dotnet · BillWagner · Sep 27, 2021 · Jul 2, 2021 · Aug 1, 2021 · Aug 1, 2021
diff --git a/standard/enums.md b/standard/enums.md
@@ -26,7 +26,12 @@ enum_declaration
     ;
 
 enum_base
-    : ':' struct_type
+    : ':' integral_type
+    | ':' integral_type_name
+    ;
+
+integral_type_name
+    : type_name // restricted to one of System.{SByte,Byte,Int16,UInt16,Int32,UInt32,Int64,UInt64}
     ;
 
 enum_body
@@ -35,7 +40,7 @@ enum_body
     ;
 ```
 
-Each enum type has a corresponding integral type called the ***underlying type*** of the enum type. This underlying type shall be able to represent all the enumerator values defined in the enumeration. If the *enum_base* is present, it explicitly declares the underlying type. The underlying type shall be one of the *integral types* ([§9.3.6](types.md#936-integral-types)) other than `char`.
+Each enum type has a corresponding integral type called the ***underlying type*** of the enum type. This underlying type shall be able to represent all the enumerator values defined in the enumeration. If the *enum_base* is present, it explicitly declares the underlying type. The underlying type shall be one of the *integral types* ([§9.3.6](types.md#936-integral-types)) other than `char`; specified either by keyword (*integral_type*), or by one of the full type names that the integral types alias ([§9.3.5](types.md#935-simple-types)) (*integral_type_name*).
 
 > *Note*: Neither `char` nor `System.Char` can be used as an underlying type. *end note*
 

diff --git a/standard/expressions.md b/standard/expressions.md
@@ -1130,6 +1130,8 @@ primary_no_array_creation_expression
     ;
 ```
 
+> *Note*: These grammar rules are not ANTLR-ready as they are part of a set of mutually left-recursive rules (`primary_expression`, `primary_no_array_creation_expression`, `member_access`, `invocation_expression`, `element_access`, `post_increment_expression`, `post_decrement_expression`, `pointer_member_access` and `pointer_element_access`) which ANTLR does not handle. Standard techniques can be used to transform the grammar to remove the mutual left-recursion. This has not been done as not all parsing strategies require it (e.g. an LALR parser would not) and doing so would obfuscate the structure and description.
+
 *pointer_member_access* ([§23.6.3](unsafe-code.md#2363-pointer-member-access)) and *pointer_element_access* ([§23.6.4](unsafe-code.md#2364-pointer-element-access)) are only available in unsafe code ([§23](unsafe-code.md#23-unsafe-code)).
 
 Primary expressions are divided between *array_creation_expression*s and *primary_no_array_creation_expression*s. Treating *array_creation_expression* in this way, rather than listing it along with the other simple expression forms, enables the grammar to disallow potentially confusing code such as
@@ -2330,14 +2332,13 @@ nameof_expression
     ;
 
 named_entity
-    : simple_name
-    | named_entity_target '.' identifier type_argument_list?
+    : named_entity_target ('.' identifier type_argument_list?)*
     ;
 
 named_entity_target
-    : 'this'
+    : simple_name
+    | 'this'
     | 'base'
-    | named_entity 
     | predefined_type 
     | qualified_alias_member
     ;

diff --git a/standard/grammar.md b/standard/grammar.md
@@ -508,7 +508,7 @@ namespace_name
 type_name
     : namespace_or_type_name
     ;
-    
+
 namespace_or_type_name
     : identifier type_argument_list?
     | namespace_or_type_name '.' identifier type_argument_list?
@@ -566,14 +566,18 @@ delegate_type
 
 // Source: §9.3.1 General
 value_type
+    : non_nullable_value_type
+    | nullable_value_type
+    ;
+
+non_nullable_value_type
     : struct_type
     | enum_type
     ;
 
 struct_type
     : type_name
     | simple_type
-    | nullable_value_type
     ;
 
 simple_type
@@ -604,18 +608,14 @@ floating_point_type
     | 'double'
     ;
 
-nullable_value_type
-    : non_nullable_value_type '?'
-    ;
-
-non_nullable_value_type
-    : type
-    ;
-
 enum_type
     : type_name
     ;
 
+nullable_value_type
+    : non_nullable_value_type '?'
+    ;
+
 // Source: §9.4.2 Type arguments
 type_argument_list
     : '<' type_arguments '>'
@@ -850,7 +850,6 @@ comma
     : ','
     ;
 
