metadata_spec.js 11 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118
  1. /**
  2. * @licstart The following is the entire license notice for the
  3. * Javascript code in this page
  4. *
  5. * Copyright 2019 Mozilla Foundation
  6. *
  7. * Licensed under the Apache License, Version 2.0 (the "License");
  8. * you may not use this file except in compliance with the License.
  9. * You may obtain a copy of the License at
  10. *
  11. * http://www.apache.org/licenses/LICENSE-2.0
  12. *
  13. * Unless required by applicable law or agreed to in writing, software
  14. * distributed under the License is distributed on an "AS IS" BASIS,
  15. * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  16. * See the License for the specific language governing permissions and
  17. * limitations under the License.
  18. *
  19. * @licend The above is the entire license notice for the
  20. * Javascript code in this page
  21. */
  22. "use strict";
  23. var _util = require("../../shared/util");
  24. var _metadata = require("../../display/metadata");
  25. describe('metadata', function () {
  26. it('should handle valid metadata', function () {
  27. var data = '<x:xmpmeta xmlns:x=\'adobe:ns:meta/\'>' + '<rdf:RDF xmlns:rdf=\'http://www.w3.org/1999/02/22-rdf-syntax-ns#\'>' + '<rdf:Description xmlns:dc=\'http://purl.org/dc/elements/1.1/\'>' + '<dc:title><rdf:Alt><rdf:li xml:lang="x-default">Foo bar baz</rdf:li>' + '</rdf:Alt></dc:title></rdf:Description></rdf:RDF></x:xmpmeta>';
  28. var metadata = new _metadata.Metadata(data);
  29. expect(metadata.has('dc:title')).toBeTruthy();
  30. expect(metadata.has('dc:qux')).toBeFalsy();
  31. expect(metadata.get('dc:title')).toEqual('Foo bar baz');
  32. expect(metadata.get('dc:qux')).toEqual(null);
  33. expect(metadata.getAll()).toEqual({
  34. 'dc:title': 'Foo bar baz'
  35. });
  36. });
  37. it('should repair and handle invalid metadata', function () {
  38. var data = '<x:xmpmeta xmlns:x=\'adobe:ns:meta/\'>' + '<rdf:RDF xmlns:rdf=\'http://www.w3.org/1999/02/22-rdf-syntax-ns#\'>' + '<rdf:Description xmlns:dc=\'http://purl.org/dc/elements/1.1/\'>' + '<dc:title>\\376\\377\\000P\\000D\\000F\\000&</dc:title>' + '</rdf:Description></rdf:RDF></x:xmpmeta>';
  39. var metadata = new _metadata.Metadata(data);
  40. expect(metadata.has('dc:title')).toBeTruthy();
  41. expect(metadata.has('dc:qux')).toBeFalsy();
  42. expect(metadata.get('dc:title')).toEqual('PDF&');
  43. expect(metadata.get('dc:qux')).toEqual(null);
  44. expect(metadata.getAll()).toEqual({
  45. 'dc:title': 'PDF&'
  46. });
  47. });
  48. it('should repair and handle invalid metadata (bug 1424938)', function () {
