Index: lucene/src/test/org/apache/lucene/analysis/TestUAX29Tokenizer.java =================================================================== --- lucene/src/test/org/apache/lucene/analysis/TestUAX29Tokenizer.java (revision 0) +++ lucene/src/test/org/apache/lucene/analysis/TestUAX29Tokenizer.java (revision 0) @@ -0,0 +1,186 @@ +package org.apache.lucene.analysis; + +import java.io.IOException; +import java.io.Reader; +import java.io.StringReader; +import java.util.Arrays; + +import org.apache.lucene.analysis.standard.UAX29Tokenizer; + +/** + * 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. + */ + +public class TestUAX29Tokenizer extends BaseTokenStreamTestCase { + + public void testHugeDoc() throws IOException { + StringBuilder sb = new StringBuilder(); + char whitespace[] = new char[4094]; + Arrays.fill(whitespace, ' '); + sb.append(whitespace); + sb.append("testing 1234"); + String input = sb.toString(); + UAX29Tokenizer tokenizer = new UAX29Tokenizer(new StringReader(input)); + assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" }); + } + + private Analyzer a = new ReusableAnalyzerBase() { + @Override + protected TokenStreamComponents createComponents + (String fieldName, Reader reader) { + + Tokenizer tokenizer = new UAX29Tokenizer(reader); + return new TokenStreamComponents(tokenizer); + } + }; + + public void testArmenian() throws Exception { + assertAnalyzesTo(a, "Վիքիպեդիայի 13 միլիոն հոդվածները (4,600` հայերեն վիքիպեդիայում) գրվել են կամավորների կողմից ու համարյա բոլոր հոդվածները կարող է խմբագրել ցանկաց մարդ ով կարող է բացել Վիքիպեդիայի կայքը։", + new String[] { "Վիքիպեդիայի", "13", "միլիոն", "հոդվածները", "4,600", "հայերեն", "վիքիպեդիայում", "գրվել", "են", "կամավորների", "կողմից", + "ու", "համարյա", "բոլոր", "հոդվածները", "կարող", "է", "խմբագրել", "ցանկաց", "մարդ", "ով", "կարող", "է", "բացել", "Վիքիպեդիայի", "կայքը" } ); + } + + public void testAmharic() throws Exception { + assertAnalyzesTo(a, "ዊኪፔድያ የባለ ብዙ ቋንቋ የተሟላ ትክክለኛና ነጻ መዝገበ ዕውቀት (ኢንሳይክሎፒዲያ) ነው። ማንኛውም", + new String[] { "ዊኪፔድያ", "የባለ", "ብዙ", "ቋንቋ", "የተሟላ", "ትክክለኛና", "ነጻ", "መዝገበ", "ዕውቀት", "ኢንሳይክሎፒዲያ", "ነው", "ማንኛውም" } ); + } + + public void testArabic() throws Exception { + assertAnalyzesTo(a, "الفيلم الوثائقي الأول عن ويكيبيديا يسمى \"الحقيقة بالأرقام: قصة ويكيبيديا\" (بالإنجليزية: Truth in Numbers: The Wikipedia Story)، سيتم إطلاقه في 2008.", + new String[] { "الفيلم", "الوثائقي", "الأول", "عن", "ويكيبيديا", "يسمى", "الحقيقة", "بالأرقام", "قصة", "ويكيبيديا", + "بالإنجليزية", "Truth", "in", "Numbers", "The", "Wikipedia", "Story", "سيتم", "إطلاقه", "في", "2008" } ); + } + + public void testAramaic() throws Exception { + assertAnalyzesTo(a, "ܘܝܩܝܦܕܝܐ (ܐܢܓܠܝܐ: Wikipedia) ܗܘ ܐܝܢܣܩܠܘܦܕܝܐ ܚܐܪܬܐ ܕܐܢܛܪܢܛ ܒܠܫܢ̈ܐ ܣܓܝܐ̈ܐ܂ ܫܡܗ ܐܬܐ ܡܢ ܡ̈ܠܬܐ ܕ\"ܘܝܩܝ\" ܘ\"ܐܝܢܣܩܠܘܦܕܝܐ\"܀", + new String[] { "ܘܝܩܝܦܕܝܐ", "ܐܢܓܠܝܐ", "Wikipedia", "ܗܘ", "ܐܝܢܣܩܠܘܦܕܝܐ", "ܚܐܪܬܐ", "ܕܐܢܛܪܢܛ", "ܒܠܫܢ̈ܐ", "ܣܓܝܐ̈ܐ", "ܫܡܗ", + "ܐܬܐ", "ܡܢ", "ܡ̈ܠܬܐ", "ܕ", "ܘܝܩܝ", "ܘ", "ܐܝܢܣܩܠܘܦܕܝܐ"}); + } + + public void testBengali() throws Exception { + assertAnalyzesTo(a, "এই বিশ্বকোষ পরিচালনা করে উইকিমিডিয়া ফাউন্ডেশন (একটি অলাভজনক সংস্থা)। উইকিপিডিয়ার শুরু ১৫ জানুয়ারি, ২০০১ সালে। এখন পর্যন্ত ২০০টিরও বেশী ভাষায় উইকিপিডিয়া রয়েছে।", + new String[] { "এই", "বিশ্বকোষ", "পরিচালনা", "করে", "উইকিমিডিয়া", "ফাউন্ডেশন", "একটি", "অলাভজনক", "সংস্থা", "উইকিপিডিয়ার", + "শুরু", "১৫", "জানুয়ারি", "২০০১", "সালে", "এখন", "পর্যন্ত", "২০০টিরও", "বেশী", "ভাষায়", "উইকিপিডিয়া", "রয়েছে" }); + } + + public void testFarsi() throws Exception { + assertAnalyzesTo(a, "ویکی پدیای انگلیسی در تاریخ ۲۵ دی ۱۳۷۹ به صورت مکملی برای دانشنامهٔ تخصصی نوپدیا نوشته شد.", + new String[] { "ویکی", "پدیای", "انگلیسی", "در", "تاریخ", "۲۵", "دی", "۱۳۷۹", "به", "صورت", "مکملی", + "برای", "دانشنامهٔ", "تخصصی", "نوپدیا", "نوشته", "شد" }); + } + + public void testGreek() throws Exception { + assertAnalyzesTo(a, "Γράφεται σε συνεργασία από εθελοντές με το λογισμικό wiki, κάτι που σημαίνει ότι άρθρα μπορεί να προστεθούν ή να αλλάξουν από τον καθένα.", + new String[] { "Γράφεται", "σε", "συνεργασία", "από", "εθελοντές", "με", "το", "λογισμικό", "wiki", "κάτι", "που", + "σημαίνει", "ότι", "άρθρα", "μπορεί", "να", "προστεθούν", "ή", "να", "αλλάξουν", "από", "τον", "καθένα" }); + } + + public void testTibetan() throws Exception { + assertAnalyzesTo(a, "སྣོན་མཛོད་དང་ལས་འདིས་བོད་ཡིག་མི་ཉམས་གོང་འཕེལ་དུ་གཏོང་བར་ཧ་ཅང་དགེ་མཚན་མཆིས་སོ། །", + new String[] { "སྣོན", "མཛོད", "དང", "ལས", "འདིས", "བོད", "ཡིག", + "མི", "ཉམས", "གོང", "འཕེལ", "དུ", "གཏོང", "བར", + "ཧ", "ཅང", "དགེ", "མཚན", "མཆིས", "སོ" }); + } + + /* + * For chinese, tokenize as char (these can later form bigrams or whatever) + * TODO: why do full-width numerics have no word-break prop? + */ + public void testChinese() throws Exception { + assertAnalyzesTo(a, "我是中国人。 １２３４ Ｔｅｓｔｓ ", + new String[] { "我", "是", "中", "国", "人", "Ｔｅｓｔｓ"}); + } + + public void testEmpty() throws Exception { + assertAnalyzesTo(a, "", new String[] {}); + assertAnalyzesTo(a, ".", new String[] {}); + assertAnalyzesTo(a, " ", new String[] {}); + } + + /* test various jira issues this analyzer is related to */ + + public void testLUCENE1545() throws Exception { + /* + * Standard analyzer does not correctly tokenize combining character U+0364 COMBINING LATIN SMALL LETTRE E. + * The word "moͤchte" is incorrectly tokenized into "mo" "chte", the combining character is lost. + * Expected result is only on token "moͤchte". + */ + assertAnalyzesTo(a, "moͤchte", new String[] { "moͤchte" }); + } + + /* Tests from StandardAnalyzer, just to show behavior is similar */ + public void testAlphanumericSA() throws Exception { + // alphanumeric tokens + assertAnalyzesTo(a, "B2B", new String[]{"B2B"}); + assertAnalyzesTo(a, "2B", new String[]{"2B"}); + } + + public void testDelimitersSA() throws Exception { + // other delimiters: "-", "/", "," + assertAnalyzesTo(a, "some-dashed-phrase", new String[]{"some", "dashed", "phrase"}); + assertAnalyzesTo(a, "dogs,chase,cats", new String[]{"dogs", "chase", "cats"}); + assertAnalyzesTo(a, "ac/dc", new String[]{"ac", "dc"}); + } + + public void testApostrophesSA() throws Exception { + // internal apostrophes: O'Reilly, you're, O'Reilly's + assertAnalyzesTo(a, "O'Reilly", new String[]{"O'Reilly"}); + assertAnalyzesTo(a, "you're", new String[]{"you're"}); + assertAnalyzesTo(a, "she's", new String[]{"she's"}); + assertAnalyzesTo(a, "Jim's", new String[]{"Jim's"}); + assertAnalyzesTo(a, "don't", new String[]{"don't"}); + assertAnalyzesTo(a, "O'Reilly's", new String[]{"O'Reilly's"}); + } + + public void testNumericSA() throws Exception { + // floating point, serial, model numbers, ip addresses, etc. + // every other segment must have at least one digit + assertAnalyzesTo(a, "21.35", new String[]{"21.35"}); + assertAnalyzesTo(a, "R2D2 C3PO", new String[]{"R2D2", "C3PO"}); + assertAnalyzesTo(a, "216.239.63.104", new String[]{"216.239.63.104"}); + assertAnalyzesTo(a, "216.239.63.104", new String[]{"216.239.63.104"}); + } + + public void testTextWithNumbersSA() throws Exception { + // numbers + assertAnalyzesTo(a, "David has 5000 bones", new String[]{"David", "has", "5000", "bones"}); + } + + public void testVariousTextSA() throws Exception { + // various + assertAnalyzesTo(a, "C embedded developers wanted", new String[]{"C", "embedded", "developers", "wanted"}); + assertAnalyzesTo(a, "foo bar FOO BAR", new String[]{"foo", "bar", "FOO", "BAR"}); + assertAnalyzesTo(a, "foo bar . FOO <> BAR", new String[]{"foo", "bar", "FOO", "BAR"}); + assertAnalyzesTo(a, "\"QUOTED\" word", new String[]{"QUOTED", "word"}); + } + + public void testKoreanSA() throws Exception { + // Korean words + assertAnalyzesTo(a, "안녕하세요 한글입니다", new String[]{"안녕하세요", "한글입니다"}); + } + + public void testOffsets() throws Exception { + assertAnalyzesTo(a, "David has 5000 bones", + new String[] {"David", "has", "5000", "bones"}, + new int[] {0, 6, 10, 15}, + new int[] {5, 9, 14, 20}); + } + + public void testTypes() throws Exception { + assertAnalyzesTo(a, "David has 5000 bones", + new String[] {"David", "has", "5000", "bones"}, + new String[] { "", "", "", "" }); + }} Index: lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.java =================================================================== --- lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.java (revision 0) +++ lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.java (revision 0) @@ -0,0 +1,787 @@ +/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 5/9/10 12:24 AM */ + +package org.apache.lucene.analysis.standard; + +/** + * 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. + */ + +import java.io.IOException; +import java.io.Reader; +import java.nio.CharBuffer; + +import org.apache.lucene.analysis.Tokenizer; +import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.analysis.tokenattributes.TypeAttribute; +import org.apache.lucene.util.AttributeSource; + + +/** + * This class implements the Unicode Text Segmentation algorithm, as specified + * in Unicode Standard Annex #29 . + */ + +public class UAX29Tokenizer extends Tokenizer { + + /** This character denotes the end of file */ + public static final int YYEOF = -1; + + /** initial size of the lookahead buffer */ + private static final int ZZ_BUFFERSIZE = 16384; + + /** lexical states */ + public static final int YYINITIAL = 