pp_pack.c, simplifying genpacksizetables

Message-Id: <d11kvt$1k7$1@post.home.lunix>

p4raw-id: //depot/perl@24038

1 files changed, 220 insertions, 206 deletions

diff --git a/pp_pack.c b/pp_pack.c
index 3c00743b36..e62f56d1e4 100644
--- a/pp_pack.c
+++ b/pp_pack.c
@@ -314,213 +314,253 @@ S_mul128(pTHX_ SV *sv, U8 m)
 #define PACK_SIZE_UNPREDICTABLE		0x40	/* Not a fixed size element */
 #define PACK_SIZE_MASK			0x3F
 
-
-struct packsize_t {
-    const unsigned char *array;
-    int first;
-    int size;
-};
-
-#define PACK_SIZE_NORMAL 0
-#define PACK_SIZE_SHRIEKING 1
-
 /* These tables are regenerated by genpacksizetables.pl (and then hand pasted
    in).  You're unlikely ever to need to regenerate them.  */
+
+#if TYPE_IS_SHRIEKING != 0x100
+   ++++shriek offset should be 256
+#endif
+
+typedef U8 packprops_t;
 #if 'J'-'I' == 1
 /* ASCII */
-unsigned char size_normal[53] = {
-  /* C */ sizeof(unsigned char),
+const packprops_t packprops[512] = {
+    /* normal */
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0,
+    /* C */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
 #if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE)
-  /* D */ LONG_DOUBLESIZE,
+    /* D */ LONG_DOUBLESIZE,
 #else
-  0,
+    0,
 #endif
-  0,
-  /* F */ NVSIZE,
-  0, 0,
-  /* I */ sizeof(unsigned int),
-  /* J */ UVSIZE,
-  0,
-  /* L */ SIZE32,
-  0,
-  /* N */ SIZE32,
-  0, 0,
+    0,
+    /* F */ NVSIZE,
+    0, 0,
+    /* I */ sizeof(unsigned int),
+    /* J */ UVSIZE,
+    0,
+    /* L */ SIZE32,
+    0,
+    /* N */ SIZE32,
+    0, 0,
 #if defined(HAS_QUAD)
-  /* Q */ sizeof(Uquad_t),
+    /* Q */ sizeof(Uquad_t),
 #else
-  0,
+    0,
 #endif
-  0,
-  /* S */ SIZE16,
-  0,
-  /* U */ sizeof(char) | PACK_SIZE_UNPREDICTABLE,
-  /* V */ SIZE32,
-  /* W */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* c */ sizeof(char),
-  /* d */ sizeof(double),
-  0,
-  /* f */ sizeof(float),
-  0, 0,
-  /* i */ sizeof(int),
-  /* j */ IVSIZE,
-  0,
-  /* l */ SIZE32,
-  0,
-  /* n */ SIZE16,
-  0,
-  /* p */ sizeof(char *) | PACK_SIZE_CANNOT_CSUM,
+    0,
+    /* S */ SIZE16,
+    0,
+    /* U */ sizeof(char) | PACK_SIZE_UNPREDICTABLE,
+    /* V */ SIZE32,
+    /* W */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* c */ sizeof(char),
+    /* d */ sizeof(double),
+    0,
+    /* f */ sizeof(float),
+    0, 0,
+    /* i */ sizeof(int),
+    /* j */ IVSIZE,
+    0,
+    /* l */ SIZE32,
+    0,
+    /* n */ SIZE16,
+    0,
+    /* p */ sizeof(char *) | PACK_SIZE_CANNOT_CSUM,
 #if defined(HAS_QUAD)
-  /* q */ sizeof(Quad_t),
+    /* q */ sizeof(Quad_t),
 #else
-  0,
+    0,
 #endif
-  0,
-  /* s */ SIZE16,
-  0, 0,
-  /* v */ SIZE16,
-  /* w */ sizeof(char) | PACK_SIZE_UNPREDICTABLE | PACK_SIZE_CANNOT_CSUM,
-};
-unsigned char size_shrieking[46] = {
-  /* I */ sizeof(unsigned int),
-  0, 0,
-  /* L */ sizeof(unsigned long),
-  0,
+    0,
+    /* s */ SIZE16,
+    0, 0,
+    /* v */ SIZE16,
+    /* w */ sizeof(char) | PACK_SIZE_UNPREDICTABLE | PACK_SIZE_CANNOT_CSUM,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0,
+    /* shrieking */
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* I */ sizeof(unsigned int),
+    0, 0,
+    /* L */ sizeof(unsigned long),
+    0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* N */ SIZE32,
+    /* N */ SIZE32,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0,
-  /* S */ sizeof(unsigned short),
-  0, 0,
+    0, 0, 0, 0,
+    /* S */ sizeof(unsigned short),
+    0, 0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* V */ SIZE32,
+    /* V */ SIZE32,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* i */ sizeof(int),
-  0, 0,
-  /* l */ sizeof(long),
-  0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0,
+    /* i */ sizeof(int),
+    0, 0,
+    /* l */ sizeof(long),
+    0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* n */ SIZE16,
+    /* n */ SIZE16,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0,
-  /* s */ sizeof(short),
-  0, 0,
+    0, 0, 0, 0,
+    /* s */ sizeof(short),
+    0, 0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* v */ SIZE16
+    /* v */ SIZE16,
 #else
-  0
+    0,
 #endif
-};
