You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@calcite.apache.org by el...@apache.org on 2016/05/31 23:24:06 UTC
[08/14] calcite git commit: [CALCITE-1253] Elasticsearch adapter
(Subhobrata Dey)
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/elasticsearch/src/test/java/org/apache/calcite/test/ElasticsearchAdapterIT.java
----------------------------------------------------------------------
diff --git a/elasticsearch/src/test/java/org/apache/calcite/test/ElasticsearchAdapterIT.java b/elasticsearch/src/test/java/org/apache/calcite/test/ElasticsearchAdapterIT.java
new file mode 100644
index 0000000..d99351e
--- /dev/null
+++ b/elasticsearch/src/test/java/org/apache/calcite/test/ElasticsearchAdapterIT.java
@@ -0,0 +1,270 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to you under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.calcite.test;
+
+import org.apache.calcite.util.Util;
+
+import com.google.common.base.Function;
+import com.google.common.collect.ImmutableMap;
+
+import org.junit.Test;
+
+import java.util.List;
+import javax.annotation.Nullable;
+
+/**
+ * Tests for the {@code org.apache.calcite.adapter.elasticsearch} package.
+ *
+ * <p>Before calling this test, you need to populate Elasticsearch, as follows:
+ *
+ * <blockquote><code>
+ * git clone https://github.com/vlsi/calcite-test-dataset<br>
+ * cd calcite-test-dataset<br>
+ * mvn install
+ * </code></blockquote>
+ *
+ * This will create a virtual machine with Elasticsearch and the "zips" test
+ * dataset.
+ */
+public class ElasticsearchAdapterIT {
+ /**
+ * Whether to run Elasticsearch tests. Enabled by default, however test is only
+ * included if "it" profile is activated ({@code -Pit}). To disable,
+ * specify {@code -Dcalcite.test.elasticsearch=false} on the Java command line.
+ */
+ private static final boolean ENABLED = Util.getBooleanProperty("calcite.test.elasticsearch",
+ true);
+
+ /** Connection factory based on the "zips-es" model. */
+ private static final ImmutableMap<String, String> ZIPS = ImmutableMap.of("model",
+ ElasticsearchAdapterIT.class.getResource("/elasticsearch-zips-model.json").getPath());
+
+ /** Whether to run this test. */
+ private boolean enabled() {
+ return ENABLED;
+ }
+
+ /** Returns a function that checks that a particular Elasticsearch pipeline is
+ * generated to implement a query. */
+ private static Function<List, Void> elasticsearchChecker(final String... strings) {
+ return new Function<List, Void>() {
+ @Nullable
+ @Override public Void apply(@Nullable List actual) {
+ Object[] actualArray = actual == null || actual.isEmpty() ? null
+ : ((List) actual.get(0)).toArray();
+ CalciteAssert.assertArrayEqual("expected Elasticsearch query not found", strings,
+ actualArray);
+ return null;
+ }
+ };
+ }
+
+ @Test public void testSort() {
+ final String explain = "PLAN=ElasticsearchToEnumerableConverter\n"
+ + " ElasticsearchSort(sort0=[$4], dir0=[ASC])\n"
+ + " ElasticsearchProject(city=[CAST(ITEM($0, 'city')):VARCHAR(20) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"], longitude=[CAST(ITEM(ITEM($0, 'loc'), 0)):FLOAT], latitude=[CAST(ITEM(ITEM($0, 'loc'), 1)):FLOAT], pop=[CAST(ITEM($0, 'pop')):INTEGER], state=[CAST(ITEM($0, 'state')):VARCHAR(2) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"], id=[CAST(ITEM($0, 'id')):VARCHAR(5) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"])\n"
+ + " ElasticsearchTableScan(table=[[elasticsearch_raw, zips]])";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select * from zips order by \"state\"")
+ .returnsCount(10)
