/* ** $Id: ltable.c,v 2.32.1.2 2007/12/28 15:32:23 roberto Exp $ ** Lua tables (hash) ** See Copyright Notice in lua.h */ /* ** Implementation of tables (aka arrays, objects, or hash tables). ** Tables keep its elements in two parts: an array part and a hash part. ** Non-negative integer keys are all candidates to be kept in the array ** part. The actual size of the array is the largest `n' such that at ** least half the slots between 0 and n are in use. ** Hash uses a mix of chained scatter table with Brent's variation. ** A main invariant of these tables is that, if an element is not ** in its main position (i.e. the `original' position that its hash gives ** to it), then the colliding element is in its own main position. ** Hence even when the load factor reaches 100%, performance remains good. */ #define ltable_c #define LUA_CORE #define LUAC_CROSS_FILE #include "lua.h" #include C_HEADER_MATH #include C_HEADER_STRING #include "ldebug.h" #include "ldo.h" #include "lgc.h" #include "lmem.h" #include "lobject.h" #include "lstate.h" #include "ltable.h" #include "lrotable.h" /* ** max size of array part is 2^MAXBITS */ #if LUAI_BITSINT > 26 #define MAXBITS 26 #else #define MAXBITS (LUAI_BITSINT-2) #endif #define MAXASIZE (1 << MAXBITS) #define hashpow2(t,n) (gnode(t, lmod((n), sizenode(t)))) #define hashstr(t,str) hashpow2(t, (str)->tsv.hash) #define hashboolean(t,p) hashpow2(t, p) /* ** for some types, it is better to avoid modulus by power of 2, as ** they tend to have many 2 factors. */ #define hashmod(t,n) (gnode(t, ((n) % ((sizenode(t)-1)|1)))) #define hashpointer(t,p) hashmod(t, IntPoint(p)) /* ** number of ints inside a lua_Number */ #define numints cast_int(sizeof(lua_Number)/sizeof(int)) #define dummynode (&dummynode_) static const Node dummynode_ = { {LUA_TVALUE_NIL}, /* value */ {LUA_TKEY_NIL} /* key */ }; /* ** hash for lua_Numbers */ static Node *hashnum (const Table *t, lua_Number n) { unsigned int a[numints]; int i; if (luai_numeq(n, 0)) /* avoid problems with -0 */ return gnode(t, 0); c_memcpy(a, &n, sizeof(a)); for (i = 1; i < numints; i++) a[0] += a[i]; return hashmod(t, a[0]); } /* ** returns the `main' position of an element in a table (that is, the index ** of its hash value) */ static Node *mainposition (const Table *t, const TValue *key) { switch (ttype(key)) { case LUA_TNUMBER: return hashnum(t, nvalue(key)); case LUA_TSTRING: return hashstr(t, rawtsvalue(key)); case LUA_TBOOLEAN: return hashboolean(t, bvalue(key)); case LUA_TROTABLE: return hashpointer(t, rvalue(key)); case LUA_TLIGHTUSERDATA: case LUA_TLIGHTFUNCTION: return hashpointer(t, pvalue(key)); default: return hashpointer(t, gcvalue(key)); } } /* ** returns the index for `key' if `key' is an appropriate key to live in ** the array part of the table, -1 otherwise. */ static int arrayindex (const TValue *key) { if (ttisnumber(key)) { lua_Number n = nvalue(key); int k; lua_number2int(k, n); if (luai_numeq(cast_num(k), n)) return k; } return -1; /* `key' did not match some condition */ } /* ** returns the index of a `key' for table traversals. First goes all ** elements in the array part, then elements in the hash part. The ** beginning of a traversal is signalled by -1. */ static int findindex (lua_State *L, Table *t, StkId key) { int i; if (ttisnil(key)) return -1; /* first iteration */ i = arrayindex(key); if (0 < i && i <= t->sizearray) /* is `key' inside array part? */ return i-1; /* yes; that's the index (corrected to C) */ else { Node *n = mainposition(t, key); do { /* check whether `key' is somewhere in the chain */ /* key may be dead already, but it is ok to use it in `next' */ if (luaO_rawequalObj(key2tval(n), key) || (ttype(gkey(n)) == LUA_TDEADKEY && iscollectable(key) && gcvalue(gkey(n)) == gcvalue(key))) { i = cast_int(n - gnode(t, 0)); /* key index in hash table */ /* hash elements are numbered after array ones */ return i + t->sizearray; } else n = gnext(n); } while (n); luaG_runerror(L, "invalid key to " LUA_QL("next")); /* key not found */ return 0; /* to avoid warnings */ } } int luaH_next (lua_State *L, Table *t, StkId key) { int i = findindex(L, t, key); /* find original element */ for (i++; i < t->sizearray; i++) { /* try first array part */ if (!ttisnil(&t->array[i])) { /* a non-nil value? */ setnvalue(key, cast_num(i+1)); setobj2s(L, key+1, &t->array[i]); return 1; } } for (i -= t->sizearray; i < sizenode(t); i++) { /* then hash part */ if (!ttisnil(gval(gnode(t, i)))) { /* a non-nil value? */ setobj2s(L, key, key2tval(gnode(t, i))); setobj2s(L, key+1, gval(gnode(t, i))); return 1; } } return 0; /* no more elements */ } int luaH_next_ro (lua_State *L, void *t, StkId key) { luaR_next(L, t, key, key+1); return ttisnil(key) ? 0 : 1; } /* ** {============================================================= ** Rehash ** ============================================================== */ static int computesizes (int nums[], int *narray) { int i; int twotoi; /* 2^i */ int a = 0; /* number of elements smaller than 2^i */ int na = 0; /* number of elements to go to array part */ int n = 0; /* optimal size for array part */ for (i = 0, twotoi = 1; twotoi/2 < *narray; i++, twotoi *= 2) { if (nums[i] > 0) { a += nums[i]; if (a > twotoi/2) { /* more than half elements present? */ n = twotoi; /* optimal size (till now) */ na = a; /* all elements smaller than n will go to array part */ } } if (a == *narray) break; /* all elements already counted */ } *narray = n; lua_assert(*narray/2 <= na && na <= *narray); return na; } static int countint (const TValue *key, int *nums) { int k = arrayindex(key); if (0 < k && k <= MAXASIZE) { /* is `key' an appropriate array index? */ nums[ceillog2(k)]++; /* count as such */ return 1; } else return 0; } static int numusearray (const Table *t, int *nums) { int lg; int ttlg; /* 2^lg */ int ause = 0; /* summation of `nums' */ int i = 1; /* count to traverse all array keys */ for (lg=0, ttlg=1; lg<=MAXBITS; lg++, ttlg*=2) { /* for each slice */ int lc = 0; /* counter */ int lim = ttlg; if (lim > t->sizearray) { lim = t->sizearray; /* adjust upper limit */ if (i > lim) break; /* no more elements to count */ } /* count elements in range (2^(lg-1), 2^lg] */ for (; i <= lim; i++) { if (!ttisnil(&t->array[i-1])) lc++; } nums[lg] += lc; ause += lc; } return ause; } static int numusehash (const Table *t, int *nums, int *pnasize) { int totaluse = 0; /* total number of elements */ int ause = 0; /* summation of `nums' */ int i = sizenode(t); while (i--) { Node *n = &t->node[i]; if (!ttisnil(gval(n))) { ause += countint(key2tval(n), nums); totaluse++; } } *pnasize += ause; return totaluse; } static void setarrayvector (lua_State *L, Table *t, int size) { int i; luaM_reallocvector(L, t->array, t->sizearray, size, TValue); for (i=t->sizearray; iarray[i]); t->sizearray = size; } static Node *getfreepos (Table *t) { while (t->lastfree-- > t->node) { if (ttisnil(gkey(t->lastfree))) return t->lastfree; } return NULL; /* could not find a free place */ } static void resizenodevector (lua_State *L, Table *t, int oldsize, int newsize) { int lsize; if (newsize == 0) { /* no elements to hash part? */ t->node = cast(Node *, dummynode); /* use common `dummynode' */ lsize = 0; } else { Node *node = t->node; int i; lsize = ceillog2(newsize); if (lsize > MAXBITS) luaG_runerror(L, "table overflow"); newsize = twoto(lsize); if (node == dummynode) { oldsize = 0; node = NULL; /* don't try to realloc `dummynode' pointer. */ } luaM_reallocvector(L, node, oldsize, newsize, Node); t->node = node; for (i=oldsize; ilsizenode = cast_byte(lsize); t->lastfree = gnode(t, newsize); /* reset lastfree to end of table. */ } static Node *find_prev_node(Node *mp, Node *next) { Node *prev = mp; while (prev != NULL && gnext(prev) != next) prev = gnext(prev); return prev; } /* ** move a node from it's old position to it's new position