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 38ed2ba WIP.
38ed2ba is described below
commit 38ed2ba92ff2103af8b621978992769387a54d98
Author: Sergey Kamov <[email protected]>
AuthorDate: Mon Dec 27 16:06:14 2021 +0300
WIP.
---
.../token/parser/opennlp/NCEnOpenNlpTokenParserBenchmark.java | 7 ++-----
.../nlp/token/enricher/NCEnBracketsTokenEnricherSpec.scala | 8 +-------
.../nlp/token/enricher/NCEnQuotesTokenEnricherSpec.scala | 8 +-------
.../nlp/token/enricher/NCOpenNlpTokenEnricherSpec.scala | 8 +-------
.../nlp/token/parser/opennlp/NCEnOpenNlpTokenParserSpec.scala | 11 ++---------
.../org/apache/nlpcraft/internal/nlp/util/NCTestUtils.scala | 11 +++++++++++
6 files changed, 18 insertions(+), 35 deletions(-)
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/benchmark/token/parser/opennlp/NCEnOpenNlpTokenParserBenchmark.java
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/benchmark/token/parser/opennlp/NCEnOpenNlpTokenParserBenchmark.java
index 6777557..62c6df0 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/benchmark/token/parser/opennlp/NCEnOpenNlpTokenParserBenchmark.java
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/benchmark/token/parser/opennlp/NCEnOpenNlpTokenParserBenchmark.java
@@ -19,6 +19,7 @@ package
org.apache.nlpcraft.internal.nlp.benchmark.token.parser.opennlp;
import org.apache.nlpcraft.internal.nlp.benchmark.NCBenchmarkAdapter;
import
org.apache.nlpcraft.internal.nlp.token.parser.opennlp.NCEnOpenNlpTokenParser;
+import org.apache.nlpcraft.internal.nlp.util.NCTestUtils;
import org.junit.jupiter.api.Disabled;
import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.Setup;
@@ -52,11 +53,7 @@ public class NCEnOpenNlpTokenParserBenchmark extends
NCBenchmarkAdapter {
* @return
*/
private static NCEnOpenNlpTokenParser prepareParser() {
- NCEnOpenNlpTokenParser p = new NCEnOpenNlpTokenParser(
- "opennlp/en-token.bin",
- "opennlp/en-pos-maxent.bin",
- "opennlp/en-lemmatizer.dict"
- );
+ NCEnOpenNlpTokenParser p = NCTestUtils.mkEnParser();
p.start();
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnBracketsTokenEnricherSpec.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnBracketsTokenEnricherSpec.scala
index 8fdbdaf..57efa08 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnBracketsTokenEnricherSpec.scala
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnBracketsTokenEnricherSpec.scala
@@ -33,13 +33,7 @@ class NCEnBracketsTokenEnricherSpec:
@BeforeEach
def start(): Unit = enricher =
- parser = NCTestUtils.makeAndStart(
- new NCEnOpenNlpTokenParser(
- "opennlp/en-token.bin",
- "opennlp/en-pos-maxent.bin",
- "opennlp/en-lemmatizer.dict"
- )
- )
+ parser = NCTestUtils.makeAndStart(NCTestUtils.mkEnParser)
NCTestUtils.makeAndStart(new NCEnBracketsTokenEnricher())
/**
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnQuotesTokenEnricherSpec.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnQuotesTokenEnricherSpec.scala
index a7048ea..514f588 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnQuotesTokenEnricherSpec.scala
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCEnQuotesTokenEnricherSpec.scala
@@ -33,13 +33,7 @@ class NCEnQuotesTokenEnricherSpec:
@BeforeEach
def start(): Unit =
- parser = NCTestUtils.makeAndStart(
- new NCEnOpenNlpTokenParser(
- "opennlp/en-token.bin",
- "opennlp/en-pos-maxent.bin",
- "opennlp/en-lemmatizer.dict"
- )
- )
+ parser = NCTestUtils.makeAndStart(NCTestUtils.mkEnParser)
enricher = NCTestUtils.makeAndStart(new NCEnQuotesTokenEnricher)
/**
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCOpenNlpTokenEnricherSpec.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCOpenNlpTokenEnricherSpec.scala
index 3a3ea55..3b4302a 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCOpenNlpTokenEnricherSpec.scala
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/enricher/NCOpenNlpTokenEnricherSpec.scala
@@ -34,13 +34,7 @@ class NCOpenNlpTokenEnricherSpec:
@BeforeEach
def start(): Unit =
- parser = NCTestUtils.makeAndStart(
- new NCEnOpenNlpTokenParser(
- "opennlp/en-token.bin",
- "opennlp/en-pos-maxent.bin",
- "opennlp/en-lemmatizer.dict"
- )
- )
+ parser = NCTestUtils.makeAndStart(NCTestUtils.mkEnParser)
enricher = NCTestUtils.makeAndStart(
// en-ner-time.bin is skipped. I can't find any working example.
new NCOpenNlpTokenEnricher(
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCEnOpenNlpTokenParserSpec.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCEnOpenNlpTokenParserSpec.scala
index 90ab8e6..ef25ed8 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCEnOpenNlpTokenParserSpec.scala
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/token/parser/opennlp/NCEnOpenNlpTokenParserSpec.scala
@@ -17,10 +17,10 @@
package org.apache.nlpcraft.internal.nlp.token.parser.opennlp
+import org.apache.nlpcraft.*
import org.apache.nlpcraft.internal.ascii.NCAsciiTable
import org.apache.nlpcraft.internal.nlp
import org.apache.nlpcraft.internal.nlp.util.*
-import org.apache.nlpcraft.*
import org.junit.jupiter.api.*
import java.util
@@ -33,14 +33,7 @@ class NCEnOpenNlpTokenParserSpec:
private var parser: NCEnOpenNlpTokenParser = _
@BeforeEach
- def start(): Unit =
- parser = NCTestUtils.makeAndStart(
- new NCEnOpenNlpTokenParser(
- "opennlp/en-token.bin",
- "opennlp/en-pos-maxent.bin",
- "opennlp/en-lemmatizer.dict"
- )
- )
+ def start(): Unit = parser =
NCTestUtils.makeAndStart(NCTestUtils.mkEnParser)
private def test(txt: String, validate: Seq[NCToken] => _): Unit =
val toks = parser.parse(nlp.util.NCTestRequest(txt)).asScala.toSeq
diff --git
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/util/NCTestUtils.scala
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/util/NCTestUtils.scala
index 2b6b270..b53bb51 100644
---
a/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/util/NCTestUtils.scala
+++
b/nlpcraft/src/test/java/org/apache/nlpcraft/internal/nlp/util/NCTestUtils.scala
@@ -19,6 +19,7 @@ package org.apache.nlpcraft.internal.nlp.util
import org.apache.nlpcraft.internal.ascii.NCAsciiTable
import org.apache.nlpcraft.*
+import
org.apache.nlpcraft.internal.nlp.token.parser.opennlp.NCEnOpenNlpTokenParser
/**
*
@@ -84,3 +85,13 @@ object NCTestUtils:
t.start()
println(s"'${t.getClass.getSimpleName}' created with time=${started -
start} ms and started=${now() - started} ms.")
t
+
+ /**
+ *
+ * @return
+ */
+ def mkEnParser: NCEnOpenNlpTokenParser = new NCEnOpenNlpTokenParser(
+ "opennlp/en-token.bin",
+ "opennlp/en-pos-maxent.bin",
+ "opennlp/en-lemmatizer.dict"
+ )
