You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ki...@apache.org on 2022/12/02 14:06:45 UTC
[opennlp] branch master updated: OPENNLP-1400 Enhance JavaDoc in opennlp.tools.sentdetect package
This is an automated email from the ASF dual-hosted git repository.
kinow pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/opennlp.git
The following commit(s) were added to refs/heads/master by this push:
new d0675ed8 OPENNLP-1400 Enhance JavaDoc in opennlp.tools.sentdetect package
d0675ed8 is described below
commit d0675ed806d1d35cb89a4363ced80ea273edf834
Author: Martin Wiesner <ma...@hs-heilbronn.de>
AuthorDate: Fri Dec 2 14:55:57 2022 +0100
OPENNLP-1400 Enhance JavaDoc in opennlp.tools.sentdetect package
- adds missing JavaDoc
- improves existing documentation for clarity
- removes superfluous text
- fixes typos
- adjusts SentenceSample to implement Sample interface to be consistent with other cases (see changes in: OPENNLP-1394)
- adds 'final' modifier where useful and applicable
- removes deprecated constructors in SDCrossValidator
---
.../main/java/opennlp/tools/postag/POSTagger.java | 6 +--
.../java/opennlp/tools/postag/POSTaggerME.java | 8 ++--
.../sentdetect/DefaultEndOfSentenceScanner.java | 11 ++++--
.../sentdetect/DefaultSDContextGenerator.java | 29 +++++++-------
.../sentdetect/EmptyLinePreprocessorStream.java | 3 +-
.../tools/sentdetect/EndOfSentenceScanner.java | 20 +++++-----
.../tools/sentdetect/NewlineSentenceDetector.java | 4 +-
.../tools/sentdetect/SDContextGenerator.java | 2 +-
.../opennlp/tools/sentdetect/SDCrossValidator.java | 45 +++-------------------
.../opennlp/tools/sentdetect/SDEventStream.java | 8 ++--
.../opennlp/tools/sentdetect/SentenceDetector.java | 6 +--
.../sentdetect/SentenceDetectorEvaluator.java | 8 ++--
.../tools/sentdetect/SentenceDetectorFactory.java | 9 +++--
.../tools/sentdetect/SentenceDetectorME.java | 24 ++++++------
.../opennlp/tools/sentdetect/SentenceSample.java | 19 ++++-----
.../tools/sentdetect/SentenceSampleStream.java | 5 ++-
.../opennlp/tools/sentdetect/package-info.java | 2 +-
.../opennlp/tools/postag/POSEvaluatorTest.java | 4 +-
.../uima/sentdetect/AbstractSentenceDetector.java | 6 +--
.../main/java/opennlp/uima/sentdetect/package.html | 2 +-
20 files changed, 95 insertions(+), 126 deletions(-)
diff --git a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTagger.java b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTagger.java
index bc334ea0..e7599047 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTagger.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTagger.java
@@ -26,14 +26,14 @@ public interface POSTagger {
/**
* Assigns the sentence of tokens pos tags.
- * @param sentence The sentece of tokens to be tagged.
+ * @param sentence The sentence of tokens to be tagged.
* @return an array of pos tags for each token provided in sentence.
