Move more token filters to analysis-common module

The following token filters were moved: arabic_stem, brazilian_stem, czech_stem, dutch_stem, french_stem, german_stem and russian_stem. Relates to #23658
2025-03-27 18:38:41 +00:00 · 2017-08-03 15:00:56 +02:00 · 2017-08-03 15:00:56 +02:00 · 1146a35870
commit 1146a35870
parent 7e3cd6a019
15 changed files with 256 additions and 51 deletions
--- a/core/src/main/java/org/elasticsearch/indices/analysis/AnalysisModule.java
+++ b/core/src/main/java/org/elasticsearch/indices/analysis/AnalysisModule.java
@ -30,11 +30,9 @@ import org.elasticsearch.index.IndexSettings;
 import org.elasticsearch.index.analysis.AnalysisRegistry;
 import org.elasticsearch.index.analysis.AnalyzerProvider;
 import org.elasticsearch.index.analysis.ArabicAnalyzerProvider;
-import org.elasticsearch.index.analysis.ArabicStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.ArmenianAnalyzerProvider;
 import org.elasticsearch.index.analysis.BasqueAnalyzerProvider;
 import org.elasticsearch.index.analysis.BrazilianAnalyzerProvider;
-import org.elasticsearch.index.analysis.BrazilianStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.BulgarianAnalyzerProvider;
 import org.elasticsearch.index.analysis.CatalanAnalyzerProvider;
 import org.elasticsearch.index.analysis.CharFilterFactory;
@ -42,19 +40,15 @@ import org.elasticsearch.index.analysis.ChineseAnalyzerProvider;
 import org.elasticsearch.index.analysis.CjkAnalyzerProvider;
 import org.elasticsearch.index.analysis.ClassicTokenizerFactory;
 import org.elasticsearch.index.analysis.CzechAnalyzerProvider;
-import org.elasticsearch.index.analysis.CzechStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.DanishAnalyzerProvider;
 import org.elasticsearch.index.analysis.DutchAnalyzerProvider;
-import org.elasticsearch.index.analysis.DutchStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.EdgeNGramTokenizerFactory;
 import org.elasticsearch.index.analysis.EnglishAnalyzerProvider;
 import org.elasticsearch.index.analysis.FingerprintAnalyzerProvider;
 import org.elasticsearch.index.analysis.FinnishAnalyzerProvider;
 import org.elasticsearch.index.analysis.FrenchAnalyzerProvider;
-import org.elasticsearch.index.analysis.FrenchStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.GalicianAnalyzerProvider;
 import org.elasticsearch.index.analysis.GermanAnalyzerProvider;
-import org.elasticsearch.index.analysis.GermanStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.GreekAnalyzerProvider;
 import org.elasticsearch.index.analysis.HindiAnalyzerProvider;
 import org.elasticsearch.index.analysis.HungarianAnalyzerProvider;
@ -80,7 +74,6 @@ import org.elasticsearch.index.analysis.PreConfiguredTokenFilter;
 import org.elasticsearch.index.analysis.PreConfiguredTokenizer;
 import org.elasticsearch.index.analysis.RomanianAnalyzerProvider;
 import org.elasticsearch.index.analysis.RussianAnalyzerProvider;
-import org.elasticsearch.index.analysis.RussianStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.ShingleTokenFilterFactory;
 import org.elasticsearch.index.analysis.SimpleAnalyzerProvider;
 import org.elasticsearch.index.analysis.SnowballAnalyzerProvider;
@ -172,14 +165,6 @@ public final class AnalysisModule {
        tokenFilters.register("stop", StopTokenFilterFactory::new);
        tokenFilters.register("standard", StandardTokenFilterFactory::new);
        tokenFilters.register("shingle", ShingleTokenFilterFactory::new);
-        tokenFilters.register("arabic_stem", ArabicStemTokenFilterFactory::new);
-        tokenFilters.register("brazilian_stem", BrazilianStemTokenFilterFactory::new);
-        tokenFilters.register("czech_stem", CzechStemTokenFilterFactory::new);
-        tokenFilters.register("dutch_stem", DutchStemTokenFilterFactory::new);
-        tokenFilters.register("french_stem", FrenchStemTokenFilterFactory::new);
-        tokenFilters.register("german_stem", GermanStemTokenFilterFactory::new);
-        tokenFilters.register("russian_stem", RussianStemTokenFilterFactory::new);
-
        tokenFilters.register("hunspell", requriesAnalysisSettings((indexSettings, env, name, settings) -> new HunspellTokenFilterFactory
            (indexSettings, name, settings, hunspellService)));

