1 | // GPDefSyntaxAnalyzerLex.cs HDO, 2006-08-28
|
---|
2 | // -------------
|
---|
3 | // Lexical analyzer (finite-state machine interpreter).
|
---|
4 | // Generated by Coco-2 (SG).
|
---|
5 | //=====================================|========================================
|
---|
6 |
|
---|
7 | #undef TEST_Lex
|
---|
8 |
|
---|
9 | using System;
|
---|
10 | using System.Collections;
|
---|
11 | using System.Collections.Specialized;
|
---|
12 | using System.IO;
|
---|
13 | using System.Text;
|
---|
14 |
|
---|
15 | public class GPDefSyntaxAnalyzerLex {
|
---|
16 |
|
---|
17 | public const String MODULENAME = "GPDefSyntaxAnalyzerLex";
|
---|
18 | public const int EOFSPIX = 1;
|
---|
19 |
|
---|
20 | public static TextReader src;
|
---|
21 |
|
---|
22 | // --- token information ---
|
---|
23 | public static int token; // current token
|
---|
24 | public static int tokenLine, tokenCol; // position of current token
|
---|
25 | public static String tokenStr; // token string recognized
|
---|
26 |
|
---|
27 | // --- current char. info, for "power users" only ---
|
---|
28 | public static char curCh; // current input character
|
---|
29 | public static int curLine, curCol; // position of curCh
|
---|
30 |
|
---|
31 |
|
---|
32 | public static void GPDefSyntaxAnalyzerLexMethod(Utils.ModuleAction action, out String moduleName) {
|
---|
33 | //-----------------------------------|----------------------------------------
|
---|
34 | moduleName = MODULENAME;
|
---|
35 | switch (action) {
|
---|
36 | case Utils.ModuleAction.getModuleName:
|
---|
37 | return;
|
---|
38 | case Utils.ModuleAction.initModule:
|
---|
39 | caseSensitive = true;
|
---|
40 | lt = new LexicalTable();
|
---|
41 | tokenStrArr = new char[256];
|
---|
42 | kwHt = CreateHashtable();
|
---|
43 | nHt = CreateHashtable();
|
---|
44 | nl = new ArrayList();
|
---|
45 | break;
|
---|
46 | case Utils.ModuleAction.resetModule:
|
---|
47 | kwHt.Clear();
|
---|
48 | nHt.Clear();
|
---|
49 | nl.Clear();
|
---|
50 | break;
|
---|
51 | case Utils.ModuleAction.cleanupModule:
|
---|
52 | lt = null;
|
---|
53 | tokenStrArr = null;
|
---|
54 | kwHt = null;
|
---|
55 | nHt = null;
|
---|
56 | nl = null;
|
---|
57 | break;
|
---|
58 | } // switch
|
---|
59 | } // GPDefSyntaxAnalyzerLexMethod
|
---|
60 |
|
---|
61 | private static Hashtable CreateHashtable() {
|
---|
62 | if (caseSensitive)
|
---|
63 | return new Hashtable();
|
---|
64 | else
|
---|
65 | return CollectionsUtil.CreateCaseInsensitiveHashtable();
|
---|
66 | } // CreateHashtable
|
---|
67 |
|
---|
68 |
|
---|
69 | public static void InitLex() {
|
---|
70 | //-----------------------------------|----------------------------------------
|
---|
71 | // --- initialize keyword hash table ---
|
---|
72 | kwHt.Clear();
|
---|
73 | EnterKeyword( 1, "PROBLEM");
|
---|
74 | EnterKeyword( 2, "END");
|
---|
75 | EnterKeyword( 3, "EPS");
|
---|
76 | EnterKeyword( 4, "LOCAL");
|
---|
77 | EnterKeyword( 5, "NONTERMINALS");
|
---|
78 | EnterKeyword( 6, "RULES");
|
---|
79 | EnterKeyword( 7, "SEM");
|
---|
80 | EnterKeyword( 8, "MAXIMIZE");
|
---|
