mirror of
https://github.com/KevinMidboe/linguist.git
synced 2025-10-29 09:40:21 +00:00
Add Jison (#3488)
This commit is contained in:
Nate Whetsell
committed by
Brandon Black
Brandon Black
parent
9ca6a5841e
commit
733ef63193
418
samples/Jison/ansic.jison
Normal file
418
samples/Jison/ansic.jison
Normal file
@@ -0,0 +1,418 @@
|
||||
%token IDENTIFIER CONSTANT STRING_LITERAL SIZEOF
|
||||
%token PTR_OP INC_OP DEC_OP LEFT_OP RIGHT_OP LE_OP GE_OP EQ_OP NE_OP
|
||||
%token AND_OP OR_OP MUL_ASSIGN DIV_ASSIGN MOD_ASSIGN ADD_ASSIGN
|
||||
%token SUB_ASSIGN LEFT_ASSIGN RIGHT_ASSIGN AND_ASSIGN
|
||||
%token XOR_ASSIGN OR_ASSIGN TYPE_NAME
|
||||
|
||||
%token TYPEDEF EXTERN STATIC AUTO REGISTER
|
||||
%token CHAR SHORT INT LONG SIGNED UNSIGNED FLOAT DOUBLE CONST VOLATILE VOID
|
||||
%token STRUCT UNION ENUM ELLIPSIS
|
||||
|
||||
%token CASE DEFAULT IF ELSE SWITCH WHILE DO FOR GOTO CONTINUE BREAK RETURN
|
||||
|
||||
%nonassoc IF_WITHOUT_ELSE
|
||||
%nonassoc ELSE
|
||||
|
||||
%start translation_unit
|
||||
%%
|
||||
|
||||
primary_expression
|
||||
: IDENTIFIER
|
||||
| CONSTANT
|
||||
| STRING_LITERAL
|
||||
| '(' expression ')'
|
||||
;
|
||||
|
||||
postfix_expression
|
||||
: primary_expression
|
||||
| postfix_expression '[' expression ']'
|
||||
| postfix_expression '(' ')'
|
||||
| postfix_expression '(' argument_expression_list ')'
|
||||
| postfix_expression '.' IDENTIFIER
|
||||
| postfix_expression PTR_OP IDENTIFIER
|
||||
| postfix_expression INC_OP
|
||||
| postfix_expression DEC_OP
|
||||
;
|
||||
|
||||
argument_expression_list
|
||||
: assignment_expression
|
||||
| argument_expression_list ',' assignment_expression
|
||||
;
|
||||
|
||||
unary_expression
|
||||
: postfix_expression
|
||||
| INC_OP unary_expression
|
||||
| DEC_OP unary_expression
|
||||
| unary_operator cast_expression
|
||||
| SIZEOF unary_expression
|
||||
| SIZEOF '(' type_name ')'
|
||||
;
|
||||
|
||||
unary_operator
|
||||
: '&'
|
||||
| '*'
|
||||
| '+'
|
||||
| '-'
|
||||
| '~'
|
||||
| '!'
|
||||
;
|
||||
|
||||
cast_expression
|
||||
: unary_expression
|
||||
| '(' type_name ')' cast_expression
|
||||
;
|
||||
|
||||
multiplicative_expression
|
||||
: cast_expression
|
||||
| multiplicative_expression '*' cast_expression
|
||||
| multiplicative_expression '/' cast_expression
|
||||
| multiplicative_expression '%' cast_expression
|
||||
;
|
||||
|
||||
additive_expression
|
||||
: multiplicative_expression
|
||||
| additive_expression '+' multiplicative_expression
|
||||
| additive_expression '-' multiplicative_expression
|
||||
;
|
||||
|
||||
shift_expression
|
||||
: additive_expression
|
||||
| shift_expression LEFT_OP additive_expression
|
||||
| shift_expression RIGHT_OP additive_expression
|
||||
;
|
||||
|
||||
relational_expression
|
||||
: shift_expression
|
||||
| relational_expression '<' shift_expression
|
||||
| relational_expression '>' shift_expression
|
||||
| relational_expression LE_OP shift_expression
|
||||
| relational_expression GE_OP shift_expression
|
||||
;
|
||||
|
||||
equality_expression
|
||||
: relational_expression
|
||||
| equality_expression EQ_OP relational_expression
|
||||
| equality_expression NE_OP relational_expression
|
||||
;
|
||||
|
||||
and_expression
|
||||
: equality_expression
|
||||
| and_expression '&' equality_expression
|
||||
