Function gdv_fn_substring_index

cpp/src/gandiva/gdv_string_function_stubs.cc:361–452

Substring_index

// Substring_index
GDV_FORCE_INLINE
const char* gdv_fn_substring_index(int64_t context, const char* txt, int32_t txt_len,
                                   const char* pat, int32_t pat_len, int32_t cnt,
                                   int32_t* out_len) {
  if (txt_len == 0 || pat_len == 0 || cnt == 0) {
    *out_len = 0;
    return "";
  }

  char* out = reinterpret_cast<char*>(gdv_fn_context_arena_malloc(context, txt_len));
  if (out == nullptr) {
    gdv_fn_context_set_error_msg(context, "Could not allocate memory for output string");
    *out_len = 0;
    return "";
  }

  std::vector<int> lps(pat_len);
  int len = 0;

  lps[0] = 0;  // lps[0] is always 0

  // the loop calculates lps[i] for i = 1 to M-1
  int i = 1;
  while (i < pat_len) {
    if (pat[i] == pat[len]) {
      len++;
      lps[i] = len;
      i++;
    } else {
      // (pat[i] != pat[len])
      // This is tricky. Consider the example.
      // AAACAAAA and i = 7. The idea is similar
      // to search step.
      if (len != 0) {
        len = lps[len - 1];

        // Also, note that we do not increment
        // i here
      } else {
        // if (len == 0)
        lps[i] = 0;
        i++;
      }
    }
  }

  std::vector<int> occ;

  i = 0;      // index for txt[]
  int j = 0;  // index for pat[]
  while (i < txt_len) {
    if (pat[j] == txt[i]) {
      j++;
      i++;
    }

    if (j == pat_len) {
      occ.push_back(i - j);