This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-468
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-468 by this push:
new 13337bb WIP.
13337bb is described below
commit 13337bbf0fb961355a1e4b9c6b4350684e9cbbec
Author: Sergey Kamov <[email protected]>
AuthorDate: Tue Oct 12 20:41:28 2021 +0300
WIP.
---
.../model/components/detectors/NCDefaultStopWordsDetector.java | 3 +++
.../model/components/detectors/NCDefaultSwearWordsDetector.java | 3 +++
.../nlpcraft/model/components/detectors/NCFileWordsDetector.java | 5 +++++
.../nlpcraft/model/components/ner/opennlp/NCOpenNlpNerParser.java | 4 +++-
.../nlpcraft/model/components/ner/synonyms/NCSynonymsNerParser.java | 4 +++-
.../components/ner/synonyms/builders/NCSynonymsNerParserBuilder.java | 3 +++
.../nlpcraft/model/components/tokenizer/NCOpenNlpTokenizer.java | 4 +++-
7 files changed, 23 insertions(+), 3 deletions(-)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultStopWordsDetector.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultStopWordsDetector.java
index 5ab3c26..6fe2ca3 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultStopWordsDetector.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultStopWordsDetector.java
@@ -23,6 +23,9 @@ import org.apache.nlpcraft.model.nlp.NCNlpWordsDetector;
import java.util.Collections;
import java.util.List;
+/**
+ * Stopwords detector default implementation.
+ */
public class NCDefaultStopWordsDetector implements NCNlpWordsDetector {
@Override
public List<NCNlpWord> detect(List<NCNlpWord> sen) {
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultSwearWordsDetector.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultSwearWordsDetector.java
index 44abf59..4603e20 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultSwearWordsDetector.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCDefaultSwearWordsDetector.java
@@ -23,6 +23,9 @@ import org.apache.nlpcraft.model.nlp.NCNlpWordsDetector;
import java.util.Collections;
import java.util.List;
+/**
+ * Swearwords detector default implementation.
+ */
public class NCDefaultSwearWordsDetector implements NCNlpWordsDetector {
@Override
public List<NCNlpWord> detect(List<NCNlpWord> sen) {
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCFileWordsDetector.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCFileWordsDetector.java
index 53765f3..6d8144d 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCFileWordsDetector.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCFileWordsDetector.java
@@ -25,6 +25,11 @@ import java.net.URL;
import java.util.Collections;
import java.util.List;
+/**
+ * TODO: do we need it?
+ * File based detector default implementation.
+ * Helper.
+ */
public class NCFileWordsDetector implements NCNlpWordsDetector {
public NCFileWordsDetector(File data) {
}
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/opennlp/NCOpenNlpNerParser.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/opennlp/NCOpenNlpNerParser.java
index e030b83..fa11313 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/opennlp/NCOpenNlpNerParser.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/opennlp/NCOpenNlpNerParser.java
@@ -25,7 +25,9 @@ import org.apache.nlpcraft.model.nlp.NCNlpWord;
import java.util.List;
-// Implementation by default for opennlp NERs. Stanford in another module.
+/**
+ * NERs implementation based on OpenNlp NERs.
+ */
public class NCOpenNlpNerParser implements NCNlpNerParser {
@Override
public List<NCNlpToken> parse(NCRequest req, NCModelConfig cfg,
List<NCNlpWord> words, List<NCNlpToken> elements) {
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/NCSynonymsNerParser.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/NCSynonymsNerParser.java
index ac83b7d..9c05476 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/NCSynonymsNerParser.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/NCSynonymsNerParser.java
@@ -24,7 +24,9 @@ import java.util.Collections;
import java.util.Map;
import java.util.Set;
-// TODO: maybe class.
+/**
+ * Nlpcraft synonyms based NER provider.
+ */
public interface NCSynonymsNerParser extends NCNlpNerParser {
/**
* Default value for {@link #getMaxElementSynonyms()} method.
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/builders/NCSynonymsNerParserBuilder.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/builders/NCSynonymsNerParserBuilder.java
index a5f54ae..a285a66 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/builders/NCSynonymsNerParserBuilder.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/ner/synonyms/builders/NCSynonymsNerParserBuilder.java
@@ -24,6 +24,9 @@ import java.io.File;
import java.util.List;
import java.util.Map;
+/**
+ * Nlpcraft synonyms based NER provider builder.
+ */
public class NCSynonymsNerParserBuilder {
public NCSynonymsNerParserBuilder withMaxElementSynonyms(int
maxElementSynonyms) { return null; }
public NCSynonymsNerParserBuilder withMaxTotalSynonyms(int
maxTotalSynonyms) {
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/tokenizer/NCOpenNlpTokenizer.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/tokenizer/NCOpenNlpTokenizer.java
index 43df0e4..bafc4be 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/tokenizer/NCOpenNlpTokenizer.java
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/tokenizer/NCOpenNlpTokenizer.java
@@ -23,7 +23,9 @@ import org.apache.nlpcraft.model.nlp.NCNlpWord;
import java.util.List;
-// Implementation by default. Stanford in another module. Can be provided by
user.
+/**
+ * Defaгде tokenizer based on OpenNlp.
+ */
public class NCOpenNlpTokenizer implements NCNlpTokenizer {
@Override
public List<NCNlpWord> tokenize(NCRequest req) {
