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 2026/09/21 04:20:59 UTC

(opennlp) branch OPENNLP-1974-emoji-normalizer updated (9dc83d4b5 -> dab9ea794)

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

krickert pushed a change to branch OPENNLP-1974-emoji-normalizer
in repository https://gitbox.apache.org/repos/asf/opennlp.git


    omit 9dc83d4b5 OPENNLP-1974: Stop EmojiCharSequenceNormalizer from blanking hyphens and BMP characters
     add 89efde8d7 OPENNLP-1983: Enable GitHub issues and discussions (#1316)
     add 6331d6e19 OPENNLP-1937: Expose text embeddings through the provider SPI (#1310)
     add 4cce2c59c OPENNLP-1928: Regex removal (1/10): Replace trivial patterns with character scans (#1311)
     add f2ab1ccd4 OPENNLP-1946: UrlCharSequenceNormalizer removes whole URLs including ports, userinfo and non-ASCII hosts (#1315)
     add 9e7bee3ad OPENNLP-1930: Regex removal (2/10): Parse Arvores Deitadas markup with cursor scans (#1276)
     add c36ff62f7 OPENNLP-1942: Test the shared deep-learning encoder and fix the token type javadoc (#1288)
     add 4683a2ad3 OPENNLP-1974: Normalize complete Unicode emoji sequences
     add dab9ea794 OPENNLP-1974: Include Unicode emoji license in runtime JAR

This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version.  This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:

 * -- * -- B -- O -- O -- O   (9dc83d4b5)
            \
             N -- N -- N   refs/heads/OPENNLP-1974-emoji-normalizer (dab9ea794)

You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.

Any revisions marked "omit" are not gone; other references still
refer to them.  Any revisions marked "discard" are gone forever.

No new revisions were added by this update.

