vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum (#7797)

Browse source 
* json: support minimum for positive integer values

* json: fix min 0

* json: min + max integer constraints

* json: handle negative min / max integer bounds

* json: fix missing paren min/max bug

* json: proper paren fix

* json: integration test for schemas

* json: fix bounds tests

* Update json-schema-to-grammar.cpp

* json: fix negative max

* json: fix negative min (w/ more than 1 digit)

* Update test-grammar-integration.cpp

* json: nit: move string rules together

* json: port min/max integer support to Python & JS

* nit: move + rename _build_min_max_int

* fix min in [1, 9]

* Update test-grammar-integration.cpp

* add C++11-compatible replacement for std::string_view

* add min/max constrained int field to pydantic json schema example

* fix merge

* json: add integration tests for min/max bounds

* reshuffle/merge min/max integ test cases

* nits / cleanups

* defensive code against string out of bounds (apparently different behaviour of libstdc++ vs. clang's libc++, can't read final NULL char w/ former)
This commit is contained in:
Olivier Chafik 2024-06-25 20:06:20 +01:00 • committed by GitHub
parent dd047b476c
commit 84631fe150
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 1150 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

264
tests/test-json-schema-to-grammar.cpp
View file

@ -80,6 +80,232 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
runner(tc);
};
test({
SUCCESS,
"min 0",
R"""({
"type": "integer",
"minimum": 0
})""",
R"""(
root ::= ([0] | [1-9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 1",
R"""({
"type": "integer",
"minimum": 1
})""",
R"""(
root ::= ([1-9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 3",
R"""({
"type": "integer",
"minimum": 3
})""",
R"""(
root ::= ([1-2] [0-9]{1,15} | [3-9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 9",
R"""({
"type": "integer",
"minimum": 9
})""",
R"""(
root ::= ([1-8] [0-9]{1,15} | [9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 10",
R"""({
"type": "integer",
"minimum": 10
})""",
R"""(
root ::= ([1] ([0-9]{1,15}) | [2-9] [0-9]{1,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 25",
R"""({
"type": "integer",
"minimum": 25
})""",
R"""(
root ::= ([1] [0-9]{2,15} | [2] ([0-4] [0-9]{1,14} | [5-9] [0-9]{0,14}) | [3-9] [0-9]{1,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"max 30",
R"""({
"type": "integer",
"maximum": 30
})""",
R"""(
root ::= ("-" [1-9] [0-9]{0,15} | [0-9] | ([1-2] [0-9] | [3] "0")) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min -5",
R"""({
"type": "integer",
"minimum": -5
})""",
R"""(
root ::= ("-" ([0-5]) | [0] | [1-9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min -123",
R"""({
"type": "integer",
"minimum": -123
})""",
R"""(
root ::= ("-" ([0-9] | ([1-8] [0-9] | [9] [0-9]) | "1" ([0-1] [0-9] | [2] [0-3])) | [0] | [1-9] [0-9]{0,15}) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"max -5",
R"""({
"type": "integer",
"maximum": -5
})""",
R"""(
root ::= ("-" ([0-4] [0-9]{1,15} | [5-9] [0-9]{0,15})) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"max 1",
R"""({
"type": "integer",
"maximum": 1
})""",
R"""(
root ::= ("-" [1-9] [0-9]{0,15} | [0-1]) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"max 100",
R"""({
"type": "integer",
"maximum": 100
})""",
R"""(
root ::= ("-" [1-9] [0-9]{0,15} | [0-9] | ([1-8] [0-9] | [9] [0-9]) | "100") space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 0 max 23",
R"""({
"type": "integer",
"minimum": 0,
"maximum": 23
})""",
R"""(
root ::= ([0-9] | ([1] [0-9] | [2] [0-3])) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 15 max 300",
R"""({
"type": "integer",
"minimum": 15,
"maximum": 300
})""",
R"""(
root ::= (([1] ([5-9]) | [2-9] [0-9]) | ([1-2] [0-9]{2} | [3] "00")) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min 5 max 30",
R"""({
"type": "integer",
"minimum": 5,
"maximum": 30
})""",
R"""(
root ::= ([5-9] | ([1-2] [0-9] | [3] "0")) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min -123 max 42",
R"""({
"type": "integer",
"minimum": -123,
"maximum": 42
})""",
R"""(
root ::= ("-" ([0-9] | ([1-8] [0-9] | [9] [0-9]) | "1" ([0-1] [0-9] | [2] [0-3])) | [0-9] | ([1-3] [0-9] | [4] [0-2])) space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min -10 max 10",
R"""({
"type": "integer",
"minimum": -10,
"maximum": 10
})""",
R"""(
root ::= ("-" ([0-9] | "10") | [0-9] | "10") space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
FAILURE,
"unknown type",
@ -390,6 +616,44 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
)"""
});
test({
SUCCESS,
"min + max items with min + max values across zero",
R"""({
"items": {
"type": "integer",
"minimum": -12,
"maximum": 207
},
"minItems": 3,
"maxItems": 5
})""",
R"""(
item ::= ("-" ([0-9] | "1" [0-2]) | [0-9] | ([1-8] [0-9] | [9] [0-9]) | ([1] [0-9]{2} | [2] "0" [0-7])) space
root ::= "[" space item ("," space item){2,4} "]" space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"min + max items with min + max values",
R"""({
"items": {
"type": "integer",
"minimum": 12,
"maximum": 207
},
"minItems": 3,
"maxItems": 5
})""",
R"""(
item ::= (([1] ([2-9]) | [2-9] [0-9]) | ([1] [0-9]{2} | [2] "0" [0-7])) space
root ::= "[" space item ("," space item){2,4} "]" space
space ::= | " " | "\n" [ \t]{0,20}
)"""
});
test({
SUCCESS,
"simple regexp",