swish-e/src/list.c

/*
** Copyright (C) 1995, 1996, 1997, 1998 Hewlett-Packard Company
** Originally by Kevin Hughes, kev@kevcom.com, 3/11/94
**
** This program and library is free software; you can redistribute it and/or
** modify it under the terms of the GNU (Library) General Public License
** as published by the Free Software Foundation; either version 2
** of the License, or any later version.
**
** This program is distributed in the hope that it will be useful,
** but WITHOUT ANY WARRANTY; without even the implied warranty of
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
** GNU (Library) General Public License for more details.
**
** You should have received a copy of the GNU (Library) General Public License
** along with this program; if not, write to the Free Software
** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
**
** 1998-07-04  addfilter   ( R. Scherg)
** 2001-02-28  rasc  -- addfilter removed here
**
*/

#include "swish.h"
#include "list.h"
#include "mem.h"
#include "metanames.h"
#include "string.h"


struct swline *addswline(struct swline *rp, char *line)
{
struct swline *newnode;

        newnode = (struct swline *) emalloc(sizeof(struct swline));
        newnode->line = (char *) estrdup(line);
        newnode->next = NULL;

        if (rp == NULL)
                rp = newnode;
        else
                rp->nodep->next = newnode;
        
        rp->nodep = newnode;
        
        return rp;
}

struct swline *dupswline(struct swline *rp)
{
struct swline *tmp=NULL, *tmp2=NULL;
struct swline *newnode;
        while(rp)
        {
                newnode = (struct swline *) emalloc(sizeof(struct swline));
                newnode->line = (char *) estrdup(rp->line);
                newnode->next = NULL;
                
                if(!tmp)
                        tmp = newnode;
                else
                        tmp2->next=newnode;
                tmp2 = newnode;
                rp=rp->next;
        }
        return tmp;
}

IndexFILE *addindexfile(IndexFILE *rp, char *line)
{
    IndexFILE *newnode;

        newnode = (IndexFILE *) emalloc(sizeof(IndexFILE));
        memset( newnode, 0, sizeof(IndexFILE) );

        newnode->line = (char *) estrdup(line);


        init_header(&newnode->header);

        newnode->next = NULL;


    /* Add default meta names -- these will be replaced if reading from an index file */
        add_default_metanames(newnode);

        if (rp == NULL)
                rp = newnode;
        else
                rp->nodep->next = newnode;
        
        rp->nodep = newnode;
        
        return rp;
}


void freeswline(struct swline *tmplist)
{
struct swline *tmplist2;

        while (tmplist) {
                tmplist2 = tmplist->next;
                efree(tmplist->line);
                efree(tmplist);
                tmplist = tmplist2;
        }
}


void freeindexfile(IndexFILE *tmplist)
{
IndexFILE *tmplist2;

        while (tmplist) {
                tmplist2 = tmplist->next;
                efree(tmplist->line);
                efree(tmplist);
                tmplist = tmplist2;
        }
}


void init_header(INDEXDATAHEADER *header)
{

        header->lenwordchars=header->lenbeginchars=header->lenendchars=header->lenignorelastchar=header->lenignorefirstchar=header->lenbumpposchars=MAXCHARDEFINED;

        header->wordchars = (char *)emalloc(header->lenwordchars + 1);
        header->wordchars = SafeStrCopy(header->wordchars,WORDCHARS,&header->lenwordchars);
        sortstring(header->wordchars);  /* Sort chars and remove dups */
        makelookuptable(header->wordchars,header->wordcharslookuptable);

        header->beginchars = (char *)emalloc(header->lenbeginchars + 1);
        header->beginchars = SafeStrCopy(header->beginchars,BEGINCHARS,&header->lenbeginchars);
        sortstring(header->beginchars);  /* Sort chars and remove dups */
        makelookuptable(header->beginchars,header->begincharslookuptable);

        header->endchars = (char *)emalloc(header->lenendchars + 1);
        header->endchars = SafeStrCopy(header->endchars,ENDCHARS,&header->lenendchars);
        sortstring(header->endchars);  /* Sort chars and remove dups */
        makelookuptable(header->endchars,header->endcharslookuptable);

