|
1 /**************************************************************************** |
|
2 ** |
|
3 ** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies). |
|
4 ** All rights reserved. |
|
5 ** Contact: Nokia Corporation (qt-info@nokia.com) |
|
6 ** |
|
7 ** This file is part of the tools applications of the Qt Toolkit. |
|
8 ** |
|
9 ** $QT_BEGIN_LICENSE:LGPL$ |
|
10 ** No Commercial Usage |
|
11 ** This file contains pre-release code and may not be distributed. |
|
12 ** You may use this file in accordance with the terms and conditions |
|
13 ** contained in the Technology Preview License Agreement accompanying |
|
14 ** this package. |
|
15 ** |
|
16 ** GNU Lesser General Public License Usage |
|
17 ** Alternatively, this file may be used under the terms of the GNU Lesser |
|
18 ** General Public License version 2.1 as published by the Free Software |
|
19 ** Foundation and appearing in the file LICENSE.LGPL included in the |
|
20 ** packaging of this file. Please review the following information to |
|
21 ** ensure the GNU Lesser General Public License version 2.1 requirements |
|
22 ** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html. |
|
23 ** |
|
24 ** In addition, as a special exception, Nokia gives you certain additional |
|
25 ** rights. These rights are described in the Nokia Qt LGPL Exception |
|
26 ** version 1.1, included in the file LGPL_EXCEPTION.txt in this package. |
|
27 ** |
|
28 ** If you have questions regarding the use of this file, please contact |
|
29 ** Nokia at qt-info@nokia.com. |
|
30 ** |
|
31 ** |
|
32 ** |
|
33 ** |
|
34 ** |
|
35 ** |
|
36 ** |
|
37 ** |
|
38 ** $QT_END_LICENSE$ |
|
39 ** |
|
40 ****************************************************************************/ |
|
41 #include <stdio.h> |
|
42 #include <string.h> |
|
43 #include <qbytearray.h> |
|
44 #include <qlist.h> |
|
45 |
|
46 struct Keyword |
|
47 { |
|
48 const char *lexem; |
|
49 const char *token; |
|
50 }; |
|
51 |
|
52 static const Keyword pp_keywords[] = { |
|
53 { "<", "PP_LANGLE" }, |
|
54 { ">", "PP_RANGLE" }, |
|
55 { "(", "PP_LPAREN"}, |
|
56 { ")", "PP_RPAREN"}, |
|
57 { ",", "PP_COMMA"}, |
|
58 { "\n", "PP_NEWLINE"}, |
|
59 { "#define", "PP_DEFINE"}, |
|
60 { "#if", "PP_IF"}, |
|
61 { "#undef", "PP_UNDEF"}, |
|
62 { "#ifdef", "PP_IFDEF"}, |
|
63 { "#ifndef", "PP_IFNDEF"}, |
|
64 { "#elif", "PP_ELIF"}, |
|
65 { "#else", "PP_ELSE"}, |
|
66 { "#endif", "PP_ENDIF"}, |
|
67 { "#include", "PP_INCLUDE"}, |
|
68 { "defined", "PP_DEFINED"}, |
|
69 { "+", "PP_PLUS" }, |
|
70 { "-", "PP_MINUS" }, |
|
71 { "*", "PP_STAR" }, |
|
72 { "/", "PP_SLASH" }, |
|
73 { "%", "PP_PERCENT" }, |
|
74 { "^", "PP_HAT" }, |
|
75 { "&", "PP_AND" }, |
|
76 { "bitand", "PP_AND" }, |
|
77 { "|", "PP_OR" }, |
|
78 { "bitor", "PP_OR" }, |
|
79 { "~", "PP_TILDE" }, |
|
80 { "compl", "PP_TILDE" }, |
