Function utf8_byte_pos

cpp/src/gandiva/precompiled/string_ops.cc:221–237

Get the byte position corresponding to a character position for a non-empty utf8 sequence

// Get the byte position corresponding to a character position for a non-empty utf8
// sequence
FORCE_INLINE
gdv_int32 utf8_byte_pos(gdv_int64 context, const char* str, gdv_int32 str_len,
                        gdv_int32 char_pos) {
  int char_len = 0;
  int byte_index = 0;
  for (gdv_int32 char_index = 0; char_index < char_pos && byte_index < str_len;
       char_index++) {
    char_len = utf8_char_length(str[byte_index]);
    if (char_len == 0 ||
        byte_index + char_len > str_len) {  // invalid byte or incomplete glyph
      set_error_for_invalid_utf(context, str[byte_index]);
      return -1;
    }
    byte_index += char_len;
  }
  return byte_index;
}

#define UTF8_LENGTH(NAME, TYPE)                                                 \
  FORCE_INLINE                                                                  \