You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nlpcraft.apache.org by ar...@apache.org on 2022/02/03 17:58:38 UTC
[incubator-nlpcraft] branch NLPCRAFT-477 updated: CR
This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch NLPCRAFT-477
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft.git
The following commit(s) were added to refs/heads/NLPCRAFT-477 by this push:
new ace24f0 CR
ace24f0 is described below
commit ace24f03d6d22ecef665e5575ced81d0b3f3f30c
Author: Aaron Radzinski <ar...@datalingvo.com>
AuthorDate: Thu Feb 3 09:56:04 2022 -0800
CR
---
.../internal/dialogflow/NCDialogFlowManager.scala | 1 -
.../nlpcraft/internal/makro/NCMacroCompiler.scala | 16 ++++++------
.../en/impl/NCBracketsTokenEnricherImpl.scala | 20 +++++++++++----
.../opennlp/impl/NCOpenNLPTokenParserImpl.scala | 6 ++---
.../parser/opennlp/NCOpenNLPTokenParserSpec.scala | 29 ++++++++++++----------
5 files changed, 41 insertions(+), 31 deletions(-)
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/dialogflow/NCDialogFlowManager.scala b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/dialogflow/NCDialogFlowManager.scala
index 0a35329..0a1c5a9 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/dialogflow/NCDialogFlowManager.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/dialogflow/NCDialogFlowManager.scala
@@ -74,7 +74,6 @@ class NCDialogFlowManager(mdlCfg: NCModelConfig) extends LazyLogging:
* @param intentMatch
* @param res Intent callback result.
* @param ctx Original query context.
- * @param parent
*/
def addMatchedIntent(intentMatch: NCIntentMatch, res: NCResult, ctx: NCContext): Unit =
val item: NCDialogFlowItem = new NCDialogFlowItem:
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/makro/NCMacroCompiler.scala b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/makro/NCMacroCompiler.scala
index 332139a..a385f90 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/makro/NCMacroCompiler.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/internal/makro/NCMacroCompiler.scala
@@ -115,7 +115,9 @@ object NCMacroCompiler extends LazyLogging:
if ctx.minMaxShortcut() != null then
ctx.minMaxShortcut().getText match
- case "?" => min = 0; max = 1
+ case "?" =>
+ min = 0
+ max = 1
case c => throw compilerError(s"Invalid min/max shortcut '$c' in: ${ctx.getText}")
else if ctx.MINMAX() != null then
var s = ctx.MINMAX().getText
@@ -126,15 +128,11 @@ object NCMacroCompiler extends LazyLogging:
if comma == -1 || comma == 0 || comma == s.length - 1 then
throw compilerError(s"Invalid min/max quantifier: $orig")
- try
- min = java.lang.Integer.parseInt(s.substring(0, comma).trim)
- catch
- case _: NumberFormatException => throw compilerError(s"Invalid min quantifier: $orig")
+ try min = java.lang.Integer.parseInt(s.substring(0, comma).trim)
+ catch case _: NumberFormatException => throw compilerError(s"Invalid min quantifier: $orig")
- try
- max = java.lang.Integer.parseInt(s.substring(comma + 1).trim)
- catch
- case _: NumberFormatException => throw compilerError(s"Invalid max quantifier: $orig")
+ try max = java.lang.Integer.parseInt(s.substring(comma + 1).trim)
+ catch case _: NumberFormatException => throw compilerError(s"Invalid max quantifier: $orig")
if min < 0 || max < 0 || min > max || max == 0 || max > MAX_QTY then
throw compilerError(s"[$min,$max] quantifiers should be 'max >= min, min >= 0, max > 0, max <= $MAX_QTY'.")
