diff options
author | Karl Williamson <khw@cpan.org> | 2015-08-26 15:35:05 -0600 |
---|---|---|
committer | Karl Williamson <khw@cpan.org> | 2015-09-04 10:49:22 -0600 |
commit | e9b19ab7df3480e8f710ca6faad519f6fccdb081 (patch) | |
tree | ab6c826ab4269c8fe118d11308f6af658bee1b0e | |
parent | a95ec4fb1da4ce753d2a8f3ecb2027679198a3a2 (diff) | |
download | perl-e9b19ab7df3480e8f710ca6faad519f6fccdb081.tar.gz |
utf8.h, utfebcdic.h: Add some assertions
These will detect a array bounds error that occurs on EBCDIC machines,
and by including the assert on non-EBCDIC, we verify that the code
wouldn't fail when built on EBCDIC.
-rw-r--r-- | utf8.h | 8 | ||||
-rw-r--r-- | utfebcdic.h | 10 |
2 files changed, 10 insertions, 8 deletions
@@ -127,8 +127,8 @@ END_EXTERN_C /* Native character to/from iso-8859-1. Are the identity functions on ASCII * platforms */ -#define NATIVE_TO_LATIN1(ch) (ch) -#define LATIN1_TO_NATIVE(ch) (ch) +#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) (ch)) +#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) (ch)) /* I8 is an intermediate version of UTF-8 used only in UTF-EBCDIC. We thus * consider it to be identical to UTF-8 on ASCII platforms. Strictly speaking @@ -136,8 +136,8 @@ END_EXTERN_C * because they are 8-bit encodings that serve the same purpose in Perl, and * rarely do we need to distinguish them. The term "NATIVE_UTF8" applies to * whichever one is applicable on the current platform */ -#define NATIVE_UTF8_TO_I8(ch) (ch) -#define I8_TO_NATIVE_UTF8(ch) (ch) +#define NATIVE_UTF8_TO_I8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) (ch)) +#define I8_TO_NATIVE_UTF8(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) (ch)) /* Transforms in wide UV chars */ #define UNI_TO_NATIVE(ch) (ch) diff --git a/utfebcdic.h b/utfebcdic.h index f490b586b1..51e6e77f8d 100644 --- a/utfebcdic.h +++ b/utfebcdic.h @@ -133,11 +133,13 @@ END_EXTERN_C /* EBCDIC-happy ways of converting native code to UTF-8 */ -#define NATIVE_TO_LATIN1(ch) PL_e2a[(U8)(ch)] -#define LATIN1_TO_NATIVE(ch) PL_a2e[(U8)(ch)] +/* Use these when ch is known to be < 256 */ +#define NATIVE_TO_LATIN1(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_e2a[(U8)(ch)]) +#define LATIN1_TO_NATIVE(ch) (__ASSERT_(FITS_IN_8_BITS(ch)) PL_a2e[(U8)(ch)]) -#define NATIVE_UTF8_TO_I8(ch) PL_e2utf[(U8)(ch)] -#define I8_TO_NATIVE_UTF8(ch) PL_utf2e[(U8)(ch)] +/* Use these on bytes */ +#define NATIVE_UTF8_TO_I8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_e2utf[(U8)(b)]) +#define I8_TO_NATIVE_UTF8(b) (__ASSERT_(FITS_IN_8_BITS(b)) PL_utf2e[(U8)(b)]) /* Transforms in wide UV chars */ #define NATIVE_TO_UNI(ch) (((ch) > 255) ? (ch) : NATIVE_TO_LATIN1(ch)) |