This is an automated email from the ASF dual-hosted git repository.
tballison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 7ca4d6eea9 TIKA-4842 - update docs and javadocs post 4.0.0 release
(#3074)
7ca4d6eea9 is described below
commit 7ca4d6eea9a224355c6fa72bef810fc95b37f7f7
Author: Tim Allison <[email protected]>
AuthorDate: Wed Aug 26 12:23:40 2026 -0400
TIKA-4842 - update docs and javadocs post 4.0.0 release (#3074)
---
CHANGES.txt | 18 ++++++++++++++++++
docs/modules/ROOT/pages/configuration/index.adoc | 5 +++--
.../ROOT/pages/configuration/metadata-filters.adoc | 6 ++++--
.../pages/configuration/parsers/tess4j-parser.adoc | 5 ++++-
docs/modules/ROOT/pages/developers/serialization.adoc | 6 +++---
.../ROOT/pages/maintainers/release-guides/tika.adoc | 18 +++++++++---------
docs/modules/ROOT/pages/migration-to-4x/index.adoc | 4 ++--
.../pages/migration-to-4x/metadata-changes-4x.adoc | 4 +++-
.../ROOT/pages/migration-to-4x/migrating-to-4x.adoc | 9 ++++++---
.../ROOT/pages/pipes/plugins/elasticsearch.adoc | 4 ++--
docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc | 2 +-
docs/modules/ROOT/pages/pipes/plugins/kafka.adoc | 4 ++--
docs/modules/ROOT/pages/pipes/plugins/opensearch.adoc | 4 ++--
docs/modules/ROOT/pages/pipes/plugins/solr.adoc | 6 ++++--
.../ROOT/pages/pipes/plugins/writing-a-plugin.adoc | 8 +++++---
docs/modules/ROOT/pages/pipes/unpack-config.adoc | 2 +-
docs/modules/ROOT/pages/using-tika/docker.adoc | 4 +++-
tika-ml/tika-ml-junkdetect-tools/pom.xml | 5 +++--
.../tika/ml/junkdetect/JunkFilterEncodingDetector.java | 11 +++++------
.../apache/tika/parser/ocr/tess4j/Tess4JConfig.java | 7 ++++---
.../org/apache/tika/parser/ocr/ImagePreprocessor.java | 2 +-
.../org/apache/tika/parser/ocr/TesseractOCRConfig.java | 4 ----
.../atlassianjwt/AtlassianJwtFetcherFactory.java | 4 ++--
.../tika/pipes/emitter/azblob/AZBlobEmitter.java | 4 ++--
.../pipes/emitter/azblob/AZBlobEmitterFactory.java | 4 ++--
.../pipes/fetcher/azblob/AZBlobFetcherFactory.java | 4 ++--
.../apache/tika/pipes/emitter/es/ESEmitterFactory.java | 4 ++--
.../pipes/emitter/fs/FileSystemEmitterFactory.java | 4 ++--
.../pipes/fetcher/fs/FileSystemFetcherFactory.java | 4 ++--
.../org/apache/tika/pipes/emitter/gcs/GCSEmitter.java | 4 ++--
.../tika/pipes/emitter/gcs/GCSEmitterFactory.java | 4 ++--
.../tika/pipes/fetcher/gcs/GCSFetcherFactory.java | 4 ++--
.../fetcher/googledrive/GoogleDriveFetcherFactory.java | 4 ++--
.../tika/pipes/fetcher/http/HttpFetcherFactory.java | 4 ++--
.../apache/tika/pipes/emitter/jdbc/JDBCEmitter.java | 4 ++--
.../tika/pipes/emitter/jdbc/JDBCEmitterFactory.java | 4 ++--
.../apache/tika/pipes/emitter/kafka/KafkaEmitter.java | 4 ++--
.../tika/pipes/emitter/kafka/KafkaEmitterFactory.java | 4 ++--
.../microsoftgraph/MicrosoftGraphFetcherFactory.java | 4 ++--
.../emitter/opensearch/OpenSearchEmitterFactory.java | 4 ++--
.../org/apache/tika/pipes/emitter/s3/S3Emitter.java | 4 ++--
.../apache/tika/pipes/emitter/s3/S3EmitterFactory.java | 4 ++--
.../apache/tika/pipes/fetcher/s3/S3FetcherFactory.java | 4 ++--
.../apache/tika/pipes/emitter/solr/SolrEmitter.java | 4 ++--
.../tika/pipes/emitter/solr/SolrEmitterFactory.java | 4 ++--
45 files changed, 131 insertions(+), 99 deletions(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index 9b7edca602..c5ad109272 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,23 @@
Release 4.1.0 - unreleased
+ * Documentation: corrected a batch of pages and javadocs that contradicted
+ the code. Notably: the ES/OpenSearch attachmentStrategy has no default
+ (unset means embedded documents get neither the parent field nor the
+ parent/child relation); Kafka's connectionsMaxIdleMs is passed to the
+ producer, not ignored; jdbc queryTimeoutSeconds is applied only when > 0,
+ so 0 does not mean "no limit"; the Solr emitter/iterator support only
+ basic auth, not ntlm, and only when a userName is set; pipes-reporters
+ silently loads zero reporters when given a JSON array, and
+ pipes-iterator/pipes-reporters instances are built at config load rather
+ than lazily; under CONTENT_ONLY only a parse-context filter replaces the
+ built-in one, not the top-level metadata-filters chain;
+ _mime-include/_mime-exclude also accept a bare string; Tess4J locks
+ poolSize and maxImagePixels as well as the two paths. Also corrected the
+ config nesting shown in every pipes-plugin fetcher/emitter javadoc -- 23
+ of them, which had it inverted (the instance id is the outer key, the
+ component name the inner) -- and removed references to a
+ TesseractOCRConfig.properties file that 4.x does not load (TIKA-4842).