;
|
||||
|
||||
exclusive_or_expression
|
||||
: and_expression
|
||||
| exclusive_or_expression '^' and_expression
|
||||
;
|
||||
|
||||
inclusive_or_expression
|
||||
: exclusive_or_expression
|
||||
| inclusive_or_expression '|' exclusive_or_expression
|
||||
;
|
||||
|
||||
logical_and_expression
|
||||
: inclusive_or_expression
|
||||
| logical_and_expression AND_OP inclusive_or_expression
|
||||
;
|
||||
|
||||
logical_or_expression
|
||||
: logical_and_expression
|
||||
| logical_or_expression OR_OP logical_and_expression
|
||||
;
|
||||
|
||||
conditional_expression
|
||||
: logical_or_expression
|
||||
| logical_or_expression '?' expression ':' conditional_expression
|
||||
;
|
||||
|
||||
assignment_expression
|
||||
: conditional_expression
|
||||
| unary_expression assignment_operator assignment_expression
|
||||
;
|
||||
|
||||
assignment_operator
|
||||
: '='
|
||||
| MUL_ASSIGN
|
||||
| DIV_ASSIGN
|
||||
| MOD_ASSIGN
|
||||
| ADD_ASSIGN
|
||||
| SUB_ASSIGN
|
||||
| LEFT_ASSIGN
|
||||
| RIGHT_ASSIGN
|
||||
| AND_ASSIGN
|
||||
| XOR_ASSIGN
|
||||
| OR_ASSIGN
|
||||
;
|
||||
|
||||
expression
|
||||
: assignment_expression
|
||||
| expression ',' assignment_expression
|
||||
;
|
||||
|
||||
constant_expression
|
||||
: conditional_expression
|
||||
;
|
||||
|
||||
declaration
|
||||
: declaration_specifiers ';'
|
||||
| declaration_specifiers init_declarator_list ';'
|
||||
;
|
||||
|
||||
declaration_specifiers
|
||||
: storage_class_specifier
|
||||
| storage_class_specifier declaration_specifiers
|
||||
| type_specifier
|
||||
| type_specifier declaration_specifiers
|
||||
| type_qualifier
|
||||
| type_qualifier declaration_specifiers
|
||||
;
|
||||
|
||||
init_declarator_list
|
||||
: init_declarator
|
||||
| init_declarator_list ',' init_declarator
|
||||
;
|
||||
|
||||
init_declarator
|
||||
: declarator
|
||||
| declarator '=' initializer
|
||||
;
|
||||
|
||||
storage_class_specifier
|
||||
: TYPEDEF
|
||||
| EXTERN
|
||||
| STATIC
|
||||
| AUTO
|
||||
| REGISTER
|
||||
;
|
||||
|
||||
type_specifier
|
||||
: VOID
|
||||
| CHAR
|
||||
| SHORT
|
||||
| INT
|
||||
| LONG
|
||||
| FLOAT
|
||||
| DOUBLE
|
||||
| SIGNED
|
||||
| UNSIGNED
|
||||
| struct_or_union_specifier
|
||||
| enum_specifier
|
||||
| TYPE_NAME
|
||||
;
|
||||
|
||||
struct_or_union_specifier
|
||||
: struct_or_union IDENTIFIER '{' struct_declaration_list '}'
|
||||
| struct_or_union '{' struct_declaration_list '}'
|
||||
| struct_or_union IDENTIFIER
|
||||
;
|
||||
|
||||
struct_or_union
|
||||
: STRUCT
|
||||
| UNION
|
||||
;
|
||||
|
||||
struct_declaration_list
|
||||
: struct_declaration
|
||||
| struct_declaration_list struct_declaration
|
||||
;
|
||||
|
||||
struct_declaration
|
||||
: specifier_qualifier_list struct_declarator_list ';'
|
||||
;
|
||||
|
||||
specifier_qualifier_list
|
||||
: type_specifier specifier_qualifier_list
|
||||
| type_specifier
|
||||
| type_qualifier specifier_qualifier_list
|
||||
| type_qualifier
|
||||
;
|
||||
|
||||
struct_declarator_list
|
||||
: struct_declarator
|
||||
| struct_declarator_list ',' struct_declarator
|
||||
;
|
||||
|
||||
struct_declarator
|
||||
: declarator
|
||||
| ':' constant_expression
|
||||
| declarator ':' constant_expression
|
||||
;
|
||||
|
||||
enum_specifier
|
||||
: ENUM '{' enumerator_list '}'
|
