Added support for char filters in the analyze API

Closes #5148
This commit is contained in:
Brusic 2014-02-17 20:25:12 -08:00 committed by Luca Cavanna
parent f4c0c3dae6
commit 95274c18c5
6 changed files with 116 additions and 21 deletions

View File

@ -12,12 +12,16 @@ analyzers:
curl -XGET 'localhost:9200/_analyze?analyzer=standard' -d 'this is a test' curl -XGET 'localhost:9200/_analyze?analyzer=standard' -d 'this is a test'
-------------------------------------------------- --------------------------------------------------
Or by building a custom transient analyzer out of tokenizers and Or by building a custom transient analyzer out of tokenizers,
filters: token filters and char filters. Token filters can use the shorter 'filters'
parameter name:
[source,js] [source,js]
-------------------------------------------------- --------------------------------------------------
curl -XGET 'localhost:9200/_analyze?tokenizer=keyword&filters=lowercase' -d 'this is a test' curl -XGET 'localhost:9200/_analyze?tokenizer=keyword&filters=lowercase' -d 'this is a test'
curl -XGET 'localhost:9200/_analyze?tokenizer=keyword&token_filters=lowercase&char_filters=html_strip' -d 'this is a <b>test</b>'
-------------------------------------------------- --------------------------------------------------
It can also run against a specific index: It can also run against a specific index:

View File

@ -18,9 +18,11 @@
*/ */
package org.elasticsearch.action.admin.indices.analyze; package org.elasticsearch.action.admin.indices.analyze;
import org.elasticsearch.Version;
import org.elasticsearch.action.ActionRequestValidationException; import org.elasticsearch.action.ActionRequestValidationException;
import org.elasticsearch.action.support.single.custom.SingleCustomOperationRequest; import org.elasticsearch.action.support.single.custom.SingleCustomOperationRequest;
import org.elasticsearch.common.Nullable; import org.elasticsearch.common.Nullable;
import org.elasticsearch.common.Strings;
import org.elasticsearch.common.io.stream.StreamInput; import org.elasticsearch.common.io.stream.StreamInput;
import org.elasticsearch.common.io.stream.StreamOutput; import org.elasticsearch.common.io.stream.StreamOutput;
@ -42,7 +44,9 @@ public class AnalyzeRequest extends SingleCustomOperationRequest<AnalyzeRequest>
private String tokenizer; private String tokenizer;
private String[] tokenFilters; private String[] tokenFilters = Strings.EMPTY_ARRAY;
private String[] charFilters = Strings.EMPTY_ARRAY;
private String field; private String field;
@ -110,6 +114,15 @@ public class AnalyzeRequest extends SingleCustomOperationRequest<AnalyzeRequest>
return this.tokenFilters; return this.tokenFilters;
} }
public AnalyzeRequest charFilters(String... charFilters) {
this.charFilters = charFilters;
return this;
}
public String[] charFilters() {
return this.charFilters;
}
public AnalyzeRequest field(String field) { public AnalyzeRequest field(String field) {
this.field = field; this.field = field;
return this; return this;
@ -125,6 +138,12 @@ public class AnalyzeRequest extends SingleCustomOperationRequest<AnalyzeRequest>
if (text == null) { if (text == null) {
validationException = addValidationError("text is missing", validationException); validationException = addValidationError("text is missing", validationException);
} }
if (tokenFilters == null) {
validationException = addValidationError("token filters must not be null", validationException);
}
if (charFilters == null) {
validationException = addValidationError("char filters must not be null", validationException);
}
return validationException; return validationException;
} }
@ -135,12 +154,9 @@ public class AnalyzeRequest extends SingleCustomOperationRequest<AnalyzeRequest>
text = in.readString(); text = in.readString();
analyzer = in.readOptionalString(); analyzer = in.readOptionalString();
tokenizer = in.readOptionalString(); tokenizer = in.readOptionalString();
int size = in.readVInt(); tokenFilters = in.readStringArray();
if (size > 0) { if (in.getVersion().onOrAfter(Version.V_1_1_0)) {
tokenFilters = new String[size]; charFilters = in.readStringArray();
for (int i = 0; i < size; i++) {
tokenFilters[i] = in.readString();
}
} }
field = in.readOptionalString(); field = in.readOptionalString();
} }
@ -152,13 +168,9 @@ public class AnalyzeRequest extends SingleCustomOperationRequest<AnalyzeRequest>
out.writeString(text); out.writeString(text);
out.writeOptionalString(analyzer); out.writeOptionalString(analyzer);
out.writeOptionalString(tokenizer); out.writeOptionalString(tokenizer);
if (tokenFilters == null) { out.writeStringArray(tokenFilters);
out.writeVInt(0); if (out.getVersion().onOrAfter(Version.V_1_1_0)) {
} else { out.writeStringArray(charFilters);
out.writeVInt(tokenFilters.length);
for (String tokenFilter : tokenFilters) {
out.writeString(tokenFilter);
}
} }
out.writeOptionalString(field); out.writeOptionalString(field);
} }