81 | EnterKeyword( 9, "MINIMIZE");
|
---|
82 | EnterKeyword( 10, "TERMINALS");
|
---|
83 | EnterKeyword( 11, "CONSTRAINTS");
|
---|
84 | EnterKeyword( 12, "INIT");
|
---|
85 | EnterKeyword( 13, "CODE");
|
---|
86 | EnterKeyword( 14, "IN");
|
---|
87 | EnterKeyword( 15, "SET");
|
---|
88 | EnterKeyword( 16, "RANGE");
|
---|
89 | // --- initialize name data structures ---
|
---|
90 | nHt.Clear();
|
---|
91 | nl.Clear();
|
---|
92 | nl.Add(""); // so spix = 0 is the empty string
|
---|
93 | nl.Add("!EOF!"); // so EOFSPIX = 1
|
---|
94 | // --- (re)set global data ---
|
---|
95 | curLineStr = "";
|
---|
96 | curCh = ' ';
|
---|
97 | curLine = 0;
|
---|
98 | curCol = 2;
|
---|
99 | tokenStr = null;
|
---|
100 | token = 0;
|
---|
101 | tokenCol = 0;
|
---|
102 | tokenLine = 0;
|
---|
103 | tokenStrLen = 0;
|
---|
104 | pendingEOLs = 0;
|
---|
105 | apxLen = pendingEOLs; // to prevent warning
|
---|
106 | } // InitLex
|
---|
107 |
|
---|
108 | private static void EnterKeyword(int token, String keyword) {
|
---|
109 | kwHt.Add(keyword, token);
|
---|
110 | } // EnterKeyword
|
---|
111 |
|
---|
112 |
|
---|
113 | // *** start of global LEX declarations from ATG ***
|
---|
114 |
|
---|
115 | // *** end of global LEX declarations from ATG ***
|
---|
116 |
|
---|
117 |
|
---|
118 | public static bool caseSensitive;
|
---|
119 |
|
---|
120 | private class LexicalTable {
|
---|
121 | public int header = 4;
|
---|
122 | public int[] startTab = {
|
---|
123 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
124 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
125 | 0, 0, 0, 0, 0, 0, 0, 0, 4, 5, 0, 0, 0, 0, 17, 0,
|
---|
126 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 14, 2, 10, 0,
|
---|
127 | 0, 16, 16, 16, 16, 16, 13, 16, 13, 16, 13, 13, 16, 16, 16, 16,
|
---|
128 | 16, 13, 16, 16, 16, 16, 13, 13, 16, 13, 16, 6, 0, 7, 0, 0,
|
---|
129 | 0, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
|
---|
130 | 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 8, 3, 9, 0, 0,
|
---|
131 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
132 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
133 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
134 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
135 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
136 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
137 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
---|
138 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
|
---|
139 | };
|
---|
140 | public Sets.Set256 ignoredChars = new Sets.Set256(
|
---|
141 | 0x0600, 0x0000, 0x0001
|
---|
142 | );
|
---|
143 | public Sets.Set256 commentStart = new Sets.Set256(
|
---|
144 | 0x0000, 0x0000, 0x8000
|
---|
145 | );
|
---|
146 | public Sets.Set256[] cls = {
|
---|
147 | new Sets.Set256( 0x0000, 0x0000, 0x0000, 0x0000, 0xfffe, 0x07ff, 0xfffe, 0x07ff),
|
---|
148 | new Sets.Set256( 0x0000, 0x0000, 0x0000, 0x03ff),
|
---|
149 | new Sets.Set256( 0x0000, 0x0000, 0x0000, 0x0000, 0xf2be, 0x053d),
|
---|
150 | new Sets.Set256( 0x0000, 0x0000, 0x0000, 0x0000, 0x0d40, 0x02c2, 0xfffe, 0x07ff)
