Add a new memorybuffer class, to unify all the file reading code in the system

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@36553 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Support/MemoryBuffer.h b/include/llvm/Support/MemoryBuffer.h
new file mode 100644 (file)
index 0000000..e4635d0
--- /dev/null
+++ b/include/llvm/Support/MemoryBuffer.h
@@ -0,0 +1,83 @@
+//===--- MemoryBuffer.h - Memory Buffer Interface ---------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file was developed by Chris Lattner and is distributed under
+// the University of Illinois Open Source License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+//  This file defines the MemoryBuffer interface.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_MEMORYBUFFER_H
+#define LLVM_SUPPORT_MEMORYBUFFER_H
+
+#include "llvm/Support/DataTypes.h"
+
+namespace llvm {
+
+/// MemoryBuffer - This interface provides simple read-only access to a block
+/// of memory, and provides simple methods for reading files and standard input
+/// into a memory buffer.  In addition to basic access to the characters in the
+/// file, this interface guarantees you can read one character past the end of
+/// the file, and that this character will read as '\0'.
+class MemoryBuffer {
+  const char *BufferStart; // Start of the buffer.
+  const char *BufferEnd;   // End of the buffer.
+
+  /// MustDeleteBuffer - True if we allocated this buffer.  If so, the
+  /// destructor must know the delete[] it.
+  bool MustDeleteBuffer;
+protected:
+  MemoryBuffer() : MustDeleteBuffer(false) {}
+  void init(const char *BufStart, const char *BufEnd);
+  void initCopyOf(const char *BufStart, const char *BufEnd);
+public:
+  virtual ~MemoryBuffer();
+  
+  const char *getBufferStart() const { return BufferStart; }
+  const char *getBufferEnd() const   { return BufferEnd; }
+  unsigned getBufferSize() const { return BufferEnd-BufferStart; }
+  
+  /// getBufferIdentifier - Return an identifier for this buffer, typically the
+  /// filename it was read from.
+  virtual const char *getBufferIdentifier() const {
+    return "Unknown buffer";
+  }
+
+  /// getFile - Open the specified file as a MemoryBuffer, returning a new
+  /// MemoryBuffer if successful, otherwise returning null.  If FileSize is
+  /// specified, this means that the client knows that the file exists and that
+  /// it has the specified size.
+  static MemoryBuffer *getFile(const char *FilenameStart, unsigned FnSize,
+                               int64_t FileSize = -1);
+
+  /// getMemBuffer - Open the specified memory range as a MemoryBuffer.  Note
+  /// that EndPtr[0] must be a null byte and be accessible!
+  static MemoryBuffer *getMemBuffer(const char *StartPtr, const char *EndPtr,
+                                    const char *BufferName = "");
+  
+  /// getNewMemBuffer - Allocate a new MemoryBuffer of the specified size that
+  /// is completely initialized to zeros.  Note that the caller should
+  /// initialize the memory allocated by this method.  The memory is owned by
+  /// the MemoryBuffer object.
+  static MemoryBuffer *getNewMemBuffer(unsigned Size,
+                                       const char *BufferName = "");
+  
+  /// getNewUninitMemBuffer - Allocate a new MemoryBuffer of the specified size
+  /// that is not initialized.  Note that the caller should initialize the
+  /// memory allocated by this method.  The memory is owned by the MemoryBuffer
+  /// object.
+  static MemoryBuffer *getNewUninitMemBuffer(unsigned Size,
+                                             const char *BufferName = "");
+  
+  /// getSTDIN - Read all of stdin into a file buffer, and return it.  This
+  /// fails if stdin is empty.
+  static MemoryBuffer *getSTDIN();
+};
+
+} // end namespace llvm
+
+#endif

diff --git a/lib/Support/MemoryBuffer.cpp b/lib/Support/MemoryBuffer.cpp
new file mode 100644 (file)
index 0000000..c590f02
--- /dev/null
+++ b/lib/Support/MemoryBuffer.cpp
@@ -0,0 +1,239 @@
+//===--- MemoryBuffer.cpp - Memory Buffer implementation ------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file was developed by Chris Lattner and is distributed under
+// the University of Illinois Open Source License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+//  This file implements the MemoryBuffer interface.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/System/MappedFile.h"
+#include "llvm/System/Process.h"
+#include <cstdio>
+#include <cstring>
+#include <cerrno>
+using namespace llvm;
+
+//===----------------------------------------------------------------------===//
+// MemoryBuffer implementation itself.
