1 | /*
|
---|
2 | * 07/14/2006
|
---|
3 | *
|
---|
4 | * LuaTokenMaker.java - Scanner for the Lua programming language.
|
---|
5 | *
|
---|
6 | * This library is distributed under a modified BSD license. See the included
|
---|
7 | * RSyntaxTextArea.License.txt file for details.
|
---|
8 | */
|
---|
9 | package org.fife.ui.rsyntaxtextarea.modes;
|
---|
10 |
|
---|
11 | import java.io.*;
|
---|
12 | import javax.swing.text.Segment;
|
---|
13 |
|
---|
14 | import org.fife.ui.rsyntaxtextarea.*;
|
---|
15 |
|
---|
16 |
|
---|
17 | /**
|
---|
18 | * Scanner for the Lua programming language.<p>
|
---|
19 | *
|
---|
20 | * This implementation was created using
|
---|
21 | * <a href="http://www.jflex.de/">JFlex</a> 1.4.1; however, the generated file
|
---|
22 | * was modified for performance. Memory allocation needs to be almost
|
---|
23 | * completely removed to be competitive with the handwritten lexers (subclasses
|
---|
24 | * of <code>AbstractTokenMaker</code>, so this class has been modified so that
|
---|
25 | * Strings are never allocated (via yytext()), and the scanner never has to
|
---|
26 | * worry about refilling its buffer (needlessly copying chars around).
|
---|
27 | * We can achieve this because RText always scans exactly 1 line of tokens at a
|
---|
28 | * time, and hands the scanner this line as an array of characters (a Segment
|
---|
29 | * really). Since tokens contain pointers to char arrays instead of Strings
|
---|
30 | * holding their contents, there is no need for allocating new memory for
|
---|
31 | * Strings.<p>
|
---|
32 | *
|
---|
33 | * The actual algorithm generated for scanning has, of course, not been
|
---|
34 | * modified.<p>
|
---|
35 | *
|
---|
36 | * If you wish to regenerate this file yourself, keep in mind the following:
|
---|
37 | * <ul>
|
---|
38 | * <li>The generated <code>LuaTokenMaker.java</code> file will contain two
|
---|
39 | * definitions of both <code>zzRefill</code> and <code>yyreset</code>.
|
---|
40 | * You should hand-delete the second of each definition (the ones
|
---|
41 | * generated by the lexer), as these generated methods modify the input
|
---|
42 | * buffer, which we'll never have to do.</li>
|
---|
43 | * <li>You should also change the declaration/definition of zzBuffer to NOT
|
---|
44 | * be initialized. This is a needless memory allocation for us since we
|
---|
45 | * will be pointing the array somewhere else anyway.</li>
|
---|
46 | * <li>You should NOT call <code>yylex()</code> on the generated scanner
|
---|
47 | * directly; rather, you should use <code>getTokenList</code> as you would
|
---|
48 | * with any other <code>TokenMaker</code> instance.</li>
|
---|
49 | * </ul>
|
---|
50 | *
|
---|
51 | * @author Robert Futrell
|
---|
52 | * @version 0.4
|
---|
53 | *
|
---|
54 | */
|
---|
55 | %%
|
---|
56 |
|
---|
57 | %public
|
---|
58 | %class LuaTokenMaker
|
---|
59 | %extends AbstractJFlexTokenMaker
|
---|
60 | %implements TokenMaker
|
---|
61 | %unicode
|
---|
62 | %type org.fife.ui.rsyntaxtextarea.Token
|
---|
63 |
|
---|
64 |
|
---|
65 | %{
|
---|
66 |
|
---|
67 |
|
---|
68 | /**
|
---|
69 | * Constructor. This must be here because JFlex does not generate a
|
---|
70 | * no-parameter constructor.
|
---|
71 | */
|
---|
72 | public LuaTokenMaker() {
|
---|
73 | }
|
---|
74 |
|
---|
75 |
|
---|
76 | /**
|
---|
77 | * Adds the token specified to the current linked list of tokens.
|
---|
78 | *
|
---|
79 | * @param tokenType The token's type.
|
---|
80 | */
|
---|
81 | private void addToken(int tokenType) {
|
---|
82 | addToken(zzStartRead, zzMarkedPos-1, tokenType);
|
---|
83 | }
|
---|
84 |
|
---|
85 |
|
---|
86 | /**
|
---|
87 | * Adds the token specified to the current linked list of tokens.