+
* Pipes plugins no longer bundle their own Jackson: jackson-core, -databind
and -annotations are provided by the host (tika-serialization) and the
plugins parent pom now bans bundling them, so a mapper can cross the
diff --git a/docs/modules/ROOT/pages/configuration/index.adoc
b/docs/modules/ROOT/pages/configuration/index.adoc
index 0ddf7048e1..9d1407a603 100644
--- a/docs/modules/ROOT/pages/configuration/index.adoc
+++ b/docs/modules/ROOT/pages/configuration/index.adoc
@@ -81,8 +81,9 @@ produces no error and no effect:
read;
* the body of a self-configuring component under `parse-context` — it is
handed to the component
untouched;
-* `_mime-include` / `_mime-exclude` when the value is not a JSON array — a
shape error yields an
- empty filter rather than a failure;
+* `_mime-include` / `_mime-exclude` when the value is neither a JSON array nor
a string — a bare
+ string is read as a one-element list, but any other shape yields an empty
filter rather than a
+ failure;
* a non-textual entry inside `default-parser`'s `exclude` list — the list
expects plain strings,
so an object or array entry such as `[{"pdf-parser": {}}]` is skipped and
the component stays
enabled. (An *unregistered name* in that list, and an unknown *key* in that
same block, are
diff --git a/docs/modules/ROOT/pages/configuration/metadata-filters.adoc
b/docs/modules/ROOT/pages/configuration/metadata-filters.adoc
index c6eee220fa..c7b1eeae30 100644
--- a/docs/modules/ROOT/pages/configuration/metadata-filters.adoc
+++ b/docs/modules/ROOT/pages/configuration/metadata-filters.adoc
@@ -235,8 +235,10 @@ one for that request rather than adding to it.
NOTE: In `CONTENT_ONLY` xref:pipes/parse-modes.adoc[parse mode], Tika applies
an
`include-field-metadata-filter` for `tk:content` and
`tk:exception:container-exception` when you have
-configured no filter of your own. Configure one and yours wins — including
having to keep
-`tk:content` yourself.
+configured no filter of your own. Only a filter that reaches the
`parse-context` replaces it —
+whether from the request or from the `parse-context` block of the server's own
config — and then
+you are responsible for keeping `tk:content` yourself. The top-level
`metadata-filters` chain this
+page documents is not consulted in this mode.
== Writing your own
diff --git a/docs/modules/ROOT/pages/configuration/parsers/tess4j-parser.adoc
b/docs/modules/ROOT/pages/configuration/parsers/tess4j-parser.adoc
index 3f37619dba..882abbbca4 100644
--- a/docs/modules/ROOT/pages/configuration/parsers/tess4j-parser.adoc
+++ b/docs/modules/ROOT/pages/configuration/parsers/tess4j-parser.adoc
@@ -273,4 +273,7 @@ context.set(Tess4JConfig.class, override);
NOTE: In caller-supplied JSON config — the tika-server `/config` endpoints,
tika-grpc's
`parse_context_json` — `dataPath` and `nativeLibPath` are locked at parser
initialization, and
setting either throws `TikaConfigException`. They point at native code, so a
caller must not be
-able to move them.
+able to move them. `poolSize` and `maxImagePixels` are locked in the same way
but throw
+`IllegalStateException` -- for different reasons. The OCR pool is sized at
initialization and
+cannot be resized per parse. `maxImagePixels` *is* read per parse, but it is
the guard that
+bounds image decode against OOM, so a caller must not be able to raise it.
diff --git a/docs/modules/ROOT/pages/developers/serialization.adoc
b/docs/modules/ROOT/pages/developers/serialization.adoc
index ecd0612424..35dde82a26 100644
--- a/docs/modules/ROOT/pages/developers/serialization.adoc
+++ b/docs/modules/ROOT/pages/developers/serialization.adoc
@@ -190,7 +190,7 @@ it needs it. `Parser` extends `SelfConfiguring`, so every
parser is self-configu
[source,java]
----
@TikaComponent
-public class PDFParser implements Parser {
+public class PDFParser implements Parser, RenderingParser {
private final PDFParserConfig defaultConfig = new PDFParserConfig();
@@ -276,8 +276,8 @@ the allowlist constrains.
}
----
-That fails with "Unrecognized parse-context entry 'java.lang.Runtime'" — the
class
-is not registered.
+That fails with "Unrecognized parse-context entry 'java.lang.Runtime'. Check
for a typo; it does
+not match any registered component."
