You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

TestEmbeddedExtractor.java 4.7KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115
  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. http://www.apache.org/licenses/LICENSE-2.0
  9. Unless required by applicable law or agreed to in writing, software
  10. distributed under the License is distributed on an "AS IS" BASIS,
  11. WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12. See the License for the specific language governing permissions and
  13. limitations under the License.
  14. ==================================================================== */
  15. package org.apache.poi.ss.extractor;
  16. import static org.junit.Assert.assertEquals;
  17. import java.io.IOException;
  18. import java.io.InputStream;
  19. import java.security.MessageDigest;
  20. import java.security.NoSuchAlgorithmException;
  21. import java.util.ArrayList;
  22. import java.util.List;
  23. import javax.xml.bind.DatatypeConverter;
  24. import org.apache.poi.EncryptedDocumentException;
  25. import org.apache.poi.POIDataSamples;
  26. import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
  27. import org.apache.poi.ss.usermodel.Sheet;
  28. import org.apache.poi.ss.usermodel.Workbook;
  29. import org.apache.poi.ss.usermodel.WorkbookFactory;
  30. import org.junit.Test;
  31. public class TestEmbeddedExtractor {
  32. private static final POIDataSamples samples = POIDataSamples.getSpreadSheetInstance();
  33. @Test
  34. public void extractPDFfromEMF() throws Exception {
  35. InputStream fis = samples.openResourceAsStream("Basic_Expense_Template_2011.xls");
  36. Workbook wb = WorkbookFactory.create(fis);
  37. fis.close();
  38. EmbeddedExtractor ee = new EmbeddedExtractor();
  39. List<EmbeddedData> edList = new ArrayList<EmbeddedData>();
  40. for (Sheet s : wb) {
  41. edList.addAll(ee.extractAll(s));
  42. }
  43. wb.close();
  44. assertEquals(2, edList.size());
  45. String filename1 = "Sample.pdf";
  46. EmbeddedData ed0 = edList.get(0);
  47. assertEquals(filename1, ed0.getFilename());
  48. assertEquals(filename1, ed0.getShape().getShapeName().trim());
  49. assertEquals("uNplB1QpYug+LWappiTh0w==", md5hash(ed0.getEmbeddedData()));
  50. String filename2 = "kalastuslupa_jiyjhnj_yuiyuiyuio_uyte_sldfsdfsdf_sfsdfsdf_sfsssfsf_sdfsdfsdfsdf_sdfsdfsdf.pdf";
  51. EmbeddedData ed1 = edList.get(1);
  52. assertEquals(filename2, ed1.getFilename());
  53. assertEquals(filename2, ed1.getShape().getShapeName().trim());
  54. assertEquals("QjLuAZ+cd7KbhVz4sj+QdA==", md5hash(ed1.getEmbeddedData()));
  55. }
  56. @Test
  57. public void extractFromXSSF() throws IOException, EncryptedDocumentException, InvalidFormatException {
  58. InputStream fis = samples.openResourceAsStream("58325_db.xlsx");
  59. Workbook wb = WorkbookFactory.create(fis);
  60. fis.close();
  61. EmbeddedExtractor ee = new EmbeddedExtractor();
  62. List<EmbeddedData> edList = new ArrayList<EmbeddedData>();
  63. for (Sheet s : wb) {
  64. edList.addAll(ee.extractAll(s));
  65. }
  66. wb.close();
  67. assertEquals(4, edList.size());
  68. EmbeddedData ed0 = edList.get(0);
  69. assertEquals("Object 1.pdf", ed0.getFilename());
  70. assertEquals("Object 1", ed0.getShape().getShapeName().trim());
  71. assertEquals("Oyys6UtQU1gbHYBYqA4NFA==", md5hash(ed0.getEmbeddedData()));
  72. EmbeddedData ed1 = edList.get(1);
  73. assertEquals("Object 2.pdf", ed1.getFilename());
  74. assertEquals("Object 2", ed1.getShape().getShapeName().trim());
  75. assertEquals("xLScPUS0XH+5CTZ2A3neNw==", md5hash(ed1.getEmbeddedData()));
  76. EmbeddedData ed2 = edList.get(2);
  77. assertEquals("Object 3.pdf", ed2.getFilename());
  78. assertEquals("Object 3", ed2.getShape().getShapeName().trim());
  79. assertEquals("rX4klZqJAeM5npb54Gi2+Q==", md5hash(ed2.getEmbeddedData()));
  80. EmbeddedData ed3 = edList.get(3);
  81. assertEquals("Microsoft_Excel_Worksheet1.xlsx", ed3.getFilename());
  82. assertEquals("Object 1", ed3.getShape().getShapeName().trim());
  83. assertEquals("4m4N8ji2tjpEGPQuw2YwGA==", md5hash(ed3.getEmbeddedData()));
  84. }
  85. public static String md5hash(byte[] input) {
  86. try {
  87. MessageDigest md = MessageDigest.getInstance("MD5");
  88. byte hash[] = md.digest(input);
  89. return DatatypeConverter.printBase64Binary(hash);
  90. } catch (NoSuchAlgorithmException e) {
  91. // doesn't happen
  92. return "";
  93. }
  94. }
  95. }