This is an automated email from the ASF dual-hosted git repository.
nightowl888 pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/lucenenet.git.
from 472cc20 Lucene.Net.TestFramework: Implemented dispose pattern where
applicable
new 4ed5304 Refactored Lucene.Net.ICU to utilize ICU4N instead of icu.net
+ added all missing functionality and tests from Java Lucene (100% passing).
This is built against ICU4N 60.1.0-alpha.22.ga154ecb7c2 (which corresponds to
ICU 60.1 and is about 40% of the total ICU4J package). Added Lucene version
compatibility level to each file, as some files have been ported from Lucene
7.1.0.
new 50e21e4 Upgraded to ICU4N 60.1.0-alpha.46
The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
build/Dependencies.props | 8 +-
.../Analysis/Th/ThaiAnalyzer.cs | 2 +-
.../Analysis/Th/ThaiTokenizer.cs | 51 +-
.../Analysis/Th/ThaiWordFilter.cs | 24 +-
.../Analysis/Util/CharArrayIterator.cs | 64 ++-
.../Analysis/Util/SegmentingTokenizerBase.cs | 6 +-
.../Analysis/Icu/Data/uax29/Default.rbbi | 186 ++++++++
.../Analysis/Icu/Data/uax29/MyanmarSyllable.rbbi | 50 ++
.../Analysis/Icu/ICUFoldingFilter.cs | 127 +++--
.../Analysis/Icu/ICUFoldingFilterFactory.cs | 102 ++--
.../Analysis/Icu/ICUNormalizer2CharFilter.cs | 516 +++++++++++----------
.../Icu/ICUNormalizer2CharFilterFactory.cs | 164 ++++---
.../Analysis/Icu/ICUNormalizer2Filter.cs | 169 ++++---
.../Analysis/Icu/ICUNormalizer2FilterFactory.cs | 164 ++++---
.../Analysis/Icu/ICUTransformFilter.cs | 367 ++++++++-------
.../Analysis/Icu/ICUTransformFilterFactory.cs | 113 +++--
.../Icu/Segmentation/BreakIteratorWrapper.cs | 363 +++++++--------
.../Analysis/Icu/Segmentation/CharArrayIterator.cs | 17 +-
.../Icu/Segmentation/CompositeBreakIterator.cs | 264 +++++------
.../Analysis/Icu/Segmentation/Default.brk | Bin 0 -> 38720 bytes
.../Icu/Segmentation/DefaultICUTokenizerConfig.cs | 276 +++++------
.../Analysis/Icu/Segmentation/ICUTokenizer.cs | 493 ++++++++++----------
.../Icu/Segmentation/ICUTokenizerConfig.cs | 97 ++--
.../Icu/Segmentation/ICUTokenizerFactory.cs | 307 ++++++------
.../Analysis/Icu/Segmentation/MyanmarSyllable.brk | Bin 0 -> 22728 bytes
.../Analysis/Icu/Segmentation/ScriptIterator.cs | 429 ++++++++---------
.../Icu/TokenAttributes/ScriptAttribute.cs | 103 ++--
.../Icu/TokenAttributes/ScriptAttributeImpl.cs | 168 +++----
src/Lucene.Net.Analysis.ICU/Analysis/Icu/utr30.nrm | Bin 0 -> 59044 bytes
.../Collation/ICUCollationAttributeFactory.cs | 20 +-
.../Collation/ICUCollationDocValuesField.cs | 26 +-
.../Collation/ICUCollationKeyAnalyzer.cs | 20 +-
.../Collation/ICUCollationKeyFilter.cs | 26 +-
.../Collation/ICUCollationKeyFilterFactory.cs | 59 +--
.../ICUCollatedTermAttributeImpl.cs | 26 +-
.../HMMChineseTokenizer.cs | 8 +-
.../Lucene.Net.Analysis.SmartCn.csproj | 6 +-
.../ByTask/Tasks/NewCollationAnalyzerTask.cs | 11 +-
.../ByTask/Tasks/WriteLineDocTask.cs | 2 +-
src/Lucene.Net.Benchmark/ByTask/Utils/Algorithm.cs | 3 +-
.../ByTask/Utils/StreamUtils.cs | 2 +-
