffect/ae/SESentenceFeatureAnnotator.java
@@ -1,4 +1,4 @@
-/**
+/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
@@ -29,6 +29,7 @@ import
org.apache.uima.analysis_engine.AnalysisEngineProcessException;
import org.apache.uima.jcas.JCas;
import org.apache.uima.jcas.JFSIndexRepository;
import org.apache.uima.jcas.cas.StringArray;
+import org.apache.uima.jcas.tcas.Annotation;
import org.apache.uima.resource.ResourceInitializationException;
import java.io.BufferedReader;
@@ -44,18 +45,18 @@ import java.util.*;
* @author Mayo Clinic
*/
public class SESentenceFeatureAnnotator extends JCasAnnotator_ImplBase {
- private Map metaKeywords; // key:metakeyword, value:set of keywords
- private List metaKey; // metaKeywords.keySet()
+ private Map<String,Set<String>> metaKeywords; // key:metakeyword,
value:set of keywords
+ private List<String> metaKey; // metaKeywords.keySet()
- private class SideEffect {
- String text;
- int begin, end;
- }
+// private static class SideEffect {
+// String text;
+// int begin, end;
+// }
public void initialize(UimaContext annotCtx)
throws ResourceInitializationException {
super.initialize(annotCtx);
- metaKey = new ArrayList();
+ metaKey = new ArrayList<>();
try {
String metaKeywordsFileName = (String) annotCtx
@@ -80,34 +81,32 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
* Annotate PSESentenceFeature to be used to classify SE sentences
based on
* the previously trained model
*
- * @param jcas
+ * @param jcas -
*/
private void annotatePSESentenceFeatures(JCas jcas) {
JFSIndexRepository indexes = jcas.getJFSIndexRepository();
- Iterator pseSenIter =
indexes.getAnnotationIndex(PSESentence.type)
- .iterator();
- while (pseSenIter.hasNext()) {
- PSESentence ps = (PSESentence) pseSenIter.next();
- List fea = new ArrayList();
+ for ( final Annotation annotation : indexes.getAnnotationIndex(
PSESentence.type ) ) {
+ PSESentence ps = (PSESentence) annotation;
// get features
- fea.addAll(getLocationFeaturesFromMetaKeywords(jcas,
ps));
+ List<String> fea = new ArrayList<>(
getLocationFeaturesFromMetaKeywords( jcas, ps ) );
- PSESentenceFeature psf = new PSESentenceFeature(jcas);
- StringArray feaArray = new StringArray(jcas,
fea.size());
+ PSESentenceFeature psf = new PSESentenceFeature( jcas );
+ StringArray feaArray = new StringArray( jcas,
fea.size() );
// cf) In FSArray the argument must be FeatureStructure
("String"
// does not work)
- for (int i = 0; i < fea.size(); i++) {
- feaArray.set(i, (String) fea.get(i));
+ for ( int i = 0; i < fea.size(); i++ ) {
+ feaArray.set( i, fea.get( i ) );
}
// set PSESentenceFeature
- if (feaArray != null)
- psf.setFeatures(feaArray); // TODO ?? - could
be no text in
-
// sentence??
- psf.setPseSen(ps);
+ if ( feaArray != null ) {
+ psf.setFeatures( feaArray ); // TODO ?? - could
be no text in
+ }
+ // sentence??
