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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
|
from __future__ import print_function, absolute_import, division, generators, nested_scopes
import sys
import os.path
import logging
import ply.yacc
from jsonpath_rw.jsonpath import *
from jsonpath_rw.lexer import JsonPathLexer
logger = logging.getLogger(__name__)
def parse(string):
return JsonPathParser().parse(string)
class JsonPathParser(object):
'''
An LALR-parser for JsonPath
'''
tokens = JsonPathLexer.tokens
def __init__(self, debug=False, lexer_class=None):
if self.__doc__ == None:
raise Exception('Docstrings have been removed! By design of PLY, jsonpath-rw requires docstrings. You must not use PYTHONOPTIMIZE=2 or python -OO.')
self.debug = debug
self.lexer_class = lexer_class or JsonPathLexer # Crufty but works around statefulness in PLY
def parse(self, string, lexer = None):
lexer = lexer or self.lexer_class()
return self.parse_token_stream(lexer.tokenize(string))
def parse_token_stream(self, token_iterator, start_symbol='jsonpath'):
# Since PLY has some crufty aspects and dumps files, we try to keep them local
# However, we need to derive the name of the output Python file :-/
output_directory = os.path.dirname(__file__)
try:
module_name = os.path.splitext(os.path.split(__file__)[1])[0]
except:
module_name = __name__
parsing_table_module = '_'.join([module_name, start_symbol, 'parsetab'])
# And we regenerate the parse table every time; it doesn't actually take that long!
new_parser = ply.yacc.yacc(module=self,
debug=self.debug,
tabmodule = parsing_table_module,
outputdir = output_directory,
write_tables=0,
start = start_symbol,
errorlog = logger)
return new_parser.parse(lexer = IteratorToTokenStream(token_iterator))
# ===================== PLY Parser specification =====================
precedence = [
('left', ','),
('left', 'DOUBLEDOT'),
('left', '.'),
('left', '|'),
('left', '&'),
('left', 'WHERE'),
]
def p_error(self, t):
raise Exception('Parse error at %s:%s near token %s (%s)' % (t.lineno, t.col, t.value, t.type))
def p_jsonpath_binop(self, p):
"""jsonpath : jsonpath '.' jsonpath
| jsonpath DOUBLEDOT jsonpath
| jsonpath WHERE jsonpath
| jsonpath '|' jsonpath
| jsonpath '&' jsonpath"""
op = p[2]
if op == '.':
p[0] = Child(p[1], p[3])
elif op == '..':
p[0] = Descendants(p[1], p[3])
elif op == 'where':
p[0] = Where(p[1], p[3])
elif op == '|':
p[0] = Union(p[1], p[3])
elif op == '&':
p[0] = Intersect(p[1], p[3])
def p_jsonpath_fields(self, p):
"jsonpath : fields_or_any"
p[0] = Fields(*p[1])
def p_jsonpath_named_operator(self, p):
"jsonpath : NAMED_OPERATOR"
if p[1] == 'this':
p[0] = This()
elif p[1] == 'parent':
p[0] = Parent()
else:
raise Exception('Unknown named operator `%s` at %s:%s' % (p[1], p.lineno(1), p.lexpos(1)))
def p_jsonpath_root(self, p):
"jsonpath : '$'"
p[0] = Root()
def p_jsonpath_idx(self, p):
"jsonpath : '[' idx ']'"
p[0] = p[2]
def p_jsonpath_slice(self, p):
"jsonpath : '[' slice ']'"
p[0] = p[2]
def p_jsonpath_fieldbrackets(self, p):
"jsonpath : '[' fields ']'"
p[0] = Fields(*p[2])
def p_jsonpath_child_fieldbrackets(self, p):
"jsonpath : jsonpath '[' fields ']'"
p[0] = Child(p[1], Fields(*p[3]))
def p_jsonpath_child_idxbrackets(self, p):
"jsonpath : jsonpath '[' idx ']'"
p[0] = Child(p[1], p[3])
def p_jsonpath_child_slicebrackets(self, p):
"jsonpath : jsonpath '[' slice ']'"
p[0] = Child(p[1], p[3])
def p_jsonpath_parens(self, p):
"jsonpath : '(' jsonpath ')'"
p[0] = p[2]
# Because fields in brackets cannot be '*' - that is reserved for array indices
def p_fields_or_any(self, p):
"""fields_or_any : fields
| '*' """
if p[1] == '*':
p[0] = ['*']
else:
p[0] = p[1]
def p_fields_id(self, p):
"fields : ID"
p[0] = [p[1]]
def p_fields_comma(self, p):
"fields : fields ',' fields"
p[0] = p[1] + p[3]
def p_idx(self, p):
"idx : NUMBER"
p[0] = Index(p[1])
def p_slice_any(self, p):
"slice : '*'"
p[0] = Slice()
def p_slice(self, p): # Currently does not support `step`
"slice : maybe_int ':' maybe_int"
p[0] = Slice(start=p[1], end=p[3])
def p_maybe_int(self, p):
"""maybe_int : NUMBER
| empty"""
p[0] = p[1]
def p_empty(self, p):
'empty :'
p[0] = None
class IteratorToTokenStream(object):
def __init__(self, iterator):
self.iterator = iterator
def token(self):
try:
return next(self.iterator)
except StopIteration:
return None
if __name__ == '__main__':
logging.basicConfig()
parser = JsonPathParser(debug=True)
print(parser.parse(sys.stdin.read()))
|