*/
String[] tag(String[] sentence);
- String[] tag(String[] sentence, Object[] additionaContext);
+ String[] tag(String[] sentence, Object[] additionalContext);
Sequence[] topKSequences(String[] sentence);
- Sequence[] topKSequences(String[] sentence, Object[] additionaContext);
+ Sequence[] topKSequences(String[] sentence, Object[] additionalContext);
}
diff --git a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java
index 95ffffef..655c2fde 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/postag/POSTaggerME.java
@@ -144,8 +144,8 @@ public class POSTaggerME implements POSTagger {
return this.tag(sentence, null);
}
- public String[] tag(String[] sentence, Object[] additionaContext) {
- bestSequence = model.bestSequence(sentence, additionaContext, contextGen, sequenceValidator);
+ public String[] tag(String[] sentence, Object[] additionalContext) {
+ bestSequence = model.bestSequence(sentence, additionalContext, contextGen, sequenceValidator);
List<String> t = bestSequence.getOutcomes();
return t.toArray(new String[t.size()]);
}
@@ -173,8 +173,8 @@ public class POSTaggerME implements POSTagger {
return this.topKSequences(sentence, null);
}
- public Sequence[] topKSequences(String[] sentence, Object[] additionaContext) {
- return model.bestSequences(size, sentence, additionaContext, contextGen, sequenceValidator);
+ public Sequence[] topKSequences(String[] sentence, Object[] additionalContext) {
+ return model.bestSequences(size, sentence, additionalContext, contextGen, sequenceValidator);
}
/**
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultEndOfSentenceScanner.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultEndOfSentenceScanner.java
index 2b8c0bee..bc9f004d 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultEndOfSentenceScanner.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultEndOfSentenceScanner.java
@@ -25,19 +25,19 @@ import java.util.Set;
/**
* Default implementation of the {@link EndOfSentenceScanner}.
- * It uses an character array with possible end of sentence chars
+ * It uses a character array with possible end of sentence chars
* to identify potential sentence endings.
*/
public class DefaultEndOfSentenceScanner implements EndOfSentenceScanner {
- private Set<Character> eosCharacters;
+ private final Set<Character> eosCharacters;
@Deprecated
- private char[] eosChars;
+ private final char[] eosChars;
/**
* Initializes the current instance.
*
- * @param eosCharacters
+ * @param eosCharacters The characters to be used to detect sentence endings.
*/
public DefaultEndOfSentenceScanner(char[] eosCharacters) {
this.eosCharacters = new HashSet<>();
@@ -47,14 +47,17 @@ public class DefaultEndOfSentenceScanner implements EndOfSentenceScanner {
this.eosChars = eosCharacters;
}
+ @Override
public List<Integer> getPositions(String s) {
return getPositions(s.toCharArray());
}
+ @Override
public List<Integer> getPositions(StringBuffer buf) {
return getPositions(buf.toString().toCharArray());
}
+ @Override
public List<Integer> getPositions(char[] cbuf) {
List<Integer> l = new ArrayList<>();
for (int i = 0; i < cbuf.length; i++) {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultSDContextGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultSDContextGenerator.java
index 8c2822bd..f972d575 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultSDContextGenerator.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/DefaultSDContextGenerator.java
@@ -41,15 +41,14 @@ public class DefaultSDContextGenerator implements SDContextGenerator {
*/
protected List<String> collectFeats;
- private Set<String> inducedAbbreviations;
+ private final Set<String> inducedAbbreviations;
- private Set<Character> eosCharacters;
+ private final Set<Character> eosCharacters;
/**
- * Creates a new <code>SDContextGenerator</code> instance with
- * no induced abbreviations.
+ * Creates a new instance with no induced abbreviations.
*
- * @param eosCharacters
+ * @param eosCharacters The characters to be used to detect sentence endings.
*/
public DefaultSDContextGenerator(char[] eosCharacters) {
this(Collections.emptySet(), eosCharacters);
@@ -63,7 +62,7 @@ public class DefaultSDContextGenerator implements SDContextGenerator {
* representing induced abbreviations in the training data.
* Example: "Mr."
*
- * @param eosCharacters
+ * @param eosCharacters The characters to be used to detect sentence endings.
*/
public DefaultSDContextGenerator(Set<String> inducedAbbreviations, char[] eosCharacters) {
this.inducedAbbreviations = inducedAbbreviations;
@@ -87,9 +86,7 @@ public class DefaultSDContextGenerator implements SDContextGenerator {
return new String(new char[]{c});
}
- /* (non-Javadoc)
- * @see opennlp.tools.sentdetect.SDContextGenerator#getContext(java.lang.StringBuffer, int)
- */
+ @Override
public String[] getContext(CharSequence sb, int position) {
/*
@@ -164,7 +161,7 @@ public class DefaultSDContextGenerator implements SDContextGenerator {
}
/**
- * Determines some of the features for the sentence detector and adds them to list features.
