This is an automated email from the ASF dual-hosted git repository.
krickert pushed a change to branch OPENNLP-1850-3-dl
in repository https://gitbox.apache.org/repos/asf/opennlp.git
discard 8534bb36f OPENNLP-1850 Make DL entity spans offset-safe under input
normalization
discard 39616baad OPENNLP-1850 Offset-safe input normalization in the DL
components
discard 67c922aea OPENNLP-1850 Address Copilot review on the UAX #29 tokenizer
discard b493f8959 OPENNLP-1850 UAX #29 word tokenizer and the layered Term
model
add 7c58c0c7d OPENNLP-1850 Add Alignment offset model; move normalizer
engine to opennlp-api
add 463f95129 OPENNLP-1850 Report the offending line on malformed
confusables data
add d55353c13 OPENNLP-1850 Add edge-case tests for the aligned offset API
add b445a90b0 OPENNLP-1850 UAX #29 word tokenizer and the layered Term
model
add be5eb5d1a OPENNLP-1850 Address Copilot review on the UAX #29 tokenizer
add 81aa6c5f0 OPENNLP-1850 Address tokenizer review comments
add 5154da457 OPENNLP-1850 Offset-safe, Unicode-aware input normalization
in the DL components
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 (8534bb36f)
\
N -- N -- N refs/heads/OPENNLP-1850-3-dl (5154da457)
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:
.../opennlp/tools/util/normalizer/AlignedText.java | 58 +++
.../opennlp/tools/util/normalizer/Alignment.java | 284 ++++++++++++++
.../opennlp/tools/util/normalizer/CharClass.java | 164 ++++++--
.../tools/util/normalizer/CodePointSet.java | 0
.../tools/util/normalizer/NormalizedText.java | 51 ---
.../opennlp/tools/util/normalizer/OffsetMap.java | 140 -------
.../opennlp/tools/util/normalizer/UnicodeDash.java | 0
.../tools/util/normalizer/UnicodeWhitespace.java | 0
.../tools/util/normalizer/AlignmentTest.java | 181 +++++++++
.../tools/util/normalizer/CharClassTest.java | 361 ++++++++++++++++++
.../tools/util/normalizer/CodePointSetTest.java | 0
.../tools/util/normalizer/OffsetMapTest.java | 89 -----
.../tools/util/normalizer/UnicodeDashTest.java | 0
.../util/normalizer/UnicodeWhitespaceTest.java | 0
opennlp-core/opennlp-ml/opennlp-dl/README.md | 8 +-
opennlp-core/opennlp-ml/opennlp-dl/pom.xml | 5 +-
.../src/main/java/opennlp/dl/AbstractDL.java | 48 +--
.../java/opennlp/dl/namefinder/NameFinderDL.java | 38 +-
.../java/opennlp/dl/AbstractDLChunkingTest.java | 39 +-
.../tools/tokenize/uax29/WordSegmenter.java | 9 +-
.../tools/tokenize/uax29/WordTokenizer.java | 3 +
.../opennlp/tools/tokenize/uax29/WordType.java | 2 +-
.../opennlp/tools/util/normalizer/Confusables.java | 47 ++-
.../java/opennlp/tools/util/normalizer/Term.java | 8 +
.../tools/util/normalizer/CharClassTest.java | 424 ---------------------
25 files changed, 1141 insertions(+), 818 deletions(-)
create mode 100644
opennlp-api/src/main/java/opennlp/tools/util/normalizer/AlignedText.java
create mode 100644
opennlp-api/src/main/java/opennlp/tools/util/normalizer/Alignment.java
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/main/java/opennlp/tools/util/normalizer/CharClass.java (69%)
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/main/java/opennlp/tools/util/normalizer/CodePointSet.java
(100%)
delete mode 100644
opennlp-api/src/main/java/opennlp/tools/util/normalizer/NormalizedText.java
delete mode 100644
opennlp-api/src/main/java/opennlp/tools/util/normalizer/OffsetMap.java
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/main/java/opennlp/tools/util/normalizer/UnicodeDash.java (100%)
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/main/java/opennlp/tools/util/normalizer/UnicodeWhitespace.java
(100%)
create mode 100644
opennlp-api/src/test/java/opennlp/tools/util/normalizer/AlignmentTest.java
create mode 100644
opennlp-api/src/test/java/opennlp/tools/util/normalizer/CharClassTest.java
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/test/java/opennlp/tools/util/normalizer/CodePointSetTest.java
(100%)
delete mode 100644
opennlp-api/src/test/java/opennlp/tools/util/normalizer/OffsetMapTest.java
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/test/java/opennlp/tools/util/normalizer/UnicodeDashTest.java
(100%)
rename {opennlp-core/opennlp-runtime =>
opennlp-api}/src/test/java/opennlp/tools/util/normalizer/UnicodeWhitespaceTest.java
(100%)
delete mode 100644
opennlp-core/opennlp-runtime/src/test/java/opennlp/tools/util/normalizer/CharClassTest.java