Ignore encrypted documents

Original request:
        I am sending multiple pdf, word etc. attachments in one documents to be indexed.

        Some of them (pdf) are encrypted and I am getting a MapperParsingException caused by org.apache.tika.exception.TikaException: Unable to extract PDF content cause by
        org.apache.pdfbox.exceptions.WrappedIOException: Error decrypting document.

        I was wondering if the attachment mapper could expose some switch to ignore the documents it can not extract?

 As we now have option `ignore_errors`, we can support it. See #38 relative to this option.

Closes #18.
This commit is contained in:
David Pilato 2013-08-20 18:31:06 +02:00
parent d6aa2f0615
commit b35ad804df
5 changed files with 270 additions and 1 deletions

View File

@ -356,7 +356,9 @@ public class AttachmentMapper implements Mapper {
// Set the maximum length of strings returned by the parseToString method, -1 sets no limit // Set the maximum length of strings returned by the parseToString method, -1 sets no limit
parsedContent = tika().parseToString(new BytesStreamInput(content, false), metadata, indexedChars); parsedContent = tika().parseToString(new BytesStreamInput(content, false), metadata, indexedChars);
} catch (Throwable e) { } catch (Throwable e) {
throw new MapperParsingException("Failed to extract [" + indexedChars + "] characters of text for [" + name + "]", e); // #18: we could ignore errors when Tika does not parse data
if (!ignoreErrors) throw new MapperParsingException("Failed to extract [" + indexedChars + "] characters of text for [" + name + "]", e);
return;
} }
context.externalValue(parsedContent); context.externalValue(parsedContent);

