Merge branch 'ZackerySpytz-cpp11_u_U_char_encoding_prefixes'

* ZackerySpytz-cpp11_u_U_char_encoding_prefixes:
  Document C++11 UCS-2 UCS-4 and C++17 UTF8 character literals support
  c++17 u8 character literals testcase
  C++17 u8 character literals fix
  C++17 u8 character literals testcase
  Fix the Java tests
  Add support for the C++11 u and U encoding prefixes for char literals

CHANGES.current

@@ -7,6 +7,10 @@ the issue number to the end of the URL: https://github.com/swig/swig/issues/
 Version 4.0.0 (in progress)
 ===========================
 
+2019-02-10: ZackerySpytz
+	    #1450 Add support for C++11 UCS-2 and UCS-4 character literals. Also add support for
+            C++17 UTF8 character literals.
+
 2019-02-10: wsfulton
 	    [MzScheme] #1437 MzScheme/Racket is now an 'Experimental' language. The examples work
             and a large portion of the test-suite is also working.

Doc/Manual/CPlusPlus11.html

@@ -714,6 +714,22 @@ const int SIZE = sizeof...(ClassName<int, int>);
 In the above example <tt>SIZE</tt> is of course wrapped as a constant.
 </p>
 
+<H3><a name="CPlusPlus11_new_char_literals">7.2.19 New character literals</a></H3>
+
+<p>
+C++11 adds support for UCS-2 and UCS-4 character literals.
+These character literals are preceded by either 'u' or 'U'.
+</p>
+
+<div class="code"><pre>
+char16_t a = u'a';
+char32_t b = U'b';
+</pre></div>
+
+<p>
+<b>Compatibility note:</b> SWIG-4.0.0 was the first version to support these Universal Coded Character Set (UCS) character literals.
+</p>
+
 <H3><a name="CPlusPlus11_new_string_literals">7.2.19 New string literals</a></H3>
 
 

Doc/Manual/CPlusPlus17.html

@@ -32,6 +32,10 @@ There isn't much in C++17 that affects SWIG, however, work has only just begun o
 C++17 support.
 </p>
 
+<p>
+<b>Compatibility note:</b> SWIG-4.0.0 is the first version to support any C++17 features.
+</p>
+
 <H2><a name="CPlusPlus17_core_language_changes">8.2 Core language changes</a></H2>
 
 
@@ -67,10 +71,20 @@ namespace A {
 </pre>
 </div>
 
+<H3><a name="CPlusPlus17_u8_char_literals">8.2.2 UTF-8 character literals</a></H3>
+
 <p>
-<b>Compatibility note:</b> SWIG-4.0.0 was the first version to support nested namespace definitions.
+C++17 added UTF-8 (u8) character literals.
+These are of type char.
+Example:
 </p>
 
+<div class="code">
+<pre>
+char a = u8'a';
+</pre>
+</div>
+
 <H2><a name="CPlusPlus17_standard_library_changes">8.3 Standard library changes</a></H2>
 
 

Examples/test-suite/common.mk

@@ -164,6 +164,7 @@ CPP_TEST_CASES += \
 	cpp_typedef \
 	cpp17_nested_namespaces \
 	cpp17_nspace_nested_namespaces \
+	cpp17_u8_char_literals \
 	curiously_recurring_template_pattern \
 	default_args \
 	default_arg_expressions \

Examples/test-suite/cpp11_raw_string_literals.i

@@ -47,6 +47,9 @@ wstring         aa =  L"Wide string";
 const char     *bb = u8"UTF-8 string";
 const char16_t *cc =  u"UTF-16 string";
 const char32_t *dd =  U"UTF-32 string";
+// New char literals
+char16_t char16_t_char = u'a';
+char32_t char32_t_char = U'b';
 %}
 
 /* Raw string literals */

Examples/test-suite/cpp17_u8_char_literals.i

@@ -0,0 +1,26 @@
+%module cpp17_u8_char_literals
+
+// Tests are designed so that code compiles with C++98 compilers
+
+%{
+#if __cplusplus >= 201703L
+#define CPP17 1
+#endif
+%}
+
+// UTF-8 character literals will (apparently) have type char8_t in C++20.
+char a = u8'a';
+char u = u8'u';
+char u8 = u8'8';
+
+%{
+#if defined(CPP17)
+char a = u8'a';
+char u = u8'u';
+char u8 = u8'8';
+#else
+char a = 'a';
+char u = 'u';
+char u8 = '8';
+#endif
+%}

Examples/test-suite/python/cpp17_u8_char_literals_runme.py

@@ -0,0 +1,10 @@
+from cpp17_u8_char_literals import *
+
+if cvar.a != 'a':
+    raise RuntimeError
+
+if cvar.u != 'u':
+    raise RuntimeError
+
+if cvar.u8 != '8':
+    raise RuntimeError

Source/Swig/scanner.c

@@ -938,10 +938,14 @@ static int look(Scanner *s) {
 	retract(s, 1);
 	state = 1000;
       }
+      else if (c == '\'') { /* Definitely u, U or L char */
+	retract(s, 1);
+	state = 77;
+      }
       else if (c == 'R') { /* Possibly CUSTOM DELIMITER u, U, L string */
 	state = 73;
       }
-      else if (c == '8') { /* Possibly u8 string */
+      else if (c == '8') { /* Possibly u8 string/char */
 	state = 71;
       }
       else {
@@ -961,7 +965,7 @@ static int look(Scanner *s) {
       }
       break;
     
-    case 71:			/* Possibly u8 string */
+    case 71:			/* Possibly u8 string/char */
       if ((c = nextchar(s)) == 0) {
 	state = 76;
       }
@@ -969,6 +973,10 @@ static int look(Scanner *s) {
 	retract(s, 1); /* Definitely u8 string */
 	state = 1000;
       }
+      else if (c=='\'') {
+	retract(s, 1); /* Definitely u8 char */
+	state = 77;
+      }
       else if (c=='R') {
 	state = 74; /* Possibly CUSTOM DELIMITER u8 string */
       }