Method TestValidateData

cpp/src/arrow/array/array_binary_test.cc:302–325

  }

  void TestValidateData() {
    // Valid UTF8
    ASSERT_OK(ValidateFull(R"(["Voix", "ambiguë", "d’un", "cœur"])"));
    ASSERT_OK(ValidateFull(R"(["いろはにほへと", "ちりぬるを", "わかよたれそ"])"));
    ASSERT_OK(ValidateFull(R"(["😀", "😄"])"));
    ASSERT_OK(ValidateFull(1, {0, 4}, "\xf4\x8f\xbf\xbf"));  // \U0010ffff

    // Invalid UTF8
    auto ty = TypeTraits<T>::type_singleton();
    auto st1 = ValidateFull(3, {0, 4, 6, 9}, "abc \xff def");
    // Hypothetical \U00110000
    auto st2 = ValidateFull(1, {0, 4}, "\xf4\x90\x80\x80");
    // Single UTF8 character straddles two entries
    auto st3 = ValidateFull(2, {0, 1, 2}, "\xc3\xa9");
    if (T::is_utf8) {
      ASSERT_RAISES(Invalid, st1);
      ASSERT_RAISES(Invalid, st2);
      ASSERT_RAISES(Invalid, st3);
    } else {
      ASSERT_OK(st1);
      ASSERT_OK(st2);
      ASSERT_OK(st3);
    }
  }

 protected:
  std::vector<offset_type> offsets_;