How to add file extensions based on file type on Linux/Unix?

Question

This is a question regarding Unix shell scripting (any shell), but any other "standard" scripting language solution would also be appreciated:

I have a directory full of files where the filenames are hash values like this:

fd73d0cf8ee68073dce270cf7e770b97
fec8047a9186fdcc98fdbfc0ea6075ee

These files have different original file types such as png, zip, doc, pdf etc.

Can anybody provide a script that would rename the files so they get their appropriate file extension, probably based on the output of the file command?

Answer:

J.F. Sebastian's script will work for both ouput of the filenames as well as the actual renaming.

Answer 1

Here's mimetypes' version:

#!/usr/bin/env python
"""It is a `filename -> filename.ext` filter. 

   `ext` is mime-based.

"""
import fileinput
import mimetypes
import os
import sys
from subprocess import Popen, PIPE

if len(sys.argv) > 1 and sys.argv[1] == '--rename':
    do_rename = True
    del sys.argv[1]
else:
    do_rename = False    

for filename in (line.rstrip() for line in fileinput.input()):
    output, _ = Popen(['file', '-bi', filename], stdout=PIPE).communicate()
    mime = output.split(';', 1)[0].lower().strip()
    ext = mimetypes.guess_extension(mime, strict=False)
    if ext is None:
        ext = os.path.extsep + 'undefined'
    filename_ext = filename + ext
    print filename_ext
    if do_rename:
       os.rename(filename, filename_ext)

Example:

$ ls *.file? | python add-ext.py --rename
avi.file.avi
djvu.file.undefined
doc.file.dot
gif.file.gif
html.file.html
ico.file.obj
jpg.file.jpe
m3u.file.ksh
mp3.file.mp3
mpg.file.m1v
pdf.file.pdf
pdf.file2.pdf
pdf.file3.pdf
png.file.png
tar.bz2.file.undefined

---

Following @Phil H's response that follows @csl' response:

#!/usr/bin/env python
"""It is a `filename -> filename.ext` filter. 

