Pulled from regcomp.c.
*/
PERL_STATIC_INLINE I32
-S_regcurly(pTHX_ const char *s)
+S_regcurly(const char *s)
{
PERL_ARGS_ASSERT_REGCURLY;
while (isDIGIT(*s))
s++;
}
- if (*s != '}')
- return FALSE;
- return TRUE;
+
+ return *s == '}';
}
/* XXX Add documentation after final interface and behavior is decided */
*/
STATIC char
-S_grok_bslash_c(pTHX_ const char source, const bool utf8, const bool output_warning)
+S_grok_bslash_c(pTHX_ const char source, const bool output_warning)
{
U8 result;
- if (utf8) {
- /* Trying to deprecate non-ASCII usages. This construct has never
- * worked for a utf8 variant. So, even though are accepting non-ASCII
- * Latin1 in 5.14, no need to make them work under utf8 */
- if (! isASCII(source)) {
- Perl_croak(aTHX_ "Character following \"\\c\" must be ASCII");
- }
+ if (! isPRINT_A(source)) {
+ Perl_croak(aTHX_ "%s",
+ "Character following \"\\c\" must be printable ASCII");
+ }
+ else if (source == '{') {
+ const char control = toCTRL('{');
+ if (isPRINT_A(control)) {
+ /* diag_listed_as: Use "%s" instead of "%s" */
+ Perl_croak(aTHX_ "Use \"%c\" instead of \"\\c{\"", control);
+ }
+ else {
+ Perl_croak(aTHX_ "Sequence \"\\c{\" invalid");
+ }
}
result = toCTRL(source);
- if (! isASCII(source)) {
- Perl_ck_warner_d(aTHX_ packWARN2(WARN_DEPRECATED, WARN_SYNTAX),
- "Character following \"\\c\" must be ASCII");
- }
- else if (! isCNTRL(result) && output_warning) {
- if (source == '{') {
- Perl_ck_warner_d(aTHX_ packWARN2(WARN_DEPRECATED, WARN_SYNTAX),
- "\"\\c{\" is deprecated and is more clearly written as \";\"");
- }
- else {
- U8 clearer[3];
- U8 i = 0;
- if (! isWORDCHAR(result)) {
- clearer[i++] = '\\';
- }
- clearer[i++] = result;
- clearer[i++] = '\0';
-
- Perl_ck_warner(aTHX_ packWARN(WARN_SYNTAX),
- "\"\\c%c\" is more clearly written simply as \"%s\"",
- source,
- clearer);
- }
+ if (output_warning && isPRINT_A(result)) {
+ U8 clearer[3];
+ U8 i = 0;
+ if (! isWORDCHAR(result)) {
+ clearer[i++] = '\\';
+ }
+ clearer[i++] = result;
+ clearer[i++] = '\0';
+
+ Perl_ck_warner(aTHX_ packWARN(WARN_SYNTAX),
+ "\"\\c%c\" is more clearly written simply as \"%s\"",
+ source,
+ clearer);
}
return result;
STATIC bool
S_grok_bslash_o(pTHX_ char **s, UV *uv, const char** error_msg,
const bool output_warning, const bool strict,
+ const bool silence_non_portable,
const bool UTF)
{
* them
* strict is true if this should fail instead of warn if there are
* non-octal digits within the braces
+ * silence_non_portable is true if to suppress warnings about the code
+ * point returned being too large to fit on all platforms.
* UTF is true iff the string *s is encoded in UTF-8.
