file/magic/Magdir/msooxml

#------------------------------------------------------------------------------
# $File: msooxml,v 1.1 2011/01/25 18:36:19 christos Exp $
# msooxml:  file(1) magic for Microsoft Office XML
# From: Ralf Brown <ralf.brown@gmail.com>

# .docx, .pptx, and .xlsx are XML plus other files inside a ZIP
#   archive.  The first member file is normally "[Content_Types].xml".
# Since MSOOXML doesn't have anything like the uncompressed "mimetype"
#   file of ePub or OpenDocument, we'll have to scan for a filename
#   which can distinguish between the three types

# start by checking for ZIP local file header signature
0               string          PK\003\004
# make sure the first file is correct
>0x1E           string          [Content_Types].xml
# skip to the second local file header
#   since some documents include a 520-byte extra field following the file
#   header,  we need to scan for the next header
>>(18.l+49)     search/2000     PK\003\004
# now skip to the *third* local file header; again, we need to scan due to a
#   520-byte extra field following the file header
>>>&26          search/1000     PK\003\004
# and check the subdirectory name to determine which type of OOXML
#   file we have
>>>>&26         string          word/           Microsoft Word 2007+
!:mime application/msword
>>>>&26         string          ppt/            Microsoft PowerPoint 2007+
!:mime application/vnd.ms-powerpoint
>>>>&26         string          xl/             Microsoft Excel 2007+
!:mime application/vnd.ms-excel
>>>>&26         default         x               Microsoft OOXML
!:strength +10