From fadf8cbec7a9c62f1361dcc470920b9b7f72f91e Mon Sep 17 00:00:00 2001
From: Rafael Espindola <rafael.espindola@gmail.com>
Date: Tue, 14 Jul 2015 22:18:43 +0000
Subject: [PATCH] Add support for reading members out of thin archives.

For now the Archive owns the buffers of the thin archive members.
This makes for a simple API, but all the buffers are destructed
only when the archive is destructed. This should be fine since we
close the files after mmap so we should not hit an open file
limit.

llvm-svn: 242215
---
 include/llvm/Object/Archive.h    | 11 +++++++----
 lib/Object/Archive.cpp           | 23 ++++++++++++++++++++++-
 test/Object/archive-extract.test |  6 ++++++
 tools/llvm-ar/llvm-ar.cpp        |  6 ++++--
 4 files changed, 39 insertions(+), 7 deletions(-)

diff --git a/include/llvm/Object/Archive.h b/include/llvm/Object/Archive.h
index e461564ace8..597f0d48c11 100644
--- a/include/llvm/Object/Archive.h
+++ b/include/llvm/Object/Archive.h
@@ -94,9 +94,7 @@ public:
     /// \return the size in the archive header for this member.
     uint64_t getRawSize() const;
 
-    StringRef getBuffer() const {
-      return StringRef(Data.data() + StartOfFile, getSize());
-    }
+    ErrorOr<StringRef> getBuffer() const;
     uint64_t getChildOffset() const;
 
     ErrorOr<MemoryBufferRef> getMemoryBufferRef() const;
@@ -208,7 +206,11 @@ public:
 
   bool hasSymbolTable() const;
   child_iterator getSymbolTableChild() const { return SymbolTable; }
-  StringRef getSymbolTable() const { return SymbolTable->getBuffer(); }
+  StringRef getSymbolTable() const {
+    // We know that the symbol table is not an external file,
+    // so we just assert there is no error.
+    return *SymbolTable->getBuffer();
+  }
   uint32_t getNumberOfSymbols() const;
 
 private:
@@ -217,6 +219,7 @@ private:
   child_iterator FirstRegular;
   unsigned Format : 2;
   unsigned IsThin : 1;
+  mutable std::vector<std::unique_ptr<MemoryBuffer>> ThinBuffers;
 };
 
 }
diff --git a/lib/Object/Archive.cpp b/lib/Object/Archive.cpp
index c29e63941f2..d4821196a6c 100644
--- a/lib/Object/Archive.cpp
+++ b/lib/Object/Archive.cpp
@@ -17,6 +17,7 @@
 #include "llvm/ADT/Twine.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/Path.h"
 
 using namespace llvm;
 using namespace object;
@@ -115,6 +116,23 @@ uint64_t Archive::Child::getRawSize() const {
   return getHeader()->getSize();
 }
 
+ErrorOr<StringRef> Archive::Child::getBuffer() const {
+  if (!Parent->IsThin)
+    return StringRef(Data.data() + StartOfFile, getSize());
+  ErrorOr<StringRef> Name = getName();
+  if (std::error_code EC = Name.getError())
+    return EC;
+  SmallString<128> FullName =
+      Parent->getMemoryBufferRef().getBufferIdentifier();
+  sys::path::remove_filename(FullName);
+  sys::path::append(FullName, *Name);
+  ErrorOr<std::unique_ptr<MemoryBuffer>> Buf = MemoryBuffer::getFile(FullName);
+  if (std::error_code EC = Buf.getError())
+    return EC;
+  Parent->ThinBuffers.push_back(std::move(*Buf));
+  return Parent->ThinBuffers.back()->getBuffer();
+}
+
 Archive::Child Archive::Child::getNext() const {
   size_t SpaceToSkip = Data.size();
   // If it's odd, add 1 to make it even.
@@ -186,7 +204,10 @@ ErrorOr<MemoryBufferRef> Archive::Child::getMemoryBufferRef() const {
   if (std::error_code EC = NameOrErr.getError())
     return EC;
   StringRef Name = NameOrErr.get();
-  return MemoryBufferRef(getBuffer(), Name);
+  ErrorOr<StringRef> Buf = getBuffer();
+  if (std::error_code EC = Buf.getError())
+    return EC;
+  return MemoryBufferRef(*Buf, Name);
 }
 
 ErrorOr<std::unique_ptr<Binary>>
diff --git a/test/Object/archive-extract.test b/test/Object/archive-extract.test
index c1ddcf71725..a77adf2cabb 100644
--- a/test/Object/archive-extract.test
+++ b/test/Object/archive-extract.test
@@ -48,3 +48,9 @@ NOTFOUND: foo.o was not found
 
 RUN: not llvm-ar x %p/Inputs/thin.a foo.o 2>&1 | FileCheck %s --check-prefix=THINEXTRACT
 THINEXTRACT: extracting from a thin archive is not supported
+
+RUN: llvm-ar p %p/Inputs/thin.a evenlen | FileCheck %s --check-prefix=EVENLEN
+EVENLEN: evenlen
+
+RUN: not llvm-ar p %p/Inputs/thin-path.a t/test2.o | FileCheck %s --check-prefix=MISSING
+MISSING: No such file or directory.
diff --git a/tools/llvm-ar/llvm-ar.cpp b/tools/llvm-ar/llvm-ar.cpp
index c87606d7826..2c9668c63b8 100644
--- a/tools/llvm-ar/llvm-ar.cpp
+++ b/tools/llvm-ar/llvm-ar.cpp
@@ -299,7 +299,9 @@ static void doPrint(StringRef Name, const object::Archive::Child &C) {
   if (Verbose)
     outs() << "Printing " << Name << "\n";
 
-  StringRef Data = C.getBuffer();
+  ErrorOr<StringRef> DataOrErr = C.getBuffer();
+  failIfError(DataOrErr.getError());
+  StringRef Data = *DataOrErr;
   outs().write(Data.data(), Data.size());
 }
 
@@ -355,7 +357,7 @@ static void doExtract(StringRef Name, const object::Archive::Child &C) {
     raw_fd_ostream file(FD, false);
 
     // Get the data and its length
-    StringRef Data = C.getBuffer();
+    StringRef Data = *C.getBuffer();
 
     // Write the data.
     file.write(Data.data(), Data.size());