This is an automated email from the ASF dual-hosted git repository.
krickert pushed a change to branch OPENNLP-1870
in repository https://gitbox.apache.org/repos/asf/opennlp.git
discard ce0a188da OPENNLP-1870: Read the fold table through the Direction
accessor in the annotation audit
discard e43943b99 OPENNLP-1870: Wire emoji annotations as opt-in features for
NameFinder, Doccat, and Sentiment
discard 89742e06c OPENNLP-1870: EmojiAnnotator, the opt-in Term-adjacent
annotation surface
discard f682f38db OPENNLP-1870: Derived flag facts: ISO 3166 decoding from
flag emoji sequences
discard b7fbcd9bb OPENNLP-1870: Emoji annotation record store with bundled
facts and audit
add 9796b1a09 Allowlist based class Instantiation (#1178)
add 4a435d3c3 OPENNLP-1890: Using allowlist based class loading in
StreamFactoryRegistry
add fa79a5243 OPENNLP-1890: Using allowlist based class loading in
StringInterners
add db7adf0a6 OPENNLP-1876: Replace regex with cursor scans in the legacy
CharSequenceNormalizers (#1151)
add 16b82540d Bump actions/setup-java from 5.5.0 to 5.6.0 (#1184)
add 2ae4146b9 OPENNLP-1875: Align whitespace handling with the Unicode
White_Space property (#1150)
add b181fa03b OPENNLP-1870: Emoji annotation record store with bundled
facts and audit
add 38d907bd3 OPENNLP-1870: Derived flag facts: ISO 3166 decoding from
flag emoji sequences
add 697bcf7f0 OPENNLP-1870: EmojiAnnotator, the opt-in Term-adjacent
annotation surface
add 55e2daf4a OPENNLP-1870: Wire emoji annotations as opt-in features for
NameFinder, Doccat, and Sentiment
add 80bac3e01 OPENNLP-1870: Read the fold table through the Direction
accessor in the annotation audit
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 (ce0a188da)
\
N -- N -- N refs/heads/OPENNLP-1870 (80bac3e01)
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/license.yml | 2 +-
.github/workflows/maven.yml | 8 +-
.github/workflows/publish-snapshots.yml | 2 +-
.../main/java/opennlp/tools/util/StringUtil.java | 173 +++++-
.../java/opennlp/tools/util/WhitespaceMode.java | 134 +++++
.../util/normalizer/CharSequenceNormalizer.java | 2 +-
.../opennlp/tools/util/WhitespaceModeTest.java | 130 +++++
.../tools/cmdline/stopword/StopwordFilterTool.java | 5 +-
.../tools/cmdline/StreamFactoryRegistry.java | 27 +-
.../tools/cmdline/StreamFactoryRegistryTest.java | 82 +++
.../tools/langdetect/LanguageDetectorFactory.java | 15 +-
.../sentdetect/DefaultSDContextGenerator.java | 6 +-
.../tools/stopword/DictionaryStopwordFilter.java | 9 +-
.../tokenize/DefaultTokenContextGenerator.java | 6 +
.../tools/util/featuregen/GeneratorFactory.java | 45 +-
.../tools/util/jvm/CHMStringDeduplicator.java | 2 +-
.../opennlp/tools/util/jvm/CHMStringInterner.java | 2 +-
.../opennlp/tools/util/jvm/HMStringInterner.java | 2 +-
.../opennlp/tools/util/jvm/JvmStringInterner.java | 2 +-
.../opennlp/tools/util/jvm/NoOpStringInterner.java | 2 +-
.../opennlp/tools/util/jvm/StringInterners.java | 12 +-
.../AccentFoldCharSequenceNormalizer.java | 6 +-
.../AggregateCharSequenceNormalizer.java | 4 +
.../opennlp/tools/util/normalizer/AsciiChars.java | 77 +++
.../normalizer/CaseFoldCharSequenceNormalizer.java | 6 +-
.../ConfusableSkeletonCharSequenceNormalizer.java | 6 +-
.../normalizer/EmojiCharSequenceNormalizer.java | 4 +
.../util/normalizer/NfcCharSequenceNormalizer.java | 6 +-
.../normalizer/NfkcCharSequenceNormalizer.java | 6 +-
