Use hash for library placeholders.

7 files changed, 69 insertions, 9 deletions

diff --git a/Changelog.md b/Changelog.md
index 86376017..b817dc22 100644
--- a/Changelog.md
+++ b/Changelog.md
@@ -17,6 +17,7 @@ Breaking Changes:
  * Commandline interface: Remove obsolete ``--formal`` option.
  * Commandline interface: Rename the ``--julia`` option to ``--yul``.
  * Commandline interface: Require ``-`` if standard input is used as source.
+ * Commandline interface: Use hash of library name for link placeholder instead of name itself.
  * Compiler interface: Disallow remappings with empty prefix.
  * Control Flow Analyzer: Consider mappings as well when checking for uninitialized return values.
  * Control Flow Analyzer: Turn warning about returning uninitialized storage pointers into an error.
diff --git a/libevmasm/LinkerObject.cpp b/libevmasm/LinkerObject.cpp
index 1d5efecb..0ac69966 100644
--- a/libevmasm/LinkerObject.cpp
+++ b/libevmasm/LinkerObject.cpp
@@ -21,6 +21,7 @@
 
 #include <libevmasm/LinkerObject.h>
 #include <libdevcore/CommonData.h>
+#include <libdevcore/SHA3.h>
 
 using namespace dev;
 using namespace dev::eth;
@@ -50,14 +51,19 @@ string LinkerObject::toHex() const
 	for (auto const& ref: linkReferences)
 	{
 		size_t pos = ref.first * 2;
-		string const& name = ref.second;
+		string hash = libraryPlaceholder(ref.second);
 		hex[pos] = hex[pos + 1] = hex[pos + 38] = hex[pos + 39] = '_';
 		for (size_t i = 0; i < 36; ++i)
-			hex[pos + 2 + i] = i < name.size() ? name[i] : '_';
+			hex[pos + 2 + i] = hash.at(i);
 	}
 	return hex;
 }
 
+string LinkerObject::libraryPlaceholder(string const& _libraryName)
+{
+	return keccak256(_libraryName).hex().substr(0, 36);
+}
+
 h160 const*
 LinkerObject::matchLibrary(
 	string const& _linkRefName,
diff --git a/libevmasm/LinkerObject.h b/libevmasm/LinkerObject.h
index 152487b4..92890803 100644
--- a/libevmasm/LinkerObject.h
+++ b/libevmasm/LinkerObject.h
@@ -50,6 +50,11 @@ struct LinkerObject
 	/// addresses by placeholders.
 	std::string toHex() const;
 
+	/// @returns a 36 character string that is used as a placeholder for the library
+	/// address (enclosed by `__` on both sides). The placeholder is the hex representation
+	/// of the first 18 bytes of the keccak-256 hash of @a _libraryName.
+	static std::string libraryPlaceholder(std::string const& _libraryName);
+
 private:
 	static h160 const* matchLibrary(
 		std::string const& _linkRefName,
diff --git a/solc/CommandLineInterface.cpp b/solc/CommandLineInterface.cpp
index 8fd0d6ef..7ab76c12 100644
--- a/solc/CommandLineInterface.cpp
+++ b/solc/CommandLineInterface.cpp
@@ -226,21 +226,21 @@ void CommandLineInterface::handleBinary(string const& _contract)
 	if (m_args.count(g_argBinary))
 	{
 		if (m_args.count(g_argOutputDir))
-			createFile(m_compiler->filesystemFriendlyName(_contract) + ".bin", m_compiler->object(_contract).toHex());
+			createFile(m_compiler->filesystemFriendlyName(_contract) + ".bin", objectWithLinkRefsHex(m_compiler->object(_contract)));
 		else
 		{
 			cout << "Binary: " << endl;
-			cout << m_compiler->object(_contract).toHex() << endl;
+			cout << objectWithLinkRefsHex(m_compiler->object(_contract)) << endl;
 		}
 	}
 	if (m_args.count(g_argBinaryRuntime))
 	{
 		if (m_args.count(g_argOutputDir))
-			createFile(m_compiler->filesystemFriendlyName(_contract) + ".bin-runtime", m_compiler->runtimeObject(_contract).toHex());
+			createFile(m_compiler->filesystemFriendlyName(_contract) + ".bin-runtime", objectWithLinkRefsHex(m_compiler->runtimeObject(_contract)));
 		else
 		{
 			cout << "Binary of the runtime part: " << endl;
-			cout << m_compiler->runtimeObject(_contract).toHex() << endl;
+			cout << objectWithLinkRefsHex(m_compiler->runtimeObject(_contract)) << endl;
 		}
 	}
 }
@@ -1056,8 +1056,12 @@ bool CommandLineInterface::link()
 	{
 		string const& name = library.first;
 		// Library placeholders are 40 hex digits (20 bytes) that start and end with '__'.
-		// This leaves 36 characters for the library name, while too short library names are
-		// padded on the right with '_' and too long names are truncated.
+		// This leaves 36 characters for the library identifier. The identifier used to
+		// be just the cropped or '_'-padded library name, but this changed to
+		// the cropped hex representation of the hash of the library name.
+		// We support both ways of linking here.
+		librariesReplacements["__" + eth::LinkerObject::libraryPlaceholder(name) + "__"] = library.second;
+
 		string replacement = "__";
 		for (size_t i = 0; i < placeholderSize - 4; ++i)
 			replacement.push_back(i < name.size() ? name[i] : '_');
@@ -1087,6 +1091,11 @@ bool CommandLineInterface::link()
 				cerr << "Reference \"" << name << "\" in file \"" << src.first << "\" still unresolved." << endl;
 			it += placeholderSize;
 		}
+		// Remove hints for resolved libraries.
+		for (auto const& library: m_libraries)
+			boost::algorithm::erase_all(src.second, "\n" + libraryPlaceholderHint(library.first));
+		while (!src.second.empty() && *prev(src.second.end()) == '\n')
+			   src.second.resize(src.second.size() - 1);
 	}
 	return true;
 }
@@ -1100,6 +1109,23 @@ void CommandLineInterface::writeLinkedFiles()
 			writeFile(src.first, src.second);
 }
 