View File

@ -81,6 +81,14 @@ public class AnalyzeRequestBuilder extends SingleCustomOperationRequestBuilder<A
return this; return this;
} }
/**
* Sets char filters that will be used before the tokenizer.
*/
public AnalyzeRequestBuilder setCharFilters(String... charFilters) {
request.charFilters(charFilters);
return this;
}
@Override @Override
protected void doExecute(ActionListener<AnalyzeResponse> listener) { protected void doExecute(ActionListener<AnalyzeResponse> listener) {
((IndicesAdminClient) client).analyze(request, listener); ((IndicesAdminClient) client).analyze(request, listener);

View File

@ -162,6 +162,7 @@ public class TransportAnalyzeAction extends TransportSingleCustomOperationAction
throw new ElasticsearchIllegalArgumentException("failed to find tokenizer under [" + request.tokenizer() + "]"); throw new ElasticsearchIllegalArgumentException("failed to find tokenizer under [" + request.tokenizer() + "]");
} }
} }
TokenFilterFactory[] tokenFilterFactories = new TokenFilterFactory[0]; TokenFilterFactory[] tokenFilterFactories = new TokenFilterFactory[0];
if (request.tokenFilters() != null && request.tokenFilters().length > 0) { if (request.tokenFilters() != null && request.tokenFilters().length > 0) {
tokenFilterFactories = new TokenFilterFactory[request.tokenFilters().length]; tokenFilterFactories = new TokenFilterFactory[request.tokenFilters().length];
@ -170,21 +171,45 @@ public class TransportAnalyzeAction extends TransportSingleCustomOperationAction
if (indexService == null) { if (indexService == null) {
TokenFilterFactoryFactory tokenFilterFactoryFactory = indicesAnalysisService.tokenFilterFactoryFactory(tokenFilterName); TokenFilterFactoryFactory tokenFilterFactoryFactory = indicesAnalysisService.tokenFilterFactoryFactory(tokenFilterName);
if (tokenFilterFactoryFactory == null) { if (tokenFilterFactoryFactory == null) {
throw new ElasticsearchIllegalArgumentException("failed to find global token filter under [" + request.tokenizer() + "]"); throw new ElasticsearchIllegalArgumentException("failed to find global token filter under [" + tokenFilterName + "]");
} }
tokenFilterFactories[i] = tokenFilterFactoryFactory.create(tokenFilterName, ImmutableSettings.Builder.EMPTY_SETTINGS); tokenFilterFactories[i] = tokenFilterFactoryFactory.create(tokenFilterName, ImmutableSettings.Builder.EMPTY_SETTINGS);
} else { } else {
tokenFilterFactories[i] = indexService.analysisService().tokenFilter(tokenFilterName); tokenFilterFactories[i] = indexService.analysisService().tokenFilter(tokenFilterName);
if (tokenFilterFactories[i] == null) { if (tokenFilterFactories[i] == null) {
throw new ElasticsearchIllegalArgumentException("failed to find token filter under [" + request.tokenizer() + "]"); throw new ElasticsearchIllegalArgumentException("failed to find token filter under [" + tokenFilterName + "]");
} }
} }
if (tokenFilterFactories[i] == null) { if (tokenFilterFactories[i] == null) {
throw new ElasticsearchIllegalArgumentException("failed to find token filter under [" + request.tokenizer() + "]"); throw new ElasticsearchIllegalArgumentException("failed to find token filter under [" + tokenFilterName + "]");
} }
} }
} }
analyzer = new CustomAnalyzer(tokenizerFactory, new CharFilterFactory[0], tokenFilterFactories);
CharFilterFactory[] charFilterFactories = new CharFilterFactory[0];
if (request.charFilters() != null && request.charFilters().length > 0) {
charFilterFactories = new CharFilterFactory[request.charFilters().length];
for (int i = 0; i < request.charFilters().length; i++) {
String charFilterName = request.charFilters()[i];
if (indexService == null) {
CharFilterFactoryFactory charFilterFactoryFactory = indicesAnalysisService.charFilterFactoryFactory(charFilterName);
if (charFilterFactoryFactory == null) {
throw new ElasticsearchIllegalArgumentException("failed to find global char filter under [" + charFilterName + "]");
}
charFilterFactories[i] = charFilterFactoryFactory.create(charFilterName, ImmutableSettings.Builder.EMPTY_SETTINGS);
} else {
charFilterFactories[i] = indexService.analysisService().charFilter(charFilterName);
if (charFilterFactories[i] == null) {
throw new ElasticsearchIllegalArgumentException("failed to find token char under [" + charFilterName + "]");
}
}
if (charFilterFactories[i] == null) {
throw new ElasticsearchIllegalArgumentException("failed to find token char under [" + charFilterName + "]");
}
}
}
analyzer = new CustomAnalyzer(tokenizerFactory, charFilterFactories, tokenFilterFactories);
closeAnalyzer = true; closeAnalyzer = true;
} else if (analyzer == null) { } else if (analyzer == null) {
if (indexService == null) { if (indexService == null) {

