Skip to content

[libc] Added a helper to StringConverter to check if a conversion has been completed (reached null terminator) #149364

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

Closed
wants to merge 1 commit into from
Closed

[libc] Added a helper to StringConverter to check if a conversion has been completed (reached null terminator) #149364

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
11 changes: 9 additions & 2 deletions libc/src/__support/wchar/string_converter.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ template <typename T> class StringConverter {
const T *src;
size_t src_len;
size_t src_idx;
bool completed = false;

// # of pops we are allowed to perform (essentially size of the dest buffer)
size_t num_to_write;
Expand Down Expand Up @@ -70,8 +71,10 @@ template <typename T> class StringConverter {
}

auto out = cr.pop_utf32();
if (out.has_value() && out.value() == L'\0')
if (out.has_value() && out.value() == L'\0') {
completed = true;
src_len = src_idx;
}

num_to_write--;

Expand All @@ -93,15 +96,19 @@ template <typename T> class StringConverter {
}

auto out = cr.pop_utf8();
if (out.has_value() && out.value() == '\0')
if (out.has_value() && out.value() == '\0') {
completed = true;
src_len = src_idx;
}

num_to_write--;

return out;
}

size_t getSourceIndex() { return src_idx; }

bool isConversionComplete() { return completed; }
};

} // namespace internal
Expand Down
16 changes: 16 additions & 0 deletions libc/test/src/__support/wchar/string_converter_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,26 +38,31 @@ TEST(LlvmLibcStringConverterTest, UTF8To32) {
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x1f921);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 4);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF32();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x2211);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 7);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF32();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xff);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 9);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF32();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x41);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 10);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF32();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 11);
ASSERT_TRUE(sc.isConversionComplete());

res = sc.popUTF32();
ASSERT_FALSE(res.has_value());
Expand All @@ -79,60 +84,71 @@ TEST(LlvmLibcStringConverterTest, UTF32To8) {
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xF0);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 1);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x9F);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 1);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xA4);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 1);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xA1);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 1);
ASSERT_FALSE(sc.isConversionComplete());

// end of clown emoji, sigma symbol begins
res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xE2);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 2);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x88);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 2);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x91);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 2);
ASSERT_FALSE(sc.isConversionComplete());

// end of sigma symbol, y with diaeresis begins
res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xC3);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 3);
ASSERT_FALSE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0xBF);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 3);
ASSERT_FALSE(sc.isConversionComplete());

// end of y with diaeresis, letter A begins
res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0x41);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 4);
ASSERT_FALSE(sc.isConversionComplete());

// null byte
res = sc.popUTF8();
ASSERT_TRUE(res.has_value());
ASSERT_EQ(static_cast<int>(res.value()), 0);
ASSERT_EQ(static_cast<int>(sc.getSourceIndex()), 5);
ASSERT_TRUE(sc.isConversionComplete());

res = sc.popUTF8();
ASSERT_FALSE(res.has_value());
Expand Down
Loading