|
---|
88 | *
|
---|
89 | * @param tokenType The token's type.
|
---|
90 | */
|
---|
91 | private void addToken(int start, int end, int tokenType) {
|
---|
92 | int so = start + offsetShift;
|
---|
93 | addToken(zzBuffer, start,end, tokenType, so);
|
---|
94 | }
|
---|
95 |
|
---|
96 |
|
---|
97 | /**
|
---|
98 | * Adds the token specified to the current linked list of tokens.
|
---|
99 | *
|
---|
100 | * @param array The character array.
|
---|
101 | * @param start The starting offset in the array.
|
---|
102 | * @param end The ending offset in the array.
|
---|
103 | * @param tokenType The token's type.
|
---|
104 | * @param startOffset The offset in the document at which this token
|
---|
105 | * occurs.
|
---|
106 | */
|
---|
107 | public void addToken(char[] array, int start, int end, int tokenType, int startOffset) {
|
---|
108 | super.addToken(array, start,end, tokenType, startOffset);
|
---|
109 | zzStartRead = zzMarkedPos;
|
---|
110 | }
|
---|
111 |
|
---|
112 |
|
---|
113 | /**
|
---|
114 | * Returns the text to place at the beginning and end of a
|
---|
115 | * line to "comment" it in a this programming language.
|
---|
116 | *
|
---|
117 | * @return The start and end strings to add to a line to "comment"
|
---|
118 | * it out.
|
---|
119 | */
|
---|
120 | public String[] getLineCommentStartAndEnd() {
|
---|
121 | return new String[] { "--", null };
|
---|
122 | }
|
---|
123 |
|
---|
124 |
|
---|
125 | /**
|
---|
126 | * Returns the first token in the linked list of tokens generated
|
---|
127 | * from <code>text</code>. This method must be implemented by
|
---|
128 | * subclasses so they can correctly implement syntax highlighting.
|
---|
129 | *
|
---|
130 | * @param text The text from which to get tokens.
|
---|
131 | * @param initialTokenType The token type we should start with.
|
---|
132 | * @param startOffset The offset into the document at which
|
---|
133 | * <code>text</code> starts.
|
---|
134 | * @return The first <code>Token</code> in a linked list representing
|
---|
135 | * the syntax highlighted text.
|
---|
136 | */
|
---|
137 | public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
|
---|
138 |
|
---|
139 | resetTokenList();
|
---|
140 | this.offsetShift = -text.offset + startOffset;
|
---|
141 |
|
---|
142 | // Start off in the proper state.
|
---|
143 | int state = Token.NULL;
|
---|
144 | switch (initialTokenType) {
|
---|
145 | case Token.COMMENT_MULTILINE:
|
---|
146 | state = MLC;
|
---|
147 | start = text.offset;
|
---|
148 | break;
|
---|
149 | case Token.LITERAL_STRING_DOUBLE_QUOTE:
|
---|
150 | state = LONGSTRING;
|
---|
151 | start = text.offset;
|
---|
152 | break;
|
---|
153 | default:
|
---|
154 | state = Token.NULL;
|
---|
155 | }
|
---|
156 |
|
---|
157 | s = text;
|
---|
158 | try {
|
---|
159 | yyreset(zzReader);
|
---|
160 | yybegin(state);
|
---|
161 | return yylex();
|
---|
162 | } catch (IOException ioe) {
|
---|
163 | ioe.printStackTrace();
|
---|
164 | return new DefaultToken();
|
---|
165 | }
|
---|
166 |
|
---|
167 | }
|
---|
168 |
|
---|
169 |
|
---|
170 | /**
|
---|
171 | * Refills the input buffer.
|
---|
172 | *
|
---|
173 | * @return <code>true</code> if EOF was reached, otherwise
|
---|
174 | * <code>false</code>.
|
---|
175 | * @exception IOException if any I/O-Error occurs.
|
---|
176 | */
|
---|
177 | private boolean zzRefill() throws java.io.IOException {
|
---|
178 | return zzCurrentPos>=s.offset+s.count;
|
---|
179 | }
|
---|
180 |
|
---|
181 |
|
---|
182 | /**
|
---|
183 | * Resets the scanner to read from a new input stream.