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCBracketsTokenEnricherImpl.scala b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCBracketsTokenEnricherImpl.scala
index 3a88225..cd5f3bf 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCBracketsTokenEnricherImpl.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/enricher/en/impl/NCBracketsTokenEnricherImpl.scala
@@ -39,11 +39,21 @@ class NCBracketsTokenEnricherImpl extends NCTokenEnricher with LazyLogging:
for (t <- toks.asScala if ok)
t.getText match
- case "(" | "{" | "[" | "<" => mark(t); stack.push(t.getText)
- case ")" => check("("); mark(t)
- case "}" => check("{"); mark(t)
- case "]" => check("["); mark(t)
- case ">" => check("<"); mark(t)
+ case "(" | "{" | "[" | "<" =>
+ mark(t)
+ stack.push(t.getText)
+ case ")" =>
+ check("(")
+ mark(t)
+ case "}" =>
+ check("{")
+ mark(t)
+ case "]" =>
+ check("[")
+ mark(t)
+ case ">" =>
+ check("<")
+ mark(t)
case _ => mark(t)
if ok && stack.isEmpty then map.foreach { (tok, b) => tok.put("brackets", b) }
diff --git a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/impl/NCOpenNLPTokenParserImpl.scala b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/impl/NCOpenNLPTokenParserImpl.scala
index 44adafd..e85fd74 100644
--- a/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/impl/NCOpenNLPTokenParserImpl.scala
+++ b/nlpcraft/src/main/scala/org/apache/nlpcraft/nlp/token/parser/opennlp/impl/NCOpenNLPTokenParserImpl.scala
@@ -52,15 +52,15 @@ class NCOpenNLPTokenParserImpl(tokMdl: String, posMdlSrc: String, lemmaDicSrc:
private def init(): Unit =
NCUtils.execPar(
() =>
- tagger = new POSTaggerME(new POSModel(NCUtils.getStream(posMdlSrc)));
+ tagger = new POSTaggerME(new POSModel(NCUtils.getStream(posMdlSrc)))
logger.trace(s"Loaded resource: $posMdlSrc")
,
() =>
- lemmatizer = new DictionaryLemmatizer(NCUtils.getStream(lemmaDicSrc));
+ lemmatizer = new DictionaryLemmatizer(NCUtils.getStream(lemmaDicSrc))
logger.trace(s"Loaded resource: $lemmaDicSrc")
,
() =>
- tokenizer = new TokenizerME(new TokenizerModel(NCUtils.getStream(tokMdl)));
+ tokenizer = new TokenizerME(new TokenizerModel(NCUtils.getStream(tokMdl)))
logger.trace(s"Loaded resource: $tokMdl")
)(ExecutionContext.Implicits.global)
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 e417397..12b52d3 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
@@ -50,16 +50,17 @@ class NCOpenNLPTokenParserSpec:
test(
"Test requests!",
toks =>
- require(toks.sizeIs == 3);
- require(!isStopWord(toks.head));
+ require(toks.sizeIs == 3)
+ require(!isStopWord(toks.head))
require(isStopWord(toks.last))
)
test(
"Test requests !",
- toks =>
- require(toks.sizeIs == 3);
- require(!isStopWord(toks.head));
+ toks => {
+ require(toks.sizeIs == 3)
+ require(!isStopWord(toks.head))
require(isStopWord(toks.last))
+ }
)
test(
// First and last are stop words,
@@ -67,21 +68,23 @@ class NCOpenNLPTokenParserSpec:
// Note that "a ` a a` a" parsed as 5 tokens ("a", "`", ""a, "a`", "a") because OpenNLP tokenizer logic,
// So we use spaces around quotes to simplify test.
"a ` a a ` a",
- toks =>
- require(toks.sizeIs == 6);
- require(isStopWord(toks.head));
- require(isStopWord(toks.last));
+ toks => {
+ require(toks.sizeIs == 6)
+ require(isStopWord(toks.head))
+ require(isStopWord(toks.last))
require(toks.drop(1).reverse.drop(1).forall(p => !isStopWord(p)))
+ }
)
test(
// First and last are stop words,
// Third and fourth are not because brackets.
"a ( a a ) a",
- toks =>
- require(toks.sizeIs == 6);
- require(isStopWord(toks.head));
- require(isStopWord(toks.last));
+ toks => {
+ require(toks.sizeIs == 6)
+ require(isStopWord(toks.head))
+ require(isStopWord(toks.last))
require(toks.drop(1).reverse.drop(1).forall(p => !isStopWord(p)))
+ }
)
test(
// Invalid brackets.