#!/usr/bin/python -tt
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Library General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
# (c) 2007 Red Hat, Inc - Written by Seth Vidal skvidal at fedoraproject.org


# command line or nagios-plugin to check to make sure
# a given repo is correct/valid




# take url
# append repodata (if it doesn't already have it)
# download repomd.xml
# parse out checksums
# download each item from the file
# checksum them
# for each of the xml files, run xmllint --noout over there and check return
# codes
# return nothing if all is well
# scream holy fuck if they are broken

import sys
from yum import repoMDObject
from yum.misc import checksum
import urlgrabber
import tempfile
import subprocess
import os


def main(myurl):
    tempdir = tempfile.mkdtemp()
    errorstrings = []
    if myurl[-1] != '/':
        myurl += '/'
    baseurl = myurl
    if not myurl.endswith('repodata/'):
        myurl += 'repodata/'
    else:
        baseurl = baseurl.replace('repodata/', '/')
    
    rf = myurl + 'repomd.xml'
    try:
        rm = urlgrabber.urlopen(rf)
        repomd = repoMDObject.RepoMD('foo', rm)
        for t in repomd.fileTypes():
            data = repomd.getData(t)
            base, href = data.location
            if base:
                loc = base + '/' + href
            else:
                loc = baseurl + href

            destfn = tempdir + '/' + os.path.basename(href)
            dest =  urlgrabber.urlgrab(loc, destfn)
            ctype, known_csum = data.checksum
            csum = checksum(ctype, dest)
            if csum != known_csum:
                errorstrings.append("checksum: %s" % t)

            if href.find('xml') != -1:
                retcode = subprocess.call(['/usr/bin/xmllint', '--noout', dest])
                if retcode != 0:
                    errorstrings.append("failed xml read: %s" % t)

    except urlgrabber.grabber.URLGrabError, e:
        errorstrings.append('Error accessing repository %s' % e)
    
        
    if errorstrings:
        print ','.join(errorstrings)
        return 2
    else:
        print "OK all checked out"
        return 0
        
if __name__ == '__main__':
    if len(sys.argv) < 2:
        print "Usage:\n    sanity-check-repodata <url>\n\n"
        sys.exit(4)
        
    sys.exit(main(sys.argv[1]))