centvrion/parser.py

from rply import ParserGenerator

from lexer import all_tokens
import ast_nodes

ALL_TOKENS = list(set([i[0] for i in all_tokens]))

class Parser():
    def __init__(self):
        self.pg = ParserGenerator(ALL_TOKENS)

    def parse(self):
        @self.pg.production('program : opt_newline module_calls statements')
        def program(tokens):
            return ast_nodes.Program(tokens[-2], tokens[-1])

        @self.pg.production('opt_newline : ')
        @self.pg.production('opt_newline : NEWLINE')
        def opt_newline(_):
            return None

        @self.pg.production('module_calls : ')
        @self.pg.production('module_calls : module_call NEWLINE module_calls')
        def module_calls(calls):
            if len(calls) == 0:
                return []
            else:
                return [calls[0]] + calls[2]

        @self.pg.production('module_call : KEYWORD_VOCA MODULE')
        def module_call(tokens):
            return ast_nodes.ModuleCall(tokens[1].value)

        @self.pg.production('statements : ')
        @self.pg.production('statements : statement NEWLINE statements')
        def statements(calls):
            if len(calls) == 0:
                return []
            else:
                return [calls[0]] + calls[2]

        @self.pg.production('statement : KEYWORD_DESIGNA id KEYWORD_UT expression')
        def statement_designa(tokens):
            return ast_nodes.Designa(tokens[1], tokens[3])

        @self.pg.production('statement : expression')
        def statement_expression(tokens):
            return ast_nodes.ExpressionStatement(tokens[0])

        @self.pg.production('expressions : ')
        @self.pg.production('expressions : expression expressions')
        def expressions(calls):
            if len(calls) == 0:
                return []
            else:
                return [calls[0]] + calls[1]

        @self.pg.production('ids : ')
        @self.pg.production('ids : id ids')
        def ids(calls):
            if len(calls) == 0:
                return []
            else:
                return [calls[0]] + calls[1]

        @self.pg.production('expression : id')
        def expression_id(tokens):
            return tokens[0]

        @self.pg.production('statement : KEYWORD_DEFINI id ids KEYWORD_UT SYMBOL_LCURL opt_newline statements opt_newline SYMBOL_RCURL')
        def defini(tokens):
            return ast_nodes.Defini(tokens[1], tokens[2], tokens[6])

        @self.pg.production('statement : KEYWORD_REDI expressions')
        def redi(tokens):
            return ast_nodes.Redi(tokens[1])

        @self.pg.production('expression : DATA_STRING')
        def expression_string(tokens):
            return ast_nodes.String(tokens[0].value)

        @self.pg.production('expression : DATA_NUMERAL')
        def expression_numeral(tokens):
            return ast_nodes.Numeral(tokens[0].value)

        @self.pg.production('expression : KEYWORD_FALSITAS')
        @self.pg.production('expression : KEYWORD_VERITAS')
        def expression_bool(tokens):
            return ast_nodes.Bool(tokens[0].name == "KEYWORD_VERITAS")

        @self.pg.production('expression : KEYWORD_NULLUS')
        def expression_nullus(_):
            return ast_nodes.Nullus()

        @self.pg.production('expression : expression SYMBOL_MINUS expression')
        @self.pg.production('expression : expression SYMBOL_PLUS expression')
        @self.pg.production('expression : expression KEYWORD_EST expression')
        @self.pg.production('expression : expression KEYWORD_MINUS expression')
        @self.pg.production('expression : expression KEYWORD_PLUS expression')
        def binop(tokens):
            return ast_nodes.BinOp(tokens[0], tokens[2], tokens[1].name)

        @self.pg.production('expression : BUILTIN expressions')
        def expression_builtin(tokens):
            return ast_nodes.BuiltIn(tokens[0].value, tokens[1])

        @self.pg.production("id : ID")
        def id_expression(tokens):
            return ast_nodes.ID(tokens[0].value)

        @self.pg.production('expression : KEYWORD_INVOCA id expressions')
        def invoca(tokens):
            return ast_nodes.Invoca(tokens[1], tokens[2])

        @self.pg.production('statement : si_statement')
        def si_statement(tokens):
            return tokens[0]

        @self.pg.production('statement : dum_statement')
        def dum_statement(tokens):
            return tokens[0]

        @self.pg.production('si_statement : KEYWORD_SI expression KEYWORD_TUNC SYMBOL_LCURL opt_newline statements opt_newline SYMBOL_RCURL opt_newline aluid_statement')
        def si(tokens):
            return ast_nodes.SiStatement(tokens[1], tokens[5], tokens[9])

        @self.pg.production('dum_statement : KEYWORD_DUM expression KEYWORD_FACE SYMBOL_LCURL opt_newline statements opt_newline SYMBOL_RCURL')
        def dum(tokens):
            return ast_nodes.DumStatement(tokens[1], tokens[5])

        @self.pg.production('aluid_statement : ')
        def aluid_empty(_):
            return None

        @self.pg.production('aluid_statement : KEYWORD_ALUID si_statement')
        def aluid_si(tokens):
            return [tokens[1]]

        @self.pg.production('aluid_statement : KEYWORD_ALUID SYMBOL_LCURL opt_newline statements opt_newline SYMBOL_RCURL aluid_statement')
        def aluid(tokens):
            return tokens[3]

        @self.pg.production('expression : SYMBOL_LPARENS expression SYMBOL_RPARENS')
        def parens(tokens):
            return tokens[1]

        @self.pg.error
        def error_handle(token):
            raise ValueError(token)


    def get_parser(self):
        return self.pg.build()