You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ji...@apache.org on 2018/10/26 14:21:15 UTC
lucene-solr:branch_7x: 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
Repository: lucene-solr
Updated Branches:
refs/heads/branch_7x 0498cddb3 -> c5fcae8fb
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.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/c5fcae8f
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/c5fcae8f
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/c5fcae8f
Branch: refs/heads/branch_7x
Commit: c5fcae8fbd9d0f41d82cb42eb2cd92a34e0e0a92
Parents: 0498cdd
Author: Jim Ferenczi <ji...@apache.org>
Authored: Fri Oct 26 16:03:42 2018 +0200
Committer: Jim Ferenczi <ji...@apache.org>
Committed: Fri Oct 26 16:20:59 2018 +0200
----------------------------------------------------------------------
lucene/analysis/common/README.txt | 2 +
lucene/analysis/common/build.xml | 88 ++++++----------------------------
2 files changed, 17 insertions(+), 73 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/c5fcae8f/lucene/analysis/common/README.txt
----------------------------------------------------------------------
diff --git a/lucene/analysis/common/README.txt b/lucene/analysis/common/README.txt
index a9fc5f1..f3382f8 100644
--- a/lucene/analysis/common/README.txt
+++ b/lucene/analysis/common/README.txt
@@ -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!
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/c5fcae8f/lucene/analysis/common/build.xml
----------------------------------------------------------------------
diff --git a/lucene/analysis/common/build.xml b/lucene/analysis/common/build.xml
index 2064e19..b8eb37a 100644
--- a/lucene/analysis/common/build.xml
+++ b/lucene/analysis/common/build.xml
@@ -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("unused") \0" flags="m" encoding="UTF-8">
- <restrict>
- <fileset refid="snowball.programs"/>
- <rsel:not>
- <rsel:contains text="patched"/>
- </rsel:not>
- </restrict>
- </replaceregexp>
-
- <replaceregexp match="new Among\(([^,]*,[^,]*,[^,]*?)(?=\))" replace="\0, "", methodObject" flags="g" encoding="UTF-8">
- <restrict>
- <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 id="snowball.programs" dir="${snowball.programs.dir}" includes="*Stemmer.java"/>
+ <replaceregexp match="^public class \w+Stemmer\b" replace="@SuppressWarnings("unused") \0" flags="m" encoding="UTF-8">
<fileset refid="snowball.programs"/>
- <rsel:not>
- <rsel:contains text="patched"/>
- </rsel:not>
- </restrict>
- </replaceregexp>
-
- <replaceregexp match="current" replace="getCurrent()" flags="g" encoding="UTF-8">
- <restrict>
+ </replaceregexp>
+ <replaceregexp match="private final static \w+Stemmer methodObject\b.*$" 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="(?: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>