--- a/core/src/test/java/org/elasticsearch/indices/analysis/AnalysisModuleTests.java
+++ b/core/src/test/java/org/elasticsearch/indices/analysis/AnalysisModuleTests.java
@ -188,14 +188,6 @@ public class AnalysisModuleTests extends ESTestCase {
        assertThat(analyzer, instanceOf(CustomAnalyzer.class));
        CustomAnalyzer custom4 = (CustomAnalyzer) analyzer;
        assertThat(custom4.tokenFilters()[0], instanceOf(MyFilterTokenFilterFactory.class));
-
-//        // verify Czech stemmer
-//        analyzer = analysisService.analyzer("czechAnalyzerWithStemmer").analyzer();
-//        assertThat(analyzer, instanceOf(CustomAnalyzer.class));
-//        CustomAnalyzer czechstemmeranalyzer = (CustomAnalyzer) analyzer;
-//        assertThat(czechstemmeranalyzer.tokenizerFactory(), instanceOf(StandardTokenizerFactory.class));
-//        assertThat(czechstemmeranalyzer.tokenFilters().length, equalTo(4));
-//        assertThat(czechstemmeranalyzer.tokenFilters()[3], instanceOf(CzechStemTokenFilterFactory.class));
    }

    public void testWordListPath() throws Exception {
--- a/core/src/test/resources/org/elasticsearch/index/analysis/test1.json
+++ b/core/src/test/resources/org/elasticsearch/index/analysis/test1.json
@ -35,10 +35,6 @@
                "custom6":{
                    "tokenizer":"standard",
                    "position_increment_gap": 256
-                },
-                "czechAnalyzerWithStemmer":{
-                    "tokenizer":"standard",
-                    "filter":["standard", "lowercase", "stop", "czech_stem"]
                }
            }
        }
--- a/core/src/test/resources/org/elasticsearch/index/analysis/test1.yml
+++ b/core/src/test/resources/org/elasticsearch/index/analysis/test1.yml
@ -28,6 +28,3 @@ index :
      custom7 :
        type : standard
        version: 3.6
-      czechAnalyzerWithStemmer :
-        tokenizer : standard
-        filter : [standard, lowercase, stop, czech_stem]
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ArabicStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/ArabicStemTokenFilterFactory.java
@ -17,17 +17,18 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.ar.ArabicStemFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;

 public class ArabicStemTokenFilterFactory extends AbstractTokenFilterFactory {

-    public ArabicStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    ArabicStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
    }

--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BrazilianStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/BrazilianStemTokenFilterFactory.java
@ -17,7 +17,7 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.br.BrazilianStemFilter;
@ -26,12 +26,14 @@ import org.apache.lucene.analysis.CharArraySet;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+import org.elasticsearch.index.analysis.Analysis;

 public class BrazilianStemTokenFilterFactory extends AbstractTokenFilterFactory {

    private final CharArraySet exclusions;

