Move the ingest attachment processor to the default distribution

benchmarks/src/main/resources/org/elasticsearch/benchmark/xcontent/monitor_cluster_stats.json

@@ -298,16 +298,6 @@
           "extended_plugins" : [ ],
           "has_native_controller" : false
         },
-        {
-          "name" : "ingest-attachment",
-          "version" : "7.10.0",
-          "elasticsearch_version" : "7.10.0",
-          "java_version" : "1.8",
-          "description" : "Ingest processor that uses Apache Tika to extract contents",
-          "classname" : "org.elasticsearch.ingest.attachment.IngestAttachmentPlugin",
-          "extended_plugins" : [ ],
-          "has_native_controller" : false
-        },
         {
           "name" : "mapper-murmur3",
           "version" : "7.10.0",

build-tools-internal/version.properties

@@ -24,7 +24,7 @@ netty             = 4.1.77.Final
 commons_lang3                   = 3.9
 
 # when updating this version, you need to ensure compatibility with:
-#  - plugins/ingest-attachment (transitive dependency, check the upstream POM)
+#  - modules/ingest-attachment (transitive dependency, check the upstream POM)
 #  - distribution/tools/plugin-cli
 #  - x-pack/plugin/security
 bouncycastle=1.64

distribution/tools/plugin-cli/src/main/java/org/elasticsearch/plugins/cli/InstallPluginAction.java

@@ -159,7 +159,12 @@ public class InstallPluginAction implements Closeable {
      * maintained so that existing user workflows that install these plugins do not need to be updated
      * immediately.
      */
-    public static final Set<String> PLUGINS_CONVERTED_TO_MODULES = Set.of("repository-azure", "repository-gcs", "repository-s3");
+    public static final Set<String> PLUGINS_CONVERTED_TO_MODULES = Set.of(
+        "repository-azure",
+        "repository-gcs",
+        "repository-s3",
+        "ingest-attachment"
+    );
 
     static final Set<PosixFilePermission> BIN_DIR_PERMS;
     static final Set<PosixFilePermission> BIN_FILES_PERMS;

distribution/tools/plugin-cli/src/test/java/org/elasticsearch/plugins/cli/InstallPluginActionTests.java

@@ -1503,7 +1503,7 @@ public void testMultipleJars() throws Exception {
      * instead simply print a message to the terminal.
      */
     public void testInstallMigratedPlugins() throws Exception {
-        for (String id : List.of("repository-azure", "repository-gcs", "repository-s3")) {
+        for (String id : List.of("repository-azure", "repository-gcs", "repository-s3", "ingest-attachment")) {
             installPlugin(id);
             assertThat(terminal.getErrorOutput(), containsString("[" + id + "] is no longer a plugin"));
         }

docs/build.gradle

@@ -25,9 +25,9 @@ ext.docsFileTree = fileTree(projectDir) {
   // Broken code snippet tests
   exclude 'reference/graph/explore.asciidoc'
   if (BuildParams.inFipsJvm) {
-    // We don't install/support this plugin in FIPS 140
-    exclude 'plugins/ingest-attachment.asciidoc'
-    // We can't conditionally control output, this would be missing the ingest-attachment plugin
+    // We don't support this component in FIPS 140
+    exclude 'reference/ingest/processors/attachment.asciidoc'
+    // We can't conditionally control output, this would be missing the ingest-attachment component
     exclude 'reference/cat/plugins.asciidoc'
   }
 }
@@ -105,7 +105,7 @@ testClusters.matching { it.name == "yamlRestTest"}.configureEach {
       return
     }
     // Do not install ingest-attachment in a FIPS 140 JVM as this is not supported
-    if (subproj.path.startsWith(':plugins:ingest-attachment') && BuildParams.inFipsJvm) {
+    if (subproj.path.startsWith(':modules:ingest-attachment') && BuildParams.inFipsJvm) {
       return
     }
     plugin subproj.path

docs/changelog/87989.yaml

@@ -0,0 +1,5 @@
+pr: 87989
+summary: Move the ingest attachment processor to the default distribution
+area: Ingest
+type: enhancement
+issues: []

docs/plugins/index.asciidoc

@@ -44,8 +44,6 @@ include::analysis.asciidoc[]
 
 include::discovery.asciidoc[]
 
