regcomp.sym: Add new regnode type for (?[])

This new regnode is used to handle interpolated already-compiled regex
sets inside outer regex sets.

If it isn't present, it will mean that what appears to be a nested,
interpolated set really isn't.

I created a new regnode structure to hold a pointer.  This has to be
temporary as pointers can be invalidated.  I thought of just having a
regnode without a pointer as a marker, and using a parallel array to
store the data, rather than creating a whole new regnode structure for
just pointers, but parallel data structures can get out of sync, so this
seemed best.

This commit just sets up the regnode; a future commit will actually use
it.

4 files changed, 33 insertions, 4 deletions

diff --git a/pod/perldebguts.pod b/pod/perldebguts.pod
index 5a205e0ca7..cc908393cf 100644
--- a/pod/perldebguts.pod
+++ b/pod/perldebguts.pod
@@ -858,6 +858,9 @@ will be lost.
  # mean "not seen anything to optimize yet".
  PSEUDO           off        Pseudo opcode for internal use.
 
+ REGEX_SET        depth p    Regex set, temporary node used in pre-
+                             optimization compilation
+
 =for regcomp.pl end
 
 =for unprinted-credits
diff --git a/regcomp.h b/regcomp.h
index 0104482d4b..67a4323ca5 100644
--- a/regcomp.h
+++ b/regcomp.h
@@ -181,6 +181,16 @@ struct regnode_1 {
     U32 arg1;
 };
 
+/* Node whose argument is 'void *', a pointer to void.  This needs to be used
+ * very carefully in situations where pointers won't become invalid because of,
+ * say re-mallocs */
+struct regnode_p {
+    U8	flags;
+    U8  type;
+    U16 next_off;
+    void * arg1;
+};
+
 /* Similar to a regnode_1 but with an extra signed argument */
 struct regnode_2L {
     U8	flags;
@@ -296,11 +306,13 @@ struct regnode_ssc {
 #undef ARG2
 
 #define ARG(p) ARG_VALUE(ARG_LOC(p))
+#define ARGp(p) ARG_VALUE(ARGp_LOC(p))
 #define ARG1(p) ARG_VALUE(ARG1_LOC(p))
 #define ARG2(p) ARG_VALUE(ARG2_LOC(p))
 #define ARG2L(p) ARG_VALUE(ARG2L_LOC(p))
 
 #define ARG_SET(p, val) ARG__SET(ARG_LOC(p), (val))
+#define ARGp_SET(p, val) ARG__SET(ARGp_LOC(p), (val))
 #define ARG1_SET(p, val) ARG__SET(ARG1_LOC(p), (val))
 #define ARG2_SET(p, val) ARG__SET(ARG2_LOC(p), (val))
 #define ARG2L_SET(p, val) ARG__SET(ARG2L_LOC(p), (val))
@@ -388,6 +400,7 @@ struct regnode_ssc {
 
 #define	NODE_ALIGN(node)
 #define	ARG_LOC(p)	(((struct regnode_1 *)p)->arg1)
+#define ARGp_LOC(p)	(((struct regnode_p *)p)->arg1)
 #define	ARG1_LOC(p)	(((struct regnode_2 *)p)->arg1)
 #define	ARG2_LOC(p)	(((struct regnode_2 *)p)->arg2)
 #define ARG2L_LOC(p)	(((struct regnode_2L *)p)->arg2)
@@ -416,6 +429,12 @@ struct regnode_ssc {
                      * that have a longer argument */                   \
                     (offset) += regarglen[op];                          \
     } STMT_END
+#define FILL_ADVANCE_NODE_ARGp(offset, op, arg)                          \
+    STMT_START {                                                        \
+                    ARGp_SET(REGNODE_p(offset), arg);                    \
+                    FILL_ADVANCE_NODE(offset, op);                      \
+                    (offset) += regarglen[op];                          \
+    } STMT_END
 #define FILL_ADVANCE_NODE_2L_ARG(offset, op, arg1, arg2)                \
     STMT_START {                                                        \
                     ARG_SET(REGNODE_p(offset), arg1);                   \
diff --git a/regcomp.sym b/regcomp.sym
index 4b8670fa2c..7c0bf7a484 100644
--- a/regcomp.sym
+++ b/regcomp.sym
@@ -297,6 +297,8 @@ OPTIMIZED   NOTHING,    off       ; Placeholder for dump.
 #* mean "not seen anything to optimize yet".
 PSEUDO      PSEUDO,     off       ; Pseudo opcode for internal use.
 
