1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00

Add methods to data extractor for extracting bytes and fixed length C strings.

Summary:
These modificaitons will be used in D74883.

Fixed length C strings can have trailing NULLs or sometimes spaces (BSD archive files), so the fixed length C string defaults to stripping trailing NULLs, but can have the arguments specify to remove one or more kinds of spaces if needed. This is used to extract fixed length C strings from ELF NOTEs in D74883.

Reviewers: labath, dblaikie, aprantl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D74991
This commit is contained in:
Greg Clayton 2020-02-21 15:21:07 -08:00
parent e5455cb803
commit 6beeaecd76
3 changed files with 118 additions and 0 deletions

View File

@ -141,6 +141,62 @@ public:
/// a default-initialized StringRef will be returned.
StringRef getCStrRef(uint64_t *offset_ptr) const;
/// Extract a fixed length string from \a *OffsetPtr and consume \a Length
/// bytes.
///
/// Returns a StringRef for the string from the data at the offset
/// pointed to by \a OffsetPtr. A fixed length C string will be extracted
/// and the \a OffsetPtr will be advanced by \a Length bytes.
///
/// \param[in,out] OffsetPtr
/// A pointer to an offset within the data that will be advanced
/// by the appropriate number of bytes if the value is extracted
/// correctly. If the offset is out of bounds or there are not
/// enough bytes to extract this value, the offset will be left
/// unmodified.
///
/// \param[in] Length
/// The length of the fixed length string to extract. If there are not
/// enough bytes in the data to extract the full string, the offset will
/// be left unmodified.
///
/// \param[in] TrimChars
/// A set of characters to trim from the end of the string. Fixed length
/// strings are commonly either NULL terminated by one or more zero
/// bytes. Some clients have one or more spaces at the end of the string,
/// but a good default is to trim the NULL characters.
///
/// \return
/// A StringRef for the C string value in the data. If the offset
/// pointed to by \a OffsetPtr is out of bounds, or if the
/// offset plus the length of the C string is out of bounds,
/// a default-initialized StringRef will be returned.
StringRef getFixedLengthString(uint64_t *OffsetPtr,
uint64_t Length, StringRef TrimChars = {"\0", 1}) const;
/// Extract a fixed number of bytes from the specified offset.
///
/// Returns a StringRef for the bytes from the data at the offset
/// pointed to by \a OffsetPtr. A fixed length C string will be extracted
/// and the \a OffsetPtr will be advanced by \a Length bytes.
///
/// \param[in,out] OffsetPtr
/// A pointer to an offset within the data that will be advanced
/// by the appropriate number of bytes if the value is extracted
/// correctly. If the offset is out of bounds or there are not
/// enough bytes to extract this value, the offset will be left
/// unmodified.
///
/// \param[in] Length
/// The number of bytes to extract. If there are not enough bytes in the
/// data to extract all of the bytes, the offset will be left unmodified.
///
/// \return
/// A StringRef for the extracted bytes. If the offset pointed to by
/// \a OffsetPtr is out of bounds, or if the offset plus the length
/// is out of bounds, a default-initialized StringRef will be returned.
StringRef getBytes(uint64_t *OffsetPtr, uint64_t Length) const;
/// Extract an unsigned integer of size \a byte_size from \a
/// *offset_ptr.
///

View File

@ -171,6 +171,21 @@ StringRef DataExtractor::getCStrRef(uint64_t *offset_ptr) const {
return StringRef();
}
StringRef DataExtractor::getFixedLengthString(uint64_t *OffsetPtr,
uint64_t Length,
StringRef TrimChars) const {
StringRef Bytes(getBytes(OffsetPtr, Length));
return Bytes.trim(TrimChars);
}
StringRef DataExtractor::getBytes(uint64_t *OffsetPtr, uint64_t Length) const {
if (!isValidOffsetForDataOfSize(*OffsetPtr, Length))
return StringRef();
StringRef Result = Data.substr(*OffsetPtr, Length);
*OffsetPtr += Length;
return Result;
}
uint64_t DataExtractor::getULEB128(uint64_t *offset_ptr,
llvm::Error *Err) const {
assert(*offset_ptr <= Data.size());

View File

@ -278,4 +278,51 @@ TEST(DataExtractorTest, size) {
DataExtractor DE2(ArrayRef<uint8_t>(Data), false, 8);
EXPECT_EQ(DE2.size(), sizeof(Data));
}
TEST(DataExtractorTest, FixedLengthString) {
const char Data[] = "hello\x00\x00\x00world \thola\x00";
DataExtractor DE(StringRef(Data, sizeof(Data)-1), false, 8);
uint64_t Offset = 0;
StringRef Str;
// Test extracting too many bytes doesn't modify Offset and returns None.
Str = DE.getFixedLengthString(&Offset, sizeof(Data));
EXPECT_TRUE(Str.empty());
EXPECT_EQ(Offset, 0u);
// Test extracting a fixed width C string with trailing NULL characters.
Str = DE.getFixedLengthString(&Offset, 8);
EXPECT_EQ(Offset, 8u);
EXPECT_EQ(Str.size(), 5u);
EXPECT_EQ(Str, "hello");
// Test extracting a fixed width C string with trailing space and tab
// characters.
Str = DE.getFixedLengthString(&Offset, 8, " \t");
EXPECT_EQ(Offset, 16u);
EXPECT_EQ(Str.size(), 5u);
EXPECT_EQ(Str, "world");
// Now extract a normal C string.
Str = DE.getCStrRef(&Offset);
EXPECT_EQ(Str.size(), 4u);
EXPECT_EQ(Str, "hola");
}
TEST(DataExtractorTest, GetBytes) {
// Use data with an embedded NULL character for good measure.
const char Data[] = "\x01\x02\x00\x04";
StringRef Bytes(Data, sizeof(Data)-1);
DataExtractor DE(Bytes, false, 8);
uint64_t Offset = 0;
StringRef Str;
// Test extracting too many bytes doesn't modify Offset and returns None.
Str = DE.getBytes(&Offset, sizeof(Data));
EXPECT_TRUE(Str.empty());
EXPECT_EQ(Offset, 0u);
// Test extracting 4 bytes from the stream.
Str = DE.getBytes(&Offset, 4);
EXPECT_EQ(Offset, 4u);
EXPECT_EQ(Str.size(), 4u);
EXPECT_EQ(Str, Bytes);
}
}