regen/regcharclass.pl: Generate better code for some macros

This commit revamps the recently added function calculate_mask() to not
just work to give a single mask/compare value for its input and fail if
there are none, but to return a list of masks/compares when the set can
be split up into subsets that each can be represented by a mask/compare.
If this list taken as a whole yields fewer branches than what we get
otherwise, it is better code, and is used.

Said another way, what we had there before was all or nothing; this
works to improve things even if we can't do it all.

1 files changed, 13 insertions, 13 deletions

diff --git a/regcharclass.h b/regcharclass.h
index b631cd19a8..17dee91816 100644
--- a/regcharclass.h
+++ b/regcharclass.h
@@ -193,12 +193,12 @@
 
 /*** GENERATED CODE ***/
 #define is_HORIZWS_latin1(s)                                                \
-( 0x09 == ((U8*)s)[0] || 0x20 == ((U8*)s)[0] || 0xA0 == ((U8*)s)[0] )
+( ((U8*)s)[0] == 0x09 || ( ( ((U8*)s)[0] & 0x7F ) == 0x20 ) )
 
 /*** GENERATED CODE ***/
 #define is_HORIZWS_latin1_safe(s,e)                                         \
 ( ((e)-(s) > 0) ?                                                           \
-    ( 0x09 == ((U8*)s)[0] || 0x20 == ((U8*)s)[0] || 0xA0 == ((U8*)s)[0] )   \
+    ( ((U8*)s)[0] == 0x09 || ( ( ((U8*)s)[0] & 0x7F ) == 0x20 ) )           \
 : 0 )
 
