Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-8462: Revert ant-patch-snowball modifications. 

This modifications only worked with the latest version of snowball and were specifically applied to handle the new Arabic stemmer.
This change reverts these modifications since they are not compatible with the other stemmer which are created from revision 502.
This commit is contained in:
Jim Ferenczi 2018-10-26 16:03:42 +02:00
parent 6c419454a2
commit 4fa99c2014
2 changed files with 17 additions and 73 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lucene/analysis/common/README.txt
View File

@ -15,6 +15,8 @@ A few changes has been made to the static Snowball code and compiled stemmers:
If you want to add new stemmers, use the exact revision / Git commit above to generate the Java class, place it
in src/java/org/tartarus/snowball/ext, and finally execute "ant patch-snowball". The latter will change the APIs
of the generated class to make it compatible. Already patched classes are not modified.
The Arabic stemmer has been generated from https://github.com/snowballstem/snowball/blob/master/algorithms/arabic.sbl
using the latest version of snowball and patched manually.
IMPORTANT NOTICE ON BACKWARDS COMPATIBILITY!

88
lucene/analysis/common/build.xml
View File

@ -17,10 +17,10 @@
limitations under the License.
-->
<project name="analyzers-common" default="default" xmlns:rsel="antlib:org.apache.tools.ant.types.resources.selectors">
<project name="analyzers-common" default="default">
<description>
Analyzers for indexing content in different languages and domains.
Analyzers for indexing content in different languages and domains.
</description>
<!-- some files for testing that do not have license headers -->
@ -88,7 +88,7 @@
<target xmlns:ivy="antlib:org.apache.ivy.ant" name="-resolve-icu4j" unless="icu4j.resolved" depends="ivy-availability-check,ivy-configure">
<loadproperties prefix="ivyversions" srcFile="${common.dir}/ivy-versions.properties"/>
<ivy:cachepath organisation="com.ibm.icu" module="icu4j" revision="${ivyversions./com.ibm.icu/icu4j}"
inline="true" conf="default" transitive="true" pathid="icu4j.classpath"/>
inline="true" conf="default" transitive="true" pathid="icu4j.classpath"/>
<property name="icu4j.resolved" value="true"/>
</target>
@ -102,10 +102,10 @@
<target name="gen-tlds" depends="compile-tools">
<java
classname="org.apache.lucene.analysis.standard.GenerateJflexTLDMacros"
dir="."
fork="true"
failonerror="true">
classname="org.apache.lucene.analysis.standard.GenerateJflexTLDMacros"
dir="."
fork="true"
failonerror="true">
<classpath>
<pathelement location="${build.dir}/classes/tools"/>
</classpath>
@ -117,8 +117,8 @@
<target name="compile-tools" depends="common.compile-tools">
<compile
srcdir="src/tools/java"
destdir="${build.dir}/classes/tools">
srcdir="src/tools/java"
destdir="${build.dir}/classes/tools">
<classpath refid="classpath"/>
</compile>
</target>
@ -128,71 +128,13 @@
<target name="regenerate" depends="jflex,unicode-data"/>
<target name="patch-snowball" description="Patches all snowball programs in '${snowball.programs.dir}' to make them work with MethodHandles">
<fileset id="snowball.programs" dir="${snowball.programs.dir}" includes="*Stemmer.java"/>
<replaceregexp match="^public class \w+Stemmer\b" replace="@SuppressWarnings(&quot;unused&quot;) \0" flags="m" encoding="UTF-8">
<restrict>
<fileset id="snowball.programs" dir="${snowball.programs.dir}" includes="*Stemmer.java"/>
<replaceregexp match="^public class \w+Stemmer\b" replace="@SuppressWarnings(&quot;unused&quot;) \0" flags="m" encoding="UTF-8">
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="new Among\(([^,]*,[^,]*,[^,]*?)(?=\))" replace="\0, &quot;&quot;, methodObject" flags="g" encoding="UTF-8">
<restrict>
</replaceregexp>
<replaceregexp match="private final static \w+Stemmer methodObject\b.*$" replace="/* patched */ private static final java.lang.invoke.MethodHandles.Lookup methodObject = java.lang.invoke.MethodHandles.lookup();" flags="m" encoding="UTF-8">
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="(new Among\([^,]*,[^,]*,[^,]*,[^,]*,)[^,]*?(?=\))" replace="\1 methodObject" flags="g" encoding="UTF-8">
<restrict>
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="(?:find_among(?:|_b)\()(.*?)(?=\))" replace="\0, \1.length" flags="g" encoding="UTF-8">
<restrict>
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="current" replace="getCurrent()" flags="g" encoding="UTF-8">
<restrict>
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="(?:eq_s(?:|_b)\()(.*?)(?=\))" replace="\0.length(),\1" flags="g" encoding="UTF-8">
<restrict>
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<replaceregexp match="private static final long serialVersionUID(.*)" replace="private static final long serialVersionUID = 1L; ${line.separator}${line.separator} /* patched */ private static final java.lang.invoke.MethodHandles.Lookup methodObject = java.lang.invoke.MethodHandles.lookup();" flags="m" encoding="UTF-8">
<restrict>
<fileset refid="snowball.programs"/>
<rsel:not>
<rsel:contains text="patched"/>
</rsel:not>
</restrict>
</replaceregexp>
<fixcrlf srcdir="${snowball.programs.dir}" includes="*Stemmer.java" tab="remove" tablength="2" encoding="UTF-8" javafiles="yes" fixlast="yes"/>
</replaceregexp>
<fixcrlf srcdir="${snowball.programs.dir}" includes="*Stemmer.java" tab="remove" tablength="2" encoding="UTF-8" javafiles="yes" fixlast="yes"/>
</target>
</project>