X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=hv.h;h=16b14828e2a9c3b568cd5e288c84503085104cc1;hb=abc0a0153433fe6596e1ca3a6b5572dc424d0f11;hp=08f3bed7d5b63c79e076a74b77b84840b068e024;hpb=5cbe4eec85fac3e4bdde4a7b730b88994a9df29e;p=p5sagit%2Fp5-mst-13.2.git diff --git a/hv.h b/hv.h index 08f3bed..16b1482 100644 --- a/hv.h +++ b/hv.h @@ -1,6 +1,6 @@ /* hv.h * - * Copyright (c) 1991-2000, Larry Wall + * Copyright (c) 1991-2002, Larry Wall * * You may distribute under the terms of either the GNU General Public * License or the Artistic License, as specified in the README file. @@ -23,6 +23,9 @@ struct hek { U32 hek_hash; /* hash of key */ I32 hek_len; /* length of hash key */ char hek_key[1]; /* variable-length hash key */ + /* the hash-key is \0-terminated */ + /* after the \0 there is a byte for flags, such as whether the key is + UTF8 */ }; /* hash structure: */ @@ -33,6 +36,7 @@ struct xpvhv { STRLEN xhv_max; /* subscript of last element of xhv_array */ IV xhv_keys; /* how many elements in the array */ NV xnv_nv; /* numeric value, if any */ +#define xhv_placeholders xnv_nv MAGIC* xmg_magic; /* magic for scalar array */ HV* xmg_stash; /* class package */ @@ -43,25 +47,46 @@ struct xpvhv { }; /* hash a key */ +/* FYI: This is the "One-at-a-Time" algorithm by Bob Jenkins + * from requirements by Colin Plumb. + * (http://burtleburtle.net/bob/hash/doobs.html) */ +/* The use of a temporary pointer and the casting games + * is needed to serve the dual purposes of + * (a) the hashed data being interpreted as "unsigned char" (new since 5.8, + * a "char" can be either signed or signed, depending on the compiler) + * (b) catering for old code that uses a "char" + */ #define PERL_HASH(hash,str,len) \ STMT_START { \ - register const char *s_PeRlHaSh = str; \ + register const char *s_PeRlHaSh_tmp = str; \ + register const unsigned char *s_PeRlHaSh = (const unsigned char *)s_PeRlHaSh_tmp; \ register I32 i_PeRlHaSh = len; \ register U32 hash_PeRlHaSh = 0; \ - while (i_PeRlHaSh--) \ - hash_PeRlHaSh = hash_PeRlHaSh * 33 + *s_PeRlHaSh++; \ - (hash) = hash_PeRlHaSh + (hash_PeRlHaSh>>5); \ + while (i_PeRlHaSh--) { \ + hash_PeRlHaSh += *s_PeRlHaSh++; \ + hash_PeRlHaSh += (hash_PeRlHaSh << 10); \ + hash_PeRlHaSh ^= (hash_PeRlHaSh >> 6); \ + } \ + hash_PeRlHaSh += (hash_PeRlHaSh << 3); \ + hash_PeRlHaSh ^= (hash_PeRlHaSh >> 11); \ + (hash) = (hash_PeRlHaSh + (hash_PeRlHaSh << 15)); \ } STMT_END /* +=head1 Hash Manipulation Functions + =for apidoc AmU||HEf_SVKEY This flag, used in the length slot of hash entries and magic structures, -specifies the structure contains a C pointer where a C pointer +specifies the structure contains an C pointer where a C pointer is to be expected. (For information only--not to be used). +=head1 Handy Values + =for apidoc AmU||Nullhv Null HV pointer. +=head1 Hash Manipulation Functions + =for apidoc Am|char*|HvNAME|HV* stash Returns the package name of a stash. See C, C. @@ -111,23 +136,52 @@ C. */ /* these hash entry flags ride on hent_klen (for use only in magic/tied HVs) */ -#define HEf_SVKEY -2 /* hent_key is a SV* */ +#define HEf_SVKEY -2 /* hent_key is an SV* */ #define Nullhv Null(HV*) -#define HvARRAY(hv) ((HE**)((XPVHV*) SvANY(hv))->xhv_array) +#define HvARRAY(hv) (*(HE***)&((XPVHV*) SvANY(hv))->xhv_array) #define HvFILL(hv) ((XPVHV*) SvANY(hv))->xhv_fill #define HvMAX(hv) ((XPVHV*) SvANY(hv))->xhv_max -#define HvKEYS(hv) ((XPVHV*) SvANY(hv))->xhv_keys #define HvRITER(hv) ((XPVHV*) SvANY(hv))->xhv_riter #define HvEITER(hv) ((XPVHV*) SvANY(hv))->xhv_eiter #define HvPMROOT(hv) ((XPVHV*) SvANY(hv))->xhv_pmroot #define HvNAME(hv) ((XPVHV*) SvANY(hv))->xhv_name +/* the number of keys (including any placeholers) */ +#define XHvTOTALKEYS(xhv) ((xhv)->xhv_keys) + +/* The number of placeholders in the enumerated-keys hash */ +#define XHvPLACEHOLDERS(xhv) ((xhv)->xhv_placeholders) + +/* the number of keys that exist() (i.e. excluding placeholders) */ +#define XHvUSEDKEYS(xhv) (XHvTOTALKEYS(xhv) - (IV)XHvPLACEHOLDERS(xhv)) + +/* + * HvKEYS gets the number of keys that actually exist(), and is provided + * for backwards compatibility with old XS code. The core uses HvUSEDKEYS + * (keys, excluding placeholdes) and HvTOTALKEYS (including placeholders) + */ +#define HvKEYS(hv) XHvUSEDKEYS((XPVHV*) SvANY(hv)) +#define HvUSEDKEYS(hv) XHvUSEDKEYS((XPVHV*) SvANY(hv)) +#define HvTOTALKEYS(hv) XHvTOTALKEYS((XPVHV*) SvANY(hv)) +#define HvPLACEHOLDERS(hv) XHvPLACEHOLDERS((XPVHV*) SvANY(hv)) + #define HvSHAREKEYS(hv) (SvFLAGS(hv) & SVphv_SHAREKEYS) #define HvSHAREKEYS_on(hv) (SvFLAGS(hv) |= SVphv_SHAREKEYS) #define HvSHAREKEYS_off(hv) (SvFLAGS(hv) &= ~SVphv_SHAREKEYS) +/* This is an optimisation flag. It won't be set if all hash keys have a 0 + * flag. Currently the only flags relate to utf8. + * Hence it won't be set if all keys are 8 bit only. It will be set if any key + * is utf8 (including 8 bit keys that were entered as utf8, and need upgrading + * when retrieved during iteration. It may still be set when there are no longer + * any utf8 keys. + */ +#define HvHASKFLAGS(hv) (SvFLAGS(hv) & SVphv_HASKFLAGS) +#define HvHASKFLAGS_on(hv) (SvFLAGS(hv) |= SVphv_HASKFLAGS) +#define HvHASKFLAGS_off(hv) (SvFLAGS(hv) &= ~SVphv_HASKFLAGS) + #define HvLAZYDEL(hv) (SvFLAGS(hv) & SVphv_LAZYDEL) #define HvLAZYDEL_on(hv) (SvFLAGS(hv) |= SVphv_LAZYDEL) #define HvLAZYDEL_off(hv) (SvFLAGS(hv) &= ~SVphv_LAZYDEL) @@ -151,6 +205,10 @@ C. #define HeKEY(he) HEK_KEY(HeKEY_hek(he)) #define HeKEY_sv(he) (*(SV**)HeKEY(he)) #define HeKLEN(he) HEK_LEN(HeKEY_hek(he)) +#define HeKUTF8(he) HEK_UTF8(HeKEY_hek(he)) +#define HeKWASUTF8(he) HEK_WASUTF8(HeKEY_hek(he)) +#define HeKLEN_UTF8(he) (HeKUTF8(he) ? -HeKLEN(he) : HeKLEN(he)) +#define HeKFLAGS(he) HEK_FLAGS(HeKEY_hek(he)) #define HeVAL(he) (he)->hent_val #define HeHASH(he) HEK_HASH(HeKEY_hek(he)) #define HePV(he,lp) ((HeKLEN(he) == HEf_SVKEY) ? \ @@ -175,6 +233,21 @@ C. #define HEK_HASH(hek) (hek)->hek_hash #define HEK_LEN(hek) (hek)->hek_len #define HEK_KEY(hek) (hek)->hek_key +#define HEK_FLAGS(hek) (*((unsigned char *)(HEK_KEY(hek))+HEK_LEN(hek)+1)) + +#define HVhek_UTF8 0x01 /* Key is utf8 encoded. */ +#define HVhek_WASUTF8 0x02 /* Key is bytes here, but was supplied as utf8. */ +#define HVhek_FREEKEY 0x100 /* Internal flag to say key is malloc()ed. */ +#define HVhek_PLACEHOLD 0x200 /* Internal flag to create placeholder. + * (may change, but Storable is a core module) */ +#define HVhek_MASK 0xFF + +#define HEK_UTF8(hek) (HEK_FLAGS(hek) & HVhek_UTF8) +#define HEK_UTF8_on(hek) (HEK_FLAGS(hek) |= HVhek_UTF8) +#define HEK_UTF8_off(hek) (HEK_FLAGS(hek) &= ~HVhek_UTF8) +#define HEK_WASUTF8(hek) (HEK_FLAGS(hek) & HVhek_WASUTF8) +#define HEK_WASUTF8_on(hek) (HEK_FLAGS(hek) |= HVhek_WASUTF8) +#define HEK_WASUTF8_off(hek) (HEK_FLAGS(hek) &= ~HVhek_WASUTF8) /* calculate HV array allocation */ #if defined(STRANGE_MALLOC) || defined(MYMALLOC) @@ -186,3 +259,10 @@ C. ? (size) * sizeof(HE*) \ : (size) * sizeof(HE*) * 2 - MALLOC_OVERHEAD) #endif + +/* Flags for hv_iternext_flags. */ +#define HV_ITERNEXT_WANTPLACEHOLDERS 0x01 /* Don't skip placeholders. */ + +/* available as a function in hv.c */ +#define Perl_sharepvn(sv, len, hash) HEK_KEY(share_hek(sv, len, hash)) +#define sharepvn(sv, len, hash) Perl_sharepvn(sv, len, hash)