 /*** GENERATED CODE ***/
@@ -307,7 +307,7 @@
 	( ( 0x90 <= ((U8*)s)[2] && ((U8*)s)[2] <= 0xAF ) ? 3 : 0 )          \
     : ( ( 0xBF == ((U8*)s)[1] ) && ( ((U8*)s)[2] >= 0xBE ) ) ? 3 : 0 )      \
 : ( 0xF0 == ((U8*)s)[0] ) ?                                                 \
-    ( ( ( ( 0x9F == ((U8*)s)[1] || 0xAF == ((U8*)s)[1] || 0xBF == ((U8*)s)[1] ) && ( 0xBF == ((U8*)s)[2] ) ) && ( ((U8*)s)[3] >= 0xBE ) ) ? 4 : 0 )\
+    ( ( ( ( ((U8*)s)[1] == 0x9F || ( ( ((U8*)s)[1] & 0xEF ) == 0xAF ) ) && ( 0xBF == ((U8*)s)[2] ) ) && ( ((U8*)s)[3] >= 0xBE ) ) ? 4 : 0 )\
 : ( 0xF1 <= ((U8*)s)[0] && ((U8*)s)[0] <= 0xF3 ) ?                          \
     ( ( ( ( ( ((U8*)s)[1] & 0xCF ) == 0x8F ) && ( 0xBF == ((U8*)s)[2] ) ) && ( ((U8*)s)[3] >= 0xBE ) ) ? 4 : 0 )\
 : ( ( ( ( 0xF4 == ((U8*)s)[0] ) && ( 0x8F == ((U8*)s)[1] ) ) && ( 0xBF == ((U8*)s)[2] ) ) && ( ((U8*)s)[3] >= 0xBE ) ) ? 4 : 0 )
@@ -560,12 +560,12 @@
 	( ( 0xA5 == ((U8*)s)[1] ) ?                                         \
 	    ( ( ( 0xD6 == ((U8*)s)[2] ) && ( 0x82 == ((U8*)s)[3] ) ) ? 4 : 0 )\
 	: ( 0xB4 == ((U8*)s)[1] ) ?                                         \
-	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( 0xA5 == ((U8*)s)[3] || 0xAB == ((U8*)s)[3] || 0xAD == ((U8*)s)[3] || 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
+	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( ( ( ((U8*)s)[3] & 0xF7 ) == 0xA5 ) || ((U8*)s)[3] == 0xAB || ((U8*)s)[3] == 0xB6 ) ) ? 4 : 0 )\
 	: ( ( ( 0xBE == ((U8*)s)[1] ) && ( 0xD5 == ((U8*)s)[2] ) ) && ( 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
     : ( 0xE1 == ((U8*)s)[0] ) ?                                             \
 	( ( 0xBC == ((U8*)s)[1] ) ?                                         \
 	    ( ( ( ( ( ((U8*)s)[2] & 0xD8 ) == 0x80 ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
-	: ( ( ( ( 0xBD == ((U8*)s)[1] ) && ( ( ((U8*)s)[2] & 0xF8 ) == 0xA0 || 0xB0 == ((U8*)s)[2] || 0xB4 == ((U8*)s)[2] || 0xBC == ((U8*)s)[2] ) ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
+	: ( ( ( ( 0xBD == ((U8*)s)[1] ) && ( ( ( ((U8*)s)[2] & 0xF8 ) == 0xA0 ) || ((U8*)s)[2] == 0xB0 || ( ( ((U8*)s)[2] & 0xF7 ) == 0xB4 ) ) ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
     : 0 )                                                                   \
 : ((e)-(s) > 4) ?                                                           \
     ( ( 0x61 == ((U8*)s)[0] ) ?                                             \
@@ -612,12 +612,12 @@
 	( ( 0xA5 == ((U8*)s)[1] ) ?                                         \
 	    ( ( ( 0xD6 == ((U8*)s)[2] ) && ( 0x82 == ((U8*)s)[3] ) ) ? 4 : 0 )\
 	: ( 0xB4 == ((U8*)s)[1] ) ?                                         \
-	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( 0xA5 == ((U8*)s)[3] || 0xAB == ((U8*)s)[3] || 0xAD == ((U8*)s)[3] || 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
+	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( ( ( ((U8*)s)[3] & 0xF7 ) == 0xA5 ) || ((U8*)s)[3] == 0xAB || ((U8*)s)[3] == 0xB6 ) ) ? 4 : 0 )\
 	: ( ( ( 0xBE == ((U8*)s)[1] ) && ( 0xD5 == ((U8*)s)[2] ) ) && ( 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
     : ( 0xE1 == ((U8*)s)[0] ) ?                                             \
 	( ( 0xBC == ((U8*)s)[1] ) ?                                         \
