This is an automated email from the ASF dual-hosted git repository.
sergeykamov pushed a commit to branch NLPCRAFT-472
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-472 by this push:
new c8bb1b2 WIP.
c8bb1b2 is described below
commit c8bb1b25a74d398274ab302c08ebc90d827f9dd6
Author: Sergey Kamov <skhdlem...@gmail.com>
AuthorDate: Wed Jan 12 11:22:02 2022 +0300
WIP.
---
.../nlp/token/parser/stanford/NCStanfordTokenParser.java | 2 --
.../token/parser/stanford/NCStanfordTokenParserSpec.scala | 4 ++--
nlpcraft/src/main/scala/org/apache/nlpcraft/NCEntity.java | 2 --
nlpcraft/src/main/scala/org/apache/nlpcraft/NCModel.java | 2 --
.../src/main/scala/org/apache/nlpcraft/NCModelClient.java | 1 -
.../org/apache/nlpcraft/internal/NCPipelineProcessor.scala | 6 +++---
.../org/apache/nlpcraft/internal/ascii/NCAsciiTable.scala | 2 +-
.../parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala | 4 ++--
.../nlp/token/enricher/en/impl/NCStopWordsImpl.scala | 12 ++++++------
.../apache/nlpcraft/internal/NCPipelineProcessorSpec.scala | 2 +-
.../nlp/entity/parser/nlp/NCNlpEntityParserSpec.scala | 2 +-
.../entity/parser/opennlp/NCOpenNlpEntityParserSpec.scala | 2 +-
.../parser/semantic/NCSemanticEntityParserJsonSpec.scala | 2 +-
.../entity/parser/semantic/NCSemanticEntityParserSpec.scala | 10 +++++-----
.../nlp/token/parser/opennlp/NCOpenNlpTokenParserSpec.scala | 8 ++++----
15 files changed, 27 insertions(+), 34 deletions(-)
diff --git
a/nlpcraft-stanford/src/main/java/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParser.java
b/nlpcraft-stanford/src/main/java/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParser.java
index 0b9ebf5..6896c8b 100644
---
a/nlpcraft-stanford/src/main/java/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParser.java
+++
b/nlpcraft-stanford/src/main/java/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParser.java
@@ -18,8 +18,6 @@
package org.apache.nlpcraft.nlp.token.parser.stanford;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
-import org.apache.nlpcraft.NCException;
-import org.apache.nlpcraft.NCModelConfig;
import org.apache.nlpcraft.NCToken;
import org.apache.nlpcraft.NCTokenParser;
import org.apache.nlpcraft.nlp.token.parser.stanford.impl.*;
diff --git
a/nlpcraft-stanford/src/test/scala/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParserSpec.scala
b/nlpcraft-stanford/src/test/scala/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParserSpec.scala
index 24fd34f..77ad649 100644
---
a/nlpcraft-stanford/src/test/scala/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParserSpec.scala
+++
b/nlpcraft-stanford/src/test/scala/org/apache/nlpcraft/nlp/token/parser/stanford/NCStanfordTokenParserSpec.scala
@@ -34,9 +34,9 @@ class NCStanfordTokenParserSpec:
val toks =
NCStanfordTestConfig.EN_PIPELINE.getTokenParser.tokenize("I had a
lunch with brand names 'AAA'").asScala.toSeq
- require(toks.length > 1)
+ require(toks.sizeIs > 1)
NCTestUtils.printTokens(toks)
val words = toks.map(_.getText)
- require(toks.map(_.getPos).distinct.size > 1)
+ require(toks.map(_.getPos).distinct.sizeIs > 1)
require(toks.map(_.getLemma).zip(words).exists {_ != _})
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCEntity.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCEntity.java
index 0b2bd14..ca746bb 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCEntity.java
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCEntity.java
@@ -17,8 +17,6 @@
package org.apache.nlpcraft;
-import org.apache.nlpcraft.internal.util.NCUtils;
-
import java.util.List;
/**
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModel.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModel.java
index cd82e99..56990e5 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModel.java
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModel.java
@@ -17,8 +17,6 @@
package org.apache.nlpcraft;
