1 | /*
|
---|
2 | * 01/21/2011
|
---|
3 | *
|
---|
4 | * MxmlTokenMaker.java - Generates tokens for MXML syntax highlighting.
|
---|
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 MXML.
|
---|
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>MXMLTokenMaker.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 0.5
|
---|
53 | *
|
---|
54 | */
|
---|
55 | %%
|
---|
56 |
|
---|
57 | %public
|
---|
58 | %class MxmlTokenMaker
|
---|
59 | %extends AbstractMarkupTokenMaker
|
---|
60 | %unicode
|
---|
61 | %type org.fife.ui.rsyntaxtextarea.Token
|
---|
62 |
|
---|
63 |
|
---|
64 | %{
|
---|
65 |
|
---|
66 | /**
|
---|
67 | * Type specific to JSPTokenMaker denoting a line ending with an unclosed
|
---|
68 | * double-quote attribute.
|
---|
69 | */
|
---|
70 | public static final int INTERNAL_ATTR_DOUBLE = -1;
|
---|
71 |
|
---|
72 |
|
---|
73 | /**
|
---|
74 | * Type specific to JSPTokenMaker denoting a line ending with an unclosed
|
---|
75 | * single-quote attribute.
|
---|
76 | */
|
---|
77 | public static final int INTERNAL_ATTR_SINGLE = -2;
|
---|
78 |
|
---|
79 |
|
---|
80 | /**
|
---|
81 | * Token type specific to this class; this signals that the user has
|
---|
82 | * ended a line with an unclosed XML tag; thus a new line is beginning
|
---|
83 | * still inside of the tag.
|
---|
84 | */
|
---|
85 | public static final int INTERNAL_INTAG = -3;
|
---|
86 |
|
---|
87 | /**
|
---|
88 | * Token type specific to this class; this signals that the user has
|
---|
89 | * ended a line with an unclosed Script tag; thus a new line is beginning
|
---|
90 | * still inside of the tag.
|
---|
91 | */
|
---|
92 | public static final int INTERNAL_INTAG_SCRIPT = -4;
|
---|
93 |
|
---|
94 | /**
|
---|
95 | * Token type specific to this class; this signals that the user has
|
---|
96 | * ended a line in the middle of a double-quoted attribute in a Script
|
---|
97 | * tag.
|
---|
98 | */
|
---|
99 | public static final int INTERNAL_ATTR_DOUBLE_QUOTE_SCRIPT = -5;
|
---|
100 |
|
---|
101 | /**
|
---|
102 | * Token type specific to this class; this signals that the user has
|
---|
103 | * ended a line in the middle of a single-quoted attribute in a Script
|
---|
104 | * tag.
|
---|
105 | */
|
---|
106 | public static final int INTERNAL_ATTR_SINGLE_QUOTE_SCRIPT = -6;
|
---|
107 |
|
---|
108 | /**
|
---|
109 | * Token type specific to this class; this signals that the user has
|
---|
110 | * ended a line in an ActionScript code block (text content inside a
|
---|
111 | * Script tag).
|
---|
112 | */
|
---|
113 | public static final int INTERNAL_IN_AS = -7;
|
---|
114 |
|
---|
115 | /**
|
---|
116 | * Token type specific to this class; this signals that the user has
|
---|
117 | * ended a line in an MLC in an ActionScript code block (text content
|
---|
118 | * inside a Script tag).
|
---|
119 | */
|
---|
120 | public static final int INTERNAL_IN_AS_MLC = -8;
|
---|
121 |
|
---|
122 | /**
|
---|
123 | * Whether closing markup tags are automatically completed for HTML.
|
---|
124 | */
|
---|
125 | private static boolean completeCloseTags;
|
---|
126 |
|
---|
127 |
|
---|
128 | /**
|
---|
129 | * Constructor. This must be here because JFlex does not generate a
|
---|
130 | * no-parameter constructor.
|
---|
131 | */
|
---|
132 | public MxmlTokenMaker() {
|
---|
133 | }
|
---|
134 |
|
---|
135 |
|
---|
136 | static {
|
---|
137 | completeCloseTags = true;
|
---|
138 | }
|
---|
139 |
|
---|
140 |
|
---|
141 | /**
|
---|
142 | * Adds the token specified to the current linked list of tokens as an
|
---|
143 | * "end token;" that is, at <code>zzMarkedPos</code>.
|
---|
144 | *
|
---|
145 | * @param tokenType The token's type.
|
---|
146 | */
|
---|
147 | private void addEndToken(int tokenType) {
|
---|
148 | addToken(zzMarkedPos,zzMarkedPos, tokenType);
|
---|
149 | }
|
---|
150 |
|
---|
151 |
|
---|
152 | /**
|
---|
153 | * Adds the token specified to the current linked list of tokens.
|
---|
154 | *
|
---|
155 | * @param tokenType The token's type.
|
---|
156 | * @see #addToken(int, int, int)
|
---|
157 | */
|
---|
158 | private void addHyperlinkToken(int start, int end, int tokenType) {
|
---|
159 | int so = start + offsetShift;
|
---|
160 | addToken(zzBuffer, start,end, tokenType, so, true);
|
---|
161 | }
|
---|
162 |
|
---|
163 |
|
---|
164 | /**
|
---|
165 | * Adds the token specified to the current linked list of tokens.
