问正则表达式解析Namelist输入文件中的键值对

EN

$VEHICLES
 CARS= 1,
 TRUCKS = 0,
 PLAINS= 0, TRAINS = 0,
 LIB='AUTO.DAT',
C This is a comment
C Data variable spans multiple lines
 DATA=1.2,2.34,3.12,
      4.56E-2,6.78,
$END
$PLOTTING
 PLOT=T,
 PLOT(2)=12,
$END

import re
from collections import OrderedDict

f=open('file.dat','r')
file_str=f.read()

#Compile regex pattern for requested namelist
name='Vehicles'

p_namelist = re.compile(r"\$"+name.upper()+"(.*?)\$END",flags=re.DOTALL|re.MULTILINE)

#Execute regex on file string and get a list of captured tokens
m_namelist = p_namelist.findall(file_str)

#Check for a valid result
if m_namelist:
    #The text of the desired namelist is the first captured token
    namelist=m_namelist[0]

#Split into lines
lines=namelist.splitlines()

#List comprehension which returns the list of lines that do not start with "C"
#Effectively remove comment lines
lines = [item for item in lines if not item.startswith("C")]

#Re-combine now that comment lines are removed
namelist='\n'.join(lines)

#Create key-value parsing regex
p_item = re.compile(r"([^\s,\=]+?)\s*=\s*([^=]+)(?=[\s,][^\s,\=]+\s*\=|$)",flags=re.DOTALL|re.MULTILINE)

#Execute regex
items = p_item.findall(namelist)

#Initialize namelist ordered dictionary
n = OrderedDict()

#Remove undesired characters from value    
for item in items:
    n[item[0]] = item[1].strip(',\r\n ')

([^\s,\=]+?)\s*=\s*([^=]+)(?=[\s,][^\s,\=]+\s*\=|$)

 ([^\s,\=]+?)\s*=\s*((?:\s*\d[\d\.\E\+\-]*\s*,){2,}|[^=,]+)