-import java.util.List;
-
/**
*
*/
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelClient.java
b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelClient.java
index 79c41cf..dbfa8f7 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelClient.java
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/NCModelClient.java
@@ -20,7 +20,6 @@ package org.apache.nlpcraft;
import org.apache.nlpcraft.internal.NCModelClientImpl;
import java.util.Map;
-import java.util.List;
import java.util.concurrent.*;
/**
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/NCPipelineProcessor.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/NCPipelineProcessor.scala
index a523487..494e024 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/NCPipelineProcessor.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/NCPipelineProcessor.scala
@@ -18,8 +18,8 @@
package org.apache.nlpcraft.internal
import com.typesafe.scalalogging.LazyLogging
-import org.apache.nlpcraft.{NCTokenEnricher, *}
import org.apache.nlpcraft.internal.util.NCUtils
+import org.apache.nlpcraft.*
import java.util
import java.util.concurrent.*
@@ -38,7 +38,7 @@ object NCPipelineProcessor {
case class VariantsHolder(request: NCRequest, variants: Seq[NCVariant],
checkCancel: () => Unit)
}
-import NCPipelineProcessor._
+import org.apache.nlpcraft.internal.NCPipelineProcessor.*
/**
*
@@ -130,7 +130,7 @@ class NCPipelineProcessor(mdl: NCModel) extends LazyLogging
:
// Looks at each token.
map(t => t.getIndex -> entities.filter(_.getTokens.contains(t))).
// Collects all overlapped entities.
- map { case (_, ents) => if (ents.size > 1) ents.toSet else
Set.empty }.filter(_.nonEmpty).toSeq
+ map { case (_, ents) => if (ents.sizeIs > 1) ents.toSet else
Set.empty }.filter(_.nonEmpty).toSeq
val dels =
NCSentenceHelper.findCombinations(overEntities.map(_.asJava).asJava,
pool).asScala.map(_.asScala)
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/ascii/NCAsciiTable.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/ascii/NCAsciiTable.scala
index 4a28a42..c510651 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/ascii/NCAsciiTable.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/ascii/NCAsciiTable.scala
@@ -559,7 +559,7 @@ class NCAsciiTable:
*
* @param header
*/
- def print(header: String): Unit = println(mkLogString(Some(header)))
+ def print(header: String): Unit = println(mkLogString(Option(header)))
/**
* Renders this table to log as trace.
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
index 1fa9f28..eef48cc 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/impl/NCOpenNlpEntityParserImpl.scala
@@ -71,7 +71,7 @@ class NCOpenNlpEntityParserImpl(resources: JList[String])
extends NCEntityParser
val toks = toksList.asScala
val txtArr = toks.map(_.getText).toArray
- finders.flatMap(find(_, txtArr)).flatMap(h =>
+ finders.flatMap(find(_, txtArr)).flatMap(h => {
def calcIndex(getHolderIndex: Holder => Int): Int =
toks.find(_.getIndex == getHolderIndex(h)) match
case Some(t) => t.getIndex
@@ -89,4 +89,4 @@ class NCOpenNlpEntityParserImpl(resources: JList[String])
extends NCEntityParser
override val getRequestId: String = req.getRequestId
override val getId: String = s"opennlp:${h.name}"
)
- ).asJava
\ No newline at end of file
+ }).asJava
\ No newline at end of file
diff --git
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCStopWordsImpl.scala
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCStopWordsImpl.scala
index ec87e3f..e1915f0 100644
---
a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCStopWordsImpl.scala
+++
b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCStopWordsImpl.scala
@@ -206,7 +206,7 @@ class NCStopWordsImpl(addStopsSet: JSet[String],
exclStopsSet: JSet[String]) ext
def matches(toks: Seq[NCToken]): Boolean =
val posOpt = toks.size match
case 0 => throw new AssertionError(s"Unexpected empty tokens.")
