You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by si...@apache.org on 2011/02/09 10:36:03 UTC
svn commit: r1068809 [2/36] - in /lucene/dev/branches/docvalues: ./
dev-tools/eclipse/ dev-tools/idea/.idea/ dev-tools/idea/.idea/copyright/
dev-tools/idea/lucene/ dev-tools/idea/lucene/contrib/ant/
dev-tools/idea/lucene/contrib/queryparser/ dev-tools/...
Modified: lucene/dev/branches/docvalues/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/build.xml (original)
+++ lucene/dev/branches/docvalues/build.xml Wed Feb 9 09:35:27 2011
@@ -38,6 +38,18 @@
</sequential>
</target>
+ <property name="version" value="4.0-SNAPSHOT"/>
+ <target name="get-maven-poms"
+ description="Copy Maven POMs from dev-tools/maven/ to their target locations">
+ <copy todir="." overwrite="true">
+ <fileset dir="${basedir}/dev-tools/maven"/>
+ <filterset begintoken="@" endtoken="@">
+ <filter token="version" value="${version}"/>
+ </filterset>
+ <globmapper from="*.template" to="*"/>
+ </copy>
+ </target>
+
<target name="generate-maven-artifacts" description="Generate Maven Artifacts for Lucene and Solr">
<property name="maven.dist.dir" location="dist/maven" />
<mkdir dir="${maven.dist.dir}" />
Modified: lucene/dev/branches/docvalues/dev-tools/eclipse/dot.classpath
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/eclipse/dot.classpath?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/eclipse/dot.classpath (original)
+++ lucene/dev/branches/docvalues/dev-tools/eclipse/dot.classpath Wed Feb 9 09:35:27 2011
@@ -1,6 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<classpath>
<classpathentry kind="src" path="lucene/src/java"/>
+ <classpathentry kind="src" path="lucene/src/test-framework"/>
<classpathentry kind="src" path="lucene/src/test"/>
<classpathentry kind="src" path="lucene/contrib/ant/src/java"/>
<classpathentry kind="src" path="lucene/contrib/ant/src/resources"/>
@@ -73,6 +74,10 @@
<classpathentry kind="src" path="solr/contrib/extraction/src/main/java"/>
<classpathentry kind="src" path="solr/contrib/extraction/src/test/java"/>
<classpathentry kind="src" path="solr/contrib/extraction/src/test/resources"/>
+ <classpathentry kind="src" path="solr/contrib/uima/src/main/java"/>
+ <classpathentry kind="src" path="solr/contrib/uima/src/main/resources"/>
+ <classpathentry kind="src" path="solr/contrib/uima/src/test/java"/>
+ <classpathentry kind="src" path="solr/contrib/uima/src/test/resources"/>
<classpathentry kind="lib" path="lucene/lib/ant-1.7.1.jar"/>
<classpathentry kind="lib" path="lucene/lib/ant-junit-1.7.1.jar"/>
<classpathentry kind="lib" path="lucene/lib/junit-4.7.jar"/>
@@ -88,8 +93,8 @@
<classpathentry kind="lib" path="modules/benchmark/lib/commons-compress-1.0.jar"/>
<classpathentry kind="lib" path="modules/benchmark/lib/commons-digester-1.7.jar"/>
<classpathentry kind="lib" path="modules/benchmark/lib/commons-logging-1.0.4.jar"/>
- <classpathentry kind="lib" path="modules/benchmark/lib/xercesImpl-2.10.0.jar"/>
- <classpathentry kind="lib" path="modules/benchmark/lib/xml-apis-2.10.0.jar"/>
+ <classpathentry kind="lib" path="modules/benchmark/lib/xercesImpl-2.9.1-patched-XERCESJ-1257.jar"/>
+ <classpathentry kind="lib" path="modules/benchmark/lib/xml-apis-2.9.0.jar"/>
<classpathentry kind="lib" path="solr/lib/apache-solr-noggit-r944541.jar"/>
<classpathentry kind="lib" path="solr/lib/commons-beanutils-1.7.0.jar"/>
<classpathentry kind="lib" path="solr/lib/commons-codec-1.4.jar"/>
@@ -119,7 +124,7 @@
<classpathentry kind="lib" path="solr/example/lib/jsp-2.1/jsp-2.1-glassfish-2.1.v20091210.jar"/>
<classpathentry kind="lib" path="solr/example/lib/jsp-2.1/jsp-2.1-jetty-6.1.26.jar"/>
<classpathentry kind="lib" path="solr/example/lib/jsp-2.1/jsp-api-2.1-glassfish-2.1.v20091210.jar"/>
- <classpathentry kind="lib" path="solr/contrib/clustering/lib/carrot2-core-3.4.0.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/clustering/lib/carrot2-core-3.4.2.jar"/>
<classpathentry kind="lib" path="solr/contrib/clustering/lib/commons-lang-2.4.jar"/>
<classpathentry kind="lib" path="solr/contrib/clustering/lib/hppc-0.3.1.jar"/>
<classpathentry kind="lib" path="solr/contrib/clustering/lib/jackson-core-asl-1.5.2.jar"/>
@@ -151,6 +156,12 @@
<classpathentry kind="lib" path="solr/contrib/extraction/lib/tika-core-0.8.jar"/>
<classpathentry kind="lib" path="solr/contrib/extraction/lib/tika-parsers-0.8.jar"/>
<classpathentry kind="lib" path="solr/contrib/extraction/lib/xmlbeans-2.3.0.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/commons-digester-2.0.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/uima-an-alchemy.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/uima-an-calais.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/uima-an-tagger.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/uima-an-wst.jar"/>
+ <classpathentry kind="lib" path="solr/contrib/uima/lib/uima-core.jar"/>
<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/>
<classpathentry kind="output" path="bin"/>
</classpath>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/.idea/ant.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/.idea/ant.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/.idea/ant.xml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/.idea/ant.xml Wed Feb 9 09:35:27 2011
@@ -31,5 +31,6 @@
<buildFile url="file://$PROJECT_DIR$/solr/contrib/clustering/build.xml" />
<buildFile url="file://$PROJECT_DIR$/solr/contrib/dataimporthandler/build.xml" />
<buildFile url="file://$PROJECT_DIR$/solr/contrib/extraction/build.xml" />
+ <buildFile url="file://$PROJECT_DIR$/solr/contrib/uima/build.xml" />
</component>
</project>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/.idea/modules.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/.idea/modules.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/.idea/modules.xml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/.idea/modules.xml Wed Feb 9 09:35:27 2011
@@ -32,6 +32,7 @@
<module filepath="$PROJECT_DIR$/solr/contrib/dataimporthandler/dataimporthandler.iml" />
<module filepath="$PROJECT_DIR$/solr/contrib/dataimporthandler/src/extras/extras.iml" />
<module filepath="$PROJECT_DIR$/solr/contrib/extraction/extraction.iml" />
+ <module filepath="$PROJECT_DIR$/solr/contrib/uima/uima.iml" />
</modules>
</component>
</project>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/.idea/vcs.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/.idea/vcs.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/.idea/vcs.xml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/.idea/vcs.xml Wed Feb 9 09:35:27 2011
@@ -1,5 +1,15 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
+ <component name="IssueNavigationConfiguration">
+ <option name="links">
+ <list>
+ <IssueNavigationLink>
+ <option name="issueRegexp" value="[A-Z]+\-\d+" />
+ <option name="linkRegexp" value="https://issues.apache.org/jira/browse/$0" />
+ </IssueNavigationLink>
+ </list>
+ </option>
+ </component>
<component name="VcsDirectoryMappings">
<mapping directory="" vcs="svn" />
</component>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/.idea/workspace.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/.idea/workspace.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/.idea/workspace.xml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/.idea/workspace.xml Wed Feb 9 09:35:27 2011
@@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
- <component name="RunManager">
+ <component name="RunManager" selected="JUnit.lucene">
<configuration default="false" name="analysis-extras contrib" type="JUnit" factoryName="JUnit">
<module name="analysis-extras" />
<option name="TEST_OBJECT" value="package" />
@@ -183,6 +183,13 @@
<option name="VM_PARAMETERS" value="-ea -DtempDir=temp" />
<option name="TEST_SEARCH_SCOPE"><value defaultName="singleModule" /></option>
</configuration>
+ <configuration default="false" name="uima contrib" type="JUnit" factoryName="JUnit">
+ <module name="uima" />
+ <option name="TEST_OBJECT" value="package" />
+ <option name="WORKING_DIRECTORY" value="file://$PROJECT_DIR$/solr/contrib/uima/build" />
+ <option name="VM_PARAMETERS" value="-ea -Dtests.luceneMatchVersion=4.0 -DtempDir=temp" />
+ <option name="TEST_SEARCH_SCOPE"><value defaultName="singleModule" /></option>
+ </configuration>
<configuration default="false" name="wordnet contrib" type="JUnit" factoryName="JUnit">
<module name="wordnet" />
<option name="TEST_OBJECT" value="package" />
@@ -224,8 +231,9 @@
<item index="23" class="java.lang.String" itemvalue="JUnit.spellchecker contrib" />
<item index="24" class="java.lang.String" itemvalue="JUnit.stempel analysis module" />
<item index="25" class="java.lang.String" itemvalue="JUnit.swing contrib" />
- <item index="26" class="java.lang.String" itemvalue="JUnit.wordnet contrib" />
- <item index="27" class="java.lang.String" itemvalue="JUnit.xml-query-parser contrib" />
+ <item index="26" class="java.lang.String" itemvalue="JUnit.uima contrib" />
+ <item index="27" class="java.lang.String" itemvalue="JUnit.wordnet contrib" />
+ <item index="28" class="java.lang.String" itemvalue="JUnit.xml-query-parser contrib" />
</list>
</component>
</project>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/ant/ant.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/ant/ant.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/ant/ant.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/ant/ant.iml Wed Feb 9 09:35:27 2011
@@ -6,6 +6,7 @@
<exclude-output />
<content url="file://$MODULE_DIR$">
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
+ <sourceFolder url="file://$MODULE_DIR$/src/resources" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
</content>
<orderEntry type="module" module-name="common" />
Modified: lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/queryparser/queryparser.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/queryparser/queryparser.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/queryparser/queryparser.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/lucene/contrib/queryparser/queryparser.iml Wed Feb 9 09:35:27 2011
@@ -6,6 +6,7 @@
<exclude-output />
<content url="file://$MODULE_DIR$">
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
+ <sourceFolder url="file://$MODULE_DIR$/src/resources" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
</content>
<orderEntry type="module" module-name="remote" />
