1 | /*
|
---|
2 | * 04/12/2012
|
---|
3 | *
|
---|
4 | * DtdTokenMaker.java - Generates tokens for DTD 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 DTD files.
|
---|
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>XMLTokenMaker.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 1.0
|
---|
53 | */
|
---|
54 | %%
|
---|
55 |
|
---|
56 | %public
|
---|
57 | %class DtdTokenMaker
|
---|
58 | %extends AbstractJFlexTokenMaker
|
---|
59 | %unicode
|
---|
60 | %type org.fife.ui.rsyntaxtextarea.Token
|
---|
61 |
|
---|
62 |
|
---|
63 | %{
|
---|
64 |
|
---|
65 | /**
|
---|
66 | * Token type specific to XMLTokenMaker denoting a line ending with an
|
---|
67 | * unclosed XML tag; thus a new line is beginning still inside of the tag.
|
---|
68 | */
|
---|
69 | public static final int INTERNAL_INTAG_START = -1;
|
---|
70 |
|
---|
71 | /**
|
---|
72 | * Token type specific to XMLTokenMaker denoting a line ending with an
|
---|
73 | * unclosed DOCTYPE element.
|
---|
74 | */
|
---|
75 | public static final int INTERNAL_INTAG_ELEMENT = -2;
|
---|
76 |
|
---|
77 | /**
|
---|
78 | * Token type specific to XMLTokenMaker denoting a line ending with an
|
---|
79 | * unclosed, locally-defined DTD in a DOCTYPE element.
|
---|
80 | */
|
---|
81 | public static final int INTERNAL_INTAG_ATTLIST = -3;
|
---|
82 |
|
---|
83 | /**
|
---|
84 | * Token type specific to XMLTokenMaker denoting a line ending with an
|
---|
85 | * unclosed comment. The state to return to when this comment ends is
|
---|
86 | * embedded in the token type as well.
|
---|
87 | */
|
---|
88 | public static final int INTERNAL_IN_COMMENT = -(1<<11);
|
---|
89 |
|
---|
90 | /**
|
---|
91 | * The state we were in prior to the current one. This is used to know
|
---|
92 | * what state to resume after an MLC ends.
|
---|
93 | */
|
---|
94 | private int prevState;
|
---|
95 |
|
---|
96 |
|
---|
97 | /**
|
---|
98 | * Constructor. This must be here because JFlex does not generate a
|
---|
99 | * no-parameter constructor.
|
---|
100 | */
|
---|
101 | public DtdTokenMaker() {
|
---|
102 | }
|
---|
103 |
|
---|
104 |
|
---|
105 | /**
|
---|
106 | * Adds the token specified to the current linked list of tokens as an
|
---|
107 | * "end token;" that is, at <code>zzMarkedPos</code>.
|
---|
108 | *
|
---|
109 | * @param tokenType The token's type.
|
---|
110 | */
|
---|
111 | private void addEndToken(int tokenType) {
|
---|
112 | addToken(zzMarkedPos,zzMarkedPos, tokenType);
|
---|
113 | }
|
---|
114 |
|
---|
115 |
|
---|
116 | /**
|
---|
117 | * Adds the token specified to the current linked list of tokens.
|
---|
118 | *
|
---|
119 | * @param tokenType The token's type.
|
---|
120 | * @see #addToken(int, int, int)
|
---|
121 | */
|
---|
122 | private void addHyperlinkToken(int start, int end, int tokenType) {
|
---|
123 | int so = start + offsetShift;
|
---|
124 | addToken(zzBuffer, start,end, tokenType, so, true);
|
---|
125 | }
|
---|
126 |
|
---|
127 |
|
---|
128 | /**
|
---|
129 | * Adds the token specified to the current linked list of tokens.
|
---|
130 | *
|
---|
131 | * @param tokenType The token's type.
|
---|
132 | */
|
---|
133 | private void addToken(int tokenType) {
|
---|
134 | addToken(zzStartRead, zzMarkedPos-1, tokenType);
|
---|
135 | }
|
---|
136 |
|
---|
137 |
|
---|
138 | /**
|
---|
139 | * Adds the token specified to the current linked list of tokens.
|
---|
140 | *
|
---|
141 | * @param tokenType The token's type.
|
---|
142 | */
|
---|
143 | private void addToken(int start, int end, int tokenType) {
|
---|
144 | int so = start + offsetShift;
|
---|
145 | addToken(zzBuffer, start,end, tokenType, so);
|
---|
146 | }
|
---|
147 |
|
---|
148 |
|
---|
149 | /**
|
---|
150 | * Adds the token specified to the current linked list of tokens.
|
---|
151 | *
|
---|
152 | * @param array The character array.
|
---|
153 | * @param start The starting offset in the array.
|
---|
154 | * @param end The ending offset in the array.
|
---|
155 | * @param tokenType The token's type.
|
---|
156 | * @param startOffset The offset in the document at which this token
|
---|
157 | * occurs.
