Author: mikemccand
Date: Tue Aug 30 22:50:41 2011
New Revision: 1163447
URL: http://svn.apache.org/viewvc?rev=1163447&view=rev
Log:
TIKA-392: use unicode escapes for non-ascii chars
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java?rev=1163447&r1=1163446&r2=1163447&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/rtf/RTFParserTest.java
Tue Aug 30 22:50:41 2011
@@ -84,13 +84,13 @@ public class RTFParserTest extends TikaT
public void testHexEscapeInsideWord() throws Exception {
String content = getText("testRTFHexEscapeInsideWord.rtf");
- assertContains("ESPÃRITO", content);
+ assertContains("ESP\u00cdRITO", content);
}
public void testWindowsCodepage1250() throws Exception {
String content = getText("testRTFWindowsCodepage1250.rtf");
- assertContains("zażóÅÄ gÄÅlÄ
jaźÅ", content);
- assertContains("ZAÅ»ÃÅÄ GÄÅLÄ JAŹÅ", content);
+ assertContains("za\u017c\u00f3\u0142\u0107 g\u0119\u015bl\u0105
ja\u017a\u0144", content);
+ assertContains("ZA\u017b\u00d3\u0141\u0106 G\u0118\u015aL\u0104
JA\u0179\u0143", content);
}
public void testRTFTableCellSeparation() throws Exception {