import sha
import urllib
import xml.dom.minidom as minidom
import RDF
import config
import StringIO
import gzip
class Grab(urllib.URLopener): 
   def __init__(self, *args): 
      self.version = 'SemWebAgent (julie/redlandbot 0.5)'
      urllib.URLopener.__init__(self, *args)
urllib._urlopener = Grab()
urllib._urlopener.addheader("Accept","application/rdf+xml,*/*")

debug = 0

common_namespaces = {
    'owl': 'http://www.w3.org/2002/07/owl#',
	'wn16': 'http://xmlns.com/wordnet/1.6/',
	'prf': 'http://www.openmobilealliance.org/tech/profiles/UAPROF/ccppschema-20021212#',
	'doaml': 'http://ns.balbinus.net/doaml#',
	'periodic': 'http://www.daml.org/2003/01/periodictable/PeriodicTable#',
	'tipjar': 'http://crschmidt.net/foaf/tipjar/',
	'factbook': 'http://www.daml.org/2001/12/factbook/factbook-ont#',
	'srw10': 'http://purl.org/net/inkel/rdf/schemas/lang/1.0#',
	'srw11': 'http://purl.org/net/inkel/rdf/schemas/lang/1.1#',
	'rank': 'http://www.daml.org/2002/03/ranks/rank-ont#',
	'list': 'http://crschmidt.net/ns/list#',
	'weather': 'http://purl.org/net/vocab/2004/10/weather#',
	'irc': 'http://crschmidt.net/ns/irc#',
	'menow': 'http://schema.menow.org/#',
	'kissed': 'http://www.gnowsis.org/ont/kissology',
	'todo': 'http://crschmidt.net/ns/todo#',
	'astrology': 'http://www.ideaspace.net/users/wkearney/schema/astrology/0.1#',
	'trust': 'http://trust.mindswap.org/ont/trust.owl#',
	'tz': 'http://www.isi.edu/~pan/damltime/timezone-ont.owl#',
	'exif': 'http://www.w3.org/2003/12/exif/ns#',
	'rdfs': 'http://www.w3.org/2000/01/rdf-schema#',
	'tv': 'http://xmlns.com/2003/rdftv/tv#',
	'wot': 'http://xmlns.com/wot/0.1/',
	'review': 'http://www.purl.org/stuff/rev#',
	'mtbi': 'http://www.ideaspace.net/users/wkearney/schema/mbti/0.1#',
	'rev': 'http://www.purl.org/stuff/rev#',
	'ilike': 'http://rdf.netalleynetworks.com/ilike/20040830#',
	'usranks': 'http://www.daml.org/2002/03/ranks/us#',
	'content': 'is http://purl.org/rss/1.0/modules/content/',
	'cc': 'http://web.resource.org/cc/',
	'book': 'http://www.hackcraft.net/bookrdf/vocab/0_1/',
	'music': 'http://www.kanzaki.com/ns/music#',
	'rel': 'http://purl.org/vocab/relationship/',
