1 /* This file is part of NIT ( http://www.nitlanguage.org ).
3 * Copyright 2008 Jean Privat <jean@pryen.org>
4 * Based on algorithms developped for ( http://www.sablecc.org/ ).
6 * Licensed under the Apache License, Version 2.0 (the "License");
7 * you may not use this file except in compliance with the License.
8 * You may obtain a copy of the License at
10 * http://www.apache.org/licenses/LICENSE-2.0
12 * Unless required by applicable law or agreed to in writing, software
13 * distributed under the License is distributed on an "AS IS" BASIS,
14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 * See the License for the specific language governing permissions and
16 * limitations under the License.
19 $ template make_lexer()
21 # The lexer extract NIT tokens from an input stream.
22 # It is better user with the Parser
25 var _token: nullable Token
30 # Name of the stream (as given to tokens)
31 readable var _filename: String
33 # Input stream where character are read
36 # Pushback buffer to store unread character
37 var _stream_buf: Buffer
39 # Number of character stored in the pushback buffer
42 # Current line number in the input stream
45 # Current column in the input stream
48 # Was the last character a cariage-return?
51 # If the end of stream?
52 var _eof: Bool = false
54 # Current working text read from the input stream
57 $ foreach {lexer_data/state}
58 # Constante state values
59 private fun state_${translate(@name,"ABCDEFGHIJKLMNOPQRSTUVWXYZ","abcdefghijklmnopqrstuvwxyz")}: Int do return @id end
62 # Create a new lexer for a stream (and a name)
63 init(stream: IStream, fname: String)
69 _stream_buf = new Buffer
74 # Give the next token (but do not consume it)
77 while _token == null do
80 return _token.as(not null)
83 # Give and consume the next token
87 while result == null do
91 return result.as(not null)
94 # Get a token, or null if it is discarded
95 private fun get_token: nullable Token
100 var start_line = _line
102 var accept_state = -1
103 var accept_token = -1
104 var accept_length = -1
108 var goto_table = _goto_table[_state]
109 var accept = _accept_table[_state]
138 var first_loop = true # aka until
139 while dfa_state < -1 or first_loop do
140 var old_state = dfa_state
141 if dfa_state < -1 then
142 old_state = -2 - dfa_state
147 var tmp0 = goto_table[old_state]
149 var high = tmp0.length - 1
152 var tmp1 = tmp0.intern_items
154 var middle = (low + high) / 2
155 var tmp2 = tmp1[middle].intern_items
159 else if c > tmp2[1] then
163 low = high + 1 # aka break
167 first_loop = false # aka until
177 if dfa_state >= 0 then
178 if accept[dfa_state] != -1 then
179 accept_state = dfa_state
180 accept_token = accept[dfa_state]
181 accept_length = text.length
186 if accept_state != -1 then
188 if accept_token == ${position()-1} then
189 var location = new Location(_filename, start_line + 1, accept_line + 1, start_pos + 1, accept_pos)
192 var token_text = text.substring(0, accept_length)
193 var token = new @ename.init_tk(token_text, location)
196 var token = new @ename.init_tk(location)
198 push_back(accept_length)
201 $ if {count(transition[@from!=@to])!=0}
202 var state_id = _state
203 $ foreach transition in {transition[@from!=@to]}
204 if state_id == ${/parser/lexer_data/state[@name=$transition/@from]/@id} then
205 _state = state_${translate(@to,"ABCDEFGHIJKLMNOPQRSTUVWXYZ","abcdefghijklmnopqrstuvwxyz")}
217 var location = new Location(_filename, start_line + 1, accept_line + 1, start_pos + 1, accept_pos)
218 if text.length > 0 then
219 var token = new PError.init_error("Unknown token: {text}", location)
222 var token = new EOF(location)
231 # Read the next character.
232 # The character is read from the stream of from the pushback buffer.
233 private fun get_char: Int
243 var res = _stream_buf[_stream_pos]
247 result = _stream.read_char
257 # Unread some characters.
258 # Unread characters are stored in the pushback buffer.
259 private fun push_back(accept_length: Int)
261 var length = _text.length
263 while i >= accept_length do
265 _stream_pos = _stream_pos + 1
266 _stream_buf[_stream_pos] = _text[i]
271 var _goto_table: Array[Array[Array[Array[Int]]]]
272 private fun build_goto_table
275 $ foreach {lexer_data/goto_table/state}
278 $ if {count(goto)!=0}
281 [@low, @high, @state][-sep ','-]
293 private fun nil_array: Array[Array[Int]]
295 return once new Array[Array[Int]]
298 var _accept_table: Array[Array[Int]]
299 private fun build_accept_table do
300 _accept_table = once [
301 $ foreach {lexer_data/accept_table/state}
303 [-foreach {i}-]${.}[-sep ','-][-end foreach-]