+ .explainContains(explain);
+ }
+
+ @Test public void testSortLimit() {
+ final String sql = "select \"state\", \"id\" from zips\n"
+ + "order by \"state\", \"id\" offset 2 rows fetch next 3 rows only";
+ CalciteAssert.that()
+ .with(ZIPS)
+ .query(sql)
+ .returnsUnordered("state=AK; id=99503",
+ "state=AK; id=99504",
+ "state=AK; id=99505")
+ .queryContains(
+ elasticsearchChecker(
+ "\"fields\" : [\"state\", \"id\"], \"script_fields\": {}",
+ "\"sort\": [ {\"state\": \"asc\"}, {\"id\": \"asc\"}]",
+ "\"from\": 2",
+ "\"size\": 3"));
+ }
+
+ @Test public void testOffsetLimit() {
+ final String sql = "select \"state\", \"id\" from zips\n"
+ + "offset 2 fetch next 3 rows only";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .runs()
+ .queryContains(
+ elasticsearchChecker(
+ "\"from\": 2",
+ "\"size\": 3",
+ "\"fields\" : [\"state\", \"id\"], \"script_fields\": {}"));
+ }
+
+ @Test public void testLimit() {
+ final String sql = "select \"state\", \"id\" from zips\n"
+ + "fetch next 3 rows only";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .runs()
+ .queryContains(
+ elasticsearchChecker(
+ "\"size\": 3",
+ "\"fields\" : [\"state\", \"id\"], \"script_fields\": {}"));
+ }
+
+ @Test public void testFilterSort() {
+ final String sql = "select * from zips\n"
+ + "where \"city\" = 'SPRINGFIELD' and \"id\" >= '70000'\n"
+ + "order by \"state\", \"id\"";
+ final String explain = "PLAN=ElasticsearchToEnumerableConverter\n"
+ + " ElasticsearchSort(sort0=[$4], sort1=[$5], dir0=[ASC], dir1=[ASC])\n"
+ + " ElasticsearchProject(city=[CAST(ITEM($0, 'city')):VARCHAR(20) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"], longitude=[CAST(ITEM(ITEM($0, 'loc'), 0)):FLOAT], latitude=[CAST(ITEM(ITEM($0, 'loc'), 1)):FLOAT], pop=[CAST(ITEM($0, 'pop')):INTEGER], state=[CAST(ITEM($0, 'state')):VARCHAR(2) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"], id=[CAST(ITEM($0, 'id')):VARCHAR(5) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"])\n"
+ + " ElasticsearchFilter(condition=[AND(=(CAST(ITEM($0, 'city')):VARCHAR(20) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\", 'SPRINGFIELD'), >=(CAST(ITEM($0, 'id')):VARCHAR(5) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\", '70000'))])\n"
+ + " ElasticsearchTableScan(table=[[elasticsearch_raw, zips]])";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .returnsOrdered(
+ "city=SPRINGFIELD; longitude=-92.54567; latitude=35.274879; pop=752; state=AR; id=72157",
+ "city=SPRINGFIELD; longitude=-102.617322; latitude=37.406727; pop=1992; state=CO; id=81073",
+ "city=SPRINGFIELD; longitude=-90.577479; latitude=30.415738; pop=5597; state=LA; id=70462",
+ "city=SPRINGFIELD; longitude=-123.015259; latitude=44.06106; pop=32384; state=OR; id=97477",
+ "city=SPRINGFIELD; longitude=-122.917108; latitude=44.056056; pop=27521; state=OR; id=97478")
+ .queryContains(
+ elasticsearchChecker("\"query\" : {\"constant_score\":{\"filter\":{\"bool\":"
+ + "{\"must\":[{\"term\":{\"city\":\"springfield\"}},{\"range\":{\"id\":{\"gte\":\"70000\"}}}]}}}}",
+ "\"fields\" : [\"city\", \"pop\", \"state\", \"id\"], \"script_fields\": {\"longitude\":{\"script\":\"_source.loc[0]\"}, \"latitude\":{\"script\":\"_source.loc[1]\"}}",
+ "\"sort\": [ {\"state\": \"asc\"}, {\"id\": \"asc\"}]"))
+ .explainContains(explain);
+ }
+
+ @Test public void testFilterSortDesc() {
+ final String sql = "select * from zips\n"
+ + "where \"pop\" BETWEEN 20000 AND 20100\n"
+ + "order by \"state\" desc, \"pop\"";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .limit(4)
+ .returnsOrdered(
