lua/ltable.c

/*
** $Id: ltable.c,v 2.83 2013/09/11 12:26:14 roberto Exp roberto $
** 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.
*/

#include <float.h>
#include <math.h>
#include <string.h>

#define ltable_c
#define LUA_CORE

#include "lua.h"

#include "ldebug.h"
#include "ldo.h"
#include "lgc.h"
#include "lmem.h"
#include "lobject.h"
#include "lstate.h"
#include "lstring.h"
#include "ltable.h"
#include "lvm.h"


/*
** max size of array part is 2^MAXBITS
*/
#if LUAI_BITSINT >= 32
#define MAXBITS		30
#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)
#define hashint(t,i)		hashpow2(t, i)


/*
** 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))


/* checks whether a float has a value representable as a lua_Integer
   (and does the conversion if so) */
#define numisinteger(x,i) \
	(((x) == l_floor(x)) && luaV_numtointeger(x, i))


#define dummynode		(&dummynode_)

#define isdummy(n)		((n) == dummynode)

static const Node dummynode_ = {
  {NILCONSTANT},  /* value */
  {{NILCONSTANT, 0}}  /* key */
};


/*
** hash for floating-point numbers
*/
static Node *hashfloat (const Table *t, lua_Number n) {
  int i;
  n = l_mathop(frexp)(n, &i) * cast_num(INT_MAX - DBL_MAX_EXP);
  i += cast_int(n);
  if (i < 0) {
    if (cast(unsigned int, i) == 0u - i)  /* use unsigned to avoid overflows */
      i = 0;  /* handle INT_MIN */
    i = -i;  /* must be a positive value */
  }
  return hashmod(t, i);
}



/*
** 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_TNUMINT:
      return hashint(t, ivalue(key));
    case LUA_TNUMFLT:
      return hashfloat(t, fltvalue(key));
    case LUA_TSHRSTR:
      return hashstr(t, rawtsvalue(key));
    case LUA_TLNGSTR: {
      TString *s = rawtsvalue(key);
      if (s->tsv.extra == 0) {  /* no hash? */
        s->tsv.hash = luaS_hash(getstr(s), s->tsv.len, s->tsv.hash);
        s->tsv.extra = 1;  /* now it has its hash */
      }
      return hashstr(t, rawtsvalue(key));
    }
    case LUA_TBOOLEAN:
      return hashboolean(t, bvalue(key));
    case LUA_TLIGHTUSERDATA:
      return hashpointer(t, pvalue(key));
    case LUA_TLCF:
      return hashpointer(t, fvalue(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 (ttisinteger(key)) {
    lua_Integer k = ivalue(key);
    if (0 < k && k <= MAXASIZE)  /* is `key' an appropriate array index? */
      return cast_int(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 signaled 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 {
    int nx;
    Node *n = mainposition(t, key);
    for (;;) {  /* check whether `key' is somewhere in the chain */
      /* key may be dead already, but it is ok to use it in `next' */
      if (luaV_rawequalobj(gkey(n), key) ||
            (ttisdeadkey(gkey(n)) && iscollectable(key) &&
             deadvalue(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;
      }
      nx = gnext(n);
      if (nx == 0)
        luaG_runerror(L, "invalid key to " LUA_QL("next"));  /* key not found */
      else n += nx;
    }
  }
}


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? */
      setivalue(key, 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, gkey(gnode(t, i)));
      setobj2s(L, key+1, gval(gnode(t, i)));
      return 1;
    }
  }
  return 0;  /* no more elements */
}


/*
** {=============================================================
** 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 (k > 0) {  /* is `key' an appropriate array index? */
    nums[luaO_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(gkey(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; i<size; i++)
     setnilvalue(&t->array[i]);
  t->sizearray = size;
}


static void setnodevector (lua_State *L, Table *t, int size) {
  int lsize;
  if (size == 0) {  /* no elements to hash part? */
    t->node = cast(Node *, dummynode);  /* use common `dummynode' */
    lsize = 0;
  }
  else {
    int i;
    lsize = luaO_ceillog2(size);
    if (lsize > MAXBITS)
      luaG_runerror(L, "table overflow");
    size = twoto(lsize);
    t->node = luaM_newvector(L, size, Node);
    for (i=0; i<size; i++) {
      Node *n = gnode(t, i);
      gnext(n) = 0;
      setnilvalue(gkey(n));
      setnilvalue(gval(n));
    }
  }
  t->lsizenode = cast_byte(lsize);
  t->lastfree = gnode(t, size);  /* all positions are free */
}


void luaH_resize (lua_State *L, Table *t, int nasize, int nhsize) {
  int i;
  int oldasize = t->sizearray;
  int oldhsize = t->lsizenode;
  Node *nold = t->node;  /* save old hash ... */
  if (nasize > oldasize)  /* array part must grow? */
    setarrayvector(L, t, nasize);
  /* create new hash part with appropriate size */
  setnodevector(L, t, nhsize);
  if (nasize < oldasize) {  /* array part must shrink? */
    t->sizearray = nasize;
    /* re-insert elements from vanishing slice */
    for (i=nasize; i<oldasize; i++) {
      if (!ttisnil(&t->array[i]))
        luaH_setint(L, t, i + 1, &t->array[i]);
    }
    /* shrink array */
    luaM_reallocvector(L, t->array, oldasize, nasize, TValue);
  }
  /* re-insert elements from hash part */
  for (i = twoto(oldhsize) - 1; i >= 0; i--) {
    Node *old = nold+i;
    if (!ttisnil(gval(old))) {
      /* doesn't need barrier/invalidate cache, as entry was
         already present in the table */
      setobjt2t(L, luaH_set(L, t, gkey(old)), gval(old));
    }
  }
  if (!isdummy(nold))
    luaM_freearray(L, nold, cast(size_t, twoto(oldhsize))); /* free old array */
}


void luaH_resizearray (lua_State *L, Table *t, int nasize) {
  int nsize = isdummy(t->node) ? 0 : sizenode(t);
  luaH_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 with 2^(i-1) < k <= 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 */
  luaH_resize(L, t, nasize, totaluse - na);
}