+ * Determines some features for the sentence detector and adds them to list features.
*
* @param prefix String preceding the eos character in the eos token.
* @param suffix String following the eos character in the eos token.
@@ -178,13 +175,13 @@ public class DefaultSDContextGenerator implements SDContextGenerator {
}
/**
- * Determines some of the features for the sentence detector and adds them to list features.
+ * Determines some features for the sentence detector and adds them to list features.
*
- * @param prefix String preceding the eos character in the eos token.
- * @param suffix String following the eos character in the eos token.
- * @param previous Space delimited token preceding token containing eos character.
- * @param next Space delimited token following token containing eos character.
- * @param eosChar the EOS character been analyzed
+ * @param prefix String preceding the {@code eosChar} in the eos token.
+ * @param suffix String following the {@code eosChar} in the eos token.
+ * @param previous Space delimited token preceding token containing {@code eosChar}.
+ * @param next Space delimited token following token containing {@code eosChar}.
+ * @param eosChar the EOS character been analyzed.
*/
protected void collectFeatures(String prefix, String suffix, String previous,
String next, Character eosChar) {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EmptyLinePreprocessorStream.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EmptyLinePreprocessorStream.java
index 9912155a..dc4cb61e 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EmptyLinePreprocessorStream.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EmptyLinePreprocessorStream.java
@@ -23,7 +23,7 @@ import opennlp.tools.util.FilterObjectStream;
import opennlp.tools.util.ObjectStream;
/**
- * Stream to to clean up empty lines for empty line separated document streams.<br>
+ * {@link ObjectStream} to clean up empty lines for empty line separated document streams.<br>
*
* - Skips empty line at training data start<br>
* - Transforms multiple empty lines in a row into one <br>
@@ -48,6 +48,7 @@ public class EmptyLinePreprocessorStream extends FilterObjectStream<String, Stri
return line.trim().length() == 0;
}
+ @Override
public String read() throws IOException {
String line = samples.read();
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EndOfSentenceScanner.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EndOfSentenceScanner.java
index 7963e377..c1aee346 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EndOfSentenceScanner.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/EndOfSentenceScanner.java
@@ -32,15 +32,13 @@ import java.util.Set;
public interface EndOfSentenceScanner {
/**
- * Returns an array of character which can indicate the end of a sentence.
* @return an array of character which can indicate the end of a sentence.
*/
@Deprecated
char[] getEndOfSentenceCharacters();
/**
- * Returns a set of character which can indicate the end of a sentence.
- * @return a set of character which can indicate the end of a sentence.
+ * @return a set of {@link Character characters} which can indicate the end of a sentence.
*/
Set<Character> getEOSCharacters();
@@ -48,26 +46,26 @@ public interface EndOfSentenceScanner {
* The receiver scans the specified string for sentence ending characters and
* returns their offsets.
*
- * @param s a <code>String</code> value
- * @return a <code>List</code> of Integer objects.
+ * @param s a {@link String} value
+ * @return a {@link List} of Integer objects.
*/
List<Integer> getPositions(String s);
/**
- * The receiver scans `buf' for sentence ending characters and
+ * The receiver scans {@code buf} for sentence ending characters and
* returns their offsets.
*
- * @param buf a <code>StringBuffer</code> value
- * @return a <code>List</code> of Integer objects.
+ * @param buf a {@link StringBuffer} value
+ * @return a {@link List} of Integer objects.
*/
List<Integer> getPositions(StringBuffer buf);
/**
- * The receiver scans `cbuf' for sentence ending characters and
+ * The receiver scans {@code cbuf} for sentence ending characters and
* returns their offsets.
*
- * @param cbuf a <code>char[]</code> value
- * @return a <code>List</code> of Integer objects.
+ * @param cbuf a {@code char[]} value
+ * @return a {@link List} of Integer objects.