|
---|
151 | };
|
---|
152 | } // LexicalTable
|
---|
153 |
|
---|
154 | private static LexicalTable lt;
|
---|
155 | private static Hashtable kwHt; // hash table for keywords: string -> token
|
---|
156 | private static Hashtable nHt; // hash table for names: string -> null
|
---|
157 | private static ArrayList nl; // name list for names, index is spix
|
---|
158 |
|
---|
159 | private static String curLineStr; // current source line
|
---|
160 | private static char[] tokenStrArr; // token string in an array
|
---|
161 | private static int tokenStrLen; // length of token string in tokenStrArr
|
---|
162 | private static int state; // current automaton state
|
---|
163 | private static int apxLen; // length of appendix in token string
|
---|
164 | private static int pendingEOLs; // nr of EOLs found in comment
|
---|
165 |
|
---|
166 | // --- to save and restore scanner state ---
|
---|
167 | private static char savedCh;
|
---|
168 | private static int savedCol, savedLine;
|
---|
169 |
|
---|
170 | private static void SaveScannerState() {
|
---|
171 | savedCh = curCh;
|
---|
172 | savedCol = curCol;
|
---|
173 | savedLine = curLine;
|
---|
174 | } // SaveScannerState
|
---|
175 |
|
---|
176 | private static void RestoreScannerState() {
|
---|
177 | tokenStrLen -= apxLen;
|
---|
178 | apxLen = 0;
|
---|
179 | curCh = savedCh;
|
---|
180 | curCol = savedCol;
|
---|
181 | curLine = savedLine;
|
---|
182 | } // RestoreScannerState
|
---|
183 |
|
---|
184 |
|
---|
185 | public static void NextCh() {
|
---|
186 | //-----------------------------------|----------------------------------------
|
---|
187 | for (;;) {
|
---|
188 |
|
---|
189 | if (curCol < curLineStr.Length) { // within line
|
---|
190 | curCol++;
|
---|
191 | curCh = curLineStr[curCol - 1];
|
---|
192 | return;
|
---|
193 | } else if (curCol == curLineStr.Length) { // end of line
|
---|
194 | curCol++;
|
---|
195 | curCh = Utils.LF; // to separate lines
|
---|
196 | return;
|
---|
197 | } else { // curCol > curLineStr.Length
|
---|
198 | curLineStr = src.ReadLine();
|
---|
199 | curLine++;
|
---|
200 | curCol = 0;
|
---|
201 | if (curLineStr == null) { // end of file
|
---|
202 | curLineStr = "";
|
---|
203 | curCh = Utils.EF;
|
---|
204 | return;
|
---|
205 | } // if
|
---|
206 | } // else
|
---|
207 | } // for
|
---|
208 | } // NextCh
|
---|
209 |
|
---|
210 |
|
---|
211 | private static void CommentErr() {
|
---|
212 | Errors.LexError(curLine, curCol, "end of file in comment");
|
---|
213 | } // CommentErr
|
---|
214 |
|
---|
215 | private static bool Comment() {
|
---|
216 |
|
---|
217 | int level = 1;
|
---|
218 |
|
---|
219 | SaveScannerState();
|
---|
220 | // --- from '/' '*' to '*' '/' nested ---
|
---|
221 | NextCh();
|
---|
222 | if (curCh == '*') {
|
---|
223 | NextCh();
|
---|
224 | for (;;)
|
---|
225 | switch (curCh) {
|
---|
226 | case '*':
|
---|
227 | NextCh();
|
---|
228 | if (curCh == '/') {
|
---|
229 | NextCh();
|
---|
230 | level--;
|
---|
231 | if (level == 0) {
|
---|
232 | return true;
|
---|
233 | } // if
|
---|
234 | } // if