+ "city=SHERIDAN; longitude=-106.964795; latitude=44.78486; pop=20025; state=WY; id=82801",
+ "city=MOUNTLAKE TERRAC; longitude=-122.304036; latitude=47.793061; pop=20059; state=WA; id=98043",
+ "city=FALMOUTH; longitude=-77.404537; latitude=38.314557; pop=20039; state=VA; id=22405",
+ "city=FORT WORTH; longitude=-97.318409; latitude=32.725551; pop=20012; state=TX; id=76104");
+ }
+
+ @Test public void testFilterRedundant() {
+ final String sql = "select * from zips\n"
+ + "where \"state\" > 'CA' and \"state\" < 'AZ' and \"state\" = 'OK'";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .runs()
+ .queryContains(
+ elasticsearchChecker(""
+ + "\"query\" : {\"constant_score\":{\"filter\":{\"bool\":"
+ + "{\"must\":[{\"term\":{\"state\":\"ok\"}}]}}}}",
+ "\"fields\" : [\"city\", \"pop\", \"state\", \"id\"], \"script_fields\": {\"longitude\":{\"script\":\"_source.loc[0]\"}, \"latitude\":{\"script\":\"_source.loc[1]\"}}"));
+ }
+
+ @Test public void testInPlan() {
+ final String[] searches = {
+ "\"query\" : {\"constant_score\":{\"filter\":{\"bool\":{\"should\":"
+ + "[{\"bool\":{\"must\":[{\"term\":{\"pop\":20012}}]}},{\"bool\":{\"must\":[{\"term\":"
+ + "{\"pop\":15590}}]}}]}}}}",
+ "\"fields\" : [\"city\", \"pop\", \"state\", \"id\"], \"script_fields\": {\"longitude\":{\"script\":\"_source.loc[0]\"}, \"latitude\":{\"script\":\"_source.loc[1]\"}}"
+ };
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select * from zips where \"pop\" in (20012, 15590)")
+ .returnsUnordered(
+ "city=COVINA; longitude=-117.884285; latitude=34.08596; pop=15590; state=CA; id=91723",
+ "city=ARLINGTON; longitude=-97.091987; latitude=32.654752; pop=15590; state=TX; id=76018",
+ "city=CROFTON; longitude=-76.680166; latitude=39.011163; pop=15590; state=MD; id=21114",
+ "city=FORT WORTH; longitude=-97.318409; latitude=32.725551; pop=20012; state=TX; id=76104",
+ "city=DINUBA; longitude=-119.39087; latitude=36.534931; pop=20012; state=CA; id=93618")
+ .queryContains(elasticsearchChecker(searches));
+ }
+
+ @Test public void testZips() {
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select \"state\", \"city\" from zips")
+ .returnsCount(10);
+ }
+
+ @Test public void testProject() {
+ final String sql = "select \"state\", \"city\", 0 as \"zero\"\n"
+ + "from zips\n"
+ + "order by \"state\", \"city\"";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query(sql)
+ .limit(2)
+ .returnsUnordered("state=AK; city=ELMENDORF AFB; zero=0",
+ "state=AK; city=EIELSON AFB; zero=0")
+ .queryContains(
+ elasticsearchChecker("\"sort\": [ {\"state\": \"asc\"}, {\"city\": \"asc\"}]",
+ "\"fields\" : [\"state\", \"city\"], \"script_fields\": {\"zero\":{\"script\": \"0\"}}"));
+ }
+
+ @Test public void testFilter() {
+ final String explain = "PLAN=ElasticsearchToEnumerableConverter\n"
+ + " ElasticsearchProject(state=[CAST(ITEM($0, 'state')):VARCHAR(2) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"], city=[CAST(ITEM($0, 'city')):VARCHAR(20) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\"])\n"
+ + " ElasticsearchFilter(condition=[=(CAST(ITEM($0, 'state')):VARCHAR(2) CHARACTER SET \"ISO-8859-1\" COLLATE \"ISO-8859-1$en_US$primary\", 'CA')])\n"
+ + " ElasticsearchTableScan(table=[[elasticsearch_raw, zips]])";
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select \"state\", \"city\" from zips where \"state\" = 'CA'")
+ .limit(2)
+ .returnsUnordered("state=CA; city=LOS ANGELES",
+ "state=CA; city=LOS ANGELES")
+ .explainContains(explain);
+ }
+
+ @Test public void testFilterReversed() {