|
---|
184 | * Does not close the old reader.
|
---|
185 | *
|
---|
186 | * All internal variables are reset, the old input stream
|
---|
187 | * <b>cannot</b> be reused (internal buffer is discarded and lost).
|
---|
188 | * Lexical state is set to <tt>YY_INITIAL</tt>.
|
---|
189 | *
|
---|
190 | * @param reader the new input stream
|
---|
191 | */
|
---|
192 | public final void yyreset(java.io.Reader reader) throws java.io.IOException {
|
---|
193 | // 's' has been updated.
|
---|
194 | zzBuffer = s.array;
|
---|
195 | /*
|
---|
196 | * We replaced the line below with the two below it because zzRefill
|
---|
197 | * no longer "refills" the buffer (since the way we do it, it's always
|
---|
198 | * "full" the first time through, since it points to the segment's
|
---|
199 | * array). So, we assign zzEndRead here.
|
---|
200 | */
|
---|
201 | //zzStartRead = zzEndRead = s.offset;
|
---|
202 | zzStartRead = s.offset;
|
---|
203 | zzEndRead = zzStartRead + s.count - 1;
|
---|
204 | zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
|
---|
205 | zzLexicalState = YYINITIAL;
|
---|
206 | zzReader = reader;
|
---|
207 | zzAtBOL = true;
|
---|
208 | zzAtEOF = false;
|
---|
209 | }
|
---|
210 |
|
---|
211 |
|
---|
212 | %}
|
---|
213 |
|
---|
214 | Letter = [A-Za-z_]
|
---|
215 | Digit = [0-9]
|
---|
216 |
|
---|
217 | LineTerminator = (\n)
|
---|
218 | WhiteSpace = ([ \t\f])
|
---|
219 |
|
---|
220 | UnclosedCharLiteral = ([\']([^\'\n]|"\\'")*)
|
---|
221 | CharLiteral = ({UnclosedCharLiteral}"'")
|
---|
222 | UnclosedStringLiteral = ([\"]([^\"\n]|"\\\"")*)
|
---|
223 | StringLiteral = ({UnclosedStringLiteral}[\"])
|
---|
224 | LongStringBegin = ("[[")
|
---|
225 | LongStringEnd = ("]]")
|
---|
226 |
|
---|
227 | LineCommentBegin = ("--")
|
---|
228 | MLCBegin = ({LineCommentBegin}{LongStringBegin})
|
---|
229 |
|
---|
230 | Number = ( "."? {Digit} ({Digit}|".")* ([eE][+-]?)? ({Letter}|{Digit})* )
|
---|
231 | BooleanLiteral = ("true"|"false")
|
---|
232 |
|
---|
233 | Separator = ([\(\)\{\}\[\]\]])
|
---|
234 | Separator2 = ([\;:,.])
|
---|
235 |
|
---|
236 | ArithmeticOperator = ("+"|"-"|"*"|"/"|"^"|"%")
|
---|
237 | RelationalOperator = ("<"|">"|"<="|">="|"=="|"~=")
|
---|
238 | LogicalOperator = ("and"|"or"|"not"|"#")
|
---|
239 | ConcatenationOperator = ("..")
|
---|
240 | Elipsis = ({ConcatenationOperator}".")