  49. var data = '<x:xmpmeta xmlns:x=\'adobe:ns:meta/\' ' + 'x:xmptk=\'XMP toolkit 2.9.1-13, framework 1.6\'>' + '<rdf:RDF xmlns:rdf=\'http://www.w3.org/1999/02/22-rdf-syntax-ns#\' ' + 'xmlns:iX=\'http://ns.adobe.com/iX/1.0/\'>' + '<rdf:Description rdf:about=\'61652fa7-fc1f-11dd-0000-ce81d41f9ecf\' ' + 'xmlns:pdf=\'http://ns.adobe.com/pdf/1.3/\' ' + 'pdf:Producer=\'GPL Ghostscript 8.63\'/>' + '<rdf:Description rdf:about=\'61652fa7-fc1f-11dd-0000-ce81d41f9ecf\' ' + 'xmlns:xap=\'http://ns.adobe.com/xap/1.0/\' ' + 'xap:ModifyDate=\'2009-02-13T12:42:54+01:00\' ' + 'xap:CreateDate=\'2009-02-13T12:42:54+01:00\'>' + '<xap:CreatorTool>\\376\\377\\000P\\000D\\000F\\000C\\000r\\000e\\000a' + '\\000t\\000o\\000r\\000 \\000V\\000e\\000r\\000s\\000i\\000o\\000n' + '\\000 \\0000\\000.\\0009\\000.\\0006</xap:CreatorTool>' + '</rdf:Description><rdf:Description ' + 'rdf:about=\'61652fa7-fc1f-11dd-0000-ce81d41f9ecf\' ' + 'xmlns:xapMM=\'http://ns.adobe.com/xap/1.0/mm/\' ' + 'xapMM:DocumentID=\'61652fa7-fc1f-11dd-0000-ce81d41f9ecf\'/>' + '<rdf:Description rdf:about=\'61652fa7-fc1f-11dd-0000-ce81d41f9ecf\' ' + 'xmlns:dc=\'http://purl.org/dc/elements/1.1/\' ' + 'dc:format=\'application/pdf\'><dc:title><rdf:Alt>' + '<rdf:li xml:lang=\'x-default\'>\\376\\377\\000L\\000&apos;\\000O\\000d' + '\\000i\\000s\\000s\\000e\\000e\\000 \\000t\\000h\\000\\351\\000m\\000a' + '\\000t\\000i\\000q\\000u\\000e\\000 \\000l\\000o\\000g\\000o\\000 ' + '\\000O\\000d\\000i\\000s\\000s\\000\\351\\000\\351\\000 \\000-\\000 ' + '\\000d\\000\\351\\000c\\000e\\000m\\000b\\000r\\000e\\000 \\0002\\0000' + '\\0000\\0008\\000.\\000p\\000u\\000b</rdf:li></rdf:Alt></dc:title>' + '<dc:creator><rdf:Seq><rdf:li>\\376\\377\\000O\\000D\\000I\\000S' + '</rdf:li></rdf:Seq></dc:creator></rdf:Description></rdf:RDF>' + '</x:xmpmeta>';
  50. var metadata = new _metadata.Metadata(data);
  51. expect(metadata.has('dc:title')).toBeTruthy();
  52. expect(metadata.has('dc:qux')).toBeFalsy();
  53. expect(metadata.get('dc:title')).toEqual('L\'Odissee thématique logo Odisséé - décembre 2008.pub');
  54. expect(metadata.get('dc:qux')).toEqual(null);
  55. expect(metadata.getAll()).toEqual({
  56. 'dc:creator': 'ODIS',
  57. 'dc:title': 'L\'Odissee thématique logo Odisséé - décembre 2008.pub',
  58. 'xap:creatortool': 'PDFCreator Version 0.9.6'
  59. });
  60. });
  61. it('should gracefully handle incomplete tags (issue 8884)', function () {
  62. var data = '<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d' + '<x:xmpmeta xmlns:x="adobe:ns:meta/">' + '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">' + '<rdf:Description rdf:about=""' + 'xmlns:pdfx="http://ns.adobe.com/pdfx/1.3/">' + '</rdf:Description>' + '<rdf:Description rdf:about=""' + 'xmlns:xap="http://ns.adobe.com/xap/1.0/">' + '<xap:ModifyDate>2010-03-25T11:20:09-04:00</xap:ModifyDate>' + '<xap:CreateDate>2010-03-25T11:20:09-04:00</xap:CreateDate>' + '<xap:MetadataDate>2010-03-25T11:20:09-04:00</xap:MetadataDate>' + '</rdf:Description>' + '<rdf:Description rdf:about=""' + 'xmlns:dc="http://purl.org/dc/elements/1.1/">' + '<dc:format>application/pdf</dc:format>' + '</rdf:Description>' + '<rdf:Description rdf:about=""' + 'xmlns:pdfaid="http://www.aiim.org/pdfa/ns/id/">' + '<pdfaid:part>1</pdfaid:part>' + '<pdfaid:conformance>A</pdfaid:conformance>' + '</rdf:Description>' + '</rdf:RDF>' + '</x:xmpmeta>' + '<?xpacket end="w"?>';