=== Untrusted (Wire) Input: Restricted Mode
diff --git a/docs/modules/ROOT/pages/maintainers/release-guides/tika.adoc
b/docs/modules/ROOT/pages/maintainers/release-guides/tika.adoc
index 6777c315f4..1f5be0b337 100644
--- a/docs/modules/ROOT/pages/maintainers/release-guides/tika.adoc
+++ b/docs/modules/ROOT/pages/maintainers/release-guides/tika.adoc
@@ -37,16 +37,16 @@ Before starting the release, run vulnerability and
dependency audits:
[source,bash]
----
# Identify vulnerable dependencies (add -Possindex-fail to fail the build on
findings)
-mvn ossindex:audit
+./mvnw ossindex:audit
# Check for outdated plugins
-mvn versions:display-plugin-updates
+./mvnw versions:display-plugin-updates
# Check for outdated dependencies
-mvn versions:display-dependency-updates
+./mvnw versions:display-dependency-updates
# Run full regression tests
-mvn -Papache-release clean verify
+./mvnw -Papache-release clean verify
----
== Release Process
@@ -83,7 +83,7 @@ Run the Apache RAT plugin to verify all files have proper
license headers:
[source,bash]
----
-mvn apache-rat:check
+./mvnw apache-rat:check
----
=== Step 5: Commit Changes
@@ -112,7 +112,7 @@ Execute the Maven release prepare goal:
[source,bash]
----
-mvn release:prepare
+./mvnw release:prepare
----
This will prompt you to confirm:
@@ -141,7 +141,7 @@ Execute the Maven release perform goal:
[source,bash]
----
-mvn release:perform -Darguments="-DskipITs"
+./mvnw release:perform -Darguments="-DskipITs"
----
`-DskipITs` skips integration tests during the inner build. Tests already
@@ -315,7 +315,7 @@ module that failed rather than starting over:
[source,bash]
----
cd target/checkout
-mvn deploy -Papache-release -rf :<failed-module> -DskipITs
+./mvnw deploy -Papache-release -rf :<failed-module> -DskipITs
----
If the failure was after all modules deployed and only the root-pom dist
staging
@@ -324,7 +324,7 @@ needs re-running:
[source,bash]
----
cd target/checkout
-mvn deploy --non-recursive -Papache-release -Dmaven.deploy.skip=true
+./mvnw deploy --non-recursive -Papache-release -Dmaven.deploy.skip=true
----
`--non-recursive` runs only the root pom, so the antrun fires with the right
diff --git a/docs/modules/ROOT/pages/migration-to-4x/index.adoc
b/docs/modules/ROOT/pages/migration-to-4x/index.adoc
index 692dce595e..d7f5959963 100644
--- a/docs/modules/ROOT/pages/migration-to-4x/index.adoc
+++ b/docs/modules/ROOT/pages/migration-to-4x/index.adoc
@@ -25,8 +25,8 @@ Guides and background for upgrading from Apache Tika 3.x.
SPI signatures, JSON configuration, and the API changes every upgrader hits
* xref:migration-to-4x/migrating-tika-server-4x.adoc[Tika Server Migration] --
endpoint,
wire-format, and configuration changes in tika-server 4.x
-* xref:migration-to-4x/metadata-changes-4x.adoc[Metadata Changes] -- the full
3.x -> 4.x
- key rename tables and the reserved-key write guard
+* xref:migration-to-4x/metadata-changes-4x.adoc[Metadata Changes] -- the 3.x
-> 4.x key rename
+ tables, summarised by prefix, and the reserved-key write guard
== Background Documentation
diff --git a/docs/modules/ROOT/pages/migration-to-4x/metadata-changes-4x.adoc
b/docs/modules/ROOT/pages/migration-to-4x/metadata-changes-4x.adoc
index 70e5bb0b2d..3edda9fc10 100644
--- a/docs/modules/ROOT/pages/migration-to-4x/metadata-changes-4x.adoc
+++ b/docs/modules/ROOT/pages/migration-to-4x/metadata-changes-4x.adoc
@@ -171,7 +171,9 @@ independent of casing (the name's origin).
(`xmp*:`), EXIF/`tiff:`, `iptc:`, `photoshop:`, `geo:`, the CF/CMIP
attributes under `cf:`,
MAPI property names, email headers, the ECMA-376 OOXML core/extended
property names
(`AppVersion`, `lastModifiedBy`, `TotalTime`, …), and the PDF/A/X/VT/UA
sub-namespaces
- (`pdfaid:`, `pdfx:`, …) and PDF Info-dict names (`pdf:trapped`,
`pdf:docinfo:producer`, …).
+ (`pdfaid:`, `pdfx:`, …). PDF Info-dict names (`pdf:docinfo:producer`,
`pdf:docinfo:trapped`,
+ …) are lowercased rather than verbatim — the dictionary spells them
`/Producer` and `/Trapped`
+ — but they are unchanged from 3.x.
(The `access_permission:` prefix is also normalized to `access-permission:`.
The
`extended-properties:HiddedSlides` entry additionally corrects a long-standing
spelling typo.)
diff --git a/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
b/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
index 3c0cb71dde..503f2dcaf5 100644
--- a/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
+++ b/docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
@@ -69,9 +69,12 @@ xref:advanced/spooling.adoc[spooling] for the stream
contract.
`TikaInputStream` itself dropped several members in 4.0: `isTikaInputStream`,
`cast`,
`getPath(int)`, `get(InputStreamFactory)` (both overloads),
`hasInputStreamFactory`,
`getInputStreamFactory`, and `setOpenContainer(Object, long)` — along with the
-`InputStreamFactory` class. `get(byte[])` and `getFromContainer` no longer
declare
-`IOException`. `enableRewind()` now throws a checked `IOException` when bytes
have
-already been read.
