From d760b8d16b0e2fd944ae2348f7931377c4ff399c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20G=C3=BCthler?= <mg@webfactory.de>
Date: Mon, 14 Aug 2023 14:34:17 +0200
Subject: [PATCH] Add option to set `fetcherName` for Tika >= 2.0.0

In Tika >= 2.0.0, fetching remote files via the server is done using so called [fetchers](https://cwiki.apache.org/confluence/display/TIKA/tika-pipes). If you are running a Tika Server that is configured to use an HTTP fetcher, you need the client to tell the server which fetcher to use, which is done by adding the HTTP header `fetcherName` to the request. Furthermore, the URL of the remote file to be fetched must be passed using a `fetchKey` header instead `fetchUrl` as in Tika 1.x.x.

This adds a public API method to set the fetcher name, and replaces the `fileUrl` header with `fetcherName` and `fetchKey` if a fetcher name is set. If no fetcher name is set, the `fileUrl` header is still added to the request as usual to keep TIKA 1.x.x compatibility.
---
 README.md                 | 11 +++++++++++
 src/Clients/WebClient.php | 24 +++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 117157c..aae3c58 100644
--- a/README.md
+++ b/README.md
@@ -122,6 +122,11 @@ You can use an URL instead of a file path and the library will download the file
 **no need** to add `-enableUnsecureFeatures -enableFileUrl` to command line when starting the server, as described 
 [here](https://wiki.apache.org/tika/TikaJAXRS#Specifying_a_URL_Instead_of_Putting_Bytes).
 
+If you use Apache Tika >= 2.0.0, you *can* [define an HttpFetcher](https://cwiki.apache.org/confluence/display/TIKA/tika-pipes)
+and use the option `-enableUnsecureFeatures -enableFileUrl` when starting the server to make the server download remote
+files when passing a URL instead of a filname to `$client->getText()`. In order to do so, you must set the name of
+the HttpFetcher using `$client->setFetcherName('yourFetcherName')`.
+
 ### Methods
 
 Here are the full list of available methods
@@ -254,6 +259,12 @@ $client->setOCRLanguages($languages);
 $client->getOCRLanguages();
 ```
 
+Set HTTP fetcher name (for Tika >= 2.0.0 only, see https://cwiki.apache.org/confluence/display/TIKA/tika-pipes)
+
+```php
+$client->setFetcherName($fetcherName)
+```
+
 ### Breaking changes
 
 Since 1.0 version there are some breaking changes:
diff --git a/src/Clients/WebClient.php b/src/Clients/WebClient.php
index 322d506..6958aea 100644
--- a/src/Clients/WebClient.php
+++ b/src/Clients/WebClient.php
@@ -51,6 +51,13 @@ class WebClient extends Client
      */
     protected $retries = 3;
 
+    /**
+     * Name of the fetcher to be used (for Tika >= 2.0.0 only)
+     *
+     * @var string|null
+     */
+    protected $fetcherName = null;
+
     /**
      * Default cURL options
      *
@@ -208,6 +215,16 @@ public function setRetries(int $retries): self
         return $this;
     }
 
+    /**
+     * Set the name of the fetcher to be used (for Tika >= 2.0.0 only)
+     */
+    public function setFetcherName(string $fetcherName): self
+    {
+        $this->fetcherName = $fetcherName;
+
+        return $this;
+    }
+
     /**
      * Get all the options
      */
@@ -626,7 +643,12 @@ protected function getParameters(string $type, string $file = null): array
 
         if(!empty($file) && preg_match('/^http/', $file))
         {
-            $headers[] = "fileUrl:$file";
+            if($this->fetcherName) {
+                $headers[] = "fetcherName:$this->fetcherName";
+                $headers[] = "fetchKey:$file";
+            } else {
+                $headers[] = "fileUrl:$file";
+            }
         }
 
         switch($type)