|
---|
166 | *
|
---|
167 | * @param tokenType The token's type.
|
---|
168 | */
|
---|
169 | private void addToken(int tokenType) {
|
---|
170 | addToken(zzStartRead, zzMarkedPos-1, tokenType);
|
---|
171 | }
|
---|
172 |
|
---|
173 |
|
---|
174 | /**
|
---|
175 | * Adds the token specified to the current linked list of tokens.
|
---|
176 | *
|
---|
177 | * @param tokenType The token's type.
|
---|
178 | */
|
---|
179 | private void addToken(int start, int end, int tokenType) {
|
---|
180 | int so = start + offsetShift;
|
---|
181 | addToken(zzBuffer, start,end, tokenType, so);
|
---|
182 | }
|
---|
183 |
|
---|
184 |
|
---|
185 | /**
|
---|
186 | * Adds the token specified to the current linked list of tokens.
|
---|
187 | *
|
---|
188 | * @param array The character array.
|
---|
189 | * @param start The starting offset in the array.
|
---|
190 | * @param end The ending offset in the array.
|
---|
191 | * @param tokenType The token's type.
|
---|
192 | * @param startOffset The offset in the document at which this token
|
---|
193 | * occurs.
|
---|
194 | * @param hyperlink Whether this token is a hyperlink.
|
---|
195 | */
|
---|
196 | public void addToken(char[] array, int start, int end, int tokenType,
|
---|
197 | int startOffset, boolean hyperlink) {
|
---|
198 | super.addToken(array, start,end, tokenType, startOffset, hyperlink);
|
---|
199 | zzStartRead = zzMarkedPos;
|
---|
200 | }
|
---|
201 |
|
---|
202 |
|
---|
203 | /**
|
---|
204 | * Returns whether markup close tags should be completed. For XML, the
|
---|
205 | * default value is <code>true</code>.
|
---|
206 | *
|
---|
207 | * @return Whether closing markup tags are completed.
|
---|
208 | * @see #setCompleteCloseTags(boolean)
|
---|
209 | */
|
---|
210 | public boolean getCompleteCloseTags() {
|
---|
211 | return completeCloseTags;
|
---|
212 | }
|
---|
213 |
|
---|
214 |
|
---|
215 | /**
|
---|
216 | * Static version of {@link #getCompleteCloseTags()}. This hack is
|
---|
217 | * unfortunately needed for applications to be able to query this value
|
---|
218 | * without instantiating this class.
|
---|
219 | *
|
---|
220 | * @return Whether closing markup tags are completed.
|
---|
221 | * @see #setCompleteCloseTags(boolean)
|
---|
222 | */
|
---|
223 | public static boolean getCompleteCloseMarkupTags() {
|
---|
224 | return completeCloseTags;
|
---|
225 | }
|
---|
226 |
|
---|
227 |
|
---|
228 | /**
|
---|
229 | * Always returns <tt>false</tt>, as you never want "mark occurrences"
|
---|
230 | * working in XML files.
|
---|
231 | *
|
---|
232 | * @param type The token type.
|
---|
233 | * @return Whether tokens of this type should have "mark occurrences"
|
---|
234 | * enabled.
|
---|
235 | */
|
---|
236 | public boolean getMarkOccurrencesOfTokenType(int type) {
|
---|
237 | return false;
|
---|
238 | }
|
---|
239 |
|
---|
240 |
|
---|
241 | /**
|
---|
242 | * Returns the first token in the linked list of tokens generated
|
---|
243 | * from <code>text</code>. This method must be implemented by
|
---|
244 | * subclasses so they can correctly implement syntax highlighting.
|
---|
245 | *
|
---|
246 | * @param text The text from which to get tokens.
|
---|
247 | * @param initialTokenType The token type we should start with.
|
---|
248 | * @param startOffset The offset into the document at which
|
---|
249 | * <code>text</code> starts.
|
---|
250 | * @return The first <code>Token</code> in a linked list representing
|
---|
251 | * the syntax highlighted text.
|
---|
252 | */
|
---|
253 | public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
|
---|
254 |
|
---|
255 | resetTokenList();
|
---|
256 | this.offsetShift = -text.offset + startOffset;
|
---|
257 |
|
---|
258 | // Start off in the proper state.
