WebSVN – wimsdev – Diff – /trunk/wims/src/Misc/modind.c



/*  This is an internal program,
 * used to index modules for search engine.
 */
 
#include "../wims.h"
#include "../Lib/libwims.h"
 
#define MAX_LANGS    MAX_LANGUAGES
#define MAX_MODULES    65536
char *moduledir=    "public_html/modules";
char *sheetdir=     "public_html/bases/sheet";

} mod[MAX_MODULES];
int modcnt;
 
char *mlist;
 
/*
void *xmalloc(size_t n)
{
    void *p;
    p=malloc(n);
    if(p==NULL) {
    printf("Malloc failure.\n");
    exit(1);
    }
    return p;
}
*/
 
/*
char *acctab="çéèêëúùûüáàâäãóòôöõíìïîñýÿÇÉÈÊËÚÙÛÜÁÀÂÃÄÓÒÔÖÕÍÌÏÎÑÝ",
     *deatab="ceeeeuuuuaaaaaoooooiiiinyyCEEEEUUUUAAAAAOOOOOIIIINY";
*/
/*  fold known accented letters to unaccented, other strange characters to space
 *  apostrophe is among the exceptions to be kept (important for multi-word expressions)
 */
void deaccent2(char *p)
{
    char *sp;
    char *v;
    for(sp=p;*sp;sp++) {
    if(*sp<0 && (v=strchr(acctab,*sp))!=NULL)

    char *pp;
    for(pp=p;*pp;pp++) if(!isalnum(*pp) && strchr("&$+*",*pp)==0) *pp=' ';
}
 
/*  Points to the end of the word */
/*
char *find_word_end(char *p)
{
    int i;
    for(i=0;!isspace(*p) && *p!=0 && i<MAX_LINELEN; p++,i++);
    return p;
}
*/
/*  Strips leading spaces */
/*
char *find_word_start(char *p)
{
    int i;
    for(i=0; isspace(*p) && i<MAX_LINELEN; p++,i++);
    return p;
}
*/
/*  Find first occurrence of word */
char *wordchr2(char *p, char *w)
{
    char *r;
 
    for(r=strstr(p,w);r!=NULL &&
    ( (r>p && !isspace(*(r-1))) || (!isspace(*(r+strlen(w))) && *(r+strlen(w))!=0) );

}
 
/*  find a variable in a string (math expression).
 * Returns the pointer or NULL.
 */
/*char *varchr(char *p, char *v)
{
    char *pp; int n=strlen(v);
    for(pp=strstr(p,v); pp!=NULL; pp=strstr(pp+1,v)) {
    if((pp==p || !isalnum(*(pp-1))) &&
       (!isalnum(*(pp+n)) || *(pp+n)==0)) break;
    }
    return pp;
}
*/
/*  strip trailing spaces; return string end. */
char *strip_trailing_spaces2(char *p)
{
    char *pp;
    if(*p==0) return p;
    for(pp=p+strlen(p)-1; pp>=p && isspace(*pp); *(pp--)=0);
    return pp;

    char *pp;
    pp=p; if(*pp=='<') pp++;
    for(; *pp && *pp!='>'; pp++) {
    if(*pp=='<') {
        pp=find_tag_end(pp)-1; continue;
    }
    if(*pp=='"') {
        pp=strchr(pp+1,'"');
        if(pp==NULL) return p+strlen(p); else continue;
    }
    if(*pp=='\'') {
        pp=strchr(pp+1,'\'');
        if(pp==NULL) return p+strlen(p); else continue;
    }
    }
    if(*pp=='>') pp++; return pp;
}
 
char *find_tag(char *p, char *tag)
{
    char *pp;
    int len;
    len=strlen(tag);
    for(pp=strchr(p,'<'); pp!=NULL && *pp; pp=strchr(pp+1,'<')) {
    if(strncasecmp(pp+1,tag,len)==0 && !isalnum(*(pp+1+len))) return pp;

    ovlstrcpy(pp,p2);
    }
}
 
/*  modify a string. Bufferlen must be at least MAX_LINELEN */
void string_modify3(char *start, char *bad_beg, char *bad_end, char *good,...)
{
    char buf[MAX_LINELEN+1];
    va_list vp;
 
    va_start(vp,good);
    vsnprintf(buf,sizeof(buf),good,vp); va_end(vp);
    if(strlen(start)-(bad_end-bad_beg)+strlen(buf)>=MAX_LINELEN)
      return; /* this is an error situation. */
    strcat(buf,bad_end);
    ovlstrcpy(bad_beg,buf);
}
 