  63. var metadata = new _metadata.Metadata(data);
  64. expect((0, _util.isEmptyObj)(metadata.getAll())).toEqual(true);
  65. });
  66. it('should gracefully handle "junk" before the actual metadata (issue 10395)', function () {
  67. var data = '<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d"?>' + '<x:xmpmeta x:xmptk="TallComponents PDFObjects 1.0" ' + 'xmlns:x="adobe:ns:meta/">' + '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">' + '<rdf:Description rdf:about="" ' + 'xmlns:pdf="http://ns.adobe.com/pdf/1.3/">' + '<pdf:Producer>PDFKit.NET 4.0.102.0</pdf:Producer>' + '<pdf:Keywords></pdf:Keywords>' + '<pdf:PDFVersion>1.7</pdf:PDFVersion></rdf:Description>' + '<rdf:Description rdf:about="" ' + 'xmlns:xap="http://ns.adobe.com/xap/1.0/">' + '<xap:CreateDate>2018-12-27T13:50:36-08:00</xap:CreateDate>' + '<xap:ModifyDate>2018-12-27T13:50:38-08:00</xap:ModifyDate>' + '<xap:CreatorTool></xap:CreatorTool>' + '<xap:MetadataDate>2018-12-27T13:50:38-08:00</xap:MetadataDate>' + '</rdf:Description><rdf:Description rdf:about="" ' + 'xmlns:dc="http://purl.org/dc/elements/1.1/">' + '<dc:creator><rdf:Seq><rdf:li></rdf:li></rdf:Seq></dc:creator>' + '<dc:subject><rdf:Bag /></dc:subject>' + '<dc:description><rdf:Alt><rdf:li xml:lang="x-default">' + '</rdf:li></rdf:Alt></dc:description>' + '<dc:title><rdf:Alt><rdf:li xml:lang="x-default"></rdf:li>' + '</rdf:Alt></dc:title><dc:format>application/pdf</dc:format>' + '</rdf:Description></rdf:RDF></x:xmpmeta><?xpacket end="w"?>';
  68. var metadata = new _metadata.Metadata(data);
  69. expect(metadata.has('dc:title')).toBeTruthy();
  70. expect(metadata.has('dc:qux')).toBeFalsy();
  71. expect(metadata.get('dc:title')).toEqual('');
  72. expect(metadata.get('dc:qux')).toEqual(null);
  73. expect(metadata.getAll()).toEqual({
  74. 'dc:creator': '',
  75. 'dc:description': '',
  76. 'dc:format': 'application/pdf',
  77. 'dc:subject': '',
  78. 'dc:title': '',
  79. 'pdf:keywords': '',
  80. 'pdf:pdfversion': '1.7',
  81. 'pdf:producer': 'PDFKit.NET 4.0.102.0',
  82. 'xap:createdate': '2018-12-27T13:50:36-08:00',
  83. 'xap:creatortool': '',
  84. 'xap:metadatadate': '2018-12-27T13:50:38-08:00',
  85. 'xap:modifydate': '2018-12-27T13:50:38-08:00'
  86. });
  87. });
  88. it('should correctly handle metadata containing "&apos" (issue 10407)', function () {
  89. var data = '<x:xmpmeta xmlns:x=\'adobe:ns:meta/\'>' + '<rdf:RDF xmlns:rdf=\'http://www.w3.org/1999/02/22-rdf-syntax-ns#\'>' + '<rdf:Description xmlns:dc=\'http://purl.org/dc/elements/1.1/\'>' + '<dc:title><rdf:Alt>' + '<rdf:li xml:lang="x-default">&apos;Foo bar baz&apos;</rdf:li>' + '</rdf:Alt></dc:title></rdf:Description></rdf:RDF></x:xmpmeta>';
  90. var metadata = new _metadata.Metadata(data);
  91. expect(metadata.has('dc:title')).toBeTruthy();
