1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
//! This module contains excerpts about the grammar directly from CPython's documentation //! //! CPython has it's own DFA based parser generator for which the input is `PythonGrammar`. /// The grammar as it /// ASDL's 7 builtin types are: /// /// - identifier, int, string, bytes, object, singleton, constant /// -- singleton: None, True or False /// -- constant can be None, whereas None means "no value" for object. /// /// ```raw /// /// module Python /// { /// mod = Module(stmt* body) /// | Interactive(stmt* body) /// | Expression(expr body) /// /// -- not really an actual node but useful in Jython's typesystem. /// | Suite(stmt* body) /// /// stmt = FunctionDef(identifier name, arguments args, /// stmt* body, expr* decorator_list, expr? returns) /// | AsyncFunctionDef(identifier name, arguments args, /// stmt* body, expr* decorator_list, expr? returns) /// /// | ClassDef(identifier name, /// expr* bases, /// keyword* keywords, /// stmt* body, /// expr* decorator_list) /// | Return(expr? value) /// /// | Delete(expr* targets) /// | Assign(expr* targets, expr value) /// | AugAssign(expr target, operator op, expr value) /// -- simple indicates that we annotate simple name without parens /// | AnnAssign(expr target, expr annotation, expr? value, int simple) /// /// -- use 'orelse' because else is a keyword in target languages /// | For(expr target, expr iter, stmt* body, stmt* orelse) /// | AsyncFor(expr target, expr iter, stmt* body, stmt* orelse) /// | While(expr test, stmt* body, stmt* orelse) /// | If(expr test, stmt* body, stmt* orelse) /// | With(withitem* items, stmt* body) /// | AsyncWith(withitem* items, stmt* body) /// /// | Raise(expr? exc, expr? cause) /// | Try(stmt* body, excepthandler* handlers, stmt* orelse, stmt* finalbody) /// | Assert(expr test, expr? msg) /// /// | Import(alias* names) /// | ImportFrom(identifier? module, alias* names, int? level) /// /// | Global(identifier* names) /// | Nonlocal(identifier* names) /// | Expr(expr value) /// | Pass | Break | Continue /// /// -- XXX Jython will be different /// -- col_offset is the byte offset in the utf8 string the parser uses /// attributes (int lineno, int col_offset) /// /// -- BoolOp() can use left & right? /// expr = BoolOp(boolop op, expr* values) /// | BinOp(expr left, operator op, expr right) /// | UnaryOp(unaryop op, expr operand) /// | Lambda(arguments args, expr body) /// | IfExp(expr test, expr body, expr orelse) /// | Dict(expr* keys, expr* values) /// | Set(expr* elts) /// | ListComp(expr elt, comprehension* generators) /// | SetComp(expr elt, comprehension* generators) /// | DictComp(expr key, expr value, comprehension* generators) /// | GeneratorExp(expr elt, comprehension* generators) /// -- the grammar constrains where yield expressions can occur /// | Await(expr value) /// | Yield(expr? value) /// | YieldFrom(expr value) /// -- need sequences for compare to distinguish between /// -- x < 4 < 3 and (x < 4) < 3 /// | Compare(expr left, cmpop* ops, expr* comparators) /// | Call(expr func, expr* args, keyword* keywords) /// | Num(object n) -- a number as a PyObject. /// | Str(string s) -- need to specify raw, unicode, etc? /// | FormattedValue(expr value, int? conversion, expr? format_spec) /// | JoinedStr(expr* values) /// | Bytes(bytes s) /// | NameConstant(singleton value) /// | Ellipsis /// | Constant(constant value) /// /// -- the following expression can appear in assignment context /// | Attribute(expr value, identifier attr, expr_context ctx) /// | Subscript(expr value, slice slice, expr_context ctx) /// | Starred(expr value, expr_context ctx) /// | Name(identifier id, expr_context ctx) /// | List(expr* elts, expr_context ctx) /// | Tuple(expr* elts, expr_context ctx) /// /// -- col_offset is the byte offset in the utf8 string the parser uses /// attributes (int lineno, int col_offset) /// /// expr_context = Load | Store | Del | AugLoad | AugStore | Param /// /// slice = Slice(expr? lower, expr? upper, expr? step) /// | ExtSlice(slice* dims) /// | Index(expr value) /// /// boolop = And | Or /// /// operator = Add | Sub | Mult | MatMult | Div | Mod | Pow | LShift /// | RShift | BitOr | BitXor | BitAnd | FloorDiv /// /// unaryop = Invert | Not | UAdd | USub /// /// cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn /// /// comprehension = (expr target, expr iter, expr* ifs, int is_async) /// /// excepthandler = ExceptHandler(expr? type, identifier? name, stmt* body) /// attributes (int lineno, int col_offset) /// /// arguments = (arg* args, arg? vararg, arg* kwonlyargs, expr* kw_defaults, /// arg? kwarg, expr* defaults) /// /// arg = (identifier arg, expr? annotation) /// attributes (int lineno, int col_offset) /// /// -- keyword arguments supplied to call (NULL identifier for **kwargs) /// keyword = (identifier? arg, expr value) /// /// -- import name with optional 'as' alias. /// alias = (identifier name, identifier? asname) /// /// withitem = (expr context_expr, expr? optional_vars) /// } /// ``` /// pub struct PythonASDL; /// Grammar for Python /// /// ```raw /// /// /// # Start symbols for the grammar: /// # single_input is a single interactive statement; /// # file_input is a module or sequence of commands read from an input file; /// # eval_input is the input for the eval() functions. /// # NB: compound_stmt in single_input is followed by extra NEWLINE! /// single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE /// file_input: (NEWLINE | stmt)* ENDMARKER /// eval_input: testlist NEWLINE* ENDMARKER /// /// decorator: '@' dotted_name [ '(' [arglist] ')' ] NEWLINE /// decorators: decorator+ /// decorated: decorators (classdef | funcdef | async_funcdef) /// /// async_funcdef: ASYNC funcdef /// funcdef: 'def' NAME parameters ['->' test] ':' suite /// /// parameters: '(' [typedargslist] ')' /// typedargslist: (tfpdef ['=' test] (',' tfpdef ['=' test])* [',' [ /// '*' [tfpdef] (',' tfpdef ['=' test])* [',' ['**' tfpdef [',']]] /// | '**' tfpdef [',']]] /// | '*' [tfpdef] (',' tfpdef ['=' test])* [',' ['**' tfpdef [',']]] /// | '**' tfpdef [',']) /// tfpdef: NAME [':' test] /// varargslist: (vfpdef ['=' test] (',' vfpdef ['=' test])* [',' [ /// '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]] /// | '**' vfpdef [',']]] /// | '*' [vfpdef] (',' vfpdef ['=' test])* [',' ['**' vfpdef [',']]] /// | '**' vfpdef [','] /// ) /// vfpdef: NAME /// /// stmt: simple_stmt | compound_stmt /// simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE /// small_stmt: (expr_stmt | del_stmt | pass_stmt | flow_stmt | /// import_stmt | global_stmt | nonlocal_stmt | assert_stmt) /// expr_stmt: testlist_star_expr (annassign | augassign (yield_expr|testlist) | /// ('=' (yield_expr|testlist_star_expr))*) /// annassign: ':' test ['=' test] /// testlist_star_expr: (test|star_expr) (',' (test|star_expr))* [','] /// augassign: ('+=' | '-=' | '*=' | '@=' | '/=' | '%=' | '&=' | '|=' | '^=' | /// '<<=' | '>>=' | '**=' | '//=') /// # For normal and annotated assignments, additional restrictions enforced by the interpreter /// del_stmt: 'del' exprlist /// pass_stmt: 'pass' /// flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt | yield_stmt /// break_stmt: 'break' /// continue_stmt: 'continue' /// return_stmt: 'return' [testlist] /// yield_stmt: yield_expr /// raise_stmt: 'raise' [test ['from' test]] /// import_stmt: import_name | import_from /// import_name: 'import' dotted_as_names /// # note below: the ('.' | '...') is necessary because '...' is tokenized as ELLIPSIS /// import_from: ('from' (('.' | '...')* dotted_name | ('.' | '...')