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 2026/09/30 18:54:01 UTC
(opennlp) branch OPENNLP-1975-regex-removal-output-fixes updated (0a2c0f9b1 -> 4ea6f1c71)
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a change to branch OPENNLP-1975-regex-removal-output-fixes
in repository https://gitbox.apache.org/repos/asf/opennlp.git
omit 0a2c0f9b1 OPENNLP-1975: Correct token, parser and resource scan behavior
add 9e8bfa01b Bump onnxruntime.version from 1.29.0 to 1.30.0 (#1329)
add 9383dfeef Bump org.codehaus.mojo:build-helper-maven-plugin from 3.6.1 to 3.6.2 (#1326)
add e8af18518 Minor: Regenerated NOTICE File for 9383dfeef3dd38371147ca7d92a5d92d17756d3a (#1331)
add c9e6fae69 Replace JIRA references with GitHub Issues (#1317)
add f8a45086d Run a single smoke build for draft pull requests (#1332)
add e88980c5c OPENNLP-1931: Fix JSON vocabulary and config parsing in opennlp-dl (#1277)
add dcd63490c OPENNLP-1933: Remove regex from dictionary file handling (#1320)
add 9551abb1f Bump de.thetaphi:forbiddenapis from 3.10 to 3.11 (#1334)
add 655760e6f Bump io.github.classgraph:classgraph from 4.8.195 to 4.8.196 (#1340)
add 6651704c0 Bump org.apache:apache from 39 to 40 (#1341)
add 7fd38560e Bump slf4j.version from 2.0.19 to 2.0.20 (#1338)
add 7b1dccfb6 OPENNLP-1927: Expand Hunspell dictionary support (#1270)
add 318e632a7 Minor: Regenerated NOTICE File for 7b1dccfb6aecfad8f2c85da69e7463078356aef3 (#1344)
add e6ad7ee54 OPENNLP-1932: Regex removal (4/10): Match model finder wildcards without regular expressions (#1278)
add 13d8ecf97 OPENNLP-1990: Regex removal (5c/10): Validate MASC identifiers and anchors (#1322)
add b53d6a3b9 OPENNLP-1989: Regex removal (5b/10): Preserve feature identities in event parsing (#1321)
add 4ea6f1c71 OPENNLP-1975: Correct token, parser and resource scan behavior
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 (0a2c0f9b1)
\
N -- N -- N refs/heads/OPENNLP-1975-regex-removal-output-fixes (4ea6f1c71)
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 | 5 +-
.github/PULL_REQUEST_TEMPLATE.md | 6 +-
.github/workflows/maven.yml | 18 +-
NOTICE | 8 +-
README.md | 6 +-
dev/README-hunspell-dictionaries.md | 170 +-
.../main/java/opennlp/tools/util/StringUtil.java | 82 +
.../tools/util/StringUtilByteOrderMarkTest.java | 62 +
.../tools/util/StringUtilSplitNonEmptyTest.java | 111 ++
.../leipzig/LeipzigLanguageSampleStream.java | 30 +-
.../opennlp/tools/formats/masc/MascDocument.java | 10 +-
.../tools/formats/masc/MascIdentifiers.java | 189 ++
.../tools/formats/masc/MascNamedEntityParser.java | 12 +-
.../tools/formats/masc/MascPennTagParser.java | 18 +-
.../tools/formats/masc/MascSentenceParser.java | 10 +-
.../java/opennlp/tools/formats/masc/MascWord.java | 2 +-
.../opennlp/tools/formats/masc/MascWordParser.java | 16 +-
.../leipzig/LeipzigLanguageSampleStreamTest.java | 42 +
.../tools/formats/masc/MascDocumentTest.java | 82 +
.../tools/formats/masc/MascIdentifiersTest.java | 107 +
.../formats/masc/MascNamedEntityParserTest.java | 70 +
.../tools/formats/masc/MascParserTestUtil.java | 86 +
.../tools/formats/masc/MascPennTagParserTest.java | 92 +
.../tools/formats/masc/MascSentenceParserTest.java | 68 +
.../tools/formats/masc/MascWordParserTest.java | 87 +
.../src/main/java/opennlp/dl/AbstractDL.java | 128 +-
