From 545aeb6e25386121b414e6aa0cae0a96758cf3c8 Mon Sep 17 00:00:00 2001
From: Matthias Andreas Benkard <code@mail.matthias.benkard.de>
Date: Sun, 6 Dec 2020 15:16:22 +0100
Subject: Configure Tika correctly.

With the new configuration, Tika can now extract text from PDFs and
XML documents.

Also configures logging for the application.

Change-Id: I7a89c2b232ed4e220665dd335a5f5a0cc3ef2994
---
 .../resources/eu/mulk/aendggner/logging.properties | 17 ++++++++++++
 .../resources/eu/mulk/aendggner/tika-config.xml    | 32 ++++++++++++++++++++++
 2 files changed, 49 insertions(+)
 create mode 100644 src/main/resources/eu/mulk/aendggner/logging.properties
 create mode 100644 src/main/resources/eu/mulk/aendggner/tika-config.xml

(limited to 'src/main/resources/eu')

diff --git a/src/main/resources/eu/mulk/aendggner/logging.properties b/src/main/resources/eu/mulk/aendggner/logging.properties
new file mode 100644
index 0000000..cdebd0e
--- /dev/null
+++ b/src/main/resources/eu/mulk/aendggner/logging.properties
@@ -0,0 +1,17 @@
+#
+# General settings
+#
+handlers=java.util.logging.ConsoleHandler
+java.util.logging.SimpleFormatter.format=%1$tY-%1$tm-%1$td %1$tH:%1$tM:%1$tS  %4$-11s  %2$-40s  %5$s %6$s%n
+java.util.logging.ConsoleHandler.level=ALL
+.level=INFO
+#
+# Application
+#
+eu.mulk.level=ALL
+#
+# 3rd-party libraries
+#
+org.apache.level=WARNING
+org.apache.tika.config.level=SEVERE
+org.apache.pdfbox.pdmodel.graphics.color.PDICCBased.level=SEVERE
diff --git a/src/main/resources/eu/mulk/aendggner/tika-config.xml b/src/main/resources/eu/mulk/aendggner/tika-config.xml
new file mode 100644
index 0000000..7c7983c
--- /dev/null
+++ b/src/main/resources/eu/mulk/aendggner/tika-config.xml
@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<properties>
+  <service-loader dynamic="true" loadErrorHandler="IGNORE"/>
+
+  <encodingDetectors>
+    <encodingDetector class="org.apache.tika.detect.DefaultEncodingDetector"/>
+  </encodingDetectors>
+
+  <translator class="org.apache.tika.language.translate.DefaultTranslator"/>
+
+  <detectors>
+    <detector class="org.apache.tika.detect.DefaultDetector"/>
+  </detectors>
+
+  <parsers>
+
+    <parser class="org.apache.tika.parser.DefaultParser">
+      <parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
+      <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
+    </parser>
+
+    <parser class="org.apache.tika.parser.pdf.PDFParser">
+      <params>
+        <param name="extractInlineImages" type="bool">true</param>
+        <param name="ocrStrategy" type="string">auto</param>
+      </params>
+    </parser>
+
+    <parser class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
+
+  </parsers>
+</properties>
-- 
cgit v1.2.1