Add the DataExtractor utility class.

It is an endian-aware helper that can read data from a StringRef. It will
come in handy for DWARF parsing. This class is inspired by LLDB's
DataExtractor, but is stripped down to the bare minimum needed for DWARF.

Comes with unit tests!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139626 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 176 insertions, 0 deletions

diff --git a/lib/Support/CMakeLists.txt b/lib/Support/CMakeLists.txt
index 80a237ac74..63a833c380 100644
--- a/lib/Support/CMakeLists.txt
+++ b/lib/Support/CMakeLists.txt
@@ -15,6 +15,7 @@ add_llvm_library(LLVMSupport
   CommandLine.cpp
   ConstantRange.cpp
   CrashRecoveryContext.cpp
+  DataExtractor.cpp
   Debug.cpp
   DeltaAlgorithm.cpp
   DAGDeltaAlgorithm.cpp
diff --git a/lib/Support/DataExtractor.cpp b/lib/Support/DataExtractor.cpp
new file mode 100644
index 0000000000..b946c1df83
--- /dev/null
+++ b/lib/Support/DataExtractor.cpp
@@ -0,0 +1,175 @@
+//===-- DataExtractor.cpp -------------------------------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/DataExtractor.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Host.h"
+#include "llvm/Support/SwapByteOrder.h"
+using namespace llvm;
+
+template <typename T>
+static T getU(uint32_t *offset_ptr, const DataExtractor *de,
+              bool isLittleEndian, const char *Data) {
+  T val = 0;
+  uint32_t offset = *offset_ptr;
+  if (de->isValidOffsetForDataOfSize(offset, sizeof(val))) {
+    std::memcpy(&val, &Data[offset], sizeof(val));
+    if (sys::isLittleEndianHost() != isLittleEndian)
+      val = sys::SwapByteOrder(val);
+
+    // Advance the offset
+    *offset_ptr += sizeof(val);
+  }
+  return val;
+}
+
+template <typename T>
+static T *getUs(uint32_t *offset_ptr, T *dst, uint32_t count,
+                const DataExtractor *de, bool isLittleEndian, const char *Data){
+  uint32_t offset = *offset_ptr;
+
+  if (count > 0 && de->isValidOffsetForDataOfSize(offset, sizeof(*dst)*count)) {
+    for (T *value_ptr = dst, *end = dst + count; value_ptr != end;
+        ++value_ptr, offset += sizeof(*dst))
+      *value_ptr = getU<T>(offset_ptr, de, isLittleEndian, Data);
+    // Advance the offset
+    *offset_ptr = offset;
+    // Return a non-NULL pointer to the converted data as an indicator of
+    // success
+    return dst;
+  }
+  return NULL;
+}
+
+uint8_t DataExtractor::getU8(uint32_t *offset_ptr) const {
+  return getU<uint8_t>(offset_ptr, this, IsLittleEndian, Data.data());
+}
+
+uint8_t *
+DataExtractor::getU8(uint32_t *offset_ptr, uint8_t *dst, uint32_t count) const {
+  return getUs<uint8_t>(offset_ptr, dst, count, this, IsLittleEndian,
+                       Data.data());
+}
+
+
+uint16_t DataExtractor::getU16(uint32_t *offset_ptr) const {
+  return getU<uint16_t>(offset_ptr, this, IsLittleEndian, Data.data());
+}
+
+uint16_t *DataExtractor::getU16(uint32_t *offset_ptr, uint16_t *dst,
+                                uint32_t count) const {
+  return getUs<uint16_t>(offset_ptr, dst, count, this, IsLittleEndian,
+                        Data.data());
+}
+
+uint32_t DataExtractor::getU32(uint32_t *offset_ptr) const {
+  return getU<uint32_t>(offset_ptr, this, IsLittleEndian, Data.data());
+}
+
+uint32_t *DataExtractor::getU32(uint32_t *offset_ptr, uint32_t *dst,
+                                uint32_t count) const {
+  return getUs<uint32_t>(offset_ptr, dst, count, this, IsLittleEndian,
+                        Data.data());;
+}
+
+uint64_t DataExtractor::getU64(uint32_t *offset_ptr) const {
+  return getU<uint64_t>(offset_ptr, this, IsLittleEndian, Data.data());
+}
+
+uint64_t *DataExtractor::getU64(uint32_t *offset_ptr, uint64_t *dst,
+                                uint32_t count) const {
+  return getUs<uint64_t>(offset_ptr, dst, count, this, IsLittleEndian,
+                        Data.data());
+}
+
+uint64_t
+DataExtractor::getUnsigned(uint32_t *offset_ptr, uint32_t byte_size) const {
+  switch (byte_size) {
+  case 1:
+    return getU8(offset_ptr);
+  case 2:
+    return getU16(offset_ptr);
+  case 4:
+    return getU32(offset_ptr);
+  case 8:
+    return getU64(offset_ptr);
+  }
+  llvm_unreachable("getUnsigned unhandled case!");
+}
+
+int64_t
+DataExtractor::getSigned(uint32_t *offset_ptr, uint32_t byte_size) const {
+  switch (byte_size) {
+  case 1:
+    return (int8_t)getU8(offset_ptr);
+  case 2:
+    return (int16_t)getU16(offset_ptr);
+  case 4:
+    return (int32_t)getU32(offset_ptr);
+  case 8:
+    return (int64_t)getU64(offset_ptr);
+  }
+  llvm_unreachable("getSigned unhandled case!");
+}
+
+const char *DataExtractor::getCStr(uint32_t *offset_ptr) const {
+  uint32_t offset = *offset_ptr;
+  StringRef::size_type pos = Data.find('\0', offset);
+  if (pos != StringRef::npos) {
+    *offset_ptr = pos + 1;
+    return Data.data() + offset;
+  }
+  return NULL;
+}
+
+uint64_t DataExtractor::getULEB128(uint32_t *offset_ptr) const {
+  uint64_t result = 0;
+  if (Data.empty())
+    return 0;
+
+  unsigned shift = 0;
+  uint32_t offset = *offset_ptr;
+  uint8_t byte = 0;
+
+  while (isValidOffset(offset)) {
+    byte = Data[offset++];
+    result |= (byte & 0x7f) << shift;
+    shift += 7;
+    if ((byte & 0x80) == 0)
+      break;
+  }
+
+  *offset_ptr = offset;
+  return result;
+}
+
+int64_t DataExtractor::getSLEB128(uint32_t *offset_ptr) const {
+  int64_t result = 0;
+  if (Data.empty())
+    return 0;
+
+  unsigned shift = 0;
+  uint32_t offset = *offset_ptr;
+  uint8_t byte = 0;
+
+  while (isValidOffset(offset)) {
+    byte = Data[offset++];
+    result |= (byte & 0x7f) << shift;
+    shift += 7;
+    if ((byte & 0x80) == 0)
+      break;
+  }
+
+  // Sign bit of byte is 2nd high order bit (0x40)
+  if (shift < 64 && (byte & 0x40))
+    result |= -(1 << shift);
+
+  *offset_ptr = offset;
+  return result;
+}