Modified: lucene/dev/branches/docvalues/dev-tools/idea/lucene/lucene.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/lucene/lucene.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/lucene/lucene.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/lucene/lucene.iml Wed Feb 9 09:35:27 2011
@@ -6,6 +6,7 @@
<exclude-output />
<content url="file://$MODULE_DIR$">
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
+ <sourceFolder url="file://$MODULE_DIR$/src/test-framework" isTestSource="true" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
<excludeFolder url="file://$MODULE_DIR$/build" />
</content>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/modules/analysis/common/common.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/modules/analysis/common/common.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/modules/analysis/common/common.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/modules/analysis/common/common.iml Wed Feb 9 09:35:27 2011
@@ -7,6 +7,7 @@
<content url="file://$MODULE_DIR$">
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/resources" isTestSource="false" />
+ <sourceFolder url="file://$MODULE_DIR$/src/java/tools" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
</content>
<orderEntry type="module" module-name="lucene" />
Modified: lucene/dev/branches/docvalues/dev-tools/idea/modules/benchmark/benchmark.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/modules/benchmark/benchmark.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/modules/benchmark/benchmark.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/modules/benchmark/benchmark.iml Wed Feb 9 09:35:27 2011
@@ -7,7 +7,6 @@
<content url="file://$MODULE_DIR$">
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
- <sourceFolder url="file://$MODULE_DIR$/scripts" isTestSource="false" />
<excludeFolder url="file://$MODULE_DIR$/temp" />
<excludeFolder url="file://$MODULE_DIR$/work" />
</content>
Modified: lucene/dev/branches/docvalues/dev-tools/idea/solr/solr.iml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/dev-tools/idea/solr/solr.iml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/dev-tools/idea/solr/solr.iml (original)
+++ lucene/dev/branches/docvalues/dev-tools/idea/solr/solr.iml Wed Feb 9 09:35:27 2011
@@ -10,7 +10,6 @@
<sourceFolder url="file://$MODULE_DIR$/src/webapp/src" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/webapp/web" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/java" isTestSource="false" />
- <sourceFolder url="file://$MODULE_DIR$/src/scripts" isTestSource="false" />
<sourceFolder url="file://$MODULE_DIR$/src/test" isTestSource="true" />
<sourceFolder url="file://$MODULE_DIR$/src/test-files" isTestSource="true" />
<excludeFolder url="file://$MODULE_DIR$/build" />
Modified: lucene/dev/branches/docvalues/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/CHANGES.txt?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/docvalues/lucene/CHANGES.txt Wed Feb 9 09:35:27 2011
@@ -89,19 +89,9 @@ Changes in backwards compatibility polic
* LUCENE-2484: Removed deprecated TermAttribute. Use CharTermAttribute
and TermToBytesRefAttribute instead. (Uwe Schindler)
-* LUCENE-2602: The default (LogByteSizeMergePolicy) merge policy now
- takes deletions into account by default. You can disable this by
- calling setCalibrateSizeByDeletes(false) on the merge policy. (Mike
- McCandless)
-
* LUCENE-2600: Remove IndexReader.isDeleted in favor of
IndexReader.getDeletedDocs(). (Mike McCandless)
-* LUCENE-2529, LUCENE-2668: Position increment gap and offset gap of empty
- values in multi-valued field has been changed for some cases in index.
- If you index empty fields and uses positions/offsets information on that
- fields, reindex is recommended. (David Smiley, Koji Sekiguchi)
-
* LUCENE-2667: FuzzyQuery's defaults have changed for more performant
behavior: the minimum similarity is 2 edit distances from the word,
and the priority queue size is 50. To support this, FuzzyQuery now allows
@@ -128,22 +118,43 @@ Changes in backwards compatibility polic
ParallelMultiSearcher into IndexSearcher as an optional
ExecutorServiced passed to its ctor. (Mike McCandless)
-Changes in Runtime Behavior
+* LUCENE-2831: Changed Weight#scorer, Weight#explain & Filter#getDocIdSet to
+ operate on a AtomicReaderContext instead of directly on IndexReader to enable
+ searches to be aware of IndexSearcher's context. (Simon Willnauer)
+
+* LUCENE-2839: Scorer#score(Collector,int,int) is now public because it is
+ called from other classes and part of public API. (Uwe Schindler)
+
+* LUCENE-2865: Weight#scorer(AtomicReaderContext, boolean, boolean) now accepts
+ a ScorerContext struct instead of booleans.(Simon Willnauer)
+
+* LUCENE-2882: Cut over SpanQuery#getSpans to AtomicReaderContext to enforce
+ per segment semantics on SpanQuery & Spans. (Simon Willnauer)
-* LUCENE-2650, LUCENE-2825: The behavior of FSDirectory.open has changed. On 64-bit
- Windows and Solaris systems that support unmapping, FSDirectory.open returns
- MMapDirectory. Additionally the behavior of MMapDirectory has been
- changed to enable unmapping by default if supported by the JRE.
- (Mike McCandless, Uwe Schindler, Robert Muir)
+* LUCENE-2236: Similarity can now be configured on a per-field basis. See the
+ migration notes in MIGRATE.txt for more details. (Robert Muir, Doron Cohen)
-* LUCENE-2790: LogMergePolicy.useCompoundFile's logic now factors in noCFSRatio
- to determine whether the passed in segment should be compound.
- (Shai Erera, Earwin Burrfoot)
+Changes in Runtime Behavior
-* LUCENE-2805: IndexWriter now increments the index version on every change to
- the index instead of for every commit. Committing or closing the IndexWriter
- without any changes to the index will not cause any index version increment.
- (Simon Willnauer, Mike McCandless)
+* LUCENE-2846: omitNorms now behaves like omitTermFrequencyAndPositions, if you
+ omitNorms(true) for field "a" for 1000 documents, but then add a document with
+ omitNorms(false) for field "a", all documents for field "a" will have no norms.
+ Previously, Lucene would fill the first 1000 documents with "fake norms" from
+ Similarity.getDefault(). (Robert Muir, Mike Mccandless)
+
+* LUCENE-2846: When some documents contain field "a", and others do not, the
+ documents that don't have the field get a norm byte value of 0. Previously, Lucene
+ would populate "fake norms" with Similarity.getDefault() for these documents.
+ (Robert Muir, Mike Mccandless)
+
+* LUCENE-2720: IndexWriter throws IndexFormatTooOldException on open, rather
+ than later when e.g. a merge starts. (Shai Erera, Mike McCandless, Uwe Schindler)
+
+* LUCENE-1076: The default merge policy is now able to merge
+ non-contiguous segments, which means docIDs no longer necessarily
+ say "in order". If this is a problem then you can use either of the
+ LogMergePolicy impls, and call setRequireContiguousMerge(true).
+ (Mike McCandless)
API Changes
@@ -160,17 +171,6 @@ API Changes
deleted docs (getDeletedDocs), providing a new Bits interface to
directly query by doc ID.
-* LUCENE-2402: IndexWriter.deleteUnusedFiles now deletes unreferenced commit
- points too. If you use an IndexDeletionPolicy which holds onto index commits
- (such as SnapshotDeletionPolicy), you can call this method to remove those
- commit points when they are not needed anymore (instead of waiting for the
- next commit). (Shai Erera)
-
-* LUCENE-2674: A new idfExplain method was added to Similarity, that
- accepts an incoming docFreq. If you subclass Similarity, make sure
- you also override this method on upgrade. (Robert Muir, Mike
- McCandless)
-
* LUCENE-2691: IndexWriter.getReader() has been made package local and is now
exposed via open and reopen methods on IndexReader. The semantics of the
call is the same as it was prior to the API change.
@@ -178,9 +178,18 @@ API Changes
* LUCENE-2566: QueryParser: Unary operators +,-,! will not be treated as
operators if they are followed by whitespace. (yonik)
-
-* LUCENE-2778: RAMDirectory now exposes newRAMFile() which allows to override
- and return a different RAMFile implementation. (Shai Erera)
+
+* LUCENE-2831: Weight#scorer, Weight#explain, Filter#getDocIdSet,
+ Collector#setNextReader & FieldComparator#setNextReader now expect an
+ AtomicReaderContext instead of an IndexReader. (Simon Willnauer)
+
+* LUCENE-2846: Remove the deprecated IndexReader.setNorm(int, String, float).
+ This method was only syntactic sugar for setNorm(int, String, byte), but
+ using the global Similarity.getDefault().encodeNormValue. Use the byte-based
+ method instead to ensure that the norm is encoded with your Similarity.
+ Also removed norms(String, byte[], int), which was only used by MultiReader
+ for building top-level norms. If you really need a top-level norms, use
+ MultiNorms or SlowMultiReaderWrapper. (Robert Muir, Mike Mccandless)
New features
@@ -220,10 +229,6 @@ New features
data and payloads in 5 separate files instead of the 2 used by
standard codec), and int block (really a "base" for using
block-based compressors like PForDelta for storing postings data).
-
-* LUCENE-2385: Moved NoDeletionPolicy from benchmark to core. NoDeletionPolicy
- can be used to prevent commits from ever getting deleted from the index.
- (Shai Erera)
* LUCENE-1458, LUCENE-2111: The in-memory terms index used by standard
codec is more RAM efficient: terms data is stored as block byte
@@ -238,16 +243,6 @@ New features
applications that have many unique terms, since it reduces how often
a new segment must be flushed given a fixed RAM buffer size.
-* LUCENE-1585: IndexWriter now accepts a PayloadProcessorProvider which can
- return a DirPayloadProcessor for a given Directory, which returns a
- PayloadProcessor for a given Term. The PayloadProcessor will be used to
- process the payloads of the segments as they are merged (e.g. if one wants to
- rewrite payloads of external indexes as they are added, or of local ones).
- (Shai Erera, Michael Busch, Mike McCandless)
-
-* LUCENE-2440: Add support for custom ExecutorService in
- ParallelMultiSearcher (Edward Drapkin via Mike McCandless)
-
* LUCENE-2489: Added PerFieldCodecWrapper (in oal.index.codecs) which
lets you set the Codec per field (Mike McCandless)
@@ -258,17 +253,6 @@ New features
SegmentInfosReader to allow customization of SegmentInfos data.
