1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
/* Copyright (C) 2000 MySQL AB & MySQL Finland AB & TCX DataKonsult AB
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) 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 General Public License for more details.
You should have received a copy of the GNU 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 */
/* Written by Sergei A. Golubchik, who has a shared copyright to this code */
#include "ftdefs.h"
#ifdef EVAL_RUN
#ifdef PIVOT_STAT
ulong collstat=0;
#endif
#endif /* EVAL_RUN */
typedef struct st_ft_docstat {
FT_WORD *list;
uint uniq;
double sum;
#ifdef EVAL_RUN
uint words, totlen;
double max, nsum, nsum2;
#endif /* EVAL_RUN */
MI_INFO *info;
uint keynr;
byte *keybuf;
} FT_DOCSTAT;
static int FT_WORD_cmp(FT_WORD *w1, FT_WORD *w2)
{
return _mi_compare_text(default_charset_info,
(uchar*) w1->pos,w1->len,
(uchar*) w2->pos, w2->len,0);
}
static int walk_and_copy(FT_WORD *word,uint32 count,FT_DOCSTAT *docstat)
{
word->weight=LWS_IN_USE;
#ifdef EVAL_RUN
word->cnt= (uchar) count;
if(docstat->max < word->weight) docstat->max=word->weight;
docstat->words+=count;
docstat->totlen+=word->len;
#endif /* EVAL_RUN */
docstat->sum+=word->weight;
memcpy_fixed((docstat->list)++,word,sizeof(FT_WORD));
return 0;
}
/* transforms tree of words into the array, applying normalization */
FT_WORD * ft_linearize(MI_INFO *info, uint keynr, byte *keybuf, TREE *wtree)
{
FT_WORD *wlist,*p;
FT_DOCSTAT docstat;
if ((wlist=(FT_WORD *) my_malloc(sizeof(FT_WORD)*
(1+wtree->elements_in_tree),MYF(0))))
{
docstat.info=info;
docstat.keynr=keynr;
docstat.keybuf=keybuf;
docstat.list=wlist;
docstat.uniq=wtree->elements_in_tree;
#ifdef EVAL_RUN
docstat.nsum=docstat.nsum2=docstat.max=docstat.words=docstat.totlen=
#endif /* EVAL_RUN */
docstat.sum=0;
tree_walk(wtree,(tree_walk_action)&walk_and_copy,&docstat,left_root_right);
}
delete_tree(wtree);
my_free((char*) wtree,MYF(0));
if (!wlist)
return NULL;
docstat.list->pos=NULL;
for(p=wlist;p->pos;p++)
{
p->weight=PRENORM_IN_USE;
#ifdef EVAL_RUN
docstat.nsum+=p->weight;
docstat.nsum2+=p->weight*p->weight;
#endif /* EVAL_RUN */
}
#ifdef EVAL_RUN
#ifdef PIVOT_STAT
collstat+=PIVOT_STAT;
#endif
#endif /* EVAL_RUN */
for(p=wlist;p->pos;p++)
{
p->weight/=NORM_IN_USE;
}
return wlist;
}
#ifdef HYPHEN_IS_DELIM
#define word_char(X) (isalnum(X) || (X)=='_' || (X)=='\'')
#else
#define word_char(X) (isalnum(X) || (X)=='_' || (X)=='\'' || (X)=='-')
#endif
/* this is rather dumb first version of the parser */
TREE * ft_parse(TREE *wtree, byte *doc, int doclen)
{
byte *end=doc+doclen;
FT_WORD w;
if (!wtree)
{
if (!(wtree=(TREE *)my_malloc(sizeof(TREE),MYF(0)))) return NULL;
init_tree(wtree,0,sizeof(FT_WORD),(qsort_cmp)&FT_WORD_cmp,0,NULL);
}
w.weight=0;
while (doc<end)
{
for (;doc<end;doc++)
if (word_char(*doc)) break;
for (w.pos=doc; doc<end; doc++)
if (!word_char(*doc)) break;
if ((w.len= (uint) (doc-w.pos)) < MIN_WORD_LEN) continue;
if (w.len >= HA_FT_MAXLEN) continue;
if (is_stopword(w.pos, w.len)) continue;
if (!tree_insert(wtree, &w, 0))
{
delete_tree(wtree);
my_free((char*) wtree,MYF(0));
return NULL;
}
}
return wtree;
}
|
