complete JSON grammar

examples/json-schema-to-grammar.py

@@ -9,8 +9,11 @@ SPACE_RULE = '" "?'
 
 PRIMITIVE_RULES = {
     'boolean': '("true" | "false") space',
-    'number': '[0-9]+ space', # TODO complete
+    'number': '("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? space',
-    'string': r'"\"" [ \t!#-\[\]-~]* "\"" space', # TODO complete
+    'string': r''' "\"" (
+        [^"\\] |
+        "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
+      )* "\"" space ''',
     'null': '"null" space',
 }
 

grammars/json.gbnf

@@ -1,29 +1,25 @@
-# Grammar for subset of JSON - doesn't support full string or number syntax
+root   ::= object
-
+value  ::= object | array | string | number | ("true" | "false" | "null") ws
-root  ::= object
-value ::= object | array | string | number | boolean | "null"
 
 object ::=
   "{" ws (
             string ":" ws value
     ("," ws string ":" ws value)*
-  )? "}"
+  )? "}" ws
 
 array  ::=
   "[" ws (
             value
     ("," ws value)*
-  )? "]"
+  )? "]" ws
 
-string  ::=
+string ::=
   "\"" (
     [^"\\] |
     "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]) # escapes
   )* "\"" ws
 
-# Only plain integers currently
+number ::= ("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? ws
-number  ::= "-"? [0-9]+ ws
-boolean ::= ("true" | "false") ws
 
 # Optional space: by convention, applied in this grammar after literal chars when allowed
 ws ::= ([ \t\n] ws)?