/* add a space after comma to see end of words */
 
void comma(char *p)
{
    char *pp;
    for(pp=strchr(p,','); pp; pp=strchr(pp+1,','))
      string_modify3(p,pp,pp+1,", ");
}
 
void _getdef(char buf[], char *name, char value[])
{
    char *p1, *p2, *p3;

    p3=strchr(p2,'\n');
    p2=find_word_start(p2+1);
    if(p3 <= p2) continue;
    snprintf(value,MAX_LINELEN,"%s",p2);
    if(p3!=NULL && p3-p2<MAX_LINELEN) value[p3-p2]=0;
    strip_trailing_spaces2(value);
    break;
    }
}
 
/*  Get variable definition from a file.

    for(i=0,p1=find_word_start(ibuf);
    i<SHEETINDEX_NO-1 && *p1!=':' && *p1!=0;
    i++,p1=p2) {
    p2=strchr(p1,'\n');
    if(p2!=NULL) *p2++=0; else p2=p1+strlen(p1);
    p1=find_word_start(p1); strip_trailing_spaces2(p1);
    snprintf(sindbuf[i],MAX_LINELEN,"%s",p1);
    }
    p2=strstr(p1,"\n:"); if(p2==NULL) p2=p1+strlen(p1);
    else *p2=0;
    p1=find_word_start(p1); strip_trailing_spaces2(p1);
    for(p2=p1;*p2;p2++) if(*p2=='\n') *p2=' ';
    ovlstrcpy(sindbuf[s_information],p1);
    return 0;
}
 

    int i, ll;
    char *p;
    FILE *f;
 
    if(!isalnum(*word) || (ll=strlen(word))<2 ||
       wordchr2(taken,word)!=NULL ||
       wordchr2(ignore[lind],word)!=NULL ||
       takenlen>=MAX_LINELEN-ll-16)
      return;
    if(ll==2 && (!isdigit(word[0]) || !isalpha(word[1]))) return;
    for(p=word;*p;p++) if(!isalnum(*p) && *p!=' ') return;
    taken[takenlen++]=' '; taken[takenlen++]=' ';

    towords(indbuf[i_category]);
/*   list the categories (among A=all,X=eXercise,O,D,...) corresponding
 *   to this module
 */
    for(i=catcnt=0;i<catno && catcnt<16;i++) {
    if(wordchr2(indbuf[i_category],cat[i].name)!=NULL)
      categories[catcnt++]=cat[i].typ;
    }
    if(catcnt==0) return;
    if(categories[0]!=cat[0].typ)
      categories[catcnt++]=cat[0].typ;

    fprintf(versionf,"%d:%s\n",serial,indbuf[i_version]);
 
/*   add module's information in html page for robots  */
    snprintf(buf,sizeof(buf),"%s",indbuf[i_description]);
    for(pp=strchr(buf,','); pp; pp=strchr(pp,','))
      string_modify3(buf,pp,pp+1,"&#44;");
    if(strcmp(module_language,lang[lind])==0)
      fprintf(robotf,"%s ,%s,%s,%s,%s\n",name,module_language,name,
          indbuf[i_title], buf);
 
/*   Normalize the information of trlist, using dictionary

    entrycount=dentrycount; dicbuf=ddicbuf;
    memmove(entry,dentry,dentrycount*sizeof(entry[0]));
    unknown_type=unk_leave;
    for(i=0;i<trcnt;i++) {
    detag(indbuf[trlist[i]]);
    deaccent2(indbuf[trlist[i]]);
    comma(indbuf[trlist[i]]);
    singlespace2(indbuf[trlist[i]]);
    translate(indbuf[trlist[i]]);
    }
/*   Normalize the information, using dictionary
 *   bases/sys/words.xx with suffix translation
 */