|
---|
259 | int state = Token.NULL;
|
---|
260 | switch (initialTokenType) {
|
---|
261 | case Token.COMMENT_MULTILINE:
|
---|
262 | state = COMMENT;
|
---|
263 | start = text.offset;
|
---|
264 | break;
|
---|
265 | case Token.FUNCTION:
|
---|
266 | state = DTD;
|
---|
267 | start = text.offset;
|
---|
268 | break;
|
---|
269 | case INTERNAL_ATTR_DOUBLE:
|
---|
270 | state = INATTR_DOUBLE;
|
---|
271 | start = text.offset;
|
---|
272 | break;
|
---|
273 | case INTERNAL_ATTR_SINGLE:
|
---|
274 | state = INATTR_SINGLE;
|
---|
275 | start = text.offset;
|
---|
276 | break;
|
---|
277 | case Token.MARKUP_PROCESSING_INSTRUCTION:
|
---|
278 | state = PI;
|
---|
279 | start = text.offset;
|
---|
280 | break;
|
---|
281 | case INTERNAL_INTAG:
|
---|
282 | state = INTAG;
|
---|
283 | start = text.offset;
|
---|
284 | break;
|
---|
285 | case INTERNAL_INTAG_SCRIPT:
|
---|
286 | state = INTAG_SCRIPT;
|
---|
287 | start = text.offset;
|
---|
288 | break;
|
---|
289 | case INTERNAL_ATTR_DOUBLE_QUOTE_SCRIPT:
|
---|
290 | state = INATTR_DOUBLE_SCRIPT;
|
---|
291 | start = text.offset;
|
---|
292 | break;
|
---|
293 | case INTERNAL_ATTR_SINGLE_QUOTE_SCRIPT:
|
---|
294 | state = INATTR_SINGLE_SCRIPT;
|
---|
295 | start = text.offset;
|
---|
296 | break;
|
---|
297 | case INTERNAL_IN_AS:
|
---|
298 | state = AS;
|
---|
299 | start = text.offset;
|
---|
300 | break;
|
---|
301 | case INTERNAL_IN_AS_MLC:
|
---|
302 | state = AS_MLC;
|
---|
303 | start = text.offset;
|
---|
304 | break;
|
---|
305 | case Token.MARKUP_CDATA:
|
---|
306 | state = CDATA;
|
---|
307 | start = text.offset;
|
---|
308 | break;
|
---|
309 | default:
|
---|
310 | state = Token.NULL;
|
---|
311 | }
|
---|
312 |
|
---|
313 | s = text;
|
---|
314 | try {
|
---|
315 | yyreset(zzReader);
|
---|
316 | yybegin(state);
|
---|
317 | return yylex();
|
---|
318 | } catch (IOException ioe) {
|
---|
319 | ioe.printStackTrace();
|
---|
320 | return new DefaultToken();
|
---|
321 | }
|
---|
322 |
|
---|
323 | }
|
---|
324 |
|
---|
325 |
|
---|
326 | /**
|
---|
327 | * Sets whether markup close tags should be completed.
|
---|
328 | *
|
---|
329 | * @param complete Whether closing markup tags are completed.
|
---|
330 | * @see #getCompleteCloseTags()
|
---|
331 | */
|
---|
332 | public static void setCompleteCloseTags(boolean complete) {
|
---|
333 | completeCloseTags = complete;
|
---|
334 | }
|
---|
335 |
|
---|
336 |
|
---|
337 | /**
|
---|
338 | * Refills the input buffer.
|
---|
339 | *
|
---|
340 | * @return <code>true</code> if EOF was reached, otherwise
|
---|
341 | * <code>false</code>.
|
---|
342 | */
|
---|
343 | private boolean zzRefill() {
|
---|
344 | return zzCurrentPos>=s.offset+s.count;
|
---|
345 | }
|
---|
346 |
|
---|
347 |
|
---|
348 | /**
|
---|
349 | * Resets the scanner to read from a new input stream.
|
---|
350 | * Does not close the old reader.
|
---|
351 | *
|
---|
352 | * All internal variables are reset, the old input stream
|
---|
353 | * <b>cannot</b> be reused (internal buffer is discarded and lost).
|
---|
354 | * Lexical state is set to <tt>YY_INITIAL</tt>.
|
---|
355 | *
|
---|
356 | * @param reader the new input stream
|
---|
357 | */
|
---|
358 | public final void yyreset(java.io.Reader reader) {
|
---|
359 | // 's' has been updated.
|
---|
360 | zzBuffer = s.array;
|
---|
361 | /*
|
---|
362 | * We replaced the line below with the two below it because zzRefill
|
---|
363 | * no longer "refills" the buffer (since the way we do it, it's always
|
---|
364 | * "full" the first time through, since it points to the segment's
|
---|
365 | * array). So, we assign zzEndRead here.
|
---|
366 | */
|
---|
367 | //zzStartRead = zzEndRead = s.offset;
|
---|
368 | zzStartRead = s.offset;
|
---|
369 | zzEndRead = zzStartRead + s.count - 1;
|
---|
370 | zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
|
---|
371 | zzLexicalState = YYINITIAL;
|
---|
372 | zzReader = reader;
|
---|
373 | zzAtBOL = true;
|
---|
374 | zzAtEOF = false;
|
---|
375 | }
|
---|
376 |
|
---|
377 |
|
---|
378 | %}
|
---|
379 |
|
---|
380 | /* XML macros (and some building-block macros used by AS macros). */
|
---|
381 | Letter = [A-Za-z]
|
---|
382 | NonzeroDigit = [1-9]
|
---|
383 | Digit = ("0"|{NonzeroDigit})
|
---|
384 | LetterOrUnderscore = ({Letter}|"_")
|
---|
385 | NameStartChar = ({Letter}|[\:])
|
---|
386 | NameChar = ({NameStartChar}|[\-\.]|{Digit})
|
---|
387 | TagName = ({NameStartChar}{NameChar}*)
|
---|
388 | Whitespace = ([ \t\f])
|
---|
389 | LineTerminator = ([\n])
|
---|
390 | Identifier = ([^ \t\n<&]+)
|
---|
391 | AmperItem = ([&][^; \t]*[;]?)
