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 02:54:59 UTC

(opennlp-sandbox) branch OPENNLP-1833-grpc-expansion updated (c74566b7 -> 7d081e4d)

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

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


    from c74566b7 OPENNLP-1833: Render every analysis result as document-shape layers
     add 5949712f OPENNLP-1833: Pin the SentencePiece subword step (failing tests)
     add f9f5a8b0 OPENNLP-1833: Serve SentencePiece subword encoding as a document-shape layer
     add 6bf7009a OPENNLP-1833: Pin the stemming step (failing tests)
     add 4e1f470b OPENNLP-1833: Stem tokens across snowball, porter, UniNE, and hunspell
     add dd95045c OPENNLP-1833: Pin the lexical expansion step (failing tests)
     add d3a2b271 OPENNLP-1833: Expand tokens over configured WordNet knowledge bases
     add 7174666d OPENNLP-1833: Pin the lattice tokenizer engine (failing tests)
     add b0420bf0 OPENNLP-1833: Segment with the lattice tokenizer engine
     add 4875d87d OPENNLP-1833: Pin geocode enrichment of location entities (failing tests)
     add 6f987378 OPENNLP-1833: Geocode location entities against the bundled gazetteer
     add 7d081e4d OPENNLP-1833: Document the feature-parity steps and their configuration

No new revisions were added by this update.

Summary of changes:
 opennlp-grpc/README.md                             |  14 +-
 .../apache/opennlp/grpc/v1/opennlp_document.proto  |  81 ++++++-
 .../apache/opennlp/grpc/v1/opennlp_pipeline.proto  |  90 ++++++-
 opennlp-grpc/opennlp-grpc-service/pom.xml          |  18 ++
 .../opennlp/grpc/model/HunspellRegistry.java       | 166 +++++++++++++
 .../apache/opennlp/grpc/model/LatticeRegistry.java | 153 ++++++++++++
 .../opennlp/grpc/model/ModelBundleCache.java       |  52 ++++
 .../apache/opennlp/grpc/model/SubwordRegistry.java | 149 ++++++++++++
 .../apache/opennlp/grpc/model/WordNetRegistry.java | 151 ++++++++++++
 .../opennlp/grpc/processor/PipelineStepPolicy.java |   4 +
 .../processor/basic/AnalysisRequestValidator.java  |  86 ++++++-
 .../processor/basic/BasicDocumentAnalyzer.java     |  67 ++++-
 .../grpc/processor/basic/ClassicStepRunner.java    | 269 +++++++++++++++++++++
 .../processor/basic/DocumentOffsetEncoder.java     |  18 ++
 .../processor/basic/DocumentShapeAssembler.java    |  31 ++-
 .../grpc/processor/basic/StemmerSelector.java      | 179 ++++++++++++++
 .../basic/BasicDocumentAnalyzerExpandTest.java     | 157 ++++++++++++
 .../basic/BasicDocumentAnalyzerGeocodeTest.java    | 130 ++++++++++
 .../basic/BasicDocumentAnalyzerLatticeTest.java    | 144 +++++++++++
 .../basic/BasicDocumentAnalyzerStemTest.java       | 208 ++++++++++++++++
 .../basic/BasicDocumentAnalyzerSubwordTest.java    | 163 +++++++++++++
 .../apache/opennlp/grpc/testing/TinyNerModel.java  |  32 ++-
 .../resources/subword/tiny-unigram-bytefb.model    | Bin 0 -> 250431 bytes
 .../src/test/resources/wordnet/mini-wn-lmf.xml     | 183 ++++++++++++++
 24 files changed, 2532 insertions(+), 13 deletions(-)
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/main/java/org/apache/opennlp/grpc/model/HunspellRegistry.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/main/java/org/apache/opennlp/grpc/model/LatticeRegistry.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/main/java/org/apache/opennlp/grpc/model/SubwordRegistry.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/main/java/org/apache/opennlp/grpc/model/WordNetRegistry.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/main/java/org/apache/opennlp/grpc/processor/basic/StemmerSelector.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/java/org/apache/opennlp/grpc/processor/basic/BasicDocumentAnalyzerExpandTest.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/java/org/apache/opennlp/grpc/processor/basic/BasicDocumentAnalyzerGeocodeTest.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/java/org/apache/opennlp/grpc/processor/basic/BasicDocumentAnalyzerLatticeTest.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/java/org/apache/opennlp/grpc/processor/basic/BasicDocumentAnalyzerStemTest.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/java/org/apache/opennlp/grpc/processor/basic/BasicDocumentAnalyzerSubwordTest.java
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/resources/subword/tiny-unigram-bytefb.model
 create mode 100644 opennlp-grpc/opennlp-grpc-service/src/test/resources/wordnet/mini-wn-lmf.xml