You can use tokenize.generate_tokens break the string representation of Python code into tokens. tokenize
also classifies the tokens for you. Thus you can identify string literals in Python code.
It is then not hard to manipulate the tokens, adding 'u'
where desired:
import tokenize
import token
import io
import collections
class Token(collections.namedtuple('Token', 'num val start end line')):
@property
def name(self):
return token.tok_name[self.num]
def change_str_to_unicode(text):
result = text.splitlines()
# Insert a dummy line into result so indexing result
# matches tokenize's 1-based indexing
result.insert(0, '')
changes = []
for tok in tokenize.generate_tokens(io.BytesIO(text).readline):
tok = Token(*tok)
if tok.name == 'STRING' and not tok.val.startswith('u'):
changes.append(tok.start)
for linenum, s in reversed(changes):
line = result[linenum]
result[linenum] = line[:s] + 'u' + line[s:]
return '\n'.join(result[1:])
text = '''print "result code %d" % result['code']
# doesn't touch 'strings' in comments
'handles multilines' + \
'okay'
u'Unicode is not touched'
'''
print(change_str_to_unicode(text))
yields
print u"result code %d" % result[u'code']
# doesn't touch 'strings' in comments
u'handles multilines' + u'okay'
u'Unicode is not touched'