[incubator-nlpcraft] branch NLPCRAFT-469 updated: WIP.

[sergeykamov]

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

sergeykamov pushed a commit to branch NLPCRAFT-469
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git


The following commit(s) were added to refs/heads/NLPCRAFT-469 by this push:
     new cbd72d8  WIP.
cbd72d8 is described below

commit cbd72d86a9202eb36cc45186ddd8a19763f94fea
Author: Sergey Kamov <skhdlem...@gmail.com>
AuthorDate: Tue Dec 21 18:31:31 2021 +0300

    WIP.
---
 .../internal/nlp/token/parser/opennlp/NCOpenNlpTokenParser.java     | 1 -
 .../nlp/token/parser/opennlp/impl/NCEnStopWordsFinderImpl.scala     | 6 +++---
 .../internal/nlp/token/parser/opennlp/impl/NCOpenNlpImpl.scala      | 2 +-
 .../src/main/scala/org/apache/nlpcraft/internal/util/NCUtils.scala  | 1 +
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCOpenNlpTokenParser.java
 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCOpenNlpTokenParser.java
index 86d25be..7e6a639 100644
--- 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCOpenNlpTokenParser.java
+++ 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCOpenNlpTokenParser.java
@@ -26,7 +26,6 @@ import 
org.apache.nlpcraft.internal.nlp.token.parser.opennlp.impl.NCOpenNlpImpl;
 import java.io.File;
 import java.util.List;
 import java.util.Objects;
-import java.util.Set;
 
 /*
  * Models can be downloaded from the following resources:
diff --git 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinderImpl.scala
 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinderImpl.scala
index 68f9b5e..b7fb2f3 100644
--- 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinderImpl.scala
+++ 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinderImpl.scala
@@ -37,7 +37,7 @@ object NCEnStopWordsFinderImpl:
     type Word = String
 
     /** All POSes set. http://www.clips.ua.ac.be/pages/mbsp-tags */
-    private final val POSES = Set(
+    private val POSES = Set(
         "CC",
         "CD",
         "DT",
@@ -82,7 +82,7 @@ object NCEnStopWordsFinderImpl:
         "--" // Synthetic POS.
     )
 
-    private final val STOP_BEFORE_STOP: Seq[Word] = Seq("DT", "PRP", "PRP$", 
"WDT", "WP", "WP$", "WRB")
+    private val STOP_BEFORE_STOP: Seq[Word] = Seq("DT", "PRP", "PRP$", "WDT", 
"WP", "WP$", "WRB")
 
     private val Q_POS = Set("``", "''")
 
@@ -451,7 +451,7 @@ class NCEnStopWordsFinderImpl(addStopWords: JSet[String], 
exclStopWords: JSet[St
       * @param toks
       */
     override def find(toks: JList[NCToken]): JList[NCToken] =
-        // TODO: check ? stop clear?
+        // TODO: check started? clear on stop?
         if (percents == null)
             throw new IllegalStateException(s"${this.getClass.getName} is not 
started.")
 
diff --git 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCOpenNlpImpl.scala
 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCOpenNlpImpl.scala
index 2eb8124..0f54e7e 100644
--- 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCOpenNlpImpl.scala
+++ 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCOpenNlpImpl.scala
@@ -90,7 +90,7 @@ class NCOpenNlpImpl(tokMdlIn: InputStream, posMdlIn: 
InputStream, lemmaDicIn: In
       * @return
       */
     override def parse(req: NCRequest): JList[NCToken] =
-        // TODO: check ? stop clear?
+        // TODO: check started? clear on stop?
         if (tokenizer == null)
             throw new IllegalStateException(s"${this.getClass.getName} is not 
started.")
 
diff --git 
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/util/NCUtils.scala 
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/util/NCUtils.scala
index 1784da9..9c13081 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/util/NCUtils.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/util/NCUtils.scala
@@ -927,6 +927,7 @@ object NCUtils extends LazyLogging:
         catch
             case e: IOException => throw new NCException(s"Failed to read 
stream.", e)
 
+    // TODO: is it suitable place for methods related to tokens manipulations?
     /**
       * Gets all sequential permutations of tokens in this NLP sentence.
       *