VeryCrazyDog · August 28, 2023 13:31 · Mar 9, 2015 · Mar 8, 2015 · Mar 8, 2015 · Mar 8, 2015
diff --git a/ReadUtfFile.cpp b/ReadUtfFile.cpp
@@ -1,5 +1,6 @@
 // Reading ASCII, UTF-8, UTF-16LE, UTF-16BE with auto BOM detection using C++11 on Windows platform
 // Code tested on Microsoft Visual Studio 2013 on Windows 7
+// Part of the code is referencing http://cfc.kizzx2.com/index.php/reading-a-unicode-utf16-file-in-windows-c/
 
 #include <stdio.h>
 #include <tchar.h>

diff --git a/ReadUtfFile.cpp b/ReadUtfFile.cpp
@@ -65,6 +65,7 @@ std::string readFile(std::string path)
 	else if (encoding == ENCODING_UTF16BE) {
 		std::string src = ss.str();
 		std::string dst = src;
+		// Using Windows API
 		_swab(&src[0u], &dst[0u], src.size() + 1);
 		std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> utfconv;
 		result = utfconv.to_bytes(std::wstring((wchar_t *)dst.c_str()));

diff --git a/ReadUtfFile → ReadUtfFile.cpp b/ReadUtfFile → ReadUtfFile.cpp
diff --git a/gistfile1.cpp → ReadUtfFile b/gistfile1.cpp → ReadUtfFile
diff --git a/gistfile1.cpp b/gistfile1.cpp
@@ -0,0 +1,90 @@
+// Reading ASCII, UTF-8, UTF-16LE, UTF-16BE with auto BOM detection using C++11 on Windows platform
+// Code tested on Microsoft Visual Studio 2013 on Windows 7
+
+#include <stdio.h>
+#include <tchar.h>
+#include <string>
+#include <fstream>
+#include <sstream>
+#include <locale>
+#include <codecvt>
+#include <iostream>
+#include <io.h>
+#include <fcntl.h>
+
+#define TEXT_FILE_PATH      "D:\\test.txt"
+#define ENCODING_ASCII      0
+#define ENCODING_UTF8       1
+#define ENCODING_UTF16LE    2
+#define ENCODING_UTF16BE    3
+
+std::string readFile(std::string path)
+{
+	std::string result;
+	std::ifstream ifs(path.c_str(), std::ios::binary);
+	std::stringstream ss;
+	int encoding = ENCODING_ASCII;
+
+	if (!ifs.is_open()) {
+		// Unable to read file
+		result.clear();
+		return result;
+	}
+	else if (ifs.eof()) {
+		result.clear();
+	}
+	else {
+		int ch1 = ifs.get();
+		int ch2 = ifs.get();
+		if (ch1 == 0xff && ch2 == 0xfe) {
+			// The file contains UTF-16LE BOM
+			encoding = ENCODING_UTF16LE;
+		}
+		else if (ch1 == 0xfe && ch2 == 0xff) {
+			// The file contains UTF-16BE BOM
+			encoding = ENCODING_UTF16BE;
+		}
+		else {
+			int ch3 = ifs.get();
+			if (ch1 == 0xef && ch2 == 0xbb && ch3 == 0xbf) {
+				// The file contains UTF-8 BOM
+				encoding = ENCODING_UTF8;
+			}
+			else {
+				// The file does not have BOM
+				encoding = ENCODING_ASCII;
+				ifs.seekg(0);
+			}
+		}
+	}
+	ss << ifs.rdbuf() << '\0';
+	if (encoding == ENCODING_UTF16LE) {
+		std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> utfconv;
+		result = utfconv.to_bytes(std::wstring((wchar_t *)ss.str().c_str()));
+	}
+	else if (encoding == ENCODING_UTF16BE) {
+		std::string src = ss.str();
+		std::string dst = src;
+		_swab(&src[0u], &dst[0u], src.size() + 1);
+		std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> utfconv;
+		result = utfconv.to_bytes(std::wstring((wchar_t *)dst.c_str()));
+	}
+	else if (encoding == ENCODING_UTF8) {
+		result = ss.str();
+	}
+	else {
+		result = ss.str();
+	}
+	return result;
+}
+
+int _tmain(int argc, _TCHAR* argv[])
+{
+	std::string path = TEXT_FILE_PATH;
+	std::string utf8Content = readFile(path);
+	std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> utfconv;
+	std::wstring utf16LeContent = utfconv.from_bytes(utf8Content);
+	_setmode(_fileno(stdout), _O_U8TEXT);
+	std::wcout << utf16LeContent << std::endl;
+	return 0;
+}