From 6a9f4ca6930bc4160030c9e21885af476eeeded6 Mon Sep 17 00:00:00 2001
From: PeterAlfredLee <peteralfredlee@gmail.com>
Date: Tue, 25 Aug 2020 16:50:37 +0800
Subject: [PATCH] Modify default encoding detector

Replace HtmlEncodingDetector to StandardHtmlEncodingDetector
Adjust some test case
---
 .../META-INF/services/org.apache.tika.detect.EncodingDetector | 1 +
 .../java/org/apache/tika/config/TikaEncodingDetectorTest.java | 3 ++-
 .../config/TIKA-2273-exclude-encoding-detector-default.xml    | 4 ++--
 3 files changed, 5 insertions(+), 3 deletions(-)
 create mode 100644 tika-parsers/tika-parser-html-module/src/main/resources/META-INF/services/org.apache.tika.detect.EncodingDetector

diff --git a/tika-parsers/tika-parser-html-module/src/main/resources/META-INF/services/org.apache.tika.detect.EncodingDetector b/tika-parsers/tika-parser-html-module/src/main/resources/META-INF/services/org.apache.tika.detect.EncodingDetector
new file mode 100644
index 00000000000..278536c0633
--- /dev/null
+++ b/tika-parsers/tika-parser-html-module/src/main/resources/META-INF/services/org.apache.tika.detect.EncodingDetector
@@ -0,0 +1 @@
+org.apache.tika.parser.html.charsetdetector.StandardHtmlEncodingDetector
\ No newline at end of file
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
index 4d5c66b4e96..883fd3e4f42 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/java/org/apache/tika/config/TikaEncodingDetectorTest.java
@@ -43,6 +43,7 @@
 import org.apache.tika.parser.Parser;
 import org.apache.tika.parser.ParserDecorator;
 import org.apache.tika.parser.html.HtmlEncodingDetector;
+import org.apache.tika.parser.html.charsetdetector.StandardHtmlEncodingDetector;
 import org.apache.tika.parser.txt.Icu4jEncodingDetector;
 import org.apache.tika.parser.txt.TXTParser;
 import org.apache.tika.parser.txt.UniversalEncodingDetector;
@@ -56,7 +57,7 @@ public void testDefault() {
         assertTrue(detector instanceof CompositeEncodingDetector);
         List<EncodingDetector> detectors = ((CompositeEncodingDetector) detector).getDetectors();
         assertEquals(3, detectors.size());
-        assertTrue(detectors.get(0) instanceof HtmlEncodingDetector);
+        assertTrue(detectors.get(0) instanceof StandardHtmlEncodingDetector);
         assertTrue(detectors.get(1) instanceof UniversalEncodingDetector);
         assertTrue(detectors.get(2) instanceof Icu4jEncodingDetector);
     }
diff --git a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/resources/org/apache/tika/config/TIKA-2273-exclude-encoding-detector-default.xml b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/resources/org/apache/tika/config/TIKA-2273-exclude-encoding-detector-default.xml
index 8f4de2258fd..5167c2dc01d 100644
--- a/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/resources/org/apache/tika/config/TIKA-2273-exclude-encoding-detector-default.xml
+++ b/tika-parsers/tika-parsers-classic/tika-parsers-classic-modules/tika-parser-integration-tests/src/test/resources/org/apache/tika/config/TIKA-2273-exclude-encoding-detector-default.xml
@@ -19,9 +19,9 @@
     <!-- Explicitly request default parsers -->
     <parsers/>
     <encodingDetectors>
-        <!-- All detectors except HtmlEncodingDetector -->
+        <!-- All detectors except StandardHtmlEncodingDetector -->
         <encodingDetector class="org.apache.tika.detect.DefaultEncodingDetector">
-            <encodingDetector-exclude class="org.apache.tika.parser.html.HtmlEncodingDetector"/>
+            <encodingDetector-exclude class="org.apache.tika.parser.html.charsetdetector.StandardHtmlEncodingDetector"/>
         </encodingDetector>
         <!-- One other detector, to check ordering -->
         <encodingDetector class="org.apache.tika.detect.NonDetectingEncodingDetector"/>