[tika] branch master updated: TIKA-2550 -- make sure that ToTextHandler's new behavior of ignoring script/style contents doesn't harm macro extraction in HTML parser

[ta...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/master by this push:
     new a178f61  TIKA-2550 -- make sure that ToTextHandler's new behavior of ignoring script/style contents doesn't harm macro extraction in HTML parser
a178f61 is described below

commit a178f61b1ba63f2e81d4c0fb6244a03de95f6399
Author: TALLISON <ta...@apache.org>
AuthorDate: Mon Dec 3 10:23:57 2018 -0500

    TIKA-2550 -- make sure that ToTextHandler's new behavior of
    ignoring script/style contents doesn't harm macro extraction in HTML parser
---
 tika-core/src/test/java/org/apache/tika/TikaTest.java               | 6 +++++-
 .../src/test/java/org/apache/tika/parser/html/HtmlParserTest.java   | 5 ++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/tika-core/src/test/java/org/apache/tika/TikaTest.java b/tika-core/src/test/java/org/apache/tika/TikaTest.java
index aae63e0..dde60a3 100644
--- a/tika-core/src/test/java/org/apache/tika/TikaTest.java
+++ b/tika-core/src/test/java/org/apache/tika/TikaTest.java
@@ -244,9 +244,13 @@ public abstract class TikaTest {
     }
 
     protected List<Metadata> getRecursiveMetadata(String filePath, Parser parserToWrap) throws Exception {
+        return getRecursiveMetadata(filePath, parserToWrap, BasicContentHandlerFactory.HANDLER_TYPE.XML);
+    }
+
+    protected List<Metadata> getRecursiveMetadata(String filePath, Parser parserToWrap, BasicContentHandlerFactory.HANDLER_TYPE handlerType) throws Exception {
         RecursiveParserWrapper wrapper = new RecursiveParserWrapper(parserToWrap);
         RecursiveParserWrapperHandler handler = new RecursiveParserWrapperHandler(
-                new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
+                new BasicContentHandlerFactory(handlerType, -1));
         try (InputStream is = getResourceAsStream("/test-documents/" + filePath)) {
             wrapper.parse(is, handler, new Metadata(), new ParseContext());
         }
diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
index e04a16f..a5a3aa8 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
@@ -68,6 +68,7 @@ import org.apache.tika.parser.AutoDetectParser;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
 import org.apache.tika.sax.AbstractRecursiveParserWrapperHandler;
+import org.apache.tika.sax.BasicContentHandlerFactory;
 import org.apache.tika.sax.BodyContentHandler;
 import org.apache.tika.sax.LinkContentHandler;
 import org.apache.tika.sax.RecursiveParserWrapperHandler;
@@ -1289,8 +1290,10 @@ public class HtmlParserTest extends TikaTest {
     public void testExtractScript() throws Exception {
         HtmlParser p = new HtmlParser();
         p.setExtractScripts(true);
+        //TIKA-2550 -- make absolutely sure that macros are still extracted
+        //with the ToTextHandler
         List<Metadata> metadataList = getRecursiveMetadata("testHTMLGoodScript.html",
-                p);
+                p, BasicContentHandlerFactory.HANDLER_TYPE.TEXT);
         assertEquals(2, metadataList.size());
         assertEquals("MACRO", metadataList.get(1).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE));
         assertContains("cool",