*/
char* e;
return FALSE;
}
+ if (silence_non_portable) {
+ flags |= PERL_SCAN_SILENT_NON_PORTABLE;
+ }
+
*uv = grok_oct(*s, &numbers_len, &flags, NULL);
/* Note that if has non-octal, will ignore everything starting with that up
* to the '}' */
return FALSE;
}
else if (output_warning) {
- Perl_ck_warner(aTHX_ packWARN(WARN_DIGIT),
- /* diag_listed_as: Non-octal character '%c'. Resolved as "%s" */
- "Non-octal character '%c'. Resolved as \"\\o{%.*s}\"",
- *(*s + numbers_len),
- (int) numbers_len,
- *s);
+ Perl_ck_warner(aTHX_ packWARN(WARN_DIGIT),
+ /* diag_listed_as: Non-octal character '%c'. Resolved as "%s" */
+ "Non-octal character '%c'. Resolved as \"\\o{%.*s}\"",
+ *(*s + numbers_len),
+ (int) numbers_len,
+ *s);
}
}
PERL_STATIC_INLINE bool
S_grok_bslash_x(pTHX_ char **s, UV *uv, const char** error_msg,
const bool output_warning, const bool strict,
+ const bool silence_non_portable,
const bool UTF)
{
/* Documentation to be supplied when interface nailed down finally
* This returns FALSE if there is an error which the caller need not recover
- * from; , otherwise TRUE. In either case the caller should look at *len
+ * from; , otherwise TRUE.
* On input:
* s is the address of a pointer to a NULL terminated string that begins
* with 'x', and the previous character was a backslash. At exit, *s
* fail instead of warn or be silent. For example, it requires
* exactly 2 digits following the \x (when there are no braces).
* 3 digits could be a mistake, so is forbidden in this mode.
+ * silence_non_portable is true if to suppress warnings about the code
+ * point returned being too large to fit on all platforms.
* UTF is true iff the string *s is encoded in UTF-8.
*/
char* e;
STRLEN numbers_len;
- I32 flags = 0;
+ I32 flags = PERL_SCAN_DISALLOW_PREFIX;
PERL_ARGS_ASSERT_GROK_BSLASH_X;
- PERL_UNUSED_ARG(output_warning);
-
assert(**s == 'x');
(*s)++;
- if (strict) {
+ if (strict || ! output_warning) {
flags |= PERL_SCAN_SILENT_ILLDIGIT;
}
if (**s != '{') {
STRLEN len = (strict) ? 3 : 2;
- flags |= PERL_SCAN_DISALLOW_PREFIX;
*uv = grok_hex(*s, &len, &flags, NULL);
*s += len;
if (strict && len != 2) {
*error_msg = "Number with no digits";
return FALSE;
}
+ *s = e + 1;
+ *uv = 0;
return TRUE;
}
- flags |= PERL_SCAN_ALLOW_UNDERSCORES|PERL_SCAN_DISALLOW_PREFIX;
+ flags |= PERL_SCAN_ALLOW_UNDERSCORES;
+ if (silence_non_portable) {
+ flags |= PERL_SCAN_SILENT_NON_PORTABLE;
+ }
*uv = grok_hex(*s, &numbers_len, &flags, NULL);
/* Note that if has non-hex, will ignore everything starting with that up
return TRUE;
}
+STATIC char*
+S_form_short_octal_warning(pTHX_
+ const char * const s, /* Points to first non-octal */
+ const STRLEN len /* Length of octals string, so
+ (s-len) points to first
+ octal */
+) {
+ /* Return a character string consisting of a warning message for when a
+ * string constant in octal is weird, like "\078". */
+
+ const char * sans_leading_zeros = s - len;
+
+ PERL_ARGS_ASSERT_FORM_SHORT_OCTAL_WARNING;
+
+ assert(*s == '8' || *s == '9');
+
+ /* Remove the leading zeros, retaining one zero so won't be zero length */
+ while (*sans_leading_zeros == '0') sans_leading_zeros++;
+ if (sans_leading_zeros == s) {
+ sans_leading_zeros--;
+ }
+
+ return Perl_form(aTHX_
+ "'%.*s' resolved to '\\o{%.*s}%c'",
+ (int) (len + 2), s - len - 1,
+ (int) (s - sans_leading_zeros), sans_leading_zeros,
+ *s);
+}
+
/*
* Local variables:
* c-indentation-style: bsd
https://perl5.git.perl.org / perl5.git / blobdiff