|
---|
392 | InTagIdentifier = ([^ \t\n\"\'=\/>]+)
|
---|
393 | CDataBegin = ("<![CDATA[")
|
---|
394 | CDataEnd = ("]]>")
|
---|
395 |
|
---|
396 |
|
---|
397 | /* ActionScript macros. */
|
---|
398 | HexDigit = ({Digit}|[A-Fa-f])
|
---|
399 | OctalDigit = ([0-7])
|
---|
400 | AnyCharacterButApostropheOrBackSlash = ([^\\'])
|
---|
401 | AnyCharacterButDoubleQuoteOrBackSlash = ([^\\\"\n])
|
---|
402 | EscapedSourceCharacter = ("u"{HexDigit}{HexDigit}{HexDigit}{HexDigit})
|
---|
403 | Escape = ("\\"(([btnfr\"'\\])|([0123]{OctalDigit}?{OctalDigit}?)|({OctalDigit}{OctalDigit}?)|{EscapedSourceCharacter}))
|
---|
404 | NonSeparator = ([^\t\f\r\n\ \(\)\{\}\[\]\;\,\.\=\>\<\!\~\?\:\+\-\*\/\&\|\^\%\"\']|"#"|"\\")
|
---|
405 | IdentifierStart = ({LetterOrUnderscore}|"$")
|
---|
406 | IdentifierPart = ({IdentifierStart}|{Digit}|("\\"{EscapedSourceCharacter}))
|
---|
407 |
|
---|
408 | AS_CharLiteral = ([\']({AnyCharacterButApostropheOrBackSlash}|{Escape})*[\'])
|
---|
409 | AS_UnclosedCharLiteral = ([\']([\\].|[^\\\'])*[^\']?)
|
---|
410 | AS_ErrorCharLiteral = ({AS_UnclosedCharLiteral}[\'])
|
---|
411 | AS_StringLiteral = ([\"]({AnyCharacterButDoubleQuoteOrBackSlash}|{Escape})*[\"])
|
---|
412 | AS_UnclosedStringLiteral = ([\"]([\\].|[^\\\"])*[^\"]?)
|
---|
413 | AS_ErrorStringLiteral = ({AS_UnclosedStringLiteral}[\"])
|
---|
414 |
|
---|
415 | AS_MLCBegin = ("/*")
|
---|
416 | AS_MLCEnd = ("*/")
|
---|
417 | AS_LineCommentBegin = ("//")
|
---|
418 | IntegerHelper1 = (({NonzeroDigit}{Digit}*)|"0")
|
---|
419 | IntegerHelper2 = ("0"(([xX]{HexDigit}+)|({OctalDigit}*)))
|
---|
420 | AS_IntegerLiteral = ({IntegerHelper1}[lL]?)
|
---|
421 | AS_HexLiteral = ({IntegerHelper2}[lL]?)
|
---|
422 | FloatHelper1 = ([fFdD]?)
|
---|
423 | FloatHelper2 = ([eE][+-]?{Digit}+{FloatHelper1})
|
---|
424 | FloatLiteral1 = ({Digit}+"."({FloatHelper1}|{FloatHelper2}|{Digit}+({FloatHelper1}|{FloatHelper2})))
|
---|
425 | FloatLiteral2 = ("."{Digit}+({FloatHelper1}|{FloatHelper2}))
|
---|
426 | FloatLiteral3 = ({Digit}+{FloatHelper2})
|
---|
427 | AS_FloatLiteral = ({FloatLiteral1}|{FloatLiteral2}|{FloatLiteral3}|({Digit}+[fFdD]))
|
---|
428 | AS_ErrorNumberFormat = (({AS_IntegerLiteral}|{AS_HexLiteral}|{AS_FloatLiteral}){NonSeparator}+)
|
---|
429 | AS_BooleanLiteral = ("true"|"false")
|
---|
430 |
|
---|
431 | AS_Separator = ([\(\)\{\}\[\]])
|
---|
432 | AS_Separator2 = ([\;,.])