*/
List<Integer> getPositions(char[] cbuf);
}
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/NewlineSentenceDetector.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/NewlineSentenceDetector.java
index 4f3c96c5..84cfa259 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/NewlineSentenceDetector.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/NewlineSentenceDetector.java
@@ -23,15 +23,17 @@ import java.util.List;
import opennlp.tools.util.Span;
/**
- * The Newline Sentence Detector assumes that sentences are line delimited and
+ * The Newline {@link SentenceDetector} assumes that sentences are line delimited and
* recognizes one sentence per non-empty line.
*/
public class NewlineSentenceDetector implements SentenceDetector {
+ @Override
public String[] sentDetect(String s) {
return Span.spansToStrings(sentPosDetect(s), s);
}
+ @Override
public Span[] sentPosDetect(String s) {
List<Span> sentences = new ArrayList<>();
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDContextGenerator.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDContextGenerator.java
index ade9d6a6..d0ca1f2f 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDContextGenerator.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDContextGenerator.java
@@ -31,7 +31,7 @@ public interface SDContextGenerator {
* @param position An index into the specified string buffer when a sentence boundary may occur.
*
* @return an array of contextual features for the potential sentence boundary at the
- * specified position within the specified string buffer.
+ * specified {@code position} within the specified string buffer.
*/
String[] getContext(CharSequence s, int position);
}
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDCrossValidator.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDCrossValidator.java
index 2f6daeca..9f0bdadf 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDCrossValidator.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDCrossValidator.java
@@ -23,10 +23,9 @@ import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.TrainingParameters;
import opennlp.tools.util.eval.CrossValidationPartitioner;
import opennlp.tools.util.eval.FMeasure;
-import opennlp.tools.util.model.ModelUtil;
/**
- * A cross validator for the sentence detector.
+ * A cross validator for {@link SentenceDetector sentence detectors}.
*/
public class SDCrossValidator {
@@ -34,11 +33,11 @@ public class SDCrossValidator {
private final TrainingParameters params;
- private FMeasure fmeasure = new FMeasure();
+ private final FMeasure fmeasure = new FMeasure();
- private SentenceDetectorEvaluationMonitor[] listeners;
+ private final SentenceDetectorEvaluationMonitor[] listeners;
- private SentenceDetectorFactory sdFactory;
+ private final SentenceDetectorFactory sdFactory;
public SDCrossValidator(String languageCode, TrainingParameters params,
SentenceDetectorFactory sdFactory, SentenceDetectorEvaluationMonitor... listeners) {
@@ -47,39 +46,7 @@ public class SDCrossValidator {
this.listeners = listeners;
this.sdFactory = sdFactory;
}
-
- /**
- * @deprecated Use
- * {@link #SDCrossValidator(String, TrainingParameters,
- * SentenceDetectorFactory, SentenceDetectorEvaluationMonitor...)}
- * and pass in a {@link SentenceDetectorFactory}.
- */
- public SDCrossValidator(String languageCode, TrainingParameters params) {
- this(languageCode, params, new SentenceDetectorFactory(languageCode, true,
- null, null));
- }
-
- /**
- * @deprecated use
- * {@link #SDCrossValidator(String, TrainingParameters, SentenceDetectorFactory,
- * SentenceDetectorEvaluationMonitor...)}
- * instead and pass in a TrainingParameters object.
- */
- public SDCrossValidator(String languageCode, TrainingParameters params,
- SentenceDetectorEvaluationMonitor... listeners) {
- this(languageCode, params, new SentenceDetectorFactory(languageCode, true,
- null, null), listeners);
- }
-
- /**
- * @deprecated use {@link #SDCrossValidator(String, TrainingParameters,
- * SentenceDetectorFactory, SentenceDetectorEvaluationMonitor...)}
- * instead and pass in a TrainingParameters object.
- */
- public SDCrossValidator(String languageCode) {
- this(languageCode, ModelUtil.createDefaultTrainingParameters());
- }
-
+
/**
* Starts the evaluation.
