dadoonet · dadoonet · Jul 7, 2026 · Jul 7, 2026 · Jul 7, 2026 · Jul 7, 2026
@@ -512,70 +512,80 @@ For example, a PDF document could generate:
 .. code:: json
 
    {
-      "date" : "2016-07-07T08:37:42Z",
-      "pdf:PDFVersion" : "1.5",
-      "xmp:CreatorTool" : "Microsoft Word",
-      "Keywords" : "keyword1, keyword2",
+      "access_permission:assemble_document" : "true",
+      "access_permission:can_modify" : "true",
+      "access_permission:can_print" : "true",
+      "access_permission:can_print_faithful" : "true",
+      "access_permission:extract_content" : "true",
+      "access_permission:extract_for_accessibility" : "true",
+      "access_permission:fill_in_form" : "true",
       "access_permission:modify_annotations" : "true",
-      "access_permission:can_print_degraded" : "true",
-      "subject" : "Test Tika Object",
+      "Content-Length" : "101643",
+      "Content-Type" : "application/pdf",
+      "Content-Type-Magic-Detected" : "application/pdf",
       "dc:creator" : "David Pilato",
+      "dc:format" : "application/pdf; version=1.5",
+      "dc:language" : "en-US",
+      "dc:subject" : "keyword1, keyword2",
+      "dc:title" : "Test Tika title",
       "dcterms:created" : "2016-07-07T08:37:42Z",
-      "Last-Modified" : "2016-07-07T08:37:42Z",
       "dcterms:modified" : "2016-07-07T08:37:42Z",
-      "dc:format" : "application/pdf; version=1.5",
-      "title" : "Test Tika title",
-      "Last-Save-Date" : "2016-07-07T08:37:42Z",
-      "access_permission:fill_in_form" : "true",
-      "meta:save-date" : "2016-07-07T08:37:42Z",
+      "pdf:charsPerPage" : "42",
+      "pdf:containsDamagedFont" : "false",
+      "pdf:containsNonEmbeddedFont" : "false",
+      "pdf:docinfo:created" : "2016-07-07T08:37:42Z",
+      "pdf:docinfo:creator" : "David Pilato",
+      "pdf:docinfo:creator_tool" : "Microsoft Word",
+      "pdf:docinfo:keywords" : "keyword1, keyword2",
+      "pdf:docinfo:modified" : "2016-07-07T08:37:42Z",
+      "pdf:docinfo:subject" : "Test Tika Object",
+      "pdf:docinfo:title" : "Test Tika title",
       "pdf:encrypted" : "false",
-      "dc:title" : "Test Tika title",
-      "modified" : "2016-07-07T08:37:42Z",
-      "cp:subject" : "Test Tika Object",
-      "Content-Type" : "application/pdf",
-      "X-Parsed-By" : "org.apache.tika.parser.DefaultParser",
-      "creator" : "David Pilato",
-      "meta:author" : "David Pilato",
-      "dc:subject" : "keyword1, keyword2",
-      "meta:creation-date" : "2016-07-07T08:37:42Z",
-      "created" : "Thu Jul 07 10:37:42 CEST 2016",
-      "access_permission:extract_for_accessibility" : "true",
-      "access_permission:assemble_document" : "true",
-      "xmpTPg:NPages" : "2",
-      "Creation-Date" : "2016-07-07T08:37:42Z",
-      "access_permission:extract_content" : "true",
-      "access_permission:can_print" : "true",
-      "meta:keyword" : "keyword1, keyword2",
-      "Author" : "David Pilato",
-      "access_permission:can_modify" : "true"
+      "pdf:eofOffsets" : "101460",
+      "pdf:hasCollection" : "false",
+      "pdf:hasMarkedContent" : "true",
+      "pdf:hasXFA" : "false",
+      "pdf:hasXMP" : "false",
+      "pdf:incrementalUpdateCount" : "1",
+      "pdf:num3DAnnotations" : "0",
+      "pdf:ocrPageCount" : "0",
+      "pdf:overallPercentageUnmappedUnicodeChars" : "0.0",
+      "pdf:PDFVersion" : "1.5",
+      "pdf:totalUnmappedUnicodeChars" : "0",
+      "pdf:unmappedUnicodeCharsPerPage" : "0",
+      "X-TIKA:Parsed-By" : "org.apache.tika.parser.pdf.PDFParser",
+      "X-TIKA:Parsed-By-Full-Set" : "org.apache.tika.parser.pdf.PDFParser",
+      "X-TIKA:resourceName" : "test.pdf",
+      "X-TIKA:versionCount" : "1",
+      "xmp:CreatorTool" : "Microsoft Word",
+      "xmpTPg:NPages" : "2"
    }
 
