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
|
#include <ctype.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <assert.h>
#define MAX_LINE 512
void die( char * ) ;
char buffer[MAX_LINE+1] ;
char *prog_name ;
void die( char *message )
{
fflush(stdout) ;
fprintf(stderr, "%s: %s\n", prog_name, message) ;
exit(1) ;
}
int main(int argc, char* argv[])
{
int errors ;
prog_name = *argv ;
if( argc != 1 )
die("pure filter, takes no arguments") ;
errors = 0 ;
while( fgets(buffer, MAX_LINE, stdin))
errors += do_line(buffer) ;
exit(errors ? 1 : 0 ) ;
}
int do_line(char *data)
{
char *p, *q, *r, *end, *before, *after ;
// expecting two tab-separated fields
// point r to 2nd, null terminate 1st
for( r = data ; *r && *r != '\t' ; r++ )
;
if( *r != '\t' )
return(1) ;
end = r++ ;
*end = '\0' ;
for( q = r ; *q ; q++ )
if( *q == '\n' )
*q = '\0' ;
if( !strlen(r) )
return(1) ;
// within 1st, parse as space-separated
// p will point to current word, q past its end
// before & after point to rest of text
// spaces converted to nulls & back as req'd
before = "" ;
for( p = data ; p < end ; p = q + 1 ) {
if( p > data ) {
before = data ;
p[-1] = '\0' ;
}
// find end of word
for( q = p ; *q && *q != ' ' ; q++ )
;
if( q == end )
after = "" ;
else if( q < end ) {
after = q + 1 ;
*q = '\0' ;
}
else assert(0) ;
print_line(before, p, after, r) ;
if( q < end )
*q = ' ' ;
if( p > data )
p[-1] = ' ' ;
}
return(0) ;
}
// print formatted line for permuted index
// two tab-separated fields
// 1st is sort key
// 2nd is printable line
// pipe it through something like
// sort -F | awk -F '\t' '{print $2}'
// to get final output
print_line( char *before, char *word, char *after, char *tag)
{
int i , x, y, z ;
/*
printf("%s\t%s\t%s\t%s\n", before, word, after, tag) ;
*/
if( list_word(word) )
return ;
x = strlen(before) ;
y = strlen(word) ;
z = strlen(after) ;
// put in sortable field
// strip out with awk after sorting
printf("%s %s\t", word, after) ;
// shorten before string to fit field
for( ; x > 30 ; x-- )
before++ ;
printf("%30s", before) ;
// print keyword, html tagged
printf(" %s%s</a> ", tag, word) ;
// padding, outside tag
for( ; y < 18 ; y++ )
putchar(' ') ;
if( z )
printf("%s", after) ;
printf("\n") ;
}
// avoid indexing on common English words
char *list[] = {
"the", "of", "a", "an", "to", "and", "or", "if", "for", "at",
"am", "is", "are", "was", "were", "have", "has", "had", "be", "been",
"on", "some", "with", "any", "into", "as", "by", "in", "out",
"that", "then", "this", "that", "than", "these", "those",
"he", "his", "him", "she", "her", "hers", "it", "its",
"&", "", "+", "-", "=", "--", "<", ">", "<=", ">=",
"!", "?", "#", "$", "%", "/", "\\", "\"", "\'",
NULL
} ;
// interrogative words like "how" and "where" deliberately left out of
// above list because users might want to search for "how to..." etc.
// return 1 if word in list, else 0
// case-insensitive comparison
list_word( char *p )
{
char **z ;
for( z = list ; *z != NULL ; z++ )
if( ! strcasecmp( p, *z ) )
return 1 ;
return 0 ;
}
|