+REGEX_SET   REGEX_SET,  depth p S ; Regex set, temporary node used in pre-optimization compilation
+
 -------------------------------------------------------------------------------
 # Format for second section:
 # REGOP \t typelist [ \t typelist]
diff --git a/regnodes.h b/regnodes.h
index cce9d7f1fc..46e090f39c 100644
--- a/regnodes.h
+++ b/regnodes.h
@@ -6,8 +6,8 @@
 
 /* Regops and State definitions */
 
-#define REGNODE_MAX           	108
-#define REGMATCH_STATE_MAX    	148
+#define REGNODE_MAX           	109
+#define REGMATCH_STATE_MAX    	149
 
 #define	END                   	0	/* 0000 End of program. */
 #define	SUCCEED               	1	/* 0x01 Return from a subroutine, basically. */
@@ -120,6 +120,7 @@
 #define	LNBREAK               	106	/* 0x6a generic newline pattern */
 #define	OPTIMIZED             	107	/* 0x6b Placeholder for dump. */
 #define	PSEUDO                	108	/* 0x6c Pseudo opcode for internal use. */
+#define	REGEX_SET             	109	/* 0x6d Regex set, temporary node used in pre-optimization compilation */
 	/* ------------ States ------------- */
 #define	TRIE_next             	(REGNODE_MAX + 1)	/* state for TRIE */
 #define	TRIE_next_fail        	(REGNODE_MAX + 2)	/* state for TRIE */
@@ -277,6 +278,7 @@ EXTCONST U8 PL_regkind[] = {
 	LNBREAK,  	/* LNBREAK                */
 	NOTHING,  	/* OPTIMIZED              */
 	PSEUDO,   	/* PSEUDO                 */
+	REGEX_SET,	/* REGEX_SET              */
 	/* ------------ States ------------- */
 	TRIE,     	/* TRIE_next              */
 	TRIE,     	/* TRIE_next_fail         */
@@ -435,6 +437,7 @@ static const U8 regarglen[] = {
 	0,                                   	/* LNBREAK      */
 	0,                                   	/* OPTIMIZED    */
 	0,                                   	/* PSEUDO       */
+	EXTRA_SIZE(struct regnode_p),        	/* REGEX_SET    */
 };
 
 /* reg_off_by_arg[] - Which argument holds the offset to the next node */
@@ -549,6 +552,7 @@ static const char reg_off_by_arg[] = {
 	0,	/* LNBREAK      */
 	0,	/* OPTIMIZED    */
 	0,	/* PSEUDO       */
+	0,	/* REGEX_SET    */
 };
 
 #endif /* REG_COMP_C */
@@ -669,6 +673,7 @@ EXTCONST char * const PL_reg_name[] = {
 	"LNBREAK",               	/* 0x6a */
 	"OPTIMIZED",             	/* 0x6b */
 	"PSEUDO",                	/* 0x6c */
+	"REGEX_SET",             	/* 0x6d */
 	/* ------------ States ------------- */
 	"TRIE_next",             	/* REGNODE_MAX +0x01 */
 	"TRIE_next_fail",        	/* REGNODE_MAX +0x02 */
@@ -817,7 +822,7 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__;
 EXTCONST U8 PL_simple[] __attribute__deprecated__ = {
     REG_ANY, SANY, ANYOF, ANYOFD, ANYOFL, ANYOFPOSIXL, ANYOFH, ANYOFHb,
     ANYOFHr, ANYOFHs, ANYOFR, ANYOFRb, ANYOFM, NANYOFM, POSIXD, POSIXL,
-    POSIXU, POSIXA, NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA,
+    POSIXU, POSIXA, NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA, REGEX_SET,
     0
 };
 #endif /* DOINIT */
@@ -826,7 +831,7 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__ = {
 EXTCONST U8 PL_simple_bitmask[];
 #else
 EXTCONST U8 PL_simple_bitmask[] = {
-    0x00, 0x00, 0xFF, 0xFF, 0x3F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+    0x00, 0x00, 0xFF, 0xFF, 0x3F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x20
 };
 #endif /* DOINIT */