/* In `stem(p, i, j)`, `p` is a `char` pointer, and the
* string to be stemmed is from `p[i]` to
* `p[j]` (inclusive).
*
* Typically, `i` is zero and `j` is the offset to the
* last character of a string, `(p[j + 1] == '\0')`.
* The stemmer adjusts the characters `p[i]` ... `p[j]`
* and returns the new end-point of the string, `k`.
*
* Stemming never increases word length, so `i <= k <= j`.
*
* To turn the stemmer into a module, declare 'stem' as
* extern, and delete the remainder of this file. */
int
stem(char *p, int index, int position) {
/* Copy the parameters into statics. */
b = p;
k = position;
k0 = index;
if (k <= k0 + 1) {
return k; /* --DEPARTURE-- */
}
/* With this line, strings of length 1 or 2 don't
* go through the stemming process, although no
* mention is made of this in the published
* algorithm. Remove the line to match the published
* algorithm. */
step1ab();
if (k > k0) {
step1c();
step2();
step3();
step4();
step5();
}
return k;
}
static size_t stem(char *p, size_t i, size_t j) {
b = p;
k = j;
k0 = i; /* copy the parameters into statics */
/*
* DEPARTURE: This next 'if' statement prevents strings of length 1 or 2 from
* going through the stemming process, although no mention is made of this in the
* published algorithm. Remove the line to match the publishedalgorithm.
*/
if (k <= k0 + 1)
return k;
step1ab();
if (k > k0) {
step1c();
step2();
step3();
step4();
step5();
}
return k;
}
/* In stem(p,i,j), p is a char pointer, and the string to be stemmed is from
p[i] to p[j] inclusive. Typically i is zero and j is the offset to the last
character of a string, (p[j+1] == '\0'). The stemmer adjusts the
characters p[i] ... p[j] and returns the new end-point of the string, k.
Stemming never increases word length, so i <= k <= j. To turn the stemmer
into a module, declare 'stem' as extern, and delete the remainder of this
file.
*/
static ssize_t
stem(char *s, size_t z)
{
/* copy the parameters into statics */
b = s;
k = z - 1;
k0 = 0;
if (k <= k0 + 1) {
/*-DEPARTURE-*/
return k;
}
/* With this line, strings of length 1 or 2 don't go through the
stemming process, although no mention is made of this in the
published algorithm. Remove the line to match the published
algorithm. */
step1ab();
step1c();
step2();
step3();
step4();
step5();
return k;
}
int stem(char * p, int i, int j)
{ b = p; k = j; k0 = i; /* copy the parameters into statics */
if (k <= k0+1) return k; /*-DEPARTURE-*/
/* With this line, strings of length 1 or 2 don't go through the
stemming process, although no mention is made of this in the
published algorithm. Remove the line to match the published
algorithm. */
step1ab(); step1c(); step2(); step3(); step4(); step5();
return k;
}
extern int stem_ts(struct stemmer * z, char * b, int k)
{
if (k <= 1) return k; /*-DEPARTURE-*/
z->b = b; z->k = k; /* copy the parameters into z */
/* With this line, strings of length 1 or 2 don't go through the
stemming process, although no mention is made of this in the
published algorithm. Remove the line to match the published
algorithm. */
step1ab(z); step1c(z); step2(z); step3(z); step4(z); step5(z);
return z->k;
}
/* nml: this function slightly modified to not require external stemmer
* structure or length count (accepts NUL-terminated term) */
void stem_porters(void *opaque, char *term) {
struct stemmer z;
z.b = term; z.k = str_len(term) - 1; /* copy the parameters into z */
if (z.k <= 1) return; /*-DEPARTURE-*/
/* With this line, strings of length 1 or 2 don't go through the
stemming process, although no mention is made of this in the
published algorithm. Remove the line to match the published
algorithm. */
step1ab(&z); step1c(&z); step2(&z); step3(&z); step4(&z); step5(&z);
term[z.k + 1] = '\0'; /* zero-terminate string */
}
wchar_t*
s_stem(wchar_t *word) {
wchar_t* copy;
copy = malloc(sizeof(*copy) * (wcslen(word)+1));
wcscpy(copy, word);
step1a(copy);
step1b(copy);
step1c(copy);
step2(copy);
step3(copy);
step4(copy);
step5(copy);
return copy;
}