        header->ignorelastchar = (char *)emalloc(header->lenignorelastchar + 1);
        header->ignorelastchar = SafeStrCopy(header->ignorelastchar,IGNORELASTCHAR,&header->lenignorelastchar);
        sortstring(header->ignorelastchar);  /* Sort chars and remove dups */
        makelookuptable(header->ignorelastchar,header->ignorelastcharlookuptable);

        header->ignorefirstchar = (char *)emalloc(header->lenignorefirstchar + 1);
        header->ignorefirstchar = SafeStrCopy(header->ignorefirstchar,IGNOREFIRSTCHAR,&header->lenignorefirstchar);
        sortstring(header->ignorefirstchar);  /* Sort chars and remove dups */
        makelookuptable(header->ignorefirstchar,header->ignorefirstcharlookuptable);


        header->bumpposchars = (char *)emalloc(header->lenbumpposchars + 1);
        header->bumpposchars[0]='\0';

        header->lenindexedon=header->lensavedasheader=header->lenindexn=header->lenindexd=header->lenindexp=header->lenindexa=MAXSTRLEN;
        header->indexn = (char *)emalloc(header->lenindexn + 1);header->indexn[0]='\0';
        header->indexd = (char *)emalloc(header->lenindexd + 1);header->indexd[0]='\0';
        header->indexp = (char *)emalloc(header->lenindexp + 1);header->indexp[0]='\0';
        header->indexa = (char *)emalloc(header->lenindexa + 1);header->indexa[0]='\0';
        header->savedasheader = (char *)emalloc(header->lensavedasheader + 1);header->savedasheader[0]='\0';
        header->indexedon = (char *)emalloc(header->lenindexedon + 1);header->indexedon[0]='\0';

        header->ignoreTotalWordCountWhenRanking = 1;
        header->minwordlimit = MINWORDLIMIT;
        header->maxwordlimit = MAXWORDLIMIT;

        makelookuptable("",header->bumpposcharslookuptable); 

    BuildTranslateChars(header->translatecharslookuptable,(unsigned char *)"",(unsigned char *)"");


    /* this is to ignore numbers */
    header->numberchars_used_flag = 0;  /* not used by default*/
}


void free_header(INDEXDATAHEADER *header)
{
        if(header->lenwordchars) efree(header->wordchars);
        if(header->lenbeginchars) efree(header->beginchars);
        if(header->lenendchars) efree(header->endchars);
        if(header->lenignorefirstchar) efree(header->ignorefirstchar);
        if(header->lenignorelastchar) efree(header->ignorelastchar);
        if(header->lenindexn) efree(header->indexn);
        if(header->lenindexa) efree(header->indexa);
        if(header->lenindexp) efree(header->indexp);
        if(header->lenindexd) efree(header->indexd);
        if(header->lenindexedon) efree(header->indexedon);              
        if(header->lensavedasheader) efree(header->savedasheader);      
        if(header->lenbumpposchars) efree(header->bumpposchars);


    /* ??? temporary until metas and props are seperated */
    if ( header->propIDX_to_metaID )
        efree( header->propIDX_to_metaID );

    if ( header->metaID_to_PropIDX )
        efree( header->metaID_to_PropIDX );

#ifndef USE_BTREE
    if ( header->TotalWordsPerFile )
        efree( header->TotalWordsPerFile );
#endif

}


/* 2001/04Jose Ruiz
Splits a swline struct by char c */
void splitswline(struct swline *rp, int c)
{
struct swline *temp;
char *p;
        for(p=rp->line;(p=strrchr(rp->line,c));)
        {
                *p='\0';
                p++;
                if(*p)
                {
                        temp=(struct swline *)emalloc(sizeof(struct swline));
                        temp->next=rp->next;
                        temp->line=(char *)estrdup(p);
                        rp->next=temp;
                }
        }
}

