Function Utf8CaseInsensitiveFindIteratorType_next

python/stringzilla.c:5783–5817

#pragma region UTF8 Case Insensitive Find Iterator

static PyObject *Utf8CaseInsensitiveFindIteratorType_next(Utf8CaseInsensitiveFindIterator *self) {
    // Check if we've reached the end
    sz_size_t remaining = (sz_size_t)(self->haystack_end - self->current);
    if (remaining == 0) return NULL;

    // Search for next match
    sz_size_t matched_length = 0;
    sz_cptr_t match = sz_utf8_case_insensitive_find(self->current, remaining, self->needle.start, self->needle.length,
                                                    &self->metadata, &matched_length);

    if (!match) return NULL;

    // Create a new `Str` object for the matched region
    Str *result_obj = (Str *)StrType.tp_alloc(&StrType, 0);
    if (result_obj == NULL && PyErr_NoMemory()) return NULL;

    result_obj->memory.start = match;
    result_obj->memory.length = matched_length;
    result_obj->parent = self->haystack_obj;
    Py_INCREF(self->haystack_obj);

    // Advance position for next search
    if (self->include_overlapping) {
        // Move forward by one UTF-8 codepoint to allow overlapping matches
        sz_size_t pos = 0;
        sz_utf8_decode_(match, matched_length, &pos);
        self->current = match + (pos > 0 ? pos : 1);
    }
    else {
        // Move past the entire matched region (non-overlapping)
        self->current = match + matched_length;
    }

    return (PyObject *)result_obj;
}

static void Utf8CaseInsensitiveFindIteratorType_dealloc(Utf8CaseInsensitiveFindIterator *self) {
    Py_XDECREF(self->haystack_obj);