Fix hdfs crash

src/Formats/JSONEachRowUtils.cpp

@@ -29,10 +29,12 @@ std::pair<bool, size_t> fileSegmentationEngineJSONEachRowImpl(ReadBuffer & in, D
         if (quotes)
         {
             pos = find_first_symbols<'\\', '"'>(pos, in.buffer().end());
+
             if (pos > in.buffer().end())
                 throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
             else if (pos == in.buffer().end())
                 continue;
+
             if (*pos == '\\')
             {
                 ++pos;
@@ -48,10 +50,12 @@ std::pair<bool, size_t> fileSegmentationEngineJSONEachRowImpl(ReadBuffer & in, D
         else
         {
             pos = find_first_symbols<'{', '}', '\\', '"'>(pos, in.buffer().end());
+
             if (pos > in.buffer().end())
                 throw Exception("Position in buffer is out of bounds. There must be a bug.", ErrorCodes::LOGICAL_ERROR);
             else if (pos == in.buffer().end())
                 continue;
+
             else if (*pos == '{')
             {
                 ++balance;

src/IO/ReadHelpers.cpp

@@ -351,9 +351,16 @@ static ReturnType parseJSONEscapeSequence(Vector & s, ReadBuffer & buf)
     };
 
     ++buf.position();
+
+    /// It is possible that current buffer ends with `\` (start of escape sequence), oef is not reached,
+    /// but there is no pending data yet. Without this wait we will read beyond the end of current buffer in code below.
+    while (!buf.eof() && !buf.hasPendingData()) {}
+
     if (buf.eof())
         return error("Cannot parse escape sequence", ErrorCodes::CANNOT_PARSE_ESCAPE_SEQUENCE);
 
+    assert(buf.hasPendingData());
+
     switch (*buf.position())
     {
         case '"':
@@ -1124,10 +1131,13 @@ void saveUpToPosition(ReadBuffer & in, DB::Memory<> & memory, char * current)
     const size_t old_bytes = memory.size();
     const size_t additional_bytes = current - in.position();
     const size_t new_bytes = old_bytes + additional_bytes;
+
     /// There are no new bytes to add to memory.
     /// No need to do extra stuff.
     if (new_bytes == 0)
         return;
+
+    assert(in.position() + additional_bytes <= in.buffer().end());
     memory.resize(new_bytes);
     memcpy(memory.data() + old_bytes, in.position(), additional_bytes);
     in.position() = current;
@@ -1140,6 +1150,8 @@ bool loadAtPosition(ReadBuffer & in, DB::Memory<> & memory, char * & current)
     if (current < in.buffer().end())
         return true;
 
+    while (!in.eof() && !in.hasPendingData()) {}
+
     saveUpToPosition(in, memory, current);
 
     bool loaded_more = !in.eof();