This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-471
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-471 by this push:
new 9d72903 WIP.
9d72903 is described below
commit 9d72903a925a6e1340b1d4246359d20320db8b52
Author: Sergey Kamov <[email protected]>
AuthorDate: Tue Dec 28 19:33:48 2021 +0300
WIP.
---
.../parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala | 12 ++++++------
.../internal/nlp/token/enricher/impl/NCEnQuotesImpl.scala | 2 +-
.../nlp/token/parser/opennlp/impl/NCEnOpenNlpImpl.scala | 4 ++--
.../nlp/token/parser/opennlp/impl/NCEnStopWordsFinder.scala | 2 +-
.../scala/org/apache/nlpcraft/internal/util/NCUtils.scala | 2 --
5 files changed, 10 insertions(+), 12 deletions(-)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
index 95e5ecb..0edfc2b 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
@@ -26,6 +26,7 @@ import org.apache.nlpcraft.internal.util.NCUtils
import java.io.*
import java.util
import java.util.{Optional, List as JList, Map as JMap}
+import scala.Option.*
import scala.concurrent.ExecutionContext
import scala.jdk.CollectionConverters.*
import scala.language.postfixOps
@@ -71,17 +72,16 @@ class NCOpenNlpEntityParserImpl(is: InputStream, res:
String) extends NCEntityPa
val i1 = calcIndex(_.start)
lazy val i2 = calcIndex(_.end)
- NCUtils.getOpt(
- i1 != -1 && i2 != -1,
+ Option.when(i1 != -1 && i2 != -1)(
new NCPropertyMapAdapter with NCEntity {
put(s"opennlp:${h.name}:probability", h.probability)
-
+
override def getTokens: JList[NCToken] =
- toksIdxs.flatMap { case (t, idx) => if idx >= i1 &&
idx <= i2 then Some(t) else None }.asJava
+ toksIdxs.flatMap { case (t, idx) => Option.when(idx >=
i1 && idx <= i2)(t) }.asJava
override def getRequestId: String = req.getRequestId
override def getId: String = s"opennlp:${h.name}"
override def getIndex: Int = 0 // TODO:
override def getGuid: String = NCUtils.genUUID().toString
- }
- )
+ }
+ )
).toSeq.asJava
\ No newline at end of file
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/enricher/impl/NCEnQuotesImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/enricher/impl/NCEnQuotesImpl.scala
index e37dce4..d3ffb00 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/enricher/impl/NCEnQuotesImpl.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/enricher/impl/NCEnQuotesImpl.scala
@@ -46,7 +46,7 @@ class NCEnQuotesImpl extends NCTokenEnricher with LazyLogging:
if quotes.nonEmpty && quotes.size % 2 == 0 then
val m = toksSeq.zipWithIndex.toMap
val pairs = quotes.zipWithIndex.drop(1).flatMap {
- (t, idx) => if idx % 2 != 0 then Some(m(t) -> m(quotes(idx -
1))) else None
+ (t, idx) => Option.when(idx % 2 != 0)(m(t) -> m(quotes(idx -
1)))
}
toksSeq.zipWithIndex.foreach { (tok, idx) =>
tok.put("quoted:en", pairs.exists { case (from, to) => from >
idx && to < idx })
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnOpenNlpImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnOpenNlpImpl.scala
index 5f6483b..9e4c712 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnOpenNlpImpl.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnOpenNlpImpl.scala
@@ -142,7 +142,7 @@ class NCEnOpenNlpImpl(
// Valid POS list:
https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html
val suspIdxs = lemmas.zip(posTags).zipWithIndex.flatMap {
// "0" is flag that lemma cannot be obtained for some reasons.
- case ((lemma, pos), i) => if lemma == "O" && pos == "NN" then
Some(i) else None
+ case ((lemma, pos), i) => Option.when(lemma == "O" && pos ==
"NN")(i)
}
if suspIdxs.nonEmpty then
@@ -150,7 +150,7 @@ class NCEnOpenNlpImpl(
lemmatize(suspIdxs.map(i => words(i)).toArray,
suspIdxs.map(_ => "NNN").toArray).
zipWithIndex.
flatMap {
- (lemma, i) => if lemma != "0" then Some(suspIdxs(i) ->
lemma) else None
+ (lemma, i) => Option.when(lemma != "0")(suspIdxs(i) ->
lemma)
}.toMap
lemmas = lemmas.zipWithIndex.map {
(lemma, idx) => fixes.getOrElse(idx, lemma)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinder.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinder.scala
index 6ba39f4..278f560 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinder.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/impl/NCEnStopWordsFinder.scala
@@ -543,7 +543,7 @@ private[impl] class NCEnStopWordsFinder(addStems:
Set[String], exclStems: Set[St
if quotes.nonEmpty then
val m = toks.zipWithIndex.toMap
val pairs = quotes.zipWithIndex.drop(1).flatMap {
- (t, idx) => if idx % 2 != 0 then Some(m(t) -> m(quotes(idx -
1))) else None
+ (t, idx) => Option.when(idx % 2 != 0)(m(t) -> m(quotes(idx -
1)))
}
stops --= stops.filter(t => pairs.exists { (from, to) =>
val idx = m(t)
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 63b9985..77bb9d7 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
@@ -933,8 +933,6 @@ object NCUtils extends LazyLogging:
* @return
*/
def genUUID(): UUID = UUID.randomUUID()
-
- def getOpt[T](cond: Boolean, make: => T): Option[T] = if (cond) Some(make)
else None
/**
* Gets all sequential permutations of tokens in this NLP sentence.