+//===----------------------------------------------------------------------===//
+
+MemoryBuffer::~MemoryBuffer() {
+  if (MustDeleteBuffer)
+    delete [] BufferStart;
+}
+
+/// initCopyOf - Initialize this source buffer with a copy of the specified
+/// memory range.  We make the copy so that we can null terminate it
+/// successfully.
+void MemoryBuffer::initCopyOf(const char *BufStart, const char *BufEnd) {
+  size_t Size = BufEnd-BufStart;
+  BufferStart = new char[Size+1];
+  BufferEnd = BufferStart+Size;
+  memcpy(const_cast<char*>(BufferStart), BufStart, Size);
+  *const_cast<char*>(BufferEnd) = 0;   // Null terminate buffer.
+  MustDeleteBuffer = false;
+}
+
+/// init - Initialize this MemoryBuffer as a reference to externally allocated
+/// memory, memory that we know is already null terminated.
+void MemoryBuffer::init(const char *BufStart, const char *BufEnd) {
+  assert(BufEnd[0] == 0 && "Buffer is not null terminated!");
+  BufferStart = BufStart;
+  BufferEnd = BufEnd;
+  MustDeleteBuffer = false;
+}
+
+//===----------------------------------------------------------------------===//
+// MemoryBufferMem implementation.
+//===----------------------------------------------------------------------===//
+
+namespace {
+class MemoryBufferMem : public MemoryBuffer {
+  std::string FileID;
+public:
+  MemoryBufferMem(const char *Start, const char *End, const char *FID)
+  : FileID(FID) {
+    init(Start, End);
+  }
+  
+  virtual const char *getBufferIdentifier() const {
+    return FileID.c_str();
+  }
+};
+}
+
+/// getMemBuffer - Open the specified memory range as a MemoryBuffer.  Note
+/// that EndPtr[0] must be a null byte and be accessible!
+MemoryBuffer *MemoryBuffer::getMemBuffer(const char *StartPtr, 
+                                         const char *EndPtr,
+                                         const char *BufferName) {
+  return new MemoryBufferMem(StartPtr, EndPtr, BufferName);
+}
+
+/// getNewUninitMemBuffer - Allocate a new MemoryBuffer of the specified size
+/// that is completely initialized to zeros.  Note that the caller should
+/// initialize the memory allocated by this method.  The memory is owned by
+/// the MemoryBuffer object.
+MemoryBuffer *MemoryBuffer::getNewUninitMemBuffer(unsigned Size,
+                                                  const char *BufferName) {
+  char *Buf = new char[Size+1];
+  Buf[Size] = 0;
+  MemoryBufferMem *SB = new MemoryBufferMem(Buf, Buf+Size, BufferName);
+  // The memory for this buffer is owned by the MemoryBuffer.
+  SB->MustDeleteBuffer = true;
+  return SB;
+}
+
+/// getNewMemBuffer - Allocate a new MemoryBuffer of the specified size that
+/// is completely initialized to zeros.  Note that the caller should
+/// initialize the memory allocated by this method.  The memory is owned by
+/// the MemoryBuffer object.
+MemoryBuffer *MemoryBuffer::getNewMemBuffer(unsigned Size,
+                                            const char *BufferName) {
+  MemoryBuffer *SB = getNewUninitMemBuffer(Size, BufferName);
+  memset(const_cast<char*>(SB->getBufferStart()), 0, Size+1);
+  return SB;
+}
+
+
+//===----------------------------------------------------------------------===//
+// MemoryBufferMMapFile implementation.
+//===----------------------------------------------------------------------===//
+
+namespace {
+class MemoryBufferMMapFile : public MemoryBuffer {
+  sys::MappedFile File;
+public:
+  MemoryBufferMMapFile(const sys::Path &Filename);
+  
+  virtual const char *getBufferIdentifier() const {
+    return File.path().c_str();
+  }
+    
+  ~MemoryBufferMMapFile();
+};
+}
+
+MemoryBufferMMapFile::MemoryBufferMMapFile(const sys::Path &Filename) {
+  // FIXME: This does an extra stat syscall to figure out the size, but we
+  // already know the size!
