com.groupbyinc.flux.common.apache.lucene.analysis.th.ThaiTokenizer.class Maven / Gradle / Ivy
???? 4 ? Bcom/groupbyinc/flux/common/apache/lucene/analysis/th/ThaiTokenizer Ncom/groupbyinc/flux/common/apache/lucene/analysis/util/SegmentingTokenizerBase ThaiTokenizer.java DBBI_AVAILABLE Z proto Ljava/text/BreakIterator;
sentenceProto wordBreaker wrapper JLcom/groupbyinc/flux/common/apache/lucene/analysis/util/CharArrayIterator;
sentenceStart I sentenceEnd termAtt ULcom/groupbyinc/flux/common/apache/lucene/analysis/tokenattributes/CharTermAttribute; offsetAtt SLcom/groupbyinc/flux/common/apache/lucene/analysis/tokenattributes/OffsetAttribute; ()V DEFAULT_TOKEN_ATTRIBUTE_FACTORY @Lcom/groupbyinc/flux/common/apache/lucene/util/AttributeFactory; C(Lcom/groupbyinc/flux/common/apache/lucene/util/AttributeFactory;)V
this DLcom/groupbyinc/flux/common/apache/lucene/analysis/th/ThaiTokenizer;
java/text/BreakIterator " clone ()Ljava/lang/Object; $ %
# & \(Lcom/groupbyinc/flux/common/apache/lucene/util/AttributeFactory;Ljava/text/BreakIterator;)V (
) Hcom/groupbyinc/flux/common/apache/lucene/analysis/util/CharArrayIterator + newWordInstance L()Lcom/groupbyinc/flux/common/apache/lucene/analysis/util/CharArrayIterator; - .
, /
1 Scom/groupbyinc/flux/common/apache/lucene/analysis/tokenattributes/CharTermAttribute 3 addAttribute L(Ljava/lang/Class;)Lcom/groupbyinc/flux/common/apache/lucene/util/Attribute; 5 6
7 9 Qcom/groupbyinc/flux/common/apache/lucene/analysis/tokenattributes/OffsetAttribute ; = ? 'java/lang/UnsupportedOperationException A 4This JRE does not have support for Thai segmentation C (Ljava/lang/String;)V E
B F >com/groupbyinc/flux/common/apache/lucene/util/AttributeFactory H J L factory setNextSentence (II)V Q S buffer [C U V W setText ([CII)V Y Z
, [ (Ljava/text/CharacterIterator;)V Y ]
# ^
incrementWord ()Z current ()I b c
# d next f c
# g java/lang/Character i codePointAt ([CII)I k l
j m isLetterOrDigit (I)Z o p
j q clearAttributes s
t
copyBuffer v Z 4 w offset y z
correctOffset (I)I | }
~ setOffset ? P <