[incubator-nlpcraft] branch NLPCRAFT-468 updated: WIP.

[sergeykamov]

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 a6ce6e2  WIP.
a6ce6e2 is described below

commit a6ce6e2ac8f7dcb6c69ada3f6252ebbf4ad233d3
Author: Sergey Kamov <skhdlem...@gmail.com>
AuthorDate: Tue Oct 12 21:01:01 2021 +0300

    WIP.
---
 ...rdsDetector.java => NCListBasedWordsDetector.java} | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

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/NCListBasedWordsDetector.java
similarity index 72%
rename from 
nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCFileWordsDetector.java
rename to 
nlpcraft/src/main/scala/org/apache/nlpcraft/model/components/detectors/NCListBasedWordsDetector.java
index 6d8144d..3af4512 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/NCListBasedWordsDetector.java
@@ -20,25 +20,24 @@ package org.apache.nlpcraft.model.components.detectors;
 import org.apache.nlpcraft.model.nlp.NCNlpWord;
 import org.apache.nlpcraft.model.nlp.NCNlpWordsDetector;
 
-import java.io.File;
-import java.net.URL;
 import java.util.Collections;
 import java.util.List;
+import java.util.Set;
+import java.util.stream.Collectors;
 
 /**
- * TODO: do we need it?
- * File based detector default implementation.
- * Helper.
+ *
  */
-public class NCFileWordsDetector implements NCNlpWordsDetector  {
-    public NCFileWordsDetector(File data) {
-    }
+public class NCListBasedWordsDetector implements NCNlpWordsDetector  {
+    private final Set<String> words;
 
-    public NCFileWordsDetector(URL data) {
+    public NCListBasedWordsDetector(Set<String> words) {
+        this.words = words == null ? Collections.emptySet() : words;
     }
 
     @Override
     public List<NCNlpWord> detect(List<NCNlpWord> sen) {
-        return Collections.emptyList();
+        // TODO: stems, normal form.
+        return sen.stream().filter(p -> 
words.contains(p.getWord())).collect(Collectors.toList());
     }
 }