-struct packsize_t packsize[2] = {
-  {size_normal, 67, 53},
-  {size_shrieking, 73, 46}
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0
 };
 #else
 /* EBCDIC (or bust) */
-unsigned char size_normal[100] = {
-  /* c */ sizeof(char),
-  /* d */ sizeof(double),
-  0,
-  /* f */ sizeof(float),
-  0, 0,
-  /* i */ sizeof(int),
-  0, 0, 0, 0, 0, 0, 0,
-  /* j */ IVSIZE,
-  0,
-  /* l */ SIZE32,
-  0,
-  /* n */ SIZE16,
-  0,
-  /* p */ sizeof(char *) | PACK_SIZE_CANNOT_CSUM,
+const packprops_t packprops[512] = {
+    /* normal */
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0,
+    /* c */ sizeof(char),
+    /* d */ sizeof(double),
+    0,
+    /* f */ sizeof(float),
+    0, 0,
+    /* i */ sizeof(int),
+    0, 0, 0, 0, 0, 0, 0,
+    /* j */ IVSIZE,
+    0,
+    /* l */ SIZE32,
+    0,
+    /* n */ SIZE16,
+    0,
+    /* p */ sizeof(char *) | PACK_SIZE_CANNOT_CSUM,
 #if defined(HAS_QUAD)
-  /* q */ sizeof(Quad_t),
+    /* q */ sizeof(Quad_t),
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* s */ SIZE16,
-  0, 0,
-  /* v */ SIZE16,
-  /* w */ sizeof(char) | PACK_SIZE_UNPREDICTABLE | PACK_SIZE_CANNOT_CSUM,
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  0, 0,
-  /* C */ sizeof(unsigned char),
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* s */ SIZE16,
+    0, 0,
+    /* v */ SIZE16,
+    /* w */ sizeof(char) | PACK_SIZE_UNPREDICTABLE | PACK_SIZE_CANNOT_CSUM,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* C */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
 #if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE)
-  /* D */ LONG_DOUBLESIZE,
+    /* D */ LONG_DOUBLESIZE,
 #else
-  0,
+    0,
 #endif
-  0,
-  /* F */ NVSIZE,
-  0, 0,
-  /* I */ sizeof(unsigned int),
-  0, 0, 0, 0, 0, 0, 0,
-  /* J */ UVSIZE,
-  0,
-  /* L */ SIZE32,
-  0,
-  /* N */ SIZE32,
-  0, 0,
+    0,
+    /* F */ NVSIZE,
+    0, 0,
+    /* I */ sizeof(unsigned int),
+    0, 0, 0, 0, 0, 0, 0,
+    /* J */ UVSIZE,
+    0,
+    /* L */ SIZE32,
+    0,
+    /* N */ SIZE32,
+    0, 0,
 #if defined(HAS_QUAD)
-  /* Q */ sizeof(Uquad_t),
+    /* Q */ sizeof(Uquad_t),
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* S */ SIZE16,
-  0,
-  /* U */ sizeof(char) | PACK_SIZE_UNPREDICTABLE,
-  /* V */ SIZE32,
-  /* W */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
-};
-unsigned char size_shrieking[93] = {
-  /* i */ sizeof(int),
-  0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* l */ sizeof(long),
-  0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* S */ SIZE16,
+    0,
+    /* U */ sizeof(char) | PACK_SIZE_UNPREDICTABLE,
+    /* V */ SIZE32,
+    /* W */ sizeof(unsigned char) | PACK_SIZE_UNPREDICTABLE,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* shrieking */
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* i */ sizeof(int),
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* l */ sizeof(long),
+    0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* n */ SIZE16,
+    /* n */ SIZE16,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* s */ sizeof(short),
-  0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* s */ sizeof(short),
+    0, 0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* v */ SIZE16,
+    /* v */ SIZE16,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* I */ sizeof(unsigned int),
-  0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* L */ sizeof(unsigned long),
-  0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0,
+    /* I */ sizeof(unsigned int),
+    0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* L */ sizeof(unsigned long),
+    0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* N */ SIZE32,
+    /* N */ SIZE32,
 #else
-  0,
+    0,
 #endif
-  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-  /* S */ sizeof(unsigned short),
-  0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    /* S */ sizeof(unsigned short),
+    0, 0,
 #if defined(PERL_PACK_CAN_SHRIEKSIGN)
-  /* V */ SIZE32
+    /* V */ SIZE32,
 #else
-  0
+    0,
 #endif
-};
-struct packsize_t packsize[2] = {
-  {size_normal, 131, 100},
-  {size_shrieking, 137, 93}
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 };
 #endif
 
