This is an automated email from the ASF dual-hosted git repository.
krickert pushed a change to branch OPENNLP-1850-1-foundation
in repository https://gitbox.apache.org/repos/asf/opennlp.git
from 7b5dfff77 OPENNLP-1850 Address Copilot review on the normalization
foundation
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
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/tools/util/normalizer/Confusables.java | 47 ++-
.../tools/util/normalizer/CharClassTest.java | 424 ---------------------
16 files changed, 1045 insertions(+), 754 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