You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by kr...@apache.org on 2026/08/15 00:14:41 UTC

(opennlp) 05/14: Merge PR #1155 head into OPENNLP-1833-grpc-helper

This is an automated email from the ASF dual-hosted git repository.

krickert pushed a commit to branch OPENNLP-1833-grpc-helper
in repository https://gitbox.apache.org/repos/asf/opennlp.git

commit f2174d25bde2b5c5aedcf8c5bb62f594e927d046
Merge: 03baf568d c678d6579
Author: Kristian Rickert <kr...@gmail.com>
AuthorDate: Fri Aug 14 20:01:59 2026 -0400

    Merge PR #1155 head into OPENNLP-1833-grpc-helper
    
    # Conflicts:
    #       opennlp-distr/pom.xml
    #       opennlp-distr/src/main/assembly/bin.xml
    #       opennlp-docs/src/docbkx/opennlp.xml
    #       pom.xml
    #       rat-excludes

 .../tools/wordnet/LexicalKnowledgeBase.java        |  85 +++
 .../main/java/opennlp/tools/wordnet/Synset.java    | 123 ++++
 .../java/opennlp/tools/wordnet/WordNetPOS.java     |  40 ++
 .../opennlp/tools/wordnet/WordNetRelation.java     | 115 ++++
 .../tools/wordnet/LexicalKnowledgeBaseTest.java    | 105 ++++
 .../java/opennlp/tools/wordnet/SynsetTest.java     | 150 +++++
 opennlp-distr/pom.xml                              |   5 +
 opennlp-distr/src/main/assembly/bin.xml            |   7 +
 opennlp-docs/src/docbkx/opennlp.xml                |   1 +
 opennlp-docs/src/docbkx/wordnet.xml                | 106 ++++
 opennlp-extensions/{ => opennlp-wordnet}/pom.xml   |  52 +-
 .../opennlp/wordnet/InMemoryWordNetLexicon.java    | 157 +++++
 .../main/java/opennlp/wordnet/LemmaFolding.java    |  75 +++
 .../java/opennlp/wordnet/MorphyExceptions.java     | 145 +++++
 .../java/opennlp/wordnet/MorphyLemmatizer.java     | 241 ++++++++
 .../src/main/java/opennlp/wordnet/WnLmfReader.java | 618 ++++++++++++++++++++
 .../src/main/java/opennlp/wordnet/WndbReader.java  | 642 +++++++++++++++++++++
 .../wordnet/InMemoryWordNetLexiconTest.java        |  89 +++
 .../java/opennlp/wordnet/LemmaFoldingTest.java     |  71 +++
 .../opennlp/wordnet/LexiconConcurrencyTest.java    |  91 +++
 .../java/opennlp/wordnet/MorphyExceptionsTest.java | 129 +++++
 .../java/opennlp/wordnet/MorphyLemmatizerTest.java | 203 +++++++
 .../opennlp/wordnet/ReaderEquivalenceTest.java     | 121 ++++
 .../test/java/opennlp/wordnet/WnLmfReaderTest.java | 387 +++++++++++++
 .../test/java/opennlp/wordnet/WndbReaderTest.java  | 311 ++++++++++
 .../opennlp/wordnet/WordNetUsageExampleTest.java   | 101 ++++
 .../test/resources/opennlp/wordnet/mini-wn-lmf.xml | 183 ++++++
 .../opennlp/wordnet/mini-wndb/.gitattributes       |   7 +
 .../resources/opennlp/wordnet/mini-wndb/adj.exc    |   1 +
 .../resources/opennlp/wordnet/mini-wndb/adv.exc    |   1 +
 .../resources/opennlp/wordnet/mini-wndb/data.adj   |  22 +
 .../resources/opennlp/wordnet/mini-wndb/data.adv   |  20 +
 .../resources/opennlp/wordnet/mini-wndb/data.noun  |  27 +
 .../resources/opennlp/wordnet/mini-wndb/data.verb  |  22 +
 .../resources/opennlp/wordnet/mini-wndb/index.adj  |  22 +
 .../resources/opennlp/wordnet/mini-wndb/index.adv  |  20 +
 .../resources/opennlp/wordnet/mini-wndb/index.noun |  27 +
 .../resources/opennlp/wordnet/mini-wndb/index.verb |  22 +
 .../resources/opennlp/wordnet/mini-wndb/noun.exc   |   4 +
 .../resources/opennlp/wordnet/mini-wndb/verb.exc   |   4 +
 opennlp-extensions/pom.xml                         |   1 +
 pom.xml                                            |   6 +
 rat-excludes                                       |   8 +
 43 files changed, 4546 insertions(+), 21 deletions(-)

diff --cc opennlp-distr/pom.xml
index 71e47e43a,39269575e..a45bbf89c
--- a/opennlp-distr/pom.xml
+++ b/opennlp-distr/pom.xml
@@@ -95,16 -91,11 +95,21 @@@
        <groupId>org.apache.opennlp</groupId>
        <artifactId>opennlp-spellcheck</artifactId>
      </dependency>
 +    <dependency>
 +      <groupId>org.apache.opennlp</groupId>
 +      <artifactId>opennlp-subword</artifactId>
 +    </dependency>
 +
 +    <dependency>
 +      <groupId>org.apache.opennlp</groupId>
 +      <artifactId>opennlp-embeddings</artifactId>
 +    </dependency>
 +
+     <dependency>
+       <groupId>org.apache.opennlp</groupId>
+       <artifactId>opennlp-wordnet</artifactId>
+     </dependency>
+ 
      <!-- OpenNLP Docs - Ensure that "docs" are build before distribution -->
      <dependency>
        <groupId>org.apache.opennlp</groupId>
diff --cc opennlp-distr/src/main/assembly/bin.xml
index ad465a18d,36c556d47..62be4dbb6
--- a/opennlp-distr/src/main/assembly/bin.xml
+++ b/opennlp-distr/src/main/assembly/bin.xml
@@@ -253,13 -239,13 +253,20 @@@
        <outputDirectory>docs/apidocs/opennlp-spellcheck</outputDirectory>
      </fileSet>
  
