gistfile1.txt

➜  file 89595bd2-8076-4da0-8880-518c291e7904
89595bd2-8076-4da0-8880-518c291e7904: EPUB document

➜  tika -m -j 89595bd2-8076-4da0-8880-518c291e7904
Exception in thread "main" org.apache.tika.exception.TikaException: TIKA-237: Illegal SAXException from org.apache.tika.parser.epub.EpubParser@3a320ade
        at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:310)
        at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:298)
        at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:203)
        at org.apache.tika.cli.TikaCLI$OutputType.process(TikaCLI.java:1071)
        at org.apache.tika.cli.TikaCLI.process(TikaCLI.java:493)
        at org.apache.tika.cli.TikaCLI.main(TikaCLI.java:256)
Caused by: org.xml.sax.SAXParseException; lineNumber: 1; columnNumber: 1; Content is not allowed in prolog.
        at org.apache.xerces.util.ErrorHandlerWrapper.createSAXParseException(Unknown Source)
        at org.apache.xerces.util.ErrorHandlerWrapper.fatalError(Unknown Source)
        at org.apache.xerces.impl.XMLErrorReporter.reportError(Unknown Source)
        at org.apache.xerces.impl.XMLErrorReporter.reportError(Unknown Source)
        at org.apache.xerces.impl.XMLErrorReporter.reportError(Unknown Source)
        at org.apache.xerces.impl.XMLScanner.reportFatalError(Unknown Source)
        at org.apache.xerces.impl.XMLDocumentScannerImpl$PrologDispatcher.dispatch(Unknown Source)
        at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl.scanDocument(Unknown Source)
        at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source)
        at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source)
        at org.apache.xerces.parsers.XMLParser.parse(Unknown Source)
        at org.apache.xerces.parsers.AbstractSAXParser.parse(Unknown Source)
        at org.apache.xerces.jaxp.SAXParserImpl$JAXPSAXParser.parse(Unknown Source)
        at org.apache.xerces.jaxp.SAXParserImpl.parse(Unknown Source)
        at java.xml/javax.xml.parsers.SAXParser.parse(SAXParser.java:197)
        at org.apache.tika.utils.XMLReaderUtils.parseSAX(XMLReaderUtils.java:513)
        at org.apache.tika.parser.epub.EpubContentParser.parse(EpubContentParser.java:50)
        at org.apache.tika.parser.epub.EpubParser.bufferedParseZipFile(EpubParser.java:289)
        at org.apache.tika.parser.epub.EpubParser.bufferedParse(EpubParser.java:175)
        at org.apache.tika.parser.epub.EpubParser.parse(EpubParser.java:124)
        at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:298)
        ... 5 more


➜   sf 89595bd2-8076-4da0-8880-518c291e7904
---
siegfried   : 1.9.6
scandate    : 2023-12-21T16:52:55+01:00
signature   : default.sig
created     : 2022-11-06T17:44:52+01:00
identifiers :
  - name    : 'pronom'
    details : 'DROID_SignatureFile_V109.xml; container-signature-20221102.xml'
---
filename : '89595bd2-8076-4da0-8880-518c291e7904'
filesize : 1373574
modified : 2023-07-04T21:39:45+02:00
errors   :
matches  :
  - ns      : 'pronom'
    id      : 'fmt/483'
    format  : 'ePub format'
    version :
    mime    : 'application/epub+zip'
    basis   : 'container name mimetype with byte match at 0, 20'
    warning : 'extension mismatch'
    
    
➜  unzip -l 89595bd2-8076-4da0-8880-518c291e7904
Archive:  89595bd2-8076-4da0-8880-518c291e7904
  Length      Date    Time    Name
---------  ---------- -----   ----
       20  00-00-1980 00:00   mimetype
      258  00-00-1980 00:00   META-INF/container.xml
     4945  00-00-1980 00:00   OEBPS/content.opf
      544  00-00-1980 00:00   OEBPS/page-template.xpgt
      944  00-00-1980 00:00   OEBPS/9788834025161.css
     3536  00-00-1980 00:00   OEBPS/toc.ncx
      384  00-00-1980 00:00   OEBPS/01_cover.html
     1104  00-00-1980 00:00   OEBPS/02_front.html
     5696  00-00-1980 00:00   OEBPS/25_toc.html
      688  00-00-1980 00:00   OEBPS/03_front1.html
      400  00-00-1980 00:00   OEBPS/04_half.html
      400  00-00-1980 00:00   OEBPS/06_titlepage.html
      768  00-00-1980 00:00   OEBPS/07_preface.html
    26688  00-00-1980 00:00   OEBPS/09_chapter2.html
      672  00-00-1980 00:00   OEBPS/05_half1.html
    24784  00-00-1980 00:00   OEBPS/16_chapter9.html
    26592  00-00-1980 00:00   OEBPS/17_chapter10.html
    30176  00-00-1980 00:00   OEBPS/18_chapter11.html
    29680  00-00-1980 00:00   OEBPS/19_chapter12.html
    30640  00-00-1980 00:00   OEBPS/20_chapter13.html
    28928  00-00-1980 00:00   OEBPS/21_chapter14.html
    29056  00-00-1980 00:00   OEBPS/22_chapter15.html
    25904  00-00-1980 00:00   OEBPS/23_chapter16.html
    26192  00-00-1980 00:00   OEBPS/08_chapter1.html
    25472  00-00-1980 00:00   OEBPS/14_chapter7.html
    27120  00-00-1980 00:00   OEBPS/13_chapter6.html
    25344  00-00-1980 00:00   OEBPS/10_chapter3.html
    28064  00-00-1980 00:00   OEBPS/12_chapter5.html
    27632  00-00-1980 00:00   OEBPS/11_chapter4.html
    28784  00-00-1980 00:00   OEBPS/15_chapter8.html
   106772  00-00-1980 00:00   OEBPS/images/cover.jpg
    37376  00-00-1980 00:00   OEBPS/images/half.jpg
    46000  00-00-1980 00:00   OEBPS/images/titlepage.jpg
    68384  00-00-1980 00:00   OEBPS/images/pg33.jpg
    12720  00-00-1980 00:00   OEBPS/images/circle.jpg
    57216  00-00-1980 00:00   OEBPS/images/pg36.jpg
    51232  00-00-1980 00:00   OEBPS/images/pg104.jpg
    79072  00-00-1980 00:00   OEBPS/images/pg194.jpg
    82192  00-00-1980 00:00   OEBPS/images/pg216.jpg
    64704  00-00-1980 00:00   OEBPS/images/pg232.jpg
    75200  00-00-1980 00:00   OEBPS/images/pg251.jpg
    82000  00-00-1980 00:00   OEBPS/images/pg252.jpg
    36304  00-00-1980 00:00   OEBPS/images/pg254.jpg
    93616  00-00-1980 00:00   OEBPS/images/pg261.jpg
    40736  00-00-1980 00:00   OEBPS/images/pg281.jpg
    39589  00-00-1980 00:00   META-INF/encryption.xml
---------                     -------
  1434528                     46 files
➜  drm-epub