|
---|
241 | Operator = ({ArithmeticOperator}|{RelationalOperator}|{LogicalOperator}|{ConcatenationOperator}|{Elipsis})
|
---|
242 |
|
---|
243 | Identifier = ({Letter}({Letter}|{Digit})*)
|
---|
244 |
|
---|
245 |
|
---|
246 | %state MLC
|
---|
247 | %state LONGSTRING
|
---|
248 | %state LINECOMMENT
|
---|
249 |
|
---|
250 |
|
---|
251 | %%
|
---|
252 |
|
---|
253 | /* Keywords */
|
---|
254 | <YYINITIAL> "break" { addToken(Token.RESERVED_WORD); }
|
---|
255 | <YYINITIAL> "do" { addToken(Token.RESERVED_WORD); }
|
---|
256 | <YYINITIAL> "else" { addToken(Token.RESERVED_WORD); }
|
---|
257 | <YYINITIAL> "elseif" { addToken(Token.RESERVED_WORD); }
|
---|
258 | <YYINITIAL> "end" { addToken(Token.RESERVED_WORD); }
|
---|
259 | <YYINITIAL> "for" { addToken(Token.RESERVED_WORD); }
|
---|
260 | <YYINITIAL> "function" { addToken(Token.RESERVED_WORD); }
|
---|
261 | <YYINITIAL> "if" { addToken(Token.RESERVED_WORD); }
|
---|
262 | <YYINITIAL> "local" { addToken(Token.RESERVED_WORD); }
|
---|
263 | <YYINITIAL> "nil" { addToken(Token.RESERVED_WORD); }
|
---|
264 | <YYINITIAL> "repeat" { addToken(Token.RESERVED_WORD); }
|
---|
265 | <YYINITIAL> "return" { addToken(Token.RESERVED_WORD); }
|
---|
266 | <YYINITIAL> "then" { addToken(Token.RESERVED_WORD); }
|
---|
267 | <YYINITIAL> "until" { addToken(Token.RESERVED_WORD); }
|
---|
268 | <YYINITIAL> "while" { addToken(Token.RESERVED_WORD); }
|
---|
269 |
|
---|
270 | /* Data types. */
|
---|
271 | <YYINITIAL> "<number>" { addToken(Token.DATA_TYPE); }
|
---|
272 | <YYINITIAL> "<name>" { addToken(Token.DATA_TYPE); }
|
---|
273 | <YYINITIAL> "<string>" { addToken(Token.DATA_TYPE); }
|
---|
274 | <YYINITIAL> "<eof>" { addToken(Token.DATA_TYPE); }
|
---|
275 | <YYINITIAL> "NULL" { addToken(Token.DATA_TYPE); }
|
---|
276 |
|
---|
277 | /* Functions. */
|
---|
278 | <YYINITIAL> "_G" { addToken(Token.FUNCTION); }
|
---|
279 | <YYINITIAL> "_VERSION" { addToken(Token.FUNCTION); }
|
---|
280 | <YYINITIAL> "assert" { addToken(Token.FUNCTION); }
|
---|
281 | <YYINITIAL> "collectgarbage" { addToken(Token.FUNCTION); }
|
---|
282 | <YYINITIAL> "dofile" { addToken(Token.FUNCTION); }
|
---|
283 | <YYINITIAL> "error" { addToken(Token.FUNCTION); }
|
---|
284 | <YYINITIAL> "getfenv" { addToken(Token.FUNCTION); }
|
---|
285 | <YYINITIAL> "getmetatable" { addToken(Token.FUNCTION); }
|
---|
286 | <YYINITIAL> "ipairs" { addToken(Token.FUNCTION); }
|
---|
287 | <YYINITIAL> "load" { addToken(Token.FUNCTION); }
|
---|
288 | <YYINITIAL> "loadfile" { addToken(Token.FUNCTION); }
|
---|
289 | <YYINITIAL> "loadstring" { addToken(Token.FUNCTION); }
|
---|
290 | <YYINITIAL> "module" { addToken(Token.FUNCTION); }
|
---|
291 | <YYINITIAL> "next" { addToken(Token.FUNCTION); }
|
---|
292 | <YYINITIAL> "pairs" { addToken(Token.FUNCTION); }
|
---|
293 | <YYINITIAL> "pcall" { addToken(Token.FUNCTION); }
|
---|
294 | <YYINITIAL> "print" { addToken(Token.FUNCTION); }
|
---|
295 | <YYINITIAL> "rawequal" { addToken(Token.FUNCTION); }
|
---|
296 | <YYINITIAL> "rawget" { addToken(Token.FUNCTION); }
|
---|
297 | <YYINITIAL> "rawset" { addToken(Token.FUNCTION); }
|
---|
298 | <YYINITIAL> "require" { addToken(Token.FUNCTION); }
|
---|
299 | <YYINITIAL> "select" { addToken(Token.FUNCTION); }
|
---|
300 | <YYINITIAL> "setfenv" { addToken(Token.FUNCTION); }
|
---|