.../src/main/java/opennlp/dl/JsonScan.java | 651 +++++++
.../dl/doccat/DocumentCategorizerConfig.java | 51 +-
.../opennlp/dl/doccat/DocumentCategorizerDL.java | 50 +-
.../java/opennlp/dl/namefinder/NameFinderDL.java | 4 +
.../java/opennlp/dl/vectors/SentenceVectorsDL.java | 4 +
.../src/test/java/opennlp/dl/JsonScanTest.java | 454 +++++
.../src/test/java/opennlp/dl/LoadVocabTest.java | 227 ++-
.../dl/doccat/DocumentCategorizerConfigTest.java | 175 ++
.../dl/doccat/DocumentCategorizerDLTest.java | 33 +
.../java/opennlp/tools/ml/model/EventFields.java | 78 +
.../opennlp/tools/ml/model/FileEventStream.java | 19 +-
.../tools/ml/model/RealValueFileEventStream.java | 44 +-
.../tools/ml/model/SimpleEventStreamBuilder.java | 81 +-
.../opennlp/tools/ml/AbstractEventStreamTest.java | 8 +
.../tools/ml/model/FileEventStreamTest.java | 29 +
.../ml/model/RealValueFileEventStreamTest.java | 220 ++-
.../ml/model/SimpleEventStreamBuilderTest.java | 217 +++
.../tools/ml/maxent/RealBasicEventStream.java | 29 +-
.../tools/ml/maxent/RealBasicEventStreamTest.java | 31 +-
opennlp-core/opennlp-model-resolver/pom.xml | 5 +
.../tools/models/AbstractClassPathModelFinder.java | 54 +-
.../java/opennlp/tools/models/WildcardMatcher.java | 76 +
.../tools/models/dir/DirectoryModelFinder.java | 17 +-
.../models/simple/SimpleClassPathModelFinder.java | 35 +-
.../models/AbstractClassPathModelFinderTest.java | 230 +++
.../opennlp/tools/models/ModelFinderPathTest.java | 173 ++
.../java/opennlp/tools/models/UnescapedUrls.java | 56 +
.../opennlp/tools/models/WildcardMatcherTest.java | 234 +++
.../tools/models/dir/DirectoryModelFinderTest.java | 130 ++
.../simple/SimpleClassPathModelFinderTest.java | 78 +
opennlp-core/opennlp-runtime/pom.xml | 2 +-
.../tools/stemmer/hunspell/HunspellAffixTable.java | 84 +
.../stemmer/hunspell/HunspellCompoundRule.java | 157 ++
.../tools/stemmer/hunspell/HunspellConversion.java | 204 ++
.../tools/stemmer/hunspell/HunspellDictionary.java | 2061 +++++++++++++++++---
.../tools/stemmer/hunspell/HunspellStemmer.java | 1421 ++++++++++++--
.../hunspell/HunspellCompatibilityTest.java | 480 +++++
.../stemmer/hunspell/HunspellCompletionTest.java | 410 ++++
.../stemmer/hunspell/HunspellConversionTest.java | 65 +
.../hunspell/HunspellDictionaryLoadTest.java | 538 +++++
.../hunspell/HunspellManualExampleTest.java | 28 +
.../hunspell/HunspellRealDictionaryTest.java | 126 --
.../stemmer/hunspell/HunspellStemmerTest.java | 174 +-
opennlp-distr/README_FOOTER.html | 11 +-
opennlp-distr/pom.xml | 28 -
opennlp-distr/src/main/assembly/bin.xml | 7 -
opennlp-distr/src/main/readme/NOTICE | 8 +-
opennlp-docs/src/docbkx/coref.xml | 3 +-
opennlp-docs/src/docbkx/corpora.xml | 27 +
opennlp-docs/src/docbkx/doccat.xml | 13 +
opennlp-docs/src/docbkx/langdetect.xml | 8 +-
opennlp-docs/src/docbkx/machine-learning.xml | 18 +-
opennlp-docs/src/docbkx/model-loading.xml | 17 +
opennlp-docs/src/docbkx/parser.xml | 6 +-
opennlp-docs/src/docbkx/spellcheck.xml | 8 +-
opennlp-docs/src/docbkx/stemmer.xml | 147 +-
.../tools/eval/HunspellCompatibilityEval.java | 401 ++++
opennlp-extensions/opennlp-morfologik/pom.xml | 6 +
.../builder/MorfologikDictionaryBuilder.java | 25 +-
.../builder/MorfologikDictionaryBuilderTest.java | 24 +-
opennlp-extensions/opennlp-spellcheck/pom.xml | 6 +
