some new features for the term lists

Author: jprante

README.md

@@ -1,34 +1,36 @@
 # Elasticsearch Index Termlist Plugin
 
-This plugin extends Elasticsearch with a term list capability, not only revealing all occuring terms but
-also stating each terms frequency. Term lists can be generated from indexes, or even of all of the
-indexes in the cluster.
+This plugin extends Elasticsearch with a term list capability. It presents a list of terms in a field of an index
+and can also list each terms frequency. Term lists can be generated from one index or even of all of the
+indexes.
 
 ## Versions
 
 | Elasticsearch  | Plugin       | Release date |
 | -------------- | ------------ | ------------ |
+| 1.3.2          | 1.3.0.0      | Aug 21, 2014 |
 | 1.2.1          | 1.2.1.0      | Jul  3, 2014 |
 
 ## Installation
 
-    ./bin/plugin -install index-termlist -url http://xbib.org/repository/org/xbib/elasticsearch/plugin/elasticsearch-index-termlist/1.2.1.0/elasticsearch-index-termlist-1.2.1.0-plugin.zip
+    ./bin/plugin -install index-termlist -url http://xbib.org/repository/org/xbib/elasticsearch/plugin/elasticsearch-index-termlist/1.3.0.0/elasticsearch-index-termlist-1.3.0.0-plugin.zip
 
 Do not forget to restart the node after installing.
 
 ## Checksum
 
 | File                                              | SHA1                                     |
 | ------------------------------------------------- | -----------------------------------------|
+| elasticsearch-index-termlist-1.3.0.0-plugin.zip   | 07ea40e85584c9887337c14ec5cca098a31089b5 |
 | elasticsearch-index-termlist-1.2.1.0-plugin.zip   | c51a8d626b32a4a6cd2ac4335b5578f0e5cccaa6 |
 
 ## Project docs
 
-The Maven project site is available at [Github](http://jprante.github.io/elasticsearch-index-termlis)
+The Maven project site is available at [Github](http://jprante.github.io/elasticsearch-index-termlist)
 
 ## Issues
 
-All feedback is welcome! If you find issues, please post them at [Github](https://github.com/jprante/elasticsearch-index-termlis/issues)
+All feedback is welcome! If you find issues, please post them at [Github](https://github.com/jprante/elasticsearch-index-termlist/issues)
 
 # Introduction
 
@@ -48,34 +50,42 @@ like `_uid`, `_all`, or `_type` are always skipped.
 
 # Example
 
-Consider the following example index::
+Consider the following example index
 
+	curl -XDELETE 'http://localhost:9200/test/'
 	curl -XPUT 'http://localhost:9200/test/'
 	curl -XPUT 'http://localhost:9200/test/test/1' -d '{ "test": "Hello World" }'
 	curl -XPUT 'http://localhost:9200/test/test/2' -d '{ "test": "Hello Jörg Prante" }'
 	curl -XPUT 'http://localhost:9200/test/test/3' -d '{ "message": "elastic search" }'
 
-Get term list of index ``test``::
+Get term list of index ``test``
 
 	curl -XGET 'http://localhost:9200/test/_termlist'
-	{"_shards":{"total":5,"successful":5,"failed":0},"terms":[{"name":"search"},{"name":"prante"},{"name":"hello"},{"name":"elastic"},{"name":"world"},{"name":"jörg"}]}
+	{"_shards":{"total":5,"successful":5,"failed":0},"total":6,"terms":[{"name":"search"},{"name":"prante"},{"name":"hello"},{"name":"world"},{"name":"jörg"},{"name":"elastic"}]}
 
-Get term list of index `test` of field `message`::
+Get term list of index `test` of field `message`
 
 	curl -XGET 'http://localhost:9200/test/_termlist?field=message'
-	{"_shards":{"total":5,"successful":5,"failed":0},"terms":[{"name":"elastic"},{"name":"search"}]}
+	{"_shards":{"total":5,"successful":5,"failed":0},"total":2,"terms":[{"name":"elastic"},{"name":"search"}]}
 
-Get term list of index `test` with total frequencies::
+Get term list of index `test` with total frequencies
 
 	curl -XGET 'http://localhost:9200/test/_termlist?totalfreqs'
-	{"_shards":{"total":5,"successful":5,"failed":0},"terms":[{"name":"hello","totalfreq":2},{"name":"world","totalfreq":1},{"name":"search","totalfreq":1},{"name":"prante","totalfreq":1},{"name":"jörg","totalfreq":1},{"name":"elastic","totalfreq":1}]}
+	{"_shards":{"total":5,"successful":5,"failed":0},"total":6,"terms":[{"name":"search","totalfreq":1},{"name":"prante","totalfreq":1},{"name":"hello","totalfreq":2},{"name":"world","totalfreq":1},{"name":"jörg","totalfreq":1},{"name":"elastic","totalfreq":1}]}
 