- case 1 => Some(toks.head.getPos)
+ case 1 => Option(toks.head.getPos)
case _ => None
// Hash access.
@@ -237,9 +237,9 @@ class NCStopWordsImpl(addStopsSet: JSet[String],
exclStopsSet: JSet[String]) ext
def permutations(toks: Seq[NCToken]): Seq[Seq[NCToken]] =
def multiple(seq: Seq[Seq[Option[NCToken]]], t: NCToken):
Seq[Seq[Option[NCToken]]] =
if seq.isEmpty then
- if isStopWord(t) then IndexedSeq(IndexedSeq(Some(t)),
IndexedSeq(None)) else IndexedSeq(IndexedSeq(Some(t)))
+ if isStopWord(t) then IndexedSeq(IndexedSeq(Option(t)),
IndexedSeq(None)) else IndexedSeq(IndexedSeq(Option(t)))
else
- (for (subSeq <- seq) yield subSeq :+ Some(t)) ++ (if
isStopWord(t) then for (subSeq <- seq) yield subSeq :+ None else Seq.empty)
+ (for (subSeq <- seq) yield subSeq :+ Option(t)) ++ (if
isStopWord(t) then for (subSeq <- seq) yield subSeq :+ None else Seq.empty)
var res: Seq[Seq[Option[NCToken]]] = Seq.empty
for (t <- toks) res = multiple(res, t)
@@ -295,9 +295,9 @@ class NCStopWordsImpl(addStopsSet: JSet[String],
exclStopsSet: JSet[String]) ext
val dups = addStems.intersect(exclStems)
if dups.nonEmpty then
- throw new NCException(s"Duplicate stems detected between
additional and excluded stopwords [" +
- s"dups=${dups.mkString(",")}" + // TODO: error texts.
- s"]")
+ throw new NCException(
+ s"Duplicate stems detected between additional and excluded
stopwords [dups=${dups.mkString(",")}]"
+ )
percents = PERCENTS.map(stem)
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/internal/NCPipelineProcessorSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/internal/NCPipelineProcessorSpec.scala
index 177e079..762bcb9 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/internal/NCPipelineProcessorSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/internal/NCPipelineProcessorSpec.scala
@@ -53,7 +53,7 @@ class NCPipelineProcessorSpec:
println(s"Variant: $idx")
NCTestUtils.printEntities(txt, v.getEntities.asScala.toSeq)
- require(res.variants.size == variantCnt)
+ require(res.variants.sizeIs == variantCnt)
test("t1 t2", 4, NCSemanticTestElement("t1", "t2"),
NCSemanticTestElement("t2", "t1"))
test("t1 t2", 2, NCSemanticTestElement("t1", "t2"),
NCSemanticTestElement("t2"))
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/nlp/NCNlpEntityParserSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/nlp/NCNlpEntityParserSpec.scala
index b14e90d..ea5caf9 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/nlp/NCNlpEntityParserSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/nlp/NCNlpEntityParserSpec.scala
@@ -43,7 +43,7 @@ class NCNlpEntityParserSpec:
NCTestUtils.printEntities(req.txt, entities)
- require(entities.size == toks.size())
+ require(entities.sizeIs == toks.size())
entities.zipWithIndex.foreach { (ent, idx) =>
require(ent.getTokens.size() == 1)
require(ent.getTokens.get(0) == toks.get(idx))
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/NCOpenNlpEntityParserSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/NCOpenNlpEntityParserSpec.scala
index d9f0035..0f37bb6 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/NCOpenNlpEntityParserSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/opennlp/NCOpenNlpEntityParserSpec.scala
@@ -51,7 +51,7 @@ class NCOpenNlpEntityParserSpec:
NCTestUtils.printEntities(txt, ents)
- require(ents.size == 1)
+ require(ents.sizeIs == 1)
require(ents.exists(_.getOpt(s"opennlp:$expected:probability").isPresent))
@Test
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserJsonSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserJsonSpec.scala
index bffef2c..560ba45 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserJsonSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserJsonSpec.scala
@@ -64,5 +64,5 @@ class NCSemanticEntityParserJsonSpec:
"Ping me in 3 minutes tomorrow",
"x:alarm",
// File contains these data for element.
