Lucene example source code file (Lao.rbbi)

This example Lucene source code file (Lao.rbbi) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" ^TM.

Java - Lucene tags/keywords

section, x, x, x1, x1, x10_1, x10_2, x10_3, x2, x2, x5, x5, x8, x9

The Lucene Lao.rbbi source code

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Parses Lao text, with syllable as token.
#
# The definition of Lao syllable is based from:
#
#   Syllabification of Lao Script for Line Breaking
#   Phonpasit Phissamay, Valaxay Dalolay, Chitaphone Chanhsililath, Oulaiphone Silimasak, 
#     Sarmad Hussain, Nadir Durrani, Science Technology and Environment Agency, CRULP
#   http://www.panl10n.net/english/final%20reports/pdf%20files/Laos/LAO06.pdf
#	http://www.panl10n.net/Presentations/Cambodia/Phonpassit/LineBreakingAlgo.pdf
#
# NOTE:
# There are some ambiguities in Lao syllabification without additional processing, as mentioned in the paper.
# For this reason, this RBBI grammar really only works with LaoBreakIterator, as it does this additional work.
#
# Syllable structure, where X is the nuclear consonant:
#
#           +----+
#           | X5 |
#           +----+
#           | X4 |
# +----+----+----+----+----+----+----+-----+
# | X0 | X1 | X  | X6 | X7 | X8 | X9 | X10 |
# +----+----+----+----+----+----+----+-----+
#           | X2 |
#           +----+
#           | X3 |
#           +----+
#
# X0 represents a vowel which occurs before the nuclear consonant. 
# It can always define the beginning of syllable.
$X0 = [\u0EC0-\u0EC4];
# X1 is a combination consonant which comes before the nuclear consonant, 
# but only if nuclear consonant is one of {ງ ຍ ລ ວ ຼ ມ ນ ຣ}
$X1 = [\u0EAB];
# X represents the nuclear consonant.
$X = [\u0E81-\u0EAE\u0EDC\u0EDD];
# X2 is a combination consonant which comes after the nuclear consonant, 
# which is placed under or next to the nuclear consonant.
$X2 = [\u0EBC\u0EA3\u0EA7\u0EA5];
# X3 represents a vowel which occurs under the nuclear consonant.
$X3 = [\u0EB8\u0EB9];
# X4 represents a vowel which occurs above the nuclear consonant. 
$X4 = [\u0EB4-\u0EB7\u0ECD\u0EBB\u0EB1];
# X5 represents a tone mark which occurs above the nuclear consonant or upper vowel.
$X5 = [\u0EC8-\u0ECB];
# X6 represents a consonant vowel, which occurs after the nuclear consonant. 
# It functions when the syllable doesn’t have any vowels. And it always exists with X8.
$X6 = [\u0EA7\u0EAD\u0EBD];
# X7 represents a final vowel. 
# However X7_1 always represents the end of syllable and it never exists with tone mark.
$X7 = [\u0EB0\u0EB2\u0EB3];
# X8 represents an alternate consonant.
$X8 = [\u0E81\u0E87\u0E8D\u0E94\u0E99\u0EA1\u0E9A\u0EA7];
# X9 represents alternate consonants to pronounce foreign terms, it always exist with X10_3.
$X9 = [\u0E88\u0EAA\u0E8A\u0E9E\u0E9F\u0EA5];
# X10 represents a sign mark. 
# It always occurs at the end of a syllable, but mostly people keep it separate from syllable.
$X10 = [\u0EAF\u0EC6\u0ECC];

# Section 1
$X0_1 = [\u0EC0];
$X4_1_2 = [\u0EB4\u0EB5];
$X4_3_4 = [\u0EB6\u0EB7];
$X4_6 = [\u0EBB];
$X4_7 = [\u0EB1];
$X6_2 = [\u0EAD];
$X6_3 = [\u0EBD];
$X7_1 = [\u0EB0];
$X7_2 = [\u0EB2];
$X10_1 = [\u0EAF];
$X10_2 = [\u0EC6];
$X10_3 = [\u0ECC];

$Rule1_1 = $X0_1 ($X1)? $X ($X2)? ($X5)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule1_2 = $X0_1 ($X1)? $X ($X2)? $X4_1_2 ($X5)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule1_3 = $X0_1 ($X1)? $X ($X2)? $X4_3_4 ($X5)? $X6_2 ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule1_4 = $X0_1 ($X1)? $X ($X2)? ($X7_2)? $X7_1;
$Rule1_5 = $X0_1 ($X1)? $X ($X2)? $X4_6 ($X5)? $X7_2 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule1_6 = $X0_1 ($X1)? $X ($X2)? $X4_7 ($X5)? $X8 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule1_7 = $X0_1 ($X1)? $X ($X2)? ($X4_7)? ($X5)? $X6_3 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