.../Lucene.Net.Benchmark.csproj | 2 +-
.../PostingsHighlight/CambridgeMA.utf8 | 1 -
.../PostingsHighlight/PostingsHighlighter.cs | 19 +-
.../PostingsHighlight/WholeBreakIterator.cs | 36 +-
.../BreakIteratorBoundaryScanner.cs | 2 +-
.../Analysis/CollationTestBase.cs | 6 +-
.../Lucene.Net.TestFramework.csproj | 1 -
.../Analysis/Th/TestThaiAnalyzer.cs | 3 +-
.../Analysis/Th/TestThaiTokenizerFactory.cs | 6 +-
.../Analysis/Th/TestThaiWordFilterFactory.cs | 6 +-
.../Analysis/Util/TestCharArrayIterator.cs | 34 +-
.../Analysis/Util/TestSegmentingTokenizerBase.cs | 10 +-
.../Icu/Segmentation/KeywordTokenizer.rbbi} | 10 +-
.../Latin-break-only-on-whitespace.rbbi | 40 ++
.../Segmentation/Latin-dont-break-on-hyphens.rbbi | 135 ++++++
.../Icu/Segmentation/TestCharArrayIterator.cs | 15 +-
.../Analysis/Icu/Segmentation/TestICUTokenizer.cs | 417 +++++++++++++++++
.../Icu/Segmentation/TestICUTokenizerCJK.cs | 128 +++++
.../Icu/Segmentation/TestICUTokenizerFactory.cs | 115 +++++
.../Icu/Segmentation/TestMyanmarSyllable.cs | 201 ++++++++
.../Icu/Segmentation/TestWithCJKBigramFilter.cs | 261 +++++++++++
.../Analysis/Icu/TestICUFoldingFilter.cs | 112 +++++
.../Analysis/Icu/TestICUFoldingFilterFactory.cs} | 31 +-
.../Analysis/Icu/TestICUNormalizer2CharFilter.cs | 462 ++++++++++++++++++
.../Icu/TestICUNormalizer2CharFilterFactory.cs} | 29 +-
.../Analysis/Icu/TestICUNormalizer2Filter.cs | 194 ++++----
.../Icu/TestICUNormalizer2FilterFactory.cs | 115 +++--
.../Analysis/Icu/TestICUTransformFilter.cs | 118 +++++
.../Analysis/Icu/TestICUTransformFilterFactory.cs | 98 ++++
.../Collation/TestICUCollationDocValuesField.cs | 10 +-
.../Collation/TestICUCollationKeyAnalyzer.cs | 22 +-
.../Collation/TestICUCollationKeyFilter.cs | 20 +-
.../Collation/TestICUCollationKeyFilterFactory.cs | 69 ++-
.../ByTask/Tasks/WriteLineDocTaskTest.cs | 10 +-
.../ByTask/TestPerfTasksLogic.cs | 10 +-
.../Lucene.Net.Tests.Benchmark.csproj | 6 +-
.../PostingsHighlight/TestPostingsHighlighter.cs | 79 +---
.../PostingsHighlight/TestWholeBreakIterator.cs | 21 +-
.../BreakIteratorBoundaryScannerTest.cs | 15 +-
src/Lucene.Net/Analysis/CharFilter.cs | 12 +
src/Lucene.Net/Support/Character.cs | 25 +
.../Lucene.Net.ICU/Analysis/Th/stopwords.txt | 119 -----
src/dotnet/Lucene.Net.ICU/Data/jdk7/jdksent.rbbi | 134 ++++++
src/dotnet/Lucene.Net.ICU/Data/jdk7/jdkword.rbbi | 229 +++++++++
src/dotnet/Lucene.Net.ICU/Lucene.Net.ICU.csproj | 12 +-
src/dotnet/Lucene.Net.ICU/Support/BreakIterator.cs | 248 ----------
.../Lucene.Net.ICU/Support/CharacterIterator.cs | 50 --
.../Support/Document/DocumentExtensions.cs | 2 +-
.../Lucene.Net.ICU/Support/IcuBreakIterator.cs | 393 ----------------
.../Lucene.Net.ICU/Support/JDKBreakIterator.cs | 98 ++++
.../Support/StringCharacterIterator.cs | 204 --------
src/dotnet/Lucene.Net.ICU/Support/jdksent.brk | Bin 0 -> 37136 bytes
src/dotnet/Lucene.Net.ICU/Support/jdkword.brk | Bin 0 -> 59656 bytes
.../Lucene.Net.Tests.ICU.csproj | 12 +-
.../Support/TestApiConsistency.cs | 34 +-