1	adcroft	1.1	/*
2			** Copyright (C) 1995, 1996, 1997, 1998 Hewlett-Packard Company
3			** Originally by Kevin Hughes, kev@kevcom.com, 3/11/94
4			**
5			** This program and library is free software; you can redistribute it and/or
6			** modify it under the terms of the GNU (Library) General Public License
7			** as published by the Free Software Foundation; either version 2
8			** of the License, or any later version.
9			**
10			** This program is distributed in the hope that it will be useful,
11			** but WITHOUT ANY WARRANTY; without even the implied warranty of
12			** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13			** GNU (Library) General Public License for more details.
14			**
15			** You should have received a copy of the GNU (Library) General Public License
16			** along with this program; if not, write to the Free Software
17			** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
18			**
19			** 1998-07-04 addfilter ( R. Scherg)
20			** 2001-02-28 rasc -- addfilter removed here
21			**
22			*/
23
24			#include "swish.h"
25			#include "list.h"
26			#include "mem.h"
27			#include "metanames.h"
28			#include "string.h"
29
30
31			struct swline addswline(struct swline rp, char *line)
32			{
33			struct swline *newnode;
34
35			newnode = (struct swline *) emalloc(sizeof(struct swline));
36			newnode->line = (char *) estrdup(line);
37			newnode->next = NULL;
38
39			if (rp == NULL)
40			rp = newnode;
41			else
42			rp->nodep->next = newnode;
43
44			rp->nodep = newnode;
45
46			return rp;
47			}
48
49			struct swline dupswline(struct swline rp)
50			{
51			struct swline tmp=NULL, tmp2=NULL;
52			struct swline *newnode;
53			while(rp)
54			{
55			newnode = (struct swline *) emalloc(sizeof(struct swline));
56			newnode->line = (char *) estrdup(rp->line);
57			newnode->next = NULL;
58
59			if(!tmp)
60			tmp = newnode;
61			else
62			tmp2->next=newnode;
63			tmp2 = newnode;
64			rp=rp->next;
65			}
66			return tmp;
67			}
68
69			IndexFILE addindexfile(IndexFILE rp, char *line)
70			{
71			IndexFILE *newnode;
72
73			newnode = (IndexFILE *) emalloc(sizeof(IndexFILE));
74			memset( newnode, 0, sizeof(IndexFILE) );
75
76			newnode->line = (char *) estrdup(line);
77
78
79			init_header(&newnode->header);
80
81			newnode->next = NULL;
82
83
84			/* Add default meta names -- these will be replaced if reading from an index file */
85			add_default_metanames(newnode);
86
87			if (rp == NULL)
88			rp = newnode;
89			else
90			rp->nodep->next = newnode;
91
92			rp->nodep = newnode;
93
94			return rp;
95			}
96
97
98			void freeswline(struct swline *tmplist)
99			{
100			struct swline *tmplist2;
101
102			while (tmplist) {
103			tmplist2 = tmplist->next;
104			efree(tmplist->line);
105			efree(tmplist);
106			tmplist = tmplist2;
107			}
108			}
109
110
111			void freeindexfile(IndexFILE *tmplist)
112			{
113			IndexFILE *tmplist2;
114
115			while (tmplist) {
116			tmplist2 = tmplist->next;
117			efree(tmplist->line);
118			efree(tmplist);
119			tmplist = tmplist2;
120			}
121			}
122
123
124			void init_header(INDEXDATAHEADER *header)
125			{
126
127			header->lenwordchars=header->lenbeginchars=header->lenendchars=header->lenignorelastchar=header->lenignorefirstchar=header->lenbumpposchars=MAXCHARDEFINED;
128
129			header->wordchars = (char *)emalloc(header->lenwordchars + 1);
130			header->wordchars = SafeStrCopy(header->wordchars,WORDCHARS,&header->lenwordchars);
131			sortstring(header->wordchars); /* Sort chars and remove dups */
132			makelookuptable(header->wordchars,header->wordcharslookuptable);
133
134			header->beginchars = (char *)emalloc(header->lenbeginchars + 1);
135			header->beginchars = SafeStrCopy(header->beginchars,BEGINCHARS,&header->lenbeginchars);
136			sortstring(header->beginchars); /* Sort chars and remove dups */
