From d9b817cba6daeae7ccbe8f88d14c878d78e8646c Mon Sep 17 00:00:00 2001 From: "k.privezentsev" Date: Wed, 29 May 2013 15:20:30 +0400 Subject: [PATCH] TIKA-1128 Replace line tabular by line break, when extracting text from Word document --- .../tika/parser/microsoft/WordExtractor.java | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java index 11ffb7d..4640333 100644 --- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java +++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/WordExtractor.java @@ -309,6 +309,9 @@ public class WordExtractor extends AbstractPOIFSExtractor { // Copied from POI's org/apache/poi/hwpf/converter/AbstractWordConverter.processCharacters: + // line tabulator as break line + text = text.replace((char)0x000b,'\n'); + // Non-breaking hyphens are returned as char 30 text = text.replace((char) 30, UNICODECHAR_NONBREAKING_HYPHEN); -- 1.7.9.5