From 7945f41ccc63510a3fcb68d7c00e0c48143c4ed3 Mon Sep 17 00:00:00 2001
From: Alex Beregszaszi <alex@rtfs.hu>
Date: Fri, 5 Aug 2016 10:56:59 +0100
Subject: [PATCH] Include UTF8 helpers in libdevcore

---
 libdevcore/UTF8.cpp | 86 +++++++++++++++++++++++++++++++++++++++++++++
 libdevcore/UTF8.h   | 40 +++++++++++++++++++++
 2 files changed, 126 insertions(+)
 create mode 100644 libdevcore/UTF8.cpp
 create mode 100644 libdevcore/UTF8.h

diff --git a/libdevcore/UTF8.cpp b/libdevcore/UTF8.cpp
new file mode 100644
index 000000000..4bae75efa
--- /dev/null
+++ b/libdevcore/UTF8.cpp
@@ -0,0 +1,86 @@
+/*
+	This file is part of cpp-ethereum.
+
+	cpp-ethereum is free software: you can redistribute it and/or modify
+	it under the terms of the GNU General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	cpp-ethereum is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU General Public License for more details.
+
+	You should have received a copy of the GNU General Public License
+	along with cpp-ethereum.  If not, see <http://www.gnu.org/licenses/>.
+*/
+/** @file UTF8.cpp
+ * @author Alex Beregszaszi
+ * @date 2016
+ *
+ * UTF-8 related helpers
+ */
+
+#include "UTF8.h"
+
+
+namespace dev
+{
+
+namespace utf8
+{
+
+
+bool validate(std::string input, int &invalidPosition)
+{
+	const int length = input.length();
+	bool valid = true;
+	int i = 0;
+
+	for (; i < length; i++)
+	{
+		if ((unsigned char)input[i] < 0x80)
+			continue;
+
+		int count = 0;
+		switch(input[i] & 0xe0) {
+			case 0xc0: count = 1; break;
+			case 0xe0: count = 2; break;
+			case 0xf0: count = 3; break;
+			default: break;
+		}
+
+		if (count == 0)
+		{
+			valid = false;
+			break;
+		}
+
+		if ((i + count) >= length)
+		{
+			valid = false;
+			break;
+		}
+
+		for (int j = 0; j < count; j++)
+		{
+			i++;
+			if ((input[i] & 0xc0) != 0x80)
+			{
+				valid = false;
+				break;
+			}
+		}
+	}
+
+	if (valid)
+		return true;
+
+	invalidPosition = i;
+	return false;
+}
+
+
+}
+
+}
diff --git a/libdevcore/UTF8.h b/libdevcore/UTF8.h
new file mode 100644
index 000000000..39f76a116
--- /dev/null
+++ b/libdevcore/UTF8.h
@@ -0,0 +1,40 @@
+/*
+	This file is part of cpp-ethereum.
+
+	cpp-ethereum is free software: you can redistribute it and/or modify
+	it under the terms of the GNU General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	cpp-ethereum is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU General Public License for more details.
+
+	You should have received a copy of the GNU General Public License
+	along with cpp-ethereum.  If not, see <http://www.gnu.org/licenses/>.
+*/
+/** @file UTF8.h
+ * @author Alex Beregszaszi
+ * @date 2016
+ *
+ * UTF-8 related helpers
+ */
+
+#pragma once
+
+#include <string>
+
+namespace dev
+{
+
+namespace utf8
+{
+
+/// Validate an input for UTF8 encoding
+/// @returns true if it is invalid and the first invalid position in invalidPosition
+bool validate(std::string input, int &invalidPosition);
+
+}
+
+}