You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2023/08/16 18:01:47 UTC
[tika] branch TIKA-3109 updated: TIKA-3109 -- parse iframe's srcdoc as an embedded document -- add check for iframe and remove debug
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch TIKA-3109
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/TIKA-3109 by this push:
new 83793014f TIKA-3109 -- parse iframe's srcdoc as an embedded document -- add check for iframe and remove debug
83793014f is described below
commit 83793014f588214152e5e92c7653b36a63739432
Author: tallison <ta...@apache.org>
AuthorDate: Wed Aug 16 14:01:39 2023 -0400
TIKA-3109 -- parse iframe's srcdoc as an embedded document -- add check for iframe and remove debug
---
.../src/main/java/org/apache/tika/parser/html/HtmlHandler.java | 9 +++++----
.../src/test/java/org/apache/tika/parser/html/SrcDocTest.java | 1 -
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
index 79c48aaea..3050422c4 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/java/org/apache/tika/parser/html/HtmlHandler.java
@@ -187,10 +187,11 @@ class HtmlHandler extends TextContentHandler {
handleDataURIScheme(value);
}
}
- String srcDoc = atts.getValue("srcdoc");
- if (! StringUtils.isBlank(srcDoc)) {
- //check for iframe?
- handleSrcDoc(srcDoc);
+ if ("IFRAME".equals(name)) {
+ String srcDoc = atts.getValue("srcdoc");
+ if (!StringUtils.isBlank(srcDoc)) {
+ handleSrcDoc(srcDoc);
+ }
}
}
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/SrcDocTest.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/SrcDocTest.java
index 64f1189f3..e7f6d1c70 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/SrcDocTest.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/SrcDocTest.java
@@ -33,7 +33,6 @@ public class SrcDocTest extends TikaTest {
@Test
public void testBasic() throws Exception {
List<Metadata> metadataList = getRecursiveMetadata("testSrcDoc.html");
- debug(metadataList);
assertEquals(2, metadataList.size());
assertContains("outside", metadataList.get(0).get(TikaCoreProperties.TIKA_CONTENT));
assertContains("this is the iframe content",