-include::ingest.asciidoc[]
-
 include::mapper.asciidoc[]
 
 include::repository.asciidoc[]

docs/plugins/redirects.asciidoc

@@ -145,3 +145,17 @@ include::redirects.asciidoc[tag=gcs-repo-migration]
 === Google Cloud Storage repository plugin
 
 include::redirects.asciidoc[tag=gcs-repo-migration]
+
+[role="exclude",id="ingest-attachment"]
+=== Ingest Attachment plugin
+
+// tag::ingest-attachment-migration[]
+The Ingest Attachment plugin is now included in {es}.
+See the {ref}/attachment.html[Ingest Attachment] processor.
+// end::ingest-attachment-migration[]
+
+[role="exclude",id="ingest"]
+=== Ingest plugins
+
+All ingest functionality has been moved into the default distribution.
+For more information refer to the {ref}/processors.html[existing processors].

docs/reference/cat/plugins.asciidoc

@@ -7,8 +7,8 @@
 
 [IMPORTANT]
 ====
-cat APIs are only intended for human consumption using the command line or {kib} 
-console. They are _not_ intended for use by applications. For application 
+cat APIs are only intended for human consumption using the command line or {kib}
+console. They are _not_ intended for use by applications. For application
 consumption, use the <<cluster-nodes-info,nodes info API>>.
 ====
 
@@ -67,7 +67,6 @@ U7321H6 analysis-ukrainian      {version_qualified} The Ukrainian Analysis plugi
 U7321H6 discovery-azure-classic {version_qualified} The Azure Classic Discovery plugin allows to use Azure Classic API for the unicast discovery mechanism
 U7321H6 discovery-ec2           {version_qualified} The EC2 discovery plugin allows to use AWS API for the unicast discovery mechanism.
 U7321H6 discovery-gce           {version_qualified} The Google Compute Engine (GCE) Discovery plugin allows to use GCE API for the unicast discovery mechanism.
-U7321H6 ingest-attachment       {version_qualified} Ingest processor that uses Apache Tika to extract contents
 U7321H6 mapper-annotated-text   {version_qualified} The Mapper Annotated_text plugin adds support for text fields with markup used to inject annotation tokens into the index.
 U7321H6 mapper-murmur3          {version_qualified} The Mapper Murmur3 plugin allows to compute hashes of a field's values at index-time and to store them in the index.
 U7321H6 mapper-size             {version_qualified} The Mapper Size plugin allows document to record their uncompressed size at index time.

docs/reference/ingest/processors.asciidoc

@@ -29,10 +29,11 @@ installed.
 
 [source,yaml]
 ----
-plugin.mandatory: ingest-attachment
+plugin.mandatory: my-ingest-plugin
 ----
 
 include::processors/append.asciidoc[]
+include::processors/attachment.asciidoc[]
 include::processors/bytes.asciidoc[]
 include::processors/circle.asciidoc[]
 include::processors/community-id.asciidoc[]

docs/plugins/ingest-attachment.asciidoc → docs/reference/ingest/processors/attachment.asciidoc

@@ -1,23 +1,21 @@
-[[ingest-attachment]]
-=== Ingest Attachment Processor Plugin
+[[attachment]]
+=== Attachment processor
+++++
+<titleabbrev>Attachment</titleabbrev>
+++++
 
-The ingest attachment plugin lets Elasticsearch extract file attachments in common formats (such as PPT, XLS, and PDF) by
+The attachment processor lets Elasticsearch extract file attachments in common formats (such as PPT, XLS, and PDF) by
 using the Apache text extraction library https://tika.apache.org/[Tika].
 
