You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by to...@apache.org on 2019/08/11 05:34:58 UTC
[lucene-solr] branch master updated: LUCENE-8948: Change 'name'
argument in ICU factories to 'form'.
This is an automated email from the ASF dual-hosted git repository.
tomoko pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/lucene-solr.git
The following commit(s) were added to refs/heads/master by this push:
new 407ba89 LUCENE-8948: Change 'name' argument in ICU factories to 'form'.
407ba89 is described below
commit 407ba89aad028a37cf5ec0f131b8773d394177c2
Author: Tomoko Uchida <to...@apache.org>
AuthorDate: Sun Aug 11 14:33:31 2019 +0900
LUCENE-8948: Change 'name' argument in ICU factories to 'form'.
---
lucene/CHANGES.txt | 3 +++
.../analysis/icu/ICUNormalizer2CharFilterFactory.java | 6 +++---
.../lucene/analysis/icu/ICUNormalizer2FilterFactory.java | 6 +++---
.../analysis/icu/TestICUNormalizer2CharFilterFactory.java | 14 +++++++++++++-
.../analysis/icu/TestICUNormalizer2FilterFactory.java | 12 ++++++++++++
5 files changed, 34 insertions(+), 7 deletions(-)
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index a88988b..1db0da0 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -30,6 +30,9 @@ API Changes
* LUCENE-8909: The deprecated IndexWriter#getFieldNames() method has been removed.
(Adrien Grand, Munendra S N)
+* LUCENE-8948: Change "name" argument in ICU factories to "form". Here, "form" is
+ named after "Unicode Normalization Form". (Tomoko Uchida)
+
Improvements
* LUCENE-8757: When provided with an ExecutorService to run queries across
diff --git a/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2CharFilterFactory.java b/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2CharFilterFactory.java
index 8a4db89..fe73f5a 100644
--- a/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2CharFilterFactory.java
+++ b/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2CharFilterFactory.java
@@ -31,7 +31,7 @@ import org.apache.lucene.analysis.util.CharFilterFactory;
* <p>
* Supports the following attributes:
* <ul>
- * <li>name: A <a href="http://unicode.org/reports/tr15/">Unicode Normalization Form</a>,
+ * <li>form: A <a href="http://unicode.org/reports/tr15/">Unicode Normalization Form</a>,
* one of 'nfc','nfkc', 'nfkc_cf'. Default is nfkc_cf.
* <li>mode: Either 'compose' or 'decompose'. Default is compose. Use "decompose" with nfc
* or nfkc, to get nfd or nfkd, respectively.
@@ -55,10 +55,10 @@ public class ICUNormalizer2CharFilterFactory extends CharFilterFactory {
/** Creates a new ICUNormalizer2CharFilterFactory */
public ICUNormalizer2CharFilterFactory(Map<String,String> args) {
super(args);
- String name = get(args, "name", "nfkc_cf");
+ String form = get(args, "form", "nfkc_cf");
String mode = get(args, "mode", Arrays.asList("compose", "decompose"), "compose");
Normalizer2 normalizer = Normalizer2.getInstance
- (null, name, "compose".equals(mode) ? Normalizer2.Mode.COMPOSE : Normalizer2.Mode.DECOMPOSE);
+ (null, form, "compose".equals(mode) ? Normalizer2.Mode.COMPOSE : Normalizer2.Mode.DECOMPOSE);
String filter = get(args, "filter");
if (filter != null) {
diff --git a/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2FilterFactory.java b/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2FilterFactory.java
index d4e1ecd..e26de19 100644
--- a/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2FilterFactory.java
+++ b/lucene/analysis/icu/src/java/org/apache/lucene/analysis/icu/ICUNormalizer2FilterFactory.java
@@ -31,7 +31,7 @@ import org.apache.lucene.analysis.util.TokenFilterFactory;
* <p>
* Supports the following attributes:
* <ul>
- * <li>name: A <a href="http://unicode.org/reports/tr15/">Unicode Normalization Form</a>,
+ * <li>form: A <a href="http://unicode.org/reports/tr15/">Unicode Normalization Form</a>,
* one of 'nfc','nfkc', 'nfkc_cf'. Default is nfkc_cf.