Summary of changes:
 .asf.yaml                                          |    7 +
 .gitignore                                         |    3 +
 LICENSE                                            |    2 +-
 NOTICE                                             |   11 +-
 dev/README-unicode-emoji-sequences.md              |   46 +
 dev/UnicodeEmojiSequenceGenerator.java             |  178 +
 .../EmbeddingException.java}                       |   18 +-
 .../opennlp/tools/embeddings/TextEmbedder.java     |  108 +
 .../TextEmbedderProvider.java}                     |    8 +-
 .../opennlp/tools/tokenize/WordpieceEncoder.java   |    3 +-
 .../main/java/opennlp/tools/util/StringUtil.java   |  169 +-
 .../opennlp/tools/embeddings/TextEmbedderTest.java |   82 +
 .../formats/DetokenizerSampleStreamFactory.java    |    6 +-
 .../java/opennlp/tools/formats/ad/ADMetadata.java  |  151 +
 .../tools/formats/ad/ADNameSampleStream.java       |  304 +-
 .../tools/formats/ad/ADPOSSampleStream.java        |   33 +-
 .../tools/formats/ad/ADSentenceSampleStream.java   |   23 +-
 .../opennlp/tools/formats/ad/ADSentenceStream.java |  745 +++-
 .../tools/formats/ad/ADChunkSampleStreamTest.java  |   23 +
 .../opennlp/tools/formats/ad/ADMetadataTest.java   |  167 +
 .../tools/formats/ad/ADNameSampleStreamTest.java   |  162 +
 .../tools/formats/ad/ADPOSSampleStreamTest.java    |   31 +
 .../formats/ad/ADSentenceSampleStreamTest.java     |   48 +
 .../tools/formats/ad/ADSentenceStreamTest.java     |  638 ++++
 .../src/main/java/opennlp/dl/Tokens.java           |    4 +-
 .../dl/vectors/OnnxTextEmbedderProvider.java       |  190 +
 .../dl/{Tokens.java => vectors/Pooling.java}       |   18 +-
 .../java/opennlp/dl/vectors/SentenceVectorsDL.java |  355 +-
 .../opennlp.tools.embeddings.TextEmbedderProvider} |    2 +-
 .../opennlp/dl/AbstractDLEncodeTokensTest.java     |  354 ++
 .../test/java/opennlp/dl/CreateTokenizerTest.java  |   27 -
 .../src/test/java/opennlp/dl/ModelFreeDL.java      |   54 +
 .../dl/vectors/OnnxTextEmbedderProviderTest.java   |   93 +
 .../dl/vectors/SentenceVectorsDLEmbedderTest.java  |  264 ++
 .../opennlp/dl/vectors/gen_tiny_pooled_model.py    |   98 +
 .../opennlp/dl/vectors/gen_tiny_vectors_model.py   |   57 +
 .../resources/opennlp/dl/vectors/tiny-pooled.onnx  |  Bin 0 -> 513 bytes
 .../resources/opennlp/dl/vectors/tiny-vectors.onnx |  Bin 0 -> 373 bytes
 .../src/main/appended-resources/META-INF/LICENSE   |   45 +
 .../src/main/appended-resources/META-INF/NOTICE    |    9 +
 .../tools/langdetect/LanguageDetectorFactory.java  |    8 +-
 .../DefaultLemmatizerContextGenerator.java         |   10 +-
 .../namefind/BilouNameFinderSequenceValidator.java |    4 +-
 .../main/java/opennlp/tools/namefind/BioCodec.java |   41 +-
 .../java/opennlp/tools/namefind/NameFinderME.java  |   18 -
 .../namefind/NameFinderSequenceValidator.java      |    4 +-
 .../tools/postag/DefaultPOSContextGenerator.java   |    9 +-
 .../tools/util/featuregen/BrownCluster.java        |    6 +-
 .../featuregen/TokenPatternFeatureGenerator.java   |   19 +-
 .../opennlp/tools/util/normalizer/AsciiChars.java  |    5 +
 .../normalizer/EmojiCharSequenceNormalizer.java    |   96 +-
 .../tools/util/normalizer/MailAddressScan.java     |  107 +
 .../util/normalizer/UnicodeEmojiSequences.java     |  204 +
 .../util/normalizer/UrlCharSequenceNormalizer.java |  324 +-
 .../util/normalizer/emoji/EmojiSequences-17.0.txt  | 3960 ++++++++++++++++++++
 .../DefaultLemmatizerContextGeneratorTest.java     |   48 +
 .../java/opennlp/tools/namefind/BioCodecTest.java  |   34 +
 .../postag/DefaultPOSContextGeneratorTest.java     |   23 +
 .../tools/util/featuregen/BrownClusterTest.java    |   92 +
 .../TokenPatternFeatureGeneratorTest.java          |   18 +
 ...CharSequenceNormalizerCharacterizationTest.java |   17 +-
 opennlp-distr/src/main/readme/LICENSE              |    1 +
 opennlp-distr/src/main/readme/NOTICE               |   11 +-
 opennlp-docs/src/docbkx/corpora.xml                |   35 +
 opennlp-docs/src/docbkx/introduction.xml           |   37 -
 opennlp-docs/src/docbkx/langdetect.xml             |   30 +-
 opennlp-docs/src/docbkx/machine-learning.xml       |   37 +
 .../opennlp/dl/vectors/SentenceVectorsDLEval.java  |   16 +-
 .../opennlp/tools/eval/ArvoresDeitadasEval.java    |    2 +-
 .../java/opennlp/tools/util/StringUtilTest.java    |  178 +
 .../EmojiCharSequenceNormalizerTest.java           |  260 +-
 .../normalizer/UrlCharSequenceNormalizerTest.java  |  302 +-
 rat-excludes                                       |    5 +
 src/license/NOTICE.template                        |   13 +-
 74 files changed, 9737 insertions(+), 773 deletions(-)
 create mode 100644 dev/README-unicode-emoji-sequences.md
 create mode 100644 dev/UnicodeEmojiSequenceGenerator.java
 copy opennlp-api/src/main/java/opennlp/tools/{util/ext/AmbiguousProviderException.java => embeddings/EmbeddingException.java} (67%)
 create mode 100644 opennlp-api/src/main/java/opennlp/tools/embeddings/TextEmbedder.java
 copy opennlp-api/src/main/java/opennlp/tools/{document/DocumentAnnotatorProvider.java => embeddings/TextEmbedderProvider.java} (76%)
 create mode 100644 opennlp-api/src/test/java/opennlp/tools/embeddings/TextEmbedderTest.java
 create mode 100644 opennlp-core/opennlp-formats/src/main/java/opennlp/tools/formats/ad/ADMetadata.java
 create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/ad/ADMetadataTest.java
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/main/java/opennlp/dl/vectors/OnnxTextEmbedderProvider.java
 copy opennlp-core/opennlp-ml/opennlp-dl/src/main/java/opennlp/dl/{Tokens.java => vectors/Pooling.java} (69%)
 copy opennlp-core/{opennlp-runtime/src/main/resources/META-INF/services/opennlp.tools.document.DocumentAnnotatorProvider => opennlp-ml/opennlp-dl/src/main/resources/META-INF/services/opennlp.tools.embeddings.TextEmbedderProvider} (94%)
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/AbstractDLEncodeTokensTest.java
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/ModelFreeDL.java
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/vectors/OnnxTextEmbedderProviderTest.java
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/vectors/SentenceVectorsDLEmbedderTest.java
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/resources/opennlp/dl/vectors/gen_tiny_pooled_model.py
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/resources/opennlp/dl/vectors/gen_tiny_vectors_model.py
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/resources/opennlp/dl/vectors/tiny-pooled.onnx
 create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/resources/opennlp/dl/vectors/tiny-vectors.onnx
 create mode 100644 opennlp-core/opennlp-runtime/src/main/appended-resources/META-INF/LICENSE
 create mode 100644 opennlp-core/opennlp-runtime/src/main/appended-resources/META-INF/NOTICE
 create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/MailAddressScan.java
 create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/UnicodeEmojiSequences.java
 create mode 100644 opennlp-core/opennlp-runtime/src/main/resources/opennlp/tools/util/normalizer/emoji/EmojiSequences-17.0.txt
 create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/lemmatizer/DefaultLemmatizerContextGeneratorTest.java
 create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/featuregen/BrownClusterTest.java