From 218f41fa439a4bace43d035a21ae6a1070f2ec5e Mon Sep 17 00:00:00 2001
From: Olivier Chafik <ochafik@google.com>
Date: Wed, 24 Apr 2024 23:54:35 +0100
Subject: [PATCH] json: update numeric rule to be unambiguous

---
 common/json-schema-to-grammar.cpp             |  2 +-
 examples/json_schema_to_grammar.py            |  2 +-
 examples/pydantic_models_to_grammar.py        |  2 +-
 .../server/public/json-schema-to-grammar.mjs  |  2 +-
 tests/test-json-schema-to-grammar.cpp         | 28 +++++++++----------
 5 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/common/json-schema-to-grammar.cpp b/common/json-schema-to-grammar.cpp
index 5ba141edd..93d2e9ea2 100644
--- a/common/json-schema-to-grammar.cpp
+++ b/common/json-schema-to-grammar.cpp
@@ -50,7 +50,7 @@ struct BuiltinRule {
 std::unordered_map<std::string, BuiltinRule> PRIMITIVE_RULES = {
     {"boolean", {"(\"true\" | \"false\") space", {}}},
     {"decimal-part", {"[0-9]{1,16}", {}}},
-    {"integral-part", {"[0-9] | [1-9] [0-9]{1,15}", {}}},
+    {"integral-part", {"[0] | [1-9] [0-9]{1,15}", {}}},
     {"number", {"(\"-\"? integral-part) (\".\" decimal-part)? ([eE] [-+]? integral-part)? space", {"integral-part", "decimal-part"}}},
     {"integer", {"(\"-\"? integral-part) space", {"integral-part"}}},
     {"value", {"object | array | string | number | boolean | null", {"object", "array", "string", "number", "boolean", "null"}}},
diff --git a/examples/json_schema_to_grammar.py b/examples/json_schema_to_grammar.py
index c8742efd6..31b3e3a24 100755
--- a/examples/json_schema_to_grammar.py
+++ b/examples/json_schema_to_grammar.py
@@ -36,7 +36,7 @@ SPACE_RULE = '" "?'
 PRIMITIVE_RULES = {
     'boolean'      : BuiltinRule('("true" | "false") space', []),
     'decimal-part' : BuiltinRule('[0-9]{1,16}', []),
-    'integral-part': BuiltinRule('[0-9] | [1-9] [0-9]{1,15}', []),
+    'integral-part': BuiltinRule('[0] | [1-9] [0-9]{1,15}', []),
     'number'       : BuiltinRule('("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space', ['integral-part', 'decimal-part']),
     'integer'      : BuiltinRule('("-"? integral-part) space', ['integral-part']),
     'value'        : BuiltinRule('object | array | string | number | boolean | null', ['object', 'array', 'string', 'number', 'boolean', 'null']),
diff --git a/examples/pydantic_models_to_grammar.py b/examples/pydantic_models_to_grammar.py
index 9acc7cc6d..f029c73a2 100644
--- a/examples/pydantic_models_to_grammar.py
+++ b/examples/pydantic_models_to_grammar.py
@@ -624,7 +624,7 @@ string ::= "\"" (
         "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
       )* "\"" ws
 ws ::= ([ \t\n] ws)?
-float ::= ("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? ws
+float ::= ("-"? ([0] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? ws
 
 integer ::= [0-9]+"""
 
diff --git a/examples/server/public/json-schema-to-grammar.mjs b/examples/server/public/json-schema-to-grammar.mjs
index aceb39a8e..758b4c3d6 100644
--- a/examples/server/public/json-schema-to-grammar.mjs
+++ b/examples/server/public/json-schema-to-grammar.mjs
@@ -34,7 +34,7 @@ class BuiltinRule {
 const PRIMITIVE_RULES = {
   boolean        : new BuiltinRule('("true" | "false") space', []),
   'decimal-part' : new BuiltinRule('[0-9]{1,16}', []),
-  'integral-part': new BuiltinRule('[0-9] | [1-9] [0-9]{1,15}', []),
+  'integral-part': new BuiltinRule('[0] | [1-9] [0-9]{1,15}', []),
   number         : new BuiltinRule('("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space', ['integral-part', 'decimal-part']),
   integer        : new BuiltinRule('("-"? integral-part) space', ['integral-part']),
   value          : new BuiltinRule('object | array | string | number | boolean | null', ['object', 'array', 'string', 'number', 'boolean', 'null']),
diff --git a/tests/test-json-schema-to-grammar.cpp b/tests/test-json-schema-to-grammar.cpp
index de593a9fc..c69cd313b 100755
--- a/tests/test-json-schema-to-grammar.cpp
+++ b/tests/test-json-schema-to-grammar.cpp
@@ -106,7 +106,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             boolean ::= ("true" | "false") space
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             null ::= "null" space
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@@ -233,7 +233,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             "type": "integer"
         })""",
         R"""(
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             root ::= ("-"? integral-part) space
             space ::= " "?
         )"""
@@ -298,7 +298,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
         R"""(
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "[" space string "," space number "]" space
             space ::= " "?
@@ -314,7 +314,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
         })""",
         R"""(
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             root ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             space ::= " "?
         )"""
@@ -381,7 +381,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
         R"""(
             decimal-part ::= [0-9]{1,16}
             integer ::= ("-"? integral-part) space
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             item ::= number | integer
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "[" space item ("," space item){2,4} "]" space
@@ -555,7 +555,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             additional-value ::= "[" space (number ("," space number)*)? "]" space
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "{" space  (additional-kvs )? "}" space
             space ::= " "?
@@ -575,7 +575,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             boolean ::= ("true" | "false") space
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             null ::= "null" space
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@@ -597,7 +597,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             boolean ::= ("true" | "false") space
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             null ::= "null" space
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@@ -638,7 +638,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             additional-kvs ::= additional-kv ( "," space additional-kv )*
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "{" space a-kv ( "," space ( additional-kvs ) )? "}" space
             space ::= " "?
@@ -663,7 +663,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             additional-kvs ::= additional-kv ( "," space additional-kv )*
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "{" space  (a-kv a-rest | additional-kvs )? "}" space
             space ::= " "?
@@ -691,7 +691,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             b-rest ::= additional-kvs
             char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "{" space a-kv ( "," space ( b-kv b-rest | additional-kvs ) )? "}" space
             space ::= " "?
@@ -755,7 +755,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             decimal-part ::= [0-9]{1,16}
             foo ::= "{" space  (foo-a-kv )? "}" space
             foo-a-kv ::= "\"a\"" space ":" space number
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= alternative-0 | alternative-1
             space ::= " "?
@@ -799,7 +799,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
             d-kv ::= "\"d\"" space ":" space number
             d-rest ::= ( "," space c-kv )?
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             root ::= "{" space a-kv "," space b-kv ( "," space ( d-kv d-rest | c-kv ) )? "}" space
             space ::= " "?
@@ -842,7 +842,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
         })""",
         R"""(
             decimal-part ::= [0-9]{1,16}
-            integral-part ::= [0-9] | [1-9] [0-9]{1,15}
+            integral-part ::= [0] | [1-9] [0-9]{1,15}
             number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
             number- ::= "{" space number-number-kv "}" space
             number-kv ::= "\"number\"" space ":" space number-