Custom locale configuration for float conversion

Question

I need to convert a string in the format \"1.234.345,00\" to the float value 1234345.00.

One way is to use repeated str.repl

Answer 1

Here's something, using Babel, that works for me.

First you feed it some test data, with your expectations and it builds a dictionary of separator to locale alias that fits.

Then you can convert from that point on.

import string
from decimal import Decimal
from babel.numbers import parse_decimal, NumberFormatError
from babel.core import UnknownLocaleError
import locale

traindata = [
    ("1.234.345,00", Decimal("1234345.00")),
    ("1,234,345.00", Decimal("1234345.00")),
    ("345", Decimal("345.00")),
]

data = traindata + [
    ("345,00", Decimal("345.00")),
    ("345.00", Decimal("345.00")),
    ("746", Decimal("746.00")),
]

def findseps(input_):
    #you need to have no separator 
    #or at least a decimal separator for this to work...

    seps = [c for c in input_ if not c in string.digits]
    if not seps:
        return ""

    sep = seps[-1]
    #if the decimal is something then thousand will be the other...
    seps = "." + sep if sep == "," else "," + sep
    return seps 


def setup(input_, exp, lookup):


    key = findseps(input_)

    if key in lookup:
        return

    for alias in locale.locale_alias:
        #print(alias)

        try:
            got = parse_decimal(input_, locale=alias)
        except (NumberFormatError,UnknownLocaleError, ValueError) as e:
            continue
        except (Exception,) as e:
            raise
        if exp == got:
            lookup[key] = alias
            return


def convert(input_, lookup):
    seps = findseps(input_)
    try:
        locale_ = lookup[seps]
        convert.locale_ = locale_
    except (KeyError,) as e:
        convert.locale_ = None
        return "unexpected seps:%s" % seps

    try:
        return parse_decimal(input_, locale=locale_)
    except (Exception,) as e:
        return e


lookup = {}

#train your data
for input_, exp in traindata:
    setup(input_, exp, lookup)

#once it's trained you know which locales to use
print(data)


for input_, exp in data:
    got = convert(input_, lookup)

    # print (input_)
    msg = "%s => %s with local:%s:" % (input_, got, convert.locale_)
    if exp == got:
        print("\n  success : " + msg)
    else:
        print("\n  failure : " + msg)

print(lookup)

output:

[('1.234.345,00', Decimal('1234345.00')), ('1,234,345.00', Decimal('1234345.00')), ('345', Decimal('345.00')), ('345,00', Decimal('345.00')), ('345.00', Decimal('345.00')), ('746', Decimal('746.00'))]

  success : 1.234.345,00 => 1234345.00 with local:is_is:

  success : 1,234,345.00 => 1234345.00 with local:ko_kr.euc:

  success : 345 => 345 with local:ko_kr.euc:

  success : 345,00 => 345.00 with local:is_is:

  success : 345.00 => 345.00 with local:ko_kr.euc:

  success : 746 => 746 with local:ko_kr.euc:
{',.': 'ko_kr.euc', '': 'ko_kr.euc', '.,': 'is_is'}