*
@@ -88,7 +55,7 @@ public class SDCrossValidator {
* @param nFolds
* number of folds
*
- * @throws IOException
+ * @throws IOException Thrown if IO errors occurred during processing.
*/
public void evaluate(ObjectStream<SentenceSample> samples, int nFolds) throws IOException {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDEventStream.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDEventStream.java
index a6561431..9c02ce43 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDEventStream.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SDEventStream.java
@@ -28,13 +28,15 @@ import opennlp.tools.util.Span;
public class SDEventStream extends AbstractEventStream<SentenceSample> {
- private SDContextGenerator cg;
- private EndOfSentenceScanner scanner;
+ private final SDContextGenerator cg;
+ private final EndOfSentenceScanner scanner;
/**
* Initializes the current instance.
*
- * @param samples
+ * @param samples An {@link ObjectStream stream} of {@link SentenceSample samples}.
+ * @param cg The {@link SDContextGenerator} to be used.
+ * @param scanner The {@link EndOfSentenceScanner scanner} to be used.
*/
public SDEventStream(ObjectStream<SentenceSample> samples, SDContextGenerator cg,
EndOfSentenceScanner scanner) {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetector.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetector.java
index 01e3d99b..38cf3def 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetector.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetector.java
@@ -29,7 +29,7 @@ public interface SentenceDetector {
/**
* Sentence detect a string.
*
- * @param s The string to be sentence detected.
+ * @param s The string for which sentences shall to be detected.
* @return The String[] with the individual sentences as the array
* elements.
*/
@@ -38,9 +38,9 @@ public interface SentenceDetector {
/**
* Sentence detect a string.
*
- * @param s The string to be sentence detected.
+ * @param s The string for which sentences shall be detected.
*
- * @return The Span[] with the spans (offsets into s) for each
+ * @return The array of {@link Span spans} (offsets into {@code s}) for each
* detected sentence as the individuals array elements.
*/
Span[] sentPosDetect(String s);
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorEvaluator.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorEvaluator.java
index 3effda8b..eee3ece7 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorEvaluator.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorEvaluator.java
@@ -32,18 +32,18 @@ import opennlp.tools.util.eval.FMeasure;
*/
public class SentenceDetectorEvaluator extends Evaluator<SentenceSample> {
- private FMeasure fmeasure = new FMeasure();
+ private final FMeasure fmeasure = new FMeasure();
/**
* The {@link SentenceDetector} used to predict sentences.
*/
- private SentenceDetector sentenceDetector;
+ private final SentenceDetector sentenceDetector;
/**
* Initializes the current instance.
*
- * @param sentenceDetector
- * @param listeners evaluation sample listeners
+ * @param sentenceDetector The {@link SentenceDetector} to be used for predicting sentences.
+ * @param listeners The {@link SentenceDetectorEvaluationMonitor evaluation sample listeners}.
*/
public SentenceDetectorEvaluator(SentenceDetector sentenceDetector,
SentenceDetectorEvaluationMonitor... listeners) {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorFactory.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorFactory.java
index 54dcc648..0276f931 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorFactory.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorFactory.java
@@ -28,7 +28,7 @@ import opennlp.tools.util.InvalidFormatException;
import opennlp.tools.util.ext.ExtensionLoader;
/**
- * The factory that provides SentenceDetecor default implementations and
+ * The factory that provides {@link SentenceDetector} default implementations and
* resources
*/
public class SentenceDetectorFactory extends BaseToolFactory {
@@ -53,9 +53,10 @@ public class SentenceDetectorFactory extends BaseToolFactory {
* Creates a {@link SentenceDetectorFactory}. Use this constructor to
* programmatically create a factory.
*
- * @param languageCode
- * @param abbreviationDictionary
- * @param eosCharacters
+ * @param languageCode The ISO language code to be used for this factory.
+ * @param useTokenEnd {@code true} if {@link #TOKEN_END_PROPERTY} shall be used, {@code false} otherwise.