   `ext` is mime-based.
"""
# Mapping of mime-types to extensions is taken form here:
# http://as3corelib.googlecode.com/svn/trunk/src/com/adobe/net/MimeTypeMap.as
mime2exts_list = [
    ["application/andrew-inset","ez"],
    ["application/atom+xml","atom"],
    ["application/mac-binhex40","hqx"],
    ["application/mac-compactpro","cpt"],
    ["application/mathml+xml","mathml"],
    ["application/msword","doc"],
    ["application/octet-stream","bin","dms","lha","lzh","exe","class","so","dll","dmg"],
    ["application/oda","oda"],
    ["application/ogg","ogg"],
    ["application/pdf","pdf"],
    ["application/postscript","ai","eps","ps"],
    ["application/rdf+xml","rdf"],
    ["application/smil","smi","smil"],
    ["application/srgs","gram"],
    ["application/srgs+xml","grxml"],
    ["application/vnd.adobe.apollo-application-installer-package+zip","air"],
    ["application/vnd.mif","mif"],
    ["application/vnd.mozilla.xul+xml","xul"],
    ["application/vnd.ms-excel","xls"],
    ["application/vnd.ms-powerpoint","ppt"],
    ["application/vnd.rn-realmedia","rm"],
    ["application/vnd.wap.wbxml","wbxml"],
    ["application/vnd.wap.wmlc","wmlc"],
    ["application/vnd.wap.wmlscriptc","wmlsc"],
    ["application/voicexml+xml","vxml"],
    ["application/x-bcpio","bcpio"],
    ["application/x-cdlink","vcd"],
    ["application/x-chess-pgn","pgn"],
    ["application/x-cpio","cpio"],
    ["application/x-csh","csh"],
    ["application/x-director","dcr","dir","dxr"],
    ["application/x-dvi","dvi"],
    ["application/x-futuresplash","spl"],
    ["application/x-gtar","gtar"],
    ["application/x-hdf","hdf"],
    ["application/x-javascript","js"],
    ["application/x-koan","skp","skd","skt","skm"],
    ["application/x-latex","latex"],
    ["application/x-netcdf","nc","cdf"],
    ["application/x-sh","sh"],
    ["application/x-shar","shar"],
    ["application/x-shockwave-flash","swf"],
    ["application/x-stuffit","sit"],
    ["application/x-sv4cpio","sv4cpio"],
    ["application/x-sv4crc","sv4crc"],
    ["application/x-tar","tar"],
    ["application/x-tcl","tcl"],
    ["application/x-tex","tex"],
    ["application/x-texinfo","texinfo","texi"],
    ["application/x-troff","t","tr","roff"],
    ["application/x-troff-man","man"],
    ["application/x-troff-me","me"],
    ["application/x-troff-ms","ms"],
    ["application/x-ustar","ustar"],
    ["application/x-wais-source","src"],
    ["application/xhtml+xml","xhtml","xht"],
    ["application/xml","xml","xsl"],
    ["application/xml-dtd","dtd"],
    ["application/xslt+xml","xslt"],
    ["application/zip","zip"],
    ["audio/basic","au","snd"],
    ["audio/midi","mid","midi","kar"],
    ["audio/mpeg","mp3","mpga","mp2"],
    ["audio/x-aiff","aif","aiff","aifc"],
    ["audio/x-mpegurl","m3u"],
    ["audio/x-pn-realaudio","ram","ra"],
    ["audio/x-wav","wav"],
    ["chemical/x-pdb","pdb"],
    ["chemical/x-xyz","xyz"],
    ["image/bmp","bmp"],
    ["image/cgm","cgm"],
    ["image/gif","gif"],
    ["image/ief","ief"],
    ["image/jpeg","jpg","jpeg","jpe"],
    ["image/png","png"],
    ["image/svg+xml","svg"],
    ["image/tiff","tiff","tif"],
    ["image/vnd.djvu","djvu","djv"],
    ["image/vnd.wap.wbmp","wbmp"],
    ["image/x-cmu-raster","ras"],
    ["image/x-icon","ico"],
    ["image/x-portable-anymap","pnm"],
    ["image/x-portable-bitmap","pbm"],
    ["image/x-portable-graymap","pgm"],
    ["image/x-portable-pixmap","ppm"],
    ["image/x-rgb","rgb"],
    ["image/x-xbitmap","xbm"],
    ["image/x-xpixmap","xpm"],
    ["image/x-xwindowdump","xwd"],
    ["model/iges","igs","iges"],
    ["model/mesh","msh","mesh","silo"],
    ["model/vrml","wrl","vrml"],
    ["text/calendar","ics","ifb"],
    ["text/css","css"],
    ["text/html","html","htm"],
    ["text/plain","txt","asc"],
    ["text/richtext","rtx"],
    ["text/rtf","rtf"],
    ["text/sgml","sgml","sgm"],
    ["text/tab-separated-values","tsv"],
    ["text/vnd.wap.wml","wml"],
    ["text/vnd.wap.wmlscript","wmls"],
    ["text/x-setext","etx"],
    ["video/mpeg","mpg","mpeg","mpe"],
    ["video/quicktime","mov","qt"],
    ["video/vnd.mpegurl","m4u","mxu"],
    ["video/x-flv","flv"],
    ["video/x-msvideo","avi"],
    ["video/x-sgi-movie","movie"],
    ["x-conference/x-cooltalk","ice"]]

#NOTE: take only the first extension
mime2ext = dict(x[:2] for x in mime2exts_list)

if __name__ == '__main__':
    import fileinput, os.path
    from subprocess import Popen, PIPE

    for filename in (line.rstrip() for line in fileinput.input()):
        output, _ = Popen(['file', '-bi', filename], stdout=PIPE).communicate()
        mime = output.split(';', 1)[0].lower().strip()
        print filename + os.path.extsep + mime2ext.get(mime, 'undefined')

---

Here's a snippet for old python's versions (not tested):

#NOTE: take only the first extension
mime2ext = {}
for x in mime2exts_list:
    mime2ext[x[0]] = x[1]

if __name__ == '__main__':
    import os
    import sys

    # this version supports only stdin (part of fileinput.input() functionality)
    lines = sys.stdin.read().split('\n')
    for line in lines:
        filename = line.rstrip()
        output = os.popen('file -bi ' + filename).read()        
        mime = output.split(';')[0].lower().strip()
        try: ext = mime2ext[mime]
        except KeyError:
             ext = 'undefined'
        print filename + '.' + ext

It should work on Python 2.3.5 (I guess).

Answer 2

You can use

file -i filename

to get a MIME-type. You could potentially lookup the type in a list and then append an extension. You can find a list of MIME-types and example file extensions on the net.