$Rule1 = ($Rule1_1 | $Rule1_2 | $Rule1_3 | $Rule1_4 | $Rule1_5 | $Rule1_6 | $Rule1_7);

# Section 2
$X0_2 = [\u0EC1];

$Rule2_1 = $X0_2 ($X1)? $X ($X2)? ($X5)? ($X6)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule2_2 = $X0_2 ($X1)? $X ($X2)? $X7_1;
$Rule2_3 = $X0_2 ($X1)? $X ($X2)? $X4_7 ($X5)? $X8 ($X9 $X10_3)? ($X10_2)? ($X10_1)?; 

$Rule2 = ($Rule2_1 | $Rule2_2 | $Rule2_3);

# Section 3
$X0_3 = [\u0EC2];
$X8_3 = [\u0E8D];
$X8_8 = [\u0EA7];

$Rule3_1 = $X0_3 ($X1)? $X ($X2)? ($X5)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule3_2 = $X0_3 ($X1)? $X ($X2)? $X7_1;
$Rule3_3 = $X0_3 ($X1)? $X ($X2)? $X4_7 ($X5)? ($X8_3 | $X8_8);

$Rule3 = ($Rule3_1 | $Rule3_2 | $Rule3_3);

# Section 4
$X0_4 = [\u0EC4];
$X6_1 = [\u0EA7];

$Rule4 = $X0_4 ($X1)? $X ($X2)? ($X5)? ($X6_1)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 5
$X0_5 = [\u0EC3];

$Rule5 = $X0_5 ($X1)? $X ($X2)? ($X5)? ($X6_1)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 6
$Rule6 = ($X1)? $X ($X2)? $X3 ($X5)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 7
$X4_1_4 = [\u0EB4-\u0EB7];

$Rule7 = ($X1)? $X ($X2)? $X4_1_4 ($X5)? ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 8
$X4_5 = [\u0ECD];

$Rule8 = ($X1)? $X ($X2)? $X4_5 ($X5)? ($X7_2)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 9

$Rule9_1 = ($X1)? $X ($X2)? $X4_6 ($X5)? $X8 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;
$Rule9_2 = ($X1)? $X ($X2)? $X4_6 ($X5)? $X6_1 $X7_1;

$Rule9 = ($Rule9_1 | $Rule9_2);

# Section 10
$Rule10 = ($X1)? $X ($X2)? $X4_7 ($X5)? ($X6_1)? $X8 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 11
$Rule11 = ($X1)? $X ($X2)? ($X5)? $X6 $X8 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 12
$Rule12 = ($X1)? $X ($X2)? ($X5)? $X7_1;

# Section 13
$Rule13 = ($X1)? $X ($X2)? ($X5)? $X7_2 ($X8)? ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

# Section 14
$X7_3 = [\u0EB3];

$Rule14 = ($X1)? $X ($X2)? ($X5)? $X7_3 ($X9 $X10_3)? ($X10_2)? ($X10_1)?;

$LaoSyllableEx = ($Rule1 | $Rule2 | $Rule3 | $Rule4 | $Rule5 | $Rule6 | $Rule7 | $Rule8 | $Rule9 | $Rule10 | $Rule11 | $Rule12 | $Rule13 | $Rule14);

$WordJoin = [:Line_Break=Word_Joiner:];

$LaoJoinedSyllableEx = $LaoSyllableEx ($WordJoin $LaoSyllableEx)*;

#
# default numerical definitions
#
$Extend       = [\p{Word_Break = Extend}];
$Format       = [\p{Word_Break = Format}];
$MidNumLet    = [\p{Word_Break = MidNumLet}];
$MidNum       = [\p{Word_Break = MidNum}];
$Numeric      = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];                                                          
$MidNumLetEx    = $MidNumLet    ($Extend |  $Format)*;
$MidNumEx       = $MidNum       ($Extend |  $Format)*;
$NumericEx      = $Numeric      ($Extend |  $Format)*;
$ExtendNumLetEx = $ExtendNumLet ($Extend |  $Format)*;

!!forward;

$LaoJoinedSyllableEx {200};
# default numeric rules
$NumericEx $ExtendNumLetEx? (($MidNumEx | $MidNumLetEx)? $NumericEx $ExtendNumLetEx?)*  {100};