||||
| ENUM IDENTIFIER '{' enumerator_list '}'
|
||||
| ENUM IDENTIFIER
|
||||
;
|
||||
|
||||
enumerator_list
|
||||
: enumerator
|
||||
| enumerator_list ',' enumerator
|
||||
;
|
||||
|
||||
enumerator
|
||||
: IDENTIFIER
|
||||
| IDENTIFIER '=' constant_expression
|
||||
;
|
||||
|
||||
type_qualifier
|
||||
: CONST
|
||||
| VOLATILE
|
||||
;
|
||||
|
||||
declarator
|
||||
: pointer direct_declarator
|
||||
| direct_declarator
|
||||
;
|
||||
|
||||
direct_declarator
|
||||
: IDENTIFIER
|
||||
| '(' declarator ')'
|
||||
| direct_declarator '[' constant_expression ']'
|
||||
| direct_declarator '[' ']'
|
||||
| direct_declarator '(' parameter_type_list ')'
|
||||
| direct_declarator '(' identifier_list ')'
|
||||
| direct_declarator '(' ')'
|
||||
;
|
||||
|
||||
pointer
|
||||
: '*'
|
||||
| '*' type_qualifier_list
|
||||
| '*' pointer
|
||||
| '*' type_qualifier_list pointer
|
||||
;
|
||||
|
||||
type_qualifier_list
|
||||
: type_qualifier
|
||||
| type_qualifier_list type_qualifier
|
||||
;
|
||||
|
||||
|
||||
parameter_type_list
|
||||
: parameter_list
|
||||
| parameter_list ',' ELLIPSIS
|
||||
;
|
||||
|
||||
parameter_list
|
||||
: parameter_declaration
|
||||
| parameter_list ',' parameter_declaration
|
||||
;
|
||||
|
||||
parameter_declaration
|
||||
: declaration_specifiers declarator
|
||||
| declaration_specifiers abstract_declarator
|
||||
| declaration_specifiers
|
||||
;
|
||||
|
||||
identifier_list
|
||||
: IDENTIFIER
|
||||
| identifier_list ',' IDENTIFIER
|
||||
;
|
||||
|
||||
type_name
|
||||
: specifier_qualifier_list
|
||||
| specifier_qualifier_list abstract_declarator
|
||||
;
|
||||
|
||||
abstract_declarator
|
||||
: pointer
|
||||
| direct_abstract_declarator
|
||||
| pointer direct_abstract_declarator
|
||||
;
|
||||
|
||||
direct_abstract_declarator
|
||||
: '(' abstract_declarator ')'
|
||||
| '[' ']'
|
||||
| '[' constant_expression ']'
|
||||
| direct_abstract_declarator '[' ']'
|
||||
| direct_abstract_declarator '[' constant_expression ']'
|
||||
| '(' ')'
|
||||
| '(' parameter_type_list ')'
|
||||
| direct_abstract_declarator '(' ')'
|
||||
| direct_abstract_declarator '(' parameter_type_list ')'
|
||||
;
|
||||
|
||||
initializer
|
||||
: assignment_expression
|
||||
| '{' initializer_list '}'
|
||||
| '{' initializer_list ',' '}'
|
||||
;
|
||||
|
||||
initializer_list
|
||||
: initializer
|
||||
| initializer_list ',' initializer
|
||||
;
|
||||
|
||||
statement
|
||||
: labeled_statement
|
||||
| compound_statement
|
||||
| expression_statement
|
||||
| selection_statement
|
||||
| iteration_statement
|
||||
| jump_statement
|
||||
;
|
||||
|
||||
labeled_statement
|
||||
: IDENTIFIER ':' statement
|
||||
| CASE constant_expression ':' statement
|
||||
| DEFAULT ':' statement
|
||||
;
|
||||
|
||||
compound_statement
|
||||
: '{' '}'
|
||||
| '{' statement_list '}'
|
||||
| '{' declaration_list '}'
|
||||
| '{' declaration_list statement_list '}'
|
||||
;
|
||||
|
||||
declaration_list
|
||||
: declaration
|
||||
| declaration_list declaration
|
||||
;
|
||||
|
||||
statement_list
|
||||
: statement
|
||||
| statement_list statement
|
||||
;
|
||||
|
||||
expression_statement
|
||||
: ';'
|
||||
| expression ';'
|
||||
;
|
||||
|
||||
selection_statement
|
||||
: IF '(' expression ')' statement %prec IF_WITHOUT_ELSE
