Annotation of OpenXM/src/kan96xx/Kan/scanner2.c, Revision 1.4
1.4 ! takayama 1: /* $OpenXM: OpenXM/src/kan96xx/Kan/scanner2.c,v 1.3 2001/05/04 01:06:25 takayama Exp $ */
1.1 maekawa 2: /* scanner2.c (SM StackMachine) */
3: /* export: struct tokens decompostToTokens(char *str,int *sizep);
4: scanner2.c is for getting tokens from a string.
5: */
6: #include <stdio.h>
7: #include "datatype.h"
8: #include "stackm.h"
9: struct tokens lookupTokens(struct tokens t);
10: int isLiteral(char *s);
11: struct object lookupLiteralString(char *s);
12: /**************** defined in stackm.h ****************************
1.3 takayama 13: typedef enum {INIT,GET,PUT,OPEN} actionType;
1.1 maekawa 14:
1.3 takayama 15: struct tokens{
16: char *token;
17: int kind;
18: };
1.1 maekawa 19:
20:
1.3 takayama 21: #define ID 2
22: #define DOLLAR 3 strings enclosed by dollar sign
23: #define EXECUTABLE_STRING 4 strings enclosed by {}
24: #define EXECUTABLE_ARRAY 8 Don't set it in this file.
1.1 maekawa 25: ******************************************************************/
26:
27:
28: /******* declaration-part of lexical analizer ********************/
29: #define mygetchar() getSM()
30: /* to use getSM() ( input from StringSM ),
31: setup StringSM;
32: getokenSM(INIT);
33: */
34:
35:
36:
37:
38: #define BUF0LIMIT 40000
39: static char *StringSM;
40: static int StrpSM = 0;
41: static char BufSMorg[BUF0LIMIT];
42: static char *BufSM = BufSMorg;
43: static int Buf0limit = BUF0LIMIT ;
44: static int ExistSM = 0;
45: static int TypeSM = ID;
46:
47: /**************** end of declaration part of lexical analizer ******/
48:
49: static int getSM();
50: static putSM();
51: static struct tokens flushSM();
52: static isSpaceSM();
53: static isDollarSM();
54: static isBraceSM();
55: static isKakkoSM();
56: static isSymbolSM();
57: static struct tokens getokenSM2();
58:
59: /**************** code part of lexical analizer ********************/
60:
61: struct tokens *decomposeToTokens(str,sizep)
1.3 takayama 62: char *str;
63: int *sizep;
1.1 maekawa 64: {
65: struct tokens *tArray;
66: struct tokens token;
67: int k;
68: int size;
69:
70: StringSM = (char *) sGC_malloc((strlen(str)+3)*sizeof(char));
71: if (StringSM == (char *)NULL) {
72: errorScanner2("I have no memormy.");
73: }
74: strcpy(StringSM,str);
75: getokenSM2(INIT);
76: size = 0;
77: token = getokenSM2(GET);
78: while (token.kind != -1) {
79: size++;
80: token = getokenSM2(GET);
81: }
82:
83: tArray = (struct tokens *)sGC_malloc((size+1)*sizeof(struct tokens));
84: strcpy(StringSM,str);
85: getokenSM2(INIT);
86: for (k=0; k<size; k++) {
87: tArray[k] = getokenSM2(GET);
88: }
89:
90: *sizep = size;
91: return(tArray);
92: }
93:
94:
95:
96: static int getSM()
1.3 takayama 97: /* get a letter from StringSM */
1.1 maekawa 98: {
99: int c;
100: c = StringSM[StrpSM++];
101: if (c == '\0') {
102: StrpSM--;return(EOF);
103: } else return(c);
104: }
105:
106: static putSM(c)
1.3 takayama 107: int c;
108: /* put a letter on BufSM */
1.1 maekawa 109: {
110: char *new; int i;
111: BufSM[ExistSM++] = ((c=='\n')? ' ' : c);
112: if (ExistSM >= Buf0limit-1) {
113: new = (char *) sGC_malloc(sizeof(char *)*Buf0limit*2) ;
114: if (new == (char *)NULL) {
115: fprintf(stderr,"No more memory in parserpass0.c\n");
116: exit(18);
117: }
118: fprintf(stderr,"\nSystem Message: Increasing BufSM to %d in scanner2.c\n",Buf0limit*2);
119: for (i=0; i<Buf0limit; i++) {
120: new[i] = BufSM[i];
121: }
122: BufSM = new; Buf0limit *= 2;
123: }
124: }
125:
126: static struct tokens flushSM()
127: {
128: char *token;
129: struct tokens r;
130: if (ExistSM<=0) {
131: fprintf(stderr,"\n flushSM() is called without data. Don't use the empty string $$. \n");
132: r.token = (char *)NULL; r.kind = -10; /* -1 ==> -10 ***/
133: return(r);
134: }
135: BufSM[ExistSM] = '\0';
136: ExistSM = 0;
137: token = (char *)sGC_malloc((strlen(BufSM)+1)*sizeof(char));
138: strcpy(token,BufSM);
139: r.token = token;
140: r.kind = TypeSM;
141: if (r.kind == ID) {
142: if (isLiteral(r.token)) {
1.3 takayama 143: r.object = lookupLiteralString(r.token);
1.1 maekawa 144: }else{