|
---|
433 |
|
---|
434 | NonAssignmentOperator = ("+"|"-"|"<="|"^"|"++"|"<"|"*"|">="|"%"|"--"|">"|"/"|"!="|"?"|">>"|"!"|"&"|"=="|":"|">>"|"~"|"|"|"&&"|">>>")
|
---|
435 | AssignmentOperator = ("="|"-="|"*="|"/="|"|="|"&="|"^="|"+="|"%="|"<<="|">>="|">>>=")
|
---|
436 | AS_Operator = ({NonAssignmentOperator}|{AssignmentOperator})
|
---|
437 |
|
---|
438 | AS_Identifier = ({IdentifierStart}{IdentifierPart}*)
|
---|
439 | AS_ErrorIdentifier = ({NonSeparator}+)
|
---|
440 | AS_EndScriptTag = ("</"({NameStartChar}{NameChar}*":")?"Script"{Whitespace}*">")
|
---|
441 |
|
---|
442 | URLGenDelim = ([:\/\?#\[\]@])
|
---|
443 | URLSubDelim = ([\!\$&'\(\)\*\+,;=])
|
---|
444 | URLUnreserved = ({LetterOrUnderscore}|{Digit}|[\-\.\~])
|
---|
445 | URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
|
---|
446 | URLCharacters = ({URLCharacter}*)
|
---|
447 | URLEndCharacter = ([\/\$]|{Letter}|{Digit})
|
---|
448 | URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
|
---|
449 |
|
---|
450 | %state COMMENT
|
---|
451 | %state PI
|
---|
452 | %state DTD
|
---|
453 | %state INTAG
|
---|
454 | %state INATTR_DOUBLE
|
---|
455 | %state INATTR_SINGLE
|
---|
456 | %state INTAG_SCRIPT
|
---|
457 | %state INATTR_DOUBLE_SCRIPT
|
---|
458 | %state INATTR_SINGLE_SCRIPT
|
---|
459 | %state CDATA
|
---|
460 |
|
---|
461 | %state AS
|
---|
462 | %state AS_MLC
|
---|
463 | %state AS_EOL_COMMENT
|
---|
464 |
|
---|
465 | %%
|
---|
466 |
|
---|
467 | <YYINITIAL> {
|
---|
468 | "<!--" { start = zzMarkedPos-4; yybegin(COMMENT); }
|
---|
469 | {CDataBegin} { addToken(Token.DATA_TYPE); start = zzMarkedPos; yybegin(CDATA); }
|
---|
470 | "<!" { start = zzMarkedPos-2; yybegin(DTD); }
|
---|
471 | "<?" { start = zzMarkedPos-2; yybegin(PI); }
|
---|
472 | "<"{TagName} {
|
---|
473 | int count = yylength();
|
---|
474 | String tag = yytext(); // Get before addToken calls
|
---|
475 | addToken(zzStartRead,zzStartRead, Token.MARKUP_TAG_DELIMITER);
|
---|
476 | addToken(zzMarkedPos-(count-1), zzMarkedPos-1, Token.MARKUP_TAG_NAME);
|
---|
477 | if (tag.endsWith(":Script") || tag.equals("<Script")) {
|
---|
478 | yybegin(INTAG_SCRIPT);
|
---|
479 | }
|
---|
480 | else {
|
---|
481 | yybegin(INTAG);
|
---|
482 | }
|
---|
483 | }
|
---|
484 | "</"{TagName} {
|
---|
485 | int count = yylength();
|
---|
486 | addToken(zzStartRead,zzStartRead+1, Token.MARKUP_TAG_DELIMITER);
|
---|
487 | addToken(zzMarkedPos-(count-2), zzMarkedPos-1, Token.MARKUP_TAG_NAME);
|
---|
488 | yybegin(INTAG);
|
---|
489 | }
|
---|
490 | "<" { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG); }
|
---|
491 | "</" { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG); }
|
---|
492 | {LineTerminator} { addNullToken(); return firstToken; }
|
---|
493 | {Identifier} { addToken(Token.IDENTIFIER); }
|
---|
494 | {AmperItem} { addToken(Token.DATA_TYPE); }
|
---|
495 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
496 | <<EOF>> { addNullToken(); return firstToken; }
|
---|
497 | }
|
---|
498 |
|
---|
499 | <COMMENT> {
|
---|
500 | [^\n\-]+ {}
|
---|
501 | {LineTerminator} { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); return firstToken; }
|
---|
502 | "-->" { yybegin(YYINITIAL); addToken(start,zzStartRead+2, Token.COMMENT_MULTILINE); }
|
---|
503 | "-" {}
|
---|
504 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); return firstToken; }
|
---|
505 | }
|
---|
506 |
|
---|
507 | <PI> {
|
---|
508 | [^\n\?]+ {}
|
---|
509 | {LineTerminator} { addToken(start,zzStartRead-1, Token.MARKUP_PROCESSING_INSTRUCTION); return firstToken; }
|
---|
510 | "?>" { yybegin(YYINITIAL); addToken(start,zzStartRead+1, Token.MARKUP_PROCESSING_INSTRUCTION); }
|
---|
511 | "?" {}
|
---|
512 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_PROCESSING_INSTRUCTION); return firstToken; }
|
---|
513 | }
|
---|
514 |
|
---|
515 | <DTD> {
