Use the UTF8 macros a bit. They can't be used with abandon

everywhere because we do generate illegal UTF-8 in some situations.
This is of course naughty.

p4raw-id: //depot/perl@8033

diff --git a/pod/perlapi.pod b/pod/perlapi.pod
index 50ac40c..7fdc55e 100644 (file)
--- a/pod/perlapi.pod
+++ b/pod/perlapi.pod
@@ -3234,11 +3234,12 @@ Found in file utf8.c
 
 =item utf8_hop
 
-Move the C<s> pointing to UTF-8 data by C<off> characters, either forward
-or backward.
+Return the UTF-8 pointer C<s> displaced by C<off> characters, either
+forward or backward.
 
 WARNING: do not use the following unless you *know* C<off> is within
-the UTF-8 buffer pointed to by C<s>.
+the UTF-8 data pointed to by C<s> *and* that on entry C<s> is aligned
+on the first byte of character or just after the last byte of a character.
 
        U8*     utf8_hop(U8 *s, I32 off)
 
@@ -3279,10 +3280,10 @@ If C<s> does not point to a well-formed UTF8 character, the behaviour
 is dependent on the value of C<flags>: if it contains UTF8_CHECK_ONLY,
 it is assumed that the caller will raise a warning, and this function
 will set C<retlen> to C<-1> and return zero.  If the C<flags> does not
-contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT_CHARACTER (0xFFFD)
-will be returned, and C<retlen> will be set to the expected length of
-the UTF-8 character in bytes.  The C<flags> can also contain various
-flags to allow deviations from the strict UTF-8 encoding (see F<utf8.h>).
+contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT (0xFFFD) will be
+returned, and C<retlen> will be set to the expected length of the
+UTF-8 character in bytes.  The C<flags> can also contain various flags
+to allow deviations from the strict UTF-8 encoding (see F<utf8.h>).
 
        U8* s   utf8_to_uv(STRLEN curlen, STRLEN *retlen, U32 flags)
 

diff --git a/utf8.c b/utf8.c
index 98e13e8..7a652b4 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -137,7 +137,7 @@ Perl_is_utf8_char(pTHX_ U8 *s)
     while (slen--) {
        if ((*s & 0xc0) != 0x80)
            return 0;
-       uv = (uv << 6) | (*s & 0x3f);
+       uv = UTF8_ACCUMULATE(uv, *s);
        if (uv < ouv)
            return 0;
        ouv = uv;
@@ -285,7 +285,7 @@ Perl_utf8_to_uv(pTHX_ U8* s, STRLEN curlen, STRLEN* retlen, U32 flags)
            goto malformed;
        }
        else
-           uv = (uv << 6) | (*s & 0x3f);
+           uv = UTF8_ACCUMULATE(uv, *s);
        if (uv < ouv) {
            /* This cannot be allowed. */
            if (dowarn)
@@ -379,6 +379,10 @@ Perl_utf8_length(pTHX_ U8* s, U8* e)
 {
     STRLEN len = 0;
 
+    /* Note: cannot use UTF8_IS_...() too eagerly here since e.g.
+     * the bitops (especially ~) can create illegal UTF-8.
+     * In other words: in Perl UTF-8 is not just for Unicode. */
+
     if (e < s)
        Perl_croak(aTHX_ "panic: utf8_length: unexpected end");
     while (s < e) {
@@ -409,6 +413,10 @@ Perl_utf8_distance(pTHX_ U8 *a, U8 *b)
 {
     IV off = 0;
 
+    /* Note: cannot use UTF8_IS_...() too eagerly here since  e.g.
+     * the bitops (especially ~) can create illegal UTF-8.
+     * In other words: in Perl UTF-8 is not just for Unicode. */
+
     if (a < b) {
        while (a < b) {
            U8 c = UTF8SKIP(a);
@@ -436,17 +444,22 @@ Perl_utf8_distance(pTHX_ U8 *a, U8 *b)
 /*
 =for apidoc Am|U8*|utf8_hop|U8 *s|I32 off
 
-Move the C<s> pointing to UTF-8 data by C<off> characters, either forward
-or backward.
+Return the UTF-8 pointer C<s> displaced by C<off> characters, either
+forward or backward.
 
 WARNING: do not use the following unless you *know* C<off> is within
-the UTF-8 buffer pointed to by C<s>.
+the UTF-8 data pointed to by C<s> *and* that on entry C<s> is aligned
+on the first byte of character or just after the last byte of a character.
 
 =cut */
 
 U8 *
 Perl_utf8_hop(pTHX_ U8 *s, I32 off)
 {
+    /* Note: cannot use UTF8_IS_...() too eagerly here since e.g
+     * the bitops (especially ~) can create illegal UTF-8.
+     * In other words: in Perl UTF-8 is not just for Unicode. */
+
     if (off >= 0) {
        while (off--)
            s += UTF8SKIP(s);
@@ -454,10 +467,8 @@ Perl_utf8_hop(pTHX_ U8 *s, I32 off)
     else {
        while (off++) {
            s--;
-           if (*s & 0x80) {
-               while ((*s & 0xc0) == 0x80)
-                   s--;
-           }
+           while (UTF8_IS_CONTINUATION(*s))
+               s--;
        }
     }
     return s;

diff --git a/utf8.h b/utf8.h
index bafdc57..26ef723 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -65,6 +65,11 @@ END_EXTERN_C
 #define UTF8_IS_ASCII(c)               ((c) <  0x80)
 #define UTF8_IS_START(c)               ((c) >= 0xc0 && ((c) <= 0xfd))
 #define UTF8_IS_CONTINUATION(c)                ((c) >= 0x80 && ((c) <= 0xbf))
+#define UTF8_IS_CONTINUED(c)           ((c) &  0x80)
+
+#define UTF8_CONTINUATION_MASK         0x3f
+#define UTF8_ACCUMULATION_SHIFT                6
+#define UTF8_ACCUMULATE(old, new)      ((old) << UTF8_ACCUMULATION_SHIFT | ((new) & UTF8_CONTINUATION_MASK))
 
 #ifdef HAS_QUAD
 #define UNISKIP(uv) ( (uv) < 0x80           ? 1 : \