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

Fix bug in the treatment of the anyOf keywork in JSON schema #552

Merged
merged 1 commit into from
Jan 18, 2024
Merged

Fix bug in the treatment of the anyOf keywork in JSON schema #552

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
10 changes: 1 addition & 9 deletions outlines/fsm/json_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
import inspect
import itertools as it
import json
import re
from typing import Callable, Union
Expand Down Expand Up @@ -80,7 +79,6 @@ def to_regex(resolver: Resolver, instance: dict):
Note
----
Many features of JSON schema are missing:
- Support the fact that fields in an object are optional by default
- Handle `additionalProperties` keyword
- Handle types defined as a list
- Handle constraints on numbers
Expand Down Expand Up @@ -153,13 +151,7 @@ def to_regex(resolver: Resolver, instance: dict):
# any (one or more) of the given subschemas.
elif "anyOf" in instance:
subregexes = [to_regex(resolver, t) for t in instance["anyOf"]]
combinations = [
"(" + "".join(c) + ")"
for r in range(1, len(subregexes) + 1)
for c in it.permutations(subregexes, r)
]

return rf"({'|'.join(combinations)})"
return rf"({'|'.join(subregexes)})"

# To validate against oneOf, the given data must be valid against exactly
# one of the given subschemas.
Expand Down
12 changes: 6 additions & 6 deletions tests/fsm/test_json_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,8 +241,8 @@ def test_match_number(pattern, does_match):
"title": "Foo",
"anyOf": [{"type": "string"}, {"type": "integer"}],
},
r'(("(?:[^"\\\x00-\x1f\x7f-\x9f]|\\.)*")|((0|[1-9][0-9]*))|("(?:[^"\\\x00-\x1f\x7f-\x9f]|\\.)*"(0|[1-9][0-9]*))|((0|[1-9][0-9]*)"(?:[^"\\\x00-\x1f\x7f-\x9f]|\\.)*"))',
[("12", True), ('"a"', True), ('1"a"', True)],
rf"({STRING}|{INTEGER})",
[("12", True), ('"a"', True), ('1"a"', False)],
),
# allOf
(
Expand Down Expand Up @@ -361,7 +361,7 @@ def test_match_number(pattern, does_match):
"title": "Character",
"type": "object",
},
f'\\{{[\\n ]*"name"[\\n ]*:[\\n ]*{STRING}([\\n ]*,[\\n ]*"age"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?([\\n ]*,[\\n ]*"weapon"[\\n ]*:[\\n ]*(({STRING})|(null)|({STRING}null)|(null{STRING})))?[\\n ]*\\}}',
f'\\{{[\\n ]*"name"[\\n ]*:[\\n ]*{STRING}([\\n ]*,[\\n ]*"age"[\\n ]*:[\\n ]*({INTEGER}|null))?([\\n ]*,[\\n ]*"weapon"[\\n ]*:[\\n ]*({STRING}|null))?[\\n ]*\\}}',
[
('{ "name" : "Player" }', True),
('{ "name" : "Player", "weapon" : "sword" }', True),
Expand All @@ -381,7 +381,7 @@ def test_match_number(pattern, does_match):
"title": "Character",
"type": "object",
},
f'\\{{[\\n ]*"name"[\\n ]*:[\\n ]*{STRING}[\\n ]*,([\\n ]*"age"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER}))[\\n ]*,)?[\\n ]*"weapon"[\\n ]*:[\\n ]*{STRING}([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?[\\n ]*\\}}',
f'\\{{[\\n ]*"name"[\\n ]*:[\\n ]*{STRING}[\\n ]*,([\\n ]*"age"[\\n ]*:[\\n ]*({INTEGER}|null)[\\n ]*,)?[\\n ]*"weapon"[\\n ]*:[\\n ]*{STRING}([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*({INTEGER}|null))?[\\n ]*\\}}',
[
('{ "name" : "Player" , "weapon" : "sword" }', True),
(
Expand All @@ -405,7 +405,7 @@ def test_match_number(pattern, does_match):
"title": "Character",
"type": "object",
},
f'\\{{([\\n ]*"name"[\\n ]*:[\\n ]*(({STRING})|(null)|({STRING}null)|(null{STRING}))[\\n ]*,)?[\\n ]*"age"[\\n ]*:[\\n ]*{INTEGER}[\\n ]*,[\\n ]*"armor"[\\n ]*:[\\n ]*{STRING}[\\n ]*,([\\n ]*"strength"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER}))[\\n ]*,)?[\\n ]*"weapon"[\\n ]*:[\\n ]*{STRING}[\\n ]*\\}}',
f'\\{{([\\n ]*"name"[\\n ]*:[\\n ]*({STRING}|null)[\\n ]*,)?[\\n ]*"age"[\\n ]*:[\\n ]*{INTEGER}[\\n ]*,[\\n ]*"armor"[\\n ]*:[\\n ]*{STRING}[\\n ]*,([\\n ]*"strength"[\\n ]*:[\\n ]*({INTEGER}|null)[\\n ]*,)?[\\n ]*"weapon"[\\n ]*:[\\n ]*{STRING}[\\n ]*\\}}',
[
(
'{ "name" : "Player", "age" : 10, "armor" : "plate", "strength" : 11, "weapon" : "sword" }',
Expand All @@ -429,7 +429,7 @@ def test_match_number(pattern, does_match):
"title": "Character",
"type": "object",
},
f'\\{{([\\n ]*"name"[\\n ]*:[\\n ]*(({STRING})|(null)|({STRING}null)|(null{STRING}))([\\n ]*,[\\n ]*"age"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?|([\\n ]*"name"[\\n ]*:[\\n ]*(({STRING})|(null)|({STRING}null)|(null{STRING}))[\\n ]*,)?[\\n ]*"age"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER}))([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?|([\\n ]*"name"[\\n ]*:[\\n ]*(({STRING})|(null)|({STRING}null)|(null{STRING}))[\\n ]*,)?([\\n ]*"age"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER}))[\\n ]*,)?[\\n ]*"strength"[\\n ]*:[\\n ]*(({INTEGER})|(null)|({INTEGER}null)|(null{INTEGER})))?[\\n ]*\\}}',
f'\\{{([\\n ]*"name"[\\n ]*:[\\n ]*({STRING}|null)([\\n ]*,[\\n ]*"age"[\\n ]*:[\\n ]*({INTEGER}|null))?([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*({INTEGER}|null))?|([\\n ]*"name"[\\n ]*:[\\n ]*({STRING}|null)[\\n ]*,)?[\\n ]*"age"[\\n ]*:[\\n ]*({INTEGER}|null)([\\n ]*,[\\n ]*"strength"[\\n ]*:[\\n ]*({INTEGER}|null))?|([\\n ]*"name"[\\n ]*:[\\n ]*({STRING}|null)[\\n ]*,)?([\\n ]*"age"[\\n ]*:[\\n ]*({INTEGER}|null)[\\n ]*,)?[\\n ]*"strength"[\\n ]*:[\\n ]*({INTEGER}|null))?[\\n ]*\\}}',
[
('{ "name" : "Player" }', True),
('{ "name" : "Player", "age" : 10, "strength" : 10 }', True),
Expand Down