|
---|
516 | [^\n>]+ {}
|
---|
517 | {LineTerminator} { addToken(start,zzStartRead-1, Token.FUNCTION); return firstToken; }
|
---|
518 | ">" { yybegin(YYINITIAL); addToken(start,zzStartRead, Token.FUNCTION); }
|
---|
519 | <<EOF>> { addToken(start,zzStartRead-1, Token.FUNCTION); return firstToken; }
|
---|
520 | }
|
---|
521 |
|
---|
522 | <INTAG> {
|
---|
523 | {InTagIdentifier} { addToken(Token.MARKUP_TAG_ATTRIBUTE); }
|
---|
524 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
525 | "=" { addToken(Token.OPERATOR); }
|
---|
526 | "/" { addToken(Token.MARKUP_TAG_DELIMITER); /* Not valid but we'll still accept it */ }
|
---|
527 | "/>" { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); }
|
---|
528 | ">" { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); }
|
---|
529 | [\"] { start = zzMarkedPos-1; yybegin(INATTR_DOUBLE); }
|
---|
530 | [\'] { start = zzMarkedPos-1; yybegin(INATTR_SINGLE); }
|
---|
531 | <<EOF>> { addToken(start,zzStartRead-1, INTERNAL_INTAG); return firstToken; }
|
---|
532 | }
|
---|
533 |
|
---|
534 | <INATTR_DOUBLE> {
|
---|
535 | [^\"]* {}
|
---|
536 | [\"] { yybegin(INTAG); addToken(start,zzStartRead, Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
537 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_TAG_ATTRIBUTE_VALUE); addEndToken(INTERNAL_ATTR_DOUBLE); return firstToken; }
|
---|
538 | }
|
---|
539 |
|
---|
540 | <INATTR_SINGLE> {
|
---|
541 | [^\']* {}
|
---|
542 | [\'] { yybegin(INTAG); addToken(start,zzStartRead, Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
543 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_TAG_ATTRIBUTE_VALUE); addEndToken(INTERNAL_ATTR_SINGLE); return firstToken; }
|
---|
544 | }
|
---|
545 |
|
---|
546 | <INTAG_SCRIPT> {
|
---|
547 | {InTagIdentifier} { addToken(Token.MARKUP_TAG_ATTRIBUTE); }
|
---|
548 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
549 | "=" { addToken(Token.OPERATOR); }
|
---|
550 | "/" { addToken(Token.MARKUP_TAG_DELIMITER); /* Not valid but we'll still accept it */ }
|
---|
551 | "/>" { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); }
|
---|
552 | ">" { yybegin(AS); addToken(Token.MARKUP_TAG_DELIMITER); }
|
---|
553 | [\"] { start = zzMarkedPos-1; yybegin(INATTR_DOUBLE_SCRIPT); }
|
---|
554 | [\'] { start = zzMarkedPos-1; yybegin(INATTR_SINGLE_SCRIPT); }
|
---|
555 | <<EOF>> { addToken(start,zzStartRead-1, INTERNAL_INTAG_SCRIPT); return firstToken; }
|
---|
556 | }
|
---|
557 |
|
---|
558 | <INATTR_DOUBLE_SCRIPT> {
|
---|
559 | [^\"]* {}
|
---|
560 | [\"] { yybegin(INTAG_SCRIPT); addToken(start,zzStartRead, Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
561 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_TAG_ATTRIBUTE_VALUE); addEndToken(INTERNAL_ATTR_DOUBLE_QUOTE_SCRIPT); return firstToken; }
|
---|
562 | }
|
---|
563 |
|
---|
564 | <INATTR_SINGLE_SCRIPT> {
|
---|
565 | [^\']* {}
|
---|
566 | [\'] { yybegin(INTAG_SCRIPT); addToken(start,zzStartRead, Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
567 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_TAG_ATTRIBUTE_VALUE); addEndToken(INTERNAL_ATTR_SINGLE_QUOTE_SCRIPT); return firstToken; }
|
---|
568 | }
|
---|
569 |
|
---|
570 | <CDATA> {
|
---|
571 | [^\]]+ {}
|
---|
572 | {CDataEnd} { int temp=zzStartRead; yybegin(YYINITIAL); addToken(start,zzStartRead-1, Token.MARKUP_CDATA); addToken(temp,zzMarkedPos-1, Token.DATA_TYPE); }
|
---|
573 | "]" {}
|
---|
574 | <<EOF>> { addToken(start,zzStartRead-1, Token.MARKUP_CDATA); return firstToken; }
|
---|
575 | }
|
---|
576 |
|
---|
577 | <AS> {
|
---|
578 |
|
---|
579 | {AS_EndScriptTag} {
|
---|
580 | int origStart = zzStartRead;
|
---|
581 | String text = yytext();
|
---|
582 | int tagNameEnd = text.length() - 2; // "-1" is '>'
|
---|
583 | while (Character.isWhitespace(text.charAt(tagNameEnd))) {
|
---|
584 | tagNameEnd--;
