I understand that re.search returns a match object re.search(pattern, string, flags=0) I am testing the success of the match & then retrieving the string.
# matchTest.py --- testing match object returns
import re
# expected_pattern = suburbRegex
suburbRegex = "(?s)(,_\S \s)"
# line leading up to and including expected_pattern
mostOfLineRex = "(?s)(^. ,\S )"
# expected_pattern to end of line
theRestRex = "(?s),_\S \s\w \s(. )"
fileLines = ['173 ANDREWS John Frances 20 Bell_Road,_Sub_urbia Semi Retired\n']
for fileLine in fileLines:
result = re.search(suburbRegex, fileLine)
# print(type(result)) # re.Match
if(result):
patResult = re.search(suburbRegex, fileLine).group(0)
# print(patResult)
# print(type(patResult)) # str
# print(type(re.search(suburbRegex, fileLine).group(0))) # str
start = re.search(mostOfLineRex, fileLine)
if(start):
start = re.search(mostOfLineRex, fileLine).group(0)
# print(start)
print(type(start)) # str
end = re.search(theRestRex, fileLine)
if(end):
end = re.search(theRestRex, fileLine).group(0)
# print(end)
print(type(end)) # str
newFileLine = start ' ' end
else:
print("The listing does not have a suburb!")
# File "~\matchTest.py", line 31, in <module>
# newFileLine = start ' ' end
# TypeError: can only concatenate str (not "NoneType") to str
I checked that types for start & end are <class 'str'>
So why do I get NoneType
error?
CodePudding user response:
You have an erroneous assumption about the return values from re.search()
>>> matches = re.search(r'[0-9] ', "testme 9"); matches; type(matches)
<re.Match object; span=(7, 8), match='9'>
<class 're.Match'>
>>> matches = re.search(r'[0-9] ', "testme"); matches; type(matches)
<class 'NoneType'>
Which explains your error when trying to concatenate start
" "
and end
.