[incubator-nlpcraft] branch NLPCRAFT-483-1 updated: WIP.

[sergeykamov]

This is an automated email from the ASF dual-hosted git repository.

sergeykamov pushed a commit to branch NLPCRAFT-483-1
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git


The following commit(s) were added to refs/heads/NLPCRAFT-483-1 by this push:
     new bcd84ed  WIP.
bcd84ed is described below

commit bcd84ed0f442b2ab95504d9601d00eae9b831ca4
Author: Sergey Kamov <skhdlem...@gmail.com>
AuthorDate: Wed Mar 2 22:28:59 2022 +0300

    WIP.
---
 .../apache/nlpcraft/NCModelPipelineBuilder.java    | 27 ++++++++++++++--------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelPipelineBuilder.java 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelPipelineBuilder.java
index 02ac728..05f0110 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelPipelineBuilder.java
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelPipelineBuilder.java
@@ -71,7 +71,8 @@ public class NCModelPipelineBuilder {
     }
 
     /**
-     *
+     * TODO:
+     * EN Nlp component set. Note it used OpenNLP token parser implementation.
      * @param lang
      * @param entParsers
      */
@@ -81,19 +82,27 @@ public class NCModelPipelineBuilder {
         if (entParsers.isEmpty())
             throw new IllegalArgumentException("At least one entity parser 
must be defined.");
 
-        tokParser = new NCENOpenNLPTokenParser();
+        switch (lang) {
+            case EN:
+                tokParser = new NCENOpenNLPTokenParser();
 
-        tokEnrichers.add(new NCENOpenNlpLemmaPosTokenEnricher());
-        tokEnrichers.add(new NCENStopWordsTokenEnricher());
-        tokEnrichers.add(new 
NСENSwearWordsTokenEnricher(NCResourceReader.getPath("badfilter/swear_words.txt")));
-        tokEnrichers.add(new NCENQuotesTokenEnricher());
-        tokEnrichers.add(new NCENDictionaryTokenEnricher());
-        tokEnrichers.add(new NCENBracketsTokenEnricher());
+                tokEnrichers.add(new NCENOpenNlpLemmaPosTokenEnricher());
+                tokEnrichers.add(new NCENStopWordsTokenEnricher());
+                tokEnrichers.add(new 
NСENSwearWordsTokenEnricher(NCResourceReader.getPath("badfilter/swear_words.txt")));
+                tokEnrichers.add(new NCENQuotesTokenEnricher());
+                tokEnrichers.add(new NCENDictionaryTokenEnricher());
+                tokEnrichers.add(new NCENBracketsTokenEnricher());
+
+                this.entParsers.addAll(entParsers);
+            default:
+                throw new IllegalArgumentException("Unsupported language: " + 
lang);
+        }
 
-        this.entParsers.addAll(entParsers);
     }
 
     /**
+     * TODO:
+     * EN Nlp component set. Note it used OpenNLP token parser implementation.
      *
      * @param lang
      * @param entParsers