|
81 { "!", "PP_NOT" }, |
|
82 { "not", "PP_NOT" }, |
|
83 { "<<", "PP_LTLT" }, |
|
84 { ">>", "PP_GTGT" }, |
|
85 { "==", "PP_EQEQ" }, |
|
86 { "!=", "PP_NE" }, |
|
87 { "not_eq", "PP_NE" }, |
|
88 { "<=", "PP_LE" }, |
|
89 { ">=", "PP_GE" }, |
|
90 { "&&", "PP_ANDAND" }, |
|
91 { "||", "PP_OROR" }, |
|
92 { "?", "PP_QUESTION" }, |
|
93 { ":", "PP_COLON" }, |
|
94 { "##", "PP_HASHHASH"}, |
|
95 { "%:%:", "PP_HASHHASH"}, |
|
96 { "#", "PP_HASH"}, |
|
97 { "\"", "PP_QUOTE"}, |
|
98 { "\'", "PP_SINGLEQUOTE"}, |
|
99 { " ", "PP_WHITESPACE" }, |
|
100 { "\t", "PP_WHITESPACE" }, |
|
101 { "//", "PP_CPP_COMMENT" }, |
|
102 { "/*", "PP_C_COMMENT" }, |
|
103 { "\\", "PP_BACKSLASH" }, |
|
104 { 0, "PP_NOTOKEN"} |
|
105 }; |
|
106 |
|
107 static const Keyword keywords[] = { |
|
108 { "<", "LANGLE" }, |
|
109 { ">", "RANGLE" }, |
|
110 { "(", "LPAREN" }, |
|
111 { ")", "RPAREN" }, |
|
112 { "...", "ELIPSIS" }, |
|
113 { ",", "COMMA" }, |
|
114 { "[", "LBRACK" }, |
|
115 { "]", "RBRACK" }, |
|
116 { "<:", "LBRACK" }, |
|
117 { ":>", "RBRACK" }, |
|
118 { "<::", "LANGLE_SCOPE" }, |
|
119 { "{", "LBRACE" }, |
|
120 { "<%", "LBRACE" }, |
|
121 { "}", "RBRACE" }, |
|
122 { "%>", "RBRACE" }, |
|
123 { "=", "EQ" }, |
|
124 { "::", "SCOPE" }, |
|
125 { ";", "SEMIC" }, |
|
126 { ":", "COLON" }, |
|
127 { ".*", "DOTSTAR" }, |
|
128 { "?", "QUESTION" }, |
|
129 { ".", "DOT" }, |
|
130 { "dynamic_cast", "DYNAMIC_CAST" }, |
|
131 { "static_cast", "STATIC_CAST" }, |
|
132 { "reinterpret_cast", "REINTERPRET_CAST" }, |
|
133 { "const_cast", "CONST_CAST" }, |
|
134 { "typeid", "TYPEID" }, |
|
135 { "this", "THIS" }, |
|
136 { "template", "TEMPLATE" }, |
|
137 { "throw", "THROW" }, |
|
138 { "try", "TRY" }, |
|
139 { "catch", "CATCH" }, |
|
140 { "typedef", "TYPEDEF" }, |
|
141 { "friend", "FRIEND" }, |
|
142 { "class", "CLASS" }, |
|
143 { "namespace", "NAMESPACE" }, |
|
144 { "enum", "ENUM" }, |
|
145 { "struct", "STRUCT" }, |
|
146 { "union", "UNION" }, |
|
147 { "virtual", "VIRTUAL" }, |
|
148 { "private", "PRIVATE" }, |
|
149 { "protected", "PROTECTED" }, |
|
150 { "public", "PUBLIC" }, |
|
151 { "export", "EXPORT" }, |
|
152 { "auto", "AUTO" }, |
|
153 { "register", "REGISTER" }, |
|
154 { "extern", "EXTERN" }, |
|
155 { "mutable", "MUTABLE" }, |
|
156 { "asm", "ASM" }, |
|
157 { "using", "USING" }, |
|
158 { "inline", "INLINE" }, |
|
159 { "explicit", "EXPLICIT" }, |
|
160 { "static", "STATIC" }, |
|
161 { "const", "CONST" }, |
|
162 { "volatile", "VOLATILE" }, |
|
163 { "operator", "OPERATOR" }, |
|
164 { "sizeof", "SIZEOF" }, |
|
165 { "new", "NEW" }, |
|
166 { "delete", "DELETE" }, |
|
167 { "+", "PLUS" }, |
|
168 { "-", "MINUS" }, |
|
169 { "*", "STAR" }, |
|
170 { "/", "SLASH" }, |
|
171 { "%", "PERCENT" }, |
|
172 { "^", "HAT" }, |
|
173 { "&", "AND" }, |
|
174 { "bitand", "AND" }, |
|
175 { "|", "OR" }, |