0; + + /** + * ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l + * ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l + * at the beginning of a line + * l is of the form l = 2*k, k a non negative integer + */ + private static final int ZZ_LEXSTATE[] = { + 0, 0 + }; + + /** + * Translates characters to character classes + */ + private static final String ZZ_CMAP_PACKED = + "\47\0\1\7\4\0\1\6\1\0\1\7\1\0\12\3\1\5\1\6"+ + "\5\0\32\1\4\0\1\10\1\0\32\1\57\0\1\1\2\0\1\2"+ + "\7\0\1\1\1\0\1\5\2\0\1\1\5\0\27\1\1\0\37\1"+ + "\1\0\u01ca\1\4\0\14\1\16\0\5\1\7\0\1\1\1\0\1\1"+ + "\21\0\160\2\5\1\1\0\2\1\2\0\4\1\1\6\7\0\1\1"+ + "\1\5\3\1\1\0\1\1\1\0\24\1\1\0\123\1\1\0\213\1"+ + "\1\0\7\2\234\1\13\0\46\1\2\0\1\1\7\0\47\1\1\0"+ + "\1\6\7\0\55\2\1\0\1\2\1\0\2\2\1\0\2\2\1\0"+ + "\1\2\10\0\33\1\5\0\4\1\1\5\13\0\4\2\10\0\2\6"+ + "\2\0\13\2\6\0\52\1\24\2\1\0\12\3\1\0\1\3\1\6"+ + "\1\0\2\1\1\2\143\1\1\0\1\1\17\2\2\1\2\2\1\0"+ + "\4\2\2\1\12\3\3\1\2\0\1\1\17\0\1\2\1\1\1\2"+ + "\36\1\33\2\2\0\131\1\13\2\1\1\16\0\12\3\41\1\11\2"+ + "\2\1\2\0\1\6\1\0\1\1\5\0\26\1\4\2\1\1\11\2"+ + "\1\1\3\2\1\1\5\2\322\0\4\2\66\1\2\0\1\2\1\1"+ + "\21\2\1\0\1\1\5\2\2\0\12\1\2\2\2\0\12\3\1\0"+ + "\2\1\6\0\7\1\1\0\3\2\1\0\10\1\2\0\2\1\2\0"+ + "\26\1\1\0\7\1\1\0\1\1\3\0\4\1\2\0\1\2\1\1"+ + "\7\2\2\0\2\2\2\0\3\2\1\1\10\0\1\2\4\0\2\1"+ + "\1\0\3\1\2\2\2\0\12\3\2\1\17\0\3\2\1\0\6\1"+ + "\4\0\2\1\2\0\26\1\1\0\7\1\1\0\2\1\1\0\2\1"+ + "\1\0\2\1\2\0\1\2\1\0\5\2\4\0\2\2\2\0\3\2"+ + "\3\0\1\2\7\0\4\1\1\0\1\1\7\0\12\3\2\2\3\1"+ + "\1\2\13\0\3\2\1\0\11\1\1\0\3\1\1\0\26\1\1\0"+ + "\7\1\1\0\2\1\1\0\5\1\2\0\1\2\1\1\10\2\1\0"+ + "\3\2\1\0\3\2\2\0\1\1\17\0\2\1\2\2\2\0\12\3"+ + "\21\0\3\2\1\0\10\1\2\0\2\1\2\0\26\1\1\0\7\1"+ + "\1\0\2\1\1\0\5\1\2\0\1\2\1\1\7\2\2\0\2\2"+ + "\2\0\3\2\10\0\2\2\4\0\2\1\1\0\3\1\2\2\2\0"+ + "\12\3\1\0\1\1\20\0\1\2\1\1\1\0\6\1\3\0\3\1"+ + "\1\0\4\1\3\0\2\1\1\0\1\1\1\0\2\1\3\0\2\1"+ + "\3\0\3\1\3\0\14\1\4\0\5\2\3\0\3\2\1\0\4\2"+ + "\2\0\1\1\6\0\1\2\16\0\12\3\21\0\3\2\1\0\10\1"+ + "\1\0\3\1\1\0\27\1\1\0\12\1\1\0\5\1\3\0\1\1"+ + "\7\2\1\0\3\2\1\0\4\2\7\0\2\2\1\0\2\1\6\0"+ + "\2\1\2\2\2\0\12\3\22\0\2\2\1\0\10\1\1\0\3\1"+ + "\1\0\27\1\1\0\12\1\1\0\5\1\2\0\1\2\1\1\7\2"+ + "\1\0\3\2\1\0\4\2\7\0\2\2\7\0\1\1\1\0\2\1"+ + "\2\2\2\0\12\3\22\0\2\2\1\0\10\1\1\0\3\1\1\0"+ + "\27\1\1\0\20\1\3\0\1\1\7\2\1\0\3\2\1\0\4\2"+ + "\11\0\1\2\10\0\2\1\2\2\2\0\12\3\12\0\6\1\2\0"+ + "\2\2\1\0\22\1\3\0\30\1\1\0\11\1\1\0\1\1\2\0"+ + "\7\1\3\0\1\2\4\0\6\2\1\0\1\2\1\0\10\2\22\0"+ + "\2\2\75\0\1\2\2\0\7\2\14\0\10\2\1\0\12\3\127\0"+ + "\1\2\2\0\6\2\1\0\2\2\13\0\6\2\2\0\12\3\46\0"+ + "\1\1\27\0\2\2\6\0\12\3\13\0\1\2\1\0\1\2\1\0"+ + "\1\2\4\0\2\2\10\1\1\0\44\1\4\0\24\2\1\0\2\2"+ + "\4\1\4\0\10\2\1\0\44\2\11\0\1\2\144\0\24\2\1\0"+ + "\12\3\14\0\4\2\4\0\3\2\1\0\3\2\2\0\7\2\3\0"+ + "\4\2\15\0\14\2\1\0\1\2\12\3\4\2\2\0\46\1\12\0"+ + "\53\1\1\0\1\1\3\0\u0149\1\1\0\4\1\2\0\7\1\1\0"+ + "\1\1\1\0\4\1\2\0\51\1\1\0\4\1\2\0\41\1\1\0"+ + "\4\1\2\0\7\1\1\0\1\1\1\0\4\1\2\0\17\1\1\0"+ + "\71\1\1\0\4\1\2\0\103\1\4\0\1\2\40\0\20\1\20\0"+ + "\125\1\14\0\u026c\1\2\0\21\1\1\0\32\1\5\0\113\1\3\0"+ + "\3\1\17\0\15\1\1\0\4\1\3\2\13\0\22\1\3\2\13\0"+ + "\22\1\2\2\14\0\15\1\1\0\3\1\1\0\2\2\100\0\40\2"+ + "\11\0\1\2\2\0\12\3\41\0\3\2\2\0\12\3\6\0\130\1"+ + "\10\0\51\1\1\2\1\1\5\0\106\1\12\0\35\1\3\0\14\2"+ + "\4\0\14\2\12\0\12\3\140\0\21\2\7\0\2\2\6\0\13\3"+ + "\45\0\27\1\5\2\71\0\12\2\1\0\35\2\2\0\1\2\12\3"+ + "\6\0\12\3\146\0\5\2\57\1\21\2\7\1\4\0\12\3\21\0"+ + "\11\2\14\0\3\2\36\1\12\2\3\0\2\1\12\3\106\0\44\1"+ + "\24\2\10\0\12\3\3\0\3\1\12\3\44\1\122\0\3\2\1\0"+ + "\25\2\4\1\1\2\4\1\1\2\15\0\300\1\47\2\26\0\3\2"+ + "\u0116\1\2\0\6\1\2\0\46\1\2\0\6\1\2\0\10\1\1\0"+ + "\1\1\1\0\1\1\1\0\1\1\1\0\37\1\2\0\65\1\1\0"+ + "\7\1\1\0\1\1\3\0\3\1\1\0\7\1\3\0\4\1\2\0"+ + "\6\1\4\0\15\1\5\0\3\1\1\0\7\1\17\0\4\2\10\0"+ + "\2\7\12\0\1\7\2\0\1\5\2\0\5\2\20\0\2\10\3\0"+ + "\1\6\17\0\1\10\13\0\5\2\5\0\6\2\1\0\1\1\15\0"+ + "\1\1\20\0\5\1\73\0\41\2\21\0\1\1\4\0\1\1\2\0"+ + "\12\1\1\0\1\1\3\0\5\1\6\0\1\1\1\0\1\1\1\0"+ + "\1\1\1\0\4\1\1\0\13\1\2\0\4\1\5\0\5\1\4\0"+ + "\1\1\21\0\51\1\u032d\0\64\1\u0716\0\57\1\1\0\57\1\1\0"+ + "\205\1\6\0\4\1\3\2\16\0\46\1\12\0\66\1\11\0\1\1"+ + "\20\0\27\1\11\0\7\1\1\0\7\1\1\0\7\1\1\0\7\1"+ + "\1\0\7\1\1\0\7\1\1\0\7\1\1\0\7\1\1\0\40\2"+ + "\57\0\1\1\120\0\32\11\1\0\131\11\14\0\326\11\57\0\1\1"+ + "\1\0\1\11\31\0\11\11\6\2\1\0\5\4\2\0\3\11\1\1"+ + "\1\1\4\0\126\11\2\0\2\2\2\4\3\11\133\4\1\0\4\4"+ + "\5\0\51\1\3\0\136\1\21\0\30\1\70\0\20\4\320\0\57\4"+ + "\1\0\130\4\250\0\u19b6\11\112\0\u51cc\11\64\0\u048d\1\103\0\56\1"+ + "\2\0\u010d\1\3\0\20\1\12\3\2\1\24\0\40\1\2\0\15\1"+ + "\4\2\11\0\2\2\1\0\31\1\10\0\120\1\2\2\45\0\11\1"+ + "\2\0\147\1\2\0\2\1\156\0\7\1\1\2\3\1\1\2\4\1"+ + "\1\2\27\1\5\2\30\0\64\1\14\0\2\2\62\1\21\2\13\0"+ + "\12\3\6\0\22\2\6\1\3\0\1\1\4\0\12\3\34\1\10\2"+ + "\2\0\27\1\15\2\14\0\35\1\3\0\4\2\57\1\16\2\16\0"+ + "\1\1\12\3\46\0\51\1\16\2\11\0\3\1\1\2\10\1\2\2"+ + "\2\0\12\3\41\0\1\2\64\0\1\2\1\0\3\2\2\0\2\2"+ + "\5\0\2\2\1\0\1\2\376\0\43\1\10\2\1\0\2\2\2\0"+ + "\12\3\6\0\u2ba4\1\14\0\27\1\4\0\61\1\u2104\0\u012e\11\2\0"+ + "\76\11\2\0\152\11\46\0\7\1\14\0\5\1\5\0\1\1\1\2"+ + "\12\1\1\0\15\1\1\0\5\1\1\0\1\1\1\0\2\1\1\0"+ + "\2\1\1\0\154\1\41\0\u016b\1\22\0\100\1\2\0\66\1\50\0"+ + "\14\1\4\0\20\2\1\6\2\0\1\5\1\6\13\0\7\2\14\0"+ + "\2\10\30\0\3\10\1\6\1\0\1\7\1\0\1\6\1\5\32\0"+ + "\5\1\1\0\207\1\2\0\1\2\7\0\1\7\4\0\1\6\1\0"+ + "\1\7\13\0\1\5\1\6\5\0\32\1\4\0\1\10\1\0\32\1"+ + "\13\0\70\4\2\2\37\1\3\0\6\1\2\0\6\1\2\0\6\1"+ + "\2\0\3\1\34\0\3\2\4\0"; + + /** + * Translates characters to character classes + */ + private static final char [] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED); + + /** + * Translates DFA states to action switch labels. + */ + private static final int [] ZZ_ACTION = zzUnpackAction(); + + private static final String ZZ_ACTION_PACKED_0 = + "\1\1\1\2\1\1\1\3\4\1\1\0\1\1\1\0"+ + "\1\3\1\0"; + + private static int [] zzUnpackAction() { + int [] result = new int[13]; + int offset = 0; + offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result); + return result; + } + + private static int zzUnpackAction(String packed, int offset, int [] result) { + int i = 0; /* index in packed string */ + int j = offset; /* index in unpacked array */ + int l = packed.length(); + while (i < l) { + int count = packed.charAt(i++); + int value = packed.charAt(i++); + do result[j++] = value; while (--count > 0); + } + return j; + } + + + /** + * Translates a state to a row index in the transition table + */ + private static final int [] ZZ_ROWMAP = zzUnpackRowMap(); + + private static final String ZZ_ROWMAP_PACKED_0 = + "\0\0\0\12\0\24\0\36\0\50\0\62\0\12\0\74"+ + "\0\106\0\120\0\132\0\144\0\156"; + + private static int [] zzUnpackRowMap() { + int [] result = new int[13]; + int offset = 0; + offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result); + return result; + } + + private static int zzUnpackRowMap(String packed, int offset, int [] result) { + int i = 0; /* index in packed string */ + int j = offset; /* index in unpacked array */ + int l = packed.length(); + while (i < l) { + int high = packed.charAt(i++) << 16; + result[j++] = high | packed.charAt(i++); + } + return j; + } + + /** + * The transition table of the DFA + */ + private static final int [] ZZ_TRANS = zzUnpackTrans(); + + private static final String ZZ_TRANS_PACKED_0 = + "\1\2\1\3\1\2\1\4\1\5\3\2\1\6\1\7"+ + "\13\0\2\3\1\10\1\0\1\11\1\0\1\11\1\12"+ + "\2\0\1\3\2\4\2\0\2\13\1\14\3\0\1\5"+ + "\1\0\1\5\3\0\1\12\2\0\1\3\1\6\1\4"+ + "\1\5\3\0\1\6\2\0\1\3\2\10\2\0\2\15"+ + "\1\12\2\0\1\3\1\11\10\0\1\3\1\12\1\10"+ + "\1\5\3\0\1\12\3\0\1\13\1\4\7\0\1\3"+ + "\1\14\1\4\1\5\3\0\1\14\3\0\1\15\1\10"+ + "\6\0"; + + private static int [] zzUnpackTrans() { + int [] result = new int[120]; + int offset = 0; + offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result); + return result; + } + + private static int zzUnpackTrans(String packed, int offset, int [] result) { + int i = 0; /* index in packed string */ + int j = offset; /* index in unpacked array */ + int l = packed.length(); + while (i < l) { + int count = packed.charAt(i++); + int value = packed.charAt(i++); + value--; + do result[j++] = value; while (--count > 0); + } + return j; + } + + + /* error codes */ + private static final int ZZ_UNKNOWN_ERROR = 0; + private static final int ZZ_NO_MATCH = 1; + private static final int ZZ_PUSHBACK_2BIG = 2; + + /* error messages for the codes above */ + private static final String ZZ_ERROR_MSG[] = { + "Unkown internal scanner error", + "Error: could not match input", + "Error: pushback value was too large" + }; + + /** + * ZZ_ATTRIBUTE[aState] contains the attributes of state aState + */ + private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute(); + + private static final String ZZ_ATTRIBUTE_PACKED_0 = + "\1\1\1\11\4\1\1\11\1\1\1\0\1\1\1\0"+ + "\1\1\1\0"; + + private static int [] zzUnpackAttribute() { + int [] result = new int[13]; + int offset = 0; + offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result); + return result; + } + + private static int zzUnpackAttribute(String packed, int offset, int [] result) { + int i = 0; /* index in packed string */ + int j = offset; /* index in unpacked array */ + int l = packed.length(); + while (i < l) { + int count = packed.charAt(i++); + int value = packed.charAt(i++); + do