-You can use the ingest attachment plugin as a replacement for the mapper attachment plugin.
-
 The source field must be a base64 encoded binary. If you do not want to incur
 the overhead of converting back and forth between base64, you can use the CBOR
 format instead of JSON and specify the field as a bytes array instead of a string
 representation. The processor will skip the base64 decoding then.
 
-:plugin_name: ingest-attachment
-include::install_remove.asciidoc[]
-
-[[using-ingest-attachment]]
-==== Using the Attachment Processor in a Pipeline
+[[using-attachment]]
+==== Using the attachment processor in a pipeline
 
-[[ingest-attachment-options]]
+[[attachment-options]]
 .Attachment options
 [options="header"]
 |======
@@ -33,7 +31,7 @@ include::install_remove.asciidoc[]
 |======
 
 [discrete]
-[[ingest-attachment-json-ex]]
+[[attachment-json-ex]]
 ==== Example
 
 If attaching files to JSON documents, you must first encode the file as a base64
@@ -98,7 +96,7 @@ The document's `attachment` object contains extracted properties for the file:
 NOTE: Keeping the binary as a field within the document might consume a lot of resources. It is highly recommended
       to remove that field from the document. Set `remove_binary` to `true` to automatically remove the field.
 
-[[ingest-attachment-fields]]
+[[attachment-fields]]
 ==== Exported fields
 
 The fields which might be extracted from a document are:
@@ -154,7 +152,7 @@ NOTE: Extracting contents from binary data is a resource intensive operation and
       consumes a lot of resources. It is highly recommended to run pipelines
       using this processor in a dedicated ingest node.
 
-[[ingest-attachment-cbor]]
+[[attachment-cbor]]
 ==== Use the attachment processor with CBOR
 
 To avoid encoding and decoding JSON to base64, you can instead pass CBOR data to
@@ -201,7 +199,7 @@ with open(file, 'rb') as f:
   )
 ----
 
-[[ingest-attachment-extracted-chars]]
+[[attachment-extracted-chars]]
 ==== Limit the number of extracted chars
 
 To prevent extracting too many chars and overload the node memory, the number of chars being used for extraction
@@ -310,8 +308,8 @@ Returns this:
 // TESTRESPONSE[s/"_seq_no": \d+/"_seq_no" : $body._seq_no/ s/"_primary_term" : 1/"_primary_term" : $body._primary_term/]
 
 
-[[ingest-attachment-with-arrays]]
-==== Using the Attachment Processor with arrays
+[[attachment-with-arrays]]
+==== Using the attachment processor with arrays
 
 To use the attachment processor within an array of attachments the
 {ref}/foreach-processor.html[foreach processor] is required. This

docs/reference/redirects.asciidoc

@@ -1867,4 +1867,4 @@ For more information about reindexing from a remote cluster, refer to
 [role="exclude",id="infer-trained-model-deployment"]
 === Infer trained model deployment API
 
-See <<infer-trained-model>>.
+See <<infer-trained-model>>.

modules/ingest-attachment/licenses/commons-codec-NOTICE.txt

@@ -0,0 +1,17 @@
+Apache Commons Codec
+Copyright 2002-2015 The Apache Software Foundation
+
+This product includes software developed at
+The Apache Software Foundation (http://www.apache.org/).
+
+src/test/org/apache/commons/codec/language/DoubleMetaphoneTest.java
+contains test data from http://aspell.net/test/orig/batch0.tab.
+Copyright (C) 2002 Kevin Atkinson (kevina@gnu.org)
+
+===============================================================================
+
+The content of package org.apache.commons.codec.language.bm has been translated
+from the original php source code available at http://stevemorse.org/phoneticinfo.htm
+with permission from the original authors.
+Original source copyright:
+Copyright (c) 2008 Alexander Beider & Stephen P. Morse.