分析PHP的similar_text函数
//比较字串,返回两个字串第一个相同字符的区域
static void php_similar_str(const char *txt1, int len1, const char *txt2, int len2, int *pos1, int *pos2, int *max)
{
char *p, *q;
char *end1 = (char *) txt1 + len1;
char *end2 = (char *) txt2 + len2;
int l;
*max = 0;
//遍历字串
for (p = (char *) txt1; p < end1; p++) {
for (q = (char *) txt2; q < end2; q++) {
for (l = 0; (p + l < end1) && (q + l < end2) && (p[l] == q[l]); l++);
if (l > *max) {
//保存相同区域信息
*max = l;
*pos1 = p - txt1;
*pos2 = q - txt2;
}
}
}
}
//递归函数,比较txt1和txt2的相同字符数量
static int php_similar_char(const char *txt1, int len1, const char *txt2, int len2)
{
int sum;
int pos1, pos2, max;
php_similar_str(txt1, len1, txt2, len2, &pos1, &pos2, &max);
if ((sum = max)) {//这样写有什么意义?????!!!!!
//递归上次不同部分的前部
if (pos1 && pos2) {
sum += php_similar_char(txt1, pos1, txt2, pos2);
}
//递归上次不同部分的后部
if ((pos1 + max < len1) && (pos2 + max < len2)) {
sum += php_similar_char(txt1 + pos1 + max, len1 - pos1 - max,
txt2 + pos2 + max, len2 - pos2 - max);
}
}
//返回本次比较后的相同字符数量
return sum;
}
//PHP函数本身，一堆宏，做了些串转换和返回值换算,主功能由上面两个函数做了。
PHP_FUNCTION(similar_text)
{
zval **t1, **t2, **percent;
int ac = ZEND_NUM_ARGS();
int sim;
if (ac < 2 || ac > 3 || zend_get_parameters_ex(ac, &t1, &t2, &percent) == FAILURE) {
WRONG_PARAM_COUNT;
}
convert_to_string_ex(t1);
convert_to_string_ex(t2);
if (ac > 2) {
convert_to_double_ex(percent);
}
if (Z_STRLEN_PP(t1) + Z_STRLEN_PP(t2) == 0) {
if (ac > 2) {
Z_DVAL_PP(percent) = 0;
}
RETURN_LONG(0);
}
sim = php_similar_char(Z_STRVAL_PP(t1), Z_STRLEN_PP(t1), Z_STRVAL_PP(t2), Z_STRLEN_PP(t2));
if (ac > 2) {
Z_DVAL_PP(percent) = sim * 200.0 / (Z_STRLEN_PP(t1) + Z_STRLEN_PP(t2));
}
RETURN_LONG(sim);
}
所有看出similar_text是根据ASCII做比较的，是不考虑词组问题的。
测试了一下，结果如下：
int main(int argc, char *argv[])
{
char *str1="weican wuxin";
char *str2="wuxin weican";
int pos1,pos2,max;
php_similar_str(str1,strlen(str1),str2,strlen(str2),&pos1,&pos2,&max);
printf("php_similar_str:%d,%d=%d\n",pos1,pos2,max);
max=php_similar_char(str1,strlen(str1),str2,strlen(str2));
printf("php_similar_char:%d\n",max);
system("PAUSE");
return 0;
}
php_similar_str:0,6=6
php_similar_char:6
char *str1="TCP协议通讯工作原a理";
char *str2="TCPa协议通讯工作原理";
php_similar_str:3,4=14
php_similar_char:19