+) /// 'import' ('*' | '(' import_as_names ')' | import_as_names)) /// import_as_name: NAME ['as' NAME] /// dotted_as_name: dotted_name ['as' NAME] /// import_as_names: import_as_name (',' import_as_name)* [','] /// dotted_as_names: dotted_as_name (',' dotted_as_name)* /// dotted_name: NAME ('.' NAME)* /// global_stmt: 'global' NAME (',' NAME)* /// nonlocal_stmt: 'nonlocal' NAME (',' NAME)* /// assert_stmt: 'assert' test [',' test] /// /// compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | with_stmt | funcdef | classdef | decorated | async_stmt /// async_stmt: ASYNC (funcdef | with_stmt | for_stmt) /// if_stmt: 'if' test ':' suite ('elif' test ':' suite)* ['else' ':' suite] /// while_stmt: 'while' test ':' suite ['else' ':' suite] /// for_stmt: 'for' exprlist 'in' testlist ':' suite ['else' ':' suite] /// try_stmt: ('try' ':' suite /// ((except_clause ':' suite)+ /// ['else' ':' suite] /// ['finally' ':' suite] | /// 'finally' ':' suite)) /// with_stmt: 'with' with_item (',' with_item)* ':' suite /// with_item: test ['as' expr] /// # NB compile.c makes sure that the default except clause is last /// except_clause: 'except' [test ['as' NAME]] /// suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT /// /// test: or_test ['if' or_test 'else' test] | lambdef /// test_nocond: or_test | lambdef_nocond /// lambdef: 'lambda' [varargslist] ':' test /// lambdef_nocond: 'lambda' [varargslist] ':' test_nocond /// or_test: and_test ('or' and_test)* /// and_test: not_test ('and' not_test)* /// not_test: 'not' not_test | comparison /// comparison: expr (comp_op expr)* /// # <> isn't actually a valid comparison operator in Python. It's here for the /// # sake of a __future__ import described in PEP 401 (which really works :-) /// comp_op: '<'|'>'|'=='|'>='|'<='|'<>'|'!='|'in'|'not' 'in'|'is'|'is' 'not' /// star_expr: '*' expr /// expr: xor_expr ('|' xor_expr)* /// xor_expr: and_expr ('^' and_expr)* /// and_expr: shift_expr ('&' shift_expr)* /// shift_expr: arith_expr (('<<'|'>>') arith_expr)* /// arith_expr: term (('+'|'-') term)* /// term: factor (('*'|'@'|'/'|'%'|'//') factor)* /// factor: ('+'|'-'|'~') factor | power /// power: atom_expr ['**' factor] /// atom_expr: [AWAIT] atom trailer* /// atom: ('(' [yield_expr|testlist_comp] ')' | /// '[' [testlist_comp] ']' | /// '{' [dictorsetmaker] '}' | /// NAME | NUMBER | STRING+ | '...' | 'None' | 'True' | 'False') /// testlist_comp: (test|star_expr) ( comp_for | (',' (test|star_expr))* [','] ) /// trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME /// subscriptlist: subscript (',' subscript)* [','] /// subscript: test | [test] ':' [test] [sliceop] /// sliceop: ':' [test] /// exprlist: (expr|star_expr) (',' (expr|star_expr))* [','] /// testlist: test (',' test)* [','] /// dictorsetmaker: ( ((test ':' test | '**' expr) /// (comp_for | (',' (test ':' test | '**' expr))* [','])) | /// ((test | star_expr) /// (comp_for | (',' (test | star_expr))* [','])) ) /// /// classdef: 'class' NAME ['(' [arglist] ')'] ':' suite /// /// arglist: argument (',' argument)* [','] /// /// # The reason that keywords are test nodes instead of NAME is that using NAME /// # results in an ambiguity. ast.c makes sure it's a NAME. /// # "test '=' test" is really "keyword '=' test", but we have no such token. /// # These need to be in a single rule to avoid grammar that is ambiguous /// # to our LL(1) parser. Even though 'test' includes '*expr' in star_expr, /// # we explicitly match '*' here, too, to give it proper precedence. /// # Illegal combinations and orderings are blocked in ast.c: /// # multiple (test comp_for) arguments are blocked; keyword unpackings /// # that precede iterable unpackings are blocked; etc. /// argument: ( test [comp_for] | /// test '=' test | /// '**' test | /// '*' test ) /// /// comp_iter: comp_for | comp_if /// comp_for: [ASYNC] 'for' exprlist 'in' or_test [comp_iter] /// comp_if: 'if' test_nocond [comp_iter] /// /// # not used in grammar, but may appear in "node" passed from Parser to Compiler /// encoding_decl: NAME /// /// yield_expr: 'yield' [yield_arg] /// yield_arg: 'from' test | testlist /// ``` /// pub struct PythonGrammar;