{
    int ll;
    char *p;
 
    if(!isalnum(*word) || (ll=strlen(word))<2 ||
       wordchr2(taken,word)!=NULL ||
       wordchr2(ignore[lind],word)!=NULL ||
       takenlen>=MAX_LINELEN-ll-16)
      return;
    if(ll==2 && (!isdigit(word[0]) || !isalpha(word[1]))) return;
    for(p=word;*p;p++) if(!isalnum(*p) && *p!=' ') return;
    taken[takenlen++]=' ';taken[takenlen++]=' ';

    entrycount=dentrycount; dicbuf=ddicbuf;
    memmove(entry,dentry,dentrycount*sizeof(entry[0]));
    unknown_type=unk_leave;
    for(i=0;i<trcnt;i++) {
    detag(sindbuf[trlist[i]]);
    deaccent2(sindbuf[trlist[i]]);
    comma(sindbuf[trlist[i]]);
    singlespace2(sindbuf[trlist[i]]);
    translate(sindbuf[trlist[i]]);
    }
 
    entrycount=mentrycount; dicbuf=mdicbuf;
    memmove(entry,mentry,mentrycount*sizeof(entry[0]));

Rev 7915	Rev 8100
Line 18...	Line 18...
18	/* This is an internal program,	18	/* This is an internal program,
19	* used to index modules for search engine.	19	* used to index modules for search engine.
20	*/	20	*/
21		21
22	#include "../wims.h"	22	#include "../wims.h"
23	#include "../Lib/~~basicstr~~.c"	23	#include "../Lib/libwims.h"
24		24
25	#define MAX_LANGS MAX_LANGUAGES	25	#define MAX_LANGS MAX_LANGUAGES
26	#define MAX_MODULES 65536	26	#define MAX_MODULES 65536
27	char *moduledir= "public_html/modules";	27	char *moduledir= "public_html/modules";
28	char *sheetdir= "public_html/bases/sheet";	28	char *sheetdir= "public_html/bases/sheet";
Line 73...	Line 73...
73	} mod[MAX_MODULES];	73	} mod[MAX_MODULES];
74	int modcnt;	74	int modcnt;
75		75
76	char *mlist;	76	char *mlist;
77		77
-		78	/*
78	void *xmalloc(size_t n)	79	void *xmalloc(size_t n)
79	{	80	{
80	void *p;	81	void *p;
81	p=malloc(n);	82	p=malloc(n);
82	if(p==NULL) {	83	if(p==NULL) {
83	printf("Malloc failure.\n");	84	printf("Malloc failure.\n");
84	exit(1);	85	exit(1);
85	}	86	}
86	return p;	87	return p;
87	}	88	}
-		89	*/
88		90
-		91	/*
89	char *~~acctab=~~"~~çéèêëúùûüáàâäãóòôöõíìïîñýÇÉÈÊËÚÙÛÜÁÀÂÃÄÓÒÔÖÕÍÌÏÎÑÝ~~",	92	char *acctab="çéèêëúùûüáàâäãóòôöõíìïîñýÿÇÉÈÊËÚÙÛÜÁÀÂÃÄÓÒÔÖÕÍÌÏÎÑÝ",
90	*~~deatab=~~"~~ceeeeuuuuaaaaaoooooiiiinyCEEEEUUUUAAAAAOOOOOIIIINY~~";	93	*deatab="ceeeeuuuuaaaaaoooooiiiinyyCEEEEUUUUAAAAAOOOOOIIIINY";
91		94	*/
92	/* fold known accented letters to unaccented, other strange characters to space	95	/* fold known accented letters to unaccented, other strange characters to space
93	* apostrophe is among the exceptions to be kept (important for multi-word expressions)	96	* apostrophe is among the exceptions to be kept (important for multi-word expressions)
94	*/	97	*/
95	void ~~deaccent~~(char *p)	98	void deaccent2(char *p)
96	{	99	{
97	char *sp;	100	char *sp;
98	char *v;	101	char *v;
99	for(sp=p;*sp;sp++) {	102	for(sp=p;*sp;sp++) {
100	if(sp<0 && (v=strchr(acctab,sp))!=NULL)	103	if(sp<0 && (v=strchr(acctab,sp))!=NULL)
Line 110...	Line 113...
110	char *pp;	113	char *pp;
111	for(pp=p;pp;pp++) if(!isalnum(pp) && strchr("&$+",pp)==0) *pp=' ';	114	for(pp=p;pp;pp++) if(!isalnum(pp) && strchr("&$+",pp)==0) *pp=' ';
