[
https://issues.apache.org/jira/browse/OAK-5369?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15817819#comment-15817819
]
Thomas Mueller commented on OAK-5369:
-------------------------------------
Proposed patch. [~catholicon], [~teofili], [~chetanm], what do you think?
{noformat}
Index:
src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndex.java
===================================================================
---
src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndex.java
(revision 1777281)
+++
src/main/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndex.java
(working copy)
@@ -1456,10 +1456,34 @@
*/
private static final char[] LUCENE_QUERY_OPERATORS = {':' , '/', '!', '&',
'|', '='};
+ static String rewriteQueryText(String textsearch) {
+ String[] split = textsearch.split(" ");
+ StringBuilder buff = new StringBuilder();
+ for (int i = 0; i < split.length; i++) {
+ if (i > 0) {
+ buff.append(' ');
+ }
+ String s = split[i];
+ String rewritten;
+ if (s.length() > 1) {
+ char first = s.charAt(0);
+ if (first == '+' || first == '-') {
+ char second = s.charAt(1);
+ if (second == '+' || second == '-') {
+ s = first + "\\" + s.substring(1);
+ }
+ }
+ }
+ rewritten = rewriteQueryTextTerm(s);
+ buff.append(rewritten);
+ }
+ return buff.toString();
+ }
+
/**
* Following logic is taken from
org.apache.jackrabbit.core.query.lucene.JackrabbitQueryParser#parse(java.lang.String)
*/
- static String rewriteQueryText(String textsearch) {
+ static String rewriteQueryTextTerm(String textsearch) {
// replace escaped ' with just '
StringBuilder rewritten = new StringBuilder();
// the default lucene query parser recognizes 'AND' and 'NOT' as
Index:
src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LuceneIndexQueryTest.java
===================================================================
---
src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LuceneIndexQueryTest.java
(revision 1777281)
+++
src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LuceneIndexQueryTest.java
(working copy)
@@ -180,6 +180,22 @@
stmt.append("')]");
assertQuery(stmt.toString(), "xpath", ImmutableList.of("/test/a"));
+ // query 'hello world'
+ stmt = new StringBuffer();
+ stmt.append("/jcr:root//*[jcr:contains(., '").append(h).append("
").append(w);
+ stmt.append("')]");
+ assertQuery(stmt.toString(), "xpath", ImmutableList.of("/test/a"));
+
+ // query 'hello -- world' (OAK-5369)
+ stmt = new StringBuffer();
+ stmt.append("/jcr:root//*[jcr:contains(., '").append(h).append(" --
").append(w);
+ stmt.append("')]");
+ assertQuery(stmt.toString(), "xpath", ImmutableList.of("/test/a"));
+ stmt = new StringBuffer();
+ stmt.append("/jcr:root//*[jcr:contains(., '").append(h).append(" ++
").append(w);
+ stmt.append("')]");
+ assertQuery(stmt.toString(), "xpath", ImmutableList.of("/test/a"));
+
}
@Ignore("OAK-2424")
{noformat}
> Lucene Property Index: Syntax Error, cannot parse
> -------------------------------------------------
>
> Key: OAK-5369
> URL: https://issues.apache.org/jira/browse/OAK-5369
> Project: Jackrabbit Oak
> Issue Type: Bug
> Components: lucene
> Reporter: Thomas Mueller
> Assignee: Thomas Mueller
> Fix For: 1.5.18, 1.6, 1.4.13
>
>
> The following query throws an exception in Apache Lucene:
> {noformat}
> /jcr:root//*[jcr:contains(., 'hello -- world')]
> 22.12.2016 16:42:54.511 *WARN* [qtp1944702753-3846]
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex query via
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex@1c0006db
> failed.
> java.lang.RuntimeException: INVALID_SYNTAX_CANNOT_PARSE: Syntax Error, cannot
> parse hello -- world:
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.tokenToQuery(LucenePropertyIndex.java:1450)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.tokenToQuery(LucenePropertyIndex.java:1418)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.access$900(LucenePropertyIndex.java:180)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$3.visitTerm(LucenePropertyIndex.java:1353)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$3.visit(LucenePropertyIndex.java:1307)
> at
> org.apache.jackrabbit.oak.query.fulltext.FullTextContains.accept(FullTextContains.java:63)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.getFullTextQuery(LucenePropertyIndex.java:1303)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.getLuceneRequest(LucenePropertyIndex.java:791)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.access$300(LucenePropertyIndex.java:180)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$1.loadDocs(LucenePropertyIndex.java:375)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$1.computeNext(LucenePropertyIndex.java:317)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$1.computeNext(LucenePropertyIndex.java:306)
> at
> com.google.common.collect.AbstractIterator.tryToComputeNext(AbstractIterator.java:143)
> at
> com.google.common.collect.AbstractIterator.hasNext(AbstractIterator.java:138)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$LucenePathCursor$1.hasNext(LucenePropertyIndex.java:1571)
> at com.google.common.collect.Iterators$7.computeNext(Iterators.java:645)
> at
> com.google.common.collect.AbstractIterator.tryToComputeNext(AbstractIterator.java:143)
> at
> com.google.common.collect.AbstractIterator.hasNext(AbstractIterator.java:138)
> at
> org.apache.jackrabbit.oak.spi.query.Cursors$PathCursor.hasNext(Cursors.java:205)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex$LucenePathCursor.hasNext(LucenePropertyIndex.java:1595)
> at
> org.apache.jackrabbit.oak.query.ast.SelectorImpl.next(SelectorImpl.java:420)
> at
> org.apache.jackrabbit.oak.query.QueryImpl$RowIterator.fetchNext(QueryImpl.java:828)
> at
> org.apache.jackrabbit.oak.query.QueryImpl$RowIterator.hasNext(QueryImpl.java:853)
> at
> org.apache.jackrabbit.oak.jcr.query.QueryResultImpl$1.fetch(QueryResultImpl.java:98)
> at
> org.apache.jackrabbit.oak.jcr.query.QueryResultImpl$1.<init>(QueryResultImpl.java:94)
> at
> org.apache.jackrabbit.oak.jcr.query.QueryResultImpl.getRows(QueryResultImpl.java:78)
> Caused by:
> org.apache.lucene.queryparser.flexible.standard.parser.ParseException: Syntax
> Error, cannot parse hello -- world:
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.generateParseException(StandardSyntaxParser.java:1054)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.jj_consume_token(StandardSyntaxParser.java:936)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.Clause(StandardSyntaxParser.java:486)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.ModClause(StandardSyntaxParser.java:303)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.ConjQuery(StandardSyntaxParser.java:234)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.DisjQuery(StandardSyntaxParser.java:204)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.Query(StandardSyntaxParser.java:186)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.TopLevelQuery(StandardSyntaxParser.java:147)
> at
> org.apache.lucene.queryparser.flexible.standard.parser.StandardSyntaxParser.parse(StandardSyntaxParser.java:65)
> at
> org.apache.lucene.queryparser.flexible.core.QueryParserHelper.parse(QueryParserHelper.java:250)
> at
> org.apache.lucene.queryparser.flexible.standard.StandardQueryParser.parse(StandardQueryParser.java:168)
> at
> org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex.tokenToQuery(LucenePropertyIndex.java:1448)
> ... 63 common frames omitted
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
