Skip to content

Fix token end offset for quoted identifiers, literals, and raw strings #382

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chiliec wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

Fix token end offset for quoted identifiers, literals, and raw strings #382

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion CHANGELOG.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
Next Release (TBD)
==================

* No changes yet.
* Fix ``end`` position offset for quoted identifier, literal, and raw string
literal tokens
(`issue #380 <https://github.com/jmespath/jmespath.py/issues/380>`__)


1.1.0
Expand Down
6 changes: 3 additions & 3 deletions jmespath/lexer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,15 +174,15 @@ def _consume_literal(self):
message="Bad token %s" % lexeme)
token_len = self._position - start
return {'type': 'literal', 'value': parsed_json,
'start': start, 'end': token_len}
'start': start, 'end': start + token_len}

def _consume_quoted_identifier(self):
start = self._position
lexeme = '"' + self._consume_until('"') + '"'
try:
token_len = self._position - start
return {'type': 'quoted_identifier', 'value': loads(lexeme),
'start': start, 'end': token_len}
'start': start, 'end': start + token_len}
except ValueError as e:
error_message = str(e).split(':')[0]
raise LexerError(lexer_position=start,
Expand All @@ -194,7 +194,7 @@ def _consume_raw_string_literal(self):
lexeme = self._consume_until("'").replace("\\'", "'")
token_len = self._position - start
return {'type': 'literal', 'value': lexeme,
'start': start, 'end': token_len}
'start': start, 'end': start + token_len}

def _match_or_else(self, expected, match_type, else_type):
start = self._position
Expand Down
21 changes: 21 additions & 0 deletions tests/test_lexer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,6 +132,27 @@ def test_position_multiple_tokens(self):
]
)

def test_position_quoted_identifier(self):
tokens = list(self.lexer.tokenize('foo."q"'))
quoted = [t for t in tokens if t['type'] == 'quoted_identifier'][0]
self.assertEqual(quoted['start'], 4)
self.assertEqual(quoted['end'], 6)
self.assertGreaterEqual(quoted['end'], quoted['start'])

def test_position_literal_not_at_start(self):
tokens = list(self.lexer.tokenize('foo.`123`'))
literal = [t for t in tokens if t['type'] == 'literal'][0]
self.assertEqual(literal['start'], 4)
self.assertEqual(literal['end'], 8)
self.assertGreaterEqual(literal['end'], literal['start'])

def test_position_raw_string_not_at_start(self):
tokens = list(self.lexer.tokenize("foo.'bar'"))
literal = [t for t in tokens if t['type'] == 'literal'][0]
self.assertEqual(literal['start'], 4)
self.assertEqual(literal['end'], 8)
self.assertGreaterEqual(literal['end'], literal['start'])

def test_adds_quotes_when_invalid_json(self):
tokens = list(self.lexer.tokenize('`{{}`'))
self.assertEqual(
Expand Down