-
 // Source: §12.7.13 The sizeof operator
 sizeof_expression
    : 'sizeof' '(' unmanaged_type ')'
@@ -874,16 +873,15 @@ default_value_expression
 nameof_expression
     : 'nameof' '(' named_entity ')'
     ;
-    
+
 named_entity
-    : simple_name
-    | named_entity_target '.' identifier type_argument_list?
+    : named_entity_target ('.' identifier type_argument_list?)*
     ;
-    
+
 named_entity_target
-    : 'this'
+    : simple_name
+    | 'this'
     | 'base'
-    | named_entity 
     | predefined_type 
     | qualified_alias_member
     ;
@@ -1387,7 +1385,7 @@ catch_clause
 exception_specifier
     : '(' type identifier? ')'
     ;
-    
+
 finally_clause
     : 'finally' block
     ;
@@ -1532,7 +1530,7 @@ type_parameter_constraints_clauses
     : type_parameter_constraints_clause
     | type_parameter_constraints_clauses type_parameter_constraints_clause
     ;
-    
+
 type_parameter_constraints_clause
     : 'where' type_parameter ':' type_parameter_constraints
     ;
@@ -1715,7 +1713,7 @@ property_modifier
     | 'extern'
     | unsafe_modifier   // unsafe code support
     ;
-    
+
 property_body
     : '{' accessor_declarations '}' property_initializer?
     | '=>' expression ';'
@@ -1861,7 +1859,6 @@ operator_body
   | ';'
   ;
 
-
 // Source: §15.11.1 General
 constructor_declaration
   : attributes? constructor_modifier* constructor_declarator constructor_body
@@ -1972,7 +1969,7 @@ array_initializer
 variable_initializer_list
     : variable_initializer (',' variable_initializer)*
     ;
-    
+
 variable_initializer
     : expression
     | array_initializer
@@ -1998,13 +1995,11 @@ variant_type_parameter_list
     : '<' variant_type_parameters '>'
     ;
 
-// Source: §18.2.3.1 General
 variant_type_parameters
     : attributes? variance_annotation? type_parameter
     | variant_type_parameters ',' attributes? variance_annotation? type_parameter
     ;
 
-// Source: §18.2.3.1 General
 variance_annotation
     : 'in'
     | 'out'
@@ -2038,7 +2033,6 @@ interface_property_declaration
     : attributes? 'new'? type identifier '{' interface_accessors '}'
     ;
 
-// Source: §18.4.3 Interface properties
 interface_accessors
     : attributes? 'get' ';'
     | attributes? 'set' ';'
@@ -2062,7 +2056,12 @@ enum_declaration
     ;
 
 enum_base
-    : ':' struct_type
+    : ':' integral_type
+    | ':' integral_type_name
+    ;
+
+integral_type_name
+    : type_name // restricted to one of System.{SByte,Byte,Int16,UInt16,Int32,UInt32,Int64,UInt64}
     ;
 
 enum_body
@@ -2084,7 +2083,6 @@ enum_member_declarations
     : enum_member_declaration (',' enum_member_declaration)*
     ;
 
-// Source: §19.4 Enum members
 enum_member_declaration
     : attributes? identifier ('=' constant_expression)?
     ;
@@ -2093,7 +2091,7 @@ enum_member_declaration
 delegate_declaration
     : attributes? delegate_modifier* 'delegate' return_type identifier variant_type_parameter_list? '(' formal_parameter_list? ')' type_parameter_constraints_clause* ';'
     ;
-    
+
 delegate_modifier
     : 'new'
     | 'public'
@@ -2193,8 +2191,8 @@ unsafe_statement
 
 // Source: §23.3 Pointer types
 pointer_type
-    : unmanaged_type '*'
-    | 'void' '*'
+    : value_type '*'+
+    | 'void' '*'+
     ;
 
 // Source: §23.6.2 Pointer indirection

diff --git a/standard/lexical-structure.md b/standard/lexical-structure.md
@@ -28,7 +28,7 @@ All terminal characters are to be understood as the appropriate Unicode characte
 
 The lexical and syntactic grammars are presented in the ANTLR grammar tool's Extended Backus-Naur form.
 