(Andrzej Bialecki)
-* LUCENE-2559: Added SegmentReader.reopen methods (John Wang via Mike
- McCandless)
-
-* LUCENE-2590: Added Scorer.visitSubScorers, and Scorer.freq. Along
- with a custom Collector these experimental methods make it possible
- to gather the hit-count per sub-clause and per document while a
- search is running. (Simon Willnauer, Mike McCandless)
-
-* LUCENE-2636: Added MultiCollector which allows running the search with several
- Collectors. (Shai Erera)
-
* LUCENE-2504: FieldComparator.setNextReader now returns a
FieldComparator instance. You can "return this", to just reuse the
same instance, or you can return a comparator optimized to the new
@@ -326,18 +310,10 @@ New features
terms dict. This impl stores the indexed terms in an FST, which is
much more RAM efficient than FixedGapTermsIndex. (Mike McCandless)
-Optimizations
-
-* LUCENE-2410: ~20% speedup on exact (slop=0) PhraseQuery matching.
- (Mike McCandless)
+* LUCENE-2862: Added TermsEnum.totalTermFreq() and
+ Terms.getSumTotalTermFreq(). (Mike McCandless, Robert Muir)
-* LUCENE-2531: Fix issue when sorting by a String field that was
- causing too many fallbacks to compare-by-value (instead of by-ord).
- (Mike McCandless)
-
-* LUCENE-2574: IndexInput exposes copyBytes(IndexOutput, long) to allow for
- efficient copying by sub-classes. Optimized copy is implemented for RAM and FS
- streams. (Shai Erera)
+Optimizations
* LUCENE-2588: Don't store unnecessary suffixes when writing the terms
index, saving RAM in IndexReader; change default terms index
@@ -348,12 +324,15 @@ Optimizations
not seek backwards when a sub-range has no terms. It now only seeks
when the current term is less than the next sub-range's lower end.
(Uwe Schindler, Mike McCandless)
-
-Documentation
-
-* LUCENE-2579: Fix oal.search's package.html description of abstract
- methods. (Santiago M. Mola via Mike McCandless)
+* LUCENE-2694: Optimize MultiTermQuery to be single pass for Term lookups.
+ MultiTermQuery now stores TermState per leaf reader during rewrite to re-
+ seek the term dictionary in TermQuery / TermWeight.
+ (Simon Willnauer, Mike McCandless, Robert Muir)
+
+* LUCENE-2897: Apply deleted terms while flushing a segment. We still
+ buffer deleted terms to later apply to past segments. (Mike McCandless)
+
Bug fixes
* LUCENE-2633: PackedInts Packed32 and Packed64 did not support internal
@@ -363,13 +342,6 @@ Bug fixes
with more document deletions is requested before a reader with fewer
deletions, provided they share some segments. (yonik)
-* LUCENE-2802: NRT DirectoryReader returned incorrect values from
- getVersion, isOptimized, getCommitUserData, getIndexCommit and isCurrent due
- to a mutable reference to the IndexWriters SegmentInfos.
- (Simon Willnauer, Earwin Burrfoot)
-
-
-
======================= Lucene 3.x (not yet released) =======================
Changes in backwards compatibility policy
@@ -408,9 +380,9 @@ Changes in backwards compatibility polic
* LUCENE-2302: The new interface for term attributes, CharTermAttribute,
now implements CharSequence. This requires the toString() methods of
CharTermAttribute, deprecated TermAttribute, and Token to return only
- the term text and no other attribute contents.
- TODO: Point to new attribute inspection API coming with LUCENE-2374.
- (Uwe Schindler, Robert Muir)
+ the term text and no other attribute contents. LUCENE-2374 implements
+ an attribute reflection API to no longer rely on toString() for attribute
+ inspection. (Uwe Schindler, Robert Muir)
* LUCENE-2372, LUCENE-2389: StandardAnalyzer, KeywordAnalyzer,
PerFieldAnalyzerWrapper, WhitespaceTokenizer are now final. Also removed
@@ -434,10 +406,37 @@ Changes in backwards compatibility polic
* LUCENE-2733: Removed public constructors of utility classes with only static
methods to prevent instantiation. (Uwe Schindler)
-* LUCENE-2753: IndexReader and DirectoryReader .listCommits() now return a List
- instead of a Collection, guaranteeing the commits are sorted from oldest to
- latest. (Shai Erera)
+* LUCENE-2602: The default (LogByteSizeMergePolicy) merge policy now
+ takes deletions into account by default. You can disable this by
+ calling setCalibrateSizeByDeletes(false) on the merge policy. (Mike
+ McCandless)
+
+* LUCENE-2529, LUCENE-2668: Position increment gap and offset gap of empty
+ values in multi-valued field has been changed for some cases in index.
+ If you index empty fields and uses positions/offsets information on that
+ fields, reindex is recommended. (David Smiley, Koji Sekiguchi)
+* LUCENE-2804: Directory.setLockFactory new declares throwing an IOException.
+ (Shai Erera, Robert Muir)
+
+* LUCENE-2837: Added deprecations noting that in 4.0, Searcher and
+ Searchable are collapsed into IndexSearcher; contrib/remote and
+ MultiSearcher have been removed. (Mike McCandless)
+
+* LUCENE-2854: Deprecated SimilarityDelegator and
+ Similarity.lengthNorm; the latter is now final, forcing any custom
+ Similarity impls to cutover to the more general computeNorm (Robert
+ Muir, Mike McCandless)
+
+* LUCENE-2869: Deprecated Query.getSimilarity: instead of using
+ "runtime" subclassing/delegation, subclass the Weight instead.
+ (Robert Muir)
+
+* LUCENE-2674: A new idfExplain method was added to Similarity, that
+ accepts an incoming docFreq. If you subclass Similarity, make sure
+ you also override this method on upgrade. (Robert Muir, Mike
+ McCandless)
+
Changes in runtime behavior
* LUCENE-1923: Made IndexReader.toString() produce something
@@ -453,7 +452,7 @@ Changes in runtime behavior
invokes a merge on the incoming and target segments, but instead copies the
segments to the target index. You can call maybeMerge or optimize after this
method completes, if you need to.
-
+
In addition, Directory.copyTo* were removed in favor of copy which takes the
target Directory, source and target files as arguments, and copies the source
file to the target Directory under the target file name. (Shai Erera)
@@ -465,10 +464,41 @@ Changes in runtime behavior
usage, allowing applications to accidentally open two writers on the
same directory. (Mike McCandless)
-* LUCENE-2701: maxMergeMB and maxMergeDocs constraints set on LogMergePolicy now
- affect optimize() as well (as opposed to only regular merges). This means that
- you can run optimize() and too large segments won't be merged. (Shai Erera)
+* LUCENE-2701: maxMergeMBForOptimize and maxMergeDocs constraints set on
+ LogMergePolicy now affect optimize() as well (as opposed to only regular
+ merges). This means that you can run optimize() and too large segments won't
+ be merged. (Shai Erera)
+
+* LUCENE-2753: IndexReader and DirectoryReader .listCommits() now return a List,
+ guaranteeing the commits are sorted from oldest to latest. (Shai Erera)
+
+* LUCENE-2785: TopScoreDocCollector, TopFieldCollector and
+ the IndexSearcher search methods that take an int nDocs will now
+ throw IllegalArgumentException if nDocs is 0. Instead, you should
+ use the newly added TotalHitCountCollector. (Mike McCandless)
+
+* LUCENE-2790: LogMergePolicy.useCompoundFile's logic now factors in noCFSRatio
+ to determine whether the passed in segment should be compound.
+ (Shai Erera, Earwin Burrfoot)
+* LUCENE-2805: IndexWriter now increments the index version on every change to
+ the index instead of for every commit. Committing or closing the IndexWriter
+ without any changes to the index will not cause any index version increment.
+ (Simon Willnauer, Mike McCandless)
+
+* LUCENE-2650, LUCENE-2825: The behavior of FSDirectory.open has changed. On 64-bit
+ Windows and Solaris systems that support unmapping, FSDirectory.open returns
+ MMapDirectory. Additionally the behavior of MMapDirectory has been
+ changed to enable unmapping by default if supported by the JRE.
+ (Mike McCandless, Uwe Schindler, Robert Muir)
+
+* LUCENE-2829: Improve the performance of "primary key" lookup use
+ case (running a TermQuery that matches one document) on a
+ multi-segment index. (Robert Muir, Mike McCandless)
+
+* LUCENE-2010: Segments with 100% deleted documents are now removed on
+ IndexReader or IndexWriter commit. (Uwe Schindler, Mike McCandless)
+
API Changes
* LUCENE-2076: Rename FSDirectory.getFile -> getDirectory. (George
@@ -479,7 +509,7 @@ API Changes
custom Similarity can alter how norms are encoded, though they must
still be encoded as a single byte (Johan Kindgren via Mike
McCandless)
-
+
* LUCENE-2103: NoLockFactory should have a private constructor;
until Lucene 4.0 the default one will be deprecated.
(Shai Erera via Uwe Schindler)
@@ -551,17 +581,77 @@ API Changes
(such as SnapshotDeletionPolicy), you can call this method to remove those
commit points when they are not needed anymore (instead of waiting for the
next commit). (Shai Erera)
-
-* LUCENE-2455: IndexWriter.addIndexesNoOptimize was renamed to addIndexes.
- IndexFileNames.segmentFileName now takes another parameter to accommodate
- custom file names. You should use this method to name all your files.
- (Shai Erera)
* LUCENE-2481: SnapshotDeletionPolicy.snapshot() and release() were replaced
with equivalent ones that take a String (id) as argument. You can pass
whatever ID you want, as long as you use the same one when calling both.
(Shai Erera)
+* LUCENE-2356: Add IndexWriterConfig.set/getReaderTermIndexDivisor, to
+ set what IndexWriter passes for termsIndexDivisor to the readers it
+ opens internally when apply deletions or creating a near-real-time
+ reader. (Earwin Burrfoot via Mike McCandless)
+
+* LUCENE-2167,LUCENE-2699,LUCENE-2763,LUCENE-2847: StandardTokenizer/Analyzer
+ in common/standard/ now implement the Word Break rules from the Unicode 6.0.0
+ Text Segmentation algorithm (UAX#29), covering the full range of Unicode code
+ points, including values from U+FFFF to U+10FFFF
+
+ ClassicTokenizer/Analyzer retains the old (pre-Lucene 3.1) StandardTokenizer/
+ Analyzer implementation and behavior. Only the Unicode Basic Multilingual
+ Plane (code points from U+0000 to U+FFFF) is covered.