View File

@ -0,0 +1,130 @@
package org.elasticsearch.index.mapper.xcontent;
import org.apache.lucene.document.Document;
import org.elasticsearch.common.bytes.BytesReference;
import org.elasticsearch.common.settings.ImmutableSettings;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.analysis.AnalysisService;
import org.elasticsearch.index.mapper.DocumentMapper;
import org.elasticsearch.index.mapper.DocumentMapperParser;
import org.elasticsearch.index.mapper.MapperParsingException;
import org.elasticsearch.index.mapper.attachment.AttachmentMapper;
import org.testng.annotations.Test;
import java.io.IOException;
import static org.elasticsearch.common.io.Streams.copyToBytesFromClasspath;
import static org.elasticsearch.common.io.Streams.copyToStringFromClasspath;
import static org.elasticsearch.common.xcontent.XContentFactory.jsonBuilder;
import static org.hamcrest.MatcherAssert.assertThat;
import static org.hamcrest.Matchers.*;
/**
* Test for https://github.com/elasticsearch/elasticsearch-mapper-attachments/issues/18
* Note that we have converted /org/elasticsearch/index/mapper/xcontent/testContentLength.txt
* to a /org/elasticsearch/index/mapper/xcontent/encrypted.pdf with password `12345678`.
*/
public class EncryptedDocMapperTest {
@Test
public void testMultipleDocsEncryptedLast() throws IOException {
DocumentMapperParser mapperParser = new DocumentMapperParser(new Index("test"), new AnalysisService(new Index("test")), null, null);
mapperParser.putTypeParser(AttachmentMapper.CONTENT_TYPE, new AttachmentMapper.TypeParser());
String mapping = copyToStringFromClasspath("/org/elasticsearch/index/mapper/multipledocs/test-mapping.json");
DocumentMapper docMapper = mapperParser.parse(mapping);
byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/htmlWithValidDateMeta.html");
byte[] pdf = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/encrypted.pdf");
BytesReference json = jsonBuilder()
.startObject()
.field("_id", 1)
.field("file1", html)
.field("file2", pdf)
.endObject().bytes();
Document doc = docMapper.parse(json).rootDoc();
assertThat(doc.get(docMapper.mappers().smartName("file1").mapper().names().indexName()), containsString("World"));
assertThat(doc.get(docMapper.mappers().smartName("file1.title").mapper().names().indexName()), equalTo("Hello"));
assertThat(doc.get(docMapper.mappers().smartName("file1.author").mapper().names().indexName()), equalTo("kimchy"));
assertThat(doc.get(docMapper.mappers().smartName("file1.keywords").mapper().names().indexName()), equalTo("elasticsearch,cool,bonsai"));
assertThat(doc.get(docMapper.mappers().smartName("file1.content_type").mapper().names().indexName()), equalTo("text/html; charset=ISO-8859-1"));
assertThat(doc.getField(docMapper.mappers().smartName("file1.content_length").mapper().names().indexName()).numericValue().longValue(), is(344L));
assertThat(doc.get(docMapper.mappers().smartName("file2").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2.title").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2.author").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2.keywords").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2.content_type").mapper().names().indexName()), nullValue());
assertThat(doc.getField(docMapper.mappers().smartName("file2.content_length").mapper().names().indexName()), nullValue());
}
@Test
public void testMultipleDocsEncryptedFirst() throws IOException {
DocumentMapperParser mapperParser = new DocumentMapperParser(new Index("test"), new AnalysisService(new Index("test")), null, null);
mapperParser.putTypeParser(AttachmentMapper.CONTENT_TYPE, new AttachmentMapper.TypeParser());
String mapping = copyToStringFromClasspath("/org/elasticsearch/index/mapper/multipledocs/test-mapping.json");
DocumentMapper docMapper = mapperParser.parse(mapping);
byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/htmlWithValidDateMeta.html");
byte[] pdf = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/encrypted.pdf");
BytesReference json = jsonBuilder()
.startObject()
.field("_id", 1)
.field("file1", pdf)
.field("file2", html)
.endObject().bytes();
Document doc = docMapper.parse(json).rootDoc();
assertThat(doc.get(docMapper.mappers().smartName("file1").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.title").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.author").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.keywords").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.content_type").mapper().names().indexName()), nullValue());
assertThat(doc.getField(docMapper.mappers().smartName("file1.content_length").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2").mapper().names().indexName()), containsString("World"));
assertThat(doc.get(docMapper.mappers().smartName("file2.title").mapper().names().indexName()), equalTo("Hello"));
assertThat(doc.get(docMapper.mappers().smartName("file2.author").mapper().names().indexName()), equalTo("kimchy"));
assertThat(doc.get(docMapper.mappers().smartName("file2.keywords").mapper().names().indexName()), equalTo("elasticsearch,cool,bonsai"));
assertThat(doc.get(docMapper.mappers().smartName("file2.content_type").mapper().names().indexName()), equalTo("text/html; charset=ISO-8859-1"));
assertThat(doc.getField(docMapper.mappers().smartName("file2.content_length").mapper().names().indexName()).numericValue().longValue(), is(344L));
}
@Test(expectedExceptions = MapperParsingException.class)
public void testMultipleDocsEncryptedNotIgnoringErrors() throws IOException {
DocumentMapperParser mapperParser = new DocumentMapperParser(new Index("test"),
ImmutableSettings.builder().put("index.mapping.attachment.ignore_errors", false).build(),
new AnalysisService(new Index("test")), null, null);
mapperParser.putTypeParser(AttachmentMapper.CONTENT_TYPE, new AttachmentMapper.TypeParser());
String mapping = copyToStringFromClasspath("/org/elasticsearch/index/mapper/multipledocs/test-mapping.json");
DocumentMapper docMapper = mapperParser.parse(mapping);
byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/htmlWithValidDateMeta.html");
byte[] pdf = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/encrypted.pdf");
BytesReference json = jsonBuilder()
.startObject()
.field("_id", 1)
.field("file1", pdf)
.field("file2", html)
.endObject().bytes();
Document doc = docMapper.parse(json).rootDoc();
assertThat(doc.get(docMapper.mappers().smartName("file1").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.title").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.author").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.keywords").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file1.content_type").mapper().names().indexName()), nullValue());
assertThat(doc.getField(docMapper.mappers().smartName("file1.content_length").mapper().names().indexName()), nullValue());
assertThat(doc.get(docMapper.mappers().smartName("file2").mapper().names().indexName()), containsString("World"));
assertThat(doc.get(docMapper.mappers().smartName("file2.title").mapper().names().indexName()), equalTo("Hello"));
assertThat(doc.get(docMapper.mappers().smartName("file2.author").mapper().names().indexName()), equalTo("kimchy"));
assertThat(doc.get(docMapper.mappers().smartName("file2.keywords").mapper().names().indexName()), equalTo("elasticsearch,cool,bonsai"));
assertThat(doc.get(docMapper.mappers().smartName("file2.content_type").mapper().names().indexName()), equalTo("text/html; charset=ISO-8859-1"));
assertThat(doc.getField(docMapper.mappers().smartName("file2.content_length").mapper().names().indexName()).numericValue().longValue(), is(344L));
}
}

