Language.C.Types.Parse

A parser for C99 declarations. Currently, the parser has the following limitations:

• Array sizes can only be *, n (where n is a positive integer), x (where x is a C identifier). In C99 they can be arbitrary expressions. See the ArrayType data type.
• _Bool, _Complex, and _Imaginary are not present.
• Untyped parameter lists (pre-K&R C) are not allowed.

The parser is incremental and generic (see CParser). Pretty and Arbitrary instances are provided for all the data types.

The entry point if you want to parse C declarations is parameter_declaration.

Parser configuration

type TypeNames = HashSet CIdentifier

A collection of named types (typedefs)

data CParserContext i

Constructors

CParserContext

Fields

cpcIdentName :: String

cpcTypeNames :: TypeNames

Function used to determine whether an identifier is a type name.

cpcParseIdent :: forall m. CParser i m => m i

Parses an identifier, *without consuming whitespace afterwards*.

cpcIdentToString :: i -> String

Default configuration

data CIdentifier

A type for C identifiers.

Instances

Eq CIdentifier

Ord CIdentifier

Show CIdentifier

IsString CIdentifier

Arbitrary CIdentifier

Pretty CIdentifier

Hashable CIdentifier

Typeable * CIdentifier

unCIdentifier :: CIdentifier -> String

cIdentifierFromString :: String -> Either String CIdentifier

cCParserContext :: TypeNames -> CParserContext CIdentifier

Parser type

type CParser i m = (Monad m, Functor m, Applicative m, MonadPlus m, Parsing m, CharParsing m, TokenParsing m, LookAheadParsing m, MonadReader (CParserContext i) m, Hashable i)

All the parsing is done using the type classes provided by the parsers package. You can use the parsing routines with any of the parsers that implement the classes, such as parsec or trifecta.

We parametrize the parsing by the type of the variable identifiers, i. We do so because we use this parser to implement anti-quoters referring to Haskell variables, and thus we need to parse Haskell identifiers in certain positions.

runCParser

Arguments

:: Stream s Identity Char

=> CParserContext i

-> String

Source name.

-> s

String to parse.

-> ReaderT (CParserContext i) (Parsec s ()) a

Parser. Anything with type forall m. CParser i m => m a is a valid argument.

-> Either ParseError a

Runs a CParser using parsec.

quickCParser

Arguments

:: CParserContext i

-> String

String to parse.

-> ReaderT (CParserContext i) (Parsec String ()) a

Parser. Anything with type forall m. CParser i m => m a is a valid argument.

-> a

Useful for quick testing. Uses "quickCParser" as source name, and throws an error if parsing fails.

quickCParser_

Arguments

:: String

String to parse.

-> ReaderT (CParserContext CIdentifier) (Parsec String ()) a

Parser. Anything with type forall m. CParser i m => m a is a valid argument.

-> a

Like quickCParser, but uses cCParserContext (const False) as CParserContext.

Types and parsing

identifier_no_lex :: CParser i m => m i

data DeclarationSpecifier

Constructors

StorageClassSpecifier StorageClassSpecifier

TypeSpecifier TypeSpecifier

TypeQualifier TypeQualifier

FunctionSpecifier FunctionSpecifier

Instances

Eq DeclarationSpecifier

Show DeclarationSpecifier

Pretty DeclarationSpecifier

Typeable * DeclarationSpecifier

declaration_specifiers :: CParser i m => m [DeclarationSpecifier]

data StorageClassSpecifier

Constructors

TYPEDEF

EXTERN

STATIC

AUTO

REGISTER

Instances

Eq StorageClassSpecifier

Show StorageClassSpecifier

Arbitrary StorageClassSpecifier

Pretty StorageClassSpecifier

Typeable * StorageClassSpecifier

storage_class_specifier :: CParser i m => m StorageClassSpecifier

data TypeSpecifier

Constructors

VOID

CHAR

SHORT

INT

LONG

FLOAT

DOUBLE

SIGNED

UNSIGNED

Struct CIdentifier

Enum CIdentifier

TypeName CIdentifier

Instances

Eq TypeSpecifier

Show TypeSpecifier

Pretty TypeSpecifier

Typeable * TypeSpecifier

type_specifier :: CParser i m => m TypeSpecifier

data TypeQualifier

Constructors

CONST

RESTRICT

VOLATILE

Instances

Eq TypeQualifier

Show TypeQualifier

Arbitrary TypeQualifier

Pretty TypeQualifier

Typeable * TypeQualifier

type_qualifier :: CParser i m => m TypeQualifier

data FunctionSpecifier

Constructors

INLINE

Instances

Eq FunctionSpecifier

Show FunctionSpecifier

Arbitrary FunctionSpecifier

Pretty FunctionSpecifier

Typeable * FunctionSpecifier

function_specifier :: CParser i m => m FunctionSpecifier

data Declarator i

Constructors

Declarator

Fields

declaratorPointers :: [Pointer]

declaratorDirect :: DirectDeclarator i

Instances

Functor Declarator

Foldable Declarator

Traversable Declarator

Eq i => Eq (Declarator i)

