src/main/java/org/apache/tika/parser/microsoft/PropertiesReaderListener.java

   1 /**
   2  * Licensed to the Apache Software Foundation (ASF) under one or more
   3  * contributor license agreements.  See the NOTICE file distributed with
   4  * this work for additional information regarding copyright ownership.
   5  * The ASF licenses this file to You under the Apache License, Version 2.0
   6  * (the "License"); you may not use this file except in compliance with
   7  * the License.  You may obtain a copy of the License at
   8  *
   9  *     http://www.apache.org/licenses/LICENSE-2.0
  10  *
  11  * Unless required by applicable law or agreed to in writing, software
  12  * distributed under the License is distributed on an "AS IS" BASIS,
  13  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14  * See the License for the specific language governing permissions and
  15  * limitations under the License.
  16  */
  17 package org.apache.tika.parser.microsoft;
  18
  19 import org.apache.poi.hpsf.PropertySetFactory;
  20 import org.apache.poi.hpsf.SummaryInformation;
  21 import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent;
  22 import org.apache.poi.poifs.eventfilesystem.POIFSReaderListener;
  23 import org.apache.tika.metadata.Metadata;
  24
  25 class PropertiesReaderListener implements POIFSReaderListener {
  26
  27     private final Metadata metadata;
  28
  29     public PropertiesReaderListener(Metadata metadata) {
  30         this.metadata = metadata;
  31     }
  32
  33     public void processPOIFSReaderEvent(POIFSReaderEvent event) {
  34         if (!event.getName().startsWith(
  35                 SummaryInformation.DEFAULT_STREAM_NAME)) {
  36             return;
  37         }
  38
  39         try {
  40             SummaryInformation si = (SummaryInformation)
  41                 PropertySetFactory.create(event.getStream());
  42             if (si.getTitle() != null) {
  43                 metadata.set(Metadata.TITLE, si.getTitle());
  44             }
  45             if (si.getAuthor() != null) {
  46                 metadata.set(Metadata.AUTHOR, si.getAuthor());
  47             }
  48             if (si.getKeywords() != null) {
  49                 metadata.set(Metadata.KEYWORDS, si.getKeywords());
  50             }
  51             if (si.getSubject() != null) {
  52                 metadata.set(Metadata.SUBJECT, si.getSubject());
  53             }
  54             if (si.getLastAuthor() != null) {
  55                 metadata.set(Metadata.LAST_AUTHOR, si.getLastAuthor());
  56             }
  57             if (si.getComments() != null) {
  58                 metadata.set(Metadata.COMMENTS, si.getComments());
  59             }
  60             if (si.getTemplate() != null) {
  61                 metadata.set(Metadata.TEMPLATE, si.getTemplate());
  62             }
  63             if (si.getApplicationName() != null) {
  64                 metadata.set(Metadata.APPLICATION_NAME, si.getApplicationName());
  65             }
  66             if (si.getRevNumber() != null) {
  67                 metadata.set(Metadata.REVISION_NUMBER, si.getRevNumber());
  68             }
  69             if (si.getCreateDateTime() != null) {
  70                 metadata.set("creationdate", si.getCreateDateTime().toString());
  71             }
  72             if (si.getCharCount() > 0) {
  73                 metadata.set(
  74                         Metadata.CHARACTER_COUNT,
  75                         Integer.toString(si.getCharCount()));
  76             }
  77             if (si.getEditTime() > 0) {
  78                 metadata.set("edittime", Long.toString(si.getEditTime()));
  79             }
  80             if (si.getLastSaveDateTime() != null) {
  81                 metadata.set(
  82                         Metadata.LAST_SAVED,
  83                         si.getLastSaveDateTime().toString());
  84             }
  85             if (si.getPageCount() > 0) {
  86                 metadata.set(
  87                         Metadata.PAGE_COUNT,
  88                         Integer.toString(si.getPageCount()));
  89             }
  90             if (si.getSecurity() > 0) {
  91                 metadata.set(
  92                         "security", Integer.toString(si.getSecurity()));
  93             }
  94             if (si.getWordCount() > 0) {
  95                 metadata.set(
  96                         Metadata.WORD_COUNT,
  97                         Integer.toString(si.getWordCount()));
  98             }
  99             if (si.getLastPrinted() != null) {
 100                 metadata.set(
 101                         Metadata.LAST_PRINTED,
 102                         si.getLastPrinted().toString());
 103             }
 104         } catch (Exception ex) {
 105         }
 106     }
 107 }