301 | <YYINITIAL> "setmetatable" { addToken(Token.FUNCTION); }
|
---|
302 | <YYINITIAL> "tonumber" { addToken(Token.FUNCTION); }
|
---|
303 | <YYINITIAL> "tostring" { addToken(Token.FUNCTION); }
|
---|
304 | <YYINITIAL> "type" { addToken(Token.FUNCTION); }
|
---|
305 | <YYINITIAL> "unpack" { addToken(Token.FUNCTION); }
|
---|
306 | <YYINITIAL> "xpcall" { addToken(Token.FUNCTION); }
|
---|
307 |
|
---|
308 | /* Booleans. */
|
---|
309 | <YYINITIAL> {BooleanLiteral} { addToken(Token.LITERAL_BOOLEAN); }
|
---|
310 |
|
---|
311 |
|
---|
312 | <YYINITIAL> {
|
---|
313 |
|
---|
314 | {LineTerminator} { addNullToken(); return firstToken; }
|
---|
315 |
|
---|
316 | {WhiteSpace}+ { addToken(Token.WHITESPACE); }
|
---|
317 |
|
---|
318 | /* String/Character literals. */
|
---|
319 | {CharLiteral} { addToken(Token.LITERAL_CHAR); }
|
---|
320 | {UnclosedCharLiteral} { addToken(Token.ERROR_CHAR); addNullToken(); return firstToken; }
|
---|
321 | {StringLiteral} { addToken(Token.LITERAL_STRING_DOUBLE_QUOTE); }
|
---|
322 | {UnclosedStringLiteral} { addToken(Token.ERROR_STRING_DOUBLE); addNullToken(); return firstToken; }
|
---|
323 | {LongStringBegin} { start = zzMarkedPos-2; yybegin(LONGSTRING); }
|
---|
324 |
|
---|
325 | /* Comment literals. */
|
---|
326 | {MLCBegin} { start = zzMarkedPos-4; yybegin(MLC); }
|
---|
327 | {LineCommentBegin} { start = zzMarkedPos-2; yybegin(LINECOMMENT); }
|
---|
328 |
|
---|
329 | /* Separators. */
|
---|
330 | {Separator} { addToken(Token.SEPARATOR); }
|
---|
331 | {Separator2} { addToken(Token.IDENTIFIER); }
|
---|
332 |
|
---|
333 | /* Operators. */
|
---|
334 | {Operator} { addToken(Token.OPERATOR); }
|
---|
335 |
|
---|
336 | /* Identifiers - Comes after Operators for "and", "not" and "or". */
|
---|
337 | {Identifier} { addToken(Token.IDENTIFIER); }
|
---|
338 |
|
---|
339 | /* Numbers */
|
---|
340 | {Number} { addToken(Token.LITERAL_NUMBER_FLOAT); }
|
---|
341 |
|
---|
342 | /* Ended with a line not in a string or comment. */
|
---|
343 | <<EOF>> { addNullToken(); return firstToken; }
|
---|
344 |
|
---|
345 | /* Catch any other (unhandled) characters. */
|
---|
346 | . { addToken(Token.IDENTIFIER); }
|
---|
347 |
|
---|
348 | }
|
---|
349 |
|
---|
350 |
|
---|
351 | <MLC> {
|
---|
352 | [^\n\]]+ {}
|
---|
353 | \n { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); return firstToken; }
|
---|
354 | {LongStringEnd} { yybegin(YYINITIAL); addToken(start,zzStartRead+1, Token.COMMENT_MULTILINE); }
|
---|
355 | \] {}
|
---|
356 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); return firstToken; }
|
---|
357 | }
|
---|
358 |
|
---|
359 |
|
---|
360 | <LONGSTRING> {
|
---|
361 | [^\n\]]+ {}
|
---|
362 | \n { addToken(start,zzStartRead-1, Token.LITERAL_STRING_DOUBLE_QUOTE); return firstToken; }
|
---|
363 | {LongStringEnd} { yybegin(YYINITIAL); addToken(start,zzStartRead+1, Token.LITERAL_STRING_DOUBLE_QUOTE); }
|
---|
364 | \] {}
|
---|
365 | <<EOF>> { addToken(start,zzStartRead-1, Token.LITERAL_STRING_DOUBLE_QUOTE); return firstToken; }
|
---|
366 | }
|
---|
367 |
|
---|
368 |
|
---|
369 | <LINECOMMENT> {
|
---|
370 | [^\n]+ {}
|
---|
371 | \n { addToken(start,zzStartRead-1, Token.COMMENT_EOL); return firstToken; }
|
---|
372 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_EOL); return firstToken; }
|
---|
373 | }
|
---|