def match_format_string(format_str, s):
"""Match s against the given format string, return dict of matches.
We assume all of the arguments in format string are named keyword arguments (i.e. no {} or
{:0.2f}). We also assume that all chars are allowed in each keyword argument, so separators
need to be present which aren't present in the keyword arguments (i.e. '{one}{two}' won't work
reliably as a format string but '{one}-{two}' will if the hyphen isn't used in {one} or {two}).
We raise if the format string does not match s.
Example:
fs = '{test}-{flight}-{go}'
s = fs.format('first', 'second', 'third')
match_format_string(fs, s) -> {'test': 'first', 'flight': 'second', 'go': 'third'}
"""
# First split on any keyword arguments, note that the names of keyword arguments will be in the
# 1st, 3rd, ... positions in this list
tokens = re.split(r'\{(.*?)\}', format_str)
keywords = tokens[1::2]
# Now replace keyword arguments with named groups matching them. We also escape between keyword
# arguments so we support meta-characters there. Re-join tokens to form our regexp pattern
tokens[1::2] = map(u'(?P<{}>.*)'.format, keywords)
tokens[0::2] = map(re.escape, tokens[0::2])
pattern = ''.join(tokens)
# Use our pattern to match the given string, raise if it doesn't match
matches = re.match(pattern, s)
if not matches:
raise Exception("Format string did not match")
# Return a dict with all of our keywords and their values
return {x: matches.group(x) for x in keywords}
5条答案
按热度按时间b09cbbtk1#
parse module "与format()"相反。
示例用法:
ubby3x7f2#
你可能会觉得模拟扫描很有趣。
ctzwtxfj3#
如果你不想使用parse模块,这里有一个解决方案。它将格式字符串转换为带有命名组的正则表达式。它做了一些假设(在docstring中描述),这些假设在我的情况下是可以的,但在你的情况下可能不太好。
wfsdck304#
不如这样:
这将在破折号处拆分零件代号,获取第二个部分并将其转换为整数。
另外,我保留了
id
作为变量名,这样与你的问题的联系就很清楚了。重命名这个变量是一个好主意,它不会隐藏内置函数。vbkedwbf5#
使用lucidity