result[j++] = value; while (--count > 0); + } + return j; + } + + /** the input device */ + private java.io.Reader zzReader; + + /** the current state of the DFA */ + private int zzState; + + /** the current lexical state */ + private int zzLexicalState = YYINITIAL; + + /** this buffer contains the current text to be matched and is + the source of the yytext() string */ + private char zzBuffer[] = new char[ZZ_BUFFERSIZE]; + + /** the textposition at the last accepting state */ + private int zzMarkedPos; + + /** the current text position in the buffer */ + private int zzCurrentPos; + + /** startRead marks the beginning of the yytext() string in the buffer */ + private int zzStartRead; + + /** endRead marks the last character in the buffer, that has been read + from input */ + private int zzEndRead; + + /** number of newlines encountered up to the start of the matched text */ + private int yyline; + + /** the number of characters up to the start of the matched text */ + private int yychar; + + /** + * the number of characters from the last newline up to the start of the + * matched text + */ + private int yycolumn; + + /** + * zzAtBOL == true <=> the scanner is currently at the beginning of a line + */ + private boolean zzAtBOL = true; + + /** zzAtEOF == true <=> the scanner is at the EOF */ + private boolean zzAtEOF; + + /** denotes if the user-EOF-code has already been executed */ + private boolean zzEOFDone; + + /* user code: */ + public static final String WORD_TYPE = ""; + public static final String NUMERIC_TYPE = ""; + + private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); + private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class); + private final PositionIncrementAttribute posIncrAtt + = addAttribute(PositionIncrementAttribute.class); + private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); + + private int maxTokenLength = StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH; + private int posIncr; + + + /** + * @param source The AttributeSource to use + * @param input The input reader + */ + public UAX29Tokenizer(AttributeSource source, Reader input) { + super(source, input); + zzReader = input; + } + + /** + * @param factory The AttributeFactory to use + * @param input The input reader + */ + public UAX29Tokenizer(AttributeFactory factory, Reader input) { + super(factory, input); + zzReader = input; + } + + @Override + public final void end() { + // set final offset + int finalOffset = correctOffset(yychar + yylength()); + offsetAtt.setOffset(finalOffset, finalOffset); + } + + @Override + public void reset(Reader reader) throws IOException { + super.reset(reader); + if (zzBuffer.length > ZZ_BUFFERSIZE) { + zzBuffer = new char[ZZ_BUFFERSIZE]; + } + yyreset(reader); + } + + /** + * Populates this TokenStream's CharTermAttribute, PositionIncrementAttribute, + * OffsetAttribute, and TypeAttribute from the current match. + * + *

+ * If maxTokenLength is exceeded, the CharTermAttribute is set back to empty + * and false is returned. + * + * @param tokenType The type of the matching token + * @return true there is a token available; false otherwise + */ + private boolean populateAttributes(String tokenType) { + boolean isTokenAvailable = false; + if (yylength() > maxTokenLength) { + // When we skip a too-long token, we still increment the position + // increment, but only if the token would have otherwise been output + // (that is, only if it contains Letters and/or Numbers.) + ++posIncr; + } else { + termAtt.copyBuffer(zzBuffer, zzStartRead, yylength()); + posIncrAtt.setPositionIncrement(posIncr); + offsetAtt.setOffset(correctOffset(yychar), + correctOffset(yychar + yylength())); + typeAtt.setType(tokenType); + isTokenAvailable = true; + } + return isTokenAvailable; + } + + /** + * Set the max allowed token length. Any token longer than this is skipped. + * @param length the new max allowed token length + */ + public void setMaxTokenLength(int length) { + this.maxTokenLength = length; + } + + /** + * Returns the max allowed token length. Any token longer than this is + * skipped. + * @return the max allowed token length + */ + public int getMaxTokenLength() { + return maxTokenLength; + } + + @Override + public final boolean incrementToken() throws IOException { + // This method is required because of two JFlex limitations: + // 1. No way to insert code at the beginning of the generated scanning + // get-next-token method; and + // 2. No way to declare @Override on the generated scanning method. + clearAttributes(); + posIncr = 1; + return getNextToken(); + } + + + /** + * Creates a new scanner + * There is also a java.io.InputStream