pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / icu / src / data / uax29 / Hebrew.rbbi

diff --git a/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Hebrew.rbbi b/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Hebrew.rbbi
new file mode 100644 (file)
index 0000000..744bf0d
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Hebrew.rbbi
@@ -0,0 +1,61 @@
+#\r
+# Licensed to the Apache Software Foundation (ASF) under one or more\r
+# contributor license agreements.  See the NOTICE file distributed with\r
+# this work for additional information regarding copyright ownership.\r
+# The ASF licenses this file to You under the Apache License, Version 2.0\r
+# (the "License"); you may not use this file except in compliance with\r
+# the License.  You may obtain a copy of the License at\r
+#\r
+#     http://www.apache.org/licenses/LICENSE-2.0\r
+#\r
+# Unless required by applicable law or agreed to in writing, software\r
+# distributed under the License is distributed on an "AS IS" BASIS,\r
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\r
+# See the License for the specific language governing permissions and\r
+# limitations under the License.\r
+#\r
+#\r
+# This is an example of rule tailoring for Hebrew.\r
+# In this example the single-quote is added to the Extend category\r
+# The double-quote is added to the MidLetter category.\r
+#\r
+!!chain;\r
+$CR           = [\p{Word_Break = CR}];\r
+$LF           = [\p{Word_Break = LF}];\r
+$Newline      = [\p{Word_Break = Newline}];\r
+$Extend       = [\p{Word_Break = Extend}\u0027];\r
+$Format       = [\p{Word_Break = Format}];\r
+$ALetter      = [\p{Word_Break = ALetter}];\r
+$MidNumLet    = [\p{Word_Break = MidNumLet}];\r
+$MidLetter    = [\p{Word_Break = MidLetter}\u0022];\r
+$MidNum       = [\p{Word_Break = MidNum}];\r
+$Numeric      = [\p{Word_Break = Numeric}];\r
+$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];\r
+$dictionary   = [:LineBreak = Complex_Context:];\r
+$Control        = [\p{Grapheme_Cluster_Break = Control}]; \r
+$ALetterPlus  = [$ALetter [$dictionary-$Extend-$Control]]; \r
+                                                              \r
+$ALetterEx      = $ALetterPlus  ($Extend |  $Format)*;\r
+$MidNumLetEx    = $MidNumLet    ($Extend |  $Format)*;\r
+$MidLetterEx    = $MidLetter    ($Extend |  $Format)*;\r
+$MidNumEx       = $MidNum       ($Extend |  $Format)*;\r
+$NumericEx      = $Numeric      ($Extend |  $Format)*;\r
+$ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;\r
+\r
+!!forward;\r
+\r
+$CR $LF;\r
+[^$CR $LF $Newline]? ($Extend |  $Format)+;\r
+$NumericEx {100};\r
+$ALetterEx {200};    \r
+$ALetterEx $ALetterEx {200};\r
+$ALetterEx ($MidLetterEx | $MidNumLetEx) $ALetterEx {200};\r
+$NumericEx $NumericEx {100};\r
+$ALetterEx $NumericEx {200};\r
+$NumericEx $ALetterEx {200};\r
+$NumericEx ($MidNumEx | $MidNumLetEx) $NumericEx {100};\r
+$ALetterEx      $ExtendNumLetEx {200};    \r
+$NumericEx      $ExtendNumLetEx {100};      \r
+$ExtendNumLetEx $ExtendNumLetEx {200};    \r
+$ExtendNumLetEx $ALetterEx  {200};    \r
+$ExtendNumLetEx $NumericEx  {100};    \r