|
176 { "bitor", "OR" }, |
|
177 { "~", "TILDE" }, |
|
178 { "compl", "TILDE" }, |
|
179 { "!", "NOT" }, |
|
180 { "not", "NOT" }, |
|
181 { "+=", "PLUS_EQ" }, |
|
182 { "-=", "MINUS_EQ" }, |
|
183 { "*=", "STAR_EQ" }, |
|
184 { "/=", "SLASH_EQ" }, |
|
185 { "%=", "PERCENT_EQ" }, |
|
186 { "^=", "HAT_EQ" }, |
|
187 { "&=", "AND_EQ" }, |
|
188 { "|=", "OR_EQ" }, |
|
189 { "<<", "LTLT" }, |
|
190 { ">>", "GTGT" }, |
|
191 { ">>=", "GTGT_EQ" }, |
|
192 { "<<=", "LTLT_EQ" }, |
|
193 { "==", "EQEQ" }, |
|
194 { "!=", "NE" }, |
|
195 { "not_eq", "NE" }, |
|
196 { "<=", "LE" }, |
|
197 { ">=", "GE" }, |
|
198 { "&&", "ANDAND" }, |
|
199 { "||", "OROR" }, |
|
200 { "++", "INCR" }, |
|
201 { "--", "DECR" }, |
|
202 { ",", "COMMA" }, |
|
203 { "->*", "ARROW_STAR" }, |
|
204 { "->", "ARROW" }, |
|
205 { "char", "CHAR" }, |
|
206 { "wchar", "WCHAR" }, |
|
207 { "bool", "BOOL" }, |
|
208 { "short", "SHORT" }, |
|
209 { "int", "INT" }, |
|
210 { "long", "LONG" }, |
|
211 { "signed", "SIGNED" }, |
|
212 { "unsigned", "UNSIGNED" }, |
|
213 { "float", "FLOAT" }, |
|
214 { "double", "DOUBLE" }, |
|
215 { "void", "VOID" }, |
|
216 { "case", "CASE" }, |
|
217 { "default", "DEFAULT" }, |
|
218 { "if", "IF" }, |
|
219 { "else", "ELSE" }, |
|
220 { "switch", "SWITCH" }, |
|
221 { "while", "WHILE" }, |
|
222 { "do", "DO" }, |
|
223 { "for", "FOR" }, |
|
224 { "break", "BREAK" }, |
|
225 { "continue", "CONTINUE" }, |
|
226 { "goto", "GOTO" }, |
|
227 { "return", "RETURN" }, |
|
228 { "Q_OBJECT", "Q_OBJECT_TOKEN" }, |
|
229 { "Q_GADGET", "Q_GADGET_TOKEN" }, |
|
230 { "Q_PROPERTY", "Q_PROPERTY_TOKEN" }, |
|
231 { "Q_ENUMS", "Q_ENUMS_TOKEN" }, |
|
232 { "Q_FLAGS", "Q_FLAGS_TOKEN" }, |
|
233 { "Q_DECLARE_FLAGS", "Q_DECLARE_FLAGS_TOKEN" }, |
|
234 { "Q_DECLARE_INTERFACE", "Q_DECLARE_INTERFACE_TOKEN" }, |
|
235 { "Q_DECLARE_METATYPE", "Q_DECLARE_METATYPE_TOKEN" }, |
|
236 { "Q_DECLARE_EXTENSION_INTERFACE", "Q_DECLARE_INTERFACE_TOKEN" }, |
|
237 { "Q_SETS", "Q_FLAGS_TOKEN" }, |
|
238 { "Q_CLASSINFO", "Q_CLASSINFO_TOKEN" }, |
|
239 { "Q_INTERFACES", "Q_INTERFACES_TOKEN" }, |
|
240 { "signals", "SIGNALS" }, |
|
241 { "slots", "SLOTS" }, |
|
242 { "Q_SIGNALS", "Q_SIGNALS_TOKEN" }, |
|
243 { "Q_SLOTS", "Q_SLOTS_TOKEN" }, |
|
244 { "Q_PRIVATE_SLOT", "Q_PRIVATE_SLOT_TOKEN" }, |
|
245 { "QT_MOC_COMPAT", "Q_MOC_COMPAT_TOKEN" }, |
|
246 { "QT3_SUPPORT", "Q_QT3_SUPPORT_TOKEN" }, |
|
247 { "Q_INVOKABLE", "Q_INVOKABLE_TOKEN" }, |
|
248 { "Q_SIGNAL", "Q_SIGNAL_TOKEN" }, |
|
249 { "Q_SLOT", "Q_SLOT_TOKEN" }, |
|
250 { "Q_SCRIPTABLE", "Q_SCRIPTABLE_TOKEN" }, |
|
251 |
|
252 { "\n", "NEWLINE" }, |
|
253 { "\"", "QUOTE" }, |
|
254 { "\'", "SINGLEQUOTE" }, |
|
255 { " ", "WHITESPACE" }, |
|
256 { "\t", "WHITESPACE" }, |
|
257 { "#", "HASH" }, |
|
258 { "\\", "BACKSLASH" }, |
|
259 { "//", "CPP_COMMENT" }, |
|
260 { "/*", "C_COMMENT" }, |
