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 2026/10/07 19:14:01 UTC
(opennlp) branch gh-1416-api-javadoc updated (5f0a4c787 -> b056c5862)
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a change to branch gh-1416-api-javadoc
in repository https://gitbox.apache.org/repos/asf/opennlp.git
omit 5f0a4c787 GH-1416: Correct and trim opennlp-api Javadoc
add 19f201e80 GH-1414: Store mvnw.cmd with LF line endings (#1415)
add c98b76298 GH-1398: Add requireNonEmpty and requireNonNegative to ParamChecks (#1413)
add 1fd51808e Spellcheck correction loses the capital of a supplementary-plane initial (#1385)
add 8b8a4dc86 GH-1422: Clean up opennlp-morfologik builder and Javadoc (#1430)
add af742d8bd GH-1422: Clean up NumberUtil and its tests in opennlp-uima (#1432)
add e1a807c47 GH-1388: Load bundled Unicode data through one recoverable loader (#1373)
add 42f446a5a GH-1422: Clean up the spellcheck normalizer and loader (#1431)
add 95b1ac5ff GH-1422: Clean up the report listeners in opennlp-cli (#1429)
add d7eadeda2 GH-1422: Clean up the stemmer, Hunspell and NameFinderDL evals (#1434)
add 0a363d573 GH-1421: Clean up the AD, MASC, CoNLL-U and Brat readers (#1428)
add 97e4fb13f GH-1418: Clean up event parsing and context generators in the ml modules (#1425)
add 0ca246230 GH-1417: Remove duplicated logic in opennlp-api and the lattice tokenizer (#1424)
add b056c5862 GH-1416: Correct and trim opennlp-api Javadoc
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 (5f0a4c787)
\
N -- N -- N refs/heads/gh-1416-api-javadoc (b056c5862)
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:
.github/workflows/maven.yml | 11 +
README.md | 1 +
mvnw.cmd | 378 ++++++++++-----------
.../main/java/opennlp/tools/document/Document.java | 26 +-
.../opennlp/tools/document/DocumentMerges.java | 71 ++++
.../opennlp/tools/document/ImmutableDocument.java | 16 +-
.../java/opennlp/tools/termvector/TermVector.java | 4 +-
.../opennlp/tools/tokenize/BertNormalization.java | 35 ++
.../java/opennlp/tools/tokenize/MappedText.java | 161 +++++++++
.../java/opennlp/tools/tokenize/SubwordPiece.java | 8 +-
.../opennlp/tools/tokenize/WordpieceEncoder.java | 129 +------
.../opennlp/tools/tokenize/WordpieceTokenizer.java | 31 +-
.../main/java/opennlp/tools/util/ParamChecks.java | 134 ++++++++
.../java/opennlp/tools/util/ext/ProviderSpec.java | 4 +-
.../java/opennlp/tools/util/ext/Providers.java | 4 +-
.../opennlp/tools/util/normalizer/CharClass.java | 242 +++++++------
.../tools/util/normalizer/CodePointSet.java | 14 +-
.../tools/util/normalizer/HexCodePoints.java | 12 +
.../opennlp/tools/util/normalizer/UnicodeDash.java | 17 +-
.../tools/util/normalizer/UnicodeWhitespace.java | 36 +-
.../tools/document/DocumentContractTest.java | 4 +
.../opennlp/tools/tokenize/MappedTextTest.java | 88 +++++
.../tools/tokenize/WordpieceEncoderTest.java | 12 +-
.../java/opennlp/tools/util/ParamChecksTest.java | 131 ++++++-
.../tools/util/normalizer/CharClassTest.java | 78 +++--
.../tools/util/normalizer/CodePointSetTest.java | 16 +
.../tools/cmdline/DetailedFMeasureListener.java | 19 ++
.../tools/cmdline/FineGrainedReportListener.java | 53 +--
.../java/opennlp/tools/formats/ad/ADMetadata.java | 29 +-
.../tools/formats/ad/ADNameSampleStream.java | 31 +-
.../tools/formats/ad/ADSentenceSampleStream.java | 8 +-
.../tools/formats/brat/BratAnnotationStream.java | 7 +-
.../opennlp/tools/formats/conllu/ConlluStream.java | 3 +-
.../tools/formats/ad/ADNameSampleStreamTest.java | 3 +-
.../formats/ad/ADSentenceSampleStreamTest.java | 5 +-
