llvm-strings: introduce basic strings tool

[compnerd]

Summary

This is a replacement to binutils' string tool. It prints strings found in a
binary (object file, executable, or archive library). It is rather bare and
not functionally equivalent, however, it lays the groundwork necessary for the
strings tool, enabling iterative development of features to reach feature
parity.

[echristo]

Couple of inline comments. Don't bother putting it back up for review if you just make the changes :)

-eric

tools/llvm-strings/llvm-strings.cpp

38

Lower case. Also probably worth just making this a static helper function rather than a class member for StringRef and only have class functions that take object files/archives/etc.

46

Perhaps have it take a stream instead?

[compnerd]

SVN r286556

[mclow.lists]

thanks for doing this!

tools/llvm-strings/CMakeLists.txt

+set(LLVM_LINK_COMPONENTS
+  Object
+  )
+
+add_llvm_tool(llvm-strings
+  llvm-strings.cpp
+  )
+

tools/llvm-strings/LLVMBuild.txt

+;===- ./tools/llvm-strings/LLVMBuild.txt -----------------------*- Conf -*--===;
+;
+;                     The LLVM Compiler Infrastructure
+;
+; This file is distributed under the University of Illinois Open Source
+; License. See LICENSE.TXT for details.
+;
+;===------------------------------------------------------------------------===;
+;
+; This is an LLVMBuild description file for the components in this subdirectory.
+;
+; For more information on the LLVMBuild system, please see:
+;
+;   http://llvm.org/docs/LLVMBuild.html
+;
+;===------------------------------------------------------------------------===;
+
+[component_0]
+type = Tool
+name = llvm-strings
+parent = Tools
+required_libraries = Archive Object

tools/llvm-strings/llvm-strings.cpp

+//===-- llvm-strings.cpp - Printable String dumping utility ---------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This program is a utility that works like binutils "strings", that is, it
+// prints out printable strings in a binary, objdump, or archive file.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/Object/Archive.h"
+#include "llvm/Object/Binary.h"
+#include "llvm/Object/ObjectFile.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/PrettyStackTrace.h"
+#include "llvm/Support/Program.h"
+#include "llvm/Support/Signals.h"
+#include <string>
+
+using namespace llvm;
+using namespace llvm::object;
+
+static cl::list<std::string> InputFileNames(cl::Positional,
+                                            cl::desc("<input object files>"),
+                                            cl::ZeroOrMore);
+
+namespace {
+class Strings {
+  LLVMContext Context;
+
+  void Dump(StringRef Contents) {
+    const char *S = nullptr;
+    for (const char *P = Contents.begin(), *E = Contents.end(); P < E; ++P) {
+      if (std::isgraph(*P) || std::isblank(*P)) {
+        if (S == nullptr)
+          S = P;
+      } else if (S) {
+        if (P - S > 3)
+          llvm::outs() << StringRef(S, P - S) << '\n';
+        S = nullptr;
+      }
+    }
+  }
+
+  void Dump(const ObjectFile *O) {
+    for (const auto &S : O->sections()) {
+      StringRef Contents;
+      if (!S.getContents(Contents))
+        Dump(Contents);
+    }
+  }
+
+  void Dump(const Archive *A) {
+    Error E;
+    for (auto &Element : A->children(E)) {
+      if (Expected<std::unique_ptr<Binary>> Child =
+              Element.getAsBinary(&Context)) {
+        Dump(dyn_cast<ObjectFile>(&**Child));
+      } else {
+        if (auto E = isNotObjectErrorInvalidFileType(Child.takeError())) {
+          errs() << A->getFileName();
+          if (Expected<StringRef> Name = Element.getName())
+            errs() << '(' << *Name << ')';
+          logAllUnhandledErrors(std::move(E), errs(), "");
+          errs() << '\n';
+        }
+      }
+    }
+    static_cast<bool>(E);
+  }
+
+public:
+  void Scan(StringRef File) {
+    ErrorOr<std::unique_ptr<MemoryBuffer>> Buffer =
+        MemoryBuffer::getFileOrSTDIN(File);
+    if (std::error_code EC = Buffer.getError()) {
+      errs() << File << ": " << EC.message() << '\n';
+      return;
+    }
+
+    if (Expected<std::unique_ptr<Binary>> B =
+            createBinary(Buffer.get()->getMemBufferRef(), &Context)) {
+      if (auto *A = dyn_cast<Archive>(&**B))
+        return Dump(A);
+      if (auto *O = dyn_cast<ObjectFile>(&**B))
+        return Dump(O);
+      Dump(Buffer.get()->getMemBufferRef().getBuffer());
+    } else {
+      consumeError(B.takeError());
+      Dump(Buffer.get()->getMemBufferRef().getBuffer());
+    }
+  }
+};
+}
+
+int main(int argc, char **argv) {
+  sys::PrintStackTraceOnErrorSignal(argv[0]);
+  PrettyStackTraceProgram X(argc, argv);
+
+  cl::ParseCommandLineOptions(argc, argv, "llvm string dumper\n");
+
+  if (InputFileNames.empty())
+    InputFileNames.push_back("-");
+
+  Strings S;
+  std::for_each(InputFileNames.begin(), InputFileNames.end(),
+                [&S](StringRef F) { S.Scan(F); });
+  return EXIT_SUCCESS;
+}