pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Myanmar.rbbi b/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Myanmar.rbbi
new file mode 100644 (file)
index 0000000..47f541c
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/icu/src/data/uax29/Myanmar.rbbi
@@ -0,0 +1,50 @@
+#\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
+# Parses Myanmar text, with syllable as token. \r
+#\r
+\r
+$Cons = [[:Other_Letter:]&[:Myanmar:]];\r
+$Virama = [\u1039];\r
+$Asat = [\u103A];\r
+\r
+$WordJoin = [:Line_Break=Word_Joiner:]; \r
+\r
+#\r
+# default numerical definitions\r
+#\r
+$Extend       = [\p{Word_Break = Extend}];\r
+$Format       = [\p{Word_Break = Format}];\r
+$MidNumLet    = [\p{Word_Break = MidNumLet}];\r
+$MidNum       = [\p{Word_Break = MidNum}];\r
+$Numeric      = [\p{Word_Break = Numeric}];\r
+$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];                                                          \r
+$MidNumLetEx    = $MidNumLet    ($Extend |  $Format)*;\r
+$MidNumEx       = $MidNum       ($Extend |  $Format)*;\r
+$NumericEx      = $Numeric      ($Extend |  $Format)*;\r
+$ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;\r
+\r
+$ConsEx = $Cons ($Extend | $Format)*;\r
+$AsatEx = $Cons $Asat ($Virama $ConsEx)? ($Extend | $Format)*;\r
+$MyanmarSyllableEx = $ConsEx ($Virama $ConsEx)? ($AsatEx)*;\r
+$MyanmarJoinedSyllableEx = $MyanmarSyllableEx ($WordJoin $MyanmarSyllableEx)*;\r
+\r
+!!forward;\r
+$MyanmarJoinedSyllableEx {200};\r
+\r
+# default numeric rules\r
+$NumericEx $ExtendNumLetEx? (($MidNumEx | $MidNumLetEx)? $NumericEx $ExtendNumLetEx?)*  {100};\r