You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by rz...@apache.org on 2026/10/06 17:59:43 UTC
(opennlp) branch minor-bundled-unicode-data-loader updated (f362af254 -> a2a61fc0a)
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a change to branch minor-bundled-unicode-data-loader
in repository https://gitbox.apache.org/repos/asf/opennlp.git
discard f362af254 Reference the bundled Unicode 17.0 emoji-data.txt instead of the latest URL
discard 79df8ed96 Minor: Load bundled Unicode data through one recoverable loader
add a6871186b GH-1408: Rename ArgumentChecks to ParamChecks (#1409)
add 88fcdf119 Minor: Load bundled Unicode data through one recoverable loader
add a2a61fc0a Reference the bundled Unicode 17.0 emoji-data.txt instead of the latest URL
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 (f362af254)
\
N -- N -- N refs/heads/minor-bundled-unicode-data-loader (a2a61fc0a)
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:
.../java/opennlp/tools/document/Annotation.java | 4 +-
.../main/java/opennlp/tools/document/Document.java | 6 +--
.../opennlp/tools/document/DocumentAnalyzer.java | 4 +-
.../opennlp/tools/document/DocumentAnnotators.java | 12 +++---
.../opennlp/tools/document/ImmutableDocument.java | 16 ++++----
.../main/java/opennlp/tools/document/LayerKey.java | 4 +-
.../opennlp/tools/embeddings/TextEmbedder.java | 4 +-
.../src/main/java/opennlp/tools/parser/Parse.java | 4 +-
.../opennlp/tools/sentiment/SentimentSample.java | 6 +--
.../java/opennlp/tools/termvector/TermVector.java | 6 +--
.../java/opennlp/tools/tokenize/SubwordPiece.java | 4 +-
.../opennlp/tools/tokenize/WordpieceEncoder.java | 14 +++----
.../opennlp/tools/tokenize/WordpieceTokenizer.java | 8 ++--
.../java/opennlp/tools/util/CompatibilityMode.java | 2 +-
.../opennlp/tools/util/LanguageCodeValidator.java | 6 +--
.../util/{ArgumentChecks.java => ParamChecks.java} | 4 +-
.../java/opennlp/tools/util/ResourceLimits.java | 8 ++--
.../main/java/opennlp/tools/util/StringUtil.java | 22 +++++-----
.../java/opennlp/tools/util/WhitespaceMode.java | 2 +-
.../java/opennlp/tools/util/ext/ProviderSpec.java | 12 +++---
.../java/opennlp/tools/util/ext/Providers.java | 8 ++--
.../opennlp/tools/util/normalizer/AlignedText.java | 4 +-
.../opennlp/tools/util/normalizer/CharClass.java | 48 +++++++++++-----------
.../tools/util/normalizer/HexCodePoints.java | 14 +++----
...rgumentChecksTest.java => ParamChecksTest.java} | 12 +++---
.../src/main/java/opennlp/dl/AbstractDL.java | 24 +++++------
.../src/main/java/opennlp/dl/JsonScan.java | 6 +--
.../dl/doccat/DocumentCategorizerConfig.java | 4 +-
.../opennlp/dl/doccat/DocumentCategorizerDL.java | 8 ++--
.../java/opennlp/dl/namefinder/NameFinderDL.java | 10 ++---
.../dl/vectors/OnnxTextEmbedderProvider.java | 4 +-
.../java/opennlp/dl/vectors/SentenceVectorsDL.java | 10 ++---
.../tools/ml/model/RealValueFileEventStream.java | 4 +-
.../tools/ml/model/SimpleEventStreamBuilder.java | 4 +-
.../tools/ml/libsvm/doccat/SvmDoccatModel.java | 8 ++--
.../tools/ml/maxent/BasicContextGenerator.java | 4 +-
.../tools/models/AbstractClassPathModelFinder.java | 6 +--
.../opennlp/tools/chunker/ChunkerAnnotator.java | 4 +-
.../tools/lemmatizer/LemmatizerAnnotator.java | 4 +-
.../tools/namefind/NameFinderAnnotator.java | 4 +-
.../java/opennlp/tools/parser/ParserAnnotator.java | 6 +--
.../opennlp/tools/postag/POSTaggerAnnotator.java | 4 +-