137			makelookuptable(header->beginchars,header->begincharslookuptable);
138
139			header->endchars = (char *)emalloc(header->lenendchars + 1);
140			header->endchars = SafeStrCopy(header->endchars,ENDCHARS,&header->lenendchars);
141			sortstring(header->endchars); /* Sort chars and remove dups */
142			makelookuptable(header->endchars,header->endcharslookuptable);
143
144			header->ignorelastchar = (char *)emalloc(header->lenignorelastchar + 1);
145			header->ignorelastchar = SafeStrCopy(header->ignorelastchar,IGNORELASTCHAR,&header->lenignorelastchar);
146			sortstring(header->ignorelastchar); /* Sort chars and remove dups */
147			makelookuptable(header->ignorelastchar,header->ignorelastcharlookuptable);
148
149			header->ignorefirstchar = (char *)emalloc(header->lenignorefirstchar + 1);
150			header->ignorefirstchar = SafeStrCopy(header->ignorefirstchar,IGNOREFIRSTCHAR,&header->lenignorefirstchar);
151			sortstring(header->ignorefirstchar); /* Sort chars and remove dups */
152			makelookuptable(header->ignorefirstchar,header->ignorefirstcharlookuptable);
153
154
155			header->bumpposchars = (char *)emalloc(header->lenbumpposchars + 1);
156			header->bumpposchars[0]='\0';
157
158			header->lenindexedon=header->lensavedasheader=header->lenindexn=header->lenindexd=header->lenindexp=header->lenindexa=MAXSTRLEN;
159			header->indexn = (char *)emalloc(header->lenindexn + 1);header->indexn[0]='\0';
160			header->indexd = (char *)emalloc(header->lenindexd + 1);header->indexd[0]='\0';
161			header->indexp = (char *)emalloc(header->lenindexp + 1);header->indexp[0]='\0';
162			header->indexa = (char *)emalloc(header->lenindexa + 1);header->indexa[0]='\0';
163			header->savedasheader = (char *)emalloc(header->lensavedasheader + 1);header->savedasheader[0]='\0';
164			header->indexedon = (char *)emalloc(header->lenindexedon + 1);header->indexedon[0]='\0';
165
166			header->ignoreTotalWordCountWhenRanking = 1;
167			header->minwordlimit = MINWORDLIMIT;
168			header->maxwordlimit = MAXWORDLIMIT;
169
170			makelookuptable("",header->bumpposcharslookuptable);
171
172			BuildTranslateChars(header->translatecharslookuptable,(unsigned char )"",(unsigned char )"");
173
174
175			/* this is to ignore numbers */
176			header->numberchars_used_flag = 0; /* not used by default*/
177			}
178
179
180			void free_header(INDEXDATAHEADER *header)
181			{
182			if(header->lenwordchars) efree(header->wordchars);
183			if(header->lenbeginchars) efree(header->beginchars);
184			if(header->lenendchars) efree(header->endchars);
185			if(header->lenignorefirstchar) efree(header->ignorefirstchar);
186			if(header->lenignorelastchar) efree(header->ignorelastchar);
187			if(header->lenindexn) efree(header->indexn);
188			if(header->lenindexa) efree(header->indexa);
189			if(header->lenindexp) efree(header->indexp);
190			if(header->lenindexd) efree(header->indexd);
191			if(header->lenindexedon) efree(header->indexedon);
192			if(header->lensavedasheader) efree(header->savedasheader);
193			if(header->lenbumpposchars) efree(header->bumpposchars);
194
195
196			/* ??? temporary until metas and props are seperated */
197			if ( header->propIDX_to_metaID )
198			efree( header->propIDX_to_metaID );
199
200			if ( header->metaID_to_PropIDX )
201			efree( header->metaID_to_PropIDX );
202
203			#ifndef USE_BTREE
204			if ( header->TotalWordsPerFile )
205			efree( header->TotalWordsPerFile );
206			#endif
207
208			}
209
210
211			/* 2001/04Jose Ruiz
212			Splits a swline struct by char c */
213			void splitswline(struct swline *rp, int c)
214			{
215			struct swline *temp;
216			char *p;
217			for(p=rp->line;(p=strrchr(rp->line,c));)
218			{
219			*p='\0';
220			p++;
221			if(*p)
222			{
223			temp=(struct swline *)emalloc(sizeof(struct swline));
224			temp->next=rp->next;
225			temp->line=(char *)estrdup(p);
226			rp->next=temp;
227			}
228			}
229			}
230