Author: jukka
Date: Fri Oct 2 10:57:44 2009
New Revision: 820960
URL: http://svn.apache.org/viewvc?rev=820960&view=rev
Log:
TIKA-256: MSWord parser does not extract footnotes and comments
Patch by Maxim Valyanskiy
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java?rev=820960&r1=820959&r2=820960&view=diff
==============================================================================
---
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
(original)
+++
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OfficeParser.java
Fri Oct 2 10:57:44 2009
@@ -85,10 +85,25 @@
} else if ("WordDocument".equals(name)) {
setType(metadata, "application/msword");
WordExtractor extractor = new WordExtractor(filesystem);
+
addTextIfAny(xhtml, "header", extractor.getHeaderText());
+
for (String paragraph : extractor.getParagraphText()) {
xhtml.element("p", paragraph);
}
+
+ for (String paragraph : extractor.getFootnoteText()) {
+ xhtml.element("p", paragraph);
+ }
+
+ for (String paragraph : extractor.getCommentsText()) {
+ xhtml.element("p", paragraph);
+ }
+
+ for (String paragraph : extractor.getEndnoteText()) {
+ xhtml.element("p", paragraph);
+ }
+
addTextIfAny(xhtml, "footer", extractor.getFooterText());
} else if ("PowerPoint Document".equals(name)) {
setType(metadata, "application/vnd.ms-powerpoint");