Merge branch '1.x'

Author: vaites

.github/workflows/tests.yml

@@ -46,6 +46,7 @@ jobs:
         - '2.5.0'
         - '2.6.0'
         - '2.7.0'
+        - '2.8.0'
 
    name: PHP ${{ matrix.php }} - TIKA ${{ matrix.tika }}
 

CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## v1.3.0
+
+* Added `WebClient::setFetcherName()` to easily set the [fetcher name](https://cwiki.apache.org/confluence/display/TIKA/tika-pipes) (thanks to @relthyg)
+* Tested up to Apache Tika 1.28.5 and 2.8.0
+
 ## v1.2.5
 
 * Tested up to Apache Tika 1.28.5 and 2.7.0

README.md

@@ -31,7 +31,7 @@ to work with the new versions of the tool.
 * Support for local and remote resources
 * No heavyweight library dependencies
 * Compatible with Apache Tika 1.15 or greater
-    * Tested up to 1.28.5 and 2.7.0
+    * Tested up to 1.28.5 and 2.8.0
 * Works on Linux, macOS, Windows and probably on FreeBSD
 
 ## Requirements
@@ -124,8 +124,8 @@ You can use an URL instead of a file path and the library will download the file
 
 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')`.
+files when passing a URL instead of a filename. In order to do so, you must set the name of the HttpFetcher using 
+`$client->setFetcherName('yourFetcherName')`.
 
 ### Methods
 
@@ -190,6 +190,14 @@ $client->setDownloadRemote(true);
 $client->getDownloadRemote();
 ```
 
+
+Set the [fetcher name](https://cwiki.apache.org/confluence/display/TIKA/tika-pipes):
+
+```php
+$client->setFetcherName($fetcher); // one of FileSystemFetcher, HttpFetcher, S3Fetcher, GCSFetcher, or SolrFetcher
+$client->getFetcherName();
+```
+
 #### Command line client
 
 Set/get JAR/Java paths (only CLI mode):

composer.json

@@ -48,7 +48,7 @@
         "supported-versions": [
             "1.15", "1.16", "1.17", "1.18", "1.19", "1.19.1", "1.20", "1.21", "1.22", "1.23", "1.24", "1.24.1",
             "1.25", "1.26", "1.27", "1.28", "1.28.1", "1.28.2", "1.28.3", "1.28.4", "1.28.5",
-            "2.0.0", "2.1.0", "2.2.0", "2.2.1", "2.3.0", "2.4.0", "2.5.0", "2.6.0", "2.7.0"
+            "2.0.0", "2.1.0", "2.2.0", "2.2.1", "2.3.0", "2.4.0", "2.5.0", "2.6.0", "2.7.0", "2.8.0"
         ]
     },
     "scripts": {

src/Clients/WebClient.php

@@ -215,11 +215,28 @@ public function setRetries(int $retries): self
         return $this;
     }
 
+    /**
+     * Get the name of the fetcher to be used (for Tika >= 2.0.0 only)
+     *
+     * @return string|null
+     */
+    public function getFetcherName(): ?string
+    {
+        return $this->fetcherName;
+    }
+
     /**
      * Set the name of the fetcher to be used (for Tika >= 2.0.0 only)
+     *
+     * @link https://cwiki.apache.org/confluence/display/TIKA/tika-pipes
      */
     public function setFetcherName(string $fetcherName): self
     {
+        if(!in_array($fetcherName, ['FileSystemFetcher', 'HttpFetcher', 'S3Fetcher', 'GCSFetcher', 'SolrFetcher']))
+        {
+            throw new Exception("Fetcher name $fetcherName is invalid, see https://cwiki.apache.org/confluence/display/TIKA/tika-pipes");
+        }
+
         $this->fetcherName = $fetcherName;
 
         return $this;
@@ -643,10 +660,13 @@ protected function getParameters(string $type, string $file = null): array
 
         if(!empty($file) && preg_match('/^http/', $file))
         {
-            if($this->fetcherName) {
+            if($this->fetcherName)
+            {
                 $headers[] = "fetcherName:$this->fetcherName";
                 $headers[] = "fetchKey:$file";
-            } else {
+            }
+            else
+            {
                 $headers[] = "fileUrl:$file";
             }
         }

tests/ErrorTest.php

@@ -230,6 +230,22 @@ public function testUnsupportedChunkSize(): void
         }
     }
 
+    /**
+     * Test invalid fetcher name
+     */
+    public function testUnsupportedFetcherName(): void
+    {
+        try
+        {
+            $client = Client::make('localhost', 9998);
+            $client->setFetcherName('UnknownFetcher');
+        }
+        catch(Exception $exception)
+        {
+            $this->assertStringContainsString('Fetcher name UnknownFetcher is invalid', $exception->getMessage());
+        }
+    }
+
     /**
      * Test wrong request type for all clients
      *

tests/WebTest.php

@@ -156,6 +156,24 @@ public function testSetRetries(): void
         $this->assertEquals(5, $client->getRetries());
     }
 
+    /**
+     * Set fetcher name test
+     */
+    public function testFetcherName(): void
+    {
+        if(version_compare(self::$version, '2.0.0') >= 0)
+        {
+            $client = Client::make('localhost', 9998);
+            $client->setFetcherName('FileSystemFetcher');
+
+            $this->assertEquals('FileSystemFetcher', $client->getFetcherName());
+        }
+        else
+        {
+            $this->markTestSkipped('Apache Tika 1.x doesn\'t have tika-pipes module');
+        }
+    }
+
     /**
      * Test delayed check
      */