-    public BrazilianStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    BrazilianStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
        this.exclusions = Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET);
    }
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CommonAnalysisPlugin.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CommonAnalysisPlugin.java
@ -92,20 +92,26 @@ public class CommonAnalysisPlugin extends Plugin implements AnalysisPlugin {
        Map<String, AnalysisProvider<TokenFilterFactory>> filters = new TreeMap<>();
        filters.put("apostrophe", ApostropheFilterFactory::new);
        filters.put("arabic_normalization", ArabicNormalizationFilterFactory::new);
+        filters.put("arabic_stem", ArabicStemTokenFilterFactory::new);
        filters.put("asciifolding", ASCIIFoldingTokenFilterFactory::new);
+        filters.put("brazilian_stem", BrazilianStemTokenFilterFactory::new);
        filters.put("cjk_bigram", CJKBigramFilterFactory::new);
        filters.put("cjk_width", CJKWidthFilterFactory::new);
        filters.put("classic", ClassicFilterFactory::new);
+        filters.put("czech_stem", CzechStemTokenFilterFactory::new);
        filters.put("common_grams", requriesAnalysisSettings(CommonGramsTokenFilterFactory::new));
        filters.put("decimal_digit", DecimalDigitFilterFactory::new);
        filters.put("delimited_payload_filter", DelimitedPayloadTokenFilterFactory::new);
        filters.put("dictionary_decompounder", requriesAnalysisSettings(DictionaryCompoundWordTokenFilterFactory::new));
+        filters.put("dutch_stem", DutchStemTokenFilterFactory::new);
        filters.put("edge_ngram", EdgeNGramTokenFilterFactory::new);
        filters.put("edgeNGram", EdgeNGramTokenFilterFactory::new);
        filters.put("elision", ElisionTokenFilterFactory::new);
        filters.put("fingerprint", FingerprintTokenFilterFactory::new);
        filters.put("flatten_graph", FlattenGraphTokenFilterFactory::new);
+        filters.put("french_stem", FrenchStemTokenFilterFactory::new);
        filters.put("german_normalization", GermanNormalizationFilterFactory::new);
+        filters.put("german_stem", GermanStemTokenFilterFactory::new);
        filters.put("hindi_normalization", HindiNormalizationFilterFactory::new);
        filters.put("hyphenation_decompounder", requriesAnalysisSettings(HyphenationCompoundWordTokenFilterFactory::new));
        filters.put("indic_normalization", IndicNormalizationFilterFactory::new);
@ -124,6 +130,7 @@ public class CommonAnalysisPlugin extends Plugin implements AnalysisPlugin {
        filters.put("persian_normalization", PersianNormalizationFilterFactory::new);
        filters.put("porter_stem", PorterStemTokenFilterFactory::new);
        filters.put("reverse", ReverseTokenFilterFactory::new);
+        filters.put("russian_stem", RussianStemTokenFilterFactory::new);
        filters.put("scandinavian_folding", ScandinavianFoldingFilterFactory::new);
        filters.put("scandinavian_normalization", ScandinavianNormalizationFilterFactory::new);
        filters.put("serbian_normalization", SerbianNormalizationFilterFactory::new);
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CzechStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CzechStemTokenFilterFactory.java
@ -16,17 +16,18 @@
 * specific language governing permissions and limitations
 * under the License.
 */
-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.cz.CzechStemFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;

 public class CzechStemTokenFilterFactory extends AbstractTokenFilterFactory {

-    public CzechStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    CzechStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
    }

--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/DutchStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/DutchStemTokenFilterFactory.java
@ -17,7 +17,7 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.analysis.TokenStream;
@ -26,13 +26,15 @@ import org.apache.lucene.analysis.snowball.SnowballFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+import org.elasticsearch.index.analysis.Analysis;
 import org.tartarus.snowball.ext.DutchStemmer;

 public class DutchStemTokenFilterFactory extends AbstractTokenFilterFactory {

    private final CharArraySet exclusions;

-    public DutchStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    DutchStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
        this.exclusions = Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET);
    }
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/FrenchStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/FrenchStemTokenFilterFactory.java
@ -17,7 +17,7 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.analysis.TokenStream;
@ -26,13 +26,15 @@ import org.apache.lucene.analysis.snowball.SnowballFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+import org.elasticsearch.index.analysis.Analysis;
 import org.tartarus.snowball.ext.FrenchStemmer;

 public class FrenchStemTokenFilterFactory extends AbstractTokenFilterFactory {

    private final CharArraySet exclusions;

