X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/9444d2138b6b5264fb9381e43188986db5564e80..fcdf154797de71462d8c8f5606482a86ed73943a:/pp_pack.c diff --git a/pp_pack.c b/pp_pack.c index 7aa95a9..e9969d5 100644 --- a/pp_pack.c +++ b/pp_pack.c @@ -1,7 +1,7 @@ /* pp_pack.c * - * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, - * 2000, 2001, 2002, 2003, 2004, 2005, 2006, by Larry Wall and others + * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, + * 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 by Larry Wall and others * * You may distribute under the terms of either the GNU General Public * License or the Artistic License, as specified in the README file. @@ -14,6 +14,8 @@ * wooden spoon, a short two-pronged fork and some skewers were stowed; and * hidden at the bottom of the pack in a flat wooden box a dwindling treasure, * some salt. + * + * [p.653 of _The Lord of the Rings_, IV/iv: "Of Herbs and Stewed Rabbit"] */ /* This file contains pp ("push/pop") functions that @@ -26,7 +28,6 @@ * other pp*.c files for the rest of the pp_ functions. */ - #include "EXTERN.h" #define PERL_IN_PP_PACK_C #include "perl.h" @@ -69,9 +70,16 @@ typedef struct tempsym { (symptr)->previous = NULL; \ } STMT_END -#if PERL_VERSION >= 9 -# define PERL_PACK_CAN_BYTEORDER -# define PERL_PACK_CAN_SHRIEKSIGN +typedef union { + NV nv; + U8 bytes[sizeof(NV)]; +} NV_bytes; + +#if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE) +typedef union { + long double ld; + U8 bytes[sizeof(long double)]; +} ld_bytes; #endif #ifndef CHAR_BIT @@ -145,17 +153,20 @@ typedef struct tempsym { #define PUSH32(utf8, cur, p) PUSH_BYTES(utf8, cur, OFF32(p), SIZE32) /* Only to be used inside a loop (see the break) */ -#define SHIFT_VAR(utf8, s, strend, var, datumtype) \ +#define SHIFT_BYTES(utf8, s, strend, buf, len, datumtype) \ STMT_START { \ if (utf8) { \ if (!uni_to_bytes(aTHX_ &s, strend, \ - (char *) &var, sizeof(var), datumtype)) break;\ + (char *) (buf), len, datumtype)) break; \ } else { \ - Copy(s, (char *) &var, sizeof(var), char); \ - s += sizeof(var); \ + Copy(s, (char *) (buf), len, char); \ + s += len; \ } \ } STMT_END +#define SHIFT_VAR(utf8, s, strend, var, datumtype) \ + SHIFT_BYTES(utf8, s, strend, &(var), sizeof(var), datumtype) + #define PUSH_VAR(utf8, aptr, var) \ PUSH_BYTES(utf8, aptr, &(var), sizeof(var)) @@ -178,6 +189,8 @@ S_mul128(pTHX_ SV *sv, U8 m) char *s = SvPV(sv, len); char *t; + PERL_ARGS_ASSERT_MUL128; + if (!strnEQ(s, "0000", 4)) { /* need to grow sv */ SV * const tmpNew = newSVpvs("0000000000"); @@ -219,32 +232,6 @@ S_mul128(pTHX_ SV *sv, U8 m) #define TYPE_MODIFIERS(t) ((t) & ~0xFF) #define TYPE_NO_MODIFIERS(t) ((t) & 0xFF) -#ifdef PERL_PACK_CAN_SHRIEKSIGN -# define SHRIEKING_ALLOWED_TYPES "sSiIlLxXnNvV@." -#else -# define SHRIEKING_ALLOWED_TYPES "sSiIlLxX" -#endif - -#ifndef PERL_PACK_CAN_BYTEORDER -/* Put "can't" first because it is shorter */ -# define TYPE_ENDIANNESS(t) 0 -# define TYPE_NO_ENDIANNESS(t) (t) - -# define ENDIANNESS_ALLOWED_TYPES "" - -# define DO_BO_UNPACK(var, type) -# define DO_BO_PACK(var, type) -# define DO_BO_UNPACK_PTR(var, type, pre_cast, post_cast) -# define DO_BO_PACK_PTR(var, type, pre_cast, post_cast) -# define DO_BO_UNPACK_N(var, type) -# define DO_BO_PACK_N(var, type) -# define DO_BO_UNPACK_P(var) -# define DO_BO_PACK_P(var) -# define DO_BO_UNPACK_PC(var) -# define DO_BO_PACK_PC(var) - -#else /* PERL_PACK_CAN_BYTEORDER */ - # define TYPE_ENDIANNESS(t) ((t) & TYPE_ENDIANNESS_MASK) # define TYPE_NO_ENDIANNESS(t) ((t) & ~TYPE_ENDIANNESS_MASK) @@ -313,23 +300,20 @@ S_mul128(pTHX_ SV *sv, U8 m) } STMT_END # if PTRSIZE == INTSIZE -# define DO_BO_UNPACK_P(var) DO_BO_UNPACK_PTR(var, i, int, void) -# define DO_BO_PACK_P(var) DO_BO_PACK_PTR(var, i, int, void) # define DO_BO_UNPACK_PC(var) DO_BO_UNPACK_PTR(var, i, int, char) # define DO_BO_PACK_PC(var) DO_BO_PACK_PTR(var, i, int, char) # elif PTRSIZE == LONGSIZE -# define DO_BO_UNPACK_P(var) DO_BO_UNPACK_PTR(var, l, long, void) -# define DO_BO_PACK_P(var) DO_BO_PACK_PTR(var, l, long, void) -# define DO_BO_UNPACK_PC(var) DO_BO_UNPACK_PTR(var, l, long, char) -# define DO_BO_PACK_PC(var) DO_BO_PACK_PTR(var, l, long, char) +# if LONGSIZE < IVSIZE && IVSIZE == 8 +# define DO_BO_UNPACK_PC(var) DO_BO_UNPACK_PTR(var, 64, IV, char) +# define DO_BO_PACK_PC(var) DO_BO_PACK_PTR(var, 64, IV, char) +# else +# define DO_BO_UNPACK_PC(var) DO_BO_UNPACK_PTR(var, l, IV, char) +# define DO_BO_PACK_PC(var) DO_BO_PACK_PTR(var, l, IV, char) +# endif # elif PTRSIZE == IVSIZE -# define DO_BO_UNPACK_P(var) DO_BO_UNPACK_PTR(var, l, IV, void) -# define DO_BO_PACK_P(var) DO_BO_PACK_PTR(var, l, IV, void) # define DO_BO_UNPACK_PC(var) DO_BO_UNPACK_PTR(var, l, IV, char) # define DO_BO_PACK_PC(var) DO_BO_PACK_PTR(var, l, IV, char) # else -# define DO_BO_UNPACK_P(var) BO_CANT_DOIT(unpack, pointer) -# define DO_BO_PACK_P(var) BO_CANT_DOIT(pack, pointer) # define DO_BO_UNPACK_PC(var) BO_CANT_DOIT(unpack, pointer) # define DO_BO_PACK_PC(var) BO_CANT_DOIT(pack, pointer) # endif @@ -358,261 +342,11 @@ S_mul128(pTHX_ SV *sv, U8 m) # define DO_BO_PACK_N(var, type) BO_CANT_DOIT(pack, type) # endif -#endif /* PERL_PACK_CAN_BYTEORDER */ - #define PACK_SIZE_CANNOT_CSUM 0x80 #define PACK_SIZE_UNPREDICTABLE 0x40 /* Not a fixed size element */ #define PACK_SIZE_MASK 0x3F -/* 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 */ -STATIC 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, -#else - 0, -#endif - 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), -#else - 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, -#if defined(HAS_QUAD) - /* q */ sizeof(Quad_t), -#else - 0, -#endif - 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, -#else - 0, -#endif - 0, 0, 0, 0, - /* S */ sizeof(unsigned short), - 0, 0, -#if defined(PERL_PACK_CAN_SHRIEKSIGN) - /* V */ SIZE32, -#else - 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, -#if defined(PERL_PACK_CAN_SHRIEKSIGN) - /* n */ SIZE16, -#else - 0, -#endif - 0, 0, 0, 0, - /* s */ sizeof(short), - 0, 0, -#if defined(PERL_PACK_CAN_SHRIEKSIGN) - /* v */ SIZE16, -#else - 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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 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) */ -STATIC 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), -#else - 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) | PACK_SIZE_UNPREDICTABLE, -#if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE) - /* D */ LONG_DOUBLESIZE, -#else - 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, -#if defined(HAS_QUAD) - /* Q */ sizeof(Uquad_t), -#else - 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, - 0, 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, -#else - 0, -#endif - 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, -#else - 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, -#if defined(PERL_PACK_CAN_SHRIEKSIGN) - /* N */ SIZE32, -#else - 0, -#endif - 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, -#else - 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 -}; -#endif +#include "packsizetables.c" STATIC U8 uni_to_byte(pTHX_ const char **s, const char *end, I32 datumtype) @@ -620,17 +354,16 @@ uni_to_byte(pTHX_ const char **s, const char *end, I32 datumtype) STRLEN retlen; UV val = utf8n_to_uvchr((U8 *) *s, end-*s, &retlen, ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); - /* We try to process malformed UTF-8 as much as possible (preferrably with + /* We try to process malformed UTF-8 as much as possible (preferably with warnings), but these two mean we make no progress in the string and might enter an infinite loop */ if (retlen == (STRLEN) -1 || retlen == 0) Perl_croak(aTHX_ "Malformed UTF-8 string in '%c' format in unpack", (int) TYPE_NO_MODIFIERS(datumtype)); if (val >= 0x100) { - if (ckWARN(WARN_UNPACK)) - Perl_warner(aTHX_ packWARN(WARN_UNPACK), - "Character in '%c' format wrapped in unpack", - (int) TYPE_NO_MODIFIERS(datumtype)); + Perl_ck_warner(aTHX_ packWARN(WARN_UNPACK), + "Character in '%c' format wrapped in unpack", + (int) TYPE_NO_MODIFIERS(datumtype)); val &= 0xff; } *s += retlen; @@ -675,12 +408,12 @@ uni_to_bytes(pTHX_ const char **s, const char *end, const char *buf, int buf_len } if (from > end) from = end; } - if ((bad & 2) && ckWARN(WARN_UNPACK)) - Perl_warner(aTHX_ packWARN(datumtype & TYPE_IS_PACK ? + if ((bad & 2)) + Perl_ck_warner(aTHX_ packWARN(datumtype & TYPE_IS_PACK ? WARN_PACK : WARN_UNPACK), - "Character(s) in '%c' format wrapped in %s", - (int) TYPE_NO_MODIFIERS(datumtype), - datumtype & TYPE_IS_PACK ? "pack" : "unpack"); + "Character(s) in '%c' format wrapped in %s", + (int) TYPE_NO_MODIFIERS(datumtype), + datumtype & TYPE_IS_PACK ? "pack" : "unpack"); } *s = from; return TRUE; @@ -706,6 +439,8 @@ STATIC char * S_bytes_to_uni(const U8 *start, STRLEN len, char *dest) { const U8 * const end = start + len; + PERL_ARGS_ASSERT_BYTES_TO_UNI; + while (start < end) { const UV uv = NATIVE_TO_ASCII(*start); if (UNI_IS_INVARIANT(uv)) @@ -785,6 +520,8 @@ S_measure_struct(pTHX_ tempsym_t* symptr) { I32 total = 0; + PERL_ARGS_ASSERT_MEASURE_STRUCT; + while (next_symbol(symptr)) { I32 len; int size; @@ -809,10 +546,8 @@ S_measure_struct(pTHX_ tempsym_t* symptr) Perl_croak(aTHX_ "Invalid type '%c' in %s", (int)TYPE_NO_MODIFIERS(symptr->code), _action( symptr ) ); -#ifdef PERL_PACK_CAN_SHRIEKSIGN case '.' | TYPE_IS_SHRIEKING: case '@' | TYPE_IS_SHRIEKING: -#endif case '@': case '.': case '/': @@ -892,8 +627,10 @@ S_measure_struct(pTHX_ tempsym_t* symptr) * returns char pointer to char after match, or NULL */ STATIC const char * -S_group_end(pTHX_ register const char *patptr, register const char *patend, char ender) +S_group_end(pTHX_ const char *patptr, const char *patend, char ender) { + PERL_ARGS_ASSERT_GROUP_END; + while (patptr < patend) { const char c = *patptr++; @@ -921,9 +658,12 @@ S_group_end(pTHX_ register const char *patptr, register const char *patend, char * Advances char pointer to 1st non-digit char and returns number */ STATIC const char * -S_get_num(pTHX_ register const char *patptr, I32 *lenptr ) +S_get_num(pTHX_ const char *patptr, I32 *lenptr ) { I32 len = *patptr++ - '0'; + + PERL_ARGS_ASSERT_GET_NUM; + while (isDIGIT(*patptr)) { if (len >= 0x7FFFFFFF/10) Perl_croak(aTHX_ "pack/unpack repeat count overflow"); @@ -942,6 +682,8 @@ S_next_symbol(pTHX_ tempsym_t* symptr ) const char* patptr = symptr->patptr; const char* const patend = symptr->patend; + PERL_ARGS_ASSERT_NEXT_SYMBOL; + symptr->flags &= ~FLAG_SLASH; while (patptr < patend) { @@ -992,9 +734,8 @@ S_next_symbol(pTHX_ tempsym_t* symptr ) switch (*patptr) { case '!': modifier = TYPE_IS_SHRIEKING; - allowed = SHRIEKING_ALLOWED_TYPES; + allowed = "sSiIlLxXnNvV@."; break; -#ifdef PERL_PACK_CAN_BYTEORDER case '>': modifier = TYPE_IS_BIG_ENDIAN; allowed = ENDIANNESS_ALLOWED_TYPES; @@ -1003,7 +744,6 @@ S_next_symbol(pTHX_ tempsym_t* symptr ) modifier = TYPE_IS_LITTLE_ENDIAN; allowed = ENDIANNESS_ALLOWED_TYPES; break; -#endif /* PERL_PACK_CAN_BYTEORDER */ default: allowed = ""; modifier = 0; @@ -1025,11 +765,11 @@ S_next_symbol(pTHX_ tempsym_t* symptr ) Perl_croak(aTHX_ "Can't use '%c' in a group with different byte-order in %s", *patptr, _action( symptr ) ); - if ((code & modifier) && ckWARN(WARN_UNPACK)) { - Perl_warner(aTHX_ packWARN(WARN_UNPACK), - "Duplicate modifier '%c' after '%c' in %s", - *patptr, (int) TYPE_NO_MODIFIERS(code), - _action( symptr ) ); + if ((code & modifier)) { + Perl_ck_warner(aTHX_ packWARN(WARN_UNPACK), + "Duplicate modifier '%c' after '%c' in %s", + *patptr, (int) TYPE_NO_MODIFIERS(code), + _action( symptr ) ); } code |= modifier; @@ -1121,6 +861,9 @@ STATIC bool need_utf8(const char *pat, const char *patend) { bool first = TRUE; + + PERL_ARGS_ASSERT_NEED_UTF8; + while (pat < patend) { if (pat[0] == '#') { pat++; @@ -1136,6 +879,8 @@ need_utf8(const char *pat, const char *patend) STATIC char first_symbol(const char *pat, const char *patend) { + PERL_ARGS_ASSERT_FIRST_SYMBOL; + while (pat < patend) { if (pat[0] != '#') return pat[0]; pat++; @@ -1149,9 +894,21 @@ first_symbol(const char *pat, const char *patend) { /* =for apidoc unpackstring -The engine implementing unpack() Perl function. C puts the -extracted list items on the stack and returns the number of elements. -Issue C before and C after the call to this function. +The engine implementing the unpack() Perl function. + +Using the template pat..patend, this function unpacks the string +s..strend into a number of mortal SVs, which it pushes onto the perl +argument (@_) stack (so you will need to issue a C before and +C after the call to this function). It returns the number of +pushed elements. + +The strend and patend pointers should point to the byte following the last +character of each string. + +Although this function returns its values on the perl argument stack, it +doesn't take any parameters from that stack (and thus in particular +there's no need to do a PUSHMARK before calling it, unlike L for +example). =cut */ @@ -1160,6 +917,8 @@ Perl_unpackstring(pTHX_ const char *pat, const char *patend, const char *s, cons { tempsym_t sym; + PERL_ARGS_ASSERT_UNPACKSTRING; + if (flags & FLAG_DO_UTF8) flags |= FLAG_WAS_UTF8; else if (need_utf8(pat, patend)) { /* We probably should try to avoid this in case a scalar context call @@ -1183,10 +942,9 @@ STATIC I32 S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const char *strend, const char **new_s ) { dVAR; dSP; - SV *sv; + SV *sv = NULL; const I32 start_sp_offset = SP - PL_stack_base; howlen_t howlen; - I32 checksum = 0; UV cuv = 0; NV cdouble = 0.0; @@ -1195,6 +953,9 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c bool explicit_length; const bool unpack_only_one = (symptr->flags & FLAG_UNPACK_ONLY_ONE) != 0; bool utf8 = (symptr->flags & FLAG_PARSE_UTF8) ? 1 : 0; + + PERL_ARGS_ASSERT_UNPACK_REC; + symptr->strbeg = s - strbeg; while (next_symbol(symptr)) { @@ -1259,6 +1020,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c symptr->previous = &savsym; symptr->level++; PUTBACK; + if (len && unpack_only_one) len = 1; while (len--) { symptr->patptr = savsym.grpbeg; if (utf8) symptr->flags |= FLAG_PARSE_UTF8; @@ -1272,17 +1034,11 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c *symptr = savsym; break; } -#ifdef PERL_PACK_CAN_SHRIEKSIGN case '.' | TYPE_IS_SHRIEKING: -#endif case '.': { const char *from; SV *sv; -#ifdef PERL_PACK_CAN_SHRIEKSIGN const bool u8 = utf8 && !(datumtype & TYPE_IS_SHRIEKING); -#else /* PERL_PACK_CAN_SHRIEKSIGN */ - const bool u8 = utf8; -#endif if (howlen == e_star) from = strbeg; else if (len <= 0) from = s; else { @@ -1294,19 +1050,13 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c sv = from <= s ? newSVuv( u8 ? (UV) utf8_length((const U8*)from, (const U8*)s) : (UV) (s-from)) : newSViv(-(u8 ? (IV) utf8_length((const U8*)s, (const U8*)from) : (IV) (from-s))); - XPUSHs(sv_2mortal(sv)); + mXPUSHs(sv); break; } -#ifdef PERL_PACK_CAN_SHRIEKSIGN case '@' | TYPE_IS_SHRIEKING: -#endif case '@': s = strbeg + symptr->strbeg; -#ifdef PERL_PACK_CAN_SHRIEKSIGN if (utf8 && !(datumtype & TYPE_IS_SHRIEKING)) -#else /* PERL_PACK_CAN_SHRIEKSIGN */ - if (utf8) -#endif { while (len > 0) { if (s >= strend) @@ -1425,7 +1175,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (utf8 && (symptr->flags & FLAG_WAS_UTF8)) { for (ptr = s+len-1; ptr >= s; ptr--) if (*ptr != 0 && !UTF8_IS_CONTINUATION(*ptr) && - !is_utf8_space((U8 *) ptr)) break; + !isSPACE_utf8(ptr)) break; if (ptr >= s) ptr += UTF8SKIP(ptr); else ptr++; if (ptr > s+len) @@ -1444,7 +1194,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (!(symptr->flags & FLAG_WAS_UTF8)) sv_utf8_downgrade(sv, 0); } - XPUSHs(sv_2mortal(sv)); + mXPUSHs(sv); s += len; break; case 'B': @@ -1453,20 +1203,6 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (howlen == e_star || len > (strend - s) * 8) len = (strend - s) * 8; if (checksum) { - if (!PL_bitcount) { - int bits; - Newxz(PL_bitcount, 256, char); - for (bits = 1; bits < 256; bits++) { - if (bits & 1) PL_bitcount[bits]++; - if (bits & 2) PL_bitcount[bits]++; - if (bits & 4) PL_bitcount[bits]++; - if (bits & 8) PL_bitcount[bits]++; - if (bits & 16) PL_bitcount[bits]++; - if (bits & 32) PL_bitcount[bits]++; - if (bits & 64) PL_bitcount[bits]++; - if (bits & 128) PL_bitcount[bits]++; - } - } if (utf8) while (len >= 8 && s < strend) { cuv += PL_bitcount[uni_to_byte(aTHX_ &s, strend, datumtype)]; @@ -1527,13 +1263,15 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c } case 'H': case 'h': { - char *str; + char *str = NULL; /* Preliminary length estimate, acceptable for utf8 too */ if (howlen == e_star || len > (strend - s) * 2) len = (strend - s) * 2; - sv = sv_2mortal(newSV(len ? len : 1)); - SvPOK_on(sv); - str = SvPVX(sv); + if (!checksum) { + sv = sv_2mortal(newSV(len ? len : 1)); + SvPOK_on(sv); + str = SvPVX(sv); + } if (datumtype == 'h') { U8 bits = 0; I32 ai32 = len; @@ -1543,7 +1281,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (s >= strend) break; bits = uni_to_byte(aTHX_ &s, strend, datumtype); } else bits = * (U8 *) s++; - *str++ = PL_hexdigit[bits & 15]; + if (!checksum) + *str++ = PL_hexdigit[bits & 15]; } } else { U8 bits = 0; @@ -1554,39 +1293,52 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (s >= strend) break; bits = uni_to_byte(aTHX_ &s, strend, datumtype); } else bits = *(U8 *) s++; - *str++ = PL_hexdigit[(bits >> 4) & 15]; + if (!checksum) + *str++ = PL_hexdigit[(bits >> 4) & 15]; } } - *str = '\0'; - SvCUR_set(sv, str - SvPVX_const(sv)); - XPUSHs(sv); + if (!checksum) { + *str = '\0'; + SvCUR_set(sv, str - SvPVX_const(sv)); + XPUSHs(sv); + } break; } + case 'C': + if (len == 0) { + if (explicit_length) + /* Switch to "character" mode */ + utf8 = (symptr->flags & FLAG_DO_UTF8) ? 1 : 0; + break; + } + /* FALL THROUGH */ case 'c': - while (len-- > 0) { - int aint = SHIFT_BYTE(utf8, s, strend, datumtype); - if (aint >= 128) /* fake up signed chars */ + while (len-- > 0 && s < strend) { + int aint; + if (utf8) + { + STRLEN retlen; + aint = utf8n_to_uvchr((U8 *) s, strend-s, &retlen, + ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY); + if (retlen == (STRLEN) -1 || retlen == 0) + Perl_croak(aTHX_ "Malformed UTF-8 string in unpack"); + s += retlen; + } + else + aint = *(U8 *)(s)++; + if (aint >= 128 && datumtype != 'C') /* fake up signed chars */ aint -= 256; if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)aint))); + mPUSHi(aint); else if (checksum > bits_in_uv) cdouble += (NV)aint; else cuv += aint; } break; - case 'C': case 'W': W_checksum: - if (len == 0) { - if (explicit_length && datumtype == 'C') - /* Switch to "character" mode */ - utf8 = (symptr->flags & FLAG_DO_UTF8) ? 1 : 0; - break; - } - if (datumtype == 'C' ? - (symptr->flags & FLAG_DO_UTF8) && - !(symptr->flags & FLAG_WAS_UTF8) : utf8) { + if (utf8) { while (len-- > 0 && s < strend) { STRLEN retlen; const UV val = utf8n_to_uvchr((U8 *) s, strend-s, &retlen, @@ -1595,7 +1347,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c Perl_croak(aTHX_ "Malformed UTF-8 string in unpack"); s += retlen; if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV) val))); + mPUSHu(val); else if (checksum > bits_in_uv) cdouble += (NV) val; else @@ -1604,7 +1356,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c } else if (!checksum) while (len-- > 0) { const U8 ch = *(U8 *) s++; - PUSHs(sv_2mortal(newSVuv((UV) ch))); + mPUSHu(ch); } else if (checksum > bits_in_uv) while (len-- > 0) cdouble += (NV) *(U8 *) s++; @@ -1613,7 +1365,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c break; case 'U': if (len == 0) { - if (explicit_length) { + if (explicit_length && howlen != e_star) { /* Switch to "bytes in UTF-8" mode */ if (symptr->flags & FLAG_DO_UTF8) utf8 = 0; else @@ -1643,16 +1395,16 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c len = UTF8SKIP(result); if (!uni_to_bytes(aTHX_ &ptr, strend, (char *) &result[1], len-1, 'U')) break; - auv = utf8n_to_uvuni(result, len, &retlen, ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANYUV); + auv = utf8n_to_uvuni(result, len, &retlen, UTF8_ALLOW_DEFAULT); s = ptr; } else { - auv = utf8n_to_uvuni((U8*)s, strend - s, &retlen, ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANYUV); + auv = utf8n_to_uvuni((U8*)s, strend - s, &retlen, UTF8_ALLOW_DEFAULT); if (retlen == (STRLEN) -1 || retlen == 0) Perl_croak(aTHX_ "Malformed UTF-8 string in unpack"); s += retlen; } if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV) auv))); + mPUSHu(auv); else if (checksum > bits_in_uv) cdouble += (NV) auv; else @@ -1666,7 +1418,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, ashort, datumtype); DO_BO_UNPACK(ashort, s); if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)ashort))); + mPUSHi(ashort); else