No whitespace allowed in resouce/types

relates elastic#730
williamrandolph · Apr 4, 2016 · 5e6cff4 · 5e6cff4
1 parent 2c0c860
commit 5e6cff4
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 10 deletions.
diff --git a/mr/src/main/java/org/elasticsearch/hadoop/rest/Resource.java b/mr/src/main/java/org/elasticsearch/hadoop/rest/Resource.java
@@ -78,7 +78,8 @@ public Resource(Settings settings, boolean read) {
             Assert.hasText(type, "No type found; expecting [index]/[type]");
         }
         Assert.hasText(index, "No index found; expecting [index]/[type]");
-
+        Assert.isTrue(!StringUtils.hasWhitespace(index) && !StringUtils.hasWhitespace(type), "Index and type should not contain whitespaces");
+
         indexAndType = index + "/" + type;
 
         // check bulk

diff --git a/mr/src/main/java/org/elasticsearch/hadoop/util/StringUtils.java b/mr/src/main/java/org/elasticsearch/hadoop/util/StringUtils.java
@@ -92,6 +92,19 @@ public static boolean hasText(CharSequence sequence) {
         return false;
     }
 
+    public static boolean hasWhitespace(CharSequence sequence) {
+        if (!hasLength(sequence)) {
+            return false;
+        }
+        int length = sequence.length();
+        for (int i = 0; i < length; i++) {
+            if (Character.isWhitespace(sequence.charAt(i))) {
+                return true;
+            }
+        }
+        return false;
+    }
+
     public static int countOccurrences(String string, String substring) {
         if (string == null || substring == null || string.length() == 0 || substring.length() == 0) {
             return 0;

diff --git a/mr/src/test/java/org/elasticsearch/hadoop/rest/ResourceTest.java b/mr/src/test/java/org/elasticsearch/hadoop/rest/ResourceTest.java
@@ -86,6 +86,11 @@ public void testLowercaseNotAllowedIfTemplateIsInvalidAgain() throws Exception {
         createResource("foo}F{/bar");
     }
 
+    @Test(expected = EsHadoopIllegalArgumentException.class)
+    public void testNoWhitespaceAllowed() throws Exception {
+        createResource("foo, bar/far");
+    }
+
     private Resource createResource(String target) {
         Settings s = new TestSettings();
         s.setProperty(ConfigurationOptions.ES_RESOURCE, target);

diff --git a/spark/core/itest/scala/org/elasticsearch/spark/integration/AbstractScalaEsSpark.scala b/spark/core/itest/scala/org/elasticsearch/spark/integration/AbstractScalaEsSpark.scala
@@ -19,21 +19,16 @@
 package org.elasticsearch.spark.integration;
 
 import java.awt.Polygon
-import java.{lang => jl}
-import java.{util => ju}
+import java.{ lang => jl }
+import java.{ util => ju }
 import java.util.concurrent.TimeUnit
 
-import scala.collection.JavaConverters._
 import scala.collection.JavaConversions.propertiesAsScalaMap
-import scala.collection.JavaConverters.asScalaBufferConverter
-import scala.collection.JavaConverters.mapAsJavaMapConverter
-
 
 import org.apache.spark.SparkConf
 import org.apache.spark.SparkContext
 import org.apache.spark.SparkException
-import org.elasticsearch.hadoop.cfg.ConfigurationOptions._
-import org.elasticsearch.hadoop.cfg.ConfigurationOptions
+import org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_INDEX_READ_MISSING_AS_EMPTY
 import org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_INPUT_JSON
 import org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_MAPPING_EXCLUDE
 import org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_MAPPING_ID
@@ -43,14 +38,14 @@ import org.elasticsearch.hadoop.cfg.ConfigurationOptions.ES_RESOURCE
 import org.elasticsearch.hadoop.mr.RestUtils
 import org.elasticsearch.hadoop.util.TestSettings
 import org.elasticsearch.hadoop.util.TestUtils
-import org.elasticsearch.spark._
 import org.elasticsearch.spark.rdd.EsSpark
 import org.elasticsearch.spark.rdd.Metadata.ID
 import org.elasticsearch.spark.rdd.Metadata.TTL
 import org.elasticsearch.spark.rdd.Metadata.VERSION
 import org.elasticsearch.spark.serialization.Bean
 import org.elasticsearch.spark.serialization.ReflectionUtils
 import org.elasticsearch.spark.sparkByteArrayJsonRDDFunctions
+import org.elasticsearch.spark.sparkContextFunctions
 import org.elasticsearch.spark.sparkPairRDDFunctions
 import org.elasticsearch.spark.sparkRDDFunctions
 import org.elasticsearch.spark.sparkStringJsonRDDFunctions
@@ -399,7 +394,14 @@ class AbstractScalaEsScalaSpark(prefix: String, readMetadata: jl.Boolean) extend
     val scRDD = sc.esRDD(target, qjson)
     assertEquals(esRDD.collect().size, scRDD.collect().size)
   }
+
 
+  @Test
+  def testMultiIndexNonExisting() {
+    val rdd = EsSpark.esJsonRDD(sc, "bumpA,Stump", Map(ES_INDEX_READ_MISSING_AS_EMPTY -> "yes"))
+    assertEquals(0, rdd.count)
+  }
+
   //@Test
   def testLoadJsonFile() {
     val target = "lost/id"