|
261 { 0, "NOTOKEN"} |
|
262 }; |
|
263 |
|
264 |
|
265 inline bool is_ident_start(char s) |
|
266 { |
|
267 return ((s >= 'a' && s <= 'z') |
|
268 || (s >= 'A' && s <= 'Z') |
|
269 || s == '_' |
|
270 ); |
|
271 } |
|
272 |
|
273 inline bool is_ident_char(char s) |
|
274 { |
|
275 return ((s >= 'a' && s <= 'z') |
|
276 || (s >= 'A' && s <= 'Z') |
|
277 || (s >= '0' && s <= '9') |
|
278 || s == '_' |
|
279 ); |
|
280 } |
|
281 struct State |
|
282 { |
|
283 State(const char* token):token(token), nextindex(0), |
|
284 defchar(0), defnext(0), ident(0) { |
|
285 memset( next, 0, sizeof(next)); |
|
286 } |
|
287 QByteArray token; |
|
288 int next[128]; |
|
289 int nextindex; |
|
290 |
|
291 char defchar; |
|
292 int defnext; |
|
293 |
|
294 const char *ident; |
|
295 |
|
296 bool operator==(const State& o) const |
|
297 { |
|
298 return (token == o.token |
|
299 && nextindex == o.nextindex |
|
300 && defchar == o.defchar |
|
301 && defnext == o.defnext |
|
302 && ident == o.ident); |
|
303 } |
|
304 }; |
|
305 |
|
306 void newState(QList<State> &states, const char *token, const char *lexem, bool pre) |
|
307 { |
|
308 const char * ident = 0; |
|
309 if (is_ident_start(*lexem)) |
|
310 ident = pre?"PP_CHARACTER" : "CHARACTER"; |
|
311 else if (*lexem == '#') |
|
312 ident = pre?"PP_HASH" : "HASH"; |
|
313 |
|
314 int state = 0; |
|
315 while (*lexem) { |
|
316 int next = states[state].next[(int)*lexem]; |
|
317 if (!next) { |
|
318 const char * t = 0; |
|
319 if (ident) |
|
320 t = ident; |
|
321 else |
|
322 t = pre?"PP_INCOMPLETE":"INCOMPLETE"; |
|
323 next = states.size(); |
|
324 states += State(t); |
|
325 states[state].next[(int)*lexem] = next; |
|
326 states[next].ident = ident; |
|
327 } |
|
328 state = next; |
|
329 ++lexem; |
|
330 if (ident && !is_ident_char(*lexem)) |
|
331 ident = 0; |
|
332 } |
|
333 states[state].token = token; |
|
334 } |
|
335 |
|
336 void newState(QList<State> &states, const char *token, char lexem) |
|
337 { |
|
338 int next = states[0].next[(int)lexem]; |
|
339 if (!next) { |
|
340 next = states.size(); |
|
341 states += State(token); |
|
342 states[0].next[(int)lexem] = next; |
|
343 } else { |
|
344 states[next].token = token; |
|
345 } |
|
346 } |
|
347 |
|
348 |
|
349 void makeTable(const Keyword keywords[]) |
|
350 { |
|
351 int i,c; |
|
352 bool pre = (keywords == pp_keywords); |
|
353 QList<State> states; |
|
354 states += State(pre?"PP_NOTOKEN":"NOTOKEN"); |
|
355 |
|
356 // identifiers |
|
357 for (c = 'a'; c <= 'z'; ++c) |
|
358 newState(states, pre?"PP_CHARACTER":"CHARACTER", c); |
|
359 for (c = 'A'; c <= 'Z'; ++c) |
|
360 newState(states, pre?"PP_CHARACTER":"CHARACTER", c); |
|
361 c = '_'; |
|
362 newState(states, pre?"PP_CHARACTER":"CHARACTER", c); |
|
363 |
|
364 // add digits |
|
365 for (c = '0'; c <= '9'; ++c) |
|