+ psf.setPseSen( ps );
// add to CAS
psf.addToIndexes();
@@ -118,17 +117,18 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
* Return the List of location features of meta keywords metaKeywords -
* key:metakeyword, value:actual keyword
*
- * @param jcas
+ * @param jcas -
* @param ps
* PSESentence
- * @return
+ * @return -
*/
- private List getLocationFeaturesFromMetaKeywords(JCas jcas, PSESentence
ps) {
- List feature = new ArrayList();
- List drug = new ArrayList();
- List pse = new ArrayList();
+ private List<String> getLocationFeaturesFromMetaKeywords(JCas jcas,
PSESentence ps) {
+ List<String> feature = new ArrayList<>();
+ List<IdentifiedAnnotation> drug = new ArrayList<>();
+ List<IdentifiedAnnotation> pse = new ArrayList<>();
- Iterator neIter = FSUtil.getAnnotationsIteratorInSpan(jcas,
IdentifiedAnnotation.type, ps.getBegin(), ps.getEnd() + 1);
+ Iterator<?> neIter = FSUtil.getAnnotationsIteratorInSpan(jcas,
IdentifiedAnnotation.type, ps.getBegin(),
+
ps.getEnd() + 1);
while (neIter.hasNext()) {
IdentifiedAnnotation n = (IdentifiedAnnotation)
neIter.next();
// drug
@@ -142,32 +142,33 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
}
// for each metaKey
- Iterator metaKeyIter = metaKey.iterator();
- while (metaKeyIter.hasNext()) {
- String mk = (String) metaKeyIter.next();
- Set kwSet = (Set) metaKeywords.get(mk);
+ for ( final String mk : metaKey ) {
+ Set<String> kwSet = metaKeywords.get( mk );
// for each keyword in a given metaKey
- Iterator kwIter = kwSet.iterator();
+ Iterator<String> kwIter = kwSet.iterator();
String kw = "";
int kwPos = -1;
boolean foundKw = false;
- while (kwIter.hasNext()) {
- String pseSenText =
ps.getCoveredText().toLowerCase();
- kw = (String) kwIter.next();
- kwPos = pseSenText.indexOf(kw);
- if (kwPos == -1)
+ while ( kwIter.hasNext() ) {
+ String pseSenText = ps.getCoveredText()
+
.toLowerCase();
+ kw = kwIter.next();
+ kwPos = pseSenText.indexOf( kw );
+ if ( kwPos == -1 )
continue;
// if 1st before & after char is non-alphabet
int kwB = kwPos - 1;
int kwA = kwPos + kw.length();
// cf) end is the end index + 1;
- if ((pseSenText.length() <= kwA) || // == would
be satisfied
- (kwPos == 0 &&
pseSenText.substring(kwA, kwA + 1)
- .matches("\\W"))
- || (pseSenText.substring(kwA,
kwA + 1).matches("\\W") && pseSenText
- .substring(kwB,
kwB + 1).matches("\\W"))) {
+ final boolean matches = pseSenText.substring(
kwA, kwA + 1 )
+
.matches( "\\W" );
+ if ( ( pseSenText.length() <= kwA ) || // ==
would be satisfied
+ ( kwPos == 0 && matches )
+ || ( matches && pseSenText
+
.substring( kwB, kwB + 1 )
+
.matches( "\\W" ) ) ) {
foundKw = true;
break;
}
@@ -186,8 +187,8 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
}
// if not found the keyword, go to next keyword
- if (!foundKw) {
- feature.add("nul");
+ if ( !foundKw ) {
+ feature.add( "nul" );
continue;
}
@@ -199,70 +200,68 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
boolean betweenDrugAndPse = false;
// check if keyword exists between PSE and Drug
- Iterator iter1, iter2;
+ Iterator<IdentifiedAnnotation> iter1, iter2;
iter1 = pse.iterator();
- while (iter1.hasNext()) {
- IdentifiedAnnotation pseNE =
(IdentifiedAnnotation) iter1.next();
- if (kwBegin > pseNE.getEnd()) {
+ while ( iter1.hasNext() ) {
+ IdentifiedAnnotation pseNE = iter1.next();
+ if ( kwBegin > pseNE.getEnd() ) {
iter2 = drug.iterator();
- while (iter2.hasNext()) {
- IdentifiedAnnotation drugNE =
(IdentifiedAnnotation) iter2.next();
- if (kwEnd < drugNE.getBegin()) {
+ while ( iter2.hasNext() ) {
+ IdentifiedAnnotation drugNE =
iter2.next();
+ if ( kwEnd < drugNE.getBegin()
) {
betweenPseAndDrug =
true;
break;
}
}
}
- if (betweenPseAndDrug)
+ if ( betweenPseAndDrug )
break;
}
// check if keyword exists between Drug and PSE
iter1 = drug.iterator();
- while (iter1.hasNext()) {
- IdentifiedAnnotation drugNE =
(IdentifiedAnnotation) iter1.next();