* <li>mode: Either 'compose' or 'decompose'. Default is compose. Use "decompose" with nfc
* or nfkc, to get nfd or nfkd, respectively.
@@ -54,10 +54,10 @@ public class ICUNormalizer2FilterFactory extends TokenFilterFactory {
/** Creates a new ICUNormalizer2FilterFactory */
public ICUNormalizer2FilterFactory(Map<String,String> args) {
super(args);
- String name = get(args, "name", "nfkc_cf");
+ String form = get(args, "form", "nfkc_cf");
String mode = get(args, "mode", Arrays.asList("compose", "decompose"), "compose");
Normalizer2 normalizer = Normalizer2.getInstance
- (null, name, "compose".equals(mode) ? Normalizer2.Mode.COMPOSE : Normalizer2.Mode.DECOMPOSE);
+ (null, form, "compose".equals(mode) ? Normalizer2.Mode.COMPOSE : Normalizer2.Mode.DECOMPOSE);
String filter = get(args, "filter");
if (filter != null) {
diff --git a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilterFactory.java b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilterFactory.java
index 90055f1..a1e01ba 100644
--- a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilterFactory.java
+++ b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilterFactory.java
@@ -20,6 +20,7 @@ package org.apache.lucene.analysis.icu;
import java.io.Reader;
import java.io.StringReader;
import java.util.HashMap;
+import java.util.Map;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
@@ -35,7 +36,18 @@ public class TestICUNormalizer2CharFilterFactory extends BaseTokenStreamTestCase
TokenStream stream = whitespaceMockTokenizer(reader);
assertTokenStreamContents(stream, new String[] { "this", "is", "a", "test" });
}
-
+
+ /** Test nfkc form */
+ public void testFormArgument() throws Exception {
+ Reader reader = new StringReader("This is a Ｔｅｓｔ");
+ Map<String, String> args = new HashMap<>();
+ args.put("form", "nfkc");
+ ICUNormalizer2CharFilterFactory factory = new ICUNormalizer2CharFilterFactory(args);
+ reader = factory.create(reader);
+ TokenStream stream = whitespaceMockTokenizer(reader);
+ assertTokenStreamContents(stream, new String[] { "This", "is", "a", "Test" });
+ }
+
/** Test that bogus arguments result in exception */
public void testBogusArguments() throws Exception {
IllegalArgumentException expected = expectThrows(IllegalArgumentException.class, () -> {
diff --git a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2FilterFactory.java b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2FilterFactory.java
index 8e8de80..237afe5 100644
--- a/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2FilterFactory.java
+++ b/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2FilterFactory.java
@@ -20,6 +20,7 @@ package org.apache.lucene.analysis.icu;
import java.io.Reader;
import java.io.StringReader;
import java.util.HashMap;
+import java.util.Map;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
@@ -35,6 +36,17 @@ public class TestICUNormalizer2FilterFactory extends BaseTokenStreamTestCase {
stream = factory.create(stream);
assertTokenStreamContents(stream, new String[] { "this", "is", "a", "test" });
}
+
+ /** Test nfkc form */
+ public void testFormArgument() throws Exception {
+ Reader reader = new StringReader("This is a Ｔｅｓｔ");
+ Map<String, String> args = new HashMap<>();
+ args.put("form", "nfkc");
+ ICUNormalizer2FilterFactory factory = new ICUNormalizer2FilterFactory(args);
+ TokenStream stream = whitespaceMockTokenizer(reader);
+ stream = factory.create(stream);
+ assertTokenStreamContents(stream, new String[] { "This", "is", "a", "Test" });
+ }
/** Test that bogus arguments result in exception */
public void testBogusArguments() throws Exception {