 +    <fileSet>
 +      <directory>../opennlp-extensions/opennlp-subword/target/reports/apidocs</directory>
 +      <fileMode>644</fileMode>
 +      <directoryMode>755</directoryMode>
 +      <outputDirectory>docs/apidocs/opennlp-subword</outputDirectory>
 +    </fileSet>
 +
+     <fileSet>
+       <directory>../opennlp-extensions/opennlp-wordnet/target/reports/apidocs</directory>
+       <fileMode>644</fileMode>
+       <directoryMode>755</directoryMode>
+       <outputDirectory>docs/apidocs/opennlp-wordnet</outputDirectory>
+     </fileSet>
+ 
      <fileSet>
        <directory>../opennlp-extensions/opennlp-uima/target/reports/apidocs</directory>
        <fileMode>644</fileMode>
diff --cc opennlp-docs/src/docbkx/opennlp.xml
index 5448c20fe,f7a8a3940..3a2bbcda3
--- a/opennlp-docs/src/docbkx/opennlp.xml
+++ b/opennlp-docs/src/docbkx/opennlp.xml
@@@ -109,7 -109,7 +109,8 @@@ under the License
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./postagger.xml" />
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./lemmatizer.xml" />
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./stemmer.xml" />
+ 	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./wordnet.xml" />
 +	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./document.xml" />
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./spellcheck.xml" />
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./chunker.xml" />
  	<xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="./parser.xml" />
diff --cc opennlp-extensions/pom.xml
index db6cfa7ff,8c0e432a5..f27f84bfc
--- a/opennlp-extensions/pom.xml
+++ b/opennlp-extensions/pom.xml
@@@ -38,12 -38,10 +38,13 @@@
    </properties>
  
    <modules>
 +    <module>opennlp-embeddings</module>
 +    <module>opennlp-geo</module>
      <module>opennlp-morfologik</module>
      <module>opennlp-spellcheck</module>
 +    <module>opennlp-subword</module>
      <module>opennlp-uima</module>
+     <module>opennlp-wordnet</module>
    </modules>
  
  </project>
diff --cc pom.xml
index 0a2c79982,6c1863811..57ed91c36
--- a/pom.xml
+++ b/pom.xml
@@@ -223,10 -216,10 +223,16 @@@
  				<version>${project.version}</version>
  			</dependency>
  
 +			<dependency>
 +				<artifactId>opennlp-subword</artifactId>
 +				<groupId>${project.groupId}</groupId>
 +				<version>${project.version}</version>
++			</dependency>
++
+ 			<dependency>
+ 				<artifactId>opennlp-wordnet</artifactId>
+ 				<groupId>${project.groupId}</groupId>
+ 				<version>${project.version}</version>
  			</dependency>
  
  			<dependency>
diff --cc rat-excludes
index 7d32a5724,561869bd4..0fc8287ba
--- a/rat-excludes
+++ b/rat-excludes
@@@ -71,16 -71,11 +71,24 @@@ src/main/resources/opennlp/tools/tokeni
  src/main/resources/opennlp/tools/util/normalizer/confusables.txt
  src/test/resources/opennlp/tools/tokenize/uax29/WordBreakTest.txt
  
 +<!-- opennlp-dl tiny ONNX test model (project-generated binary, see gen_tiny_vectors_model.py committed next to it) -->
 +src/test/resources/opennlp/dl/vectors/tiny-vectors.onnx
 +<!-- opennlp-subword bundled test models and fixtures (project-generated binaries and data) -->
 +src/test/resources/opennlp/subword/sentencepiece/*.model
 +src/test/resources/opennlp/subword/sentencepiece/*.fixtures.tsv
 +src/test/resources/opennlp/subword/sentencepiece/corpus.txt
 +<!-- opennlp-embeddings copy of the opennlp-subword tiny SentencePiece test model -->
 +src/test/resources/opennlp/embeddings/tiny-unigram.model
 +<!-- opennlp-embeddings parity harness input sentences (data file, no AL header possible) -->
 +dev/embeddings/parity/sentences.txt
 +<!-- OPENNLP-1879 bundled Natural Earth gazetteer table (public domain data;
 +     the file header carries the derivation record and the LICENSE pointer) -->
 +src/main/resources/opennlp/geo/naturalearth-populated-places.txt
+ <!-- Miniature WNDB morphology exception-list fixtures; the *.exc format is bare
+      "inflected base" lines with no comment syntax, so no header can be carried.
+      The index.* and data.* fixtures in the same directory do carry the header
+      in their space-prefixed WNDB license preamble and are not excluded. -->
+ src/test/resources/opennlp/wordnet/mini-wndb/noun.exc
+ src/test/resources/opennlp/wordnet/mini-wndb/verb.exc
+ src/test/resources/opennlp/wordnet/mini-wndb/adj.exc
+ src/test/resources/opennlp/wordnet/mini-wndb/adv.exc