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select \"state\", \"city\" from zips where 'WI' < \"state\"")
+ .limit(2)
+ .returnsUnordered("state=WV; city=WELCH",
+ "state=WV; city=HANOVER");
+ CalciteAssert.that()
+ .enable(enabled())
+ .with(ZIPS)
+ .query("select \"state\", \"city\" from zips where \"state\" > 'WI'")
+ .limit(2)
+ .returnsUnordered("state=WV; city=WELCH",
+ "state=WV; city=HANOVER");
+ }
+}
+
+// End ElasticsearchAdapterIT.java
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/elasticsearch/src/test/resources/elasticsearch-zips-model.json
----------------------------------------------------------------------
diff --git a/elasticsearch/src/test/resources/elasticsearch-zips-model.json b/elasticsearch/src/test/resources/elasticsearch-zips-model.json
new file mode 100644
index 0000000..dcbf2a4
--- /dev/null
+++ b/elasticsearch/src/test/resources/elasticsearch-zips-model.json
@@ -0,0 +1,50 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to you under the Apache License, Version 2.0
+ * (the License); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an AS IS BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+{
+ "version": "1.0",
+ "defaultSchema": "elasticsearch",
+ "schemas": [
+ {
+ "type": "custom",
+ "name": "elasticsearch_raw",
+ "factory": "org.apache.calcite.adapter.elasticsearch.ElasticsearchSchemaFactory",
+ "operand": {
+ "coordinates": "{'127.0.0.1': 9300}",
+ "userConfig": "{'bulk.flush.max.actions': 10, 'bulk.flush.max.size.mb': 1}",
+ "index": "usa"
+ }
+ },
+ {
+ "name": "elasticsearch",
+ "tables": [
+ {
+ "name": "ZIPS",
+ "type": "view",
+ "sql": [
+ "select cast(_MAP['city'] AS varchar(20)) AS \"city\",\n",
+ " cast(_MAP['loc'][0] AS float) AS \"longitude\",\n",
+ " cast(_MAP['loc'][1] AS float) AS \"latitude\",\n",
+ " cast(_MAP['pop'] AS integer) AS \"pop\",\n",
+ " cast(_MAP['state'] AS varchar(2)) AS \"state\",\n",
+ " cast(_MAP['id'] AS varchar(5)) AS \"id\"\n",
+ "from \"elasticsearch_raw\".\"zips\""
+ ]
+ }
+ ]
+ }
+ ]
+}
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/elasticsearch/src/test/resources/log4j.properties
----------------------------------------------------------------------
diff --git a/elasticsearch/src/test/resources/log4j.properties b/elasticsearch/src/test/resources/log4j.properties
new file mode 100644
index 0000000..834e2db
--- /dev/null
+++ b/elasticsearch/src/test/resources/log4j.properties
@@ -0,0 +1,24 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to you under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Root logger is configured at INFO and is sent to A1
+log4j.rootLogger=INFO, A1
+
+# A1 goes to the console
+log4j.appender.A1=org.apache.log4j.ConsoleAppender
+
+# Set the pattern for each log message
+log4j.appender.A1.layout=org.apache.log4j.PatternLayout
+log4j.appender.A1.layout.ConversionPattern=%d [%t] %-5p - %m%n
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/pom.xml
----------------------------------------------------------------------
diff --git a/pom.xml b/pom.xml
index b12e430..063f16d 100644
--- a/pom.xml
+++ b/pom.xml
@@ -61,6 +61,7 @@ limitations under the License.
<commons-lang3.version>3.2</commons-lang3.version>
<commons-logging.version>1.1.3</commons-logging.version>
<eigenbase-properties.version>1.1.5</eigenbase-properties.version>
+ <elasticsearch-java-driver.version>2.3.2</elasticsearch-java-driver.version>
<findbugs.version>1.3.9</findbugs.version>
<fmpp-maven-plugin.version>1.0</fmpp-maven-plugin.version>
<foodmart-data-hsqldb.version>0.3</foodmart-data-hsqldb.version>
@@ -131,6 +132,7 @@ limitations under the License.
