dchaplinsky

import bz2

with bz2.BZ2File("test.bz2", "r") as fp:
    i = 0
    for l in fp:
        print(l)

dchaplinsky

dchaplinsky

In [1]: from unicodecsv import DictReader

In [2]: fp = open("problematic.csv", "r")

In [3]: r = DictReader(fp)

In [4]: r.next()  # First row is not interesting
Out[4]: 
{u'\u0406\u041f\u041d': u'',
 u'\u0414\u0430\u0442\u0430 \u0432\u0456\u0434\u043f\u043e\u0432\u0456\u0434\u0456': u'',

dchaplinsky

# -*- mode: ruby -*-
# vi: set ft=ruby :

# All Vagrant configuration is done below. The "2" in Vagrant.configure
# configures the configuration version (we support older styles for
# backwards compatibility). Please don't change it unless you know what
# you're doing.
Vagrant.configure(2) do |config|
  #Django Frontend
  config.vm.network "forwarded_port", guest: 8000, host: 8080

dchaplinsky

{"sentence": [["Гучне", [[["adj", "post"], ["s", "nmbr"], ["n", "gndr"], ["v_naz", "CAse"], ["compb", "forms"]], [["adj", "post"], ["s", "nmbr"], ["n", "gndr"], ["v_zna", "CAse"], ["compb", "forms"]]]], ["затримання", [[["noun", "post"], ["s", "nmbr"], ["n", "gndr"], ["v_naz", "CAse"], ["inanim", "ANim"]], [["noun", "post"], ["s", "nmbr"], ["n", "gndr"], ["v_rod", "CAse"], ["inanim", "ANim"]], [["noun", "post"], ["s", "nmbr"], ["n", "gndr"], ["v_zna", "CAse"], ["inanim", "ANim"]], [["noun", "post"], ["p", "nmbr"], ["v_naz", "CAse"], ["inanim", "ANim"]], [["noun", "post"], ["p", "nmbr"], ["v_zna", "CAse"], ["inanim", "ANim"]]]], ["підполковника", [[["noun", "post"], ["s", "nmbr"], ["m", "gndr"], ["v_rod", "CAse"], ["anim", "ANim"]], [["noun", "post"], ["s", "nmbr"], ["m", "gndr"], ["v_zna", "CAse"], ["anim", "ANim"]]]], ["Нацгвардії", []], ["за", [[["prep", "post"], ["rv_rod", "req_case"], ["rv_zna", "req_case"], ["rv_oru", "req_case"]]]], ["хабар", [[["noun", "post"], ["s", "nmbr"], ["m", "gndr"], ["v_naz", "

dchaplinsky

<root>
<id>A</id>
<author_surname></author_surname>
<author_name></author_name>
<title>На болото в Закарпатті повернулися вода та бобри</title>
<publ_in>Львівська газета</publ_in>
<url>http://www.gazeta.lviv.ua/ecology/37205</url>
<publ_part></publ_part>
<publ_place></publ_place>
<publisher></publisher>

dchaplinsky

--- misc.py~	2010-10-25 14:07:30.000000000 +0300
+++ misc.py	2010-10-25 14:13:56.000000000 +0300
@@ -1,5 +1,6 @@
 from coffin import template
-from jinja2 import Markup
+from jinja2 import Markup, nodes
+from jinja2.ext import Extension
 register = template.Library()
  
 @register.filter(jinja2_only=True)

dchaplinsky

from coffin.template import Template as JTemplate
from django.template.loaders import app_directories, filesystem
from django.template import TemplateDoesNotExist

# integrate jinja instead of django template language to take advantage of 
# all django helper function like direct_to_template

def _render_or_die(source, origin):
    """helper function for loaders below. Makes a simple check if 
    passed template seems to be jinja one and raising exception otherwise"""

dchaplinsky

from django.db.models.query import QuerySet
old_get = QuerySet.get

def new_get(self, *args, **kwargs):
    if len(kwargs) == 1:
        for field_name in kwargs:
            if "__" in field_name:
                field_name, kind = field_name.split("__")
                if kind != 'exact':
                    continue

dchaplinsky

from amazonproduct import API
import os
from hashlib import md5


old_fetch = API._fetch
old_build_url = API._build_url
old_init = API.__init__

def new_fetch(self, url):