if (checksum > bits_in_uv) cdouble += (NV)ashort; else @@ -1690,7 +1442,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c ai16 -= 65536; #endif if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)ai16))); + mPUSHi(ai16); else if (checksum > bits_in_uv) cdouble += (NV)ai16; else @@ -1704,7 +1456,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, aushort, datumtype); DO_BO_UNPACK(aushort, s); if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV) aushort))); + mPUSHu(aushort); else if (checksum > bits_in_uv) cdouble += (NV)aushort; else @@ -1712,7 +1464,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c } break; #else - /* Fallhrough! */ + /* Fallthrough! */ #endif case 'v': case 'n': @@ -1733,14 +1485,13 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c au16 = vtohs(au16); #endif if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV)au16))); + mPUSHu(au16); else if (checksum > bits_in_uv) cdouble += (NV) au16; else cuv += au16; } break; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'v' | TYPE_IS_SHRIEKING: case 'n' | TYPE_IS_SHRIEKING: while (len-- > 0) { @@ -1758,14 +1509,13 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c ai16 = (I16) vtohs((U16) ai16); # endif /* HAS_VTOHS */ if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)ai16))); + mPUSHi(ai16); else if (checksum > bits_in_uv) cdouble += (NV) ai16; else cuv += ai16; } break; -#endif /* PERL_PACK_CAN_SHRIEKSIGN */ case 'i': case 'i' | TYPE_IS_SHRIEKING: while (len-- > 0) { @@ -1773,7 +1523,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, aint, datumtype); DO_BO_UNPACK(aint, i); if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)aint))); + mPUSHi(aint); else if (checksum > bits_in_uv) cdouble += (NV)aint; else @@ -1787,7 +1537,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, auint, datumtype); DO_BO_UNPACK(auint, i); if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV)auint))); + mPUSHu(auint); else if (checksum > bits_in_uv) cdouble += (NV)auint; else @@ -1808,7 +1558,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c Perl_croak(aTHX_ "'j' not supported on this platform"); #endif if (!checksum) - PUSHs(sv_2mortal(newSViv(aiv))); + mPUSHi(aiv); else if (checksum > bits_in_uv) cdouble += (NV)aiv; else @@ -1829,7 +1579,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c Perl_croak(aTHX_ "'J' not supported on this platform"); #endif if (!checksum) - PUSHs(sv_2mortal(newSVuv(auv))); + mPUSHu(auv); else if (checksum > bits_in_uv) cdouble += (NV)auv; else @@ -1843,7 +1593,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, along, datumtype); DO_BO_UNPACK(along, l); if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)along))); + mPUSHi(along); else if (checksum > bits_in_uv) cdouble += (NV)along; else @@ -1865,7 +1615,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c if (ai32 > 2147483647) ai32 -= 4294967296; #endif if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)ai32))); + mPUSHi(ai32); else if (checksum > bits_in_uv) cdouble += (NV)ai32; else @@ -1879,7 +1629,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, aulong, datumtype); DO_BO_UNPACK(aulong, l); if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV)aulong))); + mPUSHu(aulong); else if (checksum > bits_in_uv) cdouble += (NV)aulong; else @@ -1908,46 +1658,44 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c au32 = vtohl(au32); #endif if (!checksum) - PUSHs(sv_2mortal(newSVuv((UV)au32))); + mPUSHu(au32); else if (checksum > bits_in_uv) cdouble += (NV)au32; else cuv += au32; } break; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'V' | TYPE_IS_SHRIEKING: case 'N' | TYPE_IS_SHRIEKING: while (len-- > 0) { I32 ai32; -# if U32SIZE > SIZE32 +#if U32SIZE > SIZE32 ai32 = 0; -# endif +#endif SHIFT32(utf8, s, strend, &ai32, datumtype); -# ifdef HAS_NTOHL +#ifdef HAS_NTOHL if (datumtype == ('N' | TYPE_IS_SHRIEKING)) ai32 = (I32)PerlSock_ntohl((U32)ai32); -# endif -# ifdef HAS_VTOHL +#endif +#ifdef HAS_VTOHL if (datumtype == ('V' | TYPE_IS_SHRIEKING)) ai32 = (I32)vtohl((U32)ai32); -# endif +#endif if (!checksum) - PUSHs(sv_2mortal(newSViv((IV)ai32))); + mPUSHi(ai32); else if (checksum > bits_in_uv) cdouble += (NV)ai32; else cuv += ai32; } break; -#endif /* PERL_PACK_CAN_SHRIEKSIGN */ case 'p': while (len-- > 0) { const char *aptr; SHIFT_VAR(utf8, s, strend, aptr, datumtype); DO_BO_UNPACK_PC(aptr); /* newSVpv generates undef if aptr is NULL */ - PUSHs(sv_2mortal(newSVpv(aptr, 0))); + mPUSHs(newSVpv(aptr, 0)); } break; case 'w': @@ -1962,7 +1710,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c /* UTF8_IS_XXXXX not right here - using constant 0x80 */ if (ch < 0x80) { bytes = 0; - PUSHs(sv_2mortal(newSVuv(auv))); + mPUSHu(auv); len--; auv = 0; continue; @@ -1983,7 +1731,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c while (*t == '0') t++; sv_chop(sv, t); - PUSHs(sv_2mortal(sv)); + mPUSHs(sv); len--; auv = 0; } @@ -2001,7 +1749,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, aptr, datumtype); DO_BO_UNPACK_PC(aptr); /* newSVpvn generates undef if aptr is NULL */ - PUSHs(sv_2mortal(newSVpvn(aptr, len))); + PUSHs(newSVpvn_flags(aptr, len, SVs_TEMP)); } break; #ifdef HAS_QUAD @@ -2011,8 +1759,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, aquad, datumtype); DO_BO_UNPACK(aquad, 64); if (!checksum) - PUSHs(sv_2mortal(aquad >= IV_MIN && aquad <= IV_MAX ? - newSViv((IV)aquad) : newSVnv((NV)aquad))); + mPUSHs(aquad >= IV_MIN && aquad <= IV_MAX ? + newSViv((IV)aquad) : newSVnv((NV)aquad)); else if (checksum > bits_in_uv) cdouble += (NV)aquad; else @@ -2025,8 +1773,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, auquad, datumtype); DO_BO_UNPACK(auquad, 64); if (!checksum) - PUSHs(sv_2mortal(auquad <= UV_MAX ? - newSVuv((UV)auquad):newSVnv((NV)auquad))); + mPUSHs(auquad <= UV_MAX ? + newSVuv((UV)auquad) : newSVnv((NV)auquad)); else if (checksum > bits_in_uv) cdouble += (NV)auquad; else @@ -2041,7 +1789,7 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, afloat, datumtype); DO_BO_UNPACK_N(afloat, float); if (!checksum) - PUSHs(sv_2mortal(newSVnv((NV)afloat))); + mPUSHn(afloat); else cdouble += afloat; } @@ -2052,37 +1800,37 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c SHIFT_VAR(utf8, s, strend, adouble, datumtype); DO_BO_UNPACK_N(adouble, double); if (!checksum) - PUSHs(sv_2mortal(newSVnv((NV)adouble))); + mPUSHn(adouble); else cdouble += adouble; } break; case 'F': while (len-- > 0) { - NV anv; - SHIFT_VAR(utf8, s, strend, anv, datumtype); - DO_BO_UNPACK_N(anv, NV); + NV_bytes anv; + SHIFT_BYTES(utf8, s, strend, anv.bytes, sizeof(anv.bytes), datumtype); + DO_BO_UNPACK_N(anv.nv, NV); if (!checksum) - PUSHs(sv_2mortal(newSVnv(anv))); + mPUSHn(anv.nv); else - cdouble += anv; + cdouble += anv.nv; } break; #if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE) case 'D': while (len-- > 0) { - long double aldouble; - SHIFT_VAR(utf8, s, strend, aldouble, datumtype); - DO_BO_UNPACK_N(aldouble, long double); + ld_bytes aldouble; + SHIFT_BYTES(utf8, s, strend, aldouble.bytes, sizeof(aldouble.bytes), datumtype); + DO_BO_UNPACK_N(aldouble.ld, long double); if (!checksum) - PUSHs(sv_2mortal(newSVnv((NV)aldouble))); + mPUSHn(aldouble.ld); else - cdouble += aldouble; + cdouble += aldouble.ld; } break; #endif case 'u': - { + if (!checksum) { const STRLEN l = (STRLEN) (strend - s) * 3 / 4; sv = sv_2mortal(newSV(l)); if (l) SvPOK_on(sv); @@ -2100,7 +1848,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c hunk[0] = (char)((a << 2) | (b >> 4)); hunk[1] = (char)((b << 4) | (c >> 2)); hunk[2] = (char)((c << 6) | d); - sv_catpvn(sv, hunk, (len > 3) ? 3 : len); + if (!checksum) + sv_catpvn(sv, hunk, (len > 3) ? 3 : len); len -= 3; } if (s < strend) { @@ -2141,7 +1890,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c hunk[0] = (char)((a << 2) | (b >> 4)); hunk[1] = (char)((b << 4) | (c >> 2)); hunk[2] = (char)((c << 6) | d); - sv_catpvn(sv, hunk, (len > 3) ? 3 : len); + if (!checksum) + sv_catpvn(sv, hunk, (len > 3) ? 3 : len); len -= 3; } if (*s == '\n') @@ -2151,7 +1901,8 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c s += 2; } } - XPUSHs(sv); + if (!checksum) + XPUSHs(sv); break; } @@ -2178,13 +1929,13 @@ S_unpack_rec(pTHX_ tempsym_t* symptr, const char *s, const char *strbeg, const c } sv = newSVuv(cuv); } - XPUSHs(sv_2mortal(sv)); + mXPUSHs(sv); checksum = 0; } if (symptr->flags & FLAG_SLASH){ if (SP - PL_stack_base - start_sp_offset <= 0) - Perl_croak(aTHX_ "'/' must follow a numeric type in unpack"); + break; if( next_symbol(symptr) ){ if( symptr->howlen == e_number ) Perl_croak(aTHX_ "Count after length/code in unpack" ); @@ -2269,6 +2020,8 @@ S_is_an_int(pTHX_ const char *s, STRLEN l) bool skip = 1; bool ignore = 0; + PERL_ARGS_ASSERT_IS_AN_INT; + while (*s) { switch (*s) { case ' ': @@ -2317,6 +2070,8 @@ S_div128(pTHX_ SV *pnum, bool *done) char *t = s; int m = 0; + PERL_ARGS_ASSERT_DIV128; + *done = 1; while (*t) { const int i = m * 10 + (*t - '0'); @@ -2341,11 +2096,13 @@ The engine implementing pack() Perl function. */ void -Perl_packlist(pTHX_ SV *cat, const char *pat, const char *patend, register SV **beglist, SV **endlist ) +Perl_packlist(pTHX_ SV *cat, const char *pat, const char *patend, SV **beglist, SV **endlist ) { dVAR; tempsym_t sym; + PERL_ARGS_ASSERT_PACKLIST; + TEMPSYM_INIT(&sym, pat, patend, FLAG_PACK); /* We're going to do changes through SvPVX(cat). Make sure it's valid. @@ -2399,7 +2156,8 @@ marked_upgrade(pTHX_ SV *sv, tempsym_t *sym_ptr) { if (m != marks + sym_ptr->level+1) { Safefree(marks); Safefree(to_start); - Perl_croak(aTHX_ "Assertion: marks beyond string end"); + Perl_croak(aTHX_ "panic: marks beyond string end, m=%p, marks=%p, " + "level=%d", m, marks, sym_ptr->level); } for (group=sym_ptr; group; group = group->previous) group->strbeg = marks[group->level] - to_start; @@ -2430,6 +2188,9 @@ S_sv_exp_grow(pTHX_ SV *sv, STRLEN needed) { const STRLEN cur = SvCUR(sv); const STRLEN len = SvLEN(sv); STRLEN extend; + + PERL_ARGS_ASSERT_SV_EXP_GROW; + if (len - cur > needed) return SvPVX(sv); extend = needed > len ? needed : len; return SvGROW(sv, len+extend+1); @@ -2446,6 +2207,8 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) bool utf8 = (symptr->flags & FLAG_PARSE_UTF8) ? 