- if (kwBegin > drugNE.getEnd()) {
+ while ( iter1.hasNext() ) {
+ IdentifiedAnnotation drugNE = iter1.next();
+ if ( kwBegin > drugNE.getEnd() ) {
iter2 = pse.iterator();
- while (iter2.hasNext()) {
- IdentifiedAnnotation pseNE =
(IdentifiedAnnotation) iter2.next();
- if (kwEnd < pseNE.getBegin()) {
+ while ( iter2.hasNext() ) {
+ IdentifiedAnnotation pseNE =
iter2.next();
+ if ( kwEnd < pseNE.getBegin() )
{
betweenDrugAndPse =
true;
break;
}
}
}
- if (betweenDrugAndPse)
+ if ( betweenDrugAndPse )
break;
}
- if ((!betweenPseAndDrug) && (!betweenDrugAndPse)) {
- Iterator pseIter = pse.iterator();
- while (pseIter.hasNext()) {
- IdentifiedAnnotation n =
(IdentifiedAnnotation) pseIter.next();
- if (kwEnd < n.getBegin())
+ if ( ( !betweenPseAndDrug ) && ( !betweenDrugAndPse ) )
{
+ for ( final IdentifiedAnnotation n : pse ) {
+ if ( kwEnd < n.getBegin() )
beforePse = true;
- if (kwBegin > n.getEnd())
+ if ( kwBegin > n.getEnd() )
afterPse = true;
}
}
- if (mk.equals("SideEffectWord")) {
- feature.add("pre");
+ if ( mk.equals( "SideEffectWord" ) ) {
+ feature.add( "pre" );
} else {
- if (betweenPseAndDrug && betweenDrugAndPse)
- feature.add("bet");
- else if (betweenPseAndDrug)
- feature.add("bpd");
- else if (betweenDrugAndPse)
- feature.add("bdp");
- else if (beforePse && afterPse)
- feature.add("bap");
- else if (beforePse)
- feature.add("bep");
- else if (afterPse)
- feature.add("afp");
+ if ( betweenPseAndDrug && betweenDrugAndPse )
+ feature.add( "bet" );
+ else if ( betweenPseAndDrug )
+ feature.add( "bpd" );
+ else if ( betweenDrugAndPse )
+ feature.add( "bdp" );
+ else if ( beforePse && afterPse )
+ feature.add( "bap" );
+ else if ( beforePse )
+ feature.add( "bep" );
+ else if ( afterPse )
+ feature.add( "afp" );
else
- feature.add("any");
+ feature.add( "any" );
}
}
@@ -277,9 +276,9 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
* input file format: metakeyword|keyword|keyword...
* metakeyword|keyword|keyword...
*/
- public Map readMetaKeywordsFromFile(String fileName, List key)
+ public Map<String,Set<String>> readMetaKeywordsFromFile(String
fileName, List<String> key)
throws IOException {
- Map returnValues = new LinkedHashMap();
+ Map<String,Set<String>> returnValues = new LinkedHashMap<>();
File file = new File(fileName);
BufferedReader fileReader = new BufferedReader(new
FileReader(file));
@@ -291,7 +290,7 @@ public class SESentenceFeatureAnnotator extends
JCasAnnotator_ImplBase {
continue;
String[] stk = line.trim().split("\\|");
- Set keySet = new LinkedHashSet();
+ Set<String> keySet = new LinkedHashSet<>();
for (int i = 1; i < stk.length; i++) {
keySet.add(stk[i].trim());
}
diff --git
a/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
b/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
index 855fffa..09a7703 100644
---
a/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
+++
b/ctakes-temporal/src/main/java/org/apache/ctakes/temporal/pipelines/EventExtractionPipeline.java
@@ -20,7 +20,7 @@ package org.apache.ctakes.temporal.pipelines;
import com.lexicalscope.jewel.cli.CliFactory;
import com.lexicalscope.jewel.cli.Option;
-import org.apache.ctakes.core.cc.XmiWriterCasConsumerCtakes;
+import org.apache.ctakes.core.cc.FileTreeXmiWriter;
import org.apache.ctakes.core.config.ConfigParameterConstants;
import org.apache.ctakes.temporal.ae.EventAnnotator;
import org.apache.uima.analysis_engine.AnalysisEngine;
@@ -61,8 +61,8 @@ public class EventExtractionPipeline extends
TemporalExtractionPipeline_ImplBase
aggregateBuilder.add(EventAnnotator.createAnnotatorDescription(new
File(options.getModelDirectory())));
AnalysisEngine xWriter = AnalysisEngineFactory.createEngine(
- XmiWriterCasConsumerCtakes.class,
- XmiWriterCasConsumerCtakes.PARAM_OUTPUTDIR,
+ FileTreeXmiWriter.class,
+ ConfigParameterConstants.PARAM_OUTPUTDIR,
options.getOutputDirectory());
SimplePipeline.runPipeline(
