UTF8_ALLOW_ANYUV should not allow overlong sequences [PATCH]

[perl5.git] / utf8.h

diff --git a/utf8.h b/utf8.h
index 3787832..376280d 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    utf8.h
  *
- *    Copyright (c) 1998-2002, Larry Wall
+ *    Copyright (C) 2000, 2001, 2002, by Larry Wall and others
  *
  *    You may distribute under the terms of either the GNU General Public
  *    License or the Artistic License, as specified in the README file.
@@ -8,7 +8,7 @@
  */
 
 /* Use UTF-8 as the default script encoding?
- * Turning this on will break scripts having non-UTF8 binary
+ * Turning this on will break scripts having non-UTF-8 binary
  * data (such as Latin-1) in string literals. */
 #ifdef USE_UTF8_SCRIPTS
 #    define USE_UTF8_IN_NAMES (!IN_BYTES)
@@ -80,6 +80,10 @@ END_EXTERN_C
 
 Note the A0..BF in U+0800..U+0FFF, the 80..9F in U+D000...U+D7FF,
 the 90..BF in U+10000..U+3FFFF, and the 80...8F in U+100000..U+10FFFF.
+The "gaps" are caused by legal UTF-8 avoiding non-shortest encodings:
+it is technically possible to UTF-8-encode a single code point in different
+ways, but that is explicitly forbidden, and the shortest possible encoding
+should always be used (and that is what Perl does).
 
  */
 
@@ -158,7 +162,7 @@ encoded character.
 #define isIDFIRST_lazy(p)      isIDFIRST_lazy_if(p,1)
 #define isALNUM_lazy(p)                isALNUM_lazy_if(p,1)
 
-/* how wide can a single UTF8 encoded character become */
+/* how wide can a single UTF-8 encoded character become */
 #define UTF8_MAXLEN 13
 /* how wide a character can become when upper/lowercased */
 #define UTF8_MAXLEN_UCLC_MULT 3
@@ -176,20 +180,18 @@ encoded character.
 #define UTF8_ALLOW_FE_FF               0x0008
 #define UTF8_ALLOW_SHORT               0x0010
 #define UTF8_ALLOW_SURROGATE           0x0020
-#define UTF8_ALLOW_BOM                 0x0040
-#define UTF8_ALLOW_FFFF                        0x0080
-#define UTF8_ALLOW_LONG                        0x0100
+#define UTF8_ALLOW_FFFF                        0x0040 /* Allows also FFFE. */
+#define UTF8_ALLOW_LONG                        0x0080
 #define UTF8_ALLOW_ANYUV               (UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
-                                        UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\
-                                        UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG)
-#define UTF8_ALLOW_ANY                 0x00ff
+                                        UTF8_ALLOW_SURROGATE|UTF8_ALLOW_FFFF)
+#define UTF8_ALLOW_ANY                 0x00FF
 #define UTF8_CHECK_ONLY                        0x0200
 
-#define UNICODE_SURROGATE_FIRST                0xd800
-#define UNICODE_SURROGATE_LAST         0xdfff
-#define UNICODE_REPLACEMENT            0xfffd
-#define UNICODE_BYTE_ORDER_MARK                0xfeff
-#define UNICODE_ILLEGAL                        0xffff
+#define UNICODE_SURROGATE_FIRST                0xD800
+#define UNICODE_SURROGATE_LAST         0xDFFF
+#define UNICODE_REPLACEMENT            0xFFFD
+#define UNICODE_BYTE_ORDER_MARK                0xFEFF
+#define UNICODE_ILLEGAL                        0xFFFF
 
 /* Though our UTF-8 encoding can go beyond this,
  * let's be conservative and do as Unicode 3.2 says. */
@@ -197,10 +199,9 @@ encoded character.
 
 #define UNICODE_ALLOW_SURROGATE 0x0001 /* Allow UTF-16 surrogates (EVIL) */
 #define UNICODE_ALLOW_FDD0     0x0002  /* Allow the U+FDD0...U+FDEF */
-#define UNICODE_ALLOW_BOM      0x0004  /* Allow 0xFEFF */
-#define UNICODE_ALLOW_FFFF     0x0008  /* Allow 0xFFFF, 0x1FFFF, ... */
-#define UNICODE_ALLOW_SUPER    0x0010  /* Allow past 10xFFFF */
-#define UNICODE_ALLOW_ANY      0xFFFF
+#define UNICODE_ALLOW_FFFF     0x0004  /* Allow 0xFFF[EF], 0x1FFF[EF], ... */
+#define UNICODE_ALLOW_SUPER    0x0008  /* Allow past 10xFFFF */
+#define UNICODE_ALLOW_ANY      0x000F
 
 #define UNICODE_IS_SURROGATE(c)                ((c) >= UNICODE_SURROGATE_FIRST && \
                                         (c) <= UNICODE_SURROGATE_LAST)