[R] devtools: improve default data import mechanism Validation chain is now possible with checkers Before that the expected values needed to be coherent. Now, we can use ObjectStore to validate the input data * add new input transformers: - uppercase - lowercase * add new input checkers (raise AssertionError on error): - decimal: take care of possible comma character as number separator - integer: cast to int() - yesno: to validate boolean value - isalpha - required: input value *must* not be empty * new control checker: - optional: block possible exception we delete field in the returned dict instead of raising AssertionError (exclusive with required) Helper methods to manipulate indexes: * build_rqlindex() is used to build index based on already created entities * fetch() replace get_one()/get_many() methods by factorizing code Minor changes in reporting: * use tell() for all printing * let new value for askerrors to display automatically the report (used in crontab)

     1

#!/usr/bin/python

     2

     3

"""usage: fix-po-encodings [filename...]

     4

change the encoding of the po files passed as arguments to utf-8

     5

"""

     6

import sys

     7

import re

     8

import codecs

     9

    10

def change_encoding(filename, target='UTF-8'):

    11

    fdesc = open(filename)

    12

    data = fdesc.read()

    13

    fdesc.close()

    14

    encoding = find_encoding(data)

    15

    if encoding == target:

    16

        return

    17

    data = fix_encoding(data, target)

    18

    data = unicode(data, encoding)

    19

    fdesc = codecs.open(filename, 'wb', encoding=target)

    20

    fdesc.write(data)

    21

    fdesc.close()

    22

    23

def find_encoding(data):

    24

    regexp = re.compile(r'"Content-Type:.* charset=([a-zA-Z0-9-]+)\\n"', re.M)

    25

    mo = regexp.search(data)

    26

    if mo is None:

    27

        raise ValueError('No encoding declaration')

    28

    return mo.group(1)

    29

    30

def fix_encoding(data, target_encoding):

    31

    regexp = re.compile(r'("Content-Type:.* charset=)(.*)(\\n")', re.M)

    32

    return regexp.sub(r'\1%s\3' % target_encoding, data)

    33

    34

    35

    36

for filename in sys.argv[1:]:

    37

    print filename

    38

    change_encoding(filename)