From 8b21192b1145c276bb3e5b655daaf92f9d762087 Mon Sep 17 00:00:00 2001
From: TangoCash <eric@loxat.de>
Date: Wed, 28 Mar 2018 22:24:19 +0200
Subject: [PATCH] fix webif xml encoding, part 2

Origin commit data
------------------
Branch: ni/coolstream
Commit: https://github.com/neutrino-images/ni-neutrino/commit/6b449f5d956907e87cec5f975f9f8dc1aefe334a
Author: TangoCash <eric@loxat.de>
Date: 2018-03-28 (Wed, 28 Mar 2018)


------------------
No further description and justification available within origin commit message!

------------------
This commit was generated by Migit
---
 src/nhttpd/yhttpd_core/yhook.cpp |  4 ++-
 src/system/helpers.cpp           | 57 ++++++++++++++++++++++++++++++++
 src/system/helpers.h             |  3 ++
 3 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/src/nhttpd/yhttpd_core/yhook.cpp b/src/nhttpd/yhttpd_core/yhook.cpp
index 0fd1f59fe..6cdce404b 100644
--- a/src/nhttpd/yhttpd_core/yhook.cpp
+++ b/src/nhttpd/yhttpd_core/yhook.cpp
@@ -10,6 +10,8 @@
 
 // UTF8 convert
 #include <zapit/zapit.h>
+#include <system/helpers.h>
+
 // yhttpd
 #include "yhook.h"
 #include "helper.h"
@@ -542,7 +544,7 @@ std::string CyhookHandler::outValue(std::string _content) {
 	std::string result = "";
 	switch (outType) {
 	case xml:
-		result = convert_UTF8_To_UTF8_XML(_content.c_str());
+		result = convert_UTF8_To_UTF8_XML(utf8_check_is_valid(_content) ? _content.c_str() : iso_8859_1_to_utf8(_content).c_str());
 		break;
 	case json:
 		result = json_convert_string(_content);
diff --git a/src/system/helpers.cpp b/src/system/helpers.cpp
index a117a7c7d..c198ff271 100644
--- a/src/system/helpers.cpp
+++ b/src/system/helpers.cpp
@@ -1651,3 +1651,60 @@ bool parseJsonFromString(string& jData, Json::Value *root, string *errMsg)
 	delete reader;
 	return ret;
 }
+
+std::string iso_8859_1_to_utf8(std::string &str)
+{
+	std::string strOut;
+	for (std::string::iterator it = str.begin(); it != str.end(); ++it)
+	{
+		uint8_t ch = *it;
+		if (ch < 0x80)
+		{
+			strOut.push_back(ch);
+		}
+		else
+		{
+			strOut.push_back(0xc0 | ch >> 6);
+			strOut.push_back(0x80 | (ch & 0x3f));
+		}
+	}
+	return strOut;
+}
+
+bool utf8_check_is_valid(const std::string &str)
+{
+	int c, i, ix, n, j;
+	for (i = 0, ix = str.length(); i < ix; i++)
+	{
+		c = (unsigned char) str[i];
+		/*
+		if (c==0x09 || c==0x0a || c==0x0d || (0x20 <= c && c <= 0x7e))
+			n = 0; // is_printable_ascii
+		*/
+		if (0x00 <= c && c <= 0x7f)
+			n = 0; // 0bbbbbbb
+		else if ((c & 0xE0) == 0xC0)
+			n = 1; // 110bbbbb
+		else if (c == 0xed && i < (ix - 1) && ((unsigned char)str[i + 1] & 0xa0) == 0xa0)
+			return false; // U+d800 to U+dfff
+		else if ((c & 0xF0) == 0xE0)
+			n = 2; // 1110bbbb
+		else if ((c & 0xF8) == 0xF0)
+			n = 3; // 11110bbb
+		/*
+		else if (($c & 0xFC) == 0xF8)
+			n=4; // 111110bb //byte 5, unnecessary in 4 byte UTF-8
+		else if (($c & 0xFE) == 0xFC)
+			n=5; // 1111110b //byte 6, unnecessary in 4 byte UTF-8
+		*/
+		else
+			return false;
+
+		for (j = 0; j < n && i < ix; j++) // n bytes matching 10bbbbbb follow?
+		{
+			if ((++i == ix) || (((unsigned char)str[i] & 0xC0) != 0x80))
+				return false;
+		}
+	}
+	return true;
+}
diff --git a/src/system/helpers.h b/src/system/helpers.h
index c39eac448..2c0827083 100644
--- a/src/system/helpers.h
+++ b/src/system/helpers.h
@@ -157,4 +157,7 @@ inline bool file_exists(const std::string file) { return file_exists(file.c_str(
 
 std::string readFile(std::string file);
 
+std::string iso_8859_1_to_utf8(std::string &str);
+bool utf8_check_is_valid(const std::string &str);
+
 #endif