This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch scala-2.13
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/scala-2.13 by this push:
new d9f5eb6 WIP.
d9f5eb6 is described below
commit d9f5eb60293f64bcf808fa3c144db87cc11fb91f
Author: Aaron Radzinzski <[email protected]>
AuthorDate: Thu May 20 11:26:22 2021 -0700
WIP.
---
.../apache/nlpcraft/model/impl/NCTokenLogger.scala | 30 ++++++++++----------
.../nlpcraft/probe/mgrs/NCProbeVariants.scala | 33 +++++++++++++---------
2 files changed, 34 insertions(+), 29 deletions(-)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCTokenLogger.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCTokenLogger.scala
index c3a83a6..7fba066 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCTokenLogger.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/model/impl/NCTokenLogger.scala
@@ -27,6 +27,7 @@ import org.apache.nlpcraft.model.NCToken
import org.apache.nlpcraft.model.impl.NCTokenPimp._
import org.apache.nlpcraft.common.ansi.NCAnsi._
+import scala.collection.mutable.ArrayBuffer
import scala.jdk.CollectionConverters._
/**
@@ -375,7 +376,7 @@ object NCTokenLogger extends LazyLogging {
def prepareTable(toks: Seq[NCToken]): NCAsciiTable = {
val allFree = toks.forall(_.isFreeWord)
- var headers = Seq(
+ val headers = ArrayBuffer(
"idx",
"Longtext",
"lemma",
@@ -391,7 +392,7 @@ object NCTokenLogger extends LazyLogging {
if (!allFree)
headers += "token data"
- val tbl = NCAsciiTable(headers :_*)
+ val tbl = NCAsciiTable(headers.toSeq :_*)
toks.foreach(tok => {
val md = tok.getMetadata
@@ -433,19 +434,18 @@ object NCTokenLogger extends LazyLogging {
else
tok.origText
- val row =
- Seq(
- tok.index,
- origTxtStr,
- tok.lemma,
- tok.pos,
- tok.isQuoted,
- if (tok.isStopWord) s"${r("true")}" else "false",
- if (tok.isFreeWord) s"${y("true")}" else "false",
- s"[${tok.wordIndexes.mkString(",")}]",
- tok.isDirect,
- tok.sparsity
- )
+ val row = Seq(
+ tok.index,
+ origTxtStr,
+ tok.lemma,
+ tok.pos,
+ tok.isQuoted,
+ if (tok.isStopWord) s"${r("true")}" else "false",
+ if (tok.isFreeWord) s"${y("true")}" else "false",
+ s"[${tok.wordIndexes.mkString(",")}]",
+ tok.isDirect,
+ tok.sparsity
+ )
if (allFree)
tbl += (row :_*)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/NCProbeVariants.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/NCProbeVariants.scala
index dcba4da..e682268 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/NCProbeVariants.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/probe/mgrs/NCProbeVariants.scala
@@ -19,14 +19,14 @@ package org.apache.nlpcraft.probe.mgrs
import org.apache.nlpcraft.common.nlp.{NCNlpSentence, NCNlpSentenceNote,
NCNlpSentenceToken}
import org.apache.nlpcraft.common.nlp.pos.NCPennTreebank
-import org.apache.nlpcraft.common.{NCE, TOK_META_ALIASES_KEY}
+import org.apache.nlpcraft.common._
import org.apache.nlpcraft.model.impl.{NCTokenImpl, NCTokenLogger,
NCVariantImpl}
-import org.apache.nlpcraft.model.{NCToken, NCVariant}
+import org.apache.nlpcraft.model._
-import java.io.{Serializable => JSerializable}
import java.util
import java.util.Collections.singletonList
-import scala.collection.{Seq, mutable}
+import scala.collection._
+import scala.collection.mutable.ArrayBuffer
import scala.jdk.CollectionConverters._
/**
@@ -34,13 +34,13 @@ import scala.jdk.CollectionConverters._
*/
object NCProbeVariants {
private final val IDX: java.lang.Integer = -1
- private final val IDXS: JSerializable =
singletonList(IDX).asInstanceOf[JSerializable]
- private final val IDXS2: JSerializable =
singletonList(singletonList(IDX)).asInstanceOf[JSerializable]
+ private final val IDXS: java.io.Serializable =
singletonList(IDX).asInstanceOf[java.io.Serializable]
+ private final val IDXS2: java.io.Serializable =
singletonList(singletonList(IDX)).asInstanceOf[java.io.Serializable]
case class Key(id: String, from: Int, to: Int)
object Key {
- def apply(m: util.HashMap[String, JSerializable]): Key = {
+ def apply(m: util.HashMap[String, java.io.Serializable]): Key = {
def get[T](name: String): T = m.get(name).asInstanceOf[T]
Key(get("id"), get("startcharindex"), get("endcharindex"))
@@ -103,7 +103,7 @@ object NCProbeVariants {
artTok.add(mkNote(toks))
if (key.id != "nlpcraft:nlp") {
- var ps = mkNlpNoteParams()
+ val ps = mkNlpNoteParams()
delNote.noteType match {
case "nlpcraft:relation" |
"nlpcraft:limit" => ps += "indexes" -> IDXS
@@ -111,7 +111,7 @@ object NCProbeVariants {
case _ => // No-op.
}
- artTok.add(delNote.clone(ps :_*))
+ artTok.add(delNote.clone(ps.toSeq :_*))
}
Some(artTok)
@@ -125,8 +125,8 @@ object NCProbeVariants {
*
* @return
*/
- private def mkNlpNoteParams(): Seq[(String, JSerializable)] =
- Seq("tokMinIndex" -> IDX, "tokMaxIndex" -> IDX)
+ private def mkNlpNoteParams(): ArrayBuffer[(String, java.io.Serializable)]
=
+ ArrayBuffer("tokMinIndex" -> IDX, "tokMaxIndex" -> IDX)
/**
*
@@ -175,7 +175,12 @@ object NCProbeVariants {
"swear" -> exists(_.isSwearWord)
)
- NCNlpSentenceNote(Seq(IDX.intValue()),
srcToks.flatMap(_.wordIndexes).distinct.sorted, "nlpcraft:nlp", params: _*)
+ NCNlpSentenceNote(
+ Seq(IDX.intValue()),
+ srcToks.flatMap(_.wordIndexes).distinct.sorted,
+ "nlpcraft:nlp",
+ params: _*)
+
}
/**
@@ -203,7 +208,7 @@ object NCProbeVariants {
val keys2Toks = toks.map(t => Key(t) -> t).toMap
def process(tok: NCTokenImpl, tokNlp: NCNlpSentenceToken):
Unit = {
- val optList: Option[util.List[util.HashMap[String,
JSerializable]]] =
+ val optList: Option[util.List[util.HashMap[String,
java.io.Serializable]]] =
tokNlp.find(_.isUser) match {
case Some(u) => u.dataOpt("parts")
case None => None
@@ -234,7 +239,7 @@ object NCProbeVariants {
case Some(nlpNote) =>
val artTok =
NCNlpSentenceToken(IDX)
-
artTok.add(nlpNote.clone(mkNlpNoteParams(): _*))
+
artTok.add(nlpNote.clone(mkNlpNoteParams().toSeq: _*))
mkToken(artTok)
case None =>