-While the ANTLR notation is used this Standard does not present a complete ANTLR-ready "reference grammar" for C#; writing a lexer and parser, either by hand or using a tool such as ANTLR, is outside the scope of a language specification. With that qualification, this Standard attempts to minimize the gap between the specified grammar and that required to build a lexer and parser in ANTLR with the notable exception of the preprocessor ([§7.5](lexical-structure.md#75-pre-processing-directives) which requires more substantial work to fit into the ANTLR model.
+While the ANTLR notation is used this Standard does not present a complete ANTLR-ready "reference grammar" for C#; writing a lexer and parser, either by hand or using a tool such as ANTLR, is outside the scope of a language specification. With that qualification, this Standard attempts to minimize the gap between the specified grammar and that required to build a lexer and parser in ANTLR.
 
 ANTLR distinguishes between lexical and syntactic, termed parser by ANTLR, grammars in its notation by starting lexical rules with an initial uppercase letter and parser rules with an initial lowercase letter.
 
@@ -40,8 +40,6 @@ The lexical grammar of C# is presented in [§7.3](lexical-structure.md#73-lexica
 
 Many of the terminal symbols of the syntactic grammar are not defined explicitly as tokens in the lexical grammar. Rather advantage is taken of the ANTLR behavior that literal strings in the grammar are extracted as implicit lexical tokens; this allows keywords, operators, etc. to be represented in the grammar by their literal representation rather than a token name.
 
-The same behavior is also used to simplify the lexical grammar, see [§7.3.1](lexical-structure.md#731-general).
-
 Every compilation unit in a C# program shall conform to the *input* production of the lexical grammar ([§7.3.1](lexical-structure.md#731-general)).
 
 ### 7.2.4 Syntactic grammar
@@ -1071,7 +1069,7 @@ fragment PP_Endif
     ;
 ```
 
-Conditional compilation directives shall be written as groups consisting of, in order, a `#if` directive, zero or more `#elif` directives, zero or one `#else` directive, and a `#endif` directive. Between the directives are ***conditional sections*** of source code. Each section is controlled by the immediately preceding directive. A conditional section may itself contain nested conditional compilation directives provided these directives form complete groups.
+Conditional compilation directives shall be written in groups consisting of, in order, a `#if` directive, zero or more `#elif` directives, zero or one `#else` directive, and a `#endif` directive. Between the directives are ***conditional sections*** of source code. Each section is controlled by the immediately preceding directive. A conditional section may itself contain nested conditional compilation directives provided these directives form complete groups.
 
 > *Example*: The following example illustrates how conditional compilation directives can nest:
 > ```csharp

diff --git a/standard/types.md b/standard/types.md
@@ -139,14 +139,18 @@ A value type is either a struct type or an enumeration type. C# provides a set o
 
 ```ANTLR
 value_type
+    : non_nullable_value_type
+    | nullable_value_type
+    ;
+
+non_nullable_value_type
     : struct_type
     | enum_type
     ;
 
 struct_type
     : type_name
     | simple_type
-    | nullable_value_type
     ;
 
 simple_type
@@ -177,17 +181,13 @@ floating_point_type
     | 'double'
     ;
 
-nullable_value_type
-    : non_nullable_value_type '?'
-    ;
-
-non_nullable_value_type
-    : type
-    ;
-
 enum_type
     : type_name
     ;
+
+nullable_value_type
+    : non_nullable_value_type '?'
+    ;
 ```
 
 Unlike a variable of a reference type, a variable of a value type can contain the value `null` only if the value type is a nullable value type [§9.3.11](types.md#9311-nullable-value-types). For every non-nullable value type there is a corresponding nullable value type denoting the same set of values plus the value `null`.
@@ -612,7 +612,8 @@ Because of this equivalence, the following holds:
 
 ```ANTLR
 unmanaged_type
-    : type
+    : value_type
+    | pointer_type     // unsafe code support
     ;
 ```
 

diff --git a/standard/unsafe-code.md b/standard/unsafe-code.md
@@ -99,8 +99,8 @@ A *pointer_type* is written as an *unmanaged_type* ([§9.8](types.md#98-unmanage
 
 ```ANTLR
 pointer_type
-    : unmanaged_type '*'
-    | 'void' '*'
+    : value_type ('*')+
+    | 'void' ('*')+
     ;
 ```