<module>cassandra</module>
<module>core</module>
<module>druid</module>
+ <module>elasticsearch</module>
<module>example</module>
<module>linq4j</module>
<module>mongodb</module>
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/site/_docs/adapter.md
----------------------------------------------------------------------
diff --git a/site/_docs/adapter.md b/site/_docs/adapter.md
index b003e81..01a6995 100644
--- a/site/_docs/adapter.md
+++ b/site/_docs/adapter.md
@@ -30,6 +30,7 @@ presenting the data as tables within a schema.
* [Cassandra adapter](cassandra_adapter.html) (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/cassandra/package-summary.html">calcite-cassandra</a>)
* CSV adapter (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/csv/package-summary.html">example/csv</a>)
* [Druid adapter](druid_adapter.html) (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/druid/package-summary.html">calcite-druid</a>)
+* [Elasticsearch adapter](elasticsearch_adapter.html) (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/elasticsearch/package-summary.html">calcite-elasticsearch</a>)
* JDBC adapter (part of <a href="{{ site.apiRoot }}/org/apache/calcite/adapter/jdbc/package-summary.html">calcite-core</a>)
* MongoDB adapter (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/mongodb/package-summary.html">calcite-mongodb</a>)
* Spark adapter (<a href="{{ site.apiRoot }}/org/apache/calcite/adapter/spark/package-summary.html">calcite-spark</a>)
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/site/_docs/elasticsearch_adapter.md
----------------------------------------------------------------------
diff --git a/site/_docs/elasticsearch_adapter.md b/site/_docs/elasticsearch_adapter.md
new file mode 100644
index 0000000..d87d9e3
--- /dev/null
+++ b/site/_docs/elasticsearch_adapter.md
@@ -0,0 +1,136 @@
+---
+layout: docs
+title: Elasticsearch adapter
+permalink: /docs/elasticsearch_adapter.html
+---
+<!--
+{% comment %}
+Licensed to the Apache Software Foundation (ASF) under one or more
+contributor license agreements. See the NOTICE file distributed with
+this work for additional information regarding copyright ownership.
+The ASF licenses this file to you under the Apache License, Version 2.0
+(the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+{% endcomment %}
+-->
+
+For instructions on downloading and building Calcite, start with the
+[tutorial]({{ site.baseurl }}/docs/tutorial.html).
+
+Once you've managed to compile the project, you can return here to
+start querying Elasticsearch with Calcite. First, we need a
+[model definition]({{ site.baseurl }}/docs/model.html).
+The model gives Calcite the necessary parameters to create an instance
+of the Elasticsearch adapter. The models can contain
+definitions of
+[materializations]({{ site.baseurl }}/docs/model.html#materialization).
+The name of the tables defined in the model definition corresponds to
+[types](https://www.elastic.co/blog/what-is-an-elasticsearch-index) in
+Elasticsearch. The schema/database is represented by the `index` parameter
+in the model definition.
+
+A basic example of a model file is given below:
+
+{% highlight json %}
+{
+ "version": "1.0",
+ "defaultSchema": "elasticsearch",
+ "schemas": [
+ {
+ "type": "custom",
+ "name": "elasticsearch",
+ "factory": "org.apache.calcite.adapter.elasticsearch.ElasticsearchSchemaFactory",
+ "operand": {
+ "coordinates": "{'127.0.0.1': 9300}",
+ "userConfig": "{'bulk.flush.max.actions': 10, 'bulk.flush.max.size.mb': 1}",
+ "index": "usa"
+ }
+ }
+ ]
+}
+{% endhighlight %}
+
+Assuming this file is stored as `model.json`, you can connect to
+Elasticsearch via [`sqlline`](https://github.com/julianhyde/sqlline) as
+follows:
+
+{% highlight bash %}
+$ ./sqlline
+sqlline> !connect jdbc:calcite:model=model.json admin admin
+{% endhighlight %}
+
+`sqlline` will now accept SQL queries which access your Elasticsearch types.
+The purpose of this adapter is to compile the query into the most efficient
+Elasticsearch SEARCH JSON possible by exploiting filtering and sorting directly
+in Elasticsearch where possible.
+
+For example, in the example dataset there is an Elasticsearch type
+named `zips` under index named `usa`.
