src/scratchpad/ooxml-testcases/org/apache/poi/hwpf/extractor/TestHXFWordExtractor.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.poi.hwpf.extractor;
  18
  19 import java.io.File;
  20
  21 import org.apache.poi.hwpf.HWPFXML;
  22 import org.apache.poi.hwpf.usermodel.HWPFXMLDocument;
  23 import org.apache.poi.hxf.HXFDocument;
  24
  25 import junit.framework.TestCase;
  26
  27 /**
  28  * Tests for HXFWordExtractor
  29  */
  30 public class TestHXFWordExtractor extends TestCase {
  31         /**
  32          * A very simple file
  33          */
  34         private HWPFXML xmlA;
  35         /**
  36          * A fairly complex file
  37          */
  38         private HWPFXML xmlB;
  39
  40         protected void setUp() throws Exception {
  41                 super.setUp();
  42
  43                 File fileA = new File(
  44                                 System.getProperty("HWPF.testdata.path") +
  45                                 File.separator + "sample.docx"
  46                 );
  47                 File fileB = new File(
  48                                 System.getProperty("HWPF.testdata.path") +
  49                                 File.separator + "IllustrativeCases.docx"
  50                 );
  51
  52                 xmlA = new HWPFXML(HXFDocument.openPackage(fileA));
  53                 xmlB = new HWPFXML(HXFDocument.openPackage(fileB));
  54         }
  55
  56         /**
  57          * Get text out of the simple file
  58          */
  59         public void testGetSimpleText() throws Exception {
  60                 new HXFWordExtractor(xmlA.getPackage());
  61                 new HXFWordExtractor(new HWPFXMLDocument(xmlA));
  62
  63                 HXFWordExtractor extractor =
  64                         new HXFWordExtractor(xmlA.getPackage());
  65                 extractor.getText();
  66
  67                 String text = extractor.getText();
  68                 assertTrue(text.length() > 0);
  69
  70                 // Check contents
  71                 assertTrue(text.startsWith(
  72                                 "Lorem ipsum dolor sit amet, consectetuer adipiscing elit. Nunc at risus vel erat tempus posuere. Aenean non ante. Suspendisse vehicula dolor sit amet odio."
  73                 ));
  74                 assertTrue(text.endsWith(
  75                                 "Phasellus ultricies mi nec leo. Sed tempus. In sit amet lorem at velit faucibus vestibulum.\n"
  76                 ));
  77
  78                 // Check number of paragraphs
  79                 int ps = 0;
  80                 char[] t = text.toCharArray();
  81                 for (int i = 0; i < t.length; i++) {
  82                         if(t[i] == '\n') { ps++; }
  83                 }
  84                 assertEquals(3, ps);
  85         }
  86
  87         /**
  88          * Tests getting the text out of a complex file
  89          */
  90         public void testGetComplexText() throws Exception {
  91                 HXFWordExtractor extractor =
  92                         new HXFWordExtractor(xmlB.getPackage());
  93                 extractor.getText();
  94
  95                 String text = extractor.getText();
  96                 assertTrue(text.length() > 0);
  97
  98                 char euro = '\u20ac';
  99                 System.err.println("'"+text.substring(text.length() - 20) + "'");
 100
 101                 // Check contents
 102                 assertTrue(text.startsWith(
 103                                 "  \n(V) ILLUSTRATIVE CASES\n\n"
 104                 ));
 105                 assertTrue(text.endsWith(
 106                                 "As well as gaining "+euro+"90 from child benefit increases, he will also receive the early childhood supplement of "+euro+"250 per quarter for Vincent for the full four quarters of the year.\n\n\n\n \n\n\n"
 107                 ));
 108
 109                 // Check number of paragraphs
 110                 int ps = 0;
 111                 char[] t = text.toCharArray();
 112                 for (int i = 0; i < t.length; i++) {
 113                         if(t[i] == '\n') { ps++; }
 114                 }
 115                 assertEquals(79, ps);
 116         }
 117 }