+
+ UAX29URLEmailTokenizer tokenizes URLs and E-mail addresses according to the
+ relevant RFCs, in addition to implementing the UAX#29 Word Break rules.
+ (Steven Rowe, Robert Muir, Uwe Schindler)
+
+* LUCENE-2778: RAMDirectory now exposes newRAMFile() which allows to override
+ and return a different RAMFile implementation. (Shai Erera)
+
+* LUCENE-2785: Added TotalHitCountCollector whose sole purpose is to
+ count the number of hits matching the query. (Mike McCandless)
+
+* LUCENE-2846: Deprecated IndexReader.setNorm(int, String, float). This method
+ is only syntactic sugar for setNorm(int, String, byte), but using the global
+ Similarity.getDefault().encodeNormValue(). Use the byte-based method instead
+ to ensure that the norm is encoded with your Similarity.
+ (Robert Muir, Mike McCandless)
+
+* LUCENE-2374: Added Attribute reflection API: It's now possible to inspect the
+ contents of AttributeImpl and AttributeSource using a well-defined API.
+ This is e.g. used by Solr's AnalysisRequestHandlers to display all attributes
+ in a structured way.
+ There are also some backwards incompatible changes in toString() output,
+ as LUCENE-2302 introduced the CharSequence interface to CharTermAttribute
+ leading to changed toString() return values. The new API allows to get a
+ string representation in a well-defined way using a new method
+ reflectAsString(). For backwards compatibility reasons, when toString()
+ was implemented by implementation subclasses, the default implementation of
+ AttributeImpl.reflectWith() uses toString()s output instead to report the
+ Attribute's properties. Otherwise, reflectWith() uses Java's reflection
+ (like toString() did before) to get the attribute properties.
+ In addition, the mandatory equals() and hashCode() are no longer required
+ for AttributeImpls, but can still be provided (if needed).
+ (Uwe Schindler)
+
+* LUCENE-2876: Deprecated Scorer.getSimilarity(). If your Scorer uses a Similarity,
+ it should keep it itself. Fixed Scorers to pass their parent Weight, so that
+ Scorer.visitSubScorers (LUCENE-2590) will work correctly.
+ (Robert Muir, Doron Cohen)
+
+* LUCENE-2900: When opening a near-real-time (NRT) reader
+ (IndexReader.re/open(IndexWriter)) you can now specify whether
+ deletes should be applied. Applying deletes can be costly, and some
+ expert use cases can handle seeing deleted documents returned. The
+ deletes remain buffered so that the next time you open an NRT reader
+ and pass true, all deletes will be a applied. (Mike McCandless)
+
+* LUCENE-1253: LengthFilter (and Solr's KeepWordTokenFilter) now
+ require up front specification of enablePositionIncrement. Together with
+ StopFilter they have a common base class (FilteringTokenFilter) that handles
+ the position increments automatically. Implementors only need to override an
+ accept() method that filters tokens. (Uwe Schindler, Robert Muir)
+
Bug fixes
* LUCENE-2249: ParallelMultiSearcher should shut down thread pool on
@@ -582,10 +672,6 @@ Bug fixes
a prior (corrupt) index missing its segments_N file. (Mike
McCandless)
-* LUCENE-2534: fix over-sharing bug in
- MultiTermsEnum.docs/AndPositionsEnum. (Robert Muir, Mike
- McCandless)
-
* LUCENE-2458: QueryParser no longer automatically forms phrase queries,
assuming whitespace tokenization. Previously all CJK queries, for example,
would be turned into phrase queries. The old behavior is preserved with
@@ -604,7 +690,41 @@ Bug fixes
can cause the same document to score to differently depending on
what segment it resides in. (yonik)
-* LUCENE-2272: Fix explain in PayloadNearQuery and also fix scoring issue (Peter Keegan via Grant Ingersoll)
+* LUCENE-2272: Fix explain in PayloadNearQuery and also fix scoring issue (Peter Keegan via Grant Ingersoll)
+
+* LUCENE-2732: Fix charset problems in XML loading in
+ HyphenationCompoundWordTokenFilter. (Uwe Schindler)
+
+* LUCENE-2802: NRT DirectoryReader returned incorrect values from
+ getVersion, isOptimized, getCommitUserData, getIndexCommit and isCurrent due
+ to a mutable reference to the IndexWriters SegmentInfos.
+ (Simon Willnauer, Earwin Burrfoot)
+
+* LUCENE-2852: Fixed corner case in RAMInputStream that would hit a
+ false EOF after seeking to EOF then seeking back to same block you
+ were just in and then calling readBytes (Robert Muir, Mike McCandless)
+
+* LUCENE-2860: Fixed SegmentInfo.sizeInBytes to factor includeDocStores when it
+ decides whether to return the cached computed size or not. (Shai Erera)
+
+* LUCENE-2584: SegmentInfo.files() could hit ConcurrentModificationException if
+ called by multiple threads. (Alexander Kanarsky via Shai Erera)
+
+* LUCENE-2809: Fixed IndexWriter.numDocs to take into account
+ applied but not yet flushed deletes. (Mike McCandless)
+
+* LUCENE-2879: MultiPhraseQuery previously calculated its phrase IDF by summing
+ internally, it now calls Similarity.idfExplain(Collection, IndexSearcher).
+ (Robert Muir)
+
+* LUCENE-2693: RAM used by IndexWriter was slightly incorrectly computed.
+ (Jason Rutherglen via Shai Erera)
+
+* LUCENE-1846: DateTools now uses the US locale everywhere, so DateTools.round()
+ is safe also in strange locales. (Uwe Schindler)
+
+* LUCENE-2891: IndexWriterConfig did not accept -1 in setReaderTermIndexDivisor,
+ which can be used to prevent loading the terms index into memory. (Shai Erera)
New features
@@ -630,8 +750,8 @@ New features
stopwords, and implement many analyzers in contrib with it.
(Simon Willnauer via Robert Muir)
-* LUCENE-2198: Support protected words in stemming TokenFilters using a
- new KeywordAttribute. (Simon Willnauer via Uwe Schindler)
+* LUCENE-2198, LUCENE-2901: Support protected words in stemming TokenFilters using a
+ new KeywordAttribute. (Simon Willnauer, Drew Farris via Uwe Schindler)
* LUCENE-2183, LUCENE-2240, LUCENE-2241: Added Unicode 4 support
to CharTokenizer and its subclasses. CharTokenizer now has new
@@ -677,6 +797,16 @@ New features
can be used to prevent commits from ever getting deleted from the index.
(Shai Erera)
+* LUCENE-1585: IndexWriter now accepts a PayloadProcessorProvider which can
+ return a DirPayloadProcessor for a given Directory, which returns a
+ PayloadProcessor for a given Term. The PayloadProcessor will be used to
+ process the payloads of the segments as they are merged (e.g. if one wants to
+ rewrite payloads of external indexes as they are added, or of local ones).
+ (Shai Erera, Michael Busch, Mike McCandless)
+
+* LUCENE-2440: Add support for custom ExecutorService in
+ ParallelMultiSearcher (Edward Drapkin via Mike McCandless)
+
* LUCENE-2295: Added a LimitTokenCountAnalyzer / LimitTokenCountFilter
to wrap any other Analyzer and provide the same functionality as
MaxFieldLength provided on IndexWriter. This patch also fixes a bug
@@ -684,9 +814,17 @@ New features
* LUCENE-2526: Don't throw NPE from MultiPhraseQuery.toString when
it's empty. (Ross Woolf via Mike McCandless)
+
+* LUCENE-2559: Added SegmentReader.reopen methods (John Wang via Mike
+ McCandless)
-* LUCENE-2671: Add SortField.setMissingValue( v ) to enable sorting
- behavior for documents that do not include the given field. (ryan)
+* LUCENE-2590: Added Scorer.visitSubScorers, and Scorer.freq. Along
+ with a custom Collector these experimental methods make it possible
+ to gather the hit-count per sub-clause and per document while a
+ search is running. (Simon Willnauer, Mike McCandless)
+
+* LUCENE-2636: Added MultiCollector which allows running the search with several
+ Collectors. (Shai Erera)
* LUCENE-2754, LUCENE-2757: Added a wrapper around MultiTermQueries
to add span support: SpanMultiTermQueryWrapper<Q extends MultiTermQuery>.
@@ -698,9 +836,21 @@ New features
is no longer needed and discouraged for that use case. Directly wrapping
Query improves performance, as out-of-order collection is now supported.
(Uwe Schindler)
+
+* LUCENE-2864: Add getMaxTermFrequency (maximum within-document TF) to
+ FieldInvertState so that it can be used in Similarity.computeNorm.
+ (Robert Muir)
+
+* LUCENE-2474: Added expert ReaderFinishedListener API to
+ IndexReader, to allow apps that maintain external per-segment caches
+ to evict entries when a segment is finished. (Shay Banon, Yonik
+ Seeley, Mike McCandless)
Optimizations
+* LUCENE-2494: Use CompletionService in ParallelMultiSearcher instead of
+ simple polling for results. (Edward Drapkin, Simon Willnauer)
+
* LUCENE-2075: Terms dict cache is now shared across threads instead
of being stored separately in thread local storage. Also fixed
terms dict so that the cache is used when seeking the thread local
@@ -763,6 +913,17 @@ Optimizations
(getStrings, getStringIndex), consume quite a bit less RAM in most
cases. (Mike McCandless)
+* LUCENE-2410: ~20% speedup on exact (slop=0) PhraseQuery matching.
+ (Mike McCandless)
+
+* LUCENE-2531: Fix issue when sorting by a String field that was
+ causing too many fallbacks to compare-by-value (instead of by-ord).