+ * @param abbreviationDictionary The {@link Dictionary} which holds abbreviations.
+ * @param eosCharacters The characters to be used to detect sentence endings.
*/
public SentenceDetectorFactory(String languageCode, boolean useTokenEnd,
Dictionary abbreviationDictionary, char[] eosCharacters) {
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java
index b15e08d3..b0cec962 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceDetectorME.java
@@ -60,7 +60,7 @@ public class SentenceDetectorME implements SentenceDetector {
/**
* The maximum entropy model to use to evaluate contexts.
*/
- private MaxentModel model;
+ private final MaxentModel model;
/**
* The feature context generator.
@@ -75,7 +75,7 @@ public class SentenceDetectorME implements SentenceDetector {
/**
* The list of probabilities associated with each decision.
*/
- private List<Double> sentProbs = new ArrayList<>();
+ private final List<Double> sentProbs = new ArrayList<>();
protected boolean useTokenEnd;
@@ -131,7 +131,7 @@ public class SentenceDetectorME implements SentenceDetector {
}
/**
- * Detect sentences in a String.
+ * Detect sentences in given input String.
*
* @param s The string to be processed.
*
@@ -168,10 +168,11 @@ public class SentenceDetectorME implements SentenceDetector {
* Detect the position of the first words of sentences in a String.
*
* @param s The string to be processed.
- * @return A integer array containing the positions of the end index of
+ * @return An integer array containing the positions of the end index of
* every sentence
*
*/
+ @Override
public Span[] sentPosDetect(String s) {
sentProbs.clear();
StringBuffer sb = new StringBuffer(s);
@@ -278,10 +279,11 @@ public class SentenceDetectorME implements SentenceDetector {
/**
* Returns the probabilities associated with the most recent
- * calls to sentDetect().
+ * calls to {@link SentenceDetectorME#sentDetect(String)}.
*
- * @return probability for each sentence returned for the most recent
- * call to sentDetect. If not applicable an empty array is returned.
+ * @return The probability for each sentence returned for the most recent
+ * call to {@link SentenceDetectorME#sentDetect(String)}.
+ * If not applicable, an empty array is returned.
*/
public double[] getSentenceProbabilities() {
double[] sentProbArray = new double[sentProbs.size()];
@@ -296,13 +298,13 @@ public class SentenceDetectorME implements SentenceDetector {
* trained) model from flagging obvious non-breaks as breaks based
* on some boolean determination of a break's acceptability.
*
- * <p>The implementation here always returns true, which means
+ * <p>The implementation here always returns {@link true}, which means
* that the MaxentModel's outcome is taken as is.</p>
*
* @param s the string in which the break occurred.
- * @param fromIndex the start of the segment currently being evaluated
- * @param candidateIndex the index of the candidate sentence ending
- * @return true if the break is acceptable
+ * @param fromIndex the start of the segment currently being evaluated.
+ * @param candidateIndex the index of the candidate sentence ending.
+ * @return {@link true} if the break is acceptable.
*/
protected boolean isAcceptableBreak(String s, int fromIndex, int candidateIndex) {
return true;
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSample.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSample.java
index 100f807e..e00382ba 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSample.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSample.java
@@ -17,13 +17,13 @@
package opennlp.tools.sentdetect;
-import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
+import opennlp.tools.commons.Sample;
import opennlp.tools.tokenize.Detokenizer;
import opennlp.tools.util.Span;
@@ -31,17 +31,17 @@ import opennlp.tools.util.Span;
* A {@link SentenceSample} contains a document with
* begin indexes of the individual sentences.
*/
-public class SentenceSample implements Serializable {
+public class SentenceSample implements Sample {
- private static final long serialVersionUID = -5386940708608341113L;
+ private static final long serialVersionUID = 1771522768104567531L;
private final String document;
private final List<Span> sentences;
/**
* Initializes the current instance.
*
- * @param document
- * @param sentences
+ * @param document The document represented as plain {@link CharSequence}.