	'nyse': 'http://www.daml.org/2001/10/html/nyse-ont#',
	'ref': 'http://mozref.com/2004/07/14-object-reference#',
	'dcterms': 'http://purl.org/dc/terms/',
	'quaff': 'http://purl.org/net/schemas/quaffing/',
	'schema': 'http://www.schemaweb.info/schemas/meta/rdf/',
	'foaf': 'http://xmlns.com/foaf/0.1/',
	'bio': 'http://purl.org/vocab/bio/0.1/',
	'ical': 'http://www.w3.org/2002/12/cal/ical#',
	'foafcorp': 'http://xmlns.com/foaf/corp#',
	'bloggercode': 'http://purl.org/net/bloggercode/',
	'xfn': 'http://gmpg.org/xfn/1#',
	'quote': 'http://homepage.mac.com/kpreid/2003/10/rdf-quote.xml#',
	'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#',
	'doap': 'http://usefulinc.com/ns/doap#',
	'dc': 'http://purl.org/dc/elements/1.1/',
	'cyc': 'http://opencyc.sourceforge.net/daml/cyc.daml#',
	'fc': 'http://xmlns.com/foaf/corp#',
	'fips': 'http://www.daml.org/2001/09/countries/fips#',
	'kiss': 'http://www.gnowsis.org/ont/kissology#',
	'rss': 'http://purl.org/rss/1.0/',
	'dct': 'is http://purl.org/dc/terms/',
	'geo': 'http://www.w3.org/2003/01/geo/wgs84_pos#',
	'vcard': 'http://www.w3.org/2001/vcard-rdf/3.0#',
	'vann': 'http://purl.org/vocab/vann/',
	'dc10': 'http://purl.org/dc/1.0/',
	'chiefs': 'http://www.daml.org/2002/02/chiefs/chiefs-ont#',
	'foo': 'http://www.w3.org/2005/01/wf/assign#',
	'rss11': 'http://purl.org/net/rss1.1#',
	'img': 'http://jibbering.com/2002/3/svg/#',
	'chefmoz': 'http://chefmoz.org/rdf/elements/1.0/',
	'area': 'http://www.daml.org/2002/02/telephone/1/areacodes-ont#',
	'flow': 'http://www.w3.org/2005/01/wf/flow#',
	'p': 'http://purl.org/net/rss1.1/payload#',
	'contact': 'http://www.w3.org/2000/10/swap/pim/contact#',
	'iso': 'http://www.daml.org/2001/09/countries/iso#',
	'bot': 'http://crschmidt.net/ns/bot#',
	'xsd': 'http://www.w3.org/2001/XMLSchema#',
	'witw-is': 'http://nwalsh.com/xmlns/witw-is#',
	'cyc2004': 'http://www.cyc.com/2004/06/04/cyc#',
	'pm': 'http://www.pm.org/rdf/0.1/',
	'iso3166': 'http://www.daml.org/2001/09/countries/iso-3166-ont#',
	'mozrdf': 'http://www.mozilla.org/2004/em-rdf#',
	'fact': 'http://www.daml.org/2001/12/factbook/factbook-ont#'
    }

