Index: tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java =================================================================== --- tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java (Revision 1639854) +++ tika-parsers/src/test/java/org/apache/tika/parser/microsoft/WordParserTest.java (Arbeitskopie) @@ -397,4 +397,9 @@ assertContains("
1. Organisering av vakten:
", xml); } + + @Test + public void testSpecialCharacters() throws Exception { + assertContains("Here are a few characters from the Symbol font: ∞ (infinity sign), … (three dots), • (bullet), ≥ (greater than equals), β (beta).", getXML("testWORD_specialcharacters.doc").xml); + } }