  92. expect(metadata.has('dc:qux')).toBeFalsy();
  93. expect(metadata.get('dc:title')).toEqual('\'Foo bar baz\'');
  94. expect(metadata.get('dc:qux')).toEqual(null);
  95. expect(metadata.getAll()).toEqual({
  96. 'dc:title': '\'Foo bar baz\''
  97. });
  98. });
  99. it('should gracefully handle unbalanced end tags (issue 10410)', function () {
  100. var data = '<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d"?>' + '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">' + '<rdf:Description rdf:about="" ' + 'xmlns:pdf="http://ns.adobe.com/pdf/1.3/">' + '<pdf:Producer>Soda PDF 5</pdf:Producer></rdf:Description>' + '<rdf:Description rdf:about="" ' + 'xmlns:xap="http://ns.adobe.com/xap/1.0/">' + '<xap:CreateDate>2018-10-02T08:14:49-05:00</xap:CreateDate>' + '<xap:CreatorTool>Soda PDF 5</xap:CreatorTool>' + '<xap:MetadataDate>2018-10-02T08:14:49-05:00</xap:MetadataDate> ' + '<xap:ModifyDate>2018-10-02T08:14:49-05:00</xap:ModifyDate>' + '</rdf:Description><rdf:Description rdf:about="" ' + 'xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/">' + '<xmpMM:DocumentID>uuid:00000000-1c84-3cf9-89ba-bef0e729c831' + '</xmpMM:DocumentID></rdf:Description>' + '</rdf:RDF></x:xmpmeta><?xpacket end="w"?>';
  101. var metadata = new _metadata.Metadata(data);
  102. expect((0, _util.isEmptyObj)(metadata.getAll())).toEqual(true);
  103. });
  104. it('should not be vulnerable to the billion laughs attack', function () {
  105. var data = '<?xml version="1.0"?>' + '<!DOCTYPE lolz [' + ' <!ENTITY lol "lol">' + ' <!ENTITY lol1 "&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;&lol;">' + ' <!ENTITY lol2 "&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;&lol1;">' + ' <!ENTITY lol3 "&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;&lol2;">' + ' <!ENTITY lol4 "&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;&lol3;">' + ' <!ENTITY lol5 "&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;&lol4;">' + ' <!ENTITY lol6 "&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;&lol5;">' + ' <!ENTITY lol7 "&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;&lol6;">' + ' <!ENTITY lol8 "&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;&lol7;">' + ' <!ENTITY lol9 "&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;&lol8;">' + ']>' + '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">' + ' <rdf:Description xmlns:dc="http://purl.org/dc/elements/1.1/">' + ' <dc:title>' + ' <rdf:Alt>' + ' <rdf:li xml:lang="x-default">a&lol9;b</rdf:li>' + ' </rdf:Alt>' + ' </dc:title>' + ' </rdf:Description>' + '</rdf:RDF>';
  106. var metadata = new _metadata.Metadata(data);
  107. expect(metadata.has('dc:title')).toBeTruthy();
  108. expect(metadata.has('dc:qux')).toBeFalsy();
  109. expect(metadata.get('dc:title')).toEqual('a&lol9;b');
  110. expect(metadata.get('dc:qux')).toEqual(null);
  111. expect(metadata.getAll()).toEqual({
  112. 'dc:title': 'a&lol9;b'
  113. });
  114. });
  115. });