+`InputStreamFactory` class.
+
+NOTE: Two further `TikaInputStream` changes are easy to mistake for 3.x deltas
but are deltas
+against 4.0.0-beta-1: `get(byte[])` and `getFromContainer` no longer declaring
`IOException`
+(neither declared it in 3.3.2), and `enableRewind()` throwing a checked
`IOException` (the method
+did not exist in 3.3.2). Upgrading from 3.x, neither is a change you need to
make.
[#thin-launcher-zip]
== `tika-app` and `tika-server` distributions: jar -> zip
diff --git a/docs/modules/ROOT/pages/pipes/plugins/elasticsearch.adoc
b/docs/modules/ROOT/pages/pipes/plugins/elasticsearch.adoc
index 5cc504dd6d..ffd0757e71 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/elasticsearch.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/elasticsearch.adoc
@@ -122,8 +122,8 @@ include::example$pipes-elasticsearch-emitter.json[]
|Validated non-blank, but not otherwise read: the `_id` is the emit key
(attachments get the emit key plus a random suffix).
|`attachmentStrategy`
-|`SEPARATE_DOCUMENTS`
-|How attached/embedded documents are indexed. `SEPARATE_DOCUMENTS` — each
attachment becomes its own top-level document; `PARENT_CHILD` — attachments are
nested under the parent in a parent/child relation. Absent behaves as
`SEPARATE_DOCUMENTS`.
+|_none_
+|How attached/embedded documents are indexed. `SEPARATE_DOCUMENTS` — each
attachment becomes its own top-level document; `PARENT_CHILD` — attachments are
nested under the parent in a parent/child relation. There is no default: leave
it unset and embedded documents get neither the `parent` field nor the
parent/child relation, so set it explicitly.
|`updateStrategy`
|`UPSERT`
diff --git a/docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc
b/docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc
index 1ae55988ac..eeb616fe18 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc
@@ -158,7 +158,7 @@ In addition to the required `fetcherId` / `emitterId` (see
xref:pipes/iterators.
|`queryTimeoutSeconds`
|`-1`
-|Passed straight to `Statement.setQueryTimeout(int seconds)` with no guard.
Use `0` for the JDBC contract's "no limit" — the `-1` default is outside that
contract and drivers may reject it.
+|Applied via `Statement.setQueryTimeout(int seconds)` only when greater than
`0`. `0` and any negative value both leave the driver's own setting alone, so
the JDBC contract's explicit "no limit" cannot be requested here.
|===
[#jdbc-reporter]
diff --git a/docs/modules/ROOT/pages/pipes/plugins/kafka.adoc
b/docs/modules/ROOT/pages/pipes/plugins/kafka.adoc
index e3b448e321..34d695a716 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/kafka.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/kafka.adoc
@@ -88,8 +88,8 @@ applies. The Default column below is therefore the Kafka
client's default.
|One of `none`, `gzip`, `snappy`, `lz4`, `zstd`.
|`connectionsMaxIdleMs`
-|_ignored_
-|Accepted by the config parser but never passed to the producer, so it has no
effect. Kafka's own `connections.max.idle.ms` default of `540000` always
applies.
+|`540000`
+|Passed through to the producer as `connections.max.idle.ms`.
|`deliveryTimeoutMs`
|`120000`
diff --git a/docs/modules/ROOT/pages/pipes/plugins/opensearch.adoc
b/docs/modules/ROOT/pages/pipes/plugins/opensearch.adoc
index f6c6f43389..6eb07fc6fb 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/opensearch.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/opensearch.adoc
@@ -120,8 +120,8 @@ include::example$pipes-opensearch-emitter.json[]
|Validated non-blank, but not otherwise read: the `_id` is the emit key
(attachments get the emit key plus a random suffix).
|`attachmentStrategy`
-|`SEPARATE_DOCUMENTS`
-|How attached/embedded documents are indexed. `SEPARATE_DOCUMENTS` — each
attachment becomes its own top-level document; `PARENT_CHILD` — attachments are
nested under the parent in a parent/child relation. Absent behaves as
`SEPARATE_DOCUMENTS`.
+|_none_
+|How attached/embedded documents are indexed. `SEPARATE_DOCUMENTS` — each
attachment becomes its own top-level document; `PARENT_CHILD` — attachments are
nested under the parent in a parent/child relation. There is no default: leave
it unset and embedded documents get neither the `parent` field nor the
parent/child relation, so set it explicitly.
|`updateStrategy`
|`UPSERT`
diff --git a/docs/modules/ROOT/pages/pipes/plugins/solr.adoc
b/docs/modules/ROOT/pages/pipes/plugins/solr.adoc
index 26940646ca..612089e710 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/solr.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/solr.adoc
@@ -124,7 +124,9 @@ include::example$pipes-solr-emitter-zk.json[]
|`authScheme`
|`basic`
-|Credential scheme. `basic` or `ntlm`.