112	}	115	}
113		116
114	/* Points to the end of the word */	117	/* Points to the end of the word */
-		118	/*
115	char find_word_end(char p)	119	char find_word_end(char p)
116	{	120	{
117	int i;	121	int i;
118	for(i=0;!isspace(p) && p!=0 && i<MAX_LINELEN; p++,i++);	122	for(i=0;!isspace(p) && p!=0 && i<MAX_LINELEN; p++,i++);
119	return p;	123	return p;
120	}	124	}
121		125	*/
122	/* Strips leading spaces */	126	/* Strips leading spaces */
-		127	/*
123	char find_word_start(char p)	128	char find_word_start(char p)
124	{	129	{
125	int i;	130	int i;
126	for(i=0; isspace(*p) && i<MAX_LINELEN; p++,i++);	131	for(i=0; isspace(*p) && i<MAX_LINELEN; p++,i++);
127	return p;	132	return p;
128	}	133	}
129		134	*/
130	/* Find first occurrence of word */	135	/* Find first occurrence of word */
131	char ~~wordchr~~(char p, char *w)	136	char wordchr2(char p, char *w)
132	{	137	{
133	char *r;	138	char *r;
134		139
135	for(r=strstr(p,w);r!=NULL &&	140	for(r=strstr(p,w);r!=NULL &&
136	( (r>p && !isspace((r-1))) \|\| (!isspace((r+strlen(w))) && *(r+strlen(w))!=0) );	141	( (r>p && !isspace((r-1))) \|\| (!isspace((r+strlen(w))) && *(r+strlen(w))!=0) );
Line 139...	Line 144...
139	}	144	}
140		145
141	/* find a variable in a string (math expression).	146	/* find a variable in a string (math expression).
142	* Returns the pointer or NULL.	147	* Returns the pointer or NULL.
143	*/	148	*/
144	char varchr(char p, char *v)	149	/char varchr(char p, char v)
145	{	150	{
146	char *pp; int n=strlen(v);	151	char *pp; int n=strlen(v);
147	for(pp=strstr(p,v); pp!=NULL; pp=strstr(pp+1,v)) {	152	for(pp=strstr(p,v); pp!=NULL; pp=strstr(pp+1,v)) {
148	if((pp==p \|\| !isalnum(*(pp-1))) &&	153	if((pp==p \|\| !isalnum(*(pp-1))) &&
149	(!isalnum((pp+n)) \|\| (pp+n)==0)) break;	154	(!isalnum((pp+n)) \|\| (pp+n)==0)) break;
150	}	155	}
151	return pp;	156	return pp;
152	}	157	}
153		158	*/
154	/* strip trailing spaces; return string end. */	159	/* strip trailing spaces; return string end. */
155	char ~~strip_trailing_spaces~~(char p)	160	char strip_trailing_spaces2(char p)
156	{	161	{
157	char *pp;	162	char *pp;
158	if(*p==0) return p;	163	if(*p==0) return p;
159	for(pp=p+strlen(p)-1; pp>=p && isspace(pp); (pp--)=0);	164	for(pp=p+strlen(p)-1; pp>=p && isspace(pp); (pp--)=0);
160	return pp;	165	return pp;
Line 165...	Line 170...
165	char *pp;	170	char *pp;
166	pp=p; if(*pp=='<') pp++;	171	pp=p; if(*pp=='<') pp++;
167	for(; pp && pp!='>'; pp++) {	172	for(; pp && pp!='>'; pp++) {
168	if(*pp=='<') {	173	if(*pp=='<') {
169	pp=find_tag_end(pp)-1; continue;	174	pp=find_tag_end(pp)-1; continue;
170	}	175	}
171	if(*pp=='"') {	176	if(*pp=='"') {
172	pp=strchr(pp+1,'"');	177	pp=strchr(pp+1,'"');
173	if(pp==NULL) return p+strlen(p); else continue;	178	if(pp==NULL) return p+strlen(p); else continue;
174	}	179	}
175	if(*pp=='\'') {	180	if(*pp=='\'') {
176	pp=strchr(pp+1,'\'');	181	pp=strchr(pp+1,'\'');
177	if(pp==NULL) return p+strlen(p); else continue;	182	if(pp==NULL) return p+strlen(p); else continue;
