![[BACK]](/cvsweb/icons/back.gif){kind=icon}
Return to spell.c CVS log ![[TXT]](/cvsweb/icons/text.gif){kind=icon}
![[DIR]](/cvsweb/icons/dir.gif){kind=icon}
Up to [CSRG BSD Unix] / 40BSD / cmd / spell|
Return to spell.c CVS log | Up to [CSRG BSD Unix] / 40BSD / cmd / spell |
1.1 root 1: #include "spell.h"
2: #define DLEV 2
3:
4: char *strcat();
5: int strip();
6: char *skipv();
7: int an();
8: int s();
9: int es();
10: int ily();
11: int ncy();
12: int CCe();
13: int VCe();
14: int bility();
15: int tion();
16: int ize();
17: int y_to_e();
18: int i_to_y();
19: int nop();
20: int metry();
21:
22: struct suftab {
23: char *suf;
24: int (*p1)();
25: int n1;
26: char *d1;
27: char *a1;
28: int (*p2)();
29: int n2;
30: char *d2;
31: char *a2;
32: } suftab[] = {
33: {"ssen",ily,4,"-y+iness","+ness" },
34: {"ssel",ily,4,"-y+i+less","+less" },
35: {"se",s,1,"","+s", es,2,"-y+ies","+es" },
36: {"s'",s,2,"","+'s"},
37: {"s",s,1,"","+s"},
38: {"ecn",ncy,1,"","-t+ce"},
39: {"ycn",ncy,1,"","-cy+t"},
40: {"ytilb",nop,0,"",""},
41: {"ytilib",bility,5,"-le+ility",""},
42: {"elbaif",i_to_y,4,"-y+iable",""},
43: {"elba",CCe,4,"-e+able","+able"},
44: {"yti",CCe,3,"-e+ity","+ity"},
45: {"ylb",y_to_e,1,"-e+y",""},
46: {"yl",ily,2,"-y+ily","+ly"},
47: {"laci",strip,2,"","+al"},
48: {"latnem",strip,2,"","+al"},
49: {"lanoi",strip,2,"","+al"},
50: {"tnem",strip,4,"","+ment"},
51: {"gni",CCe,3,"-e+ing","+ing"},
52: {"reta",nop,0,"",""},
53: {"re",strip,1,"","+r", i_to_y,2,"-y+ier","+er"},
54: {"de",strip,1,"","+d", i_to_y,2,"-y+ied","+ed"},
55: {"citsi",strip,2,"","+ic"},
56: {"cihparg",i_to_y,1,"-y+ic",""},
57: {"tse",strip,2,"","+st", i_to_y,3,"-y+iest","+est"},
58: {"cirtem",i_to_y,1,"-y+ic",""},
59: {"yrtem",metry,0,"-ry+er",""},
60: {"cigol",i_to_y,1,"-y+ic",""},
61: {"tsigol",i_to_y,2,"-y+ist",""},
62: {"tsi",VCe,3,"-e+ist","+ist"},
63: {"msi",VCe,3,"-e+ism","+ist"},
64: {"noitacif",i_to_y,6,"-y+ication",""},
65: {"noitazi",ize,5,"-e+ation",""},
66: {"rota",tion,2,"-e+or",""},
67: {"noit",tion,3,"-e+ion","+ion"},
68: {"naino",an,3,"","+ian"},
69: {"na",an,1,"","+n"},
70: {"evit",tion,3,"-e+ive","+ive"},
71: {"ezi",CCe,3,"-e+ize","+ize"},
72: {"pihs",strip,4,"","+ship"},
73: {"dooh",ily,4,"-y+hood","+hood"},
74: {"ekil",strip,4,"","+like"},
75: 0
76: };
77:
78: char *preftab[] = {
79: "anti",
80: "bio",
81: "dis",
82: "electro",
83: "en",
84: "fore",
85: "hyper",
86: "intra",
87: "inter",
88: "iso",
89: "kilo",
90: "magneto",
91: "meta",
92: "micro",
93: "milli",
94: "mis",
95: "mono",
96: "multi",
97: "non",
98: "out",
99: "over",
100: "photo",
101: "poly",
102: "pre",
103: "pseudo",
104: "re",
105: "semi",
