fossils/main.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
import os
import io
from PIL import Image
from HTMLParser import HTMLParser
import sqlite3 as lite
import tornado.httpserver
import tornado.ioloop
import tornado.options
import tornado.web
from tornado.options import define, options
define("port", default=8000, help="run on the given port", type=int)


PATH=os.path.dirname(os.path.abspath(__file__))


class MyHTMLParser(HTMLParser):
    def __init__(self):
        self.reset()
        self.ttype = "p"
        self.fed = []
    
    def handle_starttag(self, tag, attrs):
        self.ttype = str(tag)

    def handle_endtag(self, tag):
        self.ttype = "p"

    def handle_data(self, data):
        self.fed.append({"type": self.ttype,
                         "text": data.strip()})
        
    def get_data(self):
        return self.fed


class Application(tornado.web.Application):
    def __init__(self):
        handlers = [
            (r"/", MainHandler),
            (r"/img", ImageHandler),
            (r"/download", GenFileStreamerHandler),
        ]
        settings = dict(
            template_path=os.path.join(os.path.dirname(__file__), "templates"),
            static_path="/srv/www/katrin/static",
            debug=True,
        )
        tornado.web.Application.__init__(self, handlers, **settings)


class DATA:
    def __init__(self, index=None):
        self.con = lite.connect('fossil.db')
        cur = self.con.cursor()
        with self.con:
            if index == None:
                cur.execute("SELECT * FROM Fossil ORDER BY Id LIMIT 1")
            else:
                cur.execute("SELECT * FROM Fossil WHERE Id = ?", [index])
            data = cur.fetchone()
        
        if data == None:
            raise Exception('Database: Data Id ' + str(index) + ' does not exist.')
        
        self.index = data[0]
        self.name = data[1]
        parser = MyHTMLParser()
        parser.feed(data[2])
        self.desc = parser.get_data() 
        self.size = ("%.2f" % (data[3] / 1000000.0))

    def get_index(self):
        return self.index
    
    def get_name(self):
        return self.name
    
    def get_desc(self):
        return self.desc
    
    def get_size(self):
        return self.size
    
    def slug(self, slug=None):
        if slug:
            self.slug = slug
        else:
            self.slug = "The Fossils Data"
        return self.slug
    
    def title(self, title=None):
        if title:
            self.title = title
        else:
            self.title = """Preservation of three-dimensional 
                anatomy in phosphatized fossil arthropods enriches 
                evolutionary inference"""
        return self.title

    def get_author(self):
        return [
            "Achim H Schwermann", 
            "Tomy dos Santos Rolo",
            "Michael S Caterino",
            "Günter Bechly",
            "Heiko Schmied",
            "Tilo Baumbach",
            "Thomas van de Kamp"
        ]

    def get_institute(self):
        return [
            """Steinmann Institute for Geology, Mineralogy and Paleontology, 
            University of Bonn, Bonn, Germany""",
            """ANKA/Institute for Photon Science and Synchrotron Radiation, 
            Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, 
            Germany""",
            """Department of Agricultural and Environmental Sciences, Clemson University, 
            Clemson, United States""",
            """State Museum of Natural History Stuttgart, Stuttgart, Germany""",
            """Institute of Crop Science and Resource Conservation, University of Bonn, 
            Bonn, Germany""",
            """Laboratory for Applications of Synchrotron Radiation, Karlsruhe Institute 
            of Technology, Karlsruhe, Germany"""
        ]

    def get_list(self):
        with self.con:
            cur = self.con.cursor()
            cur.execute("SELECT * FROM Fossil ORDER BY Id")
            data = cur.fetchall()
        self.data_list = [ [x[0], x[1]] for x in data]
        return self.data_list


class MainHandler(tornado.web.RequestHandler):

    def get(self):
        index = self.get_argument("index", None)
        print index
        data = DATA(index)
        
        self.render(
            "index.html",
            slug = data.slug(),
            index = data.get_index(),
            name = data.get_name(),
            title = data.title(),
            authors = data.get_author(),
            institutes = data.get_institute(),
            data_list = data.get_list(),
            desc = data.get_desc(),
            data_size = data.get_size()
        )


class GenFileStreamerHandler(tornado.web.RequestHandler):
    
    CHUNK_SIZE = 512000
    DATA_PATH = "/home/ntj/fossils_for_nicholas"
    
    @tornado.web.asynchronous
    @tornado.gen.engine
    def get(self):
        cdid = self.get_arguments("did")
        con = lite.connect('fossil.db')
        with con:
            cur = con.cursor()
            cur.execute("SELECT name FROM Fossil WHERE name = ?", (cdid))
            data_key = cur.fetchall()
            
        if len(data_key) > 0:
            file_name = str(cdid[0]) + ".zip"
            self.path = self.DATA_PATH + str(cdid[0]) + "/" + file_name
            self.set_header('Content-Type',
                            'application/octet-stream')
            self.set_header('Content-Disposition',
                            'attachment; filename=' + file_name)
            self.set_header("Content-Length",
                            os.path.getsize(self.path))
            self.flush()
            fd = open(self.path, "rb")
            data = fd.read(self.CHUNK_SIZE)
            while data:
                self.write(data)
                yield tornado.gen.Task(self.flush)
                data = fd.read(self.CHUNK_SIZE)
            fd.close()
        self.finish()


class ImageHandler(tornado.web.RequestHandler):
    CHUNK_SIZE = 512000
    #DATA_PATH = "/srv/www/katrin/static/fossils_for_nicholas"
    DATA_PATH = "/home/ntj/fossils_for_nicholas"

    @tornado.web.asynchronous
    @tornado.gen.engine
    def get(self):
        did = self.get_argument("id")
        dname = self.get_argument("name")
        dtype = self.get_argument("type")
        dcounter = self.get_argument("counter").zfill(4)
        
        if dtype == "left" or dtype == "left-resized":
            prefix = "left"
        elif dtype == "top" or dtype == "top-resized":
            prefix = "top"
        elif dtype == "front" or dtype == "front-resized":
            prefix = "02_quercy_10_merged"
        
        if dtype == "preview":
            self.path = os.path.join(
                self.DATA_PATH,
                dname,
                str(dname)+".png")
        else:
            self.path = os.path.join(
                self.DATA_PATH,
                dname,
                dtype,
                prefix+str(dcounter)+".png")

        print did, dname, dtype, dcounter
        print self.path

        self.set_header('Content-Type', 'image/png')
        self.set_header("Content-Length",
                        os.path.getsize(self.path))
        self.flush()
        fd = open(self.path, "rb")
        data = fd.read(self.CHUNK_SIZE)
        while data:
            self.write(data)
            yield tornado.gen.Task(self.flush)
            data = fd.read(self.CHUNK_SIZE)
        fd.close()
        self.finish()


if __name__ == "__main__":
    tornado.options.parse_command_line()
    http_server = tornado.httpserver.HTTPServer(Application())
    http_server.listen(options.port)
    tornado.ioloop.IOLoop.instance().start()