diff options
| author | Karl Williamson <khw@khw-desktop.(none)> | 2010-02-19 23:53:36 -0700 |
|---|---|---|
| committer | Steve Hay <steve.m.hay@googlemail.com> | 2010-02-20 11:03:53 +0000 |
| commit | cb233ae346c666d88ee890fc837f4cd3195c1f0b (patch) | |
| tree | 0d414ca0a66af489c1d4764b5aec0f2061aa6b72 /handy.h | |
| parent | c3c4140635dd08363a20c93a8c8b6d8e7464b891 (diff) | |
| download | perl-cb233ae346c666d88ee890fc837f4cd3195c1f0b.tar.gz | |
PATCH: deprecation warnings for unreasonable charnames
Prior to now just about anything has been legal for a character name in
\N{...}. This means that legal code was broken by having \N{3,4} for
example mean [^\n]{3,4}. Such code doesn't come from standard
charnames, but from legal custom translators.
This patch deprecates "unreasonable" names. handy.h is changed by the
addition of macros that taken together define the names we deem
reasonable, namely alpha beginning with alphanumerics and some
punctuations as continuations.
toke.c is changed to parse each name and to raise a warning if any
problematic characters are found.
Some tests and diagnostic documentation are also included.
Diffstat (limited to 'handy.h')
| -rw-r--r-- | handy.h | 12 |
1 files changed, 12 insertions, 0 deletions
@@ -462,6 +462,18 @@ US-ASCII (Basic Latin) range are viewed as not having any case. #define isALNUM(c) (isALPHA(c) || isDIGIT(c) || (c) == '_') #define isIDFIRST(c) (isALPHA(c) || (c) == '_') #define isALPHA(c) (isUPPER(c) || isLOWER(c)) +/* ALPHAU includes Unicode semantics for latin1 characters. It has an extra + * >= AA test to speed up ASCII-only tests at the expense of the others */ +#define isALPHAU(c) (isALPHA(c) || (NATIVE_TO_UNI((U8) c) >= 0xAA \ + && ((NATIVE_TO_UNI((U8) c) >= 0xC0 \ + && NATIVE_TO_UNI((U8) c) != 0xD7 && NATIVE_TO_UNI((U8) c) != 0xF7) \ + || NATIVE_TO_UNI((U8) c) == 0xAA \ + || NATIVE_TO_UNI((U8) c) == 0xB5 \ + || NATIVE_TO_UNI((U8) c) == 0xBA))) +#define isALNUMU(c) (isDIGIT(c) || isALPHAU(c) || (c) == '_') + +/* continuation character for legal NAME in \N{NAME} */ +#define isCHARNAME_CONT(c) (isALNUMU(c) || (c) == ' ' || (c) == '-' || (c) == '(' || (c) == ')' || (c) == ':' || NATIVE_TO_UNI((U8) c) == 0xA0) #define isSPACE(c) \ ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f') #define isPSXSPC(c) (isSPACE(c) || (c) == '\v') |