Show i => Show (Declarator i)

Pretty i => Pretty (Declarator i)

Typeable (* -> *) Declarator

declarator :: CParser i m => m (Declarator i)

data DirectDeclarator i

Constructors

DeclaratorRoot i

ArrayOrProto (DirectDeclarator i) (ArrayOrProto i)

DeclaratorParens (Declarator i)

Instances

Functor DirectDeclarator

Foldable DirectDeclarator

Traversable DirectDeclarator

Eq i => Eq (DirectDeclarator i)

Show i => Show (DirectDeclarator i)

Pretty i => Pretty (DirectDeclarator i)

Typeable (* -> *) DirectDeclarator

direct_declarator :: CParser i m => m (DirectDeclarator i)

data ArrayOrProto i

Constructors

Array (ArrayType i)

Proto [ParameterDeclaration i]

Instances

Functor ArrayOrProto

Foldable ArrayOrProto

Traversable ArrayOrProto

Eq i => Eq (ArrayOrProto i)

Show i => Show (ArrayOrProto i)

Pretty i => Pretty (ArrayOrProto i)

Typeable (* -> *) ArrayOrProto

array_or_proto :: CParser i m => m (ArrayOrProto i)

data ArrayType i

Constructors

VariablySized

Unsized

SizedByInteger Integer

SizedByIdentifier i

Instances

Functor ArrayType

Foldable ArrayType

Traversable ArrayType

Eq i => Eq (ArrayType i)

Show i => Show (ArrayType i)

Pretty i => Pretty (ArrayType i)

Typeable (* -> *) ArrayType

array_type :: CParser i m => m (ArrayType i)

data Pointer

Constructors

Pointer [TypeQualifier]

Instances

Eq Pointer

Show Pointer

Arbitrary Pointer

Pretty Pointer

Typeable * Pointer

pointer :: CParser i m => m Pointer

data ParameterDeclaration i

Constructors

ParameterDeclaration

Fields

parameterDeclarationSpecifiers :: [DeclarationSpecifier]

parameterDeclarationDeclarator :: DeclaratorOrAbstractDeclarator i

Instances

Functor ParameterDeclaration

Foldable ParameterDeclaration

Traversable ParameterDeclaration

Eq i => Eq (ParameterDeclaration i)

Show i => Show (ParameterDeclaration i)

Pretty i => Pretty (ParameterDeclaration i)

Typeable (* -> *) ParameterDeclaration

data DeclaratorOrAbstractDeclarator i

Constructors

IsDeclarator (Declarator i)

IsAbstractDeclarator (AbstractDeclarator i)

Instances

Functor DeclaratorOrAbstractDeclarator

Foldable DeclaratorOrAbstractDeclarator

Traversable DeclaratorOrAbstractDeclarator

Eq i => Eq (DeclaratorOrAbstractDeclarator i)

Show i => Show (DeclaratorOrAbstractDeclarator i)

Typeable (* -> *) DeclaratorOrAbstractDeclarator

parameter_declaration :: CParser i m => m (ParameterDeclaration i)

parameter_list :: CParser i m => m [ParameterDeclaration i]

data AbstractDeclarator i

Constructors

AbstractDeclarator

Fields

abstractDeclaratorPointers :: [Pointer]

abstractDeclaratorDirect :: Maybe (DirectAbstractDeclarator i)

Instances

Functor AbstractDeclarator

Foldable AbstractDeclarator

Traversable AbstractDeclarator

Eq i => Eq (AbstractDeclarator i)

Show i => Show (AbstractDeclarator i)

Pretty i => Pretty (AbstractDeclarator i)

Typeable (* -> *) AbstractDeclarator

abstract_declarator :: CParser i m => m (AbstractDeclarator i)

data DirectAbstractDeclarator i

Constructors

ArrayOrProtoHere (ArrayOrProto i)

ArrayOrProtoThere (DirectAbstractDeclarator i) (ArrayOrProto i)

AbstractDeclaratorParens (AbstractDeclarator i)

Instances

Functor DirectAbstractDeclarator

Foldable DirectAbstractDeclarator

Traversable DirectAbstractDeclarator

Eq i => Eq (DirectAbstractDeclarator i)

Show i => Show (DirectAbstractDeclarator i)

Pretty i => Pretty (DirectAbstractDeclarator i)

Typeable (* -> *) DirectAbstractDeclarator

direct_abstract_declarator :: CParser i m => m (DirectAbstractDeclarator i)

YACC grammar

The parser above is derived from a modification of the YACC grammar for C99 found at http://www.quut.com/c/ANSI-C-grammar-y-1999.html, reproduced below.

