regcomp.c: Add a constant 0 element before inversion lists

This commit is the first step to separating the header from the body of
inversion lists.  Doing so will allow the compiled-in inversion lists to
be fully read-only.

To invert an inversion list, one simply unshifts a 0 to the front of it
if one is not there, and shifts off the 0 if it does have one.

The current data structure reserves an element at the beginning of each
inversion list that is either 0 or 1.  If 0, it means the inversion list
begins there; if 1, it means the inversion list starts at the next
element.  Inverting involves flipping this bit.

This commit changes the structure so that there is an additional element
just after the element that flips.  This new element is always 0, and
the flipping element now says whether the inversion list begins at the
constant 0 element, or the one after that.

Doing this allows the flipping element to be separated in later commits
from the body of the inversion list, which will always begin with the
constant 0 element.  That means that the body of the inversion list can
be const.

1 files changed, 140 insertions, 110 deletions

diff --git a/charclass_invlists.h b/charclass_invlists.h
index b5d71afb16..690526dd6e 100644
--- a/charclass_invlists.h
+++ b/charclass_invlists.h
@@ -13,11 +13,11 @@ static UV Latin1_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	0,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
-	256,
-	0
+	1039476070, /* Version and data structure type */
+	0,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
+	256
 };
 
 #endif
@@ -28,9 +28,10 @@ static UV AboveLatin1_invlist[] = {
 	1,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	256
 };
 
@@ -42,11 +43,11 @@ static UV ASCII_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	0,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
-	128,
-	0
+	1039476070, /* Version and data structure type */
+	0,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
+	128
 };
 
 #endif
@@ -57,9 +58,10 @@ static UV L1Cased_invlist[] = {
 	16,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	65,
 	91,
 	97,
@@ -86,9 +88,10 @@ static UV VertSpace_invlist[] = {
 	6,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	10,
 	14,
 	133,
@@ -105,9 +108,10 @@ static UV PerlSpace_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	14,
 	32,
@@ -122,9 +126,10 @@ static UV XPerlSpace_invlist[] = {
 	22,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	14,
 	32,
@@ -157,9 +162,10 @@ static UV PosixAlnum_invlist[] = {
 	6,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -176,9 +182,10 @@ static UV L1PosixAlnum_invlist[] = {
 	18,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -207,9 +214,10 @@ static UV PosixAlpha_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	65,
 	91,
 	97,
@@ -224,9 +232,10 @@ static UV L1PosixAlpha_invlist[] = {
 	16,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	65,
 	91,
 	97,
@@ -253,9 +262,10 @@ static UV PosixBlank_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	10,
 	32,
@@ -270,9 +280,10 @@ static UV XPosixBlank_invlist[] = {
 	18,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	10,
 	32,
@@ -301,13 +312,13 @@ static UV PosixCntrl_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	0,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	0,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	32,
 	127,
-	128,
-	0
+	128
 };
 
 #endif
@@ -318,13 +329,13 @@ static UV XPosixCntrl_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	0,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	0,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	32,
 	127,
-	160,
-	0
+	160
 };
 
 #endif
@@ -335,9 +346,10 @@ static UV PosixDigit_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58
 };
@@ -350,9 +362,10 @@ static UV PosixGraph_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	33,
 	127
 };
@@ -365,9 +378,10 @@ static UV L1PosixGraph_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	33,
 	127,
 	161,
@@ -382,9 +396,10 @@ static UV PosixLower_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	97,
 	123
 };
@@ -397,9 +412,10 @@ static UV L1PosixLower_invlist[] = {
 	12,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	97,
 	123,
 	170,
@@ -422,9 +438,10 @@ static UV PosixPrint_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	32,
 	127
 };
@@ -437,9 +454,10 @@ static UV L1PosixPrint_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	32,
 	127,
 	160,
@@ -454,9 +472,10 @@ static UV PosixPunct_invlist[] = {
 	8,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	33,
 	48,
 	58,
@@ -475,9 +494,10 @@ static UV L1PosixPunct_invlist[] = {
 	20,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	33,
 	48,
 	58,
@@ -508,9 +528,10 @@ static UV PosixSpace_invlist[] = {
 	4,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	14,
 	32,
@@ -525,9 +546,10 @@ static UV XPosixSpace_invlist[] = {
 	22,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	9,
 	14,
 	32,
@@ -560,9 +582,10 @@ static UV PosixUpper_invlist[] = {
 	2,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	65,
 	91
 };
@@ -575,9 +598,10 @@ static UV L1PosixUpper_invlist[] = {
 	6,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	65,
 	91,
 	192,
@@ -594,9 +618,10 @@ static UV PosixWord_invlist[] = {
 	8,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -615,9 +640,10 @@ static UV L1PosixWord_invlist[] = {
 	20,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -648,9 +674,10 @@ static UV PosixXDigit_invlist[] = {
 	6,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -667,9 +694,10 @@ static UV XPosixXDigit_invlist[] = {
 	12,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	48,
 	58,
 	65,
@@ -690,9 +718,10 @@ static UV NonL1_Perl_Non_Final_Folds_invlist[] = {
 	44,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	700,
 	701,
 	776,
@@ -745,9 +774,10 @@ static UV _Perl_Multi_Char_Folds_invlist[] = {
 	58,	/* Number of elements */
 	0,	/* Current iteration position */
 	0,	/* Cache of previous search index result */
-	290655244, /* Version and data structure type */
-	1,	/* 0 if this is the first element of the list proper;
-		   1 if the next element is the first */
+	1039476070, /* Version and data structure type */
+	1,	/* 0 if the list starts at 0;
+		   1 if it starts at the element beyond 0 */
+	0,
 	223,
 	224,
 	304,