.../sentdetect/SentenceDetectorAnnotator.java | 6 +--
.../java/opennlp/tools/stemmer/CachingStemmer.java | 6 +--
.../opennlp/tools/stemmer/DelegatingStemmer.java | 4 +-
.../java/opennlp/tools/stemmer/PorterStemmer.java | 4 +-
.../java/opennlp/tools/stemmer/SharingStemmer.java | 6 +--
.../opennlp/tools/stemmer/StemmerAnnotator.java | 4 +-
.../tools/stemmer/StemmerAnnotatorProvider.java | 6 +--
.../tools/stemmer/hunspell/HunspellDictionary.java | 14 +++----
.../hunspell/HunspellDictionaryDownload.java | 8 ++--
.../tools/stemmer/hunspell/HunspellStemmer.java | 8 ++--
.../stemmer/hunspell/HunspellStemmerFactory.java | 4 +-
.../stemmer/snowball/SnowballStemmerFactory.java | 6 +--
.../tools/stopword/DictionaryStopwordFilter.java | 18 ++++----
.../tools/stopword/StopwordFilterStream.java | 6 +--
.../tools/stopword/StopwordFilteringTokenizer.java | 6 +--
.../java/opennlp/tools/stopword/StopwordLists.java | 8 ++--
.../tools/termvector/TermVectorAnnotator.java | 12 +++---
.../java/opennlp/tools/tokenize/BPETokenizer.java | 8 ++--
.../tools/tokenize/BPETokenizerTrainer.java | 6 +--
.../opennlp/tools/tokenize/TokenizerAnnotator.java | 6 +--
.../tools/tokenize/TokenizerCharacterPolicy.java | 10 ++---
.../tools/tokenize/lattice/LatticeTokenizer.java | 6 +--
.../tools/tokenize/lattice/MecabDictionary.java | 6 +--
.../tokenize/lattice/MecabDictionaryInstaller.java | 12 +++---
.../opennlp/tools/tokenize/lattice/Morpheme.java | 8 ++--
.../tools/tokenize/lattice/UnigramSegmenter.java | 12 +++---
.../tools/tokenize/uax29/WordTokenizer.java | 14 +++----
.../java/opennlp/tools/util/DictionaryCatalog.java | 14 +++----
.../java/opennlp/tools/util/ResourceInstaller.java | 12 +++---
.../java/opennlp/tools/util/archive/TarStream.java | 6 +--
.../AccentFoldCharSequenceNormalizer.java | 4 +-
.../AggregateCharSequenceNormalizer.java | 6 +--
.../tools/util/normalizer/BundledUnicodeData.java | 20 ++++-----
.../normalizer/CaseFoldCharSequenceNormalizer.java | 4 +-
.../ConfusableSkeletonCharSequenceNormalizer.java | 4 +-
.../opennlp/tools/util/normalizer/Confusables.java | 8 ++--
.../normalizer/EmojiCharSequenceNormalizer.java | 4 +-
.../tools/util/normalizer/EmojiEmoticons.java | 4 +-
.../EmojiToEmoticonCharSequenceNormalizer.java | 6 +--
.../EmoticonToEmojiCharSequenceNormalizer.java | 6 +--
.../FullCaseFoldCharSequenceNormalizer.java | 6 +--
.../tools/util/normalizer/MailAddressScan.java | 4 +-
.../util/normalizer/NfcCharSequenceNormalizer.java | 4 +-
.../normalizer/NfkcCharSequenceNormalizer.java | 4 +-
.../util/normalizer/NormalizationProfile.java | 6 +--
.../util/normalizer/NormalizationProfiles.java | 8 ++--
.../normalizer/NumberCharSequenceNormalizer.java | 4 +-
.../normalizer/ShrinkCharSequenceNormalizer.java | 4 +-
.../SocialMediaCharSequenceNormalizer.java | 4 +-
.../java/opennlp/tools/util/normalizer/Term.java | 8 ++--
.../tools/util/normalizer/TermAnalyzer.java | 16 ++++----
.../tools/util/normalizer/TextNormalizer.java | 4 +-
.../util/normalizer/UrlCharSequenceNormalizer.java | 4 +-
.../SpellCheckingCharSequenceNormalizer.java | 14 +++----
.../stream/SpellCorrectingObjectStream.java | 10 ++---
.../stream/SpellCorrectingTokenStream.java | 12 +++---
98 files changed, 386 insertions(+), 386 deletions(-)
rename opennlp-api/src/main/java/opennlp/tools/util/{ArgumentChecks.java => ParamChecks.java} (96%)
rename opennlp-api/src/test/java/opennlp/tools/util/{ArgumentChecksTest.java => ParamChecksTest.java} (82%)