106: "stereo",
107: "sub",
108: "super",
109: "thermo",
110: "ultra",
111: "under", /*must precede un*/
112: "un",
113: 0
114: };
115:
116: int vflag;
117: int xflag;
118: char word[100];
119: char original[100];
120: char *deriv[40];
121: char affix[40];
122:
123: main(argc,argv)
124: char **argv;
125: {
126: register char *ep, *cp;
127: register char *dp;
128: int fold;
129: int j;
130: FILE *file, *found;
131: if(!prime(argc,argv)) {
132: fprintf(stderr,
133: "spell: cannot initialize hash table\n");
134: exit(1);
135: }
136: found = fopen(argv[2],"w");
137: for(argc-=3,argv+=3; argc>0 && argv[0][0]=='-'; argc--,argv++)
138: switch(argv[0][1]) {
139: case 'b':
140: ise();
141: break;
142: case 'v':
143: vflag++;
144: break;
145: case 'x':
146: xflag++;
147: break;
148: }
149: for(;; fprintf(file,"%s%s\n",affix,original)) {
150: affix[0] = 0;
151: file = found;
152: for(ep=word;(*ep=j=getchar())!='\n';ep++)
153: if(j == EOF)
154: exit(0);
155: for(cp=word,dp=original; cp<ep; )
156: *dp++ = *cp++;
157: *dp = 0;
158: fold = 0;
159: for(cp=word;cp<ep;cp++)
160: if(islower(*cp))
161: goto lcase;
162: if(putsuf(ep,".",0))
163: continue;
164: ++fold;
165: for(cp=original+1,dp=word+1;dp<ep;dp++,cp++)
166: *dp = Tolower(*cp);
167: lcase:
168: if(putsuf(ep,".",0)||suffix(ep,0))
169: continue;
170: if(isupper(word[0])) {
171: for(cp=original,dp=word; *dp = *cp++; dp++)
172: if (fold) *dp = Tolower(*dp);
173: word[0] = Tolower(word[0]);
174: goto lcase;
175: }
176: file = stdout;
177: }
178: }
179:
180: suffix(ep,lev)
181: char *ep;
182: {
183: register struct suftab *t;
184: register char *cp, *sp;
185: lev += DLEV;
186: deriv[lev] = deriv[lev-1] = 0;
187: for(t= &suftab[0];sp=t->suf;t++) {
188: cp = ep;
189: while(*sp)
190: if(*--cp!=*sp++)
191: goto next;
192: for(sp=cp; --sp>=word&&!vowel(*sp); ) ;
193: if(sp<word)
194: return(0);
195: if((*t->p1)(ep-t->n1,t->d1,t->a1,lev+1))
196: return(1);
197: if(t->p2!=0) {
198: deriv[lev] = deriv[lev+1] = 0;
199: return((*t->p2)(ep-t->n2,t->d2,t->a2,lev));
200: }
201: return(0);
202: next: ;
203: }
204: return(0);
205: }
206:
207: nop()
208: {
209: return(0);
210: }
211:
212: strip(ep,d,a,lev)
213: char *ep,*d,*a;
214: {
215: return(putsuf(ep,a,lev)||suffix(ep,lev));
216: }
217:
218: s(ep,d,a,lev)
219: char *ep,*d,*a;
220: {
221: if(lev>DLEV+1)
222: return(0);
223: if(*ep=='s'&&ep[-1]=='s')
224: return(0);
225: return(strip(ep,d,a,lev));
226: }
227:
228: an(ep,d,a,lev)
229: char *ep,*d,*a;
230: {
231: if(!isupper(*word)) /*must be proper name*/
232: return(0);
233: return(putsuf(ep,a,lev));
234: }
235:
236: ize(ep,d,a,lev)
237: char *ep,*d,*a;
238: {
239: *ep++ = 'e';