 Where a MP3 file would generate:
 
 .. code:: json
 
    {
-      "xmpDM:genre" : "Vocal",
-      "X-Parsed-By" : "org.apache.tika.parser.DefaultParser",
-      "creator" : "David Pilato",
+      "channels" : "2",
+      "Content-Type" : "audio/mpeg",
+      "Content-Type-Magic-Detected" : "audio/mpeg",
+      "dc:creator" : "David Pilato",
+      "dc:title" : "Test Tika",
+      "samplerate" : "44100",
+      "version" : "MPEG 3 Layer III Version 1",
+      "X-TIKA:Parsed-By" : "org.apache.tika.parser.DefaultParser",
+      "X-TIKA:Parsed-By-Full-Set" : "org.apache.tika.parser.DefaultParser",
+      "X-TIKA:resourceName" : "test.mp3",
       "xmpDM:album" : "FS Crawler",
-      "xmpDM:trackNumber" : "1",
-      "xmpDM:releaseDate" : "2016",
-      "meta:author" : "David Pilato",
       "xmpDM:artist" : "David Pilato",
-      "dc:creator" : "David Pilato",
-      "xmpDM:audioCompressor" : "MP3",
-      "title" : "Test Tika",
       "xmpDM:audioChannelType" : "Stereo",
-      "version" : "MPEG 3 Layer III Version 1",
-      "xmpDM:logComment" : "Hello but reverted",
+      "xmpDM:audioCompressor" : "MP3",
       "xmpDM:audioSampleRate" : "44100",
-      "channels" : "2",
-      "dc:title" : "Test Tika",
-      "Author" : "David Pilato",
-      "xmpDM:duration" : "1018.775146484375",
-      "Content-Type" : "audio/mpeg",
-      "samplerate" : "44100"
+      "xmpDM:duration" : "1.0187751054763794",
+      "xmpDM:genre" : "Vocal",
+      "xmpDM:logComment" : "Hello but reverted",
+      "xmpDM:releaseDate" : "2016",
+      "xmpDM:trackNumber" : "1"
    }
 
 .. note::
@@ -879,31 +889,19 @@ Tika Config Path
 
 .. versionadded:: 2.10
 
-If you want to override the default tika parser configuration, you can set the path to a custom tika
-configuration file, which will be used instead.
+.. warning::
+
+   Since the upgrade to Apache Tika 4, ``fs.tika_config_path`` is **temporarily not supported**. Tika 4
+   removed the XML-based Tika configuration file mechanism, and there is currently no drop-in replacement
+   to assemble a parser from a configuration file. If this setting is provided, FSCrawler fails fast with
+   a clear configuration error. Support is expected to return on top of Tika 4's new JSON-based
+   configuration.
+
+This setting used to let you override the default Tika parser configuration by pointing to a custom Tika
+configuration file:
 