-
-Get term list of index `test` with total frequencies but only the first three terms of the list::
+Get term list of index `test` with total frequencies but only the first three terms of the list
 
 	curl -XGET 'http://localhost:9200/test/_termlist?totalfreqs&size=3'
-	{"_shards":{"total":5,"successful":5,"failed":0},"terms":[{"name":"hello","totalfreq":2},{"name":"world","totalfreq":1},{"name":"search","totalfreq":1}]}
+	{"_shards":{"total":5,"successful":5,"failed":0},"total":6,"terms":[{"name":"prante","totalfreq":1},{"name":"hello","totalfreq":2},{"name":"world","totalfreq":1}]}
+
+Get term list of terms starting with `hello` in index `test` field `test`, with total frequencies. This can be useful to estimate hits.
+
+	curl -XGET 'http://localhost:9200/test/_termlist?field=test&term=hello&totalfreqs'
+	{"_shards":{"total":5,"successful":5,"failed":0},"total":1,"terms":[{"name":"hello","totalfreq":2}]}
+
+A complete sorted list of terms in your index beginning with `a`, pageable, complete with frequencies
 
+    curl -XGET 'http://localhost:9200/books/_termlist?term=a&totalfreqs&sortbyterms&pretty&from=0&size=100' 
 
 # Caution
 

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>org.xbib.elasticsearch.plugin</groupId>
     <artifactId>elasticsearch-index-termlist</artifactId>
-    <version>1.2.1.0</version>
+    <version>1.3.0.0</version>
 
     <packaging>jar</packaging>
 
@@ -45,24 +45,11 @@
         </repository>
     </distributionManagement>
 
-    <repositories>
-        <repository>
-            <id>xbib</id>
-            <url>http://xbib.org/repository</url>
-            <releases>
-                <enabled>true</enabled>
-            </releases>
-            <snapshots>
-                <enabled>true</enabled>
-            </snapshots>
-        </repository>
-    </repositories>
-
     <properties>
         <github.global.server>github</github.global.server>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <java.compile.version>1.7</java.compile.version>
-        <elasticsearch.version>1.2.1</elasticsearch.version>
+        <elasticsearch.version>1.3.2</elasticsearch.version>
     </properties>
 
     <dependencies>

src/main/java/org/xbib/elasticsearch/action/termlist/ShardTermlistRequest.java

@@ -10,6 +10,10 @@ class ShardTermlistRequest extends BroadcastShardOperationRequest {
 
     private String field;
 
+    private String term;
+
+    private Integer from;
+
     private Integer size;
 
     private boolean withDocFreq;
@@ -22,6 +26,8 @@ class ShardTermlistRequest extends BroadcastShardOperationRequest {
     public ShardTermlistRequest(String index, int shardId, TermlistRequest request) {
         super(index, shardId, request);
         this.field = request.getField();
+        this.term = request.getTerm();
+        this.from = request.getFrom();
         this.size = request.getSize();
         this.withDocFreq = request.getWithDocFreq();
         this.withTotalFreq = request.getWithTotalFreq();
@@ -35,6 +41,22 @@ public String getField() {
         return field;
     }
 
+    public void setTerm(String term) {
+        this.term = term;
+    }
+
+    public String getTerm() {
+        return term;
+    }
+
+    public void setFrom(Integer from) {
+        this.from = from;
+    }
+
+    public Integer getFrom() {
+        return from;
+    }
+
     public void setSize(Integer size) {
         this.size = size;
     }
@@ -63,6 +85,9 @@ public boolean getWithTotalFreq() {
     public void readFrom(StreamInput in) throws IOException {
         super.readFrom(in);
         field = in.readString();
+        term = in.readString();
+        from = in.readInt();
+        size = in.readInt();
         withDocFreq = in.readBoolean();
         withTotalFreq = in.readBoolean();
     }
@@ -71,6 +96,9 @@ public void readFrom(StreamInput in) throws IOException {
     public void writeTo(StreamOutput out) throws IOException {
         super.writeTo(out);
         out.writeString(field);
+        out.writeString(term);
+        out.writeInt(from);
+        out.writeInt(size);
         out.writeBoolean(withDocFreq);
         out.writeBoolean(withTotalFreq);
     }

src/main/java/org/xbib/elasticsearch/action/termlist/TermInfo.java

@@ -8,9 +8,9 @@
 
 public class TermInfo implements Streamable {
 
-    Integer docFreq;
+    private Integer docFreq;
 
-    Long totalFreq;
+    private Long totalFreq;
 
     public TermInfo docfreq(int docFreq) {
         this.docFreq = docFreq;

src/main/java/org/xbib/elasticsearch/action/termlist/TermlistAction.java

@@ -1,10 +1,9 @@
 package org.xbib.elasticsearch.action.termlist;
 
-import org.elasticsearch.action.Action;
+import org.elasticsearch.action.ClientAction;
 import org.elasticsearch.client.Client;
-import org.elasticsearch.client.internal.InternalGenericClient;
 
-public class TermlistAction extends Action<TermlistRequest, TermlistResponse, TermlistRequestBuilder> {
+public class TermlistAction extends ClientAction<TermlistRequest, TermlistResponse, TermlistRequestBuilder> {
 
     public static final TermlistAction INSTANCE = new TermlistAction();
 