version of this constructor. + * + * @param in the java.io.Reader to read input from. + */ + public UAX29Tokenizer(java.io.Reader in) { + super(in); + this.zzReader = in; + } + + /** + * Creates a new scanner. + * There is also java.io.Reader version of this constructor. + * + * @param in the java.io.Inputstream to read input from. + */ + public UAX29Tokenizer(java.io.InputStream in) { + this(new java.io.InputStreamReader(in)); + } + + /** + * Unpacks the compressed character translation table. + * + * @param packed the packed character translation table + * @return the unpacked character translation table + */ + private static char [] zzUnpackCMap(String packed) { + char [] map = new char[0x10000]; + int i = 0; /* index in packed string */ + int j = 0; /* index in unpacked array */ + while (i < 2030) { + int count = packed.charAt(i++); + char value = packed.charAt(i++); + do map[j++] = value; while (--count > 0); + } + return map; + } + + + /** + * Refills the input buffer. + * + * @return false, iff there was new input. + * + * @exception java.io.IOException if any I/O-Error occurs + */ + private boolean zzRefill() throws java.io.IOException { + + /* first: make room (if you can) */ + if (zzStartRead > 0) { + System.arraycopy(zzBuffer, zzStartRead, + zzBuffer, 0, + zzEndRead-zzStartRead); + + /* translate stored positions */ + zzEndRead-= zzStartRead; + zzCurrentPos-= zzStartRead; + zzMarkedPos-= zzStartRead; + zzStartRead = 0; + } + + /* is the buffer big enough? */ + if (zzCurrentPos >= zzBuffer.length) { + /* if not: blow it up */ + char newBuffer[] = new char[zzCurrentPos*2]; + System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length); + zzBuffer = newBuffer; + } + + /* finally: fill the buffer with new input */ + int numRead = zzReader.read(zzBuffer, zzEndRead, + zzBuffer.length-zzEndRead); + + if (numRead > 0) { + zzEndRead+= numRead; + return false; + } + // unlikely but not impossible: read 0 characters, but not at end of stream + if (numRead == 0) { + int c = zzReader.read(); + if (c == -1) { + return true; + } else { + zzBuffer[zzEndRead++] = (char) c; + return false; + } + } + + // numRead < 0 + return true; + } + + + /** + * Closes the input stream. + */ + public final void yyclose() throws java.io.IOException { + zzAtEOF = true; /* indicate end of file */ + zzEndRead = zzStartRead; /* invalidate buffer */ + + if (zzReader != null) + zzReader.close(); + } + + + /** + * Resets the scanner to read from a new input stream. + * Does not close the old reader. + * + * All internal variables are reset, the old input stream + * cannot be reused (internal buffer is discarded and lost). + * Lexical state is set to ZZ_INITIAL. + * + * @param reader the new input stream + */ + public final void yyreset(java.io.Reader reader) { + zzReader = reader; + zzAtBOL = true; + zzAtEOF = false; + zzEOFDone = false; + zzEndRead = zzStartRead = 0; + zzCurrentPos = zzMarkedPos = 0; + yyline = yychar = yycolumn = 0; + zzLexicalState = YYINITIAL; + } + + + /** + * Returns the current lexical state. + */ + public final int yystate() { + return zzLexicalState; + } + + + /** + * Enters a new lexical state + * + * @param newState the new lexical state + */ + public final void yybegin(int newState) { + zzLexicalState = newState; + } + + + /** + * Returns the text matched by the current regular expression. + */ + public final String yytext() { + return new String( zzBuffer, zzStartRead, zzMarkedPos-zzStartRead ); + } + + + /** + * Returns the character at position pos from the + * matched text. + * + * It is equivalent to yytext().charAt(pos), but faster + * + * @param pos the position of the character to fetch. + * A value from 0 to yylength()-1. + * + * @return the character at position pos + */ + public final char yycharat(int pos) { + return zzBuffer[zzStartRead+pos]; + } + + + /** + * Returns the length of the matched text region. + */ + public final int yylength() { + return zzMarkedPos-zzStartRead; + } + + + /** + * Reports an error that occured while scanning. + * + * In a wellformed scanner (no or only correct usage of + * yypushback(int) and a match-all fallback rule) this method + * will only be called with things that "Can't Possibly Happen". + * If this method is called, something is seriously wrong + * (e.g. a JFlex bug producing a faulty scanner etc.). + * + * Usual syntax/scanner level error handling should be done + * in error fallback rules. + * + * @param errorCode the code of the errormessage to display + */ + private void zzScanError(int errorCode) { + String message; + try { + message = ZZ_ERROR_MSG[errorCode]; + } + catch (ArrayIndexOutOfBoundsException