def get_model(options=None):
    if (options): options = ",%s" % options
    return RDF.Model(RDF.Storage(storage_name="mysql", name="abc", options_string="merge='yes',host='127.0.0.1',user='%s',password='%s',database='redland'%s" % (config.username, config.password, options)))

def count_statements(m, uri):
    j = 0
    for i in m.find_statements(RDF.Statement(None, RDF.Uri(uri), None)):
        j += 1
    return j

def rdqlquery(m, query):
    query = "%s USING rdf for <http://www.w3.org/1999/02/22-rdf-syntax-ns#>" % query
    for i in common_namespaces.keys():
        query = "%s, %s for <%s>" % (query, i, common_namespaces[i])
    q = RDF.RDQLQuery(query)
    return q.execute(m)

def parse_anything(m, string):
    url = "http://example.org/unknowndatasource"
    if (string[0:5] == "http:"):
        url = string
        u = urllib.urlopen(string)
        ct = u.info().get("Content-Type")
        content = u.read()
        u.close()
        if (ct.startswith("application/x-gzip")):
            s = StringIO.StringIO(content)
            g = gzip.GzipFile(fileobj=s)
            url = string
            string = g.read()
            if debug: print "Gzip"
        elif (ct.startswith("text/html")):
	    g = RDF.Parser(name="grddl")
	    if debug: print 'grddl'
	    g.parse_into_model(m,string)
	    return 'GRDDL'
	elif (ct.startswith("application/x-turtle") or string[-4:] == ".ttl" or string[-6:] == "turtle"):
            t = RDF.TurtleParser()
            if debug: print "turtle"
            t.parse_string_into_model(m, content,string)
            return "turtle"
        elif (ct.startswith("application/rdf+xml")):
            r = RDF.RDFXMLParser()
            if debug: print "rdf"
            r.parse_string_into_model(m, content, string)
            return "RDF/XML"
        elif (ct.startswith("image/svg+xml") or string[-4:] == ".svg"):
            p = RDF.Parser()
            p.set_feature("http://feature.librdf.org/raptor-scanForRDF", "1") 
            p.parse_string_into_model(m, content,string)
            return "SVG"
        elif (string[-3:] == ".nt"):
            nt = RDF.NTriplesParser()
            if debug: print "ntriples"
            nt.parse_string_into_model(m, content, string)
            return "ntriples"
        elif (ct.startswith("application/atom+xml") or ct.startswith("application/rss+xml")):
            rss = RDF.RSSTagSoupParser()
            if debug: print "rss"
            rss.parse_string_into_model(m, content, string)
            return "RSS"
        elif(ct.startswith("text/xml") and string[-3:] == "rss"):
            rss = RDF.RSSTagSoupParser()
            if debug: print "rss"
            rss.parse_string_into_model(m, content, string)
            return "RSS"
        elif(ct.startswith("text/xml")):
            try:
                rss = RDF.RSSTagSoupParser()
                if debug: print "rss"
                rss.parse_string_into_model(m, content, string)
                return "RSS"
            except RDF.RedlandError:
                r = RDF.RDFXMLParser()
                if debug: print "rdf"
                r.parse_string_into_model(m, content, string)
                return "RDF/XML"
        else:
            string = content
    if ("@prefix " in string):
        t = RDF.TurtleParser()
        if debug: print "turtle"
        t.parse_string_into_model(m, string, url)
        return "turtle from string"
    elif ("xmlns=" in string or "xmlns:rdf=" in string):
        r = RDF.RDFXMLParser()
        if debug: print "rdf"
        r.parse_string_into_model(m, string, url)
        return "RDF/XML from string"
    elif (string[0] == "<http://"):
        nt = RDF.NTriplesParser()
        if debug: print "ntriples"
        nt.parse_string_into_model(m, string, url)
        return "ntriples from string"
    else:
        if debug: print string
        return "no valid"
def remove_node(m,n):
    if "http:" in n:
        node = RDF.Uri(n)
    elif n.startswith("r"):
        node = RDF.Node(blank=n)
    for i in m.find_statements(RDF.Statement(None, None, node)):
        del m[i]
    for i in m.find_statements(RDF.Statement(node,None,None)):
        del m[i]

def add_sha(m, n=None):
    count = 0
    if n:
        node = uri_or_blank(n)
    else:
        node = None
        for i in m.find_statements(RDF.Statement(node, RDF.Uri("http://xmlns.com/foaf/0.1/mbox"), None)):
            if i.object.is_resource():
                s = RDF.Statement(i.subject, RDF.Uri("http://xmlns.com/foaf/0.1/mbox_sha1sum"), sha.new(str(i.object.uri)).hexdigest())
                if not s in m:
                    count +=1
                    if debug: print i.object
                    m.append(s)
    return count

def merge_nodes(m,source,target):
    if "http:" in source:
        source = RDF.Uri(source)
    elif source.startswith("r"):
        source = RDF.Node(blank=source)
    else:
        if debug: print "Failed."
        return 1

    if "http:" in target:
        target = RDF.Uri(target)
    elif target.startswith("r"):
        target = RDF.Node(blank=target)
    else:
        if debug: print "Failed."
        return 1
    for i in m.find_statements(RDF.Statement(source,None,None)):
        m.append(RDF.Statement(target,i.predicate, i.object))
        del m[RDF.Statement(source,i.predicate,i.object)]
    for i in m.find_statements(RDF.Statement(None,None,source)):
        m.append(RDF.Statement(i.subject,i.predicate, target))
        del m[RDF.Statement(i.subject,i.predicate,source)]

def uri_or_blank(n):
    if "http:" in n:
        node = RDF.Uri(n)
    elif n.startswith("r"):
        node = RDF.Node(blank=n)
    return node