int main(int argc, char** argv)
{
int i;
int al, wl;
FILE * wrdlst;
FILE * afflst;
char *wf, *af;
char * ap;
char ts[MAX_LN_LEN];
(void)argc;
/* first parse the command line options */
/* arg1 - munched wordlist, arg2 - affix file */
if (argv[1]) {
wf = mystrdup(argv[1]);
} else {
fprintf(stderr,"correct syntax is:\n");
fprintf(stderr,"unmunch dic_file affix_file\n");
exit(1);
}
if (argv[2]) {
af = mystrdup(argv[2]);
} else {
fprintf(stderr,"correct syntax is:\n");
fprintf(stderr,"unmunch dic_file affix_file\n");
exit(1);
}
/* open the affix file */
afflst = fopen(af,"r");
if (!afflst) {
fprintf(stderr,"Error - could not open affix description file\n");
exit(1);
}
/* step one is to parse the affix file building up the internal
affix data structures */
numpfx = 0;
numsfx = 0;
fullstrip = 0;
if (parse_aff_file(afflst)) {
fprintf(stderr,"Error - in affix file loading\n");
exit(1);
}
fclose(afflst);
fprintf(stderr,"parsed in %d prefixes and %d suffixes\n",numpfx,numsfx);
/* affix file is now parsed so create hash table of wordlist on the fly */
/* open the wordlist */
wrdlst = fopen(wf,"r");
if (!wrdlst) {
fprintf(stderr,"Error - could not open word list file\n");
exit(1);
}
/* skip over the hash table size */
if (! fgets(ts, MAX_LN_LEN-1,wrdlst)) {
fclose(wrdlst);
return 2;
}
mychomp(ts);
while (fgets(ts,MAX_LN_LEN-1,wrdlst)) {
mychomp(ts);
/* split each line into word and affix char strings */
ap = strchr(ts,'/');
if (ap) {
*ap = '\0';
ap++;
al = strlen(ap);
} else {
al = 0;
ap = NULL;
}
wl = strlen(ts);
numwords = 0;
wlist[numwords].word = mystrdup(ts);
wlist[numwords].pallow = 0;
numwords++;
if (al)
expand_rootword(ts,wl,ap);
for (i=0; i < numwords; i++) {
fprintf(stdout,"%s\n",wlist[i].word);
free(wlist[i].word);
wlist[i].word = NULL;
wlist[i].pallow = 0;
}
}
fclose(wrdlst);
return 0;
}
int main(int argc, char** argv)
{
int i, j, k, n;
int rl, p , nwl;
int al;
FILE * wrdlst;
FILE * afflst;
char *nword, *wf, *af;
char as[(MAX_PREFIXES + MAX_SUFFIXES)];
char * ap;
struct hentry * ep;
struct hentry * ep1;
struct affent * pfxp;
struct affent * sfxp;
/* first parse the command line options */
/* arg1 - wordlist, arg2 - affix file */
if (argv[1]) {
wf = mystrdup(argv[1]);
} else {
fprintf(stderr,"correct syntax is:\n");
fprintf(stderr,"munch word_list_file affix_file\n");
exit(1);
}
if (argv[2]) {
af = mystrdup(argv[2]);
} else {
fprintf(stderr,"correct syntax is:\n");
fprintf(stderr,"munch word_list_file affix_file\n");
exit(1);
}
/* open the affix file */
afflst = fopen(af,"r");
if (!afflst) {
fprintf(stderr,"Error - could not open affix description file\n");
exit(1);
}
/* step one is to parse the affix file building up the internal
affix data structures */
numpfx = 0;
numsfx = 0;
parse_aff_file(afflst);
fclose(afflst);
fprintf(stderr,"parsed in %d prefixes and %d suffixes\n",numpfx,numsfx);
/* affix file is now parsed so create hash table of wordlist on the fly */
/* open the wordlist */
wrdlst = fopen(wf,"r");
if (!wrdlst) {
fprintf(stderr,"Error - could not open word list file\n");
exit(1);
}
if (load_tables(wrdlst)) {
fprintf(stderr,"Error building hash tables\n");
exit(1);
}
fclose(wrdlst);
for (i=0; i< tablesize; i++) {
ep = &tableptr[i];
if (ep->word == NULL) continue;
for ( ; ep != NULL; ep = ep->next) {
numroots = 0;
aff_chk(ep->word,strlen(ep->word));
if (numroots) {
/* now there might be a number of combinations */
/* of prefixes and suffixes that might match this */
/* word. So how to choose? As a first shot look */
/* for the shortest remaining root word to */
/* to maximize the combinatorial power */
/* but be careful, do not REQUIRE a specific combination */
/* of a prefix and a suffix to generate the word since */
/* that violates the rule that the root word with just */
/* the prefix or just the suffix must also exist in the */
/* wordlist as well */
/* in fact because of the cross product issue, this not a */
/* simple choice since some combinations of previous */
/* prefixes and new suffixes may not be valid. */
/* The only way to know is to simply try them all */
rl = 1000;
p = -1;
for (j = 0; j < numroots; j++){
/* first collect the root word info and build up */
/* the potential new affix string */
nword = (roots[j].hashent)->word;
nwl = strlen(nword);
*as = '\0';
al = 0;
ap = as;
if (roots[j].prefix) *ap++ = (roots[j].prefix)->achar;
if (roots[j].suffix) *ap++ = (roots[j].suffix)->achar;
if ((roots[j].hashent)->affstr) {
strcpy(ap,(roots[j].hashent)->affstr);
} else {
*ap = '\0';
}
al =strlen(as);
/* now expand the potential affix string to generate */
/* all legal words and make sure they all exist in the */
/* word list */
numwords = 0;
wlist[numwords].word = mystrdup(nword);
wlist[numwords].pallow = 0;
numwords++;
n = 0;
if (al)
expand_rootword(nword,nwl,as,al);
for (k=0; k<numwords; k++) {
if (lookup(wlist[k].word)) n++;
free(wlist[k].word);
wlist[k].word = NULL;
wlist[k].pallow = 0;
}
/* if all exist in word list then okay */
if (n == numwords) {
if (nwl < rl) {
rl = nwl;
p = j;
}
}
}
if (p != -1) {
ep1 = roots[p].hashent;
pfxp = roots[p].prefix;
sfxp = roots[p].suffix;
ep1->keep = 1;
if (pfxp != NULL) add_affix_char(ep1,pfxp->achar);
if (sfxp != NULL) add_affix_char(ep1,sfxp->achar);
} else {
ep->keep = 1;
}
} else {
ep->keep = 1;
}
}
}
/* now output only the words to keep along with affixes info */
/* first count how many words that is */
k = 0;
for (i=0; i< tablesize; i++) {
ep = &tableptr[i];
if (ep->word == NULL) continue;
for ( ; ep != NULL; ep = ep->next) {
if (ep->keep > 0) k++;
}
}
fprintf(stdout,"%d\n",k);
for (i=0; i< tablesize; i++) {
ep = &tableptr[i];
if (ep->word == NULL) continue;
for ( ; ep != NULL; ep = ep->next) {
if (ep->keep > 0) {
if (ep->affstr != NULL) {
fprintf(stdout,"%s/%s\n",ep->word,ep->affstr);
} else {
fprintf(stdout,"%s\n",ep->word);
}
}
}
}
return 0;
}