during a rehash; ** first, check whether the moving node's main position is free. If not, check whether ** colliding node is in its main position or not: if it is not, move colliding ** node to an empty place and put moving node in its main position; otherwise ** (colliding node is in its main position), moving node goes to an empty position. */ static int move_node (lua_State *L, Table *t, Node *node) { Node *mp = mainposition(t, key2tval(node)); /* if node is in it's main position, don't need to move node. */ if (mp == node) return 1; /* if node is in it's main position's chain, don't need to move node. */ if (find_prev_node(mp, node) != NULL) return 1; /* is main position is free? */ if (!ttisnil(gval(mp)) || mp == dummynode) { /* no; move main position node if it is out of its main position */ Node *othermp; othermp = mainposition(t, key2tval(mp)); if (othermp != mp) { /* is colliding node out of its main position? */ /* yes; swap colliding node with the node that is being moved. */ Node *prev; Node tmp; tmp = *node; prev = find_prev_node(othermp, mp); /* find previous */ if (prev != NULL) gnext(prev) = node; /* redo the chain with `n' in place of `mp' */ *node = *mp; /* copy colliding node into free pos. (mp->next also goes) */ *mp = tmp; return (prev != NULL) ? 1 : 0; /* is colliding node part of its main position chain? */ } else { /* colliding node is in its own main position */ /* add node to main position's chain. */ gnext(node) = gnext(mp); /* chain new position */ gnext(mp) = node; } } else { /* main position is free, move node */ *mp = *node; gnext(node) = NULL; setnilvalue(gkey(node)); setnilvalue(gval(node)); } return 1; } static int move_number (lua_State *L, Table *t, Node *node) { int key; lua_Number n = nvalue(key2tval(node)); lua_number2int(key, n); if (luai_numeq(cast_num(key), nvalue(key2tval(node)))) {/* index is int? */ /* (1 <= key && key <= t->sizearray) */ if (cast(unsigned int, key-1) < cast(unsigned int, t->sizearray)) { setobjt2t(L, &t->array[key-1], gval(node)); setnilvalue(gkey(node)); setnilvalue(gval(node)); return 1; } } return 0; } static void resize_hashpart (lua_State *L, Table *t, int nhsize) { int i; int lsize=0; int oldhsize = (t->node != dummynode) ? twoto(t->lsizenode) : 0; if (nhsize > 0) { /* round new hashpart size up to next power of two. */ lsize=ceillog2(nhsize); if (lsize > MAXBITS) luaG_runerror(L, "table overflow"); } nhsize = twoto(lsize); /* grow hash part to new size. */ if (oldhsize < nhsize) resizenodevector(L, t, oldhsize, nhsize); else { /* hash part might be shrinking */ if (nhsize > 0) { t->lsizenode = cast_byte(lsize); t->lastfree = gnode(t, nhsize); /* reset lastfree back to end of table. */ } else { /* new hashpart size is zero. */ resizenodevector(L, t, oldhsize, nhsize); return; } } /* break old chains, try moving int keys to array part and compact keys into new hashpart */ for (i = 0; i < oldhsize; i++) { Node *old = gnode(t, i); gnext(old) = NULL; if (ttisnil(gval(old))) { /* clear nodes with nil values. */ setnilvalue(gkey(old)); continue; } if (ttisnumber(key2tval(old))) { /* try moving the int keys into array part. */ if(move_number(L, t, old)) continue; } if (i >= nhsize) { /* move all valid keys to indices < nhsize. */ Node *n = getfreepos(t); /* get a free place */ lua_assert(n != dummynode && n != NULL); *n = *old; } } /* shrink hash part */ if (oldhsize > nhsize) resizenodevector(L, t, oldhsize, nhsize); /* move nodes to their new mainposition and re-create node chains */ for (i = 0; i < nhsize; i++) { Node *curr = gnode(t, i); if (!ttisnil(gval(curr))) while (move_node(L, t, curr) == 0); } } static void resize (lua_State *L, Table *t, int nasize, int nhsize) { int i; int oldasize = t->sizearray; if (nasize > oldasize) /* array part must grow? */ setarrayvector(L, t, nasize); if (t->node != dummynode || nhsize>0) resize_hashpart(L, t, nhsize); if (nasize < oldasize) { /* array part must shrink? */ t->sizearray = nasize; /* re-insert elements from vanishing slice */ for (i=nasize; iarray[i])) setobjt2t(L, luaH_setnum(L, t, i+1), &t->array[i]); } /* shrink array */ luaM_reallocvector(L, t->array, oldasize, nasize, TValue); } } void luaH_resizearray (lua_State *L, Table *t, int nasize) { int nsize = (t->node == dummynode) ? 