View File

@ -0,0 +1,125 @@
/*
* Licensed to ElasticSearch and Shay Banon under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. ElasticSearch 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.elasticsearch.plugin.mapper.attachments.test;
import org.elasticsearch.action.admin.cluster.health.ClusterHealthResponse;
import org.elasticsearch.action.admin.cluster.health.ClusterHealthStatus;
import org.elasticsearch.action.count.CountResponse;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.elasticsearch.common.network.NetworkUtils;
import org.elasticsearch.common.settings.ImmutableSettings;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.mapper.MapperParsingException;
import org.elasticsearch.node.Node;
import org.testng.annotations.AfterClass;
import org.testng.annotations.AfterMethod;
import org.testng.annotations.BeforeClass;
import org.testng.annotations.Test;
import static org.elasticsearch.client.Requests.*;
import static org.elasticsearch.common.io.Streams.copyToBytesFromClasspath;
import static org.elasticsearch.common.io.Streams.copyToStringFromClasspath;
import static org.elasticsearch.common.settings.ImmutableSettings.settingsBuilder;
import static org.elasticsearch.common.xcontent.XContentFactory.jsonBuilder;
import static org.elasticsearch.index.query.QueryBuilders.fieldQuery;
import static org.elasticsearch.node.NodeBuilder.nodeBuilder;
import static org.hamcrest.MatcherAssert.assertThat;
import static org.hamcrest.Matchers.equalTo;
/**
* Test case for issue https://github.com/elasticsearch/elasticsearch-mapper-attachments/issues/18
*/
@Test
public class MultipleAttachmentIntegrationTests {
private final ESLogger logger = Loggers.getLogger(getClass());
private Node node;
@BeforeClass
public void setupServer() {
node = nodeBuilder().local(true).settings(settingsBuilder()
.put("path.data", "target/data")
.put("cluster.name", "test-cluster-" + NetworkUtils.getLocalAddress())
.put("gateway.type", "none")).node();
}
@AfterClass
public void closeServer() {
node.close();
}
private void createIndex(Settings settings) {
logger.info("creating index [test]");
node.client().admin().indices().create(createIndexRequest("test").settings(settingsBuilder().put("index.numberOfReplicas", 0).put(settings))).actionGet();
logger.info("Running Cluster Health");
ClusterHealthResponse clusterHealth = node.client().admin().cluster().health(clusterHealthRequest().waitForGreenStatus()).actionGet();
logger.info("Done Cluster Health, status " + clusterHealth.getStatus());
assertThat(clusterHealth.isTimedOut(), equalTo(false));
assertThat(clusterHealth.getStatus(), equalTo(ClusterHealthStatus.GREEN));
}
@AfterMethod
public void deleteIndex() {
logger.info("deleting index [test]");
node.client().admin().indices().delete(deleteIndexRequest("test")).actionGet();
}
/**
* When we want to ignore errors (default)
*/
@Test
public void testMultipleAttachmentsWithEncryptedDoc() throws Exception {
createIndex(ImmutableSettings.builder().build());
String mapping = copyToStringFromClasspath("/org/elasticsearch/index/mapper/multipledocs/test-mapping.json");
byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/htmlWithValidDateMeta.html");
byte[] pdf = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/encrypted.pdf");
node.client().admin().indices().putMapping(putMappingRequest("test").type("person").source(mapping)).actionGet();
node.client().index(indexRequest("test").type("person")
.source(jsonBuilder().startObject().field("file1", html).field("file2", pdf).field("hello","world").endObject())).actionGet();
node.client().admin().indices().refresh(refreshRequest()).actionGet();
CountResponse countResponse = node.client().count(countRequest("test").query(fieldQuery("file1", "World"))).actionGet();
assertThat(countResponse.getCount(), equalTo(1l));
countResponse = node.client().count(countRequest("test").query(fieldQuery("hello", "World"))).actionGet();
assertThat(countResponse.getCount(), equalTo(1l));
}
/**
* When we don't want to ignore errors
*/
@Test(expectedExceptions = MapperParsingException.class)
public void testMultipleAttachmentsWithEncryptedDocNotIgnoringErrors() throws Exception {
createIndex(ImmutableSettings.builder().put("index.mapping.attachment.ignore_errors", false).build());
String mapping = copyToStringFromClasspath("/org/elasticsearch/index/mapper/multipledocs/test-mapping.json");
byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/htmlWithValidDateMeta.html");
byte[] pdf = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/xcontent/encrypted.pdf");
node.client().admin().indices()
.putMapping(putMappingRequest("test").type("person").source(mapping)).actionGet();
node.client().index(indexRequest("test").type("person")
.source(jsonBuilder().startObject().field("file1", html).field("file2", pdf).field("hello","world").endObject())).actionGet();
}
}

View File

@ -0,0 +1,12 @@
{
"person":{
"properties":{
"file1":{
"type":"attachment"
},
"file2":{
"type":"attachment"
}
}
}
}