utf8 character counting to check message size < 140

src/main.cpp

@@ -14,6 +14,7 @@
 #include "chainparams.h"
 
 #include "twister.h"
+#include "utf8core.h"
 
 #include <boost/algorithm/string/replace.hpp>
 #include <boost/filesystem.hpp>
@@ -428,7 +429,10 @@ bool CheckTransaction(const CTransaction& tx, CValidationState &state, int maxHe
         string spamMsg = tx.message.ExtractPushDataString(0);
         if (!spamMsg.size())
             return state.DoS(100, error("CheckTransaction() : invalid or empty spam message"));
-        if (spamMsg.size() > MAX_SPAM_MSG_SIZE)
+        int spamMsgUtf8Size = utf8::num_characters(spamMsg.begin(), spamMsg.end());
+        if (spamMsgUtf8Size < 0)
+            return state.DoS(100, error("CheckTransaction() : spam message invalid utf8"));
+        if (spamMsgUtf8Size > MAX_SPAM_MSG_SIZE)
             return state.DoS(100, error("CheckTransaction() : spam message too big"));
 
         string spamUser = tx.userName.ExtractPushDataString(0);

src/twister.cpp

@@ -6,6 +6,7 @@
 #include "init.h"
 #include "bitcoinrpc.h"
 #include "txdb.h"
+#include "utf8core.h"
 
 using namespace json_spirit;
 using namespace std;
@@ -827,6 +828,7 @@ bool acceptSignedPost(char const *data, int data_size, std::string username, int
             } else {
                 std::string n = post->dict_find_string_value("n");
                 std::string msg = post->dict_find_string_value("msg");
+                int msgUtf8Chars = utf8::num_characters(msg.begin(), msg.end());
                 int k = post->dict_find_int_value("k",-1);
                 int height = post->dict_find_int_value("height",-1);
 
@@ -842,8 +844,10 @@ bool acceptSignedPost(char const *data, int data_size, std::string username, int
                 } else if( height < 0 || (height > getBestHeight() && getBestHeight() > 0) ) {
                     sprintf(errbuf,"post from future not accepted (height: %d > %d)",
                             height, getBestHeight());
-                } else if( msg.size() && msg.size() > 140 ) {
-                    sprintf(errbuf,"msg too big (%zd > 140)", msg.size());
+                } else if( msgUtf8Chars < 0 ) {
+                    sprintf(errbuf,"invalid utf8 string");
+                } else if( msgUtf8Chars > 140 ) {
+                    sprintf(errbuf,"msg too big (%d > 140)", msgUtf8Chars);
                 } else {
                     std::pair<char const*, int> postbuf = post->data_section();
                     ret = verifySignature(