+ (Mike McCandless)
+
+* LUCENE-2574: IndexInput exposes copyBytes(IndexOutput, long) to allow for
+ efficient copying by sub-classes. Optimized copy is implemented for RAM and FS
+ streams. (Shai Erera)
+
* LUCENE-2719: Improved TermsHashPerField's sorting to use a better
quick sort algorithm that dereferences the pivot element not on
every compare call. Also replaced lots of sorting code in Lucene
@@ -777,6 +938,16 @@ Optimizations
DirectoryReaders or other MultiReaders. This saves lots of memory
during merge of norms. (Uwe Schindler, Mike McCandless)
+* LUCENE-2824: Optimize BufferedIndexInput to do less bounds checks.
+ (Robert Muir)
+
+* LUCENE-2010: Segments with 100% deleted documents are now removed on
+ IndexReader or IndexWriter commit. (Uwe Schindler, Mike McCandless)
+
+* LUCENE-1472: Removed synchronization from static DateTools methods
+ by using a ThreadLocal. Also converted DateTools.Resolution to a
+ Java 5 enum (this should not break backwards). (Uwe Schindler)
+
Build
* LUCENE-2124: Moved the JDK-based collation support from contrib/collation
@@ -804,6 +975,13 @@ Build
"ant idea". See http://wiki.apache.org/lucene-java/HowtoConfigureIntelliJ
(Steven Rowe)
+* LUCENE-2657: Switch from using Maven POM templates to full POMs when
+ generating Maven artifacts (Steven Rowe)
+
+* LUCENE-2609: Added jar-test-framework Ant target which packages Lucene's
+ tests' framework classes. (Drew Farris, Grant Ingersoll, Shai Erera, Steven
+ Rowe)
+
Test Cases
* LUCENE-2037 Allow Junit4 tests in our environment (Erick Erickson
@@ -842,6 +1020,21 @@ Test Cases
as Eclipse and IntelliJ.
(Paolo Castagna, Steven Rowe via Robert Muir)
+* LUCENE-2804: add newFSDirectory to LuceneTestCase to create a FSDirectory at
+ random. (Shai Erera, Robert Muir)
+
+Documentation
+
+* LUCENE-2579: Fix oal.search's package.html description of abstract
+ methods. (Santiago M. Mola via Mike McCandless)
+
+* LUCENE-2625: Add a note to IndexReader.termDocs() with additional verbiage
+ that the TermEnum must be seeked since it is unpositioned.
+ (Adriano Crestani via Robert Muir)
+
+* LUCENE-2894: Use google-code-prettify for syntax highlighting in javadoc.
+ (Koji Sekiguchi)
+
================== Release 2.9.4 / 3.0.3 2010-12-03 ====================
Changes in runtime behavior
Modified: lucene/dev/branches/docvalues/lucene/MIGRATE.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/MIGRATE.txt?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/MIGRATE.txt (original)
+++ lucene/dev/branches/docvalues/lucene/MIGRATE.txt Wed Feb 9 09:35:27 2011
@@ -325,6 +325,15 @@ LUCENE-1458, LUCENE-2111: Flexible Index
global AttributeSource to each segments TermsEnum. The TermsEnum is consumer
and gets the current minimum competitive boosts (MTQ.MaxNonCompetitiveBoostAttribute).
-* LUCENE-2761: DataInput.readVInt/readVLong and DataOutput.writeVInt/writeVLong
- are final. If you subclassed this code before to encode variable-length
- integers in some specialized way, use the Codec API instead.
+* LUCENE-2374: The backwards layer in AttributeImpl was removed. To support correct
+ reflection of AttributeImpl instances, where the reflection was done using deprecated
+ toString() parsing, you have to now override reflectWith() to customize output.
+ toString() is no longer implemented by AttributeImpl, so if you have overridden
+ toString(), port your customization over to reflectWith(). reflectAsString() would
+ then return what toString() did before.
+
+* LUCENE-2236: DefaultSimilarity can no longer be set statically (and dangerously) for the entire JVM.
+ Instead, IndexWriterConfig and IndexSearcher now take a SimilarityProvider.
+ Similarity can now be configured on a per-field basis.
+ Similarity retains only the field-specific relevance methods such as tf() and idf().
+ Methods that apply to the entire query such as coord() and queryNorm() exist in SimilarityProvider.
Modified: lucene/dev/branches/docvalues/lucene/NOTICE.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/NOTICE.txt?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/NOTICE.txt (original)
+++ lucene/dev/branches/docvalues/lucene/NOTICE.txt Wed Feb 9 09:35:27 2011
@@ -27,3 +27,6 @@ The class org.apache.lucene.SorterTempla
the same name. The implementation part is mainly done using pre-existing
Lucene sorting code. In-place stable mergesort was borrowed from CGLIB,
which is Apache-licensed.
+
+The Google Code Prettify is Apache License 2.0.
+See http://code.google.com/p/google-code-prettify/
Modified: lucene/dev/branches/docvalues/lucene/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/build.xml Wed Feb 9 09:35:27 2011
@@ -17,7 +17,8 @@
limitations under the License.
-->
-<project name="core" default="default" basedir=".">
+<project name="core" default="default" basedir="."
+ xmlns:artifact="antlib:org.apache.maven.artifact.ant">
<property name="junit.includes" value="**/Test*.java"/>
@@ -32,12 +33,13 @@
<path refid="classpath"/>
<path refid="junit-path"/>
<path refid="ant-path"/>
+ <pathelement location="${build.dir}/classes/test-framework"/>
<pathelement location="${build.dir}/classes/test"/>
</path>
-
<path id="junit.classpath">
<path refid="junit-path"/>
+ <pathelement location="${build.dir}/classes/test-framework"/>
<pathelement location="${build.dir}/classes/test"/>
<pathelement location="${build.dir}/classes/java"/>
<pathelement path="${java.class.path}"/>
@@ -48,7 +50,7 @@
excludes="contrib/db/*/lib/,contrib/*/ext-libs/,src/site/build/"
/>
<patternset id="binary.build.dist.patterns"
- includes="${final.name}.jar,docs/,contrib/*/*.jar,contrib/*/*.war, contrib/*/*/*.jar"
+ includes="${final.name}*.jar,docs/,contrib/*/*.jar,contrib/*/*.war, contrib/*/*/*.jar"
/>
<patternset id="binary.root.dist.patterns"
includes="docs/,*.txt,contrib/*/README*,**/CHANGES.txt"
@@ -153,7 +155,7 @@
</target>
<target name="javadocs" description="Generate javadoc"
- depends="javadocs-all, javadocs-core, javadocs-contrib">
+ depends="javadocs-all, javadocs-core, javadocs-contrib, javadocs-test-framework">
<echo file="${javadoc.dir}/index.html" append="false">
<![CDATA[<html><head><title>${Name} ${version} Javadoc Index</title></head>
<body>
@@ -217,7 +219,6 @@
<packageset dir="contrib/memory/src/java"/>
<packageset dir="contrib/misc/src/java"/>
<packageset dir="contrib/queries/src/java"/>
- <packageset dir="contrib/remote/src/java"/>
<packageset dir="contrib/spatial/src/java"/>
<packageset dir="contrib/spellchecker/src/java"/>
<packageset dir="contrib/swing/src/java"/>
@@ -260,7 +261,7 @@
<!-- ================================================================== -->
<!-- -->
<!-- ================================================================== -->
- <target name="package" depends="jar-core, javadocs, build-contrib, init-dist, changes-to-html"/>
+ <target name="package" depends="jar-core, jar-test-framework, javadocs, build-contrib, init-dist, changes-to-html"/>
<target name="nightly" depends="test, package-tgz">
</target>
@@ -390,19 +391,38 @@
<target name="dist-all" depends="dist, dist-src"/>
- <target name="generate-maven-artifacts" depends="maven.ant.tasks-check, package, jar-src, javadocs">
+ <target name="generate-maven-artifacts" depends="maven.ant.tasks-check, package, jar-src, jar-test-framework-src, javadocs">
<sequential>
- <m2-deploy pom.xml="lucene-parent-pom.xml.template"/>
- <m2-deploy pom.xml="lucene-core-pom.xml.template">
+ <ant target="get-maven-poms" dir=".."/>
+
+ <m2-deploy pom.xml="../pom.xml"/> <!-- Lucene/Solr grandparent POM -->
+ <m2-deploy pom.xml="pom.xml"/> <!-- Lucene parent POM -->
+ <m2-deploy pom.xml="src/pom.xml"> <!-- Lucene core POM -->
<artifact-attachments>
<attach file="${build.dir}/${final.name}-src.jar"
classifier="sources"/>
<attach file="${build.dir}/${final.name}-javadoc.jar"
classifier="javadoc"/>
+ <attach file="${build.dir}/${final.name}-tests.jar"
+ classifier="tests"/>
</artifact-attachments>
</m2-deploy>
-
- <m2-deploy pom.xml="lucene-contrib-pom.xml.template"/>
+
+ <artifact:install-provider artifactId="wagon-ssh" version="1.0-beta-7"/>
+ <artifact:pom id="test-framework-pom" file="src/test-framework/pom.xml"/>
+ <artifact:deploy>
+ <attach file="${build.dir}/${final.name}-tests.jar"
+ classifier="tests" />
+ <attach file="${build.dir}/${final.name}-tests-src.jar"
+ classifier="test-sources"/>
+ <attach file="${build.dir}/${final.name}-tests-javadoc.jar"
+ classifier="test-javadoc"/>
+ <remoteRepository url="${m2.repository.url}">
+ <authentication username="${m2.repository.username}" privateKey="${m2.repository.private.key}"/>
+ </remoteRepository>
+ <pom refid="test-framework-pom"/>
+ </artifact:deploy>
+
<contrib-crawl target="dist-maven"/>
</sequential>
</target>
@@ -600,20 +620,30 @@
<patch patchfile="${patch.file}" strip="0"/>
</target>
- <target name="rat-sources-typedef">
- <typedef resource="org/apache/rat/anttasks/antlib.xml" uri="antlib:rat.anttasks">
- <classpath>
- <fileset dir="." includes="rat*.jar"/>
- </classpath>
- </typedef>
+ <target name="jar-test-framework" depends="compile-test-framework">
+ <jarify basedir="${build.dir}/classes/test-framework" destfile="${build.dir}/${final.name}-tests.jar"
+ title="Lucene Search Engine: Test Framework" />
</target>
- <target name="rat-sources" depends="rat-sources-typedef"
- description="runs the tasks over src/java">
- <rat:report xmlns:rat="antlib:org.apache.rat.anttasks">
- <fileset dir="src/java">
- </fileset>
- </rat:report>
