问当有多个分隔符或没有分隔符时，拆分字符串(数字表示单位)

EN

import re

p = re.compile('^(\s+)?(?P<sym>([\>\<]|\+\/\-|\-)\s*)?(?P<num>(\d+(\.\d+)?))((?P<orsec> (\-|or) )?(?P<num2>\d+(\.\d+)?)?)?\s*(?P<unit>[a-zA-Z\%\/]+)?$')

text = '''
 0.1 - 1000 dB/s
 >45 dB
 30 pm
 +/- 0.3 %
10 - 100                    %
 5 - 20                    mW
 10 - 62                    Watts
 -40 - 85                    C
 0.640 or 0.810 um
  0.640 or 0.810 um
 20
 15
'''

for line in text.split('\n'):
    if line.strip():
        m = p.match(line)
        if m:
            print(f'{line:40} => {m.groupdict()}')
        else:
            print(f'{line:40} => no match')

 0.1 - 1000 dB/s                           => {'sym': None, 'num': '0.1', 'orsec': ' - ', 'num2': '1000', 'unit': 'dB/s'}
 >45 dB                                    => {'sym': '>', 'num': '45', 'orsec': None, 'num2': None, 'unit': 'dB'}
 30 pm                                     => {'sym': None, 'num': '30', 'orsec': None, 'num2': None, 'unit': 'pm'}
 +/- 0.3 %                                 => {'sym': '+/- ', 'num': '0.3', 'orsec': None, 'num2': None, 'unit': '%'}
10 - 100                    %              => {'sym': None, 'num': '10', 'orsec': ' - ', 'num2': '100', 'unit': '%'}
 5 - 20                    mW              => {'sym': None, 'num': '5', 'orsec': ' - ', 'num2': '20', 'unit': 'mW'}
 10 - 62                    Watts          => {'sym': None, 'num': '10', 'orsec': ' - ', 'num2': '62', 'unit': 'Watts'}
 -40 - 85                    C             => {'sym': '-', 'num': '40', 'orsec': ' - ', 'num2': '85', 'unit': 'C'}
 0.640 or 0.810 um                         => {'sym': None, 'num': '0.640', 'orsec': ' or ', 'num2': '0.810', 'unit': 'um'}
  0.640 or 0.810 um                        => {'sym': None, 'num': '0.640', 'orsec': ' or ', 'num2': '0.810', 'unit': 'um'}
 20                                        => {'sym': None, 'num': '20', 'orsec': None, 'num2': None, 'unit': None}
 15                                        => {'sym': None, 'num': '15', 'orsec': None, 'num2': None, 'unit': None}

import re
REMOVE_SPACES = re.compile(r'( {2,})') # Matches 2 or more spaces.
lines = []
with open('data.txt') as f:
    for line in f:
        line = line.strip() # remove leading and trailing spaces
        line = REMOVE_SPACES.sub(' ', line) # Replaces more than one space with a single space
        chunks = line.split(' ') # Split on spaces
        if len(chunks) == 1: # If only one chunk then it has no unit.
            lines.append((chunks[0], None))
        else:
            lines.append((' '.join(chunks[:-1]), chunks[-1])) # Else append the value and the unit
print(*lines, sep='\r\n')

('0.1 - 1000', 'dB/s')
('>45', 'dB')
('30', 'pm')
('+/- 0.3', '%')
('10 - 100', '%')
('5 - 20', 'mW')
('10 - 62', 'Watts')
('-40 - 85', 'C')
('0.640 or 0.810', 'um')
('0.640 or 0.810', 'um')
('20', None)
('15', None)