+|Credential scheme. Only `basic` is supported, and only when `userName` is
set: the emitter then
+fails to build on any other value. With no `userName`, auth is skipped and
this setting is ignored
+rather than rejected.
|`proxyHost` / `proxyPort`
|_none_ / `0`
@@ -179,7 +181,7 @@ In addition to the required `fetcherId` / `emitterId` (see
xref:pipes/iterators.
|`additionalFields`
|_empty_
-|Further Solr fields to request alongside the four above.
+|Further Solr fields to request alongside those above. The field list always
includes `id` as well, whether or not `idField` is set to it.
|`rows`
|`5000`
diff --git a/docs/modules/ROOT/pages/pipes/plugins/writing-a-plugin.adoc
b/docs/modules/ROOT/pages/pipes/plugins/writing-a-plugin.adoc
index 03f28cf4f4..8729cb116d 100644
--- a/docs/modules/ROOT/pages/pipes/plugins/writing-a-plugin.adoc
+++ b/docs/modules/ROOT/pages/pipes/plugins/writing-a-plugin.adoc
@@ -361,10 +361,12 @@ id, because a pipeline has one iterator and reporters are
not referenced by id:
Whatever object sits innermost is re-serialized to a string and handed to your
factory as
`ExtensionConfig.json()`. Configs are validated when the config loads — an
unknown component name
-fails immediately, listing the names that *are* available — but instances are
built lazily, on
-first use.
+fails immediately, listing the names that *are* available. Fetchers and
emitters are then built
+lazily, on first use; `pipes-iterator` and `pipes-reporters` instances are
built during config
+load.
-An array in any of these sections is rejected outright rather than silently
ignored.
+An array is rejected outright in `fetchers`, `emitters` and `pipes-iterator`.
`pipes-reporters` is
+the exception: an array there loads zero reporters and reports no error, so
keep it an object.
== Developing without repackaging
diff --git a/docs/modules/ROOT/pages/pipes/unpack-config.adoc
b/docs/modules/ROOT/pages/pipes/unpack-config.adoc
index 1ea7cce174..4884b2689e 100644
--- a/docs/modules/ROOT/pages/pipes/unpack-config.adoc
+++ b/docs/modules/ROOT/pages/pipes/unpack-config.adoc
@@ -203,7 +203,7 @@ Produces names like `document-embed-00000001.pdf`. Under
the `DEFAULT` strategy
== Safety Limits
-`maxUnpackBytes` bounds zip bombs and other files that expand to enormous
sizes. The 10 GB
+`maxUnpackBytes` bounds zip bombs and other files that expand to enormous
sizes. The 10 GiB
default suits most corpora; lower it for untrusted input.
Hitting the limit is silent apart from a log line. The embedded file being
written is
diff --git a/docs/modules/ROOT/pages/using-tika/docker.adoc
b/docs/modules/ROOT/pages/using-tika/docker.adoc
index ba01436baa..bb991144a1 100644
--- a/docs/modules/ROOT/pages/using-tika/docker.adoc
+++ b/docs/modules/ROOT/pages/using-tika/docker.adoc
@@ -127,7 +127,9 @@ the Tika process. Outside Docker the equivalent is the
`tika.extras.dir` system
`/tika`, `/rmeta`, `/meta` and `/unpack` work out of the box. The pipes
endpoints (`/pipes`,
`/async`) need the fetcher and emitter plugins for whatever they talk to. The
image ships
`tika-pipes-file-system` under `/opt/tika-server/plugins/`; mount any other
plugin into that
-directory, one subdirectory per plugin.
+directory, one subdirectory per plugin. Plugins publish as `.zip`, so unzip
yours first and mount
+the resulting directory — the container cannot expand the zip in place, because
+`/opt/tika-server` is copied in root-owned while the server runs as UID 35002.
[source,bash]
----
diff --git a/tika-ml/tika-ml-junkdetect-tools/pom.xml
b/tika-ml/tika-ml-junkdetect-tools/pom.xml
index fe684093cd..fe720dafe8 100644
--- a/tika-ml/tika-ml-junkdetect-tools/pom.xml
+++ b/tika-ml/tika-ml-junkdetect-tools/pom.xml
@@ -100,8 +100,9 @@
Usage (run from the repo root so the model resource path resolves):
./mvnw package -pl tika-ml/tika-ml-junkdetect-tools -am -Ptrain
-DskipTests \
-Dmaven.repo.local=.local_m2_repo
- java -jar
tika-ml/tika-ml-junkdetect-tools/target/tika-ml-junkdetect-tools-*-tools.jar \
- [BuildJunkTrainingData|TrainJunkModel|EvalJunkDetector] [args...]
+ java -jar
tika-ml/tika-ml-junkdetect-tools/target/tika-ml-junkdetect-tools-*-tools.jar
[args...]
+ The shaded main class is TrainJunkModel; run any other tool with
+ java -cp <that jar>
org.apache.tika.ml.junkdetect.tools.BuildJunkTrainingData [args...]
-->
<id>train</id>
<build>
diff --git
a/tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkFilterEncodingDetector.java
b/tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkFilterEncodingDetector.java
index 0253502c32..2a3c08b9fe 100644
---
a/tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkFilterEncodingDetector.java
+++
b/tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkFilterEncodingDetector.java
@@ -257,12 +257,11 @@ public class JunkFilterEncodingDetector implements
MetaEncodingDetector {
// by shared content (whitespace/digits identical across decodes); on a
// COMMON-dominated doc the discriminating bytes are diluted and the
top
// candidates differ only by noise. The quality signal is STATISTICAL-
- // grade evidence, so it may override a higher-evidence anchor
- // (DECLARATIVE author intent, or STRUCTURAL byte-grammar proof) only
when
- // it beats that anchor's score by OVERRIDE_MARGIN; otherwise we defer
to
- // the anchor. This is honest low-confidence behaviour, not a
tie-break:
- // where the model has real signal (e.g. UTF-8 over garbage UTF-16,
Δ≫1)
- // it still overrides freely.
