Skip to content

[libc] Scanf shouldn't match just "0x" for hex int #112440

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

Merged
merged 2 commits into from
Oct 18, 2024
Merged

[libc] Scanf shouldn't match just "0x" for hex int #112440

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1cbfb1e
[libc] Scanf shouldn't match just "0x" for hex int
michaelrj-google Oct 15, 2024
d6b2da9
delete commented-out code
michaelrj-google Oct 17, 2024
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
20 changes: 16 additions & 4 deletions libc/src/stdio/scanf_core/int_converter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,13 +124,24 @@ int convert_int(Reader *reader, const FormatSection &to_conv) {

if (to_lower(cur_char) == 'x') {
// This is a valid hex prefix.

is_number = false;
// A valid hex prefix is not necessarily a valid number. For the
// conversion to be valid it needs to use all of the characters it
// consumes. From the standard:
// 7.23.6.2 paragraph 9: "An input item is defined as the longest
// sequence of input characters which does not exceed any specified
// field width and which is, or is a prefix of, a matching input
// sequence."
// 7.23.6.2 paragraph 10: "If the input item is not a matching sequence,
// the execution of the directive fails: this condition is a matching
// failure"
base = 16;
if (max_width > 1) {
--max_width;
cur_char = reader->getc();
} else {
write_int_with_length(0, to_conv);
return READ_OK;
return MATCHING_FAILURE;
Copy link
Member

@nickdesaulniers nickdesaulniers Oct 17, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Consider making this an early return if you reverse the conditional.

Copy link
Contributor Author

@michaelrj-google michaelrj-google Oct 17, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The if (max_width > 1) condition is a common pattern in scanf, so I'd rather keep the consistency and not reverse this conditional.

}

} else {
Expand Down Expand Up @@ -198,6 +209,9 @@ int convert_int(Reader *reader, const FormatSection &to_conv) {
// last one back.
reader->ungetc(cur_char);

if (!is_number)
return MATCHING_FAILURE;

if (has_overflow) {
write_int_with_length(MAX, to_conv);
} else {
Expand All @@ -207,8 +221,6 @@ int convert_int(Reader *reader, const FormatSection &to_conv) {
write_int_with_length(result, to_conv);
}

if (!is_number)
return MATCHING_FAILURE;
return READ_OK;
}

Expand Down
36 changes: 26 additions & 10 deletions libc/test/src/stdio/sscanf_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,13 +177,25 @@ TEST(LlvmLibcSScanfTest, IntConvMaxLengthTests) {
EXPECT_EQ(ret_val, 1);
EXPECT_EQ(result, 0);

result = -999;

// 0x is a valid prefix, but not a valid number. This should be a matching
// failure and should not modify the values.
ret_val = LIBC_NAMESPACE::sscanf("0x1", "%2i", &result);
EXPECT_EQ(ret_val, 1);
EXPECT_EQ(result, 0);
EXPECT_EQ(ret_val, 0);
EXPECT_EQ(result, -999);

ret_val = LIBC_NAMESPACE::sscanf("-0x1", "%3i", &result);
EXPECT_EQ(ret_val, 0);
EXPECT_EQ(result, -999);

ret_val = LIBC_NAMESPACE::sscanf("0x1", "%3i", &result);
EXPECT_EQ(ret_val, 1);
EXPECT_EQ(result, 0);
EXPECT_EQ(result, 1);

ret_val = LIBC_NAMESPACE::sscanf("-0x1", "%4i", &result);
EXPECT_EQ(ret_val, 1);
EXPECT_EQ(result, -1);

ret_val = LIBC_NAMESPACE::sscanf("-0x123", "%4i", &result);
EXPECT_EQ(ret_val, 1);
Expand Down Expand Up @@ -212,7 +224,7 @@ TEST(LlvmLibcSScanfTest, IntConvNoWriteTests) {
EXPECT_EQ(result, 0);

ret_val = LIBC_NAMESPACE::sscanf("0x1", "%*2i", &result);
EXPECT_EQ(ret_val, 1);
EXPECT_EQ(ret_val, 0);
EXPECT_EQ(result, 0);

ret_val = LIBC_NAMESPACE::sscanf("a", "%*i", &result);
Expand Down Expand Up @@ -679,13 +691,17 @@ TEST(LlvmLibcSScanfTest, CombinedConv) {
EXPECT_EQ(result, 123);
ASSERT_STREQ(buffer, "abc");

result = -1;

// 0x is a valid prefix, but not a valid number. This should be a matching
// failure and should not modify the values.
ret_val = LIBC_NAMESPACE::sscanf("0xZZZ", "%i%s", &result, buffer);
EXPECT_EQ(ret_val, 2);
EXPECT_EQ(result, 0);
ASSERT_STREQ(buffer, "ZZZ");
EXPECT_EQ(ret_val, 0);
EXPECT_EQ(result, -1);
ASSERT_STREQ(buffer, "abc");

ret_val = LIBC_NAMESPACE::sscanf("0xZZZ", "%X%s", &result, buffer);
EXPECT_EQ(ret_val, 2);
EXPECT_EQ(result, 0);
ASSERT_STREQ(buffer, "ZZZ");
EXPECT_EQ(ret_val, 0);
EXPECT_EQ(result, -1);
ASSERT_STREQ(buffer, "abc");
}
Loading