|
---|
235 | break;
|
---|
236 | case '/':
|
---|
237 | NextCh();
|
---|
238 | if (curCh == '*') {
|
---|
239 | level++;
|
---|
240 | NextCh();
|
---|
241 | }
|
---|
242 | break;
|
---|
243 | case Utils.EF:
|
---|
244 | CommentErr();
|
---|
245 | return true;
|
---|
246 | default:
|
---|
247 | NextCh();
|
---|
248 | break;
|
---|
249 | } // switch
|
---|
250 | } else
|
---|
251 | RestoreScannerState();
|
---|
252 | return false;
|
---|
253 | } // Comment
|
---|
254 |
|
---|
255 | private static void HandleLexErr() {
|
---|
256 | Errors.LexError(curLine, curCol,
|
---|
257 | "invalid character '{0}' (hex {1:X})", curCh, (int)curCh);
|
---|
258 | if (apxLen > 0)
|
---|
259 | RestoreScannerState();
|
---|
260 | } // HandleLexErr
|
---|
261 |
|
---|
262 |
|
---|
263 | public static void GetToken() {
|
---|
264 | //-----------------------------------|----------------------------------------
|
---|
265 | token = -1;
|
---|
266 | tokenStr = null;
|
---|
267 | do {
|
---|
268 | // --- skip ignored chars and comments ---
|
---|
269 | for (;;) {
|
---|
270 | while (Sets.member(curCh, lt.ignoredChars))
|
---|
271 | NextCh();
|
---|
272 | if (!Sets.member(curCh, lt.commentStart))
|
---|
273 | break;
|
---|
274 | if (!Comment())
|
---|
275 | break;
|
---|
276 | } // for
|
---|
277 | // --- scan for next token ---
|
---|
278 | tokenLine = curLine;
|
---|
279 | tokenCol = curCol;
|
---|
280 | tokenStrLen = 0;
|
---|
281 | apxLen = 0;
|
---|
282 | state = (curCh == Utils.EF) ? 1 : lt.startTab[curCh];
|
---|
283 | for (;;) {
|
---|
284 | tokenStrArr[tokenStrLen++]= curCh;
|
---|
285 | NextCh();
|
---|
286 | switch (state) {
|
---|
287 | case 0:
|
---|
288 | Errors.LexError(tokenLine, tokenCol, "invalid token start");
|
---|
289 | break;
|
---|
290 | case 1:
|
---|
291 | token = 0;
|
---|
292 | tokenStrLen = 0;
|
---|
293 | break; // EOF recognized
|
---|
294 | case 2:
|
---|
295 | token = 17;
|
---|
296 | break; // '=' recognized
|
---|
297 | case 3:
|
---|
298 | token = 18;
|
---|
299 | break; // '|' recognized
|
---|
300 | case 4:
|
---|
301 | token = 20;
|
---|
302 | break; // '(' recognized
|
---|
303 | case 5:
|
---|
304 | token = 21;
|
---|
305 | break; // ')' recognized
|
---|
306 | case 6:
|
---|
307 | token = 22;
|
---|
308 | break; // '[' recognized
|
---|
309 | case 7:
|
---|
310 | token = 23;
|
---|
311 | break; // ']' recognized
|
---|
312 | case 8:
|
---|
313 | token = 24;
|
---|
314 | break; // '{' recognized
|
---|
315 | case 9:
|
---|
316 | token = 25;
|
---|
317 | break; // '}' recognized
|
---|
318 | case 10:
|
---|
319 | if (curCh == '>') {
|
---|
320 | state = 11;
|
---|
321 | continue;
|
---|
322 | } // if
|
---|
323 | else {
|
---|
324 | HandleLexErr();
|
---|
325 | break;
|
---|
326 | } // else
|
---|
327 | case 11:
|
---|
328 | token = 26;
|
---|
329 | break; // '>>' recognized
|
---|
330 | case 12:
|
---|
331 | token = 27;
|
---|
332 | break; // '..' recognized
|
---|
333 | case 13:
|
---|
334 | if (Sets.member(curCh, lt.cls[0])) {
|
---|
335 | state = 13;
|
---|
336 | continue;
|
---|
337 | } // if
|
---|