|
||||
| IF '(' expression ')' statement ELSE statement
|
||||
| SWITCH '(' expression ')' statement
|
||||
;
|
||||
|
||||
iteration_statement
|
||||
: WHILE '(' expression ')' statement
|
||||
| DO statement WHILE '(' expression ')' ';'
|
||||
| FOR '(' expression_statement expression_statement ')' statement
|
||||
| FOR '(' expression_statement expression_statement expression ')' statement
|
||||
;
|
||||
|
||||
jump_statement
|
||||
: GOTO IDENTIFIER ';'
|
||||
| CONTINUE ';'
|
||||
| BREAK ';'
|
||||
| RETURN ';'
|
||||
| RETURN expression ';'
|
||||
;
|
||||
|
||||
translation_unit
|
||||
: external_declaration
|
||||
| translation_unit external_declaration
|
||||
;
|
||||
|
||||
external_declaration
|
||||
: function_definition
|
||||
| declaration
|
||||
;
|
||||
|
||||
function_definition
|
||||
: declaration_specifiers declarator declaration_list compound_statement
|
||||
| declaration_specifiers declarator compound_statement
|
||||
| declarator declaration_list compound_statement
|
||||
| declarator compound_statement
|
||||
;
|
||||
84
samples/Jison/classy.jison
Normal file
84
samples/Jison/classy.jison
Normal file
@@ -0,0 +1,84 @@
|
||||
|
||||
/* description: ClassyLang grammar. Very classy. */
|
||||
/*
|
||||
To build parser:
|
||||
|
||||
$ ./bin/jison examples/classy.jison examples/classy.jisonlex
|
||||
|
||||
*/
|
||||
|
||||
|
||||
/* author: Zach Carter */
|
||||
|
||||
%right ASSIGN
|
||||
%left OR
|
||||
%nonassoc EQUALITY GREATER
|
||||
%left PLUS MINUS
|
||||
%left TIMES
|
||||
%right NOT
|
||||
%left DOT
|
||||
|
||||
%%
|
||||
|
||||
pgm
|
||||
: cdl MAIN LBRACE vdl el RBRACE ENDOFFILE
|
||||
;
|
||||
|
||||
cdl
|
||||
: c cdl
|
||||
|
|
||||
;
|
||||
|
||||
c
|
||||
: CLASS id EXTENDS id LBRACE vdl mdl RBRACE
|
||||
;
|
||||
|
||||
vdl
|
||||
: VAR t id SEMICOLON vdl
|
||||
|
|
||||
;
|
||||
|
||||
mdl
|
||||
: t id LPAREN t id RPAREN LBRACE vdl el RBRACE mdl
|
||||
|
|
||||
;
|
||||
|
||||
t
|
||||
: NATTYPE
|
||||
| id
|
||||
;
|
||||
|
||||
id
|
||||
: ID
|
||||
;
|
||||
|
||||
el
|
||||
: e SEMICOLON el
|
||||
| e SEMICOLON
|
||||
;
|
||||
|
||||
e
|
||||
: NATLITERAL
|
||||
| NUL
|
||||
| id
|
||||
| NEW id
|
||||
| THIS
|
||||
| IF LPAREN e RPAREN LBRACE el RBRACE ELSE LBRACE el RBRACE
|
||||
| FOR LPAREN e SEMICOLON e SEMICOLON e RPAREN LBRACE el RBRACE
|
||||
| READNAT LPAREN RPAREN
|
||||
| PRINTNAT LPAREN e RPAREN
|
||||
| e PLUS e
|
||||
| e MINUS e
|
||||
| e TIMES e
|
||||
| e EQUALITY e
|
||||
| e GREATER e
|
||||
| NOT e
|
||||
| e OR e
|
||||
| e DOT id
|
||||
| id ASSIGN e
|
||||
| e DOT id ASSIGN e
|
||||
| id LPAREN e RPAREN
|
||||
| e DOT id LPAREN e RPAREN
|
||||
| LPAREN e RPAREN
|
||||
;
|
||||
|
||||
145
samples/Jison/lex.jison
Normal file
145
samples/Jison/lex.jison
Normal file
@@ -0,0 +1,145 @@
|
||||
|
||||
// `%nonassoc` tells the parser compiler (JISON) that these tokens cannot occur more than once,
|
||||
// i.e. input like '//a' (tokens '/', '/' and 'a') is not a legal input while '/a' (tokens '/' and 'a')
|
||||
// *is* legal input for this grammar.
|
||||
|
||||
%nonassoc '/' '/!'
|
||||
|
||||
// Likewise for `%left`: this informs the LALR(1) grammar compiler (JISON) that these tokens
|
||||
// *can* occur repeatedly, e.g. 'a?*' and even 'a**' are considered legal inputs given this
|
||||
// grammar!
