Skip to content
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

Jump to bottom

Ensure regex matches valid JSON for "const" and "enum" with booleans, nulls, and strings #972

Merged
merged 1 commit into from
Jun 18, 2024
Merged

Ensure regex matches valid JSON for "const" and "enum" with booleans, nulls, and strings #972

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
17 changes: 8 additions & 9 deletions outlines/fsm/json_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,19 +269,18 @@ def to_regex(
elif "enum" in instance:
choices = []
for choice in instance["enum"]:
if type(choice) in [int, float, bool, None]:
choices.append(re.escape(str(choice)))
elif type(choice) == str:
choices.append(f'"{re.escape(choice)}"')

if type(choice) in [int, float, bool, type(None), str]:
choices.append(re.escape(json.dumps(choice)))
mwootten marked this conversation as resolved.
Show resolved Hide resolved
else:
raise TypeError(f"Unsupported data type in enum: {type(choice)}")
return f"({'|'.join(choices)})"

elif "const" in instance:
const = instance["const"]
if type(const) in [int, float, bool, None]:
const = re.escape(str(const))
elif type(const) == str:
const = f'"{re.escape(const)}"'
if type(const) in [int, float, bool, type(None), str]:
const = re.escape(json.dumps(const))
mwootten marked this conversation as resolved.
Show resolved Hide resolved
else:
raise TypeError(f"Unsupported data type in const: {type(const)}")
return const

elif "$ref" in instance:
Expand Down
47 changes: 43 additions & 4 deletions tests/fsm/test_json_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,36 +177,75 @@ def test_match_number(pattern, does_match):
'"Marc"',
[('"Marc"', True), ('"Jean"', False), ('"John"', False)],
),
# Make sure strings are escaped
# Make sure strings are escaped with regex escaping
(
{"title": "Foo", "const": ".*", "type": "string"},
r'"\.\*"',
[('".*"', True), (r'"\s*"', False), (r'"\.\*"', False)],
),
# Make sure strings are escaped with JSON escaping
(
{"title": "Foo", "const": '"', "type": "string"},
r'"\\""',
[('"\\""', True), ('"""', False)],
),
# Const integer
(
{"title": "Foo", "const": 0, "type": "integer"},
"0",
[("0", True), ("1", False), ("a", False)],
),
# Const float
(
{"title": "Foo", "const": 0.2, "type": "float"},
r"0\.2",
[("0.2", True), ("032", False)],
),
# Const boolean
(
{"title": "Foo", "const": True, "type": "boolean"},
"true",
[("true", True), ("True", False)],
),
# Const null
(
{"title": "Foo", "const": None, "type": "null"},
"null",
[("null", True), ("None", False), ("", False)],
),
# Enum string
(
{"title": "Foo", "enum": ["Marc", "Jean"], "type": "string"},
'("Marc"|"Jean")',
[('"Marc"', True), ('"Jean"', True), ('"John"', False)],
),
# Make sure strings are escaped
# Make sure strings are escaped with regex and JSON escaping
(
{"title": "Foo", "enum": [".*", r"\s*"], "type": "string"},
r'("\.\*"|"\\s\*")',
[('".*"', True), (r'"\s*"', True), (r'"\.\*"', False)],
r'("\.\*"|"\\\\s\*")',
[('".*"', True), (r'"\\s*"', True), (r'"\.\*"', False)],
),
# Enum integer
(
{"title": "Foo", "enum": [0, 1], "type": "integer"},
"(0|1)",
[("0", True), ("1", True), ("a", False)],
),
# Enum mix of types
(
{"title": "Foo", "enum": [6, 5.3, "potato", True, None]},
r'(6|5\.3|"potato"|true|null)',
[
("6", True),
("5.3", True),
('"potato"', True),
("true", True),
("null", True),
("523", False),
("True", False),
("None", False),
],
),
# integer
(
{
Expand Down