|
---|
585 | }
|
---|
586 | int tagNameLen = tagNameEnd - 1;
|
---|
587 | yybegin(YYINITIAL);
|
---|
588 | addToken(zzStartRead,zzStartRead+1, Token.MARKUP_TAG_DELIMITER);
|
---|
589 | addToken(origStart+2,origStart+2+tagNameLen-1, Token.MARKUP_TAG_NAME);
|
---|
590 | if (tagNameEnd<text.length()-2) {
|
---|
591 | addToken(origStart+tagNameEnd+1, zzMarkedPos-2, Token.WHITESPACE);
|
---|
592 | }
|
---|
593 | addToken(zzMarkedPos-1,zzMarkedPos-1, Token.MARKUP_TAG_DELIMITER);
|
---|
594 | }
|
---|
595 |
|
---|
596 | /* ActionScript snippets are usually wrapped in CDATA. */
|
---|
597 | {CDataBegin} |
|
---|
598 | {CDataEnd} { addToken(Token.DATA_TYPE); }
|
---|
599 |
|
---|
600 | /* Keywords */
|
---|
601 | "add" |
|
---|
602 | "and" |
|
---|
603 | "break" |
|
---|
604 | "case" |
|
---|
605 | "catch" |
|
---|
606 | "class" |
|
---|
607 | "const" |
|
---|
608 | "continue" |
|
---|
609 | "default" |
|
---|
610 | "delete" |
|
---|
611 | "do" |
|
---|
612 | "dynamic" |
|
---|
613 | "else" |
|
---|
614 | "eq" |
|
---|
615 | "extends" |
|
---|
616 | "final" |
|
---|
617 | "finally" |
|
---|
618 | "for" |
|
---|
619 | "for each" |
|
---|
620 | "function" |
|
---|
621 | "ge" |
|
---|
622 | "get" |
|
---|
623 | "gt" |
|
---|
624 | "if" |
|
---|
625 | "ifFrameLoaded" |
|
---|
626 | "implements" |
|
---|
627 | "import" |
|
---|
628 | "in" |
|
---|
629 | "include" |
|
---|
630 | "interface" |
|
---|
631 | "internal" |
|
---|
632 | "label" |
|
---|
633 | "le" |
|
---|
634 | "lt" |
|
---|
635 | "namespace" |
|
---|
636 | "native" |
|
---|
637 | "ne" |
|
---|
638 | "new" |
|
---|
639 | "not" |
|
---|
640 | "on" |
|
---|
641 | "onClipEvent" |
|
---|
642 | "or" |
|
---|
643 | "override" |
|
---|
644 | "package" |
|
---|
645 | "private" |
|
---|
646 | "protected" |
|
---|
647 | "public" |
|
---|
648 | "return" |
|
---|
649 | "set" |
|
---|
650 | "static" |
|
---|
651 | "super" |
|
---|
652 | "switch" |
|
---|
653 | "tellTarget" |
|
---|
654 | "this" |
|
---|
655 | "throw" |
|
---|
656 | "try" |
|
---|
657 | "typeof" |
|
---|
658 | "use" |
|
---|
659 | "var" |
|
---|
660 | "void" |
|
---|
661 | "while" |
|
---|
662 | "with" |
|
---|
663 |
|
---|
664 | "null" |
|
---|
665 | "undefined" { addToken(Token.RESERVED_WORD); }
|
---|
666 |
|
---|
667 | /* Built-in objects (good idea not to use these names!) */
|
---|
668 | "Array" |
|
---|
669 | "Boolean" |
|
---|
670 | "Color" |
|
---|
671 | "Date" |
|
---|
672 | "Function" |
|
---|
673 | "int" |
|
---|
674 | "Key" |
|
---|
675 | "MovieClip" |
|
---|
676 | "Math" |
|
---|
677 | "Mouse" |
|
---|
678 | "Null" |
|
---|
679 | "Number" |
|
---|
680 | "Object" |
|
---|
681 | "Selection" |
|
---|
682 | "Sound" |
|
---|
683 | "String" |
|
---|
684 | "uint" |
|
---|
685 | "Vector" |
|
---|
686 | "void" |
|
---|
687 | "XML" |
|
---|
688 | "XMLNode" |
|
---|
689 | "XMLSocket" { addToken(Token.DATA_TYPE); }
|
---|
690 |
|
---|
691 | /* Global functions */
|
---|
692 | "call" |
|
---|
693 | "escape" |
|
---|
694 | "eval" |
|
---|
695 | "fscommand" |
|
---|
696 | "getProperty" |
|
---|
697 | "getTimer" |
|
---|
698 | "getURL" |
|
---|
699 | "getVersion" |
|
---|
700 | "gotoAndPlay" |
|
---|
701 | "gotoAndStop" |
|
---|
702 | "#include" |
|
---|
703 | "int" |
|
---|
704 | "isFinite" |
|
---|
705 | "isNaN" |
|
---|
706 | "loadMovie" |
|
---|
707 | "loadMovieNum" |
|
---|
708 | "loadVariables" |
|
---|
709 | "loadVariablesNum" |
|
---|
710 | "maxscroll" |
|
---|
711 | "newline" |
|
---|
712 | "nextFrame" |
|
---|
713 | "nextScene" |
|
---|
714 | "Number" |
|
---|
715 | "parseFloat" |
|
---|
716 | "parseInt" |
|
---|
717 | "play" |
|
---|
718 | "prevFrame" |
|
---|
719 | "prevScene" |
|
---|
720 | "print" |
|
---|
721 | "printAsBitmap" |
|
---|
722 | "printAsBitmapNum" |
|
---|
723 | "printNum" |
|
---|
724 | "random" |
|
---|
725 | "removeMovieClip" |