0 : sizenode(t); resize(L, t, nasize, nsize); } static void rehash (lua_State *L, Table *t, const TValue *ek) { int nasize, na; int nums[MAXBITS+1]; /* nums[i] = number of keys between 2^(i-1) and 2^i */ int i; int totaluse; for (i=0; i<=MAXBITS; i++) nums[i] = 0; /* reset counts */ nasize = numusearray(t, nums); /* count keys in array part */ totaluse = nasize; /* all those keys are integer keys */ totaluse += numusehash(t, nums, &nasize); /* count keys in hash part */ /* count extra key */ nasize += countint(ek, nums); totaluse++; /* compute new size for array part */ na = computesizes(nums, &nasize); /* resize the table to new computed sizes */ resize(L, t, nasize, totaluse - na); } /* ** }============================================================= */ Table *luaH_new (lua_State *L, int narray, int nhash) { Table *t = luaM_new(L, Table); luaC_link(L, obj2gco(t), LUA_TTABLE); sethvalue2s(L, L->top, t); /* put table on stack */ incr_top(L); t->metatable = NULL; t->flags = cast_byte(~0); /* temporary values (kept only if some malloc fails) */ t->array = NULL; t->sizearray = 0; t->lsizenode = 0; t->node = cast(Node *, dummynode); setarrayvector(L, t, narray); resizenodevector(L, t, 0, nhash); L->top--; /* remove table from stack */ return t; } void luaH_free (lua_State *L, Table *t) { if (t->node != dummynode) luaM_freearray(L, t->node, sizenode(t), Node); luaM_freearray(L, t->array, t->sizearray, TValue); luaM_free(L, t); } /* ** inserts a new key into a hash table; first, check whether key's main ** position is free. If not, check whether colliding node is in its main ** position or not: if it is not, move colliding node to an empty place and ** put new key in its main position; otherwise (colliding node is in its main ** position), new key goes to an empty position. */ static TValue *newkey (lua_State *L, Table *t, const TValue *key) { Node *mp = mainposition(t, key); if (!ttisnil(gval(mp)) || mp == dummynode) { Node *othern; Node *n = getfreepos(t); /* get a free place */ if (n == NULL) { /* cannot find a free place? */ rehash(L, t, key); /* grow table */ return luaH_set(L, t, key); /* re-insert key into grown table */ } lua_assert(n != dummynode); othern = mainposition(t, key2tval(mp)); if (othern != mp) { /* is colliding node out of its main position? */ /* yes; move colliding node into free position */ while (gnext(othern) != mp) othern = gnext(othern); /* find previous */ gnext(othern) = n; /* redo the chain with `n' in place of `mp' */ *n = *mp; /* copy colliding node into free pos. (mp->next also goes) */ gnext(mp) = NULL; /* now `mp' is free */ setnilvalue(gval(mp)); } else { /* colliding node is in its own main position */ /* new node will go into free position */ gnext(n) = gnext(mp); /* chain new position */ gnext(mp) = n; mp = n; } } setobj2t(L, gkey(mp), key); luaC_barriert(L, t, key); lua_assert(ttisnil(gval(mp))); return gval(mp); } /* ** search function for integers */ const TValue *luaH_getnum (Table *t, int key) { /* (1 <= key && key <= t->sizearray) */ if (cast(unsigned int, key-1) < cast(unsigned int, t->sizearray)) return &t->array[key-1]; else { lua_Number nk = cast_num(key); Node *n = hashnum(t, nk); do { /* check whether `key' is somewhere in the chain */ if (ttisnumber(gkey(n)) && luai_numeq(nvalue(gkey(n)), nk)) return gval(n); /* that's it */ else n = gnext(n); } while (n); return luaO_nilobject; } } /* same thing for rotables */ const TValue *luaH_getnum_ro (void *t, int key) { const TValue *res = luaR_findentryN(t, key, NULL); return res ? res : luaO_nilobject; } /* ** search