.../tools/formats/masc/MascParserTestUtil.java | 3 +-
.../dl/vectors/OnnxTextEmbedderProvider.java | 4 +-
.../src/main/java/opennlp/tools/ml/BeamSearch.java | 62 ++--
.../java/opennlp/tools/ml/model/EventFields.java | 37 +-
.../opennlp/tools/ml/model/FileEventStream.java | 8 +-
.../tools/ml/model/RealValueFileEventStream.java | 41 +--
.../tools/ml/model/SimpleEventStreamBuilder.java | 24 +-
.../ml/model/RealValueFileEventStreamTest.java | 38 ++-
.../ml/model/SimpleEventStreamBuilderTest.java | 43 ++-
.../tools/ml/maxent/BasicContextGenerator.java | 13 +-
.../tools/ml/maxent/RealBasicEventStream.java | 11 +-
.../tools/ml/maxent/BasicContextGeneratorTest.java | 3 +-
.../tools/ml/maxent/RealBasicEventStreamTest.java | 37 +-
.../tools/stemmer/hunspell/HunspellDictionary.java | 8 +-
.../tools/tokenize/lattice/LatticeTokenizer.java | 17 +-
.../tools/tokenize/lattice/MecabDictionary.java | 28 +-
.../tools/tokenize/lattice/UnigramSegmenter.java | 37 +-
.../tools/tokenize/lattice/WhitespaceRuns.java | 65 ++++
.../tools/tokenize/uax29/ExtendedPictographic.java | 91 ++---
.../tools/tokenize/uax29/WordBreakProperty.java | 109 +++---
.../java/opennlp/tools/util/ResourceInstaller.java | 4 +-
.../tools/util/normalizer/BundledUnicodeData.java | 204 +++++++++++
.../opennlp/tools/util/normalizer/Confusables.java | 90 +++--
.../tools/util/normalizer/EmojiAnnotations.java | 105 +++---
.../tools/util/normalizer/EmojiEmoticons.java | 92 +++--
.../FullCaseFoldCharSequenceNormalizer.java | 91 +++--
.../util/normalizer/UnicodeEmojiSequences.java | 79 ++---
.../tools/tokenize/WordpieceTokenizerTest.java | 11 +-
.../util/normalizer/BundledUnicodeDataTest.java | 161 +++++++++
opennlp-docs/src/docbkx/corpora.xml | 7 +-
opennlp-docs/src/docbkx/spellcheck.xml | 14 +
.../opennlp/dl/namefinder/NameFinderDLEval.java | 98 ++++--
.../java/opennlp/tools/eval/AbstractEvalTest.java | 29 ++
.../tools/eval/HunspellClassificationEval.java | 80 +++++
.../tools/eval/HunspellCompatibilityEval.java | 43 +--
.../tools/eval/MultiThreadedStemmerEval.java | 94 +++--
.../builder/MorfologikDictionaryBuilder.java | 14 +-
.../lemmatizer/MorfologikLemmatizer.java | 2 +
.../tagdict/MorfologikTagDictionary.java | 3 +-
.../opennlp/morfologik/AbstractMorfologikTest.java | 6 +-
.../dictionary/FrequencyDictionaryLoader.java | 3 +-
.../spellcheck/dictionary/SymSpellModel.java | 13 +-
.../dictionary/SymSpellModelResolver.java | 8 +-
.../SpellCheckingCharSequenceNormalizer.java | 69 ++--
.../SpellCheckingCharSequenceNormalizerTest.java | 60 ++--
.../normalizer/SpellCheckingUnicodeCaseTest.java | 116 +++++++
.../java/opennlp/uima/normalizer/NumberUtil.java | 7 +-
.../opennlp/uima/normalizer/NumberUtilTest.java | 26 +-
83 files changed, 2671 insertions(+), 1358 deletions(-)
create mode 100644 opennlp-api/src/main/java/opennlp/tools/document/DocumentMerges.java
create mode 100644 opennlp-api/src/main/java/opennlp/tools/tokenize/MappedText.java
create mode 100644 opennlp-api/src/test/java/opennlp/tools/tokenize/MappedTextTest.java
create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/tokenize/lattice/WhitespaceRuns.java
create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/BundledUnicodeData.java
create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/BundledUnicodeDataTest.java
create mode 100644 opennlp-eval-tests/src/test/java/opennlp/tools/eval/HunspellClassificationEval.java
create mode 100644 opennlp-extensions/opennlp-spellcheck/src/test/java/opennlp/spellcheck/normalizer/SpellCheckingUnicodeCaseTest.java