+  bool Failure = File.open(Filename);
+  Failure = Failure;  // Silence warning in no-asserts mode.
+  assert(!Failure && "Can't open file??");
+  
+  File.map();
+  
+  size_t Size = File.size();
+  
+  static unsigned PageSize = sys::Process::GetPageSize();
+  assert(((PageSize & (PageSize-1)) == 0) && PageSize &&
+         "Page size is not a power of 2!");
+  
+  // If this file is not an exact multiple of the system page size (common
+  // case), then the OS has zero terminated the buffer for us.
+  if ((Size & (PageSize-1))) {
+    init(File.charBase(), File.charBase()+Size);
+  } else {
+    // Otherwise, we allocate a new memory buffer and copy the data over
+    initCopyOf(File.charBase(), File.charBase()+Size);
+    
+    // No need to keep the file mapped any longer.
+    File.unmap();
+  }
+}
+
+MemoryBufferMMapFile::~MemoryBufferMMapFile() {
+  File.unmap();
+}
+
+//===----------------------------------------------------------------------===//
+// MemoryBuffer::getFile implementation.
+//===----------------------------------------------------------------------===//
+
+MemoryBuffer *MemoryBuffer::getFile(const char *FilenameStart, unsigned FnSize,
+                                    int64_t FileSize) {
+  sys::PathWithStatus P(FilenameStart, FnSize);
+#if 1
+  return new MemoryBufferMMapFile(P);
+#else
+  // FIXME: We need an efficient and portable method to open a file and then use
+  // 'read' to copy the bits out.  The unix implementation is below.  This is
+  // an important optimization for clients that want to open large numbers of
+  // small files (using mmap on everything can easily exhaust address space!).
+  
+  // If the user didn't specify a filesize, do a stat to find it.
+  if (FileSize == -1) {
+    const sys::FileStatus *FS = P.getFileStatus();
+    if (FS == 0) return 0;  // Error stat'ing file.
+   
+    FileSize = FS->fileSize;
+  }
+  
+  // If the file is larger than some threshold, use mmap, otherwise use 'read'.
+  if (FileSize >= 4096*4)
+    return new MemoryBufferMMapFile(P);
+  
+  MemoryBuffer *SB = getNewUninitMemBuffer(FileSize, FilenameStart);
+  char *BufPtr = const_cast<char*>(SB->getBufferStart());
+  
+  int FD = ::open(FilenameStart, O_RDONLY);
+  if (FD == -1) {
+    delete SB;
+    return 0;
+  }
+  
+  unsigned BytesLeft = FileSize;
+  while (BytesLeft) {
+    ssize_t NumRead = ::read(FD, BufPtr, BytesLeft);
+    if (NumRead != -1) {
+      BytesLeft -= NumRead;
+      BufPtr += NumRead;
+    } else if (errno == EINTR) {
+      // try again
+    } else {
+      // error reading.
+      close(FD);
+      delete SB;
+      return 0;
+    }
+  }
+  close(FD);
+  
+  return SB;
+#endif
+}
+
+
+//===----------------------------------------------------------------------===//
+// MemoryBuffer::getSTDIN implementation.
+//===----------------------------------------------------------------------===//
+
+namespace {
+class STDINBufferFile : public MemoryBuffer {
+public:
+  virtual const char *getBufferIdentifier() const {
+    return "<stdin>";
+  }
+};
+}
+
+MemoryBuffer *MemoryBuffer::getSTDIN() {
+  char Buffer[4096*4];
+  
+  std::vector<char> FileData;
+  
+  // Read in all of the data from stdin, we cannot mmap stdin.
+  while (size_t ReadBytes = fread(Buffer, 1, 4096*4, stdin))
+    FileData.insert(FileData.end(), Buffer, Buffer+ReadBytes);
+  
+  size_t Size = FileData.size();
+  MemoryBuffer *B = new STDINBufferFile();
+  B->initCopyOf(&FileData[0], &FileData[Size]);
+  return B;
+}