+ <target name="javadocs-test-framework">
+ <sequential>
+ <mkdir dir="${javadoc.dir}/test-framework"/>
+ <invoke-javadoc
+ destdir="${javadoc.dir}/test-framework"
+ title="${Name} ${version} Test Framework API">
+ <sources>
+ <packageset dir="src/test-framework"/>
+ <link href=""/>
+ </sources>
+ </invoke-javadoc>
+ <jarify basedir="${javadoc.dir}/test-framework" destfile="${build.dir}/${final.name}-tests-javadoc.jar"
+ title="Lucene Search Engine: Test Framework" />
+ </sequential>
+ </target>
+
+ <target name="jar-test-framework-src" depends="init">
+ <jarify basedir="${tests-framework.src.dir}" destfile="${build.dir}/${final.name}-tests-src.jar"
+ title="Lucene Search Engine: Test Framework" />
</target>
</project>
Modified: lucene/dev/branches/docvalues/lucene/common-build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/common-build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/common-build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/common-build.xml Wed Feb 9 09:35:27 2011
@@ -25,6 +25,9 @@
<dirname file="${ant.file.common}" property="common.dir"/>
+ <property name="dev-tools.dir" value="${common.dir}/../dev-tools"/>
+ <property name="prettify.dir" value="${dev-tools.dir}/prettify"/>
+
<!-- Give user a chance to override without editing this file
(and without typing -D each time it compiles it -->
<property file="${user.home}/lucene.build.properties"/>
@@ -110,6 +113,7 @@
<property name="src.dir" location="src/java"/>
<property name="tests.src.dir" location="src/test"/>
+ <property name="tests-framework.src.dir" location="${common.dir}/src/test-framework"/>
<property name="build.dir" location="build"/>
<property name="dist.dir" location="dist"/>
<property name="maven.dist.dir" location="dist/maven"/>
@@ -318,32 +322,22 @@
</fail>
</target>
- <property name="pom.xml" value="pom.xml.template"/>
-
<macrodef name="m2-deploy" description="Builds a Maven artifact">
<element name="artifact-attachments" optional="yes"/>
- <attribute name="pom.xml" default="${pom.xml}"/>
+ <attribute name="pom.xml" default="pom.xml"/>
<sequential>
- <copy file="@{pom.xml}" tofile="${build.dir}/@{pom.xml}">
- <filterset begintoken="@" endtoken="@">
- <filter token="version" value="${version}"/>
- </filterset>
- </copy>
- <artifact:install-provider artifactId="wagon-ssh" version="1.0-beta-2"/>
-
- <artifact:pom id="maven.project" file="${build.dir}/@{pom.xml}" />
+ <artifact:install-provider artifactId="wagon-ssh" version="1.0-beta-7"/>
+ <artifact:pom id="maven.project" file="@{pom.xml}"/>
<artifact:deploy file="${build.dir}/${maven.project.build.finalName}.jar">
<artifact-attachments/>
<remoteRepository url="${m2.repository.url}">
<authentication username="${m2.repository.username}" privateKey="${m2.repository.private.key}"/>
- </remoteRepository>
+ </remoteRepository>
<pom refid="maven.project"/>
</artifact:deploy>
</sequential>
</macrodef>
-
-
<macrodef name="build-manifest" description="Builds a manifest file">
<attribute name="title" default="Lucene Search Engine: ${ant.project.name}" />
<sequential>
@@ -370,6 +364,8 @@
<macrodef name="jarify" description="Builds a JAR file">
<attribute name="basedir" default="${build.dir}/classes/java"/>
<attribute name="destfile" default="${build.dir}/${final.name}.jar"/>
+ <attribute name="title" default="Lucene Search Engine: ${ant.project.name}"/>
+ <attribute name="excludes" default="**/pom.xml"/>
<element name="manifest-attributes" optional="yes"/>
<element name="metainf-includes" optional="yes"/>
<sequential>
@@ -379,12 +375,13 @@
<arg line="."/>
</exec>
- <build-manifest/>
+ <build-manifest title="@{title}"/>
<jar
destfile="@{destfile}"
basedir="@{basedir}"
- manifest="${manifest.file}">
+ manifest="${manifest.file}"
+ excludes="@{excludes}">
<manifest>
<manifest-attributes/>
</manifest>
@@ -397,7 +394,12 @@
</sequential>
</macrodef>
- <target name="compile-test" depends="compile-core">
+ <target name="compile-test-framework" depends="compile-core">
+ <compile-test-macro srcdir="${tests-framework.src.dir}" destdir="${common.dir}/build/classes/test-framework"
+ test.classpath="test.classpath"/>
+ </target>
+
+ <target name="compile-test" depends="compile-test-framework">
<compile-test-macro srcdir="${tests.src.dir}" destdir="${build.dir}/classes/test"
test.classpath="test.classpath"/>
</target>
@@ -560,6 +562,9 @@
<fileset dir="${src.dir}">
<include name="org/apache/**/*.java" />
</fileset>
+ <testsources dir="${tests-framework.src.dir}">
+ <include name="org/apache/**/*.java" />
+ </testsources>
<testsources dir="${tests.src.dir}">
<include name="org/apache/**/*.java" />
</testsources>
@@ -590,6 +595,9 @@
<fileset dir="contrib" id="clover.contrib.test.src.files">
<include name="**/test/**/*.java"/>
</fileset>
+ <fileset dir="${tests-framework.src.dir}" id="clover.test.src.files">
+ <include name="**/*.java" />
+ </fileset>
<fileset dir="${tests.src.dir}" id="clover.test.src.files">
<include name="**/*.java" />
</fileset>
@@ -648,6 +656,23 @@
<target name="default" depends="jar-core"/>
+ <target name="rat-sources-typedef">
+ <typedef resource="org/apache/rat/anttasks/antlib.xml" uri="antlib:rat.anttasks">
+ <classpath>
+ <fileset dir="." includes="rat*.jar"/>
+ </classpath>
+ </typedef>
+ </target>
+
+ <target name="rat-sources" depends="rat-sources-typedef"
+ description="runs the tasks over source and test files">
+ <rat:report xmlns:rat="antlib:org.apache.rat.anttasks">
+ <fileset dir="${src.dir}"/>
+ <fileset dir="${tests-framework.src.dir}"/>
+ <fileset dir="${tests.src.dir}"/>
+ </rat:report>
+ </target>
+
<!--+
| M A C R O S
+-->
@@ -703,6 +728,9 @@
<attribute name="destdir"/>
<attribute name="title" default="${Name} ${version} API"/>
<sequential>
+ <copy todir="@{destdir}/../prettify" overwrite="false">
+ <fileset dir="${prettify.dir}"/>
+ </copy>
<javadoc
overview="${src.dir}/overview.html"
packagenames="org.apache.lucene.*"
@@ -718,6 +746,7 @@
link="${javadoc.link}"
windowtitle="${Name} ${version} API"
doctitle="@{title}"
+ stylesheetfile="@{destdir}/../prettify/stylesheet+prettify.css"
maxmemory="${javadoc.maxmemory}"
bottom="Copyright &copy; ${year} Apache Software Foundation. All Rights Reserved.">
<tag name="lucene.experimental"
@@ -725,6 +754,10 @@
<tag name="lucene.internal"
description="NOTE: This API is for Lucene internal purposes only and might change in incompatible ways in the next release."/>
<link offline="true" packagelistLoc="${javadoc.dir}"/>
+ <header><![CDATA[
+ <script src="{@docRoot}/../prettify/prettify.js" type="text/javascript"></script>
+ <script language="JavaScript">window.onload=function(){windowTitle();prettyPrint();}</script>
+ ]]></header>
<sources />
Modified: lucene/dev/branches/docvalues/lucene/contrib/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/CHANGES.txt?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/CHANGES.txt (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/CHANGES.txt Wed Feb 9 09:35:27 2011
@@ -4,53 +4,39 @@ Lucene contrib change Log
Build
- * LUCENE-2413: Moved the demo out of lucene core and into contrib/demo.
- (Robert Muir)
-
* LUCENE-2845: Moved contrib/benchmark to modules.
New Features
- * LUCENE-2604: Added RegexpQuery support to contrib/queryparser.
- (Simon Willnauer, Robert Muir)
+ * LUCENE-2604: Added RegexpQuery support to contrib/queryparser.
+ (Simon Willnauer, Robert Muir)
- * LUCENE-2500: Added DirectIOLinuxDirectory, a Linux-specific
- Directory impl that uses the O_DIRECT flag to bypass the buffer
- cache. This is useful to prevent segment merging from evicting
- pages from the buffer cache, since fadvise/madvise do not seem.
- (Michael McCandless)
-
- * LUCENE-2373: Added a Codec implementation that works with append-only
- filesystems (such as e.g. Hadoop DFS). SegmentInfos writing/reading
- code is refactored to support append-only FS, and to allow for future
- customization of per-segment information. (Andrzej Bialecki)
+ * LUCENE-2373: Added a Codec implementation that works with append-only
+ filesystems (such as e.g. Hadoop DFS). SegmentInfos writing/reading
+ code is refactored to support append-only FS, and to allow for future
+ customization of per-segment information. (Andrzej Bialecki)
- * LUCENE-2479: Added ability to provide a sort comparator for spelling suggestions along
- with two implementations. The existing comparator (score, then frequency) is the default (Grant Ingersoll)
+ * LUCENE-2479: Added ability to provide a sort comparator for spelling suggestions along
+ with two implementations. The existing comparator (score, then frequency) is the default (Grant Ingersoll)
- * LUCENE-2608: Added the ability to specify the accuracy at method time in the SpellChecker. The per class
- method is also still available. (Grant Ingersoll)
+ * LUCENE-2608: Added the ability to specify the accuracy at method time in the SpellChecker. The per class
+ method is also still available. (Grant Ingersoll)
- * LUCENE-2507: Added DirectSpellChecker, which retrieves correction candidates directly
- from the term dictionary using levenshtein automata. (Robert Muir)
+ * LUCENE-2507: Added DirectSpellChecker, which retrieves correction candidates directly
+ from the term dictionary using levenshtein automata. (Robert Muir)
- * LUCENE-2791: Added WindowsDirectory, a Windows-specific Directory impl
- that doesn't synchronize on the file handle. This can be useful to
- avoid the performance problems of SimpleFSDirectory and NIOFSDirectory.