+ * @param sentences One or more {@link Span spans} that represent a sentence each.
*/
public SentenceSample(CharSequence document, Span... sentences) {
this.document = document.toString();
@@ -78,19 +78,14 @@ public class SentenceSample implements Serializable {
}
/**
- * Retrieves the document.
- *
- * @return the document
+ * @return the document as a plain string.
*/
public String getDocument() {
return document;
}
/**
- * Retrieves the sentences.
- *
- * @return the begin indexes of the sentences in the document.
-
+ * @return the {@link Span spans} of the sentences in a document.
*/
public Span[] getSentences() {
return sentences.toArray(new Span[sentences.size()]);
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSampleStream.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSampleStream.java
index 10348bda..d073af2b 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSampleStream.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/SentenceSampleStream.java
@@ -28,8 +28,8 @@ import opennlp.tools.util.Span;
/**
* This class is a stream filter which reads a sentence by line samples from
- * a <code>Reader</code> and converts them into {@link SentenceSample} objects.
- * An empty line indicates the begin of a new document.
+ * an {@link ObjectStream} and converts them into {@link SentenceSample} objects.
+ * An empty line indicates the beginning of a new document.
*/
public class SentenceSampleStream extends FilterObjectStream<String, SentenceSample> {
@@ -41,6 +41,7 @@ public class SentenceSampleStream extends FilterObjectStream<String, SentenceSam
return s.replace("<LF>", "\n").replace("<CR>", "\r");
}
+ @Override
public SentenceSample read() throws IOException {
StringBuilder sentencesString = new StringBuilder();
diff --git a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/package-info.java b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/package-info.java
index d60d84fc..f8ad58b1 100644
--- a/opennlp-tools/src/main/java/opennlp/tools/sentdetect/package-info.java
+++ b/opennlp-tools/src/main/java/opennlp/tools/sentdetect/package-info.java
@@ -16,6 +16,6 @@
*/
/**
- * Package related to identifying sentece boundries.
+ * Package related to identifying sentence boundaries.
*/
package opennlp.tools.sentdetect;
diff --git a/opennlp-tools/src/test/java/opennlp/tools/postag/POSEvaluatorTest.java b/opennlp-tools/src/test/java/opennlp/tools/postag/POSEvaluatorTest.java
index b89f2014..482b4c31 100644
--- a/opennlp-tools/src/test/java/opennlp/tools/postag/POSEvaluatorTest.java
+++ b/opennlp-tools/src/test/java/opennlp/tools/postag/POSEvaluatorTest.java
@@ -85,11 +85,11 @@ public class POSEvaluatorTest {
return null;
}
- public String[] tag(String[] sentence, Object[] additionaContext) {
+ public String[] tag(String[] sentence, Object[] additionalContext) {
return tag(sentence);
}
- public Sequence[] topKSequences(String[] sentence, Object[] additionaContext) {
+ public Sequence[] topKSequences(String[] sentence, Object[] additionalContext) {
return topKSequences(sentence);
}
diff --git a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java
index ab9095ae..e959d4fc 100644
--- a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java
+++ b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/AbstractSentenceDetector.java
@@ -37,13 +37,13 @@ public abstract class AbstractSentenceDetector extends CasAnnotator_ImplBase {
protected UimaContext context;
- /**
- * The type of the sentences to be created.
- */
protected Logger logger;
protected Type containerType;
+ /**
+ * The type of the sentences to be created.
+ */
protected Type sentenceType;
private Boolean isRemoveExistingAnnotations;
diff --git a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/package.html b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/package.html
index 550112c6..f960fb81 100644
--- a/opennlp-uima/src/main/java/opennlp/uima/sentdetect/package.html
+++ b/opennlp-uima/src/main/java/opennlp/uima/sentdetect/package.html
@@ -27,6 +27,6 @@
</head>
<body bgcolor="white">
-Package related to identifying sentece boundries.
+Package related to identifying sentence boundaries.
</body>
</html>