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 2016/04/19 21:57:10 UTC
tika git commit: epub mime can sometimes end in newline. Too small
for jira, test, imho.
Repository: tika
Updated Branches:
refs/heads/2.x 20834d0b0 -> 2fdd44cd0
epub mime can sometimes end in newline. Too small for jira, test, imho.
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/2fdd44cd
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/2fdd44cd
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/2fdd44cd
Branch: refs/heads/2.x
Commit: 2fdd44cd0c890533acff8bcf27c1add3d0222608
Parents: 20834d0
Author: tballison <ta...@mitre.org>
Authored: Tue Apr 19 15:57:02 2016 -0400
Committer: tballison <ta...@mitre.org>
Committed: Tue Apr 19 15:57:02 2016 -0400
----------------------------------------------------------------------
.../main/java/org/apache/tika/parser/epub/EpubParser.java | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/2fdd44cd/tika-parser-modules/tika-parser-ebook-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java
----------------------------------------------------------------------
diff --git a/tika-parser-modules/tika-parser-ebook-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java b/tika-parser-modules/tika-parser-ebook-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java
index 1af5e0f..14e6cf8 100644
--- a/tika-parser-modules/tika-parser-ebook-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java
+++ b/tika-parser-modules/tika-parser-ebook-module/src/main/java/org/apache/tika/parser/epub/EpubParser.java
@@ -16,6 +16,8 @@
*/
package org.apache.tika.parser.epub;
+import static java.nio.charset.StandardCharsets.UTF_8;
+
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
@@ -40,8 +42,6 @@ import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
-import static java.nio.charset.StandardCharsets.UTF_8;
-
/**
* Epub parser
*/
@@ -96,6 +96,10 @@ public class EpubParser extends AbstractParser {
while (entry != null) {
if (entry.getName().equals("mimetype")) {
String type = IOUtils.toString(zip, UTF_8);
+ //often has trailing new lines
+ if (type != null) {
+ type = type.trim();
+ }
metadata.set(Metadata.CONTENT_TYPE, type);
} else if (entry.getName().equals("metadata.xml")) {
meta.parse(zip, new DefaultHandler(), metadata, context);