-    public FrenchStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    FrenchStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
        this.exclusions = Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET);
    }
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/GermanStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/GermanStemTokenFilterFactory.java
@ -17,7 +17,7 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.CharArraySet;
 import org.apache.lucene.analysis.TokenStream;
@ -26,12 +26,14 @@ import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+import org.elasticsearch.index.analysis.Analysis;

 public class GermanStemTokenFilterFactory extends AbstractTokenFilterFactory {

    private final CharArraySet exclusions;

-    public GermanStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+    GermanStemTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
        super(indexSettings, name, settings);
        this.exclusions = Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET);
    }
--- a/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/RussianStemTokenFilterFactory.java
+++ b/modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/RussianStemTokenFilterFactory.java
@ -17,13 +17,14 @@
 * under the License.
 */

-package org.elasticsearch.index.analysis;
+package org.elasticsearch.analysis.common;

 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.snowball.SnowballFilter;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;

 public class RussianStemTokenFilterFactory extends AbstractTokenFilterFactory {

--- a/modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/CommonAnalysisFactoryTests.java
+++ b/modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/CommonAnalysisFactoryTests.java
@ -124,6 +124,10 @@ public class CommonAnalysisFactoryTests extends AnalysisFactoryTestCase {
        filters.put("fingerprint", FingerprintTokenFilterFactory.class);
        filters.put("minhash", MinHashTokenFilterFactory.class);
        filters.put("scandinavianfolding", ScandinavianFoldingFilterFactory.class);
+        filters.put("arabicstem", ArabicStemTokenFilterFactory.class);
+        filters.put("brazilianstem", BrazilianStemTokenFilterFactory.class);
+        filters.put("czechstem", CzechStemTokenFilterFactory.class);
+        filters.put("germanstem", GermanStemTokenFilterFactory.class);
        return filters;
    }

