You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nlpcraft.apache.org by se...@apache.org on 2021/09/14 16:41:49 UTC
[incubator-nlpcraft] branch NLPCRAFT-443 updated: WIP.
This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-443
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-443 by this push:
new 901187b WIP.
901187b is described below
commit 901187b2711722c4dc6bc049373fa063b00f46c3
Author: Sergey Kamov <sk...@gmail.com>
AuthorDate: Tue Sep 14 19:41:39 2021 +0300
WIP.
---
nlpcraft/src/main/resources/stopwords/stop_words.txt | 1 +
.../nlp/enrichers/stopword/NCStopWordEnricher.scala | 19 ++++++++++---------
.../enrichers/model/NCEnricherNestedModelSpec3.scala | 1 +
3 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/nlpcraft/src/main/resources/stopwords/stop_words.txt b/nlpcraft/src/main/resources/stopwords/stop_words.txt
index 3629397..d7b7409 100644
--- a/nlpcraft/src/main/resources/stopwords/stop_words.txt
+++ b/nlpcraft/src/main/resources/stopwords/stop_words.txt
@@ -63,6 +63,7 @@
# POSES list exceptions.
~may
+~no
# Postfixes list.
*ent | ~NN ~NNS ~NNP ~NNPS
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/stopword/NCStopWordEnricher.scala b/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/stopword/NCStopWordEnricher.scala
index 03e0ec9..1af22cb 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/stopword/NCStopWordEnricher.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/stopword/NCStopWordEnricher.scala
@@ -246,15 +246,6 @@ object NCStopWordEnricher extends NCProbeEnricher {
if (del.nonEmpty) {
del.foreach(t => require(t.isNlp))
- // TODO:
- logger.info(
- s"Stopwords deleted from sentence [" +
- s"srvReqId=${ns.srvReqId}, " +
- s"text=${ns.text}, " +
- s"stopWords=${del.map(p => s"${p.origText}(index=${p.wordIndexes.head})").mkString("|")}" +
- s"]"
- )
-
val delIdxs = del.flatMap(_.wordIndexes).sorted
val old = ns.tokens.clone()
@@ -273,6 +264,16 @@ object NCStopWordEnricher extends NCProbeEnricher {
t.add(n.clone(tokIdxs, wordIdxs))
})
})
+
+ // TODO:
+ logger.info(
+ s"Stopwords deleted from sentence [" +
+ s"srvReqId=${ns.srvReqId}, " +
+ s"originText=${ns.text}, " +
+ s"fixedText=${ns.tokens.map(_.origText).mkString(" ")}, " +
+ s"stopWords=${del.map(p => s"${p.origText}(index=${p.wordIndexes.head})").mkString("|")}" +
+ s"]"
+ )
}
}
diff --git a/nlpcraft/src/test/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/model/NCEnricherNestedModelSpec3.scala b/nlpcraft/src/test/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/model/NCEnricherNestedModelSpec3.scala
index 2303e30..0b10a61 100644
--- a/nlpcraft/src/test/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/model/NCEnricherNestedModelSpec3.scala
+++ b/nlpcraft/src/test/scala/org/apache/nlpcraft/probe/mgrs/nlp/enrichers/model/NCEnricherNestedModelSpec3.scala
@@ -36,6 +36,7 @@ class NCNestedTestModel3 extends NCModelAdapter("nlpcraft.nested3.test.mdl", "Ne
override def getAbstractTokens: util.Set[String] = Set("e1").asJava
override def getEnabledBuiltInTokens: util.Set[String] = Set.empty[String].asJava
+ override def getExcludedStopWords: util.Set[String] = Set("a").asJava
@NCIntent("intent=onE2 term(t1)={# == 'e2'}[12, 100]")
def onAB(): NCResult = NCResult.text("OK")