+ // grade evidence, so it yields to a higher-evidence anchor
(DECLARATIVE
+ // author intent, or STRUCTURAL byte-grammar proof) whenever the
+ // statistical layer itself abstained -- see the deferral below. This
is
+ // honest low-confidence behaviour, not a tie-break: where the model
has
+ // real signal (e.g. UTF-8 over garbage UTF-16) it still overrides
freely.
Charset champion = null;
double championZ = Double.NEGATIVE_INFINITY;
Map<Charset, Double> scoreByCharset = new LinkedHashMap<>();
diff --git
a/tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/main/java/org/apache/tika/parser/ocr/tess4j/Tess4JConfig.java
b/tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/main/java/org/apache/tika/parser/ocr/tess4j/Tess4JConfig.java
index 109a4e5ebb..b8517355a9 100644
---
a/tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/main/java/org/apache/tika/parser/ocr/tess4j/Tess4JConfig.java
+++
b/tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/main/java/org/apache/tika/parser/ocr/tess4j/Tess4JConfig.java
@@ -307,11 +307,12 @@ public class Tess4JConfig implements Serializable {
* pool settings during parse-time configuration.
* <p>
* <b>Always blocked:</b> {@code dataPath}, {@code nativeLibPath},
- * {@code poolSize}.
+ * {@code poolSize}, {@code maxImagePixels}.
* <p>
* Paths are blocked to prevent file-system access attacks.
- * Pool size is blocked because the pool is built at init time and
- * cannot be resized at runtime.
+ * Pool size is blocked because the pool is built at init time and cannot
+ * be resized. {@code maxImagePixels} is read per parse, but it is the
+ * OOM guard on image decode, so a caller must not be able to raise it.
*/
public static class RuntimeConfig extends Tess4JConfig {
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
index 07ffff21c6..fdb4c42eff 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/ImagePreprocessor.java
@@ -55,7 +55,7 @@ class ImagePreprocessor implements Serializable {
double angle = config.isApplyRotation() ? getAngle(sourceFile,
metadata) : 0d;
if (config.isEnableImagePreprocessing() || (config.isApplyRotation()
&& angle != 0)) {
- // process the image - parameter values can be set in
TesseractOCRConfig.properties
+ // process the image - parameter values come from
TesseractOCRConfig
//
// On Windows TesseractOCRParser.getImageMagickProg() returns
"magick", i.e. the
// ImageMagick 7 program. IM7's native command form is
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
index 93366eedbc..62b209cfe1 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRConfig.java
@@ -511,10 +511,6 @@ public class TesseractOCRConfig implements Serializable {
/**
* Add a key-value pair to pass to Tesseract using its -c command line
option.
* To see the possible options, run tesseract --print-parameters.
- * <p>
- * You may also add these parameters in TesseractOCRConfig.properties; any
- * key-value pair in the properties file where the key contains an
underscore
- * is passed directly to Tesseract.
*
* @param key
* @param value
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-atlassian-jwt/src/main/java/org/apache/tika/pipes/fetcher/atlassianjwt/AtlassianJwtFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-atlassian-jwt/src/main/java/org/apache/tika/pipes/fetcher/atlassianjwt/AtlassianJwtFetcherFactory.java
index 145bc80bee..c30942b22f 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-atlassian-jwt/src/main/java/org/apache/tika/pipes/fetcher/atlassianjwt/AtlassianJwtFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-atlassian-jwt/src/main/java/org/apache/tika/pipes/fetcher/atlassianjwt/AtlassianJwtFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "atlassian-jwt-fetcher": {
- * "my-atlassian-fetcher": {
+ * "my-atlassian-fetcher": {
+ * "atlassian-jwt-fetcher": {
* "sharedSecret": "your-shared-secret",
* "issuer": "your-app-key",
* "connectTimeoutMillis": 30000,
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitter.java
index 41f6baa7df..bbbe17cb5e 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitter.java
@@ -53,8 +53,8 @@ import org.apache.tika.utils.StringUtils;
* <pre>
* {
* "emitters": {
- * "az-blob-emitter": {
- * "my-azure": {
+ * "my-azure": {
+ * "az-blob-emitter": {
* "endpoint": "https://myaccount.blob.core.windows.net";,
* "sasToken": "sv=2020-08-04&ss=b...",
* "container": "my-container",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitterFactory.java
index c24ea22d3d..0729a8df56 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/emitter/azblob/AZBlobEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "az-blob-emitter": {
- * "my-az-emitter": {
+ * "my-az-emitter": {
+ * "az-blob-emitter": {
* "sasToken": "your-sas-token",
* "endpoint": "https://account.blob.core.windows.net";,
* "container": "my-container",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/fetcher/azblob/AZBlobFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/fetcher/azblob/AZBlobFetcherFactory.java
index 5508e69be5..2667526ca0 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/fetcher/azblob/AZBlobFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-az-blob/src/main/java/org/apache/tika/pipes/fetcher/azblob/AZBlobFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "az-blob-fetcher": {
- * "my-az-fetcher": {
+ * "my-az-fetcher": {
+ * "az-blob-fetcher": {
* "sasToken": "your-sas-token",
* "endpoint": "https://account.blob.core.windows.net";,
