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
|
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include <string.h>
#include <ctype.h>
#define MAX_CURSE_LEN 10
#define REPLACE_STR_LEN 20
#define NUM_CURSES 8
#define NOT_FOUND -1
typedef struct
{
char badWord[MAX_CURSE_LEN];
int beginningOnly;
int skip[128];
}
profanity;
/* if beginningOnly is true censor only looks for the curse at the beginning
* of words. Currently only set for "twat" so "saltwater", etc aren't caught.
* Grepped for the other strings in /usr/dict/words and came up with a blank,
* so beginningOnly is left off for them. */
static profanity curseWords[NUM_CURSES] =
{
{"damn", 0},
{"fuck", 0},
{"bastard", 0},
{"shit", 0},
{"bitch", 0},
{"twat", 1},
{"cunt", 0},
{"dammit", 0}
};
static char replacementChars[REPLACE_STR_LEN + 1] = "@#$%^&*%#$%@#$*&@%$%";
/* + 1 for trailing null */
void initSkipArray(char *word, int *skip)
{
int i, wordLen = strlen(word);
for (i = 0; i < 128; i++)
skip[i] = wordLen;
for (i = 0; i < wordLen; i++)
{
skip[(int) word[i]] = wordLen - i - 1;
if (isascii(toupper(word[i])))
skip[toupper(word[i])] = skip[(int) word[i]];
}
}
void initCensoring()
{
int i;
for (i = 0; i < NUM_CURSES; i++)
initSkipArray(curseWords[i].badWord, curseWords[i].skip);
}
static int search(char *word, char *text, int *skip)
{
int i, j, wordLen = strlen(word), textLen = strlen(text);
for (i = j = wordLen - 1; j >= 0; i--, j--)
while (tolower(text[i]) != word[j])
{
int t = skip[(int) text[i]];
i += (wordLen - j > t) ? wordLen - j : t;
if (i >= textLen)
return NOT_FOUND;
j = wordLen - 1;
}
return i + 1;
}
char *censor(char *text)
{
int i, j, t = strlen(text) - 1;
char *str = text;
for (i = 0; i < NUM_CURSES; i++)
{
text = str;
while ((j = search(curseWords[i].badWord, text, curseWords[i].skip))
!= NOT_FOUND)
{
int k, l, wordBegin, wordEnd;
for (wordBegin = j; wordBegin > 0; wordBegin--)
if (!isalpha(text[wordBegin - 1]))
break;
for (wordEnd = j + strlen(curseWords[i].badWord) - 1; wordEnd < t; wordEnd++)
if (!isalpha(text[wordEnd + 1]))
break;
if (!curseWords[i].beginningOnly || wordBegin == j)
for (k = wordBegin, l = 0; k <= wordEnd; k++)
{
text[k] = replacementChars[l];
if (++l >= REPLACE_STR_LEN)
l = 0; /* make sure we don't go *
* past bound of *
* replacementChars */
}
text += wordEnd; /* so we don't go into *
* infinite loop if *
* beginningOnly */
}
}
return str;
}
#undef MAX_CURSE_LEN
#undef REPLACE_STR_LEN
#undef NUM_CURSES
#undef NOT_FOUND
|