240: return(strip(ep,"",d,lev));
241: }
242:
243: y_to_e(ep,d,a,lev)
244: char *ep,*d,*a;
245: {
246: *ep++ = 'e';
247: return(strip(ep,"",d,lev));
248: }
249:
250: ily(ep,d,a,lev)
251: char *ep,*d,*a;
252: {
253: if(ep[-1]=='i')
254: return(i_to_y(ep,d,a,lev));
255: else
256: return(strip(ep,d,a,lev));
257: }
258:
259: ncy(ep,d,a,lev)
260: char *ep, *d, *a;
261: {
262: if(skipv(skipv(ep-1))<word)
263: return(0);
264: ep[-1] = 't';
265: return(strip(ep,d,a,lev));
266: }
267:
268: bility(ep,d,a,lev)
269: char *ep,*d,*a;
270: {
271: *ep++ = 'l';
272: return(y_to_e(ep,d,a,lev));
273: }
274:
275: i_to_y(ep,d,a,lev)
276: char *ep,*d,*a;
277: {
278: if(ep[-1]=='i') {
279: ep[-1] = 'y';
280: a = d;
281: }
282: return(strip(ep,"",a,lev));
283: }
284:
285: es(ep,d,a,lev)
286: char *ep,*d,*a;
287: {
288: if(lev>DLEV)
289: return(0);
290: switch(ep[-1]) {
291: default:
292: return(0);
293: case 'i':
294: return(i_to_y(ep,d,a,lev));
295: case 's':
296: case 'h':
297: case 'z':
298: case 'x':
299: return(strip(ep,d,a,lev));
300: }
301: }
302:
303: metry(ep,d,a,lev)
304: char *ep, *d,*a;
305: {
306: ep[-2] = 'e';
307: ep[-1] = 'r';
308: return(strip(ep,d,a,lev));
309: }
310:
311: tion(ep,d,a,lev)
312: char *ep,*d,*a;
313: {
314: switch(ep[-2]) {
315: case 'c':
316: case 'r':
317: return(putsuf(ep,a,lev));
318: case 'a':
319: return(y_to_e(ep,d,a,lev));
320: }
321: return(0);
322: }
323:
324: /* possible consonant-consonant-e ending*/
325: CCe(ep,d,a,lev)
326: char *ep,*d,*a;
327: {
328: switch(ep[-1]) {
329: case 'l':
330: if(vowel(ep[-2]))
331: break;
332: switch(ep[-2]) {
333: case 'l':
334: case 'r':
335: case 'w':
336: break;
337: default:
338: return(y_to_e(ep,d,a,lev));
339: }
340: break;
341: case 's':
342: if(ep[-2]=='s')
343: break;
344: case 'c':
345: case 'g':
346: if(*ep=='a')
347: return(0);
348: case 'v':
349: case 'z':
350: if(vowel(ep[-2]))
351: break;
352: case 'u':
353: if(y_to_e(ep,d,a,lev))
354: return(1);
355: if(!(ep[-2]=='n'&&ep[-1]=='g'))
356: return(0);
357: }
358: return(VCe(ep,d,a,lev));
359: }
360:
361: /* possible consonant-vowel-consonant-e ending*/
362: VCe(ep,d,a,lev)
363: char *ep,*d,*a;
364: {
365: char c;
366: c = ep[-1];
367: if(c=='e')
368: return(0);
369: if(!vowel(c) && vowel(ep[-2])) {
370: c = *ep;
371: *ep++ = 'e';
372: if(putsuf(ep,d,lev)||suffix(ep,lev))
373: return(1);
374: ep--;
375: *ep = c;
376: }
377: return(strip(ep,d,a,lev));
378: }
379:
380: char *lookuppref(wp,ep)
381: char **wp;
382: char *ep;
383: {
384: register char **sp;
385: register char *bp,*cp;
386: for(sp=preftab;*sp;sp++) {
387: bp = *wp;
388: for(cp= *sp;*cp;cp++,bp++)
389: if(Tolower(*bp)!=*cp)