366 newState(states, pre?"PP_DIGIT":"DIGIT", c); |
|
367 |
|
368 // keywords |
|
369 for (i = 0; keywords[i].lexem; ++i) |
|
370 newState(states, keywords[i].token, keywords[i].lexem, pre); |
|
371 |
|
372 // some floats |
|
373 for (c = '0'; c <= '9'; ++c) |
|
374 newState(states, pre?"PP_FLOATING_LITERAL":"FLOATING_LITERAL", |
|
375 QByteArray(".") + char(c), pre); |
|
376 |
|
377 // simplify table with default transitions |
|
378 int transindex = -1; |
|
379 for (i = 0; i < states.size(); ++i) { |
|
380 int n = 0; |
|
381 int defchar = -1; |
|
382 for (c = 0; c < 128; ++c) |
|
383 if (states[i].next[c]) { |
|
384 ++n; |
|
385 defchar = c; |
|
386 } |
|
387 if (!n) |
|
388 continue; |
|
389 if (n == 1) { |
|
390 states[i].defnext = states[i].next[defchar]; |
|
391 states[i].defchar = defchar; |
|
392 continue; |
|
393 } |
|
394 states[i].nextindex = ++transindex; |
|
395 } |
|
396 |
|
397 #if 1 |
|
398 // compress table |
|
399 int j, k; |
|
400 for (i = 0; i < states.size(); ++i) { |
|
401 for (j = i + 1; j < states.size(); ++j) { |
|
402 if ( states[i] == states[j] ) { |
|
403 for (k = 0; k < states.size(); ++k) { |
|
404 if (states[k].defnext == j) |
|
405 states[k].defnext = i; |
|
406 if (states[k].defnext > j) |
|
407 --states[k].defnext; |
|
408 for (c = 0; c < 128; ++c) { |
|
409 if (states[k].next[c] == j) |
|
410 states[k].next[c] = i; |
|
411 if (states[k].next[c] > j) |
|
412 --states[k].next[c]; |
|
413 } |
|
414 } |
|
415 states.removeAt(j); |
|
416 --j; |
|
417 } |
|
418 } |
|
419 } |
|
420 #endif |
|
421 printf("static const short %skeyword_trans[][128] = {\n", |
|
422 pre?"pp_":""); |
|
423 for (i = 0; i < states.size(); ++i) { |
|
424 if (i && !states[i].nextindex) |
|
425 continue; |
|
426 printf("%s {", i?",\n":""); |
|
427 for (c = 0; c < 128; ++c) |
|
428 printf("%s%s%d", |
|
429 c?",":"", |
|
430 (!c || c%16)?"":"\n ", |
|
431 states[i].next[c] |
|
432 ); |
|
433 printf("}"); |
|
434 } |
|
435 printf("\n};\n\n"); |
|
436 |
|
437 printf("static const struct\n{\n" |
|
438 " %sToken token;\n" |
|
439 " short next;\n" |
|
440 " char defchar;\n" |
|
441 " short defnext;\n" |
|
442 " %sToken ident;\n" |
|
443 "} %skeywords[] = {\n", |
|
444 pre ? "PP_":"", |
|
445 pre ? "PP_":"", |
|
446 pre ? "pp_":""); |
|
447 for (i = 0; i < states.size(); ++i) { |
|
448 printf("%s {%s, %d, %d, %d, %s}", |
|
449 i?",\n":"", |
|
450 states[i].token.data(), |
|
451 states[i].nextindex, |
|
452 states[i].defchar, |
|
453 states[i].defnext, |
|
454 states[i].ident?states[i].ident:(pre?"PP_NOTOKEN":"NOTOKEN")); |
|
455 } |
|
456 printf("\n};\n"); |
|
457 } |
|
458 |
|
459 int main(int argc, char **) |
|
460 { |
|
461 printf("// auto generated\n" |
|
462 "// DO NOT EDIT.\n\n"); |
|
463 if ( argc > 1 ) |
|
464 makeTable(pp_keywords); |
|
465 else |
|
466 makeTable(keywords); |
|
467 return 0; |
|
468 } |