+
+We can issue a simple query to fetch the names of all the states
+stored in the type `zips`. By default, Elasticsearch returns only 10 rows:
+
+{% highlight sql %}
+sqlline> SELECT * from "zips";
+{% endhighlight %}
+
+{% highlight json %}
+_MAP={pop=13367, loc=[-72.505565, 42.067203], city=EAST LONGMEADOW, id=01028, state=MA}
+_MAP={pop=1652, loc=[-72.908793, 42.070234], city=TOLLAND, id=01034, state=MA}
+_MAP={pop=3184, loc=[-72.616735, 42.38439], city=HATFIELD, id=01038, state=MA}
+_MAP={pop=43704, loc=[-72.626193, 42.202007], city=HOLYOKE, id=01040, state=MA}
+_MAP={pop=2084, loc=[-72.873341, 42.265301], city=HUNTINGTON, id=01050, state=MA}
+_MAP={pop=1350, loc=[-72.703403, 42.354292], city=LEEDS, id=01053, state=MA}
+_MAP={pop=8194, loc=[-72.319634, 42.101017], city=MONSON, id=01057, state=MA}
+_MAP={pop=1732, loc=[-72.204592, 42.062734], city=WALES, id=01081, state=MA}
+_MAP={pop=9808, loc=[-72.258285, 42.261831], city=WARE, id=01082, state=MA}
+_MAP={pop=4441, loc=[-72.203639, 42.20734], city=WEST WARREN, id=01092, state=MA}
+{% endhighlight %}
+
+While executing this query, the Elasticsearch adapter is able to recognize
+that `city` can be filtered by Elasticsearch and `state` can be sorted by
+Elasticsearch in ascending order.
+
+The final source json given to Elasticsearch is below:
+
+{% highlight json %}
+{
+ "query": {
+ "constant_score": {
+ "filter": {
+ "bool": {
+ "must": [
+ {
+ "term": {
+ "city": "springfield"
+ }
+ }
+ ]
+ }
+ }
+ }
+ },
+ "fields": [
+ "city",
+ "state"
+ ],
+ "script_fields": {},
+ "sort": [
+ {
+ "state": "asc"
+ }
+ ]
+}
+{% endhighlight %}
+
+This is the initial version of the Calcite Elasticsearch adapter.
+Work is in progress to introduce new features like aggregations into
+it.
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/sqlline
----------------------------------------------------------------------
diff --git a/sqlline b/sqlline
index e1b13c7..9e111a2 100755
--- a/sqlline
+++ b/sqlline
@@ -37,7 +37,7 @@ if [ ! -f target/fullclasspath.txt ]; then
fi
CP=
-for module in core avatica cassandra druid mongodb spark splunk example/csv example/function; do
+for module in core avatica cassandra druid elasticsearch mongodb spark splunk example/csv example/function; do
CP=${CP}${module}/target/classes:
CP=${CP}${module}/target/test-classes:
done
http://git-wip-us.apache.org/repos/asf/calcite/blob/f3caf13b/sqlline.bat
----------------------------------------------------------------------
diff --git a/sqlline.bat b/sqlline.bat
index b9a4875..50e9701 100644
--- a/sqlline.bat
+++ b/sqlline.bat
@@ -23,6 +23,6 @@
:: Copy dependency jars on first call. (To force jar refresh, remove target\dependencies)
if not exist target\dependencies (call mvn -B dependency:copy-dependencies -DoverWriteReleases=false -DoverWriteSnapshots=false -DoverWriteIfNewer=true -DoutputDirectory=target\dependencies)
-java -Xmx1G -cp ".\target\dependencies\*;core\target\dependencies\*;avatica\target\dependencies\*;cassandra\target\dependencies\*;mongodb\target\dependencies\*;spark\target\dependencies\*;splunk\target\dependencies\*" sqlline.SqlLine --verbose=true %*
+java -Xmx1G -cp ".\target\dependencies\*;core\target\dependencies\*;avatica\target\dependencies\*;cassandra\target\dependencies\*;elasticsearch\target\dependencies\*;mongodb\target\dependencies\*;spark\target\dependencies\*;splunk\target\dependencies\*" sqlline.SqlLine --verbose=true %*
:: End sqlline.bat