Skip to content

[llvm-strings] Use small buffer instead of reading whole file #163073

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: main
Choose a base branch
from
Open

[llvm-strings] Use small buffer instead of reading whole file #163073

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
74 changes: 55 additions & 19 deletions llvm/tools/llvm-strings/llvm-strings.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,9 @@
#include "llvm/Option/ArgList.h"
#include "llvm/Option/Option.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Errno.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/InitLLVM.h"
#include "llvm/Support/MemoryBuffer.h"
Expand Down Expand Up @@ -88,7 +90,9 @@ static void parseIntArg(const opt::InputArgList &Args, int ID, T &Value) {
}
}

static void strings(raw_ostream &OS, StringRef FileName, StringRef Contents) {
static void strings(raw_ostream &OS, StringRef FileName,
sys::fs::file_t FileHandle) {
SmallString<sys::fs::DefaultReadChunkSize> Buffer;
auto print = [&OS, FileName](unsigned Offset, StringRef L) {
if (L.size() < static_cast<size_t>(MinLength))
return;
Expand All @@ -110,19 +114,42 @@ static void strings(raw_ostream &OS, StringRef FileName, StringRef Contents) {
OS << L << '\n';
};

const char *B = Contents.begin();
const char *P = nullptr, *E = nullptr, *S = nullptr;
for (P = Contents.begin(), E = Contents.end(); P < E; ++P) {
if (isPrint(*P) || *P == '\t') {
if (S == nullptr)
S = P;
} else if (S) {
print(S - B, StringRef(S, P - S));
S = nullptr;
unsigned Offset = 0, LocalOffset = 0, CurSize = 0;
Buffer.resize(sys::fs::DefaultReadChunkSize);
auto FillBuffer = [&Buffer, FileHandle, &FileName]() -> unsigned {
Expected<size_t> ReadBytesOrErr = sys::fs::readNativeFile(
FileHandle,
MutableArrayRef(Buffer.begin(), sys::fs::DefaultReadChunkSize));
if (!ReadBytesOrErr) {
errs() << FileName << ": "
<< errorToErrorCode(ReadBytesOrErr.takeError()).message() << '\n';
return 0;
}
return *ReadBytesOrErr;
};
std::string StringBuffer;
while (true) {
if (LocalOffset == CurSize) {
CurSize = FillBuffer();
if (CurSize == 0)
break;
LocalOffset = 0;
}
char C = Buffer[LocalOffset++];
if (isPrint(C) || C == '\t') {
StringBuffer.push_back(C);
} else if (StringBuffer.size()) {
print(Offset, StringRef(StringBuffer.c_str(), StringBuffer.size()));
Offset += StringBuffer.size();
StringBuffer.clear();
++Offset;
} else {
++Offset;
}
}
if (S)
print(S - B, StringRef(S, E - S));

if (StringBuffer.size())
print(Offset, StringRef(StringBuffer.c_str(), StringBuffer.size()));
}

int main(int argc, char **argv) {
Expand Down Expand Up @@ -174,13 +201,22 @@ int main(int argc, char **argv) {
InputFileNames.push_back("-");

for (const auto &File : InputFileNames) {
ErrorOr<std::unique_ptr<MemoryBuffer>> Buffer =
MemoryBuffer::getFileOrSTDIN(File, /*IsText=*/true);
if (std::error_code EC = Buffer.getError())
errs() << File << ": " << EC.message() << '\n';
else
strings(llvm::outs(), File == "-" ? "{standard input}" : File,
Buffer.get()->getMemBufferRef().getBuffer());
sys::fs::file_t FD;
if (File == "-") {
FD = sys::fs::getStdinHandle();
} else {
Expected<sys::fs::file_t> FDOrErr =
sys::fs::openNativeFileForRead(File, sys::fs::OF_None);
;
if (!FDOrErr) {
errs() << File << ": "
<< errorToErrorCode(FDOrErr.takeError()).message() << '\n';
continue;
}
FD = *FDOrErr;
}

strings(llvm::outs(), File == "-" ? "{standard input}" : File, FD);
}

return EXIT_SUCCESS;
Expand Down