@@ -701,9 +741,6 @@ S_measure_struct(pTHX_ tempsym_t* symptr)
     while (next_symbol(symptr)) {
 	I32 len;
 	int star, size;
-	int which = (symptr->code & TYPE_IS_SHRIEKING) ?
-	    PACK_SIZE_SHRIEKING : PACK_SIZE_NORMAL;
-	int offset = TYPE_NO_MODIFIERS(symptr->code) - packsize[which].first;
 
         switch (symptr->howlen) {
 	  case e_star:
@@ -716,11 +753,7 @@ S_measure_struct(pTHX_ tempsym_t* symptr)
 	    break;
         }
 
-	if ((offset >= 0) && (offset < packsize[which].size))
-	    size = packsize[which].array[offset] & PACK_SIZE_MASK;
-	else
-	    size = 0;
-
+	size = packprops[TYPE_NO_ENDIANNESS(symptr->code)] & PACK_SIZE_MASK;
 	if (!size) {
 	    /* endianness doesn't influence the size of a type */
 	    switch(TYPE_NO_ENDIANNESS(symptr->code)) {
@@ -1151,6 +1184,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, char *s, char *strbeg, char *strend, char
     bool utf8 = (symptr->flags & FLAG_PARSE_UTF8) ? 1 : 0;
 
     while (next_symbol(symptr)) {
+	packprops_t props;
 	I32 len, ai32;
         I32 datumtype = symptr->code;
 	/* do first one only unless in list context
@@ -1174,32 +1208,22 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, char *s, char *strbeg, char *strend, char
         explicit_length = TRUE;
       redo_switch:
         beyond = s >= strend;
-	{
-	    struct packsize_t *pack_props =
-		&packsize[(symptr->code & TYPE_IS_SHRIEKING) ?
-			  PACK_SIZE_SHRIEKING : PACK_SIZE_NORMAL];
-	    const int rawtype = TYPE_NO_MODIFIERS(datumtype);
-	    int offset = rawtype - pack_props->first;
-
-	    if (offset >= 0 && offset < pack_props->size) {
-		/* Data about this template letter  */
-		unsigned char data = pack_props->array[offset];
-
-		if (data) {
-		    /* data nonzero means we can process this letter.  */
-		    long size = data & PACK_SIZE_MASK;
-		    long howmany = (strend - s) / size;
-		    if (len > howmany)
-			len = howmany;
-
-		    if (!checksum || (data & PACK_SIZE_CANNOT_CSUM)) {
-			if (len && unpack_only_one) len = 1;
-			EXTEND(SP, len);
-			EXTEND_MORTAL(len);
-		    }
-		}
+
+	props = packprops[TYPE_NO_ENDIANNESS(datumtype)];
+	if (props) {
+	    /* props nonzero means we can process this letter. */
+	    long size = props & PACK_SIZE_MASK;
+	    long howmany = (strend - s) / size;
+	    if (len > howmany)
+		len = howmany;
+
+	    if (!checksum || (props & PACK_SIZE_CANNOT_CSUM)) {
+		if (len && unpack_only_one) len = 1;
+		EXTEND(SP, len);
+		EXTEND_MORTAL(len);
 	    }
 	}
+
 	switch(TYPE_NO_ENDIANNESS(datumtype)) {
 	default:
 	    Perl_croak(aTHX_ "Invalid type '%c' in unpack", (int)TYPE_NO_MODIFIERS(datumtype) );
@@ -2435,23 +2459,13 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist )
         }
 
 	if (len) {
-	    struct packsize_t *pack_props =
-		&packsize[(symptr->code & TYPE_IS_SHRIEKING) ?
-			  PACK_SIZE_SHRIEKING : PACK_SIZE_NORMAL];
-	    const int rawtype = TYPE_NO_MODIFIERS(datumtype);
-	    int offset = rawtype - pack_props->first;
-
-	    if (offset >= 0 && offset < pack_props->size) {
-		/* Data about this template letter  */
-		unsigned char data = pack_props->array[offset];
-
-		if (data && !(data & PACK_SIZE_UNPREDICTABLE)) {
-		    /* We can process this letter.  */
-		    STRLEN size = data & PACK_SIZE_MASK;
-		    GROWING(utf8, cat, start, cur, (STRLEN) len * size);
-		}
-	    }
+	    packprops_t props = packprops[TYPE_NO_ENDIANNESS(datumtype)];
 
+	    if (props && !(props & PACK_SIZE_UNPREDICTABLE)) {
+		/* We can process this letter. */
+		STRLEN size = props & PACK_SIZE_MASK;
+		GROWING(utf8, cat, start, cur, (STRLEN) len * size);
+	    }
         }
 
         /* Look ahead for next symbol. Do we have code/code? */