--- a/modules/analysis-common/src/test/resources/rest-api-spec/test/analysis-common/40_token_filters.yml
+++ b/modules/analysis-common/src/test/resources/rest-api-spec/test/analysis-common/40_token_filters.yml
@ -1258,3 +1258,220 @@
            filter:    [scandinavian_folding]
    - length: { tokens: 1 }
    - match:  { tokens.0.token: raksmorgas }
+
+---
+"arabic_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_arabic_stem:
+                    type: arabic_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: الحسن
+            tokenizer: keyword
+            filter:    [my_arabic_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: حسن }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: الحسن
+            tokenizer: keyword
+            filter:    [arabic_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: حسن }
+
+---
+"brazilian_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_brazilian_stem:
+                    type: brazilian_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: Brasília
+            tokenizer: keyword
+            filter:    [my_brazilian_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: brasil }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: Brasília
+            tokenizer: keyword
+            filter:    [brazilian_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: brasil }
+
+---
+"czech_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_czech_stem:
+                    type: czech_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: angličtí
+            tokenizer: keyword
+            filter:    [my_czech_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: anglick }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: angličtí
+            tokenizer: keyword
+            filter:    [czech_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: anglick }
+
+---
+"dutch_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_dutch_stem:
+                    type: dutch_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: ophouden
+            tokenizer: keyword
+            filter:    [my_dutch_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: ophoud }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: ophouden
+            tokenizer: keyword
+            filter:    [dutch_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: ophoud }
+
+---
+"french_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_french_stem:
+                    type: french_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: chevaux
+            tokenizer: keyword
+            filter:    [my_french_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: cheval }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: chevaux
+            tokenizer: keyword
+            filter:    [french_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: cheval }
+
+---
+"german_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_german_stem:
+                    type: german_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: abschließen
+            tokenizer: keyword
+            filter:    [my_german_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: abschliess }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: abschließen
+            tokenizer: keyword
+            filter:    [german_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: abschliess }
+
+---
+"russian_stem":
+    - do:
+        indices.create:
+          index: test
+          body:
+            settings:
+              analysis:
+                filter:
+                  my_russian_stem:
+                    type: russian_stem
+    - do:
+        indices.analyze:
+          index: test
+          body:
+            text: журналы
+            tokenizer: keyword
+            filter:    [my_russian_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: журнал }
+
+    # Test pre-configured token filter too:
+    - do:
+        indices.analyze:
+          body:
+            text: журналы
+            tokenizer: keyword
+            filter:    [russian_stem]
+    - length: { tokens: 1 }
+    - match:  { tokens.0.token: журнал }
--- a/test/framework/src/main/java/org/elasticsearch/indices/analysis/AnalysisFactoryTestCase.java
+++ b/test/framework/src/main/java/org/elasticsearch/indices/analysis/AnalysisFactoryTestCase.java
@ -23,12 +23,8 @@ import org.apache.lucene.analysis.util.CharFilterFactory;
 import org.apache.lucene.analysis.util.TokenFilterFactory;
 import org.apache.lucene.analysis.util.TokenizerFactory;
 import org.elasticsearch.common.collect.MapBuilder;
-import org.elasticsearch.index.analysis.ArabicStemTokenFilterFactory;
-import org.elasticsearch.index.analysis.BrazilianStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.ClassicTokenizerFactory;
-import org.elasticsearch.index.analysis.CzechStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.EdgeNGramTokenizerFactory;
-import org.elasticsearch.index.analysis.GermanStemTokenFilterFactory;
 import org.elasticsearch.index.analysis.HunspellTokenFilterFactory;
 import org.elasticsearch.index.analysis.KeywordTokenizerFactory;
 import org.elasticsearch.index.analysis.LetterTokenizerFactory;
@ -114,16 +110,16 @@ public abstract class AnalysisFactoryTestCase extends ESTestCase {
        // exposed in ES
        .put("apostrophe",                MovedToAnalysisCommon.class)
        .put("arabicnormalization",       MovedToAnalysisCommon.class)
-        .put("arabicstem",                ArabicStemTokenFilterFactory.class)
+        .put("arabicstem",                MovedToAnalysisCommon.class)
        .put("asciifolding",              MovedToAnalysisCommon.class)
-        .put("brazilianstem",             BrazilianStemTokenFilterFactory.class)
+        .put("brazilianstem",             MovedToAnalysisCommon.class)
        .put("bulgarianstem",             MovedToAnalysisCommon.class)
        .put("cjkbigram",                 MovedToAnalysisCommon.class)
        .put("cjkwidth",                  MovedToAnalysisCommon.class)
        .put("classic",                   MovedToAnalysisCommon.class)
        .put("commongrams",               MovedToAnalysisCommon.class)
        .put("commongramsquery",          MovedToAnalysisCommon.class)
-        .put("czechstem",                 CzechStemTokenFilterFactory.class)
+        .put("czechstem",                 MovedToAnalysisCommon.class)
        .put("decimaldigit",              MovedToAnalysisCommon.class)
        .put("delimitedpayload",          MovedToAnalysisCommon.class)
        .put("dictionarycompoundword",    MovedToAnalysisCommon.class)
@ -136,7 +132,7 @@ public abstract class AnalysisFactoryTestCase extends ESTestCase {
        .put("frenchminimalstem",         MovedToAnalysisCommon.class)
        .put("galicianminimalstem",       MovedToAnalysisCommon.class)
        .put("galicianstem",              MovedToAnalysisCommon.class)
-        .put("germanstem",                GermanStemTokenFilterFactory.class)
+        .put("germanstem",                MovedToAnalysisCommon.class)
        .put("germanlightstem",           MovedToAnalysisCommon.class)
        .put("germanminimalstem",         MovedToAnalysisCommon.class)
        .put("germannormalization",       MovedToAnalysisCommon.class)