epee: support unicode in parsed strings

1 files changed, 59 insertions, 0 deletions

diff --git a/contrib/epee/include/storages/parserse_base_utils.h b/contrib/epee/include/storages/parserse_base_utils.h
index b5c4138c5..fe53628a5 100644
--- a/contrib/epee/include/storages/parserse_base_utils.h
+++ b/contrib/epee/include/storages/parserse_base_utils.h
@@ -31,6 +31,9 @@
 #include <algorithm>
 #include <boost/utility/string_ref.hpp>
 
+#undef MONERO_DEFAULT_LOG_CATEGORY
+#define MONERO_DEFAULT_LOG_CATEGORY "serialization"
+
 namespace epee 
 {
 namespace misc_utils
@@ -62,6 +65,26 @@ namespace misc_utils
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
     };
 
+    static const constexpr unsigned char isx[256] =
+    {
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+        0,    1,    2,    3,    4,    5,    6,    7,    8,    9, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff,   10,   11,   12,   13,   14,   15, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff,   10,   11,   12,   13,   14,   15, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+     0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    };
+
     inline bool isspace(char c)
     {
       return lut[(uint8_t)c] & 8;
@@ -162,6 +185,42 @@ namespace misc_utils
               val.push_back('\\');break;
             case '/':  //Slash character
               val.push_back('/');break;
+            case 'u':  //Unicode code point
+              if (buf_end - it < 4)
+              {
+                ASSERT_MES_AND_THROW("Invalid Unicode escape sequence");
+              }
+              else
+              {
+                uint32_t dst = 0;
+                for (int i = 0; i < 4; ++i)
+                {
+                  const unsigned char tmp = isx[(int)*++it];
+                  CHECK_AND_ASSERT_THROW_MES(tmp != 0xff, "Bad Unicode encoding");
+                  dst = dst << 4 | tmp;
+                }
+                // encode as UTF-8
+                if (dst <= 0x7f)
+                {
+                  val.push_back(dst);
+                }
+                else if (dst <= 0x7ff)
+                {
+                  val.push_back(0xc0 | (dst >> 6));
+                  val.push_back(0x80 | (dst & 0x3f));
+                }
+                else if (dst <= 0xffff)
+                {
+                  val.push_back(0xe0 | (dst >> 12));
+                  val.push_back(0x80 | ((dst >> 6) & 0x3f));
+                  val.push_back(0x80 | (dst & 0x3f));
+                }
+                else
+                {
+                  ASSERT_MES_AND_THROW("Unicode code point is out or range");
+                }
+              }
+              break;
             default:
               val.push_back(*it);
               LOG_PRINT_L0("Unknown escape sequence :\"\\" << *it << "\"");