From cb2c17d236188693f99e8a8e0e8df6fdaee57b1f Mon Sep 17 00:00:00 2001
From: reger <reger18@arcor.de>
Date: Sun, 29 Jun 2014 02:54:09 +0200
Subject: [PATCH] extract author and keywords in .doc and .ppt parser

---
 source/net/yacy/document/parser/docParser.java | 12 ++++++++++--
 source/net/yacy/document/parser/pptParser.java | 10 ++++++++--
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/source/net/yacy/document/parser/docParser.java b/source/net/yacy/document/parser/docParser.java
index 8c0263ac3..a09f9e391 100644
--- a/source/net/yacy/document/parser/docParser.java
+++ b/source/net/yacy/document/parser/docParser.java
@@ -86,6 +86,14 @@ public class docParser extends AbstractParser implements Parser {
             if (title.length() == l) break;
             l = title.length();
         }
+        // get keywords (for yacy as array)
+        final String keywords = extractor.getSummaryInformation().getKeywords();
+        final String[] keywlist;
+        if (keywords != null && !keywords.isEmpty()) {
+            keywlist = keywords.split(",");
+        } else {
+            keywlist = null;
+        }
 
         Document[] docs;
         docs = new Document[]{new Document(
@@ -94,9 +102,9 @@ public class docParser extends AbstractParser implements Parser {
                   "UTF-8",
                   this,
                   null,
-                  null,
+                  keywlist,
                   singleList(title),
-                  "", // TODO: AUTHOR
+                  extractor.getSummaryInformation().getAuthor(), // constuctor can handle null
                   extractor.getDocSummaryInformation().getCompany(), // publisher
                   null,
                   null,
diff --git a/source/net/yacy/document/parser/pptParser.java b/source/net/yacy/document/parser/pptParser.java
index f21f188bf..e0773f2ba 100644
--- a/source/net/yacy/document/parser/pptParser.java
+++ b/source/net/yacy/document/parser/pptParser.java
@@ -78,6 +78,12 @@ public class pptParser extends AbstractParser implements Parser {
                 if (title.length() == l) break;
                 l = title.length();
             }
+            // get keywords (for yacy as array)
+            final String keywords = pptExtractor.getSummaryInformation().getKeywords();
+            final String[] keywlist;
+            if (keywords != null && !keywords.isEmpty()) {
+               keywlist = keywords.split(",");
+            } else keywlist = null;
 
             /*
              * create the plasmaParserDocument for the database
@@ -89,9 +95,9 @@ public class pptParser extends AbstractParser implements Parser {
                     "UTF-8",
                     this,
                     null,
-                    null,
+                    keywlist,
                     singleList(title),
-                    "", // TODO: AUTHOR
+                    pptExtractor.getSummaryInformation().getAuthor(), // may be null
                     pptExtractor.getDocSummaryInformation().getCompany(),
                     null,
                     null,