src/utf8core.h

@@ -0,0 +1,344 @@
+// Copyright 2006 Nemanja Trifunovic
+
+/*
+Permission is hereby granted, free of charge, to any person or organization
+obtaining a copy of the software and accompanying documentation covered by
+this license (the "Software") to use, reproduce, display, distribute,
+execute, and transmit the Software, and to prepare derivative works of the
+Software, and to permit third-parties to whom the Software is furnished to
+do so, all subject to the following:
+
+The copyright notices in the Software and this entire statement, including
+the above license grant, this restriction and the following disclaimer,
+must be included in all copies of the Software, in whole or in part, and
+all derivative works of the Software, unless such copies or derivative
+works are solely in the form of machine-executable object code generated by
+a source language processor.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
+SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
+FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+DEALINGS IN THE SOFTWARE.
+*/
+
+
+#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
+
+#include <iterator>
+#include <stdint.h>
+
+namespace utf8
+{
+    // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
+    // You may need to change them to match your system.
+    // These typedefs have the same names as ones from cstdint, or boost/cstdint
+    //typedef unsigned char   uint8_t;
+    //typedef unsigned short  uint16_t;
+    //typedef unsigned int    uint32_t;
+
+// Helper code - not intended to be directly called by the library users. May be changed at any time
+namespace internal
+{
+    // Unicode constants
+    // Leading (high) surrogates: 0xd800 - 0xdbff
+    // Trailing (low) surrogates: 0xdc00 - 0xdfff
+    const uint16_t LEAD_SURROGATE_MIN  = 0xd800u;
+    const uint16_t LEAD_SURROGATE_MAX  = 0xdbffu;
+    const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
+    const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
+    const uint16_t LEAD_OFFSET         = LEAD_SURROGATE_MIN - (0x10000 >> 10);
+    const uint32_t SURROGATE_OFFSET    = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
+
+    // Maximum valid value for a Unicode code point
+    const uint32_t CODE_POINT_MAX      = 0x0010ffffu;
+
+    template<typename octet_type>
+    inline uint8_t mask8(octet_type oc)
+    {
+        return static_cast<uint8_t>(0xff & oc);
+    }
+    template<typename u16_type>
+    inline uint16_t mask16(u16_type oc)
+    {
+        return static_cast<uint16_t>(0xffff & oc);
+    }
+    template<typename octet_type>
+    inline bool is_trail(octet_type oc)
+    {
+        return ((utf8::internal::mask8(oc) >> 6) == 0x2);
+    }
+
+    template <typename u16>
+    inline bool is_lead_surrogate(u16 cp)
+    {
+        return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
+    }
+
+    template <typename u16>
+    inline bool is_trail_surrogate(u16 cp)
+    {
+        return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+    }
+
+    template <typename u16>
+    inline bool is_surrogate(u16 cp)
+    {
+        return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
+    }
+
+    template <typename u32>
+    inline bool is_code_point_valid(u32 cp)
+    {
+        return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
+    }
+
+    template <typename octet_iterator>
+    inline typename std::iterator_traits<octet_iterator>::difference_type
+    sequence_length(octet_iterator lead_it)
+    {
+        uint8_t lead = utf8::internal::mask8(*lead_it);
+        if (lead < 0x80)
+            return 1;
+        else if ((lead >> 5) == 0x6)
+            return 2;
+        else if ((lead >> 4) == 0xe)
+            return 3;
+        else if ((lead >> 3) == 0x1e)
+            return 4;
+        else
+            return 0;
+    }
+
+    template <typename octet_difference_type>
+    inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
+    {
+        if (cp < 0x80) {
+            if (length != 1) 
+                return true;
+        }
+        else if (cp < 0x800) {
+            if (length != 2) 
+                return true;
+        }
+        else if (cp < 0x10000) {
+            if (length != 3) 
+                return true;
+        }
+
+        return false;
+    }
+
+    enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
+
+    /// Helper for get_sequence_x
+    template <typename octet_iterator>
+    utf_error increase_safely(octet_iterator& it, octet_iterator end)
+    {
+        if (++it == end)
+            return NOT_ENOUGH_ROOM;
+
+        if (!utf8::internal::is_trail(*it))
+            return INCOMPLETE_SEQUENCE;
+        
+        return UTF8_OK;
+    }
+
+    #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}    
+
+    /// get_sequence_x functions decode utf-8 sequences of the length x
+    template <typename octet_iterator>
+    utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+            return NOT_ENOUGH_ROOM;
+
+        code_point = utf8::internal::mask8(*it);
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end) 
+            return NOT_ENOUGH_ROOM;
+        
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+            return NOT_ENOUGH_ROOM;
+            
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (*it) & 0x3f;
+
+        return UTF8_OK;
+    }
+
+    template <typename octet_iterator>
+    utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        if (it == end)
+           return NOT_ENOUGH_ROOM;
+
+        code_point = utf8::internal::mask8(*it);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
+
+        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+        code_point += (*it) & 0x3f;
+
+        return UTF8_OK;
+    }
+
+    #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
+
+    template <typename octet_iterator>
+    utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
+    {
+        // Save the original value of it so we can go back in case of failure
+        // Of course, it does not make much sense with i.e. stream iterators
+        octet_iterator original_it = it;
+
+        uint32_t cp = 0;
+        // Determine the sequence length based on the lead octet
+        typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
+        const octet_difference_type length = utf8::internal::sequence_length(it);
+
+        // Get trail octets and calculate the code point
+        utf_error err = UTF8_OK;
+        switch (length) {
+            case 0: 
+                return INVALID_LEAD;
+            case 1:
+                err = utf8::internal::get_sequence_1(it, end, cp);
+                break;
+            case 2:
+                err = utf8::internal::get_sequence_2(it, end, cp);
+            break;
+            case 3:
+                err = utf8::internal::get_sequence_3(it, end, cp);
+            break;
+            case 4:
+                err = utf8::internal::get_sequence_4(it, end, cp);
+            break;
+        }
+
+        if (err == UTF8_OK) {
+            // Decoding succeeded. Now, security checks...
+            if (utf8::internal::is_code_point_valid(cp)) {
+                if (!utf8::internal::is_overlong_sequence(cp, length)){
+                    // Passed! Return here.
+                    code_point = cp;
+                    ++it;
+                    return UTF8_OK;
+                }
+                else
+                    err = OVERLONG_SEQUENCE;
+            }
+            else 
+                err = INVALID_CODE_POINT;
+        }
+
+        // Failure branch - restore the original value of the iterator
+        it = original_it;
+        return err;
+    }
+
+    template <typename octet_iterator>
+    inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
+        uint32_t ignored;
+        return utf8::internal::validate_next(it, end, ignored);
+    }
+
+} // namespace internal
+
+    /// The library API - functions intended to be called by the users
+
+    // Byte order mark
+    const uint8_t bom[] = {0xef, 0xbb, 0xbf};
+
+    template <typename octet_iterator>
+    octet_iterator find_invalid(octet_iterator start, octet_iterator end)
+    {
+        octet_iterator result = start;
+        while (result != end) {
+            utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
+            if (err_code != internal::UTF8_OK)
+                return result;
+        }
+        return result;
+    }
+
+    template <typename octet_iterator>
+    int num_characters(octet_iterator start, octet_iterator end)
+    {
+        int count = 0;
+        octet_iterator it = start;
+        while (it != end) {
+            utf8::internal::utf_error err_code = utf8::internal::validate_next(it, end);
+            if (err_code != internal::UTF8_OK)
+                return -1;
+            count++;
+        }
+        return count;
+    }
+
+    template <typename octet_iterator>
+    inline bool is_valid(octet_iterator start, octet_iterator end)
+    {
+        return (utf8::find_invalid(start, end) == end);
+    }
+
+    template <typename octet_iterator>
+    inline bool starts_with_bom (octet_iterator it, octet_iterator end)
+    {
+        return (
+            ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
+            ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
+            ((it != end) && (utf8::internal::mask8(*it))   == bom[2])
+           );
+    }
+	
+    //Deprecated in release 2.3 
+    template <typename octet_iterator>
+    inline bool is_bom (octet_iterator it)
+    {
+        return (
+            (utf8::internal::mask8(*it++)) == bom[0] &&
+            (utf8::internal::mask8(*it++)) == bom[1] &&
+            (utf8::internal::mask8(*it))   == bom[2]
+           );
+    }
+} // namespace utf8
+
+#endif // header guard
+
+

twister-qt.pro

@@ -198,6 +198,7 @@ HEADERS +=  \
     src/threadsafety.h \
     src/limitedmap.h \
     src/scrypt.h \
+    src/utf8core.h \
     src/twister.h \
     src/twister_utils.h