jsonpath 0.4.4 can not parse "-" character

[ReigenDing]

jsonpath2 version

0.4.4

Platform Details

ubuntu20.04

Scenario:

import json
import typing

from jsonpath2.node import Node
from jsonpath2.nodes.root import RootNode
from jsonpath2.nodes.subscript import SubscriptNode
from jsonpath2.nodes.terminal import TerminalNode
from jsonpath2.path import Path
from jsonpath2.subscript import Subscript

data = json.loads("""
{
    "va-lues": [
        {"type": 1, "value": 2},
        {"type": 2, "value": 3},
        {"type": 1, "value": 10}
    ]
}
""")

path = Path.parse_str("$.va-lues.*[?(@.type = 1)].value")

def get_subscripts(node: Node) -> typing.List[typing.List[Subscript]]:
    return get_subscripts_(node, [])

def get_subscripts_(node: Node, accumulator: typing.List[typing.List[Subscript]]) -> typing.List[typing.List[Subscript]]:
    if isinstance(node, RootNode):
        return get_subscripts_(node.next_node, accumulator)
    elif isinstance(node, SubscriptNode):
        accumulator.append(node.subscripts)
        return get_subscripts_(node.next_node, accumulator)
    elif isinstance(node, TerminalNode):
        return accumulator

for match_data in path.match(data):
    print(f"Value: {match_data.current_value}")
    print(f"JSONPath: {match_data.node.tojsonpath()}")
    print(f"Subscripts: {get_subscripts(match_data.node)}")
    print("")

Steps to Reproduce:

[If you are filing an issue what are the things we need to do in order to reproduce your problem? How are you using this software or any resources it includes?]

Expected Result:

[What are you expecting to happen as the consequence of above reproduction steps?]

Value: 2
JSONPath: $["va-lues"][0]["value"]
Subscripts: [[<jsonpath2.subscripts.objectindex.ObjectIndexSubscript object at 0x10fe93d30>], [<jsonpath2.subscripts.arrayindex.ArrayIndexSubscript object at 0x10fe9d4f0>], [<jsonpath2.subscripts.objectindex.ObjectIndexSubscript object at 0x10fe93f10>]]

Value: 10
JSONPath: $["va-lues"][2]["value"]
Subscripts: [[<jsonpath2.subscripts.objectindex.ObjectIndexSubscript object at 0x10fe93d30>], [<jsonpath2.subscripts.arrayindex.ArrayIndexSubscript object at 0x10fe9d7f0>], [<jsonpath2.subscripts.objectindex.ObjectIndexSubscript object at 0x10fe93f10>]]

Actual Result:

[What actually happens after the reproduction steps? Include the error output or a link to a gist if possible.]

line 1:4 token recognition error at: '-l'
Traceback (most recent call last):
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/Lexer.py", line 128, in nextToken
    ttype = self._interp.match(self._input, self._mode)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/atn/LexerATNSimulator.py", line 99, in match
    return self.execATN(input, dfa.s0)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/atn/LexerATNSimulator.py", line 191, in execATN
    return self.failOrAccept(self.prevAccept, input, s.configs, t)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/atn/LexerATNSimulator.py", line 250, in failOrAccept
    raise LexerNoViableAltException(self.recog, input, self.startIndex, reach)
antlr4.error.Errors.LexerNoViableAltException: LexerNoViableAltException('-')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/qiao/workspace-py/json-test/jsonpath2-test.py", line 21, in <module>
    path = Path.parse_str("$.va-lues.*[?(@.type = 1)].value")
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/path.py", line 88, in parse_str
    return cls(_parser.parse_str(*args, **kwargs))
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/__init__.py", line 468, in parse_str
    return _parse_input_stream(input_stream)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/__init__.py", line 445, in _parse_input_stream
    tree = parser.jsonpath()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/JSONPathParser.py", line 227, in jsonpath
    self.subscript()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/JSONPathParser.py", line 436, in subscript
    self.subscriptableBareword()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/JSONPathParser.py", line 662, in subscriptableBareword
    self.match(JSONPathParser.ID)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/Parser.py", line 116, in match
    self.consume()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/Parser.py", line 340, in consume
    self.getInputStream().consume()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/BufferedTokenStream.py", line 99, in consume
    if self.sync(self.index + 1):
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/BufferedTokenStream.py", line 111, in sync
    fetched = self.fetch(n)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/BufferedTokenStream.py", line 123, in fetch
    t = self.tokenSource.nextToken()
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/Lexer.py", line 130, in nextToken
    self.notifyListeners(e)             # report error
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/Lexer.py", line 285, in notifyListeners
    listener.syntaxError(self, None, self._tokenStartLine, self._tokenStartColumn, msg, e)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/antlr4/error/ErrorListener.py", line 60, in syntaxError
    delegate.syntaxError(recognizer, offendingSymbol, line, column, msg, e)
  File "/Users/qiao/workspace-py/json-test/venv/lib/python3.8/site-packages/jsonpath2/parser/__init__.py", line 63, in syntaxError
    raise ValueError('line {}:{} {}'.format(line, column, msg))
ValueError: line 1:4 token recognition error at: '-l'

[markborkum]

Thanks for filing this issue.

The path is rejected by the parser because the bareword "va-lues" is invalid. In the ANTLR grammar for the parser, barewords are allowed to contain alphanumeric characters and underscores only. (See the definition of the "ID" terminal, c.f., https://github.com/pacifica/python-jsonpath2/blob/master/jsonpath2/parser/JSONPath.g4#L99-L101.)

To obtain the expected result, replace

path = Path.parse_str("$.va-lues.*[?(@.type = 1)].value")

with

path = Path.parse_str('$["va-lues"].*[?(@.type = 1)].value')

where the bareword is replaced with a double-quoted string.

[ReigenDing]

Thanks for your reply and tips.It's helpful!