178	}	183	}
179	}	184	}
180	if(*pp=='>') pp++; return pp;	185	if(*pp=='>') pp++; return pp;
181	}	186	}
182		187
183	char find_tag(char p, char *tag)	188	char find_tag(char p, char *tag)
184	{	189	{
185	char *pp;	190	char *pp;
186	int len;	191	int len;
187	len=strlen(tag);	192	len=strlen(tag);
188	for(pp=strchr(p,'<'); pp!=NULL && *pp; pp=strchr(pp+1,'<')) {	193	for(pp=strchr(p,'<'); pp!=NULL && *pp; pp=strchr(pp+1,'<')) {
189	if(strncasecmp(pp+1,tag,len)==0 && !isalnum(*(pp+1+len))) return pp;	194	if(strncasecmp(pp+1,tag,len)==0 && !isalnum(*(pp+1+len))) return pp;
Line 201...	Line 206...
201	ovlstrcpy(pp,p2);	206	ovlstrcpy(pp,p2);
202	}	207	}
203	}	208	}
204		209
205	/* modify a string. Bufferlen must be at least MAX_LINELEN */	210	/* modify a string. Bufferlen must be at least MAX_LINELEN */
206	void ~~string_modify~~(char start, char bad_beg, char bad_end, char good,...)	211	void string_modify3(char start, char bad_beg, char bad_end, char good,...)
207	{	212	{
208	char buf[MAX_LINELEN+1];	213	char buf[MAX_LINELEN+1];
209	va_list vp;	214	va_list vp;
210		215
211	va_start(vp,good);	216	va_start(vp,good);
212	vsnprintf(buf,sizeof(buf),good,vp); va_end(vp);	217	vsnprintf(buf,sizeof(buf),good,vp); va_end(vp);
213	if(strlen(start)-(bad_end-bad_beg)+strlen(buf)>=MAX_LINELEN)	218	if(strlen(start)-(bad_end-bad_beg)+strlen(buf)>=MAX_LINELEN)
214	return;	219	return; /* this is an error situation. */
215	strcat(buf,bad_end);	220	strcat(buf,bad_end);
216	ovlstrcpy(bad_beg,buf);	221	ovlstrcpy(bad_beg,buf);
217	}	222	}
218		223
219	/* add a space after comma to see end of words */	224	/* add a space after comma to see end of words */
220		225
221	void comma(char *p)	226	void comma(char *p)
222	{	227	{
223	char *pp;	228	char *pp;
224	for(pp=strchr(p,','); pp; pp=strchr(pp+1,','))	229	for(pp=strchr(p,','); pp; pp=strchr(pp+1,','))
225	~~string_modify~~(p,pp,pp+1,", ");	230	string_modify3(p,pp,pp+1,", ");
226	}	231	}
227		232
228	void _getdef(char buf[], char *name, char value[])	233	void _getdef(char buf[], char *name, char value[])
229	{	234	{
230	char p1, p2, *p3;	235	char p1, p2, *p3;
Line 238...	Line 243...
238	p3=strchr(p2,'\n');	243	p3=strchr(p2,'\n');
239	p2=find_word_start(p2+1);	244	p2=find_word_start(p2+1);
240	if(p3 <= p2) continue;	245	if(p3 <= p2) continue;
241	snprintf(value,MAX_LINELEN,"%s",p2);	246	snprintf(value,MAX_LINELEN,"%s",p2);
242	if(p3!=NULL && p3-p2<MAX_LINELEN) value[p3-p2]=0;	247	if(p3!=NULL && p3-p2<MAX_LINELEN) value[p3-p2]=0;
243	~~strip_trailing_spaces~~(value);	248	strip_trailing_spaces2(value);
244	break;	249	break;
245	}	250	}
246	}	251	}
247		252
248	/* Get variable definition from a file.	253	/* Get variable definition from a file.
Line 466...	Line 471...
466	for(i=0,p1=find_word_start(ibuf);	471	for(i=0,p1=find_word_start(ibuf);
467	i<SHEETINDEX_NO-1 && p1!=':' && p1!=0;	472	i<SHEETINDEX_NO-1 && p1!=':' && p1!=0;
468	i++,p1=p2) {	473	i++,p1=p2) {
469	p2=strchr(p1,'\n');	474	p2=strchr(p1,'\n');