- elemData = Some(Map("testKey" -> "testValue"))
+ elemData = Option(Map("testKey" -> "testValue"))
)
\ No newline at end of file
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserSpec.scala
index 93490eb..28fa49a 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/entity/parser/semantic/NCSemanticEntityParserSpec.scala
@@ -104,7 +104,7 @@ class NCSemanticEntityParserSpec:
val ents = parser.parse(req, NCTestConfig.CFG, toks).asScala.toSeq
NCTestUtils.printEntities(txt, ents)
- require(ents.size == 1)
+ require(ents.sizeIs == 1)
val e = ents.head
require(e.getId == id)
@@ -132,7 +132,7 @@ class NCSemanticEntityParserSpec:
val ents = parser.parse(req, NCTestConfig.CFG, toks).asScala.toSeq
NCTestUtils.printEntities(txt, ents)
- require(ents.size == ids.size)
+ require(ents.sizeIs == ids.size)
ents.map(_.getId).sorted.zip(ids.sorted).foreach { case (eId, id) =>
require(eId == id) }
@Test
@@ -143,9 +143,9 @@ class NCSemanticEntityParserSpec:
check("the t2", "t2")
check("t3 t3", "t3")
check("t3 the t3", "t3") // With stopword inside.
- check("value4", "t4", value = Some("value4"))
- check("value the 5", "t5", value = Some("value5")) // With stopword
inside.
- check("t6", "t6", elemData = Some(Map("testKey" -> "testValue")))
+ check("value4", "t4", value = Option("value4"))
+ check("value the 5", "t5", value = Option("value5")) // With stopword
inside.
+ check("t6", "t6", elemData = Option(Map("testKey" -> "testValue")))
check("the x abc x abe", "t7") // `x abc` should be matched, `x abe`
shouldn't.
checkMultiple("t1 the x abc the x the abc", "t1", "t7", "t7")
\ No newline at end of file
diff --git
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/NCOpenNlpTokenParserSpec.scala
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/NCOpenNlpTokenParserSpec.scala
index 1b6b5ee..3a96e66 100644
---
a/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/NCOpenNlpTokenParserSpec.scala
+++
b/nlpcraft/src/test/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/NCOpenNlpTokenParserSpec.scala
@@ -49,14 +49,14 @@ class NCOpenNlpTokenParserSpec:
test(
"Test requests!",
toks =>
- require(toks.length == 3);
+ require(toks.sizeIs == 3);
require(!isStopWord(toks.head));
require(isStopWord(toks.last))
)
test(
"Test requests !",
toks =>
- require(toks.length == 3);
+ require(toks.sizeIs == 3);
require(!isStopWord(toks.head));
require(isStopWord(toks.last))
)
@@ -67,7 +67,7 @@ class NCOpenNlpTokenParserSpec:
// So we use spaces around quotes to simplify test.
"a ` a a ` a",
toks =>
- require(toks.length == 6);
+ require(toks.sizeIs == 6);
require(isStopWord(toks.head));
require(isStopWord(toks.last));
require(toks.drop(1).reverse.drop(1).forall(p =>
!isStopWord(p)))
@@ -77,7 +77,7 @@ class NCOpenNlpTokenParserSpec:
// Third and fourth are not because brackets.
"a ( a a ) a",
toks =>
- require(toks.length == 6);
+ require(toks.sizeIs == 6);
require(isStopWord(toks.head));
require(isStopWord(toks.last));
require(toks.drop(1).reverse.drop(1).forall(p =>
!isStopWord(p)))