* "container": "my-container",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-es/src/main/java/org/apache/tika/pipes/emitter/es/ESEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-es/src/main/java/org/apache/tika/pipes/emitter/es/ESEmitterFactory.java
index 21771d1d5d..1515b69bdf 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-es/src/main/java/org/apache/tika/pipes/emitter/es/ESEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-es/src/main/java/org/apache/tika/pipes/emitter/es/ESEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "es-emitter": {
- * "my-es-emitter": {
+ * "my-es-emitter": {
+ * "es-emitter": {
* "esUrl": "https://localhost:9200/my-index";,
* "idField": "id",
* "apiKey": "base64-encoded-id:api_key",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/emitter/fs/FileSystemEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/emitter/fs/FileSystemEmitterFactory.java
index 0160616e2e..7a86079594 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/emitter/fs/FileSystemEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/emitter/fs/FileSystemEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "file-system-emitter": {
- * "my-emitter": {
+ * "my-emitter": {
+ * "file-system-emitter": {
* "basePath": "/path/to/output",
* "fileExtension": "json",
* "onExists": "SKIP",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcherFactory.java
index 6483f32fe7..fa2b672711 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcherFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "file-system-fetcher": {
- * "my-fetcher": {
+ * "my-fetcher": {
+ * "file-system-fetcher": {
* "basePath": "/path/to/files",
* "extractFileSystemMetadata": true
* }
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitter.java
index 0e70cac0a8..e3a9080e5d 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitter.java
@@ -49,8 +49,8 @@ import org.apache.tika.utils.StringUtils;
* <pre>
* {
* "emitters": {
- * "gcs-emitter": {
- * "my-gcs": {
+ * "my-gcs": {
+ * "gcs-emitter": {
* "projectId": "my-project-id",
* "bucket": "my-bucket",
* "prefix": "output",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitterFactory.java
index a0c7df0291..f8b088229c 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/emitter/gcs/GCSEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "gcs-emitter": {
- * "my-gcs-emitter": {
+ * "my-gcs-emitter": {
+ * "gcs-emitter": {
* "projectId": "my-project",
* "bucket": "my-bucket",
* "prefix": "output/",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/fetcher/gcs/GCSFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/fetcher/gcs/GCSFetcherFactory.java
index fceca509c5..b426cabdef 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/fetcher/gcs/GCSFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-gcs/src/main/java/org/apache/tika/pipes/fetcher/gcs/GCSFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "gcs-fetcher": {
- * "my-gcs-fetcher": {
+ * "my-gcs-fetcher": {
+ * "gcs-fetcher": {
* "projectId": "my-project",
* "bucket": "my-bucket",
* "spoolToTemp": true,
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-google-drive/src/main/java/org/apache/tika/pipes/fetcher/googledrive/GoogleDriveFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-google-drive/src/main/java/org/apache/tika/pipes/fetcher/googledrive/GoogleDriveFetcherFactory.java
index a213484b72..07f186ba2d 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-google-drive/src/main/java/org/apache/tika/pipes/fetcher/googledrive/GoogleDriveFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-google-drive/src/main/java/org/apache/tika/pipes/fetcher/googledrive/GoogleDriveFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "google-drive-fetcher": {
- * "my-drive-fetcher": {
+ * "my-drive-fetcher": {
+ * "google-drive-fetcher": {
* "serviceAccountCredentialsPath": "/path/to/credentials.json",
* "impersonatedUser": "[email protected]"
* }
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-http/src/main/java/org/apache/tika/pipes/fetcher/http/HttpFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-http/src/main/java/org/apache/tika/pipes/fetcher/http/HttpFetcherFactory.java
index d2df6bdfb6..cb9cc593d5 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-http/src/main/java/org/apache/tika/pipes/fetcher/http/HttpFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-http/src/main/java/org/apache/tika/pipes/fetcher/http/HttpFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "http-fetcher": {
- * "my-http-fetcher": {
+ * "my-http-fetcher": {
+ * "http-fetcher": {
* "userName": "user",
* "password": "pass",
* "connectTimeoutMillis": 30000,
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitter.java
index 9f850cf83a..b88db8e1f9 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitter.java
@@ -58,8 +58,8 @@ import org.apache.tika.utils.StringUtils;
* <pre>
* {
* "emitters": {
- * "jdbc-emitter": {
- * "my-db": {
+ * "my-db": {
+ * "jdbc-emitter": {
* "connection": "jdbc:postgresql://localhost/mydb",
* "createTable": "CREATE TABLE IF NOT EXISTS docs (path
VARCHAR(1024), content TEXT)",
* "insert": "INSERT INTO docs (path, content) VALUES (?, ?)",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitterFactory.java
index a63c699512..7155b0a4b3 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-jdbc/src/main/java/org/apache/tika/pipes/emitter/jdbc/JDBCEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "jdbc-emitter": {
- * "my-jdbc-emitter": {
+ * "my-jdbc-emitter": {
+ * "jdbc-emitter": {
* "connection": "jdbc:postgresql://localhost/mydb",
* "insert": "insert into docs (id, content) values (?, ?)",
* "keys": {"id": "tk:content", "content": "content"}
