2009-05-02 09:36:44 -03:00
|
|
|
"""JSON token scanner
|
2008-05-08 11:29:10 -03:00
|
|
|
"""
|
|
|
|
import re
|
2009-05-02 09:36:44 -03:00
|
|
|
try:
|
|
|
|
from _json import make_scanner as c_make_scanner
|
2013-07-04 18:43:24 -03:00
|
|
|
except ImportError:
|
2009-05-02 09:36:44 -03:00
|
|
|
c_make_scanner = None
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
__all__ = ['make_scanner']
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
NUMBER_RE = re.compile(
|
|
|
|
r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
|
|
|
|
(re.VERBOSE | re.MULTILINE | re.DOTALL))
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
def py_make_scanner(context):
|
|
|
|
parse_object = context.parse_object
|
|
|
|
parse_array = context.parse_array
|
|
|
|
parse_string = context.parse_string
|
|
|
|
match_number = NUMBER_RE.match
|
|
|
|
strict = context.strict
|
|
|
|
parse_float = context.parse_float
|
|
|
|
parse_int = context.parse_int
|
|
|
|
parse_constant = context.parse_constant
|
|
|
|
object_hook = context.object_hook
|
2010-09-04 17:16:53 -03:00
|
|
|
object_pairs_hook = context.object_pairs_hook
|
|
|
|
memo = context.memo
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
def _scan_once(string, idx):
|
|
|
|
try:
|
|
|
|
nextchar = string[idx]
|
|
|
|
except IndexError:
|
2017-04-05 03:37:24 -03:00
|
|
|
raise StopIteration(idx) from None
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
if nextchar == '"':
|
|
|
|
return parse_string(string, idx + 1, strict)
|
|
|
|
elif nextchar == '{':
|
|
|
|
return parse_object((string, idx + 1), strict,
|
2010-09-04 17:16:53 -03:00
|
|
|
_scan_once, object_hook, object_pairs_hook, memo)
|
2009-05-02 09:36:44 -03:00
|
|
|
elif nextchar == '[':
|
|
|
|
return parse_array((string, idx + 1), _scan_once)
|
|
|
|
elif nextchar == 'n' and string[idx:idx + 4] == 'null':
|
|
|
|
return None, idx + 4
|
|
|
|
elif nextchar == 't' and string[idx:idx + 4] == 'true':
|
|
|
|
return True, idx + 4
|
|
|
|
elif nextchar == 'f' and string[idx:idx + 5] == 'false':
|
|
|
|
return False, idx + 5
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
m = match_number(string, idx)
|
|
|
|
if m is not None:
|
|
|
|
integer, frac, exp = m.groups()
|
|
|
|
if frac or exp:
|
|
|
|
res = parse_float(integer + (frac or '') + (exp or ''))
|
|
|
|
else:
|
|
|
|
res = parse_int(integer)
|
|
|
|
return res, m.end()
|
|
|
|
elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
|
|
|
|
return parse_constant('NaN'), idx + 3
|
|
|
|
elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
|
|
|
|
return parse_constant('Infinity'), idx + 8
|
|
|
|
elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
|
|
|
|
return parse_constant('-Infinity'), idx + 9
|
|
|
|
else:
|
2013-01-03 02:44:15 -04:00
|
|
|
raise StopIteration(idx)
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2010-09-04 17:16:53 -03:00
|
|
|
def scan_once(string, idx):
|
|
|
|
try:
|
|
|
|
return _scan_once(string, idx)
|
|
|
|
finally:
|
|
|
|
memo.clear()
|
|
|
|
|
2018-05-22 08:55:07 -03:00
|
|
|
return scan_once
|
2008-05-08 11:29:10 -03:00
|
|
|
|
2009-05-02 09:36:44 -03:00
|
|
|
make_scanner = c_make_scanner or py_make_scanner
|