145: r = lookupTokens(r); /* Compute hashing values */
146: }
147: }
148: return(r);
149: }
150:
151: static isSpaceSM(c)
1.3 takayama 152: int c;
1.1 maekawa 153: {
1.4 ! takayama 154: static int prev=0;
! 155: if ((c == ',') && (prev == ',')) fprintf(stderr,"Warning! ,, is found.\n");
! 156: prev = c;
! 157:
! 158: if (((c <= ' ') || c == ',') && (c!= EOF)) return(1);
1.1 maekawa 159: else return(0);
160: }
161:
162: static isDollarSM(c)
1.3 takayama 163: int c;
1.1 maekawa 164: {
165: if (c == '$') return(1);
166: else return(0);
167: }
168:
169: static isBraceSM(c)
1.3 takayama 170: int c;
1.1 maekawa 171: {
172: if (c == '{') return(1);
173: else return(0);
174: }
175:
176: static isKakkoSM(c)
1.3 takayama 177: int c;
1.1 maekawa 178: {
179: if (c == '(') return(1);
180: else return(0);
181: }
182:
183: static isSymbolSM(c)
1.3 takayama 184: int c;
1.1 maekawa 185: {
186: if ((c == '{') ||
187: (c == '}') ||
188: (c == '[') ||
189: (c == ']') ||
190: (c == '(') ||
191: (c == ')'))
192: return(1);
193: else return(0);
194: }
195:
196: static struct tokens getokenSM2(kind,str)
1.3 takayama 197: actionType kind;
198: char *str;
1.1 maekawa 199: {
200: static int c;
201: static struct tokens rnull;
202: int level;
203:
204: if (kind == INIT) {
205: StrpSM = 0;
206: ExistSM = 0;
207:
208: c = mygetchar();
209: rnull.token = (char *)NULL; rnull.kind = -1;
210: return(rnull);
211: }
212:
213:
214:
215: for (;;) {
216: TypeSM = ID;
217: if (c == EOF) {
218: if (ExistSM) return(flushSM());
219: else return(rnull);
220: } else if (isSpaceSM(c)) {
221: if (ExistSM) {
1.3 takayama 222: c = mygetchar(); return(flushSM());
1.1 maekawa 223: }else {
1.3 takayama 224: while (isSpaceSM(c=mygetchar())) ;
1.1 maekawa 225: }
226: } else if (isDollarSM(c)) { /* output contents in dollar signs. */
227: if (ExistSM) return(flushSM());
228: else {
1.3 takayama 229: c = mygetchar();
230: while ((c != EOF) && (c != '$')) {
231: putSM(c);
232: c = mygetchar();
233: }
234: if (c=='$') c=mygetchar();
235: TypeSM = DOLLAR;
236: return(flushSM());
1.1 maekawa 237: }
238: } else if (isBraceSM(c)) { /* output contents in { } */
239: /* { { } } */
240: level = 0;
241: if (ExistSM) return(flushSM());
242: else {
1.3 takayama 243: c = mygetchar();
244: while (1) {
245: if (c == '%') { /* skip the comment in the brace. */
246: while (((c=mygetchar()) != '\n') && (c != EOF)) ;
247: }
248: if (c == EOF) break;
249: if ((c == '}') && (level <= 0)) break;
250: if ( c == '{') ++level;
251: if ( c == '}') --level;
252: putSM(c);
253: c = mygetchar();
254: }
255: if (c=='}') c=mygetchar();
256: TypeSM = EXECUTABLE_STRING;
257: return(flushSM());
1.1 maekawa 258: }
259: } else if (isKakkoSM(c)) { /* output contents in ( ) */
260: level = 0;
261: if (ExistSM) return(flushSM());
262: else {
1.3 takayama 263: c = mygetchar();
264: while (1) {
265: if (c == EOF) break;
266: if (c == '\\') { /* e.g. \( */
267: putSM(c);
268: c = mygetchar();
269: if (c == EOF) break;
270: }else{
271: if ((c == ')') && (level <= 0)) break;
272: if ( c == '(') ++level;
273: if ( c == ')') --level;
274: }
275: putSM(c);
276: c = mygetchar();
277: }
278: if (c==')') c=mygetchar();
279: TypeSM = DOLLAR;
280: return(flushSM());
1.1 maekawa 281: }
282: } else if (c=='%') { /* comment */
283: while (((c=mygetchar()) != '\n') && (c != EOF)) ;
284: if(ExistSM) return(flushSM());
285: } else if (isSymbolSM(c)) { /* symbols. {,} etc */
286: if(ExistSM) return(flushSM());
287: else {
1.3 takayama 288: putSM(c);
289: c = mygetchar();
290: return(flushSM());
1.1 maekawa 291: }
292: } else { /* identifier */
293: putSM(c);
294: c =mygetchar();
295: while ((!isDollarSM(c)) &&
1.3 takayama 296: (!isSpaceSM(c)) &&
297: (!isSymbolSM(c)) &&
298: (c != EOF)) {
299: putSM(c);
300: c = mygetchar();
1.1 maekawa 301: }
302: return(flushSM());
303: }
304: }
305: }
306:
307: /*********** end of code part of lexical analizer ********************/
308:
309:
310: errorScanner2(str)
1.3 takayama 311: char *str;
1.1 maekawa 312: {
313: fprintf(stderr,"Error (scanner2.c): %s\n",str);
314: exit(10);
315: }
316:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>