 .. code:: yaml
 
    name: "test"
    fs:
      tika_config_path: '/path/to/tikaConfig.xml'
-
-An example tika config file is shown below. See |Tika_configuring|_ for more information.
-
-.. code:: xml
-
-  <?xml version="1.0" encoding="UTF-8"?>
-  <properties>
-    <service-loader dynamic="true"/>
-    <service-loader loadErrorHandler="IGNORE"/>
-    <parsers>
-      <!-- Use Default Parser for files, but Default Parser will never use HTML parser -->
-      <parser class="org.apache.tika.parser.DefaultParser">
-        <parser-exclude class="org.apache.tika.parser.html.JsoupParser"/>
-      </parser>
-      <!-- Use a different parser for XHTML -->
-      <parser class="org.apache.tika.parser.xml.XMLParser">
-        <mime>application/xhtml+xml</mime>
-      </parser>
-    </parsers>
-  </properties>
@@ -151,9 +151,12 @@ You will get back your document as it has been stored by elasticsearch:
        },
        "meta" : {
          "raw" : {
-           "X-Parsed-By" : "org.apache.tika.parser.DefaultParser",
            "Content-Encoding" : "ISO-8859-1",
-           "Content-Type" : "text/plain; charset=ISO-8859-1"
+           "Content-Type" : "text/plain; charset=ISO-8859-1",
+           "Content-Type-Magic-Detected" : "text/plain",
+           "X-TIKA:Parsed-By" : "org.apache.tika.parser.DefaultParser",
+           "X-TIKA:Parsed-By-Full-Set" : "org.apache.tika.parser.DefaultParser",
+           "X-TIKA:resourceName" : "test.txt"
          }
        },
        "path" : {
@@ -187,9 +190,12 @@ will give
        },
        "meta" : {
          "raw" : {
-           "X-Parsed-By" : "org.apache.tika.parser.DefaultParser",
            "Content-Encoding" : "ISO-8859-1",
-           "Content-Type" : "text/plain; charset=ISO-8859-1"
+           "Content-Type" : "text/plain; charset=ISO-8859-1",
+           "Content-Type-Magic-Detected" : "text/plain",
+           "X-TIKA:Parsed-By" : "org.apache.tika.parser.DefaultParser",
+           "X-TIKA:Parsed-By-Full-Set" : "org.apache.tika.parser.DefaultParser",
+           "X-TIKA:resourceName" : "test.txt"
          }
        },
        "path" : {

@@ -3,7 +3,7 @@ Version=2.10-SNAPSHOT
 JavaVersion=17
 
 [3rdParty]
-TikaVersion=3.3.1
+TikaVersion=4.0.0-beta-1
 ElasticsearchVersion7=7.17.29
 ElasticsearchVersion8=8.19.5
 ElasticsearchVersion9=9.3.0

@@ -17,6 +17,18 @@ enough. Thanks to dadoonet.
 * We don't support anymore the ``elasticsearch.nodes.url`` setting. You need to use ``elasticsearch.urls``
   instead. Thanks to dadoonet.
 * The ``_upload`` REST endpoint has been removed. Please now use the ``_document`` endpoint. Thanks to dadoonet.
+* The Apache Tika 4 upgrade changes several ``meta.raw.*`` metadata key names. If you search, aggregate or
+  map these fields, you will need to update your queries and index templates accordingly:
+
+  * Image and EXIF metadata (JPEG, PNG, TIFF, …) keys are now namespaced under ``img:``. For example
+    ``Number of Tables`` becomes ``img:Number of Tables`` and ``Exif IFD0:Orientation`` becomes
+    ``img:Exif IFD0:Orientation``.
+  * The resource name key ``resourceName`` is renamed to ``X-TIKA:resourceName``.
+  * New keys are now produced, such as ``Content-Type-Magic-Detected``, ``X-TIKA:Parsed-By-Full-Set`` and,
+    for text documents, the encoding detection keys ``X-TIKA:detectedEncoding``,
+    ``X-TIKA:encodingDetectionTrace`` and ``X-TIKA:encodingDetector``.
+
+  Thanks to dadoonet.
 
