[cubicweb/doc] Add tutorial on data import in CubicWeb. This involves creating the "tutorials/dataimport" directory structure under "cubicweb/doc" and, inside the "dataimport" directory, putting several files: - a ResT file containing the tutorial *per se*; this tutorial addresses the following issues: * creating a CubicWeb schema for representing a given data set (here, the Diseasome RDF data, for illustration purposes); * parsing the data; * importing the data, by using several stores: + the ``RQLObjectStore``, ``NoHookRQLObjectStore`` and ``SQLGenObjectStore`` from the ``dataimport`` module in CubicWeb; + the ``MassiveObjectStore`` from the ``dataimport`` module in the ``dataio`` cube. The tutorial also provides timing benchmarks of the various stores. - a set of Python files illustrating the data import, in the context of Diseasome RDF data parsing: * a Diseasome RDF data parse module, * a Diseasome data import module, * a CubicWeb schema for representing Diseasome data.

#!/usr/bin/python

"""usage: fix-po-encodings [filename...]
change the encoding of the po files passed as arguments to utf-8
"""
import sys
import re
import codecs

def change_encoding(filename, target='UTF-8'):
    fdesc = open(filename)
    data = fdesc.read()
    fdesc.close()
    encoding = find_encoding(data)
    if encoding == target:
        return
    data = fix_encoding(data, target)
    data = unicode(data, encoding)
    fdesc = codecs.open(filename, 'wb', encoding=target)
    fdesc.write(data)
    fdesc.close()

def find_encoding(data):
    regexp = re.compile(r'"Content-Type:.* charset=([a-zA-Z0-9-]+)\\n"', re.M)
    mo = regexp.search(data)
    if mo is None:
        raise ValueError('No encoding declaration')
    return mo.group(1)

def fix_encoding(data, target_encoding):
    regexp = re.compile(r'("Content-Type:.* charset=)(.*)(\\n")', re.M)
    return regexp.sub(r'\1%s\3' % target_encoding, data)
    


for filename in sys.argv[1:]:
    print filename
    change_encoding(filename)