View File

@ -70,7 +70,8 @@ public class RestAnalyzeAction extends BaseRestHandler {
analyzeRequest.analyzer(request.param("analyzer")); analyzeRequest.analyzer(request.param("analyzer"));
analyzeRequest.field(request.param("field")); analyzeRequest.field(request.param("field"));
analyzeRequest.tokenizer(request.param("tokenizer")); analyzeRequest.tokenizer(request.param("tokenizer"));
analyzeRequest.tokenFilters(request.paramAsStringArray("token_filters", request.paramAsStringArray("filters", null))); analyzeRequest.tokenFilters(request.paramAsStringArray("token_filters", request.paramAsStringArray("filters", analyzeRequest.tokenFilters())));
analyzeRequest.charFilters(request.paramAsStringArray("char_filters", analyzeRequest.charFilters()));
client.admin().indices().analyze(analyzeRequest, new ActionListener<AnalyzeResponse>() { client.admin().indices().analyze(analyzeRequest, new ActionListener<AnalyzeResponse>() {
@Override @Override
public void onResponse(AnalyzeResponse response) { public void onResponse(AnalyzeResponse response) {

View File

@ -29,6 +29,8 @@ import org.junit.Test;
import java.io.IOException; import java.io.IOException;
import static org.elasticsearch.common.settings.ImmutableSettings.settingsBuilder;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
import static org.hamcrest.Matchers.equalTo; import static org.hamcrest.Matchers.equalTo;
/** /**
@ -106,6 +108,49 @@ public class AnalyzeActionTests extends ElasticsearchIntegrationTest {
analyzeResponse = client().admin().indices().prepareAnalyze("THIS IS A TEST").setTokenizer("keyword").setTokenFilters("lowercase").execute().actionGet(); analyzeResponse = client().admin().indices().prepareAnalyze("THIS IS A TEST").setTokenizer("keyword").setTokenFilters("lowercase").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(1)); assertThat(analyzeResponse.getTokens().size(), equalTo(1));
assertThat(analyzeResponse.getTokens().get(0).getTerm(), equalTo("this is a test")); assertThat(analyzeResponse.getTokens().get(0).getTerm(), equalTo("this is a test"));
analyzeResponse = client().admin().indices().prepareAnalyze("THIS IS A TEST").setTokenizer("standard").setTokenFilters("lowercase", "reverse").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(4));
AnalyzeResponse.AnalyzeToken token = analyzeResponse.getTokens().get(0);
assertThat(token.getTerm(), equalTo("siht"));
token = analyzeResponse.getTokens().get(1);
assertThat(token.getTerm(), equalTo("si"));
token = analyzeResponse.getTokens().get(2);
assertThat(token.getTerm(), equalTo("a"));
token = analyzeResponse.getTokens().get(3);
assertThat(token.getTerm(), equalTo("tset"));
}
@Test
public void analyzeWithCharFilters() throws Exception {
assertAcked(prepareCreate("test").setSettings(settingsBuilder()
.put(indexSettings())
.put("index.analysis.char_filter.custom_mapping.type", "mapping")
.putArray("index.analysis.char_filter.custom_mapping.mappings", "ph=>f", "qu=>q")
.put("index.analysis.analyzer.custom_with_char_filter.tokenizer", "standard")
.putArray("index.analysis.analyzer.custom_with_char_filter.char_filter", "custom_mapping")));
ensureGreen();
AnalyzeResponse analyzeResponse = client().admin().indices().prepareAnalyze("<h2><b>THIS</b> IS A</h2> <a href=\"#\">TEST</a>").setTokenizer("standard").setCharFilters("html_strip").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(4));
analyzeResponse = client().admin().indices().prepareAnalyze("THIS IS A <b>TEST</b>").setTokenizer("keyword").setTokenFilters("lowercase").setCharFilters("html_strip").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(1));
assertThat(analyzeResponse.getTokens().get(0).getTerm(), equalTo("this is a test"));
analyzeResponse = client().admin().indices().prepareAnalyze("test", "jeff quit phish").setTokenizer("keyword").setTokenFilters("lowercase").setCharFilters("custom_mapping").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(1));
assertThat(analyzeResponse.getTokens().get(0).getTerm(), equalTo("jeff qit fish"));
analyzeResponse = client().admin().indices().prepareAnalyze("test", "<a href=\"#\">jeff quit fish</a>").setTokenizer("standard").setCharFilters("html_strip", "custom_mapping").execute().actionGet();
assertThat(analyzeResponse.getTokens().size(), equalTo(3));
AnalyzeResponse.AnalyzeToken token = analyzeResponse.getTokens().get(0);
assertThat(token.getTerm(), equalTo("jeff"));
token = analyzeResponse.getTokens().get(1);
assertThat(token.getTerm(), equalTo("qit"));
token = analyzeResponse.getTokens().get(2);
assertThat(token.getTerm(), equalTo("fish"));
} }
@Test @Test