function for strings */ const TValue *luaH_getstr (Table *t, TString *key) { Node *n = hashstr(t, key); do { /* check whether `key' is somewhere in the chain */ if (ttisstring(gkey(n)) && rawtsvalue(gkey(n)) == key) return gval(n); /* that's it */ else n = gnext(n); } while (n); return luaO_nilobject; } /* same thing for rotables */ const TValue *luaH_getstr_ro (void *t, TString *key) { if (!t || key->tsv.len>LUA_MAX_ROTABLE_NAME) return luaO_nilobject; return luaR_findentry(t, key, NULL); } /* ** main search function */ const TValue *luaH_get (Table *t, const TValue *key) { switch (ttype(key)) { case LUA_TNIL: return luaO_nilobject; case LUA_TSTRING: return luaH_getstr(t, rawtsvalue(key)); case LUA_TNUMBER: { int k; lua_Number n = nvalue(key); lua_number2int(k, n); if (luai_numeq(cast_num(k), nvalue(key))) /* index is int? */ return luaH_getnum(t, k); /* use specialized version */ /* else go through */ } default: { Node *n = mainposition(t, key); do { /* check whether `key' is somewhere in the chain */ if (luaO_rawequalObj(key2tval(n), key)) return gval(n); /* that's it */ else n = gnext(n); } while (n); return luaO_nilobject; } } } /* same thing for rotables */ const TValue *luaH_get_ro (void *t, const TValue *key) { switch (ttype(key)) { case LUA_TNIL: return luaO_nilobject; case LUA_TSTRING: return luaH_getstr_ro(t, rawtsvalue(key)); case LUA_TNUMBER: { int k; lua_Number n = nvalue(key); lua_number2int(k, n); if (luai_numeq(cast_num(k), nvalue(key))) /* index is int? */ return luaH_getnum_ro(t, k); /* use specialized version */ /* else go through */ } default: { return luaO_nilobject; } } } TValue *luaH_set (lua_State *L, Table *t, const TValue *key) { const TValue *p = luaH_get(t, key); t->flags = 0; if (p != luaO_nilobject) return cast(TValue *, p); else { if (ttisnil(key)) luaG_runerror(L, "table index is nil"); else if (ttisnumber(key) && luai_numisnan(nvalue(key))) luaG_runerror(L, "table index is NaN"); return newkey(L, t, key); } } TValue *luaH_setnum (lua_State *L, Table *t, int key) { const TValue *p = luaH_getnum(t, key); if (p != luaO_nilobject) return cast(TValue *, p); else { TValue k; setnvalue(&k, cast_num(key)); return newkey(L, t, &k); } } TValue *luaH_setstr (lua_State *L, Table *t, TString *key) { const TValue *p = luaH_getstr(t, key); if (p != luaO_nilobject) return cast(TValue *, p); else { TValue k; setsvalue(L, &k, key); return newkey(L, t, &k); } } static int unbound_search (Table *t, unsigned int j) { unsigned int i = j; /* i is zero or a present index */ j++; /* find `i' and `j' such that i is present and j is not */ while (!ttisnil(luaH_getnum(t, j))) { i = j; j *= 2; if (j > cast(unsigned int, MAX_INT)) { /* overflow? */ /* table was built with bad purposes: resort to linear search */ i = 1; while (!ttisnil(luaH_getnum(t, i))) i++; return i - 1; } } /* now do a binary search between them */ while (j - i > 1) { unsigned int m = (i+j)/2; if (ttisnil(luaH_getnum(t, m))) j = m; else i = m; } return i; } /* ** Try to find a boundary in table `t'. A `boundary' is an integer index ** such that t[i] is non-nil and t[i+1] is nil (and 0 if t[1] is nil). */ int luaH_getn (Table *t) { unsigned int j = t->sizearray; if (j > 0 && ttisnil(&t->array[j - 1])) { /* there is a boundary in the array part: (binary) search for it */ unsigned int i = 0; while (j - i > 1) { unsigned int m = (i+j)/2; if (ttisnil(&t->array[m - 1])) j = m; else i = m; } return i; } /* else must find a boundary in hash part */ else if (t->node == dummynode) /* hash part is empty? */ return j; /* that is easy... */ else return unbound_search(t, j); } /* same thing for rotables */ int luaH_getn_ro (void *t) { int i = 1, len=0; while(luaR_findentryN(t, i ++, NULL)) len ++; return len; } int luaH_isdummy (Node *n) { return n == dummynode; } #if defined(LUA_DEBUG) Node *luaH_mainposition (const Table *t, const TValue *key) { return mainposition(t, key); } #endif