|
||||
//
|
||||
// Token `RANGE_REGEX` may seem the odd one out here but really isn't: given the `regex_base`
|
||||
// choice/rule `regex_base range_regex`, which is recursive, this grammar tells JISON that
|
||||
// any input matching a sequence like `regex_base range_regex range_regex` *is* legal.
|
||||
// If you do not want that to be legal, you MUST adjust the grammar rule set you match your
|
||||
// actual intent.
|
||||
|
||||
%left '*' '+' '?' RANGE_REGEX
|
||||
|
||||
|
||||
%%
|
||||
|
||||
lex
|
||||
: definitions include '%%' rules '%%' EOF
|
||||
{{ $$ = {macros: $1, rules: $4};
|
||||
if ($2) $$.actionInclude = $2;
|
||||
return $$; }}
|
||||
| definitions include '%%' rules EOF
|
||||
{{ $$ = {macros: $1, rules: $4};
|
||||
if ($2) $$.actionInclude = $2;
|
||||
return $$; }}
|
||||
;
|
||||
|
||||
include
|
||||
: action
|
||||
|
|
||||
;
|
||||
|
||||
definitions
|
||||
: definitions definition
|
||||
{ $$ = $1; $$.concat($2); }
|
||||
| definition
|
||||
{ $$ = [$1]; }
|
||||
;
|
||||
|
||||
definition
|
||||
: name regex
|
||||
{ $$ = [$1, $2]; }
|
||||
;
|
||||
|
||||
name
|
||||
: NAME
|
||||
{ $$ = yytext; }
|
||||
;
|
||||
|
||||
rules
|
||||
: rules rule
|
||||
{ $$ = $1; $$.push($2); }
|
||||
| rule
|
||||
{ $$ = [$1]; }
|
||||
;
|
||||
|
||||
rule
|
||||
: regex action
|
||||
{ $$ = [$1, $2]; }
|
||||
;
|
||||
|
||||
action
|
||||
: ACTION
|
||||
{ $$ = yytext; }
|
||||
;
|
||||
|
||||
regex
|
||||
: start_caret regex_list end_dollar
|
||||
{ $$ = $1+$2+$3; }
|
||||
;
|
||||
|
||||
start_caret
|
||||
: '^'
|
||||
{ $$ = '^'; }
|
||||
|
|
||||
{ $$ = ''; }
|
||||
;
|
||||
|
||||
end_dollar
|
||||
: '$'
|
||||
{ $$ = '$'; }
|
||||
|
|
||||
{ $$ = ''; }
|
||||
;
|
||||
|
||||
regex_list
|
||||
: regex_list '|' regex_chain
|
||||
{ $$ = $1+'|'+$3; }
|
||||
| regex_chain
|
||||
;
|
||||
|
||||
regex_chain
|
||||
: regex_chain regex_base
|
||||
{ $$ = $1+$2;}
|
||||
| regex_base
|
||||
{ $$ = $1;}
|
||||
;
|
||||
|
||||
regex_base
|
||||
: '(' regex_list ')'
|
||||
{ $$ = '('+$2+')'; }
|
||||
| regex_base '+'
|
||||
{ $$ = $1+'+'; }
|
||||
| regex_base '*'
|
||||
{ $$ = $1+'*'; }
|
||||
| regex_base '?'
|
||||
{ $$ = $1+'?'; }
|
||||
| '/' regex_base
|
||||
{ $$ = '(?=' + $regex_base + ')'; }
|
||||
| '/!' regex_base
|
||||
{ $$ = '(?!' + $regex_base + ')'; }
|
||||
| name_expansion
|
||||
| regex_base range_regex
|
||||
{ $$ = $1+$2; }
|
||||
| any_group_regex
|
||||
| '.'
|
||||
{ $$ = '.'; }
|
||||
| string
|
||||
;
|
||||
|
||||
name_expansion
|
||||
: '{' name '}'
|
||||
{{ $$ = '{'+$2+'}'; }}
|
||||
;
|
||||
|
||||
any_group_regex
|
||||
: ANY_GROUP_REGEX
|
||||
{ $$ = yytext; }
|
||||
;
|
||||
|
||||
range_regex
|
||||
: RANGE_REGEX
|
||||
{ $$ = yytext; }
|
||||
;
|
||||
|
||||
string
|
||||
: STRING_LIT
|
||||
{ $$ = yy.prepareString(yytext.substr(1, yyleng-2)); }
|
||||
;
|
||||
Reference in New Issue
Block a user