%token IDENTIFIER TYPE_NAME INTEGER

%token TYPEDEF EXTERN STATIC AUTO REGISTER INLINE RESTRICT
%token CHAR SHORT INT LONG SIGNED UNSIGNED FLOAT DOUBLE CONST VOLATILE VOID
%token BOOL COMPLEX IMAGINARY
%token STRUCT UNION ENUM

%start parameter_list
%%

declaration_specifiers
	: storage_class_specifier
	| storage_class_specifier declaration_specifiers
	| type_specifier
	| type_specifier declaration_specifiers
	| type_qualifier
	| type_qualifier declaration_specifiers
	| function_specifier
	| function_specifier declaration_specifiers
	;

storage_class_specifier
	: TYPEDEF
	| EXTERN
	| STATIC
	| AUTO
	| REGISTER
	;

type_specifier
	: VOID
	| CHAR
	| SHORT
	| INT
	| LONG
	| FLOAT
	| DOUBLE
	| SIGNED
	| UNSIGNED
	| BOOL
	| COMPLEX
	| IMAGINARY
 	| STRUCT IDENTIFIER
	| UNION IDENTIFIER
	| ENUM IDENTIFIER
	| TYPE_NAME
	;

type_qualifier
	: CONST
	| RESTRICT
	| VOLATILE
	;

function_specifier
	: INLINE
	;

declarator
	: pointer direct_declarator
	| direct_declarator
	;

direct_declarator
	: IDENTIFIER
	| '(' declarator ')'
	| direct_declarator '[' type_qualifier_list ']'
	| direct_declarator '[' type_qualifier_list * ']'
	| direct_declarator '[' * ']'
 	| direct_declarator '[' IDENTIFIER ']'
	| direct_declarator '[' INTEGER ']'
	| direct_declarator '[' ']'
	| direct_declarator '(' parameter_list ')'
	| direct_declarator '(' ')'
	;

pointer
	: *
	| * type_qualifier_list
	| * pointer
	| * type_qualifier_list pointer
	;

type_qualifier_list
	: type_qualifier
	| type_qualifier_list type_qualifier
	;

parameter_list
	: parameter_declaration
	| parameter_list ',' parameter_declaration
	;

parameter_declaration
	: declaration_specifiers declarator
	| declaration_specifiers abstract_declarator
	| declaration_specifiers
	;

abstract_declarator
	: pointer
	| direct_abstract_declarator
	| pointer direct_abstract_declarator
	;

direct_abstract_declarator
	: '(' abstract_declarator ')'
	| '[' ']'
	| direct_abstract_declarator '[' ']'
	| '[' * ']'
	| direct_abstract_declarator '[' * ']'
	| '[' IDENTIFIER ']'
	| direct_abstract_declarator '[' IDENTIFIER ']'
	| '[' INTEGER ']'
	| direct_abstract_declarator '[' INTEGER ']'
	| '(' ')'
	| '(' parameter_list ')'
	| direct_abstract_declarator '(' ')'
	| direct_abstract_declarator '(' parameter_list ')'
	;

%%
#include <stdio.h>

extern char yytext[];
extern int column;

void yyerror(char const *s)
{
	fflush(stdout);
	printf("n%*sn%*sn", column, "^", column, s);
}

Testing utilities

cIdentStart :: [Char]

cIdentLetter :: [Char]

cReservedWords :: HashSet String

data ParameterDeclarationWithTypeNames i

Type used to generate an Arbitrary ParameterDeclaration with arbitrary allowed type names.

Constructors

ParameterDeclarationWithTypeNames

Fields

pdwtnTypeNames :: HashSet CIdentifier

pdwtnParameterDeclaration :: ParameterDeclaration i

Instances

Eq i => Eq (ParameterDeclarationWithTypeNames i)

Show i => Show (ParameterDeclarationWithTypeNames i)

Typeable (* -> *) ParameterDeclarationWithTypeNames

arbitraryParameterDeclarationWithTypeNames :: (Arbitrary i, Hashable i) => (i -> String) -> Gen (ParameterDeclarationWithTypeNames i)