|
---|
158 | */
|
---|
159 | public void addToken(char[] array, int start, int end, int tokenType, int startOffset) {
|
---|
160 | super.addToken(array, start,end, tokenType, startOffset);
|
---|
161 | zzStartRead = zzMarkedPos;
|
---|
162 | }
|
---|
163 |
|
---|
164 |
|
---|
165 | /**
|
---|
166 | * Always returns <tt>false</tt>, as you never want "mark occurrences"
|
---|
167 | * working in XML files.
|
---|
168 | *
|
---|
169 | * @param type The token type.
|
---|
170 | * @return Whether tokens of this type should have "mark occurrences"
|
---|
171 | * enabled.
|
---|
172 | */
|
---|
173 | public boolean getMarkOccurrencesOfTokenType(int type) {
|
---|
174 | return false;
|
---|
175 | }
|
---|
176 |
|
---|
177 |
|
---|
178 | /**
|
---|
179 | * Returns the first token in the linked list of tokens generated
|
---|
180 | * from <code>text</code>. This method must be implemented by
|
---|
181 | * subclasses so they can correctly implement syntax highlighting.
|
---|
182 | *
|
---|
183 | * @param text The text from which to get tokens.
|
---|
184 | * @param initialTokenType The token type we should start with.
|
---|
185 | * @param startOffset The offset into the document at which
|
---|
186 | * <code>text</code> starts.
|
---|
187 | * @return The first <code>Token</code> in a linked list representing
|
---|
188 | * the syntax highlighted text.
|
---|
189 | */
|
---|
190 | public Token getTokenList(Segment text, int initialTokenType, int startOffset) {
|
---|
191 |
|
---|
192 | resetTokenList();
|
---|
193 | this.offsetShift = -text.offset + startOffset;
|
---|
194 | prevState = YYINITIAL;
|
---|
195 |
|
---|
196 | // Start off in the proper state.
|
---|
197 | int state = YYINITIAL;
|
---|
198 | switch (initialTokenType) {
|
---|
199 | case INTERNAL_INTAG_START:
|
---|
200 | state = INTAG_START;
|
---|
201 | break;
|
---|
202 | case INTERNAL_INTAG_ELEMENT:
|
---|
203 | state = INTAG_ELEMENT;
|
---|
204 | break;
|
---|
205 | case INTERNAL_INTAG_ATTLIST:
|
---|
206 | state = INTAG_ATTLIST;
|
---|
207 | break;
|
---|
208 | default:
|
---|
209 | if (initialTokenType<-1024) { // INTERNAL_IN_COMMENT - prevState
|
---|
210 | int main = -(-initialTokenType & 0xffffff00);
|
---|
211 | switch (main) {
|
---|
212 | default: // Should never happen
|
---|
213 | case INTERNAL_IN_COMMENT:
|
---|
214 | state = COMMENT;
|
---|
215 | break;
|
---|
216 | }
|
---|
217 | prevState = -initialTokenType&0xff;
|
---|
218 | }
|
---|
219 | else { // Shouldn't happen
|
---|
220 | state = YYINITIAL;
|
---|
221 | }
|
---|
222 | }
|
---|
223 |
|
---|
224 | start = text.offset;
|
---|
225 | s = text;
|
---|
226 | try {
|
---|
227 | yyreset(zzReader);
|
---|
228 | yybegin(state);
|
---|
229 | return yylex();
|
---|
230 | } catch (IOException ioe) {
|
---|
231 | ioe.printStackTrace();
|
---|
232 | return new DefaultToken();
|
---|
233 | }
|
---|
234 |
|
---|
235 | }
|
---|
236 |
|
---|
237 |
|
---|
238 | /**
|
---|
239 | * Refills the input buffer.
|
---|
240 | *
|
---|
241 | * @return <code>true</code> if EOF was reached, otherwise
|
---|
242 | * <code>false</code>.
|
---|
243 | */
|
---|
244 | private boolean zzRefill() {
|
---|
245 | return zzCurrentPos>=s.offset+s.count;
|
---|
246 | }
|
---|
247 |
|
---|
248 |
|
---|
249 | /**
|
---|
250 | * Resets the scanner to read from a new input stream.
|
---|
251 | * Does not close the old reader.
|
---|
252 | *
|
---|
253 | * All internal variables are reset, the old input stream
|
---|
254 | * <b>cannot</b> be reused (internal buffer is discarded and lost).
|
---|
255 | * Lexical state is set to <tt>YY_INITIAL</tt>.
|
---|
256 | *
|
---|
257 | * @param reader the new input stream
|
---|
258 | */
|
---|
259 | public final void yyreset(java.io.Reader reader) {
|
---|
260 | // 's' has been updated.
|
---|
261 | zzBuffer = s.array;
|
---|
262 | /*
|
---|
263 | * We replaced the line below with the two below it because zzRefill
|
---|
264 | * no longer "refills" the buffer (since the way we do it, it's always
|
---|
265 | * "full" the first time through, since it points to the segment's
|
---|
266 | * array). So, we assign zzEndRead here.
