*/
#define PERL_IN_DQUOTE_STATIC_C
-#include "proto.h"
#include "embed.h"
/*
Pulled from regcomp.c.
*/
PERL_STATIC_INLINE I32
-S_regcurly(pTHX_ register const char *s)
+S_regcurly(pTHX_ const char *s,
+ const bool rbrace_must_be_escaped /* Should the terminating '} be
+ preceded by a backslash? This
+ is an abnormal case */
+ )
{
PERL_ARGS_ASSERT_REGCURLY;
while (isDIGIT(*s))
s++;
}
- if (*s != '}')
- return FALSE;
- return TRUE;
+
+ return (rbrace_must_be_escaped)
+ ? *s == '\\' && *(s+1) == '}'
+ : *s == '}';
}
/* XXX Add documentation after final interface and behavior is decided */
else {
U8 clearer[3];
U8 i = 0;
- if (! isALNUM(result)) {
+ if (! isWORDCHAR(result)) {
clearer[i++] = '\\';
}
clearer[i++] = result;
}
STATIC bool
-S_grok_bslash_o(pTHX_ const char *s,
- UV *uv,
- STRLEN *len,
- const char** error_msg,
- const bool output_warning)
+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)
{
/* 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 'o', and the previous character
- * was a backslash.
+ * s is the address of a pointer to a NULL terminated string that begins
+ * with 'o', and the previous character was a backslash. At exit, *s
+ * will be advanced to the byte just after those absorbed by this
+ * function. Hence the caller can continue parsing from there. In
+ * the case of an error, this routine has generally positioned *s to
+ * point just to the right of the first bad spot, so that a message
+ * that has a "<--" to mark the spot will be correctly positioned.
* 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
+ * 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.
*/
- const char* e;
+ char* e;
STRLEN numbers_len;
I32 flags = PERL_SCAN_ALLOW_UNDERSCORES
| PERL_SCAN_DISALLOW_PREFIX
PERL_ARGS_ASSERT_GROK_BSLASH_O;
- assert(*s == 'o');
- s++;
+ assert(**s == 'o');
+ (*s)++;
- if (*s != '{') {
- *len = 1; /* Move past the o */
+ if (**s != '{') {
*error_msg = "Missing braces on \\o{}";
return FALSE;
}
- e = strchr(s, '}');
+ e = strchr(*s, '}');
if (!e) {
- *len = 2; /* Move past the o{ */
- *error_msg = "Missing right brace on \\o{";
+ (*s)++; /* Move past the '{' */
+ while (isOCTAL(**s)) { /* Position beyond the legal digits */
+ (*s)++;
+ }
+ *error_msg = "Missing right brace on \\o{";
return FALSE;
}
- /* Return past the '}' no matter what is inside the braces */
- *len = e - s + 2; /* 2 = 1 for the o + 1 for the '}' */
-
- s++; /* Point to first digit */
-
- numbers_len = e - s;
+ (*s)++; /* Point to expected first digit (could be first byte of utf8
+ sequence if not a digit) */
+ numbers_len = e - *s;
if (numbers_len == 0) {
+ (*s)++; /* Move past the } */
*error_msg = "Number with no digits";
return FALSE;
}
- *uv = NATIVE_TO_UNI(grok_oct(s, &numbers_len, &flags, NULL));
+ 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 '}' */
- if (output_warning && numbers_len != (STRLEN) (e - 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);
+ if (numbers_len != (STRLEN) (e - *s)) {
+ if (strict) {
+ *s += numbers_len;
+ *s += (UTF) ? UTF8SKIP(*s) : (STRLEN) 1;
+ *error_msg = "Non-octal character";
+ 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);
+ }
}
+ /* Return past the '}' */
+ *s = e + 1;
+
return TRUE;
}
+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
+ * 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
+ * will be advanced to the byte just after those absorbed by this
+ * function. Hence the caller can continue parsing from there. In
+ * the case of an error, this routine has generally positioned *s to
+ * point just to the right of the first bad spot, so that a message
+ * that has a "<--" to mark the spot will be correctly positioned.
+ * uv points to a UV that will hold the output value, valid only if the
+ * return from the function is TRUE
+ * 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
+ * strict is true if anything out of the ordinary should cause this to
+ * 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 = PERL_SCAN_DISALLOW_PREFIX;
+
+ PERL_ARGS_ASSERT_GROK_BSLASH_X;
+
+ PERL_UNUSED_ARG(output_warning);
+
+ assert(**s == 'x');
+ (*s)++;
+
+ if (strict) {
+ flags |= PERL_SCAN_SILENT_ILLDIGIT;
+ }
+
+ if (**s != '{') {
+ STRLEN len = (strict) ? 3 : 2;
+
+ *uv = grok_hex(*s, &len, &flags, NULL);
+ *s += len;
+ if (strict && len != 2) {
+ if (len < 2) {
+ *s += (UTF) ? UTF8SKIP(*s) : 1;
+ *error_msg = "Non-hex character";
+ }
+ else {
+ *error_msg = "Use \\x{...} for more than two hex characters";
+ }
+ return FALSE;
+ }
+ return TRUE;
+ }
+
+ e = strchr(*s, '}');
+ if (!e) {
+ (*s)++; /* Move past the '{' */
+ while (isXDIGIT(**s)) { /* Position beyond the legal digits */
+ (*s)++;
+ }
+ /* 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;
+ }
+
+ (*s)++; /* Point to expected first digit (could be first byte of utf8
+ sequence if not a digit) */
+ numbers_len = e - *s;
+ if (numbers_len == 0) {
+ if (strict) {
+ (*s)++; /* Move past the } */
+ *error_msg = "Number with no digits";
+ return FALSE;
+ }
+ return TRUE;
+ }
+
+ 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
+ * to the '}' */
+
+ if (strict && numbers_len != (STRLEN) (e - *s)) {
+ *s += numbers_len;
+ *s += (UTF) ? UTF8SKIP(*s) : 1;
+ *error_msg = "Non-hex character";
+ return FALSE;
+ }
+
+ /* Return past the '}' */
+ *s = e + 1;
+
+ 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