How to write simple code to match strings?

[Stefan Behnel]

Steven D'Aprano, 30.12.2009 07:01:
> def _re_match_items(s):
>     # Setup some regular expressions.
>     COMMON_RE = r'\$?([-+]?[0-9,]*\.?[0-9,]+)'
>     FLOAT_RE = COMMON_RE + '$'
>     BRACKETED_FLOAT_RE = r'\(' + COMMON_RE + r'\)$'
>     DATE_RE = r'\d{1,2}-\w+-\d{1,2}$'
>     mo = re.match(FLOAT_RE, s)  # "mo" short for "match object"
>     if mo:
>         return float(mo.group(1).replace(',', ''))
>     # Otherwise mo will be None and we go on to the next test.
>     mo = re.match(BRACKETED_FLOAT_RE, s)
>     if mo:
>         return -float(mo.group(1).replace(',', ''))
>     if re.match(DATE_RE, s):
>         return dateutil.parser.parse(s, dayfirst=True)
>     raise ValueError("bad string can't be matched")

Given that this is meant for converting single data items, which may happen 
quite frequently in a program (depending on the size of the input), you 
might want to use pre-compiled regexps here.

Also, you can convert the above into a single regexp with multiple 
alternative groups and then just run the matcher once, e.g. (untested):

     COMMON_RE = r'\$?([-+]?[0-9,]*\.?[0-9,]+)'
     FLOAT_RE = COMMON_RE + '$'
     BRACKETED_FLOAT_RE = r'\(' + COMMON_RE + r'\)$'
     DATE_RE = r'(\d{1,2}-\w+-\d{1,2})$'  # note the surrounding () I added

     match_data_items = re.compile('|'.join(
         [BRACKETED_FLOAT_RE, FLOAT_RE, DATE_RE])).match

     def convert_data_item(s):
         # ...
         match = match_data_items(s)
         if match:
             bfloat_value, float_value, date_value = match.groups()
             if bfloat_value:
                 return -float(bfloat_value.replace(',', ''))
             if float_value:
                 return float(bfloat_value.replace(',', ''))
             if date_value:
                 return dateutil.parser.parse(date_value, dayfirst=True)
         raise ...

Stefan