#!/usr/bin/python

import sys
from xml.sax import ContentHandler, make_parser

from sse_defs import *
import sse_grab

license_blacklist = [
    "Other/Proprietary License with Free Trial",
    "Free for non-commercial use",
    "Free To Use But Restricted",
    "Freely Distributable",
    "Freeware",
    "Shareware",
    "Other/Proprietary License with Source",
    "Other/Proprietary License",
    "Aladdin Free Public License (AFPL)",
    "Free For Home Use",
    "Unknown",
    "Free For Educational Use",
    "SUN Community Source License",
    "Free World Licence",
    "SUN Binary Code License",
    "Voxel Public License (VPL)"
    ]

license_whitelist = [
    "GNU General Public License (GPL)",
    "GNU Lesser General Public License (LGPL)",
    "OSI Approved",
    "The Apache License",
    "Q Public License (QPL)",
    "Public Domain",
    "BSD License (original)",
    "Artistic License",
    "MIT/X Consortium License",
    "The Clarified Artistic License",
    "BSD License (revised)",
    "DFSG approved",
    "GNU Free Documentation License (FDL)",
    "W3C License",
    "Mozilla Public License (MPL)",
    "The Apache License 2.0",
    "Perl License",
    "The PHP License",
    "Python License",
    "Eiffel Forum License (EFL)",
    "QT Public License (QPL)",
    "Common Public License",
    "GNAT Modified GPL (GMGPL)",
    "Zope Public License (ZPL)",
    "Open Software License",
    "IBM Public License",
    "zlib/libpng License",
    "SUN Public License",
    "Academic Free License (AFL)",
    "Common Development and Distribution License (CDDL)",
    "Affero General Public License",
    "The Latex Project Public License (LPPL)",
    "WTFPL",
    "Guile license"
    ]

def process_record(meta):

    for k, v in meta.items():
        meta[k] = v.strip()

    meta["id"] = int(meta["id"])

    print "Next record '%s'" % meta["name"]

    archive_url = None

    for a in ("archive-tgz-url", "archive-bz2-url", "archive-zip-url"):

        if meta.has_key(a) and meta[a] != "":
            archive_url = meta[a]
            break

    if archive_url is None:
        print "Ignoring project '%s' without archive URL!" % meta["name"]
        return

    meta["archive-url"] = archive_url

    if not meta.has_key("license"):
        print "WARNING: Project '%s' has no license!" % meta["name"]
        return

    if meta["license"] in license_blacklist:
        print "Ignoring project '%s' due to evil license '%s'!" % (meta["name"], meta["license"])
        return

    if meta["license"] not in license_whitelist:
        print "WARNING: Unknown license '%s' for project '%s'!" % (meta["license"], meta["name"])
        
        f = file("graylist", "a")
        f.write("%s\t%s\n" % (meta["name"], meta["license"]))
        f.close()
        return

    sse_grab.grab_archive(meta, "freshmeat:%i" % meta["id"], SSE_PROVIDER_FRESHMEAT)

class docHandler(ContentHandler):

    meta = {}
    field = None

    def startElement(self, name, attrs):
        if name == "project":
            self.meta = {}
            self.field = None
        elif name == "project_id":
            self.field = "id"
        elif name == "projectname_full":
            self.field = "name"
        elif name == "url_project_page":
            self.field = "project-url"
        elif name == "url_tgz":
            self.field = "archive-tgz-url"
        elif name == "url_bz2":
            self.field = "archive-bz2-url"
        elif name == "url_zip":
            self.field = "archive-zip-url"
        elif name == "license":
            self.field = "license"
        elif name == "latest_release_date":
            self.field = "version"
        else:
            self.field = None

    def characters(self, data):
        
        if not self.field is None:
            if self.meta.has_key(self.field):
                self.meta[self.field] += data
            else:
                self.meta[self.field] = data

    def endElement(self, name):
        if name == "project":
            process_record(self.meta)
            self.meta = None

        self.field = None

def parse_xml(f):

    dh = docHandler()
    parser = make_parser()
    parser.setContentHandler(dh)
    parser.parse(f)

if __name__ == "__main__":
    parse_xml(sys.stdin)