- (Robert Muir, Simon Willnauer, Uwe Schindler, Michael McCandless)
-
- * LUCENE-2836: Add FieldCacheRewriteMethod, which rewrites MultiTermQueries
- using the FieldCache's TermsEnum. (Robert Muir)
+ * LUCENE-2836: Add FieldCacheRewriteMethod, which rewrites MultiTermQueries
+ using the FieldCache's TermsEnum. (Robert Muir)
API Changes
- * LUCENE-2606: Changed RegexCapabilities interface to fix thread
- safety, serialization, and performance problems. If you have
- written a custom RegexCapabilities it will need to be updated
- to the new API. (Robert Muir, Uwe Schindler)
+ * LUCENE-2606: Changed RegexCapabilities interface to fix thread
+ safety, serialization, and performance problems. If you have
+ written a custom RegexCapabilities it will need to be updated
+ to the new API. (Robert Muir, Uwe Schindler)
- * LUCENE-2638 MakeHighFreqTerms.TermStats public to make it more useful
- for API use. (Andrzej Bialecki)
+ * LUCENE-2638 MakeHighFreqTerms.TermStats public to make it more useful
+ for API use. (Andrzej Bialecki)
======================= Lucene 3.x (not yet released) =======================
@@ -100,6 +86,11 @@ Changes in runtime behavior
Bug fixes
+ * LUCENE-2855: contrib queryparser was using CharSequence as key in some internal
+ Map instances, which was leading to incorrect behaviour, since some CharSequence
+ implementors do not override hashcode and equals methods. Now the internal Maps
+ are using String instead. (Adriano Crestani)
+
* LUCENE-2068: Fixed ReverseStringFilter which was not aware of supplementary
characters. During reverse the filter created unpaired surrogates, which
will be replaced by U+FFFD by the indexer, but not at query time. The filter
@@ -117,41 +108,48 @@ Bug fixes
default. (Robert Muir, Uwe Schindler, Simon Willnauer)
* LUCENE-2184: Fixed bug with handling best fit value when the proper best fit value is
- not an indexed field. Note, this change affects the APIs. (Grant Ingersoll)
+ not an indexed field. Note, this change affects the APIs. (Grant Ingersoll)
* LUCENE-2359: Fix bug in CartesianPolyFilterBuilder related to handling of behavior around
- the 180th meridian (Grant Ingersoll)
+ the 180th meridian (Grant Ingersoll)
* LUCENE-2404: Fix bugs with position increment and empty tokens in ThaiWordFilter.
For matchVersion >= 3.1 the filter also no longer lowercases. ThaiAnalyzer
will use a separate LowerCaseFilter instead. (Uwe Schindler, Robert Muir)
-* LUCENE-2615: Fix DirectIOLinuxDirectory to not assign bogus
- permissions to newly created files, and to not silently hardwire
- buffer size to 1 MB. (Mark Miller, Robert Muir, Mike McCandless)
-
-* LUCENE-2629: Fix gennorm2 task for generating ICUFoldingFilter's .nrm file. This allows
- you to customize its normalization/folding, by editing the source data files in src/data
- and regenerating a new .nrm with 'ant gennorm2'. (David Bowen via Robert Muir)
-
-* LUCENE-2653: ThaiWordFilter depends on the JRE having a Thai dictionary, which is not
- always the case. If the dictionary is unavailable, the filter will now throw
- UnsupportedOperationException in the constructor. (Robert Muir)
+ * LUCENE-2615: Fix DirectIOLinuxDirectory to not assign bogus
+ permissions to newly created files, and to not silently hardwire
+ buffer size to 1 MB. (Mark Miller, Robert Muir, Mike McCandless)
+
+ * LUCENE-2629: Fix gennorm2 task for generating ICUFoldingFilter's .nrm file. This allows
+ you to customize its normalization/folding, by editing the source data files in src/data
+ and regenerating a new .nrm with 'ant gennorm2'. (David Bowen via Robert Muir)
+
+ * LUCENE-2653: ThaiWordFilter depends on the JRE having a Thai dictionary, which is not
+ always the case. If the dictionary is unavailable, the filter will now throw
+ UnsupportedOperationException in the constructor. (Robert Muir)
-* LUCENE-589: Fix contrib/demo for international documents.
- (Curtis d'Entremont via Robert Muir)
+ * LUCENE-589: Fix contrib/demo for international documents.
+ (Curtis d'Entremont via Robert Muir)
-* LUCENE-2246: Fix contrib/demo for Turkish html documents.
- (Selim Nadi via Robert Muir)
+ * LUCENE-2246: Fix contrib/demo for Turkish html documents.
+ (Selim Nadi via Robert Muir)
-* LUCENE-590: Demo HTML parser gives incorrect summaries when title is repeated as a heading
- (Curtis d'Entremont via Robert Muir)
+ * LUCENE-590: Demo HTML parser gives incorrect summaries when title is repeated as a heading
+ (Curtis d'Entremont via Robert Muir)
-* LUCENE-591: The demo indexer now indexes meta keywords.
- (Curtis d'Entremont via Robert Muir)
+ * LUCENE-591: The demo indexer now indexes meta keywords.
+ (Curtis d'Entremont via Robert Muir)
+
+ * LUCENE-2874: Highlighting overlapping tokens outputted doubled words.
+ (Pierre Gossé via Robert Muir)
API Changes
+ * LUCENE-2867: Some contrib queryparser methods that receives CharSequence as
+ identifier, such as QueryNode#unsetTag(CharSequence), were deprecated and
+ will be removed on version 4. (Adriano Crestani)
+
* LUCENE-2147: Spatial GeoHashUtils now always decode GeoHash strings
with full precision. GeoHash#decode_exactly(String) was merged into
GeoHash#decode(String). (Chris Male, Simon Willnauer)
@@ -192,6 +190,12 @@ API Changes
New features
+ * LUCENE-2500: Added DirectIOLinuxDirectory, a Linux-specific
+ Directory impl that uses the O_DIRECT flag to bypass the buffer
+ cache. This is useful to prevent segment merging from evicting
+ pages from the buffer cache, since fadvise/madvise do not seem.
+ (Michael McCandless)
+
* LUCENE-2306: Add NumericRangeFilter and NumericRangeQuery support to XMLQueryParser.
(Jingkei Ly, via Mark Harwood)
@@ -281,6 +285,14 @@ New features
BooleanModifiersQueryNodeProcessor, for example instead of GroupQueryNodeProcessor.
(Adriano Crestani via Robert Muir)
+ * LUCENE-2791: Added WindowsDirectory, a Windows-specific Directory impl
+ that doesn't synchronize on the file handle. This can be useful to
+ avoid the performance problems of SimpleFSDirectory and NIOFSDirectory.
+ (Robert Muir, Simon Willnauer, Uwe Schindler, Michael McCandless)
+
+ * LUCENE-2842: Add analyzer for Galician. Also adds the RSLP (Orengo) stemmer
+ for Portuguese. (Robert Muir)
+
Build
* LUCENE-2124: Moved the JDK-based collation support from contrib/collation
@@ -302,7 +314,10 @@ Build
(Robert Muir)
* LUCENE-2833: Upgrade contrib/ant's jtidy jar file to r938 (Robert Muir)
-
+
+ * LUCENE-2413: Moved the demo out of lucene core and into contrib/demo.
+ (Robert Muir)
+
Optimizations
* LUCENE-2157: DelimitedPayloadTokenFilter no longer copies the buffer
Modified: lucene/dev/branches/docvalues/lucene/contrib/contrib-build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/contrib-build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/contrib-build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/contrib-build.xml Wed Feb 9 09:35:27 2011
@@ -40,6 +40,7 @@
<path id="test.base.classpath">
<path refid="classpath"/>
+ <pathelement location="${common.dir}/build/classes/test-framework"/>
<pathelement location="${common.dir}/build/classes/test"/>
<path refid="junit-path"/>
<pathelement location="${build.dir}/classes/java"/>
@@ -50,7 +51,6 @@
<path id="junit.classpath">
<path refid="test.classpath"/>
<pathelement location="${build.dir}/classes/test"/>
- <pathelement location="${build.dir}/classes/java"/>
<pathelement path="${java.class.path}"/>
</path>
@@ -71,7 +71,7 @@
<available
type="file"
- file="${pom.xml}"
+ file="pom.xml"
property="pom.xml.present">
</available>
Modified: lucene/dev/branches/docvalues/lucene/contrib/db/bdb-je/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/db/bdb-je/build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/db/bdb-je/build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/db/bdb-je/build.xml Wed Feb 9 09:35:27 2011
@@ -39,13 +39,6 @@
<import file="../../contrib-build.xml" />
- <path id="test.classpath">
- <path refid="classpath"/>
- <pathelement location="../../../build/classes/test/"/>
- <path refid="junit-path"/>
- <pathelement location="${build.dir}/classes/java"/>
- </path>
-
<target name="get-je-jar" unless="je.jar.exists">
<mkdir dir="lib" />
<get src="http://download.oracle.com/maven/com/sleepycat/je/${je.version}/je-${je.version}.jar"
Modified: lucene/dev/branches/docvalues/lucene/contrib/db/bdb/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/db/bdb/build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/db/bdb/build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/db/bdb/build.xml Wed Feb 9 09:35:27 2011
@@ -39,13 +39,6 @@
<import file="../../contrib-build.xml" />
- <path id="test.classpath">
- <path refid="classpath"/>
- <pathelement location="../../../build/classes/test/"/>
- <path refid="junit-path"/>
- <pathelement location="${build.dir}/classes/java"/>
- </path>
-
<target name="get-db-jar" unless="db.jar.exists">
<mkdir dir="lib" />
<get src="http://downloads.osafoundation.org/db/db-${db.version}.jar"
Modified: lucene/dev/branches/docvalues/lucene/contrib/demo/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/demo/build.xml?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/demo/build.xml (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/demo/build.xml Wed Feb 9 09:35:27 2011
@@ -17,7 +17,7 @@
limitations under the License.