 	    ( ( ( ( ( ((U8*)s)[2] & 0xD8 ) == 0x80 ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
-	: ( ( ( ( 0xBD == ((U8*)s)[1] ) && ( ( ((U8*)s)[2] & 0xF8 ) == 0xA0 || 0xB0 == ((U8*)s)[2] || 0xB4 == ((U8*)s)[2] || 0xBC == ((U8*)s)[2] ) ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
+	: ( ( ( ( 0xBD == ((U8*)s)[1] ) && ( ( ( ((U8*)s)[2] & 0xF8 ) == 0xA0 ) || ((U8*)s)[2] == 0xB0 || ( ( ((U8*)s)[2] & 0xF7 ) == 0xB4 ) ) ) && ( 0xCE == ((U8*)s)[3] ) ) && ( 0xB9 == ((U8*)s)[4] ) ) ? 5 : 0 )\
     : 0 )                                                                   \
 : ((e)-(s) > 3) ?                                                           \
     ( ( 0x61 == ((U8*)s)[0] ) ?                                             \
@@ -664,7 +664,7 @@
 	( ( 0xA5 == ((U8*)s)[1] ) ?                                         \
 	    ( ( ( 0xD6 == ((U8*)s)[2] ) && ( 0x82 == ((U8*)s)[3] ) ) ? 4 : 0 )\
 	: ( 0xB4 == ((U8*)s)[1] ) ?                                         \
-	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( 0xA5 == ((U8*)s)[3] || 0xAB == ((U8*)s)[3] || 0xAD == ((U8*)s)[3] || 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
+	    ( ( ( 0xD5 == ((U8*)s)[2] ) && ( ( ( ((U8*)s)[3] & 0xF7 ) == 0xA5 ) || ((U8*)s)[3] == 0xAB || ((U8*)s)[3] == 0xB6 ) ) ? 4 : 0 )\
 	: ( ( ( 0xBE == ((U8*)s)[1] ) && ( 0xD5 == ((U8*)s)[2] ) ) && ( 0xB6 == ((U8*)s)[3] ) ) ? 4 : 0 )\
     : 0 )                                                                   \
 : ((e)-(s) > 2) ?                                                           \
@@ -703,13 +703,13 @@
 ( ((e)-(s) > 2) ?                                                           \
     ( ( ( ((U8*)s)[0] & 0xDF ) == 0x46 ) ?                                  \
 	( ( ( ((U8*)s)[1] & 0xDF ) == 0x46 ) ?                              \
-	    ( ( 0x49 == ((U8*)s)[2] || 0x4C == ((U8*)s)[2] || 0x69 == ((U8*)s)[2] || 0x6C == ((U8*)s)[2] ) ? 3 : 2 )\
-	: ( 0x49 == ((U8*)s)[1] || 0x4C == ((U8*)s)[1] || 0x69 == ((U8*)s)[1] || 0x6C == ((U8*)s)[1] ) ? 2 : 0 )\
-    : ( ( ( ((U8*)s)[0] & 0xDF ) == 0x53 ) && ( ( 0x53 == ((U8*)s)[1] || 0x54 == ((U8*)s)[1] ) || ( 0x73 == ((U8*)s)[1] || 0x74 == ((U8*)s)[1] ) ) ) ? 2 : 0 )\
+	    ( ( ( ( ((U8*)s)[2] & 0xDF ) == 0x49 ) || ( ( ((U8*)s)[2] & 0xDF ) == 0x4C ) ) ? 3 : 2 )\
+	: ( ( ( ((U8*)s)[1] & 0xDF ) == 0x49 ) || ( ( ((U8*)s)[1] & 0xDF ) == 0x4C ) ) ? 2 : 0 )\
+    : ( ( ( ((U8*)s)[0] & 0xDF ) == 0x53 ) && ( ( ( ((U8*)s)[1] & 0xDF ) == 0x53 ) || ( ( ((U8*)s)[1] & 0xDF ) == 0x54 ) ) ) ? 2 : 0 )\
 : ((e)-(s) > 1) ?                                                           \
     ( ( ( ((U8*)s)[0] & 0xDF ) == 0x46 ) ?                                  \
-	( ( 0x46 == ((U8*)s)[1] || 0x49 == ((U8*)s)[1] || 0x4C == ((U8*)s)[1] || 0x66 == ((U8*)s)[1] || 0x69 == ((U8*)s)[1] || 0x6C == ((U8*)s)[1] ) ? 2 : 0 )\
-    : ( ( ( ((U8*)s)[0] & 0xDF ) == 0x53 ) && ( ( 0x53 == ((U8*)s)[1] || 0x54 == ((U8*)s)[1] ) || ( 0x73 == ((U8*)s)[1] || 0x74 == ((U8*)s)[1] ) ) ) ? 2 : 0 )\
+	( ( ( ( ((U8*)s)[1] & 0xDF ) == 0x46 ) || ( ( ((U8*)s)[1] & 0xDF ) == 0x49 ) || ( ( ((U8*)s)[1] & 0xDF ) == 0x4C ) ) ? 2 : 0 )\
+    : ( ( ( ((U8*)s)[0] & 0xDF ) == 0x53 ) && ( ( ( ((U8*)s)[1] & 0xDF ) == 0x53 ) || ( ( ((U8*)s)[1] & 0xDF ) == 0x54 ) ) ) ? 2 : 0 )\
 : 0 )