1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
|
#!/usr/bin/env python
# Copyright (c) 2012 The Chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
'''Utility to remove comments from JSON files so that they can be parsed by
json.loads.
'''
import sys
def _Rcount(string, chars):
'''Returns the number of consecutive characters from |chars| that occur at the
end of |string|.
'''
return len(string) - len(string.rstrip(chars))
def _FindNextToken(string, tokens, start):
'''Finds the next token in |tokens| that occurs in |string| from |start|.
Returns a tuple (index, token key).
'''
min_index, min_key = (-1, None)
for k in tokens:
index = string.find(k, start)
if index != -1 and (min_index == -1 or index < min_index):
min_index, min_key = (index, k)
return (min_index, min_key)
def _ReadString(input, start, output):
output.append('"')
start_range, end_range = (start, input.find('"', start))
# \" escapes the ", \\" doesn't, \\\" does, etc.
while (end_range != -1 and
_Rcount(input[start_range:end_range], '\\') % 2 == 1):
start_range, end_range = (end_range, input.find('"', end_range + 1))
if end_range == -1:
return start_range + 1
output.append(input[start:end_range + 1])
return end_range + 1
def _ReadComment(input, start, output):
eol_tokens = ('\n', '\r')
eol_token_index, eol_token = _FindNextToken(input, eol_tokens, start)
if eol_token is None:
return len(input)
output.append(eol_token)
return eol_token_index + len(eol_token)
def _ReadMultilineComment(input, start, output):
end_tokens = ('*/',)
end_token_index, end_token = _FindNextToken(input, end_tokens, start)
if end_token is None:
raise Exception("Multiline comment end token (*/) not found")
return end_token_index + len(end_token)
def Nom(input):
token_actions = {
'"': _ReadString,
'//': _ReadComment,
'/*': _ReadMultilineComment,
}
output = []
pos = 0
while pos < len(input):
token_index, token = _FindNextToken(input, token_actions.keys(), pos)
if token is None:
output.append(input[pos:])
break
output.append(input[pos:token_index])
pos = token_actions[token](input, token_index + len(token), output)
return ''.join(output)
if __name__ == '__main__':
sys.stdout.write(Nom(sys.stdin.read()))
|
