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 2026/09/16 18:36:55 UTC

(opennlp) 05/27: Merge PR 1215 into Apache 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 8b4f30c0511e4cd57b6db91a52351d54ad03452c
Merge: c2b60e52d 8de70d68f
Author: Kristian Rickert <kr...@apache.org>
AuthorDate: Wed Sep 16 13:36:04 2026 -0400

    Merge PR 1215 into Apache helper

 dev/legal-corpus/LICENSING.md                      |  14 +
 dev/legal-corpus/README.md                         | 105 +++
 dev/legal-corpus/bouvier-snapshots.tsv             |  26 +
 dev/legal-corpus/fetch-dictionary.sh               | 128 ++++
 dev/legal-corpus/fetch-reporter.sh                 | 115 ++++
 dev/legal-corpus/fetch-scripts-test.sh             | 114 ++++
 dev/legal-corpus/fixtures/mini-dictionary.tsv      |  12 +
 dev/legal-corpus/fixtures/mini-passages.jsonl      |   6 +
 dev/legal-corpus/reporter-snapshots.tsv            |  31 +
 opennlp-docs/src/docbkx/embeddings.xml             |  33 +
 opennlp-extensions/opennlp-embeddings-cli/pom.xml  |   8 +
 .../main/java/opennlp/embeddings/cmdline/CLI.java  |   4 +
 .../embeddings/cmdline/EvalVectorSearchParams.java |  80 +++
 .../embeddings/cmdline/EvalVectorSearchTool.java   |  86 +++
 .../embeddings/cmdline/EvaluationReportFiles.java  | 126 ++++
 .../embeddings/cmdline/LearnVocabularyParams.java  |  66 ++
 .../embeddings/cmdline/LearnVocabularyTool.java    |  85 +++
 .../cmdline/NormalizeDictionaryParams.java         |  42 ++
 .../cmdline/NormalizeDictionaryTool.java           |  65 ++
 .../cmdline/NormalizeReporterParams.java           |  42 ++
 .../embeddings/cmdline/NormalizeReporterTool.java  |  77 +++
 .../java/opennlp/embeddings/cmdline/CLITest.java   |  38 +-
 .../cmdline/EvaluationReportFilesTest.java         | 385 +++++++++++
 .../embeddings/cmdline/HnswBaselineRunner.java     |  65 ++
 .../embeddings/cmdline/HnswBaselineRunnerTest.java |  56 ++
 .../java/opennlp/embeddings/eval/HnswBaseline.java | 354 ++++++++++
 .../opennlp/embeddings/eval/HnswBaselineTest.java  | 197 ++++++
 .../opennlp/embeddings/index/HnswFloatIndex.java   | 252 +++++++
 .../embeddings/index/HnswFloatIndexTest.java       | 206 ++++++
 .../index/HnswVectorIndexContractTest.java         | 317 +++++++++
 opennlp-extensions/opennlp-embeddings-core/pom.xml |  10 +
 .../embeddings/corpus/BouvierDictionaryParser.java | 434 ++++++++++++
 .../opennlp/embeddings/corpus/CapVolumeReader.java | 221 ++++++
 .../opennlp/embeddings/corpus/CasePassage.java     | 198 ++++++
 .../opennlp/embeddings/corpus/DictionaryEntry.java | 153 +++++
 .../main/java/opennlp/embeddings/corpus/Json.java  | 416 ++++++++++++
 .../java/opennlp/embeddings/corpus/TermCount.java  | 171 +++++
 .../embeddings/corpus/VocabularyLearner.java       | 205 ++++++
 .../java/opennlp/embeddings/eval/IndexBuild.java   |  70 ++
 .../opennlp/embeddings/eval/SearchEvaluator.java   | 737 +++++++++++++++++++++
 .../opennlp/embeddings/EmbeddingTestFixtures.java  |   4 +-
 .../corpus/BouvierDictionaryParserTest.java        | 120 ++++
 .../embeddings/corpus/CapVolumeReaderTest.java     | 171 +++++
 .../embeddings/corpus/InterchangeFilesTest.java    | 232 +++++++
 .../java/opennlp/embeddings/corpus/JsonTest.java   |  94 +++
 .../embeddings/corpus/VocabularyLearnerTest.java   | 135 ++++
 .../opennlp/embeddings/eval/IndexBuildTest.java    | 209 ++++++
 .../embeddings/eval/SearchEvaluatorTest.java       | 316 +++++++++
 .../opennlp/embeddings/corpus/mini-bouvier.htm     |  13 +
 .../opennlp/embeddings/corpus/mini-dictionary.tsv  |  12 +
 .../opennlp/embeddings/corpus/mini-passages.jsonl  |   6 +
 opennlp-extensions/opennlp-embeddings/TRAINING.md  |  52 ++
 pom.xml                                            |   1 +
 rat-excludes                                       |   5 +
 54 files changed, 7116 insertions(+), 4 deletions(-)