470	if(p2!=NULL) *p2++=0; else p2=p1+strlen(p1);	475	if(p2!=NULL) *p2++=0; else p2=p1+strlen(p1);
471	p1=find_word_start(p1); ~~strip_trailing_spaces~~(p1);	476	p1=find_word_start(p1); strip_trailing_spaces2(p1);
472	snprintf(sindbuf[i],MAX_LINELEN,"%s",p1);	477	snprintf(sindbuf[i],MAX_LINELEN,"%s",p1);
473	}	478	}
474	p2=strstr(p1,"\n:"); if(p2==NULL) p2=p1+strlen(p1);	479	p2=strstr(p1,"\n:"); if(p2==NULL) p2=p1+strlen(p1);
475	else *p2=0;	480	else *p2=0;
476	p1=find_word_start(p1); ~~strip_trailing_spaces~~(p1);	481	p1=find_word_start(p1); strip_trailing_spaces2(p1);
477	for(p2=p1;p2;p2++) if(p2=='\n') *p2=' ';	482	for(p2=p1;p2;p2++) if(p2=='\n') *p2=' ';
478	ovlstrcpy(sindbuf[s_information],p1);	483	ovlstrcpy(sindbuf[s_information],p1);
479	return 0;	484	return 0;
480	}	485	}
481		486
Line 489...	Line 494...
489	int i, ll;	494	int i, ll;
490	char *p;	495	char *p;
491	FILE *f;	496	FILE *f;
492		497
493	if(!isalnum(*word) \|\| (ll=strlen(word))<2 \|\|	498	if(!isalnum(*word) \|\| (ll=strlen(word))<2 \|\|
494	~~wordchr~~(taken,word)!=NULL \|\|	499	wordchr2(taken,word)!=NULL \|\|
495	~~wordchr~~(ignore[lind],word)!=NULL \|\|	500	wordchr2(ignore[lind],word)!=NULL \|\|
496	takenlen>=MAX_LINELEN-ll-16)	501	takenlen>=MAX_LINELEN-ll-16)
497	return;	502	return;
498	if(ll==2 && (!isdigit(word[0]) \|\| !isalpha(word[1]))) return;	503	if(ll==2 && (!isdigit(word[0]) \|\| !isalpha(word[1]))) return;
499	for(p=word;p;p++) if(!isalnum(p) && *p!=' ') return;	504	for(p=word;p;p++) if(!isalnum(p) && *p!=' ') return;
500	taken[takenlen++]=' '; taken[takenlen++]=' ';	505	taken[takenlen++]=' '; taken[takenlen++]=' ';
Line 546...	Line 551...
546	towords(indbuf[i_category]);	551	towords(indbuf[i_category]);
547	/* list the categories (among A=all,X=eXercise,O,D,...) corresponding	552	/* list the categories (among A=all,X=eXercise,O,D,...) corresponding
548	* to this module	553	* to this module
549	*/	554	*/
550	for(i=catcnt=0;i<catno && catcnt<16;i++) {	555	for(i=catcnt=0;i<catno && catcnt<16;i++) {
551	if(~~wordchr~~(indbuf[i_category],cat[i].name)!=NULL)	556	if(wordchr2(indbuf[i_category],cat[i].name)!=NULL)
552	categories[catcnt++]=cat[i].typ;	557	categories[catcnt++]=cat[i].typ;
553	}	558	}
554	if(catcnt==0) return;	559	if(catcnt==0) return;
555	if(categories[0]!=cat[0].typ)	560	if(categories[0]!=cat[0].typ)
556	categories[catcnt++]=cat[0].typ;	561	categories[catcnt++]=cat[0].typ;
Line 571...	Line 576...
571	fprintf(versionf,"%d:%s\n",serial,indbuf[i_version]);	576	fprintf(versionf,"%d:%s\n",serial,indbuf[i_version]);
572		577
573	/* add module's information in html page for robots */	578	/* add module's information in html page for robots */
574	snprintf(buf,sizeof(buf),"%s",indbuf[i_description]);	579	snprintf(buf,sizeof(buf),"%s",indbuf[i_description]);
575	for(pp=strchr(buf,','); pp; pp=strchr(pp,','))	580	for(pp=strchr(buf,','); pp; pp=strchr(pp,','))
576	~~string_modify~~(buf,pp,pp+1,",");	581	string_modify3(buf,pp,pp+1,",");
577	if(strcmp(module_language,lang[lind])==0)	582	if(strcmp(module_language,lang[lind])==0)