@@ -21,6 +20,6 @@ public TermlistResponse newResponse() {
 
     @Override
     public TermlistRequestBuilder newRequestBuilder(Client client) {
-        return new TermlistRequestBuilder((InternalGenericClient) client);
+        return new TermlistRequestBuilder(client);
     }
 }

src/main/java/org/xbib/elasticsearch/action/termlist/TermlistRequest.java

@@ -10,12 +10,22 @@ public class TermlistRequest extends BroadcastOperationRequest<TermlistRequest>
 
     private String field;
 
+    private String term;
+
+    private Integer from;
+
     private Integer size;
 
     private boolean withDocFreq;
 
     private boolean withTotalFreq;
 
+    private boolean sortByTerm;
+
+    private boolean sortByDocFreq;
+
+    private boolean sortByTotalFreq;
+
     TermlistRequest() {
     }
 
@@ -31,6 +41,22 @@ public String getField() {
         return field;
     }
 
+    public void setTerm(String term) {
+        this.term = term;
+    }
+
+    public String getTerm() {
+        return term;
+    }
+
+    public void setFrom(Integer from) {
+        this.from = from;
+    }
+
+    public Integer getFrom() {
+        return from;
+    }
+
     public void setSize(Integer size) {
         this.size = size;
     }
@@ -55,15 +81,54 @@ public boolean getWithTotalFreq() {
         return withTotalFreq;
     }
 
+    public void sortByTerm(boolean sortByTerm) {
+        this.sortByTerm = sortByTerm;
+    }
+
+    public boolean sortByTerm() {
+        return sortByTerm;
+    }
+
+    public void sortByDocFreq(boolean sortByDocFreq) {
+        this.sortByDocFreq = sortByDocFreq;
+    }
+
+    public boolean sortByDocFreq() {
+        return sortByDocFreq;
+    }
+
+    public void sortByTotalFreq(boolean sortByTotalFreq) {
+        this.sortByTotalFreq = sortByTotalFreq;
+    }
+
+    public boolean sortByTotalFreq() {
+        return sortByTotalFreq;
+    }
+
     @Override
     public void readFrom(StreamInput in) throws IOException {
         super.readFrom(in);
         field = in.readString();
+        term = in.readString();
+        from = in.readInt();
+        size = in.readInt();
+        withDocFreq = in.readBoolean();
+        withTotalFreq = in.readBoolean();
+        sortByDocFreq = in.readBoolean();
+        sortByTotalFreq = in.readBoolean();
+
     }
 
     @Override
     public void writeTo(StreamOutput out) throws IOException {
         super.writeTo(out);
         out.writeString(field);
+        out.writeString(term);
+        out.writeInt(from);
+        out.writeInt(size);
+        out.writeBoolean(withDocFreq);
+        out.writeBoolean(withTotalFreq);
+        out.writeBoolean(sortByDocFreq);
+        out.writeBoolean(sortByTotalFreq);
     }
 }

src/main/java/org/xbib/elasticsearch/action/termlist/TermlistRequestBuilder.java

@@ -3,17 +3,36 @@
 import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.action.support.broadcast.BroadcastOperationRequestBuilder;
 import org.elasticsearch.client.Client;
-import org.elasticsearch.client.internal.InternalGenericClient;
 
 /**
  * A request to get termlists of one or more indices.
  */
-public class TermlistRequestBuilder extends BroadcastOperationRequestBuilder<TermlistRequest, TermlistResponse, TermlistRequestBuilder> {
+public class TermlistRequestBuilder extends BroadcastOperationRequestBuilder<TermlistRequest, TermlistResponse, TermlistRequestBuilder, Client> {
 
-    public TermlistRequestBuilder(InternalGenericClient client) {
+    public TermlistRequestBuilder(Client client) {
         super(client, new TermlistRequest());
     }
 
+    public TermlistRequestBuilder setField(String field) {
+        request.setField(field);
+        return this;
+    }
+
+    public TermlistRequestBuilder setTerm(String term) {
+        request.setTerm(term);
+        return this;
+    }
+
+    public TermlistRequestBuilder setFrom(Integer from) {
+        request.setFrom(from);
+        return this;
+    }
+
+    public TermlistRequestBuilder setSize(Integer size) {
+        request.setSize(size);
+        return this;
+    }
+
     public TermlistRequestBuilder withDocFreq() {
         request.setWithDocFreq(true);
         return this;
@@ -24,8 +43,19 @@ public TermlistRequestBuilder withTotalFreq() {
         return this;
     }
 
+    public TermlistRequestBuilder sortByDocFreq(boolean sortByDocFreq) {
+        request.sortByDocFreq(sortByDocFreq);
+        return this;
+    }
+
+    public TermlistRequestBuilder sortByTotalFreq(boolean sortByTotalFreq) {
+        request.sortByTotalFreq(sortByTotalFreq);
+        return this;
+    }
+
+
     @Override
     protected void doExecute(ActionListener<TermlistResponse> listener) {
-        ((Client) client).execute(TermlistAction.INSTANCE, request, listener);
+        client.execute(TermlistAction.INSTANCE, request, listener);
     }
 }