honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

analyzers: custom analyzers names and aliases must not start with _ 

closes #9596
This commit is contained in:
Britta Weber 2015-05-22 16:59:56 +02:00
parent e97353e84a
commit 37782c1745
3 changed files with 40 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/reference/analysis/analyzers/custom-analyzer.asciidoc
View File

@ -5,6 +5,7 @@ An analyzer of type `custom` that allows to combine a `Tokenizer` with
zero or more `Token Filters`, and zero or more `Char Filters`. The
custom analyzer accepts a logical/registered name of the tokenizer to
use, and a list of logical/registered names of token filters.
The name of the custom analyzer must not start mit "_".
The following are settings that can be set for a `custom` analyzer type:

5
src/main/java/org/elasticsearch/index/analysis/AnalysisService.java
View File

@ -251,6 +251,11 @@ public class AnalysisService extends AbstractIndexComponent implements Closeable
defaultSearchAnalyzer = analyzers.containsKey("default_search") ? analyzers.get("default_search") : analyzers.get("default");
defaultSearchQuoteAnalyzer = analyzers.containsKey("default_search_quote") ? analyzers.get("default_search_quote") : defaultSearchAnalyzer;
for (Map.Entry<String, NamedAnalyzer> analyzer : analyzers.entrySet()) {
if (analyzer.getKey().startsWith("_")) {
throw new IllegalArgumentException("analyzer name must not start with _. got \"" + analyzer.getKey() + "\"");
}
}
this.analyzers = ImmutableMap.copyOf(analyzers);
}

35
src/test/java/org/elasticsearch/index/analysis/AnalysisModuleTests.java
View File

@ -31,6 +31,7 @@ import org.elasticsearch.Version;
import org.elasticsearch.cluster.metadata.IndexMetaData;
import org.elasticsearch.common.inject.Injector;
import org.elasticsearch.common.inject.ModulesBuilder;
import org.elasticsearch.common.inject.ProvisionException;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.settings.SettingsModule;
import org.elasticsearch.env.Environment;
@ -94,7 +95,7 @@ public class AnalysisModuleTests extends ElasticsearchTestCase {
Settings settings = loadFromClasspath("org/elasticsearch/index/analysis/test1.yml");
testSimpleConfiguration(settings);
}
@Test
public void testDefaultFactoryTokenFilters() throws IOException {
assertTokenFilter("keyword_repeat", KeywordRepeatFilter.class);
@ -238,4 +239,36 @@ public class AnalysisModuleTests extends ElasticsearchTestCase {
return wordListFile;
}
@Test
public void testUnderscoreInAnalyzerName() {
Settings settings = Settings.builder()
.put("index.analysis.analyzer._invalid_name.tokenizer", "keyword")
.put("path.home", createTempDir().toString())
.put(IndexMetaData.SETTING_VERSION_CREATED, "1")
.build();
try {
getAnalysisService(settings);
fail("This should fail with IllegalArgumentException because the analyzers name starts with _");
} catch (ProvisionException e) {
assertTrue(e.getCause() instanceof IllegalArgumentException);
assertThat(e.getCause().getMessage(), equalTo("analyzer name must not start with _. got \"_invalid_name\""));
}
}
@Test
public void testUnderscoreInAnalyzerNameAlias() {
Settings settings = Settings.builder()
.put("index.analysis.analyzer.valid_name.tokenizer", "keyword")
.put("index.analysis.analyzer.valid_name.alias", "_invalid_name")
.put("path.home", createTempDir().toString())
.put(IndexMetaData.SETTING_VERSION_CREATED, "1")
.build();
try {
getAnalysisService(settings);
fail("This should fail with IllegalArgumentException because the analyzers alias starts with _");
} catch (ProvisionException e) {
assertTrue(e.getCause() instanceof IllegalArgumentException);
assertThat(e.getCause().getMessage(), equalTo("analyzer name must not start with _. got \"_invalid_name\""));
}
}
}