Last active
August 29, 2015 14:05
-
-
Save henriquebastos/9b491152ffc35790dd1a to your computer and use it in GitHub Desktop.
CSV helper for python-decouple
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Example: | |
>>> csv = Csv() | |
>>> csv('127.0.0.1, .localhost, .herokuapp.com') | |
['127.0.0.1', '.localhost', '.herokuapp.com'] | |
>>> csv = Csv(int) | |
>>> csv('1,2,3,4,5') | |
[1, 2, 3, 4, 5] | |
>>> csv = Csv(cast=lambda s: s.upper(), delimiter='\t', strip=' %*') | |
>>> csv('%virtual_env%\t *important stuff*\t trailing spaces ') | |
['VIRTUAL_ENV', 'IMPORTANT STUFF', 'TRAILING SPACES'] | |
""" | |
def __init__(self, cast=text_type, delimiter=', \t\r\n', strip=string.whitespace): | |
""" | |
Parameters: | |
cast -- callable that transforms the item just before it's added to the list. | |
delimiter -- string of delimiters chars passed to shlex. | |
strip -- string of non-relevant characters to be passed to str.strip after the split. | |
""" | |
self.cast = cast | |
self.delimiter = delimiter | |
self.strip = strip | |
def __call__(self, value): | |
"""The actual transformation""" | |
transform = lambda s: self.cast(s.strip(self.strip)) | |
splitter = shlex(value, posix=True) | |
splitter.whitespace = self.delimiter | |
splitter.whitespace_split = True | |
return [transform(s) for s in splitter] |
Pode ser interessante usar o módulo shlex
para isso.
>>> splitter = shlex.shlex("""foo, bar, 'baz,qux',doo""", posix=True)
>>> splitter.whitespace = ","
>>> splitter.whitespace_split = True
>>> print [part.strip(string.whitespace) for part in splitter]
['foo', 'bar', 'baz,qux', 'doo']
Muito maneiro, @osantana! Fiz uma nova versão com o shlex
e acho q ficou redondo.
Extrapolei uns testes para garantir o quoted parse e funcionou legal.
csv = Csv()
assert ['foo', 'bar, baz', 'qux'] == csv(""" foo ,'bar, baz', 'qux'""")
assert ['foo', 'bar, baz', 'qux'] == csv(''' foo ,"bar, baz", "qux"''')
assert ['foo', "'bar, baz'", "'qux"] == csv(''' foo ,"'bar, baz'", "'qux"''')
assert ['foo', '"bar, baz"', '"qux'] == csv(""" foo ,'"bar, baz"', '"qux'""")
Só acho que agora tem uma interseção indesejada entre o delimiter e o strip... acho que o delimiter padrão deve ser só o ,
mesmo.
Também acho que usar só ',' seja melhor.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Tem um problema com quoted parse... rolaria algo como
foo,"bar,baz", "qux" -> ["foo", "bar,baz", "qux"]
seria melhor o
def __init__(..., strip=string.whitespace):
(que é o default dostr.strip()
)