From 55c3b29f7b20f3801848e0ab71e9de1d22207b95 Mon Sep 17 00:00:00 2001
From: Mike Pall <mike>
Date: Sat, 29 Aug 2015 23:58:28 +0200
Subject: [PATCH] Parse Unicode string escape \u{XX...}.

Thanks to drbo.
---
 doc/changes.html    |  1 +
 doc/extensions.html |  7 +++++++
 src/lj_lex.c        | 27 +++++++++++++++++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/doc/changes.html b/doc/changes.html
index febb03c7..125b58b4 100644
--- a/doc/changes.html
+++ b/doc/changes.html
@@ -86,6 +86,7 @@ Please take a look at the commit history for more details.
 <li>Add <tt>LJ_GC64</tt> mode: 64 bit GC object references (really: 47 bit). Interpreter-only for now.</li>
 <li>Add <tt>LJ_FR2</tt> mode: Two-slot frame info. Required by <tt>LJ_GC64</tt> mode.</li>
 <li>Add <tt>table.new()</tt> and <tt>table.clear()</tt>.</li>
+<li>Parse Unicode escape <tt>'\u{XX...}'</tt> in string literals.</li>
 <li>Parse binary number literals (<tt>0bxxx</tt>).</li>
 </ul></li>
 <li>Improvements to the JIT compiler:
diff --git a/doc/extensions.html b/doc/extensions.html
index 84ca5ce4..e034e1dc 100644
--- a/doc/extensions.html
+++ b/doc/extensions.html
@@ -344,6 +344,13 @@ Lua&nbsp;5.1, which prevents implementing features that would otherwise
 break the Lua/C API and ABI (e.g. <tt>_ENV</tt>).
 </p>
 
+<h2 id="lua53">Extensions from Lua 5.3</h2>
+<p>
+LuaJIT supports some extensions from Lua&nbsp;5.3:
+<ul>
+<li>Unicode escape <tt>'\u{XX...}'</tt> embeds the UTF-8 encoding in string literals.</li>
+</ul>
+
 <h2 id="exceptions">C++ Exception Interoperability</h2>
 <p>
 LuaJIT has built-in support for interoperating with C++&nbsp;exceptions.
diff --git a/src/lj_lex.c b/src/lj_lex.c
index 8409cd78..5a918f74 100644
--- a/src/lj_lex.c
+++ b/src/lj_lex.c
@@ -214,6 +214,33 @@ static void lex_string(LexState *ls, TValue *tv)
 	  c += 9;
 	}
 	break;
+      case 'u':  /* Unicode escape '\u{XX...}'. */
+	if (lex_next(ls) != '{') goto err_xesc;
+	lex_next(ls);
+	c = 0;
+	do {
+	  c = (c << 4) | (ls->c & 15u);
+	  if (!lj_char_isdigit(ls->c)) {
+	    if (!lj_char_isxdigit(ls->c)) goto err_xesc;
+	    c += 9;
+	  }
+	  if (c >= 0x110000) goto err_xesc;  /* Out of Unicode range. */
+	} while (lex_next(ls) != '}');
+	if (c < 0x800) {
+	  if (c < 0x80) break;
+	  lex_save(ls, 0xc0 | (c >> 6));
+	} else {
+	  if (c >= 0x10000) {
+	    lex_save(ls, 0xf0 | (c >> 18));
+	    lex_save(ls, 0x80 | ((c >> 12) & 0x3f));
+	  } else {
+	    if (c >= 0xd800 && c < 0xe000) goto err_xesc;  /* No surrogates. */
+	    lex_save(ls, 0xe0 | (c >> 12));
+	  }
+	  lex_save(ls, 0x80 | ((c >> 6) & 0x3f));
+	}
+	c = 0x80 | (c & 0x3f);
+	break;
       case 'z':  /* Skip whitespace. */
 	lex_next(ls);
 	while (lj_char_isspace(ls->c))