/* dquote_static.c
*
- * This file contains static inline functions that are related to
+ * This file contains static functions that are related to
* parsing double-quotish expressions, but are used in more than
* one file.
*
/* XXX Add documentation after final interface and behavior is decided */
/* May want to show context for error, so would pass Perl_bslash_c(pTHX_ const char* current, const char* start, const bool output_warning)
U8 source = *current;
-
- May want to add eg, WARN_REGEX
*/
STATIC char
-S_grok_bslash_c(pTHX_ const char source, const bool output_warning)
+S_grok_bslash_c(pTHX_ const char source, const bool utf8, const bool output_warning)
{
U8 result;
- if (! isASCII(source)) {
- Perl_croak(aTHX_ "Character following \"\\c\" must be ASCII");
+ 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");
+ }
}
result = toCTRL(source);
- if (! isCNTRL(result)) {
+ 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_croak(aTHX_ "It is proposed that \"\\c{\" no longer be valid. It has historically evaluated to\n \";\". If you disagree with this proposal, send email to perl5-porters@perl.org\nOtherwise, or in the meantime, you can work around this failure by changing\n\"\\c{\" to \";\"");
+ Perl_ck_warner_d(aTHX_ packWARN2(WARN_DEPRECATED, WARN_SYNTAX),
+ "\"\\c{\" is deprecated and is more clearly written as \";\"");
}
- else if (output_warning) {
+ else {
U8 clearer[3];
U8 i = 0;
if (! isALNUM(result)) {
clearer[i++] = result;
clearer[i++] = '\0';
- Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED),
- "\"\\c%c\" more clearly written simply as \"%s\"",
+ Perl_ck_warner(aTHX_ packWARN(WARN_SYNTAX),
+ "\"\\c%c\" is more clearly written simply as \"%s\"",
source,
clearer);
}
}
/* Return past the '}' no matter what is inside the braces */
- *len = e - s + 2; /* 2 = 1 for the o + 1 for the '}' */
+ *len = e - s + 2; /* 2 = 1 for the 'o' + 1 for the '}' */
s++; /* Point to first digit */
return FALSE;
}
- *uv = NATIVE_TO_UNI(grok_oct(s, &numbers_len, &flags, NULL));
+ *uv = grok_oct(s, &numbers_len, &flags, NULL);
/* Note that if has non-octal, will ignore everything starting with that up
* to the '}' */
return TRUE;
}
+PERL_STATIC_INLINE bool
+S_grok_bslash_x(pTHX_ const char *s,
+ UV *uv,
+ STRLEN *len,
+ const char** error_msg,
+ const bool output_warning)
+{
+
+/* 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
+ * On input:
+ * s points to a string that begins with 'x', and the previous character
+ * was a backslash.
+ * uv points to a UV that will hold the output value, valid only if the
+ * return from the function is TRUE
+ * len on success will point to the next character in the string past the
+ * end of this construct.
+ * on failure, it will point to the failure
+ * error_msg is a pointer that will be set to an internal buffer giving an
+ * error message upon failure (the return is FALSE). Untouched if
+ * function succeeds
+ * output_warning says whether to output any warning messages, or suppress
+ * them
+ */
+ const char* e;
+ STRLEN numbers_len;
+ I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
+ | PERL_SCAN_DISALLOW_PREFIX;
+
+ PERL_ARGS_ASSERT_GROK_BSLASH_X;
+
+ PERL_UNUSED_ARG(output_warning);
+
+ assert(*s == 'x');
+ s++;
+
+ if (*s != '{') {
+ I32 flags = PERL_SCAN_DISALLOW_PREFIX;
+ *len = 2;
+ *uv = grok_hex(s, len, &flags, NULL);
+ (*len)++;
+ return TRUE;
+ }
+
+ e = strchr(s, '}');
+ if (!e) {
+ *len = 2; /* Move past the 'x{' */
+ /* XXX The corresponding message above for \o is just '\\o{'; other
+ * messages for other constructs include the '}', so are inconsistent.
+ */
+ *error_msg = "Missing right brace on \\x{}";
+ return FALSE;
+ }
+
+ /* Return past the '}' no matter what is inside the braces */
+ *len = e - s + 2; /* 2 = 1 for the 'x' + 1 for the '}' */
+
+ s++; /* Point to first digit */
+
+ numbers_len = e - s;
+ *uv = grok_hex(s, &numbers_len, &flags, NULL);
+ /* Note that if has non-hex, will ignore everything starting with that up
+ * to the '}' */
+
+ return TRUE;
+}
+
/*
* Local variables:
* c-indentation-style: bsd
* c-basic-offset: 4
- * indent-tabs-mode: t
+ * indent-tabs-mode: nil
* End:
*
- * ex: set ts=8 sts=4 sw=4 noet:
+ * ex: set ts=8 sts=4 sw=4 et:
*/