|
---|
726 | "scroll" |
|
---|
727 | "setProperty" |
|
---|
728 | "startDrag" |
|
---|
729 | "stop" |
|
---|
730 | "stopAllSounds" |
|
---|
731 | "stopDrag" |
|
---|
732 | "String" |
|
---|
733 | "targetPath" |
|
---|
734 | "tellTarget" |
|
---|
735 | "toggleHighQuality" |
|
---|
736 | "trace" |
|
---|
737 | "unescape" |
|
---|
738 | "unloadMovie" |
|
---|
739 | "unloadMovieNum" |
|
---|
740 | "updateAfterEvent" { addToken(Token.FUNCTION); }
|
---|
741 |
|
---|
742 | /* Booleans. */
|
---|
743 | {AS_BooleanLiteral} { addToken(Token.LITERAL_BOOLEAN); }
|
---|
744 |
|
---|
745 | {LineTerminator} { addEndToken(INTERNAL_IN_AS); return firstToken; }
|
---|
746 |
|
---|
747 | {AS_Identifier} { addToken(Token.IDENTIFIER); }
|
---|
748 |
|
---|
749 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
750 |
|
---|
751 | /* String/Character literals. */
|
---|
752 | {AS_CharLiteral} { addToken(Token.LITERAL_CHAR); }
|
---|
753 | {AS_UnclosedCharLiteral} { addToken(Token.ERROR_CHAR); addNullToken(); return firstToken; }
|
---|
754 | {AS_ErrorCharLiteral} { addToken(Token.ERROR_CHAR); }
|
---|
755 | {AS_StringLiteral} { addToken(Token.LITERAL_STRING_DOUBLE_QUOTE); }
|
---|
756 | {AS_UnclosedStringLiteral} { addToken(Token.ERROR_STRING_DOUBLE); addNullToken(); return firstToken; }
|
---|
757 | {AS_ErrorStringLiteral} { addToken(Token.ERROR_STRING_DOUBLE); }
|
---|
758 |
|
---|
759 | /* Comment literals. */
|
---|
760 | "/**/" { addToken(Token.COMMENT_MULTILINE); }
|
---|
761 | {AS_MLCBegin} { start = zzMarkedPos-2; yybegin(AS_MLC); }
|
---|
762 | {AS_LineCommentBegin} { start = zzMarkedPos-2; yybegin(AS_EOL_COMMENT); }
|
---|
763 |
|
---|
764 | /* Separators. */
|
---|
765 | {AS_Separator} { addToken(Token.SEPARATOR); }
|
---|
766 | {AS_Separator2} { addToken(Token.IDENTIFIER); }
|
---|
767 |
|
---|
768 | /* Operators. */
|
---|
769 | {AS_Operator} { addToken(Token.OPERATOR); }
|
---|
770 |
|
---|
771 | /* Numbers */
|
---|
772 | {AS_IntegerLiteral} { addToken(Token.LITERAL_NUMBER_DECIMAL_INT); }
|
---|
773 | {AS_HexLiteral} { addToken(Token.LITERAL_NUMBER_HEXADECIMAL); }
|
---|
774 | {AS_FloatLiteral} { addToken(Token.LITERAL_NUMBER_FLOAT); }
|
---|
775 | {AS_ErrorNumberFormat} { addToken(Token.ERROR_NUMBER_FORMAT); }
|
---|
776 |
|
---|
777 | {AS_ErrorIdentifier} { addToken(Token.ERROR_IDENTIFIER); }
|
---|
778 |
|
---|
779 | /* Ended with a line not in a string or comment. */
|
---|
780 | <<EOF>> { addEndToken(INTERNAL_IN_AS); return firstToken; }
|
---|
781 |
|
---|
782 | /* Catch any other (unhandled) characters and flag them as bad. */
|
---|
783 | . { addToken(Token.ERROR_IDENTIFIER); }
|
---|
784 |
|
---|
785 | }
|
---|
786 |
|
---|
787 |
|
---|
788 | <AS_MLC> {
|
---|
789 |
|
---|
790 | [^hwf\n\*]+ {}
|
---|
791 | {URL} { int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_MULTILINE); start = zzMarkedPos; }
|
---|
792 | [hwf] {}
|
---|
793 |
|
---|
794 | \n { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addEndToken(INTERNAL_IN_AS_MLC); return firstToken; }
|
---|
795 | {AS_MLCEnd} { yybegin(AS); addToken(start,zzStartRead+1, Token.COMMENT_MULTILINE); }
|
---|
796 | \* {}
|
---|
797 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addEndToken(INTERNAL_IN_AS_MLC); return firstToken; }
|
---|
798 |
|
---|
799 | }
|
---|
800 |
|
---|
801 |
|
---|
802 | <AS_EOL_COMMENT> {
|
---|
803 | [^hwf\n]+ {}
|
---|
804 | {URL} { int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_EOL); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_EOL); start = zzMarkedPos; }
|
---|
805 | [hwf] {}
|
---|
806 | \n { addToken(start,zzStartRead-1, Token.COMMENT_EOL); addEndToken(INTERNAL_IN_AS); return firstToken; }
|
---|
807 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_EOL); addEndToken(INTERNAL_IN_AS); return firstToken; }
|
---|
808 |
|
---|
809 | }
|
---|