Return-Path: X-Original-To: apmail-jackrabbit-commits-archive@www.apache.org Delivered-To: apmail-jackrabbit-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id C4A576B4F for ; Thu, 30 Jun 2011 21:28:57 +0000 (UTC) Received: (qmail 61988 invoked by uid 500); 30 Jun 2011 21:28:57 -0000 Delivered-To: apmail-jackrabbit-commits-archive@jackrabbit.apache.org Received: (qmail 61927 invoked by uid 500); 30 Jun 2011 21:28:57 -0000 Mailing-List: contact commits-help@jackrabbit.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@jackrabbit.apache.org Delivered-To: mailing list commits@jackrabbit.apache.org Received: (qmail 61920 invoked by uid 99); 30 Jun 2011 21:28:56 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 30 Jun 2011 21:28:56 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 30 Jun 2011 21:28:53 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id 9C9D923888CE; Thu, 30 Jun 2011 21:28:32 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1141726 - in /jackrabbit/branches/2.2: ./ jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java Date: Thu, 30 Jun 2011 21:28:32 -0000 To: commits@jackrabbit.apache.org From: mreutegg@apache.org X-Mailer: svnmailer-1.0.8 Message-Id: <20110630212832.9C9D923888CE@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Author: mreutegg Date: Thu Jun 30 21:28:32 2011 New Revision: 1141726 URL: http://svn.apache.org/viewvc?rev=1141726&view=rev Log: JCR-3009: Prefix fulltext queries with Japanese or Chinese characters fail to match Modified: jackrabbit/branches/2.2/ (props changed) jackrabbit/branches/2.2/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java jackrabbit/branches/2.2/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java Propchange: jackrabbit/branches/2.2/ ------------------------------------------------------------------------------ --- svn:mergeinfo (original) +++ svn:mergeinfo Thu Jun 30 21:28:32 2011 @@ -2,4 +2,4 @@ /jackrabbit/sandbox/JCR-1456:774917-886178 /jackrabbit/sandbox/JCR-2170:812417-816332 /jackrabbit/sandbox/tripod-JCR-2209:795441-795863 -/jackrabbit/trunk:1038201,1038203,1038205,1038657,1039064,1039347,1039408,1039422-1039423,1039888,1039946,1040033,1040090,1040459,1040601,1040606,1040661,1040958,1041379,1041439,1041761,1042643,1042647,1042978-1042982,1043084-1043086,1043088,1043343,1043357-1043358,1043430,1043554,1043616,1043618,1043637,1043656,1043893,1043897,1044239,1044312,1044451,1044613,1049473,1049491,1049514,1049518,1049520,1049859,1049870,1049874,1049878,1049880,1049883,1049889,1049891,1049894-1049895,1049899-1049901,1049909-1049911,1049915-1049916,1049919,1049923,1049925,1049931,1049936,1049939,1050212,1050298,1050346,1050551,1055068,1055070-1055071,1055116-1055117,1055127,1055134,1055164,1055498,1060431,1060434,1060753,1063756,1064670,1065599,1065622,1066059,1066071,1069831,1071562,1071573,1071680,1074140,1079314,1079317,1080186,1080540,1087304,1088991,1089032,1089053,1089436,1092106,1092117,1092683,1097363,1097513-1097514,1098963-1098964,1099033,1099172,1100286,1104027,1128175,1130192,1130228,113 2993,1136353,1136360,1138511 +/jackrabbit/trunk:1038201,1038203,1038205,1038657,1039064,1039347,1039408,1039422-1039423,1039888,1039946,1040033,1040090,1040459,1040601,1040606,1040661,1040958,1041379,1041439,1041761,1042643,1042647,1042978-1042982,1043084-1043086,1043088,1043343,1043357-1043358,1043430,1043554,1043616,1043618,1043637,1043656,1043893,1043897,1044239,1044312,1044451,1044613,1049473,1049491,1049514,1049518,1049520,1049859,1049870,1049874,1049878,1049880,1049883,1049889,1049891,1049894-1049895,1049899-1049901,1049909-1049911,1049915-1049916,1049919,1049923,1049925,1049931,1049936,1049939,1050212,1050298,1050346,1050551,1055068,1055070-1055071,1055116-1055117,1055127,1055134,1055164,1055498,1060431,1060434,1060753,1063756,1064670,1065599,1065622,1066059,1066071,1069831,1071562,1071573,1071680,1074140,1079314,1079317,1080186,1080540,1087304,1088991,1089032,1089053,1089436,1092106,1092117,1092683,1097363,1097513-1097514,1098963-1098964,1099033,1099172,1100286,1104027,1128175,1130192,1130228,113 2993,1136353,1136360,1138511,1141717 Modified: jackrabbit/branches/2.2/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java URL: http://svn.apache.org/viewvc/jackrabbit/branches/2.2/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java?rev=1141726&r1=1141725&r2=1141726&view=diff ============================================================================== --- jackrabbit/branches/2.2/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java (original) +++ jackrabbit/branches/2.2/jackrabbit-core/src/main/java/org/apache/jackrabbit/core/query/lucene/JackrabbitQueryParser.java Thu Jun 30 21:28:32 2011 @@ -16,10 +16,15 @@ */ package org.apache.jackrabbit.core.query.lucene; +import java.io.IOException; +import java.io.StringReader; import java.util.List; import java.util.ArrayList; import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.Token; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.queryParser.ParseException; import org.apache.lucene.search.Query; @@ -148,7 +153,31 @@ public class JackrabbitQueryParser exten */ protected Query getPrefixQuery(String field, String termStr) throws ParseException { - return getWildcardQuery(field, termStr + "*"); + // only create a prefix query when the term is a single word / token + Analyzer a = getAnalyzer(); + TokenStream ts = a.tokenStream(field, new StringReader(termStr)); + int count = 0; + boolean isCJ = false; + try { + Token t = new Token(); + while ((t = ts.next(t)) != null) { + count++; + isCJ = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.CJ].equals(t.type()); + } + } catch (IOException e) { + throw new ParseException(e.getMessage()); + } finally { + try { + ts.close(); + } catch (IOException e) { + // ignore + } + } + if (count > 1 && isCJ) { + return getFieldQuery(field, termStr); + } else { + return getWildcardQuery(field, termStr + "*"); + } } /** Modified: jackrabbit/branches/2.2/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java URL: http://svn.apache.org/viewvc/jackrabbit/branches/2.2/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java?rev=1141726&r1=1141725&r2=1141726&view=diff ============================================================================== --- jackrabbit/branches/2.2/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java (original) +++ jackrabbit/branches/2.2/jackrabbit-core/src/test/java/org/apache/jackrabbit/core/query/FulltextQueryTest.java Thu Jun 30 21:28:32 2011 @@ -263,6 +263,12 @@ public class FulltextQueryTest extends A } + public void testMultiByte() throws RepositoryException { + String content = "some text with multi byte \u7530\u4e2d characters."; + + executeContainsQuery("\u7530\u4e2d*", content, true); + } + public void testPredefinedEntityReference() throws RepositoryException { String content = "Max&Moritz";