-->
-<project name="demo" default="default">
+<project name="demo" default="default" xmlns:artifact="antlib:org.apache.maven.artifact.ant">
<description>
Lucene Demo
@@ -75,4 +75,23 @@
outputDir="src/java/org/apache/lucene/demo/html"
/>
</target>
+
+ <target name="dist-maven" if="pom.xml.present" depends="compile-core,jar-src">
+ <sequential>
+ <artifact:install-provider artifactId="wagon-ssh" version="1.0-beta-7"/>
+ <artifact:pom id="maven.project" file="pom.xml"/>
+ <artifact:deploy file="${build.dir}/${demo.war.name}.war">
+ <attach file="${build.dir}/${maven.project.build.finalName}.jar"
+ classifier="classes"/>
+ <attach file="${build.dir}/${final.name}-src.jar"
+ classifier="sources"/>
+ <attach file="${build.dir}/${final.name}-javadoc.jar"
+ classifier="javadoc"/>
+ <remoteRepository url="${m2.repository.url}">
+ <authentication username="${m2.repository.username}" privateKey="${m2.repository.private.key}"/>
+ </remoteRepository>
+ <pom refid="maven.project"/>
+ </artifact:deploy>
+ </sequential>
+ </target>
</project>
Modified: lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/IndexHTML.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/IndexHTML.java?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/IndexHTML.java (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/IndexHTML.java Wed Feb 9 09:35:27 2011
@@ -84,8 +84,7 @@ public class IndexHTML {
}
writer = new IndexWriter(FSDirectory.open(index), new IndexWriterConfig(
Version.LUCENE_CURRENT, new StandardAnalyzer(Version.LUCENE_CURRENT))
- .setMaxFieldLength(1000000).setOpenMode(
- create ? OpenMode.CREATE : OpenMode.CREATE_OR_APPEND));
+ .setOpenMode(create ? OpenMode.CREATE : OpenMode.CREATE_OR_APPEND));
indexDocs(root, index, create); // add new docs
System.out.println("Optimizing index...");
Modified: lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/SearchFiles.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/SearchFiles.java?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/SearchFiles.java (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/demo/src/java/org/apache/lucene/demo/SearchFiles.java Wed Feb 9 09:35:27 2011
@@ -28,6 +28,7 @@ import org.apache.lucene.analysis.Analyz
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexReader.AtomicReaderContext;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.IndexSearcher;
@@ -160,9 +161,9 @@ public class SearchFiles {
}
@Override
- public void setNextReader(IndexReader reader, int docBase)
+ public void setNextReader(AtomicReaderContext context)
throws IOException {
- this.docBase = docBase;
+ this.docBase = context.docBase;
}
@Override
Modified: lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenSources.java Wed Feb 9 09:35:27 2011
@@ -233,7 +233,10 @@ public class TokenSources {
.size()]);
ArrayUtil.quickSort(tokensInOriginalOrder, new Comparator<Token>() {
public int compare(Token t1, Token t2) {
- return t1.startOffset() - t2.endOffset();
+ if (t1.startOffset() == t2.startOffset())
+ return t1.endOffset() - t2.endOffset();
+ else
+ return t1.startOffset() - t2.startOffset();
}
});
}
Modified: lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java Wed Feb 9 09:35:27 2011
@@ -30,6 +30,7 @@ import org.apache.lucene.analysis.Cachin
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
+import org.apache.lucene.index.IndexReader.AtomicReaderContext;
import org.apache.lucene.index.memory.MemoryIndex;
import org.apache.lucene.search.*;
import org.apache.lucene.search.spans.FieldMaskingSpanQuery;
@@ -50,7 +51,7 @@ public class WeightedSpanTermExtractor {
private String fieldName;
private TokenStream tokenStream;
- private Map<String,IndexReader> readers = new HashMap<String,IndexReader>(10);
+ private Map<String,AtomicReaderContext> readers = new HashMap<String,AtomicReaderContext>(10);
private String defaultField;
private boolean expandMultiTermQuery;
private boolean cachedTokenStream;
@@ -66,11 +67,11 @@ public class WeightedSpanTermExtractor {
}
private void closeReaders() {
- Collection<IndexReader> readerSet = readers.values();
+ Collection<AtomicReaderContext> ctxSet = readers.values();
- for (final IndexReader reader : readerSet) {
+ for (final AtomicReaderContext ctx : ctxSet) {
try {
- reader.close();
+ ctx.reader.close();
} catch (IOException e) {
// alert?
}
@@ -149,7 +150,7 @@ public class WeightedSpanTermExtractor {
query = mtq;
}
if (mtq.getField() != null) {
- IndexReader ir = getReaderForField(mtq.getField());
+ IndexReader ir = getLeafContextForField(mtq.getField()).reader;
extract(query.rewrite(ir), terms);
}
} else if (query instanceof MultiPhraseQuery) {
@@ -234,7 +235,7 @@ public class WeightedSpanTermExtractor {
final boolean mustRewriteQuery = mustRewriteQuery(spanQuery);
if (mustRewriteQuery) {
for (final String field : fieldNames) {
- final SpanQuery rewrittenQuery = (SpanQuery) spanQuery.rewrite(getReaderForField(field));
+ final SpanQuery rewrittenQuery = (SpanQuery) spanQuery.rewrite(getLeafContextForField(field).reader);
queries.put(field, rewrittenQuery);
rewrittenQuery.extractTerms(nonWeightedTerms);
}
@@ -246,12 +247,12 @@ public class WeightedSpanTermExtractor {
for (final String field : fieldNames) {
- IndexReader reader = getReaderForField(field);
+ AtomicReaderContext context = getLeafContextForField(field);
final Spans spans;
if (mustRewriteQuery) {
- spans = queries.get(field).getSpans(reader);
+ spans = queries.get(field).getSpans(context);
} else {
- spans = spanQuery.getSpans(reader);
+ spans = spanQuery.getSpans(context);
}
@@ -317,22 +318,23 @@ public class WeightedSpanTermExtractor {
return rv;
}
- private IndexReader getReaderForField(String field) throws IOException {
+ private AtomicReaderContext getLeafContextForField(String field) throws IOException {
if(wrapToCaching && !cachedTokenStream && !(tokenStream instanceof CachingTokenFilter)) {
tokenStream = new CachingTokenFilter(tokenStream);
cachedTokenStream = true;
}
- IndexReader reader = readers.get(field);
- if (reader == null) {
+ AtomicReaderContext context = readers.get(field);
+ if (context == null) {
MemoryIndex indexer = new MemoryIndex();
indexer.addField(field, tokenStream);
tokenStream.reset();
IndexSearcher searcher = indexer.createSearcher();
- reader = searcher.getIndexReader();
- readers.put(field, reader);
+ // MEM index has only atomic ctx
+ context = (AtomicReaderContext) searcher.getTopReaderContext();
+ readers.put(field, context);
}
- return reader;
+ return context;
}
/**
Modified: lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/vectorhighlight/package.html
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/vectorhighlight/package.html?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/vectorhighlight/package.html (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/java/org/apache/lucene/search/vectorhighlight/package.html Wed Feb 9 09:35:27 2011
@@ -66,7 +66,7 @@ sample text.</p>
<h3>Step 1.</h3>
<p>In Step 1, Fast Vector Highlighter generates {@link org.apache.lucene.search.vectorhighlight.FieldQuery.QueryPhraseMap} from the user query.
<code>QueryPhraseMap</code> consists of the following members:</p>
-<pre>
+<pre class="prettyprint">
public class QueryPhraseMap {
boolean terminal;
int slop; // valid if terminal == true and phraseHighlight == true
Modified: lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterPhraseTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterPhraseTest.java?rev=1068809&r1=1068808&r2=1068809&view=diff
==============================================================================
--- lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterPhraseTest.java (original)
+++ lucene/dev/branches/docvalues/lucene/contrib/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterPhraseTest.java Wed Feb 9 09:35:27 2011
@@ -36,6 +36,7 @@ import org.apache.lucene.index.IndexRead
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermPositionVector;
+import org.apache.lucene.index.IndexReader.AtomicReaderContext;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
@@ -69,7 +70,7 @@ public class HighlighterPhraseTest exten
final IndexReader indexReader = IndexReader.open(directory, true);
try {
assertEquals(1, indexReader.numDocs());
- final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ final IndexSearcher indexSearcher = newSearcher(indexReader);
try {
final PhraseQuery phraseQuery = new PhraseQuery();
phraseQuery.add(new Term(FIELD, "fox"));
@@ -113,7 +114,7 @@ public class HighlighterPhraseTest exten
final IndexReader indexReader = IndexReader.open(directory, true);
try {
assertEquals(1, indexReader.numDocs());
- final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ final IndexSearcher indexSearcher = newSearcher(indexReader);
try {
final Query phraseQuery = new SpanNearQuery(new SpanQuery[] {
new SpanTermQuery(new Term(FIELD, "fox")),
@@ -133,9 +134,9 @@ public class HighlighterPhraseTest exten
}
@Override
- public void setNextReader(IndexReader indexreader, int i)
+ public void setNextReader(AtomicReaderContext context)
throws IOException {
- this.baseDoc = i;
+ this.baseDoc = context.docBase;
}
@Override
@@ -183,7 +184,7 @@ public class HighlighterPhraseTest exten
final IndexReader indexReader = IndexReader.open(directory, true);
try {
assertEquals(1, indexReader.numDocs());
- final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ final IndexSearcher indexSearcher = newSearcher(indexReader);
try {
final PhraseQuery phraseQuery = new PhraseQuery();
phraseQuery.add(new Term(FIELD, "did"));
@@ -226,7 +227,7 @@ public class HighlighterPhraseTest exten
final IndexReader indexReader = IndexReader.open(directory, true);
try {
assertEquals(1, indexReader.numDocs());
- final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ final IndexSearcher indexSearcher = newSearcher(indexReader);
try {
final PhraseQuery phraseQuery = new PhraseQuery();
phraseQuery.add(new Term(FIELD, "did"));
@@ -267,7 +268,7 @@ public class HighlighterPhraseTest exten
final IndexReader indexReader = IndexReader.open(directory, true);
try {
assertEquals(1, indexReader.numDocs());
- final IndexSearcher indexSearcher = new IndexSearcher(indexReader);
+ final IndexSearcher indexSearcher = newSearcher(indexReader);
try {
final Query phraseQuery = new SpanNearQuery(new SpanQuery[] {
new SpanTermQuery(new Term(FIELD, "did")),