ICU-59117.0.1.tar.gz

[apple/icu.git] / icuSources / common / unicode / umachine.h

diff --git a/icuSources/common/unicode/umachine.h b/icuSources/common/unicode/umachine.h
index 939a11706ad2dfa7ff789ba011b3e1a9a4eea37e..b03809e1e87bcddd45956feb5695aa2441431b3b 100644 (file)
--- a/icuSources/common/unicode/umachine.h
+++ b/icuSources/common/unicode/umachine.h
@@ -1,3 +1,5 @@
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
 /*
 ******************************************************************************
 *
@@ -6,7 +8,7 @@
 *
 ******************************************************************************
 *   file name:  umachine.h
-*   encoding:   US-ASCII
+*   encoding:   UTF-8
 *   tab size:   8 (not used)
 *   indentation:4
 *
@@ -288,30 +290,92 @@ typedef int8_t UBool;
 /** Number of bytes in a UChar. @stable ICU 2.0 */
 #define U_SIZEOF_UCHAR 2
 
+/**
+ * \def U_CHAR16_IS_TYPEDEF
+ * If 1, then char16_t is a typedef and not a real type (yet)
+ * @internal
+ */
+#if (U_PLATFORM == U_PF_AIX) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11)
+// for AIX, uchar.h needs to be included
+# include <uchar.h>
+# define U_CHAR16_IS_TYPEDEF 1
+#else
+# define U_CHAR16_IS_TYPEDEF 0
+#endif
+
+
 /**
  * \var UChar
- * Define UChar to be UCHAR_TYPE, if that is #defined (for example, to char16_t),
- * or wchar_t if that is 16 bits wide; always assumed to be unsigned.
- * If neither is available, then define UChar to be uint16_t.
  *
- * This makes the definition of UChar platform-dependent
- * but allows direct string type compatibility with platforms with
- * 16-bit wchar_t types.
+ * The base type for UTF-16 code units and pointers.
+ * Unsigned 16-bit integer.
+ * Starting with ICU 59, C++ API uses char16_t directly, while C API continues to use UChar.
+ *
+ * UChar is configurable by defining the macro UCHAR_TYPE
+ * on the preprocessor or compiler command line:
+ * -DUCHAR_TYPE=uint16_t or -DUCHAR_TYPE=wchar_t (if U_SIZEOF_WCHAR_T==2) etc.
+ * (The UCHAR_TYPE can also be #defined earlier in this file, for outside the ICU library code.)
+ * This is for transitional use from application code that uses uint16_t or wchar_t for UTF-16.
+ *
+ * The default is UChar=char16_t.
+ *
+ * C++11 defines char16_t as bit-compatible with uint16_t, but as a distinct type.
+ *
+ * In C, char16_t is a simple typedef of uint_least16_t.
+ * ICU requires uint_least16_t=uint16_t for data memory mapping.
+ * On macOS, char16_t is not available because the uchar.h standard header is missing.
  *
  * @stable ICU 4.4
  */
-#if defined(UCHAR_TYPE)
+
+#if 0
+    // #if 1 is normal. UChar defaults to char16_t in C++.
+    // For configuration testing of UChar=uint16_t temporarily change this to #if 0.
+    // The intltest Makefile #defines UCHAR_TYPE=char16_t,
+    // so we only #define it to uint16_t if it is undefined so far.
+#elif !defined(UCHAR_TYPE)
+#   define UCHAR_TYPE uint16_t
+#endif
+
+#if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \
+        defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION)
+    // Inside the ICU library code, never configurable.
+    typedef char16_t UChar;
+#elif defined(UCHAR_TYPE)
     typedef UCHAR_TYPE UChar;
-/* Not #elif U_HAVE_CHAR16_T -- because that is type-incompatible with pre-C++11 callers
-    typedef char16_t UChar;  */
-#elif U_SIZEOF_WCHAR_T==2
-    typedef wchar_t UChar;
-#elif defined(__CHAR16_TYPE__)
-    typedef __CHAR16_TYPE__ UChar;
+#elif defined(__cplusplus)
+    typedef char16_t UChar;
 #else
     typedef uint16_t UChar;
 #endif
 
+/**
+ * \var OldUChar
+ * Default ICU 58 definition of UChar.
+ * A base type for UTF-16 code units and pointers.
+ * Unsigned 16-bit integer.
+ *
+ * Define OldUChar to be wchar_t if that is 16 bits wide.
+ * If wchar_t is not 16 bits wide, then define UChar to be uint16_t.
+ *
+ * This makes the definition of OldUChar platform-dependent
+ * but allows direct string type compatibility with platforms with
+ * 16-bit wchar_t types.
+ *
+ * This is how UChar was defined in ICU 58, for transition convenience.
+ * Exception: ICU 58 UChar was defined to UCHAR_TYPE if that macro was defined.
+ * The current UChar responds to UCHAR_TYPE but OldUChar does not.
+ *
+ * @draft ICU 59
+ */
+#if U_SIZEOF_WCHAR_T==2
+    typedef wchar_t OldUChar;
+#elif defined(__CHAR16_TYPE__)
+    typedef __CHAR16_TYPE__ OldUChar;
+#else
+    typedef uint16_t OldUChar;
+#endif
+
 /**
  * Define UChar32 as a type for single Unicode code points.
  * UChar32 is a signed 32-bit integer (same as int32_t).