contrib/nitcc/src/nitcc_parser_gen.nit

   1 # This file is part of NIT ( http://www.nitlanguage.org ).
   2 #
   3 # Licensed under the Apache License, Version 2.0 (the "License");
   4 # you may not use this file except in compliance with the License.
   5 # You may obtain a copy of the License at
   6 #
   7 #     http://www.apache.org/licenses/LICENSE-2.0
   8 #
   9 # Unless required by applicable law or agreed to in writing, software
  10 # distributed under the License is distributed on an "AS IS" BASIS,
  11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12 # See the License for the specific language governing permissions and
  13 # limitations under the License.
  14
  15 # Bootstraping the nitcc parser
  16 #
  17 # Instead of commiting a generated parser on each version,
  18 # this program just generate the nitcc_parser using the API of `grammar`
  19 #
  20 # Pros:
  21 #
  22 #  - no generated file commited
  23 #  - easier to modify and bootstrap
  24 #
  25 # Cons:
  26 #
  27 #  - somewhat dublicate the ful grammar of nitcc
  28 #  - need an ad-hoc lexer (nitcc_lexer0.nit)
  29 #
  30 module nitcc_parser_gen
  31
  32 import grammar
  33
  34 var g = new Gram
  35 var p_gr = new Production("grammar")
  36 var p_lex = new Production("lexer")
  37 var p_exprs = new Production("exprs")
  38 var p_expr = new Production("expression")
  39 var p_re = new Production("re")
  40 var p_re1 = new Production("re1")
  41 var p_re2 = new Production("re2")
  42 var p_re3 = new Production("re3")
  43 var p_par = new Production("parser")
  44 var p_ign = new Production("ignored")
  45 var p_prods = new Production("prods")
  46 var p_prod = new Production("production")
  47 var p_ptrans_o = new Production("ptrans_o")
  48 var p_alts = new Production("alts")
  49 var p_alt = new Production("alternative")
  50 var p_altid_o = new Production("altid_o")
  51 var p_altid = new Production("altident")
  52 var p_elems = new Production("elems")
  53 var p_elem = new Production("elem")
  54 g.prods.add_all([p_gr, p_re, p_re1, p_re2, p_re3, p_lex, p_exprs, p_expr, p_par, p_ign, p_prods, p_prod, p_ptrans_o, p_alts, p_alt, p_altid_o, p_altid, p_elems, p_elem])
  55 g.prods.add(new Production("atrans"))
  56 g.prods.add(new Production("elemid"))
  57 g.prods.add(new Production("nelem"))
  58
  59 var t_opar = new Token("opar")
  60 var t_cpar = new Token("cpar")
  61 var t_ocur = new Token("ocur")
  62 var t_ccur = new Token("ccur")
  63 var t_pipe = new Token("pipe")
  64 var t_star = new Token("star")
  65 var t_ques = new Token("ques")
  66 var t_plus = new Token("plus")
  67 var t_minus = new Token("minus")
  68 var t_colo = new Token("colo")
  69 var t_semi = new Token("semi")
  70 var t_dot = new Token("dot")
  71 var t_eq = new Token("eq")
  72 var t_arrow = new Token("arrow")
  73 var t_str = new Token("str")
  74 var t_id = new Token("id")
  75 var t_kw = new Token("kw")
  76 var t_any = new Token("any")
  77 var t_ch_dec = new Token("ch_dec")
  78 g.tokens.add_all([t_opar, t_cpar, t_ocur, t_ccur, t_pipe, t_star, t_ques, t_plus, t_minus, t_colo, t_semi, t_dot, t_eq, t_arrow, t_str, t_id, t_kw, t_any, t_ch_dec])
  79
  80 p_gr.new_alt("gr", t_kw, t_id, t_semi, p_lex, p_par)
  81
  82 p_lex.new_alt("lex", t_kw, p_exprs)
  83
  84 p_exprs.new_alt("exprs_many", p_exprs, p_expr)
  85 p_exprs.new_alt0("exprs_none")
  86
  87 p_expr.new_alt("expr", t_id, t_eq, p_re, t_semi)
  88
  89 p_re.new_alt("re_alter", p_re, t_pipe, p_re1)
  90 p_re.new_alt("re_re2", p_re1)
  91
  92 p_re1.new_alt("re_minus", p_re1, t_minus, p_re2)
  93 p_re1.new_alt("re_re1", p_re2)
  94
  95 p_re2.new_alt("re_conc", p_re2, p_re3)
  96 p_re2.new_alt("re_re3", p_re3)
  97
  98 p_re3.new_alt("re_star", p_re3, t_star)
  99 p_re3.new_alt("re_ques", p_re3, t_ques)
 100 p_re3.new_alt("re_plus", p_re3, t_plus)
 101 p_re3.new_alt("re_par", t_opar, p_re, t_cpar)
 102 p_re3.new_alt("re_str", t_str)
 103 p_re3.new_alt("re_ch_dec", t_ch_dec)
 104 p_re3.new_alt("re_class", t_str, t_dot, t_dot, t_str)
 105 p_re3.new_alt("re_any", t_any)
 106 p_re3.new_alt("re_id", t_id)
 107
 108 p_par.new_alt("par", t_kw, p_ign, p_prods)
 109
 110 p_ign.new_alt0("ign_none")
 111 p_ign.new_alt("ign", t_kw, t_id, t_semi)
 112
 113 p_prods.new_alt("prods_many", p_prods, p_prod)
 114 p_prods.new_alt0("prods_none")
 115
 116 p_prod.new_alt("prod", t_id, p_ptrans_o, t_eq, p_alts, t_semi)
 117
 118 p_ptrans_o.new_alt("ptrans", t_ocur, t_arrow, t_id, t_ccur)
 119 p_ptrans_o.new_alt0("ptrans_none")
 120
 121 p_alts.new_alt("alts_many", p_alts, t_pipe, p_alt)
 122 p_alts.new_alt("alts_one", p_alt)
 123
 124 p_alt.new_alt("alt", p_altid_o, p_elems)
 125
 126 p_altid_o.new_alt0("altid_o_none")
 127 p_altid_o.new_alt("altid_o_one", p_altid)
 128
 129 p_altid.new_alt("altid", t_ocur, t_id, t_colo, t_ccur)
 130
 131 p_elems.new_alt("elems_many", p_elems, p_elem)
 132 p_elems.new_alt0("elems_none")
 133
 134 p_elem.new_alt("elem_id", t_id)
 135 p_elem.new_alt("elem_str", t_str)
 136 p_elem.new_alt("elem_par", t_opar, p_alts, t_cpar)
 137 p_elem.new_alt("elem_star", p_elem, t_star)
 138 p_elem.new_alt("elem_ques", p_elem, t_ques)
 139 p_elem.new_alt("elem_plus", p_elem, t_plus)
 140
 141 var a = g.lr0
 142
 143 print "LR automaton: {a.states.length} states (see nitcc0.lr.dot)"
 144 a.to_dot("nitcc0.lr.dot")
 145
 146 a.gen_to_nit("nitcc_parser.nit", "nitcc")
 147
 148 var f = new OFStream.open("nitcc_lexer.nit")
 149 f.write("import nitcc_lexer0\n")
 150 f.close