1 : 0; bool warn_utf8 = ckWARN(WARN_UTF8); + PERL_ARGS_ASSERT_PACK_REC; + if (symptr->level == 0 && found && symptr->code == 'U') { marked_upgrade(aTHX_ cat, symptr); symptr->flags |= FLAG_DO_UTF8; @@ -2496,18 +2259,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) if (lookahead.howlen == e_number) count = lookahead.length; else { if (items > 0) { - if (SvGAMAGIC(*beglist)) { - /* Avoid reading the active data more than once - by copying it to a temporary. */ - STRLEN len; - const char *const pv = SvPV_const(*beglist, len); - SV *const temp = sv_2mortal(newSVpvn(pv, len)); - if (SvUTF8(*beglist)) - SvUTF8_on(temp); - *beglist = temp; - } - count = DO_UTF8(*beglist) ? - sv_len_utf8(*beglist) : sv_len(*beglist); + count = sv_len_utf8(*beglist); } else count = 0; if (lookahead.code == 'Z') count++; @@ -2533,9 +2285,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) Perl_croak(aTHX_ "'%%' may not be used in pack"); { char *from; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case '.' | TYPE_IS_SHRIEKING: -#endif case '.': if (howlen == e_star) from = start; else if (len == 0) from = cur; @@ -2548,17 +2298,11 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) fromstr = NEXTFROM; len = SvIV(fromstr); goto resize; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case '@' | TYPE_IS_SHRIEKING: -#endif case '@': from = start + symptr->strbeg; resize: -#ifdef PERL_PACK_CAN_SHRIEKSIGN if (utf8 && !(datumtype & TYPE_IS_SHRIEKING)) -#else /* PERL_PACK_CAN_SHRIEKSIGN */ - if (utf8) -#endif if (len >= 0) { while (len && from < cur) { from += UTF8SKIP(from); @@ -2728,7 +2472,9 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) GROWING(0, cat, start, cur, len); if (!uni_to_bytes(aTHX_ &aptr, end, cur, fromlen, datumtype | TYPE_IS_PACK)) - Perl_croak(aTHX_ "Perl bug: predicted utf8 length not available"); + Perl_croak(aTHX_ "panic: predicted utf8 length not available, " + "for '%c', aptr=%p end=%p cur=%p, fromlen=%"UVuf, + (int)datumtype, aptr, end, cur, (UV)fromlen); cur += fromlen; len -= fromlen; } else if (utf8) { @@ -2767,6 +2513,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) } memset(cur, datumtype == 'A' ? ' ' : '\0', len); cur += len; + SvTAINT(cat); break; } case 'B': @@ -2918,10 +2665,9 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) IV aiv; fromstr = NEXTFROM; aiv = SvIV(fromstr); - if ((-128 > aiv || aiv > 127) && - ckWARN(WARN_PACK)) - Perl_warner(aTHX_ packWARN(WARN_PACK), - "Character in 'c' format wrapped in pack"); + if ((-128 > aiv || aiv > 127)) + Perl_ck_warner(aTHX_ packWARN(WARN_PACK), + "Character in 'c' format wrapped in pack"); PUSH_BYTE(utf8, cur, (U8)(aiv & 0xff)); } break; @@ -2930,16 +2676,14 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) utf8 = (symptr->flags & FLAG_DO_UTF8) ? 1 : 0; break; } - GROWING(0, cat, start, cur, len); while (len-- > 0) { IV aiv; fromstr = NEXTFROM; aiv = SvIV(fromstr); - if ((0 > aiv || aiv > 0xff) && - ckWARN(WARN_PACK)) - Perl_warner(aTHX_ packWARN(WARN_PACK), - "Character in 'C' format wrapped in pack"); - *cur++ = (char)(aiv & 0xff); + if ((0 > aiv || aiv > 0xff)) + Perl_ck_warner(aTHX_ packWARN(WARN_PACK), + "Character in 'C' format wrapped in pack"); + PUSH_BYTE(utf8, cur, (U8)(aiv & 0xff)); } break; case 'W': { @@ -2980,9 +2724,8 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) end = start+SvLEN(cat)-UTF8_MAXLEN; goto W_utf8; } - if (ckWARN(WARN_PACK)) - Perl_warner(aTHX_ packWARN(WARN_PACK), - "Character in 'W' format wrapped in pack"); + Perl_ck_warner(aTHX_ packWARN(WARN_PACK), + "Character in 'W' format wrapped in pack"); auv &= 0xff; } if (cur >= end) { @@ -3049,20 +2792,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) NV anv; fromstr = NEXTFROM; anv = SvNV(fromstr); -#ifdef __VOS__ - /* VOS does not automatically map a floating-point overflow - during conversion from double to float into infinity, so we - do it by hand. This code should either be generalized for - any OS that needs it, or removed if and when VOS implements - posix-976 (suggestion to support mapping to infinity). - Paul.Green@stratus.com 02-04-02. */ - if (anv > FLT_MAX) - afloat = _float_constants[0]; /* single prec. inf. */ - else if (anv < -FLT_MAX) - afloat = _float_constants[0]; /* single prec. inf. */ - else afloat = (float) anv; -#else /* __VOS__ */ -# if defined(VMS) && !defined(__IEEE_FP) +# if defined(VMS) && !defined(_IEEE_FP) /* IEEE fp overflow shenanigans are unavailable on VAX and optional * on Alpha; fake it if we don't have them. */ @@ -3074,7 +2804,6 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) # else afloat = (float)anv; # endif -#endif /* __VOS__ */ DO_BO_PACK_N(afloat, float); PUSH_VAR(utf8, cur, afloat); } @@ -3085,20 +2814,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) NV anv; fromstr = NEXTFROM; anv = SvNV(fromstr); -#ifdef __VOS__ - /* VOS does not automatically map a floating-point overflow - during conversion from long double to double into infinity, - so we do it by hand. This code should either be generalized - for any OS that needs it, or removed if and when VOS - implements posix-976 (suggestion to support mapping to - infinity). Paul.Green@stratus.com 02-04-02. */ - if (anv > DBL_MAX) - adouble = _double_constants[0]; /* double prec. inf. */ - else if (anv < -DBL_MAX) - adouble = _double_constants[0]; /* double prec. inf. */ - else adouble = (double) anv; -#else /* __VOS__ */ -# if defined(VMS) && !defined(__IEEE_FP) +# if defined(VMS) && !defined(_IEEE_FP) /* IEEE fp overflow shenanigans are unavailable on VAX and optional * on Alpha; fake it if we don't have them. */ @@ -3110,39 +2826,46 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) # else adouble = (double)anv; # endif -#endif /* __VOS__ */ DO_BO_PACK_N(adouble, double); PUSH_VAR(utf8, cur, adouble); } break; case 'F': { - NV anv; + NV_bytes anv; Zero(&anv, 1, NV); /* can be long double with unused bits */ while (len-- > 0) { fromstr = NEXTFROM; - anv = SvNV(fromstr); +#ifdef __GNUC__ + /* to work round a gcc/x86 bug; don't use SvNV */ + anv.nv = sv_2nv(fromstr); +#else + anv.nv = SvNV(fromstr); +#endif DO_BO_PACK_N(anv, NV); - PUSH_VAR(utf8, cur, anv); + PUSH_BYTES(utf8, cur, anv.bytes, sizeof(anv.bytes)); } break; } #if defined(HAS_LONG_DOUBLE) && defined(USE_LONG_DOUBLE) case 'D': { - long double aldouble; + ld_bytes aldouble; /* long doubles can have unused bits, which may be nonzero */ Zero(&aldouble, 1, long double); while (len-- > 0) { fromstr = NEXTFROM; - aldouble = (long double)SvNV(fromstr); +# ifdef __GNUC__ + /* to work round a gcc/x86 bug; don't use SvNV */ + aldouble.ld = (long double)sv_2nv(fromstr); +# else + aldouble.ld = (long double)SvNV(fromstr); +# endif DO_BO_PACK_N(aldouble, long double); - PUSH_VAR(utf8, cur, aldouble); + PUSH_BYTES(utf8, cur, aldouble.bytes, sizeof(aldouble.bytes)); } break; } #endif -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'n' | TYPE_IS_SHRIEKING: -#endif case 'n': while (len-- > 0) { I16 ai16; @@ -3154,9 +2877,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) PUSH16(utf8, cur, &ai16); } break; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'v' | TYPE_IS_SHRIEKING: -#endif case 'v': while (len-- > 0) { I16 ai16; @@ -3289,7 +3010,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) goto w_string; else if (SvNOKp(fromstr)) { /* 10**NV_MAX_10_EXP is the largest power of 10 - so 10**(NV_MAX_10_EXP+1) is definately unrepresentable + so 10**(NV_MAX_10_EXP+1) is definitely unrepresentable given 10**(NV_MAX_10_EXP+1) == 128 ** x solve for x: x = (NV_MAX_10_EXP+1) * log (10) / log (128) And with that many bytes only Inf can overflow. @@ -3353,9 +3074,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) PUSH_VAR(utf8, cur, aint); } break; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'N' | TYPE_IS_SHRIEKING: -#endif case 'N': while (len-- > 0) { U32 au32; @@ -3367,9 +3086,7 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) PUSH32(utf8, cur, &au32); } break; -#ifdef PERL_PACK_CAN_SHRIEKSIGN case 'V' | TYPE_IS_SHRIEKING: -#endif case 'V': while (len-- > 0) { U32 au32; @@ -3463,9 +3180,9 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) * gone. */ if ((SvTEMP(fromstr) || (SvPADTMP(fromstr) && - !SvREADONLY(fromstr))) && ckWARN(WARN_PACK)) { - Perl_warner(aTHX_ packWARN(WARN_PACK), - "Attempt to pack pointer to temporary value"); + !SvREADONLY(fromstr)))) { + Perl_ck_warner(aTHX_ packWARN(WARN_PACK), + "Attempt to pack pointer to temporary value"); } if (SvPOK(fromstr) || SvNIOK(fromstr)) aptr = SvPV_nomg_const_nolen(fromstr); @@ -3484,16 +3201,15 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) if (len <= 2) len = 45; else len = len / 3 * 3; if (len >= 64) { - if (ckWARN(WARN_PACK)) - Perl_warner(aTHX_ packWARN(WARN_PACK), - "Field too wide in 'u' format in pack"); + Perl_ck_warner(aTHX_ packWARN(WARN_PACK), + "Field too wide in 'u' format in pack"); len = 63; } aptr = SvPV_const(fromstr, fromlen); from_utf8 = DO_UTF8(fromstr); if (from_utf8) { aend = aptr + fromlen; - fromlen = sv_len_utf8(fromstr); + fromlen = sv_len_utf8_nomg(fromstr); } else aend = NULL; /* Unused, but keep compilers happy */ GROWING(utf8, cat, start, cur, (fromlen+2) / 3 * 4 + (fromlen+len-1)/len * 2); while (fromlen > 0) { @@ -3511,7 +3227,9 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) 'u' | TYPE_IS_PACK)) { *cur = '\0'; SvCUR_set(cat, cur - start); - Perl_croak(aTHX_ "Assertion: string is shorter than advertised"); + Perl_croak(aTHX_ "panic: string is shorter than advertised, " + "aptr=%p, aend=%p, buffer=%p, todo=%ld", + aptr, aend, buffer, (long) todo); } end = doencodes(hunk, buffer, todo); } else { @@ -3537,14 +3255,14 @@ S_pack_rec(pTHX_ SV *cat, tempsym_t* symptr, SV **beglist, SV **endlist ) PP(pp_pack) { dVAR; dSP; dMARK; dORIGMARK; dTARGET; - register SV *cat = TARG; + SV *cat = TARG; STRLEN fromlen; SV *pat_sv = *++MARK; - register const char *pat = SvPV_const(pat_sv, fromlen); - register const char *patend = pat + fromlen; + const char *pat = SvPV_const(pat_sv, fromlen); + const char *patend = pat + fromlen; MARK++; - sv_setpvn(cat, "", 0); + sv_setpvs(cat, ""); SvUTF8_off(cat); packlist(cat, pat, patend, MARK, SP + 1); @@ -3559,8 +3277,8 @@ PP(pp_pack) * Local variables: * c-indentation-style: bsd * c-basic-offset: 4 - * indent-tabs-mode: t + * indent-tabs-mode: nil * End: * - * ex: set ts=8 sts=4 sw=4 noet: + * ex: set ts=8 sts=4 sw=4 et: */