You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ro...@apache.org on 2018/05/22 08:09:53 UTC
[1/2] lucene-solr:branch_7x: LUCENE-8273: Don't wrap MinHashFilter in
a condition
Repository: lucene-solr
Updated Branches:
refs/heads/branch_7x cc2ee2305 -> 0934e2a99
refs/heads/master 0bf1eae92 -> 24c186eff
LUCENE-8273: Don't wrap MinHashFilter in a condition
MinHashFilter needs to consume the entire tokenstream, so wrapping it in a
randomized condition makes no sense, and breaks offsets.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/0934e2a9
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/0934e2a9
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/0934e2a9
Branch: refs/heads/branch_7x
Commit: 0934e2a998ac43e46594e049daab751d8cae2476
Parents: cc2ee23
Author: Alan Woodward <ro...@apache.org>
Authored: Tue May 22 09:08:23 2018 +0100
Committer: Alan Woodward <ro...@apache.org>
Committed: Tue May 22 09:09:34 2018 +0100
----------------------------------------------------------------------
.../test/org/apache/lucene/analysis/core/TestRandomChains.java | 3 +++
1 file changed, 3 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/0934e2a9/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
----------------------------------------------------------------------
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
index e393e5e..8cb1591 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
@@ -71,6 +71,7 @@ import org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.analysis.hunspell.Dictionary;
import org.apache.lucene.analysis.hunspell.TestHunspellStemFilter;
+import org.apache.lucene.analysis.minhash.MinHashFilter;
import org.apache.lucene.analysis.miscellaneous.ConditionalTokenFilter;
import org.apache.lucene.analysis.miscellaneous.DelimitedTermFrequencyTokenFilter;
import org.apache.lucene.analysis.miscellaneous.FingerprintFilter;
@@ -120,6 +121,8 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
static {
// Fingerprint filter needs to consume the whole tokenstream, so conditionals don't make sense here
avoidConditionals.add(FingerprintFilter.class);
+ // Ditto MinHashFilter
+ avoidConditionals.add(MinHashFilter.class);
}
private static final Map<Constructor<?>,Predicate<Object[]>> brokenConstructors = new HashMap<>();
[2/2] lucene-solr:master: LUCENE-8273: Don't wrap MinHashFilter in a
condition
Posted by ro...@apache.org.
LUCENE-8273: Don't wrap MinHashFilter in a condition
MinHashFilter needs to consume the entire tokenstream, so wrapping it in a
randomized condition makes no sense, and breaks offsets.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/24c186ef
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/24c186ef
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/24c186ef
Branch: refs/heads/master
Commit: 24c186eff9a9b2b2c0a86fc0a828bd81ba0993e8
Parents: 0bf1eae
Author: Alan Woodward <ro...@apache.org>
Authored: Tue May 22 09:08:23 2018 +0100
Committer: Alan Woodward <ro...@apache.org>
Committed: Tue May 22 09:09:36 2018 +0100
----------------------------------------------------------------------
.../test/org/apache/lucene/analysis/core/TestRandomChains.java | 3 +++
1 file changed, 3 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/24c186ef/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
----------------------------------------------------------------------
diff --git a/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java b/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
index e393e5e..8cb1591 100644
--- a/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
+++ b/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
@@ -71,6 +71,7 @@ import org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.analysis.hunspell.Dictionary;
import org.apache.lucene.analysis.hunspell.TestHunspellStemFilter;
+import org.apache.lucene.analysis.minhash.MinHashFilter;
import org.apache.lucene.analysis.miscellaneous.ConditionalTokenFilter;
import org.apache.lucene.analysis.miscellaneous.DelimitedTermFrequencyTokenFilter;
import org.apache.lucene.analysis.miscellaneous.FingerprintFilter;
@@ -120,6 +121,8 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
static {
// Fingerprint filter needs to consume the whole tokenstream, so conditionals don't make sense here
avoidConditionals.add(FingerprintFilter.class);
+ // Ditto MinHashFilter
+ avoidConditionals.add(MinHashFilter.class);
}
private static final Map<Constructor<?>,Predicate<Object[]>> brokenConstructors = new HashMap<>();