Function ReportErrorBytes

be/src/exprs/string-functions-ir.cc:363–375

Reports the error in parsing multibyte characters with leading bytes and current locale. Used in Utf8CaseConversion().

/// Reports the error in parsing multibyte characters with leading bytes and current
/// locale. Used in Utf8CaseConversion().
static void ReportErrorBytes(FunctionContext* context, const StringVal& str,
    int current_idx) {
  DCHECK_LT(current_idx, str.len);
  stringstream ss;
  ss << "[0x" << std::hex << (int)DCHECK_NOTNULL(str.ptr)[current_idx];
  for (int k = 1; k < 4 && current_idx + k < str.len; ++k) {
    ss << ", 0x" << std::hex << (int)str.ptr[current_idx + k];
  }
  ss << "]";
  context->AddWarning(Substitute(
      "Illegal multi-byte character in string. Leading bytes: $0. Current locale: $1",
      ss.str(), std::locale("").name()).c_str());
}

/// Converts string based on the transform function 'fn'. The unit of the conversion is
/// a wchar_t (i.e. uint32_t) which is parsed from multi bytes using std::mbtowc().