+string CommandLineInterface::libraryPlaceholderHint(string const& _libraryName)
+{
+	return "// " + eth::LinkerObject::libraryPlaceholder(_libraryName) + " -> " + _libraryName;
+}
+
+string CommandLineInterface::objectWithLinkRefsHex(eth::LinkerObject const& _obj)
+{
+	string out = _obj.toHex();
+	if (!_obj.linkReferences.empty())
+	{
+		out += "\n";
+		for (auto const& linkRef: _obj.linkReferences)
+			out += "\n" + libraryPlaceholderHint(linkRef.second);
+	}
+	return out;
+}
+
 bool CommandLineInterface::assemble(
 	AssemblyStack::Language _language,
 	AssemblyStack::Machine _targetMachine
diff --git a/solc/CommandLineInterface.h b/solc/CommandLineInterface.h
index 010dce34..aa49383a 100644
--- a/solc/CommandLineInterface.h
+++ b/solc/CommandLineInterface.h
@@ -54,6 +54,10 @@ public:
 private:
 	bool link();
 	void writeLinkedFiles();
+	/// @returns the ``// <identifier> -> name`` hint for library placeholders.
+	static std::string libraryPlaceholderHint(std::string const& _libraryName);
+	/// @returns the full object with library placeholder hints in hex.
+	static std::string objectWithLinkRefsHex(eth::LinkerObject const& _obj);
 
 	bool assemble(AssemblyStack::Language _language, AssemblyStack::Machine _targetMachine);
 
diff --git a/test/cmdlineTests.sh b/test/cmdlineTests.sh
index 71866bce..20254ef4 100755
--- a/test/cmdlineTests.sh
+++ b/test/cmdlineTests.sh
@@ -233,6 +233,24 @@ echo '' | "$SOLC" - --link --libraries a:0x90f20564390eAe531E810af625A22f51385Cd
 printTask "Testing long library names..."
 echo '' | "$SOLC" - --link --libraries aveeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeerylonglibraryname:0x90f20564390eAe531E810af625A22f51385Cd222 >/dev/null
 
+printTask "Testing linking itself..."
+SOLTMPDIR=$(mktemp -d)
+(
+    cd "$SOLTMPDIR"
+    set -e
+    echo 'library L { function f() public pure {} } contract C { function f() public pure { L.f(); } }' > x.sol
+    "$SOLC" --bin -o . x.sol 2>/dev/null
+    # Explanation and placeholder should be there
+    grep -q '//' C.bin && grep -q '__' C.bin
+    # But not in library file.
+    grep -q -v '[/_]' L.bin
+    # Now link
+    "$SOLC" --link --libraries x.sol:L:0x90f20564390eAe531E810af625A22f51385Cd222 C.bin
+    # Now the placeholder and explanation should be gone.
+    grep -q -v '[/_]' C.bin
+)
+rm -rf "$SOLTMPDIR"
+
 printTask "Testing overwriting files..."
 SOLTMPDIR=$(mktemp -d)
 (
diff --git a/test/libevmasm/Assembler.cpp b/test/libevmasm/Assembler.cpp
index bc652f56..38ed9732 100644
--- a/test/libevmasm/Assembler.cpp
+++ b/test/libevmasm/Assembler.cpp
@@ -94,7 +94,7 @@ BOOST_AUTO_TEST_CASE(all_assembly_items)
 
 	BOOST_CHECK_EQUAL(
 		_assembly.assemble().toHex(),
-		"5b6001600220606773__someLibrary___________________________"
+		"5b6001600220606773__bf005014d9d0f534b8fcb268bd84c491a238__"
 		"6000567f556e75736564206665617475726520666f722070757368696e"
 		"6720737472696e605f6001605e73000000000000000000000000000000000000000000fe"
 		"fe010203044266eeaa"