e) { + message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR]; + } + + throw new Error(message); + } + + + /** + * Pushes the specified amount of characters back into the input stream. + * + * They will be read again by then next call of the scanning method + * + * @param number the number of characters to be read again. + * This number must not be greater than yylength()! + */ + public void yypushback(int number) { + if ( number > yylength() ) + zzScanError(ZZ_PUSHBACK_2BIG); + + zzMarkedPos -= number; + } + + + /** + * Resumes scanning until the next regular expression is matched, + * the end of input is encountered or an I/O-Error occurs. + * + * @return the next token + * @exception java.io.IOException if any I/O-Error occurs + */ + public boolean getNextToken() throws java.io.IOException { + int zzInput; + int zzAction; + + // cached fields: + int zzCurrentPosL; + int zzMarkedPosL; + int zzEndReadL = zzEndRead; + char [] zzBufferL = zzBuffer; + char [] zzCMapL = ZZ_CMAP; + + int [] zzTransL = ZZ_TRANS; + int [] zzRowMapL = ZZ_ROWMAP; + int [] zzAttrL = ZZ_ATTRIBUTE; + + while (true) { + zzMarkedPosL = zzMarkedPos; + + yychar+= zzMarkedPosL-zzStartRead; + + zzAction = -1; + + zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; + + zzState = ZZ_LEXSTATE[zzLexicalState]; + + + zzForAction: { + while (true) { + + if (zzCurrentPosL < zzEndReadL) + zzInput = zzBufferL[zzCurrentPosL++]; + else if (zzAtEOF) { + zzInput = YYEOF; + break zzForAction; + } + else { + // store back cached positions + zzCurrentPos = zzCurrentPosL; + zzMarkedPos = zzMarkedPosL; + boolean eof = zzRefill(); + // get translated positions and possibly new buffer + zzCurrentPosL = zzCurrentPos; + zzMarkedPosL = zzMarkedPos; + zzBufferL = zzBuffer; + zzEndReadL = zzEndRead; + if (eof) { + zzInput = YYEOF; + break zzForAction; + } + else { + zzInput = zzBufferL[zzCurrentPosL++]; + } + } + int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMapL[zzInput] ]; + if (zzNext == -1) break zzForAction; + zzState = zzNext; + + int zzAttributes = zzAttrL[zzState]; + if ( (zzAttributes & 1) == 1 ) { + zzAction = zzState; + zzMarkedPosL = zzCurrentPosL; + if ( (zzAttributes & 8) == 8 ) break zzForAction; + } + + } + } + + // store back cached position + zzMarkedPos = zzMarkedPosL; + + switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) { + case 3: + { if (populateAttributes(NUMERIC_TYPE)) return true; + } + case 4: break; + case 2: + { /* Not numeric, word, ideographic, or hiragana -- ignore it. */ + } + case 5: break; + case 1: + { if (populateAttributes(WORD_TYPE)) return true; + } + case 6: break; + default: + if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { + zzAtEOF = true; + { + return false; + } + } + else { + zzScanError(ZZ_NO_MATCH); + } + } + } + } + + +} Index: lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.jflex =================================================================== --- lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.jflex (revision 0) +++ lucene/src/java/org/apache/lucene/analysis/standard/UAX29Tokenizer.jflex (revision 0) @@ -0,0 +1,213 @@ +package org.apache.lucene.analysis.standard; + +/** + * 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. + */ + +import java.io.IOException; +import java.io.Reader; +import java.nio.CharBuffer; + +import org.apache.lucene.analysis.Tokenizer; +import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.analysis.tokenattributes.TypeAttribute; +import org.apache.lucene.util.AttributeSource; + + +/** + * This class implements the Unicode Text Segmentation algorithm, as specified + * in Unicode Standard Annex #29 . + */ +%% + +%unicode 5.2 +%public +%class UAX29Tokenizer +%extends Tokenizer +%type boolean +%function getNextToken +%char + +%init{ + super(in); +%init} + +// WB4. X (Extend | Format)* --> X +// +ALetterEx = \p{WB:ALetter} [\p{WB:Format}\p{WB:Extend}]* +NumericEx = \p{WB:Numeric} [\p{WB:Format}\p{WB:Extend}]* +KatakanaEx = \p{WB:Katakana} [\p{WB:Format}\p{WB:Extend}]* + +MidLetterEx = [\p{WB:MidLetter}\p{WB:MidNumLet}] [\p{WB:Format}\p{WB:Extend}]* +MidNumericEx = [\p{WB:MidNum}\p{WB:MidNumLet}] [\p{WB:Format}\p{WB:Extend}]* + +ExtendNumLetEx = \p{WB:ExtendNumLet} [\p{WB:Format}\p{WB:Extend}]* + +%{ + public static final String WORD_TYPE = ""; + public static final String NUMERIC_TYPE = ""; + + private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); + private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class); + private final PositionIncrementAttribute posIncrAtt + = addAttribute(PositionIncrementAttribute.class); + private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); + + private