578	fprintf(robotf,"%s ,%s,%s,%s,%s\n",name,module_language,name,	583	fprintf(robotf,"%s ,%s,%s,%s,%s\n",name,module_language,name,
579	indbuf[i_title], buf);	584	indbuf[i_title], buf);
580		585
581	/* Normalize the information of trlist, using dictionary	586	/* Normalize the information of trlist, using dictionary
Line 584...	Line 589...
584	entrycount=dentrycount; dicbuf=ddicbuf;	589	entrycount=dentrycount; dicbuf=ddicbuf;
585	memmove(entry,dentry,dentrycount*sizeof(entry[0]));	590	memmove(entry,dentry,dentrycount*sizeof(entry[0]));
586	unknown_type=unk_leave;	591	unknown_type=unk_leave;
587	for(i=0;i<trcnt;i++) {	592	for(i=0;i<trcnt;i++) {
588	detag(indbuf[trlist[i]]);	593	detag(indbuf[trlist[i]]);
589	~~deaccent~~(indbuf[trlist[i]]);	594	deaccent2(indbuf[trlist[i]]);
590	comma(indbuf[trlist[i]]);	595	comma(indbuf[trlist[i]]);
591	~~singlespace~~(indbuf[trlist[i]]);	596	singlespace2(indbuf[trlist[i]]);
592	translate(indbuf[trlist[i]]);	597	translate(indbuf[trlist[i]]);
593	}	598	}
594	/* Normalize the information, using dictionary	599	/* Normalize the information, using dictionary
595	* bases/sys/words.xx with suffix translation	600	* bases/sys/words.xx with suffix translation
596	*/	601	*/
Line 718...	Line 723...
718	{	723	{
719	int ll;	724	int ll;
720	char *p;	725	char *p;
721		726
722	if(!isalnum(*word) \|\| (ll=strlen(word))<2 \|\|	727	if(!isalnum(*word) \|\| (ll=strlen(word))<2 \|\|
723	~~wordchr~~(taken,word)!=NULL \|\|	728	wordchr2(taken,word)!=NULL \|\|
724	~~wordchr~~(ignore[lind],word)!=NULL \|\|	729	wordchr2(ignore[lind],word)!=NULL \|\|
725	takenlen>=MAX_LINELEN-ll-16)	730	takenlen>=MAX_LINELEN-ll-16)
726	return;	731	return;
727	if(ll==2 && (!isdigit(word[0]) \|\| !isalpha(word[1]))) return;	732	if(ll==2 && (!isdigit(word[0]) \|\| !isalpha(word[1]))) return;
728	for(p=word;p;p++) if(!isalnum(p) && *p!=' ') return;	733	for(p=word;p;p++) if(!isalnum(p) && *p!=' ') return;
729	taken[takenlen++]=' ';taken[takenlen++]=' ';	734	taken[takenlen++]=' ';taken[takenlen++]=' ';
Line 750...	Line 755...
750	entrycount=dentrycount; dicbuf=ddicbuf;	755	entrycount=dentrycount; dicbuf=ddicbuf;
751	memmove(entry,dentry,dentrycount*sizeof(entry[0]));	756	memmove(entry,dentry,dentrycount*sizeof(entry[0]));
752	unknown_type=unk_leave;	757	unknown_type=unk_leave;
753	for(i=0;i<trcnt;i++) {	758	for(i=0;i<trcnt;i++) {
754	detag(sindbuf[trlist[i]]);	759	detag(sindbuf[trlist[i]]);
755	~~deaccent~~(sindbuf[trlist[i]]);	760	deaccent2(sindbuf[trlist[i]]);
756	comma(sindbuf[trlist[i]]);	761	comma(sindbuf[trlist[i]]);
757	~~singlespace~~(sindbuf[trlist[i]]);	762	singlespace2(sindbuf[trlist[i]]);
758	translate(sindbuf[trlist[i]]);	763	translate(sindbuf[trlist[i]]);
759	}	764	}
760		765
761	entrycount=mentrycount; dicbuf=mdicbuf;	766	entrycount=mentrycount; dicbuf=mdicbuf;
762	memmove(entry,mentry,mentrycount*sizeof(entry[0]));	767	memmove(entry,mentry,mentrycount*sizeof(entry[0]));

Subversion Repositories wimsdev

(root)/trunk/wims/src/Misc/modind.c – Rev 7915 → 8100