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitter.java
index 9b25d0748f..b4b95aacb2 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitter.java
@@ -44,8 +44,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <pre>
* {
* "emitters": {
- * "kafka-emitter": {
- * "my-kafka": {
+ * "my-kafka": {
+ * "kafka-emitter": {
* "topic": "tika-output",
* "bootstrapServers": "localhost:9092",
* "acks": "all",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitterFactory.java
index d69874ded7..1bff542561 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-kafka/src/main/java/org/apache/tika/pipes/emitter/kafka/KafkaEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "kafka-emitter": {
- * "my-kafka-emitter": {
+ * "my-kafka-emitter": {
+ * "kafka-emitter": {
* "topic": "my-topic",
* "bootstrapServers": "localhost:9092",
* "acks": "all",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-microsoft-graph/src/main/java/org/apache/tika/pipes/fetchers/microsoftgraph/MicrosoftGraphFetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-microsoft-graph/src/main/java/org/apache/tika/pipes/fetchers/microsoftgraph/MicrosoftGraphFetcherFactory.java
index a0b4e88c1b..0ea0a18888 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-microsoft-graph/src/main/java/org/apache/tika/pipes/fetchers/microsoftgraph/MicrosoftGraphFetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-microsoft-graph/src/main/java/org/apache/tika/pipes/fetchers/microsoftgraph/MicrosoftGraphFetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "microsoft-graph-fetcher": {
- * "my-graph-fetcher": {
+ * "my-graph-fetcher": {
+ * "microsoft-graph-fetcher": {
* "spoolToTemp": true,
* "scopes": ["https://graph.microsoft.com/.default";],
* "clientSecretCredentialsConfig": {
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-opensearch/src/main/java/org/apache/tika/pipes/emitter/opensearch/OpenSearchEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-opensearch/src/main/java/org/apache/tika/pipes/emitter/opensearch/OpenSearchEmitterFactory.java
index 7d42c1e310..56fb958bc0 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-opensearch/src/main/java/org/apache/tika/pipes/emitter/opensearch/OpenSearchEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-opensearch/src/main/java/org/apache/tika/pipes/emitter/opensearch/OpenSearchEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "opensearch-emitter": {
- * "my-opensearch-emitter": {
+ * "my-opensearch-emitter": {
+ * "opensearch-emitter": {
* "openSearchUrl": "http://localhost:9200/my-index";,
* "idField": "id",
* "attachmentStrategy": "PARENT_CHILD",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3Emitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3Emitter.java
index 0462d7b459..c73a14f638 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3Emitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3Emitter.java
@@ -68,8 +68,8 @@ import org.apache.tika.utils.StringUtils;
* <pre>
* {
* "emitters": {
- * "s3-emitter": {
- * "my-s3": {
+ * "my-s3": {
+ * "s3-emitter": {
* "region": "us-east-1",
* "bucket": "my-bucket",
* "credentialsProvider": "profile",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3EmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3EmitterFactory.java
index 99d45b7a7b..ecf36a20b3 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3EmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/emitter/s3/S3EmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "s3-emitter": {
- * "my-s3-emitter": {
+ * "my-s3-emitter": {
+ * "s3-emitter": {
* "region": "us-east-1",
* "bucket": "my-bucket",
* "credentialsProvider": "profile",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/fetcher/s3/S3FetcherFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/fetcher/s3/S3FetcherFactory.java
index fd98da1e22..2115a97aeb 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/fetcher/s3/S3FetcherFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-s3/src/main/java/org/apache/tika/pipes/fetcher/s3/S3FetcherFactory.java
@@ -32,8 +32,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "fetchers": {
- * "s3-fetcher": {
- * "my-s3-fetcher": {
+ * "my-s3-fetcher": {
+ * "s3-fetcher": {
* "region": "us-east-1",
* "bucket": "my-bucket",
* "credentialsProvider": "profile",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitter.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitter.java
index c7a4477282..8ce35dc441 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitter.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitter.java
@@ -49,8 +49,8 @@ import org.apache.tika.utils.StringUtils;
* <pre>
* {
* "emitters": {
- * "solr-emitter": {
- * "my-solr": {
+ * "my-solr": {
+ * "solr-emitter": {
* "solrCollection": "my-collection",
* "solrUrls": ["http://localhost:8983/solr";],
* "idField": "id",
diff --git
a/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitterFactory.java
b/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitterFactory.java
index ebd8932924..33fe4333dc 100644
---
a/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitterFactory.java
+++
b/tika-pipes/tika-pipes-plugins/tika-pipes-solr/src/main/java/org/apache/tika/pipes/emitter/solr/SolrEmitterFactory.java
@@ -31,8 +31,8 @@ import org.apache.tika.plugins.ExtensionConfig;
* <p>Example JSON configuration:
* <pre>
* "emitters": {
- * "solr-emitter": {
- * "my-solr-emitter": {
+ * "my-solr-emitter": {
+ * "solr-emitter": {
* "solrCollection": "my-collection",
* "solrUrls": ["http://localhost:8983/solr";],
* "idField": "id",