.../Support/TestIcuBreakIterator.cs | 421 -----------------
.../Support/TestJDKBreakIterator.cs | 354 ++++++++++++++
src/dotnet/tools/lucene-cli/lucene-cli.csproj | 4 -
99 files changed, 5896 insertions(+), 4163 deletions(-)
create mode 100644
src/Lucene.Net.Analysis.ICU/Analysis/Icu/Data/uax29/Default.rbbi
create mode 100644
src/Lucene.Net.Analysis.ICU/Analysis/Icu/Data/uax29/MyanmarSyllable.rbbi
create mode 100644
src/Lucene.Net.Analysis.ICU/Analysis/Icu/Segmentation/Default.brk
create mode 100644
src/Lucene.Net.Analysis.ICU/Analysis/Icu/Segmentation/MyanmarSyllable.brk
create mode 100644 src/Lucene.Net.Analysis.ICU/Analysis/Icu/utr30.nrm
delete mode 100644
src/Lucene.Net.Highlighter/PostingsHighlight/CambridgeMA.utf8
copy
src/{Lucene.Net.Tests.Analysis.Common/Analysis/Compound/compoundDictionary.txt
=>
Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/KeywordTokenizer.rbbi}
(80%)
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/Latin-break-only-on-whitespace.rbbi
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/Latin-dont-break-on-hyphens.rbbi
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/TestICUTokenizer.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/TestICUTokenizerCJK.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/TestICUTokenizerFactory.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/TestMyanmarSyllable.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/Segmentation/TestWithCJKBigramFilter.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUFoldingFilter.cs
copy
src/{Lucene.Net.Tests.Analysis.Kuromoji/TestJapaneseBaseFormFilterFactory.cs =>
Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUFoldingFilterFactory.cs} (58%)
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUNormalizer2CharFilter.cs
copy
src/{Lucene.Net.Tests.Analysis.Kuromoji/TestJapaneseBaseFormFilterFactory.cs =>
Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUNormalizer2CharFilterFactory.cs}
(60%)
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUTransformFilter.cs
create mode 100644
src/Lucene.Net.Tests.Analysis.ICU/Analysis/Icu/TestICUTransformFilterFactory.cs
delete mode 100644 src/dotnet/Lucene.Net.ICU/Analysis/Th/stopwords.txt
create mode 100644 src/dotnet/Lucene.Net.ICU/Data/jdk7/jdksent.rbbi
create mode 100644 src/dotnet/Lucene.Net.ICU/Data/jdk7/jdkword.rbbi
delete mode 100644 src/dotnet/Lucene.Net.ICU/Support/BreakIterator.cs
delete mode 100644 src/dotnet/Lucene.Net.ICU/Support/CharacterIterator.cs
delete mode 100644 src/dotnet/Lucene.Net.ICU/Support/IcuBreakIterator.cs
create mode 100644 src/dotnet/Lucene.Net.ICU/Support/JDKBreakIterator.cs
delete mode 100644 src/dotnet/Lucene.Net.ICU/Support/StringCharacterIterator.cs
create mode 100644 src/dotnet/Lucene.Net.ICU/Support/jdksent.brk
create mode 100644 src/dotnet/Lucene.Net.ICU/Support/jdkword.brk
delete mode 100644
src/dotnet/Lucene.Net.Tests.ICU/Support/TestIcuBreakIterator.cs
create mode 100644
src/dotnet/Lucene.Net.Tests.ICU/Support/TestJDKBreakIterator.cs