|
---|
267 | */
|
---|
268 | //zzStartRead = zzEndRead = s.offset;
|
---|
269 | zzStartRead = s.offset;
|
---|
270 | zzEndRead = zzStartRead + s.count - 1;
|
---|
271 | zzCurrentPos = zzMarkedPos = zzPushbackPos = s.offset;
|
---|
272 | zzLexicalState = YYINITIAL;
|
---|
273 | zzReader = reader;
|
---|
274 | zzAtBOL = true;
|
---|
275 | zzAtEOF = false;
|
---|
276 | }
|
---|
277 |
|
---|
278 |
|
---|
279 | %}
|
---|
280 |
|
---|
281 | Whitespace = ([ \t\f])
|
---|
282 | LineTerminator = ([\n])
|
---|
283 | UnclosedString = ([\"][^\"]*)
|
---|
284 | UnclosedChar = ([\'][^\']*)
|
---|
285 |
|
---|
286 | URLGenDelim = ([:\/\?#\[\]@])
|
---|
287 | URLSubDelim = ([\!\$&'\(\)\*\+,;=])
|
---|
288 | URLUnreserved = ([A-Za-z_0-9\-\.\~])
|
---|
289 | URLCharacter = ({URLGenDelim}|{URLSubDelim}|{URLUnreserved}|[%])
|
---|
290 | URLCharacters = ({URLCharacter}*)
|
---|
291 | URLEndCharacter = ([\/\$A-Za-z0-9])
|
---|
292 | URL = (((https?|f(tp|ile))"://"|"www.")({URLCharacters}{URLEndCharacter})?)
|
---|
293 |
|
---|
294 | %state COMMENT
|
---|
295 | %state INTAG_START
|
---|
296 | %state INTAG_ELEMENT
|
---|
297 | %state INTAG_ATTLIST
|
---|
298 |
|
---|
299 | %%
|
---|
300 |
|
---|
301 | <YYINITIAL> {
|
---|
302 | ([^ \t\f<]+) { /* Not really valid */ addToken(Token.IDENTIFIER); }
|
---|
303 | "<!--" { start = zzStartRead; prevState = zzLexicalState; yybegin(COMMENT); }
|
---|
304 | "<!" { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG_START); }
|
---|
305 | "<" { addToken(Token.IDENTIFIER); }
|
---|
306 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
307 | {LineTerminator} |
|
---|
308 | <<EOF>> { addNullToken(); return firstToken; }
|
---|
309 | }
|
---|
310 |
|
---|
311 | <COMMENT> {
|
---|
312 | [^hwf\n\-]+ {}
|
---|
313 | {URL} { int temp=zzStartRead; addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addHyperlinkToken(temp,zzMarkedPos-1, Token.COMMENT_MULTILINE); start = zzMarkedPos; }
|
---|
314 | [hwf] {}
|
---|
315 | "-->" { int temp = zzMarkedPos; addToken(start,zzStartRead+2, Token.COMMENT_MULTILINE); start = temp; yybegin(prevState); }
|
---|
316 | "-" {}
|
---|
317 | {LineTerminator} |
|
---|
318 | <<EOF>> { addToken(start,zzStartRead-1, Token.COMMENT_MULTILINE); addEndToken(INTERNAL_IN_COMMENT - prevState); return firstToken; }
|
---|
319 | }
|
---|
320 |
|
---|
321 | <INTAG_START> {
|
---|
322 | ("ELEMENT") { addToken(Token.MARKUP_TAG_NAME); yybegin(INTAG_ELEMENT); }
|
---|
323 | ("ATTLIST") { addToken(Token.MARKUP_TAG_NAME); yybegin(INTAG_ATTLIST); }
|
---|
324 | ([^ \t\f>]+) { addToken(Token.IDENTIFIER); }
|
---|
325 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
326 | (">") { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(YYINITIAL); }
|
---|
327 | <<EOF>> { addEndToken(INTERNAL_INTAG_START); return firstToken; }
|
---|
328 | }
|
---|
329 |
|
---|
330 | <INTAG_ELEMENT> {
|
---|
331 | ([^ \t\f>]+) { addToken(Token.MARKUP_TAG_ATTRIBUTE); }
|
---|
332 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
333 | (">") { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(YYINITIAL); }
|
---|
334 | <<EOF>> { addEndToken(INTERNAL_INTAG_ELEMENT); return firstToken; }
|
---|
335 | }
|
---|
336 |
|
---|
337 | <INTAG_ATTLIST> {
|
---|
338 | ("CDATA"|"#IMPLIED"|"#REQUIRED") { addToken(Token.MARKUP_PROCESSING_INSTRUCTION); }
|
---|
339 | ([^ \t\f>\"\']+) { addToken(Token.MARKUP_TAG_ATTRIBUTE); }
|
---|
340 | ({UnclosedString}[\"]?) { addToken(Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
341 | ({UnclosedChar}[\']?) { addToken(Token.MARKUP_TAG_ATTRIBUTE_VALUE); }
|
---|
342 | {Whitespace}+ { addToken(Token.WHITESPACE); }
|
---|
343 | (">") { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(YYINITIAL); }
|
---|
344 | <<EOF>> { addEndToken(INTERNAL_INTAG_ATTLIST); return firstToken; }
|
---|
345 | }
|
---|