RickMuller wrote:
> One of my all-time favorite scripts is parseline, which is printed
> below
>
> def parseline(line,format):
> xlat = {'x':None,'s':str,'f':float,'d':int,'i':int}
> result = []
> words = line.split()
> for i in range(len(format)):
> f = format[i]
> trans = xlat.get(f,'None')
> if trans: result.append(trans(words[i]))
> if len(result) == 0: return None
> if len(result) == 1: return result[0]
> return result
>
> This takes a line of text, splits it, and then applies simple
> formatting characters to return different python types. For example,
> given the line
>
> H 0.000 0.000 0.000
>
> I can call parseline(line,'sfff') and it will return the string 'H',
> and three floats. If I wanted to omit the first, I could just call
> parseline(line,'xfff'). If I only wanted the first 0.000, I could call
> parseline(line,'xf').
[...]
> I would love to hear how other people do similar things.
>
> Rick
MAP = {'s':str,'f':float,'d':int,'i':int}
def parseline( line, format, separator=' '):
'''
>>> parseline('A 1 2 3 4', 'sdxf')
['A', 1, 3.0]
'''
mapping = [ (i, MAP[f]) for (i,f) in enumerate(format) if f != 'x'
]
parts = line.split(separator)
return [f(parts[i]) for (i,f) in mapping]
def parseline2( line, format):
'''
>>> parseline('A 1 2 3 4', 'sdxf')
['A', 1, 3.0]
'''
return [f(line.split()[i]) for (i,f) in [(i, MAP[f]) for (i,f) in
enumerate(format) if f != 'x']]
def parselines(lines, format, separator=' '):
'''
>>> lines = [ 'A 1 2 3 4', 'B 5 6 7 8', 'C 9 10 11 12']
>>> list(parselines(lines, 'sdxf'))
[['A', 1, 3.0], ['B', 5, 7.0], ['C', 9, 11.0]]
'''
mapping = [ (i, MAP[f]) for (i,f) in enumerate(format) if f != 'x'
]
for line in lines:
parts = line.split(separator)
yield [f(parts[i]) for (i,f) in mapping]
import doctest
doctest.testmod(verbose=True)
--
http://mail.python.org/mailman/listinfo/python-list