int maxTokenLength = StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH; + private int posIncr; + + + /** + * @param source The AttributeSource to use + * @param input The input reader + */ + public UAX29Tokenizer(AttributeSource source, Reader input) { + super(source, input); + zzReader = input; + } + + /** + * @param factory The AttributeFactory to use + * @param input The input reader + */ + public UAX29Tokenizer(AttributeFactory factory, Reader input) { + super(factory, input); + zzReader = input; + } + + @Override + public final void end() { + // set final offset + int finalOffset = correctOffset(yychar + yylength()); + offsetAtt.setOffset(finalOffset, finalOffset); + } + + @Override + public void reset(Reader reader) throws IOException { + super.reset(reader); + if (zzBuffer.length > ZZ_BUFFERSIZE) { + zzBuffer = new char[ZZ_BUFFERSIZE]; + } + yyreset(reader); + } + + /** + * Populates this TokenStream's CharTermAttribute, PositionIncrementAttribute, + * OffsetAttribute, and TypeAttribute from the current match. + * + *

+ * If maxTokenLength is exceeded, the CharTermAttribute is set back to empty + * and false is returned. + * + * @param tokenType The type of the matching token + * @return true there is a token available; false otherwise + */ + private boolean populateAttributes(String tokenType) { + boolean isTokenAvailable = false; + if (yylength() > maxTokenLength) { + // When we skip a too-long token, we still increment the position + // increment, but only if the token would have otherwise been output + // (that is, only if it contains Letters and/or Numbers.) + ++posIncr; + } else { + termAtt.copyBuffer(zzBuffer, zzStartRead, yylength()); + posIncrAtt.setPositionIncrement(posIncr); + offsetAtt.setOffset(correctOffset(yychar), + correctOffset(yychar + yylength())); + typeAtt.setType(tokenType); + isTokenAvailable = true; + } + return isTokenAvailable; + } + + /** + * Set the max allowed token length. Any token longer than this is skipped. + * @param length the new max allowed token length + */ + public void setMaxTokenLength(int length) { + this.maxTokenLength = length; + } + + /** + * Returns the max allowed token length. Any token longer than this is + * skipped. + * @return the max allowed token length + */ + public int getMaxTokenLength() { + return maxTokenLength; + } + + @Override + public final boolean incrementToken() throws IOException { + // This method is required because of two JFlex limitations: + // 1. No way to insert code at the beginning of the generated scanning + // get-next-token method; and + // 2. No way to declare @Override on the generated scanning method. + clearAttributes(); + posIncr = 1; + return getNextToken(); + } +%} + +%% + +// WB1. sot ÷ +// WB2. ÷ eot +// +<> { return false; } + + +// WB5. ALetter × ALetter +// WB8. Numeric × Numeric +// WB11. Numeric (MidNum | MidNumLet) × Numeric +// WB12. Numeric × (MidNum | MidNumLet) Numeric +// WB13a. (ALetter | Numeric | Katakana | ExtendNumLet) × ExtendNumLet +// WB13b. ExtendNumLet × (ALetter | Numeric | Katakana) +// +{ExtendNumLetEx}* {NumericEx} ({ExtendNumLetEx}+ {NumericEx} | {MidNumericEx} {NumericEx} | {NumericEx})* {ExtendNumLetEx}* + { if (populateAttributes(NUMERIC_TYPE)) return true; } + + +// WB6. ALetter × (MidLetter | MidNumLet) ALetter +// WB7. ALetter (MidLetter | MidNumLet) × ALetter +// WB9. ALetter × Numeric +// WB10. Numeric × ALetter +// WB13. Katakana × Katakana +// WB13a. (ALetter | Numeric | Katakana | ExtendNumLet) × ExtendNumLet +// WB13b. ExtendNumLet × (ALetter | Numeric | Katakana) +// +{ExtendNumLetEx}* ( {KatakanaEx} ({ExtendNumLetEx}* {KatakanaEx})* + | ( {NumericEx} ({ExtendNumLetEx}+ {NumericEx} | {MidNumericEx} {NumericEx} | {NumericEx})* + | {ALetterEx} ({ExtendNumLetEx}+ {ALetterEx} | {MidLetterEx} {ALetterEx} | {ALetterEx})* )* ) +({ExtendNumLetEx}+ ( {KatakanaEx} ({ExtendNumLetEx}* {KatakanaEx})* + | ( {NumericEx} ({ExtendNumLetEx}+ {NumericEx} | {MidNumericEx} {NumericEx} | {NumericEx})* + | {ALetterEx} ({ExtendNumLetEx}+ {ALetterEx} | {MidLetterEx} {ALetterEx} | {ALetterEx})* )* ) )* +{ExtendNumLetEx}* + { if (populateAttributes(WORD_TYPE)) return true; } + + +// WB14. Any ÷ Any +// +[\p{Script:Han}\p{Script:Hiragana}] { if (populateAttributes(WORD_TYPE)) return true; } + + +// WB3. CR × LF +// WB3a. (Newline | CR | LF) ÷ +// WB3b. ÷ (Newline | CR | LF) +// +[^] { /* Not numeric, word, ideographic, or hiragana -- ignore it. */ } Index: lucene/build.xml =================================================================== --- lucene/build.xml (revision 942420) +++ lucene/build.xml (working copy) @@ -661,6 +661,9 @@ +