Add a function to MD5 a file's contents.

In doing so, clean up the MD5 interface a little.  Most
existing users only care about the lower 8 bytes of an MD5,
but for some users that care about the upper and lower,
there wasn't a good interface.  Furthermore, consumers
of the MD5 checksum were required to handle endianness
details on their own, so it seems reasonable to abstract
this into a nicer interface that just gives you the right
value.

Differential Revision: https://reviews.llvm.org/D31105

llvm-svn: 298322

4 files changed, 51 insertions, 17 deletions

diff --git a/llvm/lib/CodeGen/AsmPrinter/DIEHash.cpp b/llvm/lib/CodeGen/AsmPrinter/DIEHash.cpp
index d8ecc7ccfb9..8e3b88d0af0 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DIEHash.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DIEHash.cpp
@@ -490,9 +490,9 @@ uint64_t DIEHash::computeCUSignature(const DIE &Die) {
   Hash.final(Result);
 
   // ... take the least significant 8 bytes and return those. Our MD5
-  // implementation always returns its results in little endian, swap bytes
-  // appropriately.
-  return support::endian::read64le(Result + 8);
+  // implementation always returns its results in little endian, so we actually
+  // need the "high" word.
+  return Result.high();
 }
 
 /// This is based on the type signature computation given in section 7.27 of the
@@ -514,7 +514,7 @@ uint64_t DIEHash::computeTypeSignature(const DIE &Die) {
   Hash.final(Result);
 
   // ... take the least significant 8 bytes and return those. Our MD5
-  // implementation always returns its results in little endian, swap bytes
-  // appropriately.
-  return support::endian::read64le(Result + 8);
+  // implementation always returns its results in little endian, so we actually
+  // need the "high" word.
+  return Result.high();
 }
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index 0b9bacd86e5..15e5be2e65d 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -39,7 +39,6 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/Dwarf.h"
-#include "llvm/Support/Endian.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/FormattedStream.h"
 #include "llvm/Support/LEB128.h"
@@ -1945,11 +1944,11 @@ uint64_t DwarfDebug::makeTypeSignature(StringRef Identifier) {
   MD5 Hash;
   Hash.update(Identifier);
   // ... take the least significant 8 bytes and return those. Our MD5
-  // implementation always returns its results in little endian, swap bytes
-  // appropriately.
+  // implementation always returns its results in little endian, so we actually
+  // need the "high" word.
   MD5::MD5Result Result;
   Hash.final(Result);
-  return support::endian::read64le(Result + 8);
+  return Result.high();
 }
 
 void DwarfDebug::addDwarfTypeUnitType(DwarfCompileUnit &CU,
diff --git a/llvm/lib/Support/MD5.cpp b/llvm/lib/Support/MD5.cpp
index 809dbbce708..bdbf1d67793 100644
--- a/llvm/lib/Support/MD5.cpp
+++ b/llvm/lib/Support/MD5.cpp
@@ -261,10 +261,16 @@ void MD5::final(MD5Result &Result) {
   support::endian::write32le(&Result[12], d);
 }
 
-void MD5::stringifyResult(MD5Result &Result, SmallString<32> &Str) {
+SmallString<32> MD5::MD5Result::digest() const {
+  SmallString<32> Str;
   raw_svector_ostream Res(Str);
   for (int i = 0; i < 16; ++i)
-    Res << format("%.2x", Result[i]);
+    Res << format("%.2x", Bytes[i]);
+  return Str;
+}
+
+void MD5::stringifyResult(MD5Result &Result, SmallString<32> &Str) {
+  Str = Result.digest();
 }
 
 std::array<uint8_t, 16> MD5::hash(ArrayRef<uint8_t> Data) {
@@ -273,7 +279,5 @@ std::array<uint8_t, 16> MD5::hash(ArrayRef<uint8_t> Data) {
   MD5::MD5Result Res;
   Hash.final(Res);
 
-  std::array<uint8_t, 16> Arr;
-  memcpy(Arr.data(), Res, sizeof(Res));
-  return Arr;
+  return Res;
 }
diff --git a/llvm/lib/Support/Path.cpp b/llvm/lib/Support/Path.cpp
index ffb8ab22088..9fd6652ce4b 100644
--- a/llvm/lib/Support/Path.cpp
+++ b/llvm/lib/Support/Path.cpp
@@ -11,13 +11,14 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Support/Path.h"
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/Support/COFF.h"
-#include "llvm/Support/MachO.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/FileSystem.h"
-#include "llvm/Support/Path.h"
+#include "llvm/Support/MachO.h"
 #include "llvm/Support/Process.h"
 #include <cctype>
 #include <cstring>
@@ -924,6 +925,36 @@ std::error_code copy_file(const Twine &From, const Twine &To) {
   return std::error_code();
 }
 
+ErrorOr<MD5::MD5Result> md5_contents(int FD) {
+  MD5 Hash;
+
+  constexpr size_t BufSize = 4096;
+  std::vector<uint8_t> Buf(BufSize);
+  int BytesRead = 0;
+  for (;;) {
+    BytesRead = read(FD, Buf.data(), BufSize);
+    if (BytesRead <= 0)
+      break;
+    Hash.update(makeArrayRef(Buf.data(), BytesRead));
+  }
+
+  if (BytesRead < 0)
+    return std::error_code(errno, std::generic_category());
+  MD5::MD5Result Result;
+  Hash.final(Result);
+  return Result;
+}
+
+ErrorOr<MD5::MD5Result> md5_contents(const Twine &Path) {
+  int FD;
+  if (auto EC = openFileForRead(Path, FD))
+    return EC;
+
+  auto Result = md5_contents(FD);
+  close(FD);
+  return Result;
+}
+
 bool exists(file_status status) {
   return status_known(status) && status.type() != file_type::file_not_found;
 }