Skip to content

Fix mod CSV encoding errors found in HPM and DoD #93

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix mod CSV encoding errors found in HPM and DoD #93

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion src/openvic-dataloader/detail/Convert.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,11 @@ namespace ovdl::convert {

// Paradox being special, invalid Windows-1252
// Used for (semantically incorrect) Polish localization TODOs
.map<'\x8F'>("Ę");
.map<'\x8F'>("Ę")
// HPM (and derived mods) have CSVs which permit this interpretation
.map<'\x90'>("É")
// DoD 0_news.csv mixes Windows-1252 and UTF-8
.map<'\x9D'>("�");

static constexpr auto win1251_map = lexy::symbol_table<std::string_view> //
.map<'\x80'>("Ђ")
Expand Down
51 changes: 51 additions & 0 deletions tests/src/csv/Parser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -933,5 +933,56 @@ TEST_CASE("CSV Parse", "[csv-parse]") {
}
}
}

SECTION("EVTOPTA36918;\\xF3\\xED\\x90\\xE2\\x80\\x9C\\xE2\\x80\\x9D;;x") {
static constexpr auto buffer = "EVTOPTA36918;\xF3\xED\x90\xE2\x80\x9C\xE2\x80\x9D;;x"sv;
parser.load_from_string(buffer);

CHECK_PARSE();

const std::vector<LineObject>& line_list = parser.get_lines();
CHECK_FALSE(line_list.empty());
CHECK(ranges::size(line_list) == 1);

const LineObject& line = line_list.front();
CHECK_FALSE(line.empty());
CHECK(ranges::size(line) == 3);
CHECK(line.value_count() == 4);
CHECK(line.prefix_end() == 0);
CHECK(line.suffix_end() == 4);

for (const auto [index, val] : line | ranges::views::enumerate) {
CAPTURE(index);
CHECK_FALSE_OR_CONTINUE(val.second.empty());
switch (index) {
case 0:
CHECK_OR_CONTINUE(val.first == 0);
CHECK_OR_CONTINUE(val.second == "EVTOPTA36918"sv);
break;
case 1:
CHECK_OR_CONTINUE(val.first == 1);
CHECK_OR_CONTINUE(val.second == "óíÉ“â€�"sv);
break;
case 2:
CHECK_OR_CONTINUE(val.first == 3);
CHECK_OR_CONTINUE(val.second == "x"sv);
break;
default: CHECK_OR_CONTINUE(false); break;
}
}

CHECK(line.value_count() == 4);

for (const auto index : ranges::views::iota(size_t(0), line.value_count())) {
CAPTURE(index);
switch (index) {
case 0: CHECK_OR_CONTINUE(line.get_value_for(index) == "EVTOPTA36918"sv); break;
case 1: CHECK_OR_CONTINUE(line.get_value_for(index) == "óíÉ“â€�"sv); break;
case 2: CHECK_OR_CONTINUE(line.get_value_for(index) == ""sv); break;
case 3: CHECK_OR_CONTINUE(line.get_value_for(index) == "x"sv); break;
default: CHECK_OR_CONTINUE(false); break;
}
}
}
#endif
}