.../dictionary/FrequencyDictionaryLoader.java | 159 +-
.../dictionary/FrequencyDictionaryLoaderTest.java | 260 +++
.../dictionary/SymSpellModelSerializationTest.java | 26 -
pom.xml | 14 +-
91 files changed, 10901 insertions(+), 1081 deletions(-)
create mode 100644 opennlp-api/src/test/java/opennlp/tools/util/StringUtilByteOrderMarkTest.java
create mode 100644 opennlp-api/src/test/java/opennlp/tools/util/StringUtilSplitNonEmptyTest.java
create mode 100644 opennlp-core/opennlp-formats/src/main/java/opennlp/tools/formats/masc/MascIdentifiers.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascDocumentTest.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascIdentifiersTest.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascNamedEntityParserTest.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascParserTestUtil.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascPennTagParserTest.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascSentenceParserTest.java
create mode 100644 opennlp-core/opennlp-formats/src/test/java/opennlp/tools/formats/masc/MascWordParserTest.java
create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/main/java/opennlp/dl/JsonScan.java
create mode 100644 opennlp-core/opennlp-ml/opennlp-dl/src/test/java/opennlp/dl/JsonScanTest.java
create mode 100644 opennlp-core/opennlp-ml/opennlp-ml-commons/src/main/java/opennlp/tools/ml/model/EventFields.java
create mode 100644 opennlp-core/opennlp-ml/opennlp-ml-commons/src/test/java/opennlp/tools/ml/model/SimpleEventStreamBuilderTest.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/main/java/opennlp/tools/models/WildcardMatcher.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/test/java/opennlp/tools/models/AbstractClassPathModelFinderTest.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/test/java/opennlp/tools/models/ModelFinderPathTest.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/test/java/opennlp/tools/models/UnescapedUrls.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/test/java/opennlp/tools/models/WildcardMatcherTest.java
create mode 100644 opennlp-core/opennlp-model-resolver/src/test/java/opennlp/tools/models/dir/DirectoryModelFinderTest.java
create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/hunspell/HunspellAffixTable.java
create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/hunspell/HunspellCompoundRule.java
create mode 100644 opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/stemmer/hunspell/HunspellConversion.java
create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/stemmer/hunspell/HunspellCompatibilityTest.java
create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/stemmer/hunspell/HunspellCompletionTest.java
create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/stemmer/hunspell/HunspellConversionTest.java
create mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/stemmer/hunspell/HunspellDictionaryLoadTest.java
delete mode 100644 opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/stemmer/hunspell/HunspellRealDictionaryTest.java
create mode 100644 opennlp-eval-tests/src/test/java/opennlp/tools/eval/HunspellCompatibilityEval.java
create mode 100644 opennlp-extensions/opennlp-spellcheck/src/test/java/opennlp/spellcheck/dictionary/FrequencyDictionaryLoaderTest.java