contrib/nitcc/src/nitcc_lexer0.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 # Ad-hoc hand-writen lexer for nitcc
  16 # This avoid to commit (and relyon ) a generated lexer
  17 #
  18 module nitcc_lexer0
  19
  20 # Required for the tokens definitions
  21 import nitcc_parser
  22
  23 # Hand-writen lexer of nitcc
  24 # Used only for the boostrap of the tool.
  25 class Lexer_nitcc
  26         var text: String
  27
  28         var iter: Iterator[Char] = "".chars.iterator
  29         var pos = 0
  30
  31         var tokens = new Array[NToken]
  32
  33         fun lex: Array[NToken]
  34         do
  35                 iter = text.chars.iterator
  36                 while iter.is_ok do
  37                         trim
  38                         if not iter.is_ok then break
  39                         var c = iter.item
  40                         iter.next
  41                         pos += 1
  42                         if c == '*' then
  43                                 tokens.add new Nstar
  44                         else if c == '?' then
  45                                 tokens.add new Nques
  46                         else if c == '+' then
  47                                 tokens.add new Nplus
  48                         else if c == '-' then
  49                                 if iter.item == '>' then
  50                                         iter.next
  51                                         tokens.add new Narrow
  52                                 else
  53                                         tokens.add new Nminus
  54                                 end
  55                         else if c == '(' then
  56                                 tokens.add new Nopar
  57                         else if c == ')' then
  58                                 tokens.add new Ncpar
  59                         else if c == '{' then
  60                                 tokens.add new Nocur
  61                         else if c == '}' then
  62                                 tokens.add new Nccur
  63                         else if c == '|' then
  64                                 tokens.add new Npipe
  65                         else if c == ',' then
  66                                 tokens.add new Ncomma
  67                         else if c == ':' then
  68                                 tokens.add new Ncolo
  69                         else if c == ';' then
  70                                 tokens.add new Nsemi
  71                         else if c == '.' then
  72                                 tokens.add new Ndot
  73                         else if c == '=' then
  74                                 tokens.add new Neq
  75                         else if c == '\'' then
  76                                 str
  77                         else if c >= 'a' and c <= 'z' then
  78                                 id(c)
  79                         else if c >= 'A' and c <= 'Z' then
  80                                 kw(c)
  81                         else if c == '/' and iter.is_ok and iter.item == '/' then
  82                                 while iter.is_ok and iter.item != '\n' do iter.next
  83                         else
  84                                 error(c)
  85                         end
  86                 end
  87                 tokens.add new NEof
  88                 return tokens
  89         end
  90
  91         fun error(c: Char)
  92         do
  93                 print "pos {pos}: Lexer error on '{c}'."
  94                 abort
  95         end
  96
  97         fun str
  98         do
  99                 var b = new FlatBuffer
 100                 b.add('\'')
 101                 while iter.is_ok do
 102                         var c = iter.item
 103                         iter.next
 104                         if c == '\\' then
 105                                 if not iter.is_ok then
 106                                         error(c)
 107                                 end
 108                                 b.add(c)
 109                                 c = iter.item
 110                                 iter.next
 111                         else if c == '\'' then
 112                                 b.add(c)
 113                                 var token = new Nstr
 114                                 token.text = b.to_s
 115                                 tokens.add token
 116                                 return
 117                         end
 118                         b.add c
 119                 end
 120                 error('\n')
 121                 abort
 122         end
 123
 124         fun id(c: Char)
 125         do
 126                 var b = new FlatBuffer
 127                 b.add c
 128                 while iter.is_ok do
 129                         c = iter.item
 130                         if c != '_' and (c<'a' or c >'z') and (c<'0' or c>'9') then
 131                                 break
 132                         end
 133                         b.add c
 134                         iter.next
 135                 end
 136                 var token = new Nid
 137                 token.text = b.to_s
 138                 tokens.add token
 139         end
 140
 141         fun kw(c: Char)
 142         do
 143                 var b = new FlatBuffer
 144                 b.add c
 145                 while iter.is_ok do
 146                         c = iter.item
 147                         if c != '_' and (c<'a' or c >'z') and (c<'0' or c>'9') then
 148                                 break
 149                         end
 150                         b.add c
 151                         iter.next
 152                 end
 153                 var token = new Nkw
 154                 token.text = b.to_s
 155                 tokens.add token
 156         end
 157
 158         fun trim
 159         do
 160                 while iter.is_ok and iter.item <= ' ' do
 161                         iter.next
 162                         pos += 1
 163                 end
 164         end
 165 end