 New
 ---
@@ -38,6 +50,8 @@ New
 * You can now remove a document in Elasticsearch using FSCrawler ``_document`` endpoint. See :ref:`rest-service`. Thanks to dadoonet.
 * Implement our own HTTP Client for Elasticsearch. Thanks to dadoonet.
 * Add option to set path to custom tika config file. See :ref:`local-fs-settings`. Thanks to iadcode.
+  **Note**: this option is temporarily disabled after the Apache Tika 4 upgrade, which removed the XML-based
+  configuration file mechanism. It is expected to return on top of Tika 4's JSON-based configuration.
 * Support for Index Templates. See :ref:`mappings`. Thanks to dadoonet.
 * Support for Aliases. You can now index to an alias. Thanks to dadoonet.
 * Support for Access Token and Api Keys instead of Basic Authentication. See :ref:`credentials`. Thanks to dadoonet.

@@ -9,7 +9,7 @@
       <Logger name="fr.pilato.elasticsearch.crawler.fs" level="info" additivity="false">
          <AppenderRef ref="CONSOLE"/>
       </Logger>
-      <Logger name="fr.pilato.elasticsearch.crawler.fs.client" level="debug" additivity="false">
+      <Logger name="fr.pilato.elasticsearch.crawler.fs.client" level="info" additivity="false">
          <AppenderRef ref="CONSOLE"/>
       </Logger>
       <Logger name="org.glassfish" level="info" additivity="false">

@@ -43,13 +43,14 @@
 import java.nio.file.Path;
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
-import org.apache.tika.parser.external.ExternalParser;
+import org.apache.tika.exception.TikaConfigException;
+import org.apache.tika.parser.ocr.TesseractOCRParser;
 import org.assertj.core.api.Assertions;
-import org.assertj.core.api.Assumptions;
 import org.assertj.core.api.InstanceOfAssertFactories;
 import org.junit.jupiter.api.AfterAll;
 import org.junit.jupiter.api.BeforeAll;
 import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.condition.DisabledIf;
 
 /** Test all type of documents we have */
 @VerySlow
@@ -253,14 +254,28 @@ void chineseContent369() throws ElasticsearchClientException {
     }
 
     @Test
+    @DisabledIf(value = "tesseractNotInstalled", disabledReason = "Tesseract is not installed")
     void ocr() throws ElasticsearchClientException {
-        Assumptions.assumeThat(ExternalParser.check("tesseract"))
-                .as("Tesseract is not installed so we are skipping this test")
-                .isTrue();
         runSearch("test-ocr.png", "words");
         runSearch("test-ocr.pdf", "words");
     }
 
+    /**
+     * Condition for {@link #ocr()}. Tika 4 removed {@code ExternalParser.check()}, so we reuse the same Tesseract
+     * availability check as production code. Returns {@code true} (disabling the test) when Tesseract is not installed
+     * or cannot be configured.
+     *
+     * @return {@code true} when Tesseract is unavailable
+     */
+    @SuppressWarnings("unused")
+    static boolean tesseractNotInstalled() {
+        try {
+            return !new TesseractOCRParser().hasTesseract();
+        } catch (TikaConfigException e) {
+            return true;
+        }
+    }
+
     @Test
     void shiftJisEncoding() throws ElasticsearchClientException {
         runSearch("issue-400-shiftjis.txt", "elasticsearch");

@@ -273,7 +273,7 @@
    }

    @Test
    void documentWithExternalTags() throws Exception {
        // We iterate over all sample files, and we try to locate any existing tag file
        // which can overwrite the data we extracted
        AtomicInteger numFiles = new AtomicInteger();
@@ -372,7 +372,7 @@
         checkDocument("replace_meta_only.txt", hit -> {
             Assertions.assertThat((String) JsonPath.read(hit.getSource(), "$.content"))
                     .contains("This file content will be extracted");
-            Assertions.assertThat((String) JsonPath.read(hit.getSource(), "$.meta.raw.resourceName"))
+            Assertions.assertThat((String) JsonPath.read(hit.getSource(), "$.meta.raw['X-TIKA:resourceName']"))
                     .isEqualTo("another-file-name.txt");
             Assertions.assertThatThrownBy(() -> JsonPath.read(hit.getSource(), "$.external"))
                     .isInstanceOf(PathNotFoundException.class);