.../normalizer/NumberCharSequenceNormalizer.java | 33 +-
.../normalizer/ShrinkCharSequenceNormalizer.java | 128 ++++-
.../SocialMediaCharSequenceNormalizer.java | 306 ++++++++++
.../normalizer/TwitterCharSequenceNormalizer.java | 55 --
.../util/normalizer/UrlCharSequenceNormalizer.java | 192 ++++++-
.../SentenceDetectorMESpanMappingTest.java | 14 +
.../tokenize/DefaultTokenContextGeneratorTest.java | 80 +++
.../tools/tokenize/SimpleTokenizerTest.java | 46 ++
.../tools/tokenize/WhitespaceTokenizerTest.java | 46 ++
.../util/featuregen/GeneratorFactoryTest.java | 46 +-
.../tools/util/jvm/StringInternersTest.java | 74 +++
.../CharSequenceNormalizerContractTest.java | 88 +++
.../util/normalizer/CharacterizationInputs.java | 51 ++
...CharSequenceNormalizerCharacterizationTest.java | 102 ++++
...CharSequenceNormalizerCharacterizationTest.java | 166 ++++++
...CharSequenceNormalizerCharacterizationTest.java | 198 +++++++
...CharSequenceNormalizerCharacterizationTest.java | 204 +++++++
opennlp-docs/src/docbkx/introduction.xml | 50 ++
opennlp-docs/src/docbkx/tokenizer.xml | 5 +
.../opennlp/tools/eval/SourceForgeModelEval.java | 19 +
.../spellcheck/cmdline/CorrectTextTool.java | 6 +-
.../SpellCheckingCharSequenceNormalizer.java | 211 +++++--
.../stream/SpellCorrectingObjectStream.java | 31 +-
.../stream/SpellCorrectingTokenStream.java | 67 ++-
.../java/opennlp/spellcheck/symspell/SymSpell.java | 9 +-
.../SpellCheckingCharSequenceNormalizerTest.java | 122 +++-
.../stream/SpellCorrectingObjectStreamTest.java | 16 +-
.../stream/SpellCorrectingTokenStreamTest.java | 47 ++
.../spellcheck/symspell/SymSpellCompoundTest.java | 64 +++
.../java/opennlp/uima/normalizer/NumberUtil.java | 26 +-
.../opennlp/uima/normalizer/NumberUtilTest.java | 32 ++
.../java/opennlp/tools/util/StringUtilTest.java | 623 ++++++++++++++++++++-
.../TwitterCharSequenceNormalizerTest.java | 61 --
62 files changed, 3647 insertions(+), 354 deletions(-)
create mode 100644
opennlp-api/src/main/java/opennlp/tools/util/WhitespaceMode.java
create mode 100644
opennlp-api/src/test/java/opennlp/tools/util/WhitespaceModeTest.java
create mode 100644
opennlp-core/opennlp-formats/src/test/java/opennlp/tools/cmdline/StreamFactoryRegistryTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/AsciiChars.java
create mode 100644
opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/SocialMediaCharSequenceNormalizer.java
delete mode 100644
opennlp-core/opennlp-runtime/src/main/java/opennlp/tools/util/normalizer/TwitterCharSequenceNormalizer.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/tokenize/DefaultTokenContextGeneratorTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/jvm/StringInternersTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/CharSequenceNormalizerContractTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/CharacterizationInputs.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/NumberCharSequenceNormalizerCharacterizationTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/ShrinkCharSequenceNormalizerCharacterizationTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/SocialMediaCharSequenceNormalizerCharacterizationTest.java
create mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/UrlCharSequenceNormalizerCharacterizationTest.java
delete mode 100644
opennlp-tools/src/test/java/opennlp/tools/util/normalizer/TwitterCharSequenceNormalizerTest.java