338 | else if (Sets.member(curCh, lt.cls[1])) {
|
---|
339 | state = 13;
|
---|
340 | continue;
|
---|
341 | } // if
|
---|
342 | else {
|
---|
343 | token = KeywordCheck();
|
---|
344 | if (token >= 0)
|
---|
345 | break; // keyword recognized
|
---|
346 | token = 28;
|
---|
347 | break; // ident recognized
|
---|
348 | } // else
|
---|
349 | case 14:
|
---|
350 | if (curCh == '<') {
|
---|
351 | state = 15;
|
---|
352 | continue;
|
---|
353 | } // if
|
---|
354 | else {
|
---|
355 | HandleLexErr();
|
---|
356 | break;
|
---|
357 | } // else
|
---|
358 | case 15:
|
---|
359 | token = 29;
|
---|
360 | break; // source recognized
|
---|
361 | case 16:
|
---|
362 | if (Sets.member(curCh, lt.cls[1])) {
|
---|
363 | state = 13;
|
---|
364 | continue;
|
---|
365 | } // if
|
---|
366 | else if (Sets.member(curCh, lt.cls[2])) {
|
---|
367 | state = 16;
|
---|
368 | continue;
|
---|
369 | } // if
|
---|
370 | else if (Sets.member(curCh, lt.cls[3])) {
|
---|
371 | state = 13;
|
---|
372 | continue;
|
---|
373 | } // if
|
---|
374 | else {
|
---|
375 | token = KeywordCheck();
|
---|
376 | if (token >= 0)
|
---|
377 | break; // keyword recognized
|
---|
378 | token = 28;
|
---|
379 | break; // ident recognized
|
---|
380 | } // else
|
---|
381 | case 17:
|
---|
382 | if (curCh == '.') {
|
---|
383 | state = 12;
|
---|
384 | continue;
|
---|
385 | } // if
|
---|
386 | else {
|
---|
387 | token = 19;
|
---|
388 | break; // '.' recognized
|
---|
389 | } // else
|
---|
390 | } // switch
|
---|
391 | break;
|
---|
392 | } // for
|
---|
393 | } while (token < 0);
|
---|
394 | if (tokenStr == null)
|
---|
395 | tokenStr = new String(tokenStrArr, 0, tokenStrLen);
|
---|
396 | } // GetToken
|
---|
397 |
|
---|
398 | private static int KeywordCheck() {
|
---|
399 | tokenStr = new String(tokenStrArr, 0, tokenStrLen - apxLen);
|
---|
400 | Object token = kwHt[tokenStr];
|
---|
401 | return (token == null) ? -1 : (int)token;
|
---|
402 | } // KeywordCheck
|
---|
403 |
|
---|
404 |
|
---|
405 | public static int Hash(String s) {
|
---|
406 | //-----------------------------------|----------------------------------------
|
---|
407 | Object spix = nHt[s];
|
---|
408 | if (spix == null) {
|
---|
409 | if (caseSensitive)
|
---|
410 | nl.Add(s);
|
---|
411 | else
|
---|
412 | nl.Add(s.ToUpper());
|
---|
413 | spix = nl.Count - 1;
|
---|
414 | nHt[s] = spix;
|
---|
415 | } // if
|
---|
416 | return (int)spix;
|
---|
417 | } // Hash
|
---|
418 |
|
---|
419 |
|
---|
420 | public static String HashedStr(int spix) {
|
---|
421 | //-----------------------------------|----------------------------------------
|
---|
422 | return (String)nl[spix];
|
---|
423 | } // HashedStr
|
---|
424 |
|
---|
425 |
|
---|
426 | public static void GETidentAttr() {
|
---|
427 | } // GETidentAttr
|
---|
428 |
|
---|
429 | public static void GETsourceAttr() {
|
---|
430 | } // GETsourceAttr
|
---|
431 |
|
---|
432 | } // GPDefSyntaxAnalyzerLex
|
---|
433 |
|
---|
434 | // End of GPDefSyntaxAnalyzerLex.cs
|
---|
435 | //=====================================|========================================
|
---|