390: goto next;
391: for(cp=bp;cp<ep;cp++)
392: if(vowel(*cp)) {
393: *wp = bp;
394: return(*sp);
395: }
396: next: ;
397: }
398: return(0);
399: }
400:
401: putsuf(ep,a,lev)
402: char *ep,*a;
403: {
404: register char *cp;
405: char *bp;
406: register char *pp;
407: int val = 0;
408: char space[20];
409: deriv[lev] = a;
410: if(putw(word,ep,lev))
411: return(1);
412: bp = word;
413: pp = space;
414: deriv[lev+1] = pp;
415: while(cp=lookuppref(&bp,ep)) {
416: *pp++ = '+';
417: while(*pp = *cp++)
418: pp++;
419: if(putw(bp,ep,lev+1)) {
420: val = 1;
421: break;
422: }
423: }
424: deriv[lev+1] = deriv[lev+2] = 0;
425: return(val);
426: }
427:
428: putw(bp,ep,lev)
429: char *bp,*ep;
430: {
431: register i, j;
432: char duple[3];
433: if(ep-bp<=1)
434: return(0);
435: if(vowel(*ep)) {
436: if(monosyl(bp,ep))
437: return(0);
438: }
439: i = dict(bp,ep);
440: if(i==0&&vowel(*ep)&&ep[-1]==ep[-2]&&monosyl(bp,ep-1)) {
441: ep--;
442: deriv[++lev] = duple;
443: duple[0] = '+';
444: duple[1] = *ep;
445: duple[2] = 0;
446: i = dict(bp,ep);
447: }
448: if(vflag==0||i==0)
449: return(i);
450: j = lev;
451: do {
452: if(deriv[j])
453: strcat(affix,deriv[j]);
454: } while(--j>0);
455: strcat(affix,"\t");
456: return(i);
457: }
458:
459:
460: monosyl(bp,ep)
461: char *bp, *ep;
462: {
463: if(ep<bp+2)
464: return(0);
465: if(vowel(*--ep)||!vowel(*--ep)
466: ||ep[1]=='x'||ep[1]=='w')
467: return(0);
468: while(--ep>=bp)
469: if(vowel(*ep))
470: return(0);
471: return(1);
472: }
473:
474: char *
475: skipv(s)
476: char *s;
477: {
478: if(s>=word&&vowel(*s))
479: s--;
480: while(s>=word&&!vowel(*s))
481: s--;
482: return(s);
483: }
484:
485: vowel(c)
486: {
487: switch(Tolower(c)) {
488: case 'a':
489: case 'e':
490: case 'i':
491: case 'o':
492: case 'u':
493: case 'y':
494: return(1);
495: }
496: return(0);
497: }
498:
499: /* crummy way to Britishise */
500: ise()
501: {
502: register struct suftab *p;
503: for(p = suftab;p->suf;p++) {
504: ztos(p->suf);
505: ztos(p->d1);
506: ztos(p->a1);
507: }
508: }
509: ztos(s)
510: char *s;
511: {
512: for(;*s;s++)
513: if(*s=='z')
514: *s = 's';
515: }
516:
517: dict(bp,ep)
518: char *bp, *ep;
519: {
520: register char *wp;
521: long h;
522: register long *lp;
523: register i;
524: if(xflag)
525: printf("=%.*s\n",ep-bp,bp);
526: for(i=0; i<NP; i++) {
527: for (wp = bp, h = 0, lp = pow2[i]; wp < ep; ++wp, ++lp)
528: h += *wp * *lp;
529: h += '\n' * *lp;
530: h %= p[i];
531: if(get(h)==0)
532: return(0);
533: }
534: return(1);
535: }
This archive runs on limited infrastructure. Preserving old code on modern bandwidth. Automated agents are requested to crawl responsibly.