/*
** }=============================================================
*/


Table *luaH_new (lua_State *L) {
  Table *t = &luaC_newobj(L, LUA_TTABLE, sizeof(Table))->h;
  t->metatable = NULL;
  t->flags = cast_byte(~0);
  t->array = NULL;
  t->sizearray = 0;
  setnodevector(L, t, 0);
  return t;
}


void luaH_free (lua_State *L, Table *t) {
  if (!isdummy(t->node))
    luaM_freearray(L, t->node, cast(size_t, sizenode(t)));
  luaM_freearray(L, t->array, t->sizearray);
  luaM_free(L, t);
}


static Node *getfreepos (Table *t) {
  while (t->lastfree > t->node) {
    t->lastfree--;
    if (ttisnil(gkey(t->lastfree)))
      return t->lastfree;
  }
  return NULL;  /* could not find a free place */
}



/*
** 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.
*/
TValue *luaH_newkey (lua_State *L, Table *t, const TValue *key) {
  Node *mp;
  TValue aux;
  if (ttisnil(key)) luaG_runerror(L, "table index is nil");
  else if (ttisfloat(key)) {
    lua_Number n = fltvalue(key);
    lua_Integer k;
    if (luai_numisnan(n))
      luaG_runerror(L, "table index is NaN");
    if (numisinteger(n, &k)) {  /* index is int? */
      setivalue(&aux, k); 
      key = &aux;  /* insert it as an integer */
    }
  }
  mp = mainposition(t, key);
  if (!ttisnil(gval(mp)) || isdummy(mp)) {  /* main position is taken? */
    Node *othern;
    Node *f = getfreepos(t);  /* get a free place */
    if (f == NULL) {  /* cannot find a free place? */
      rehash(L, t, key);  /* grow table */
      /* whatever called 'newkey' take care of TM cache and GC barrier */
      return luaH_set(L, t, key);  /* insert key into grown table */
    }
    lua_assert(!isdummy(f));
    othern = mainposition(t, gkey(mp));
    if (othern != mp) {  /* is colliding node out of its main position? */
      /* yes; move colliding node into free position */
      while (othern + gnext(othern) != mp)  /* find previous */
        othern += gnext(othern);
      gnext(othern) = f - othern;  /* re-chain with 'f' in place of 'mp' */
      *f = *mp;  /* copy colliding node into free pos. (mp->next also goes) */
      if (gnext(mp) != 0) {
        gnext(f) += mp - f;  /* correct 'next' */
        gnext(mp) = 0;  /* now 'mp' is free */
      }
      setnilvalue(gval(mp));
    }
    else {  /* colliding node is in its own main position */
      /* new node will go into free position */
      if (gnext(mp) != 0)
        gnext(f) = (mp + gnext(mp)) - f;  /* chain new position */
      else lua_assert(gnext(f) == 0);
      gnext(mp) = f - mp;
      mp = f;
    }
  }
  setobj2t(L, gkey(mp), key);
  luaC_barrierback(L, t, key);
  lua_assert(ttisnil(gval(mp)));
  return gval(mp);
}


/*
** search function for integers
*/
const TValue *luaH_getint (Table *t, lua_Integer key) {
  /* (1 <= key && key <= t->sizearray) */
  if (cast_unsigned(key - 1) < cast_unsigned(t->sizearray))
    return &t->array[key - 1];
  else {
    Node *n = hashint(t, key);
    for (;;) {  /* check whether `key' is somewhere in the chain */
      if (ttisinteger(gkey(n)) && ivalue(gkey(n)) == key)
        return gval(n);  /* that's it */
      else {
        int nx = gnext(n);
        if (nx == 0) break;
        n += nx;
      }
    };
    return luaO_nilobject;
  }
}


/*
** search function for short strings
*/
const TValue *luaH_getstr (Table *t, TString *key) {
  Node *n = hashstr(t, key);
  lua_assert(key->tsv.tt == LUA_TSHRSTR);
  for (;;) {  /* check whether `key' is somewhere in the chain */
    if (ttisshrstring(gkey(n)) && eqshrstr(rawtsvalue(gkey(n)), key))
      return gval(n);  /* that's it */
    else {
      int nx = gnext(n);
      if (nx == 0) break;
      n += nx;
    }
  };
  return luaO_nilobject;
}


/*
** main search function
*/
const TValue *luaH_get (Table *t, const TValue *key) {
  switch (ttype(key)) {
    case LUA_TSHRSTR: return luaH_getstr(t, rawtsvalue(key));
    case LUA_TNUMINT: return luaH_getint(t, ivalue(key));
    case LUA_TNIL: return luaO_nilobject;
    case LUA_TNUMFLT: {
      lua_Integer k;
      if (numisinteger(fltvalue(key), &k)) /* index is int? */
        return luaH_getint(t, k);  /* use specialized version */
      /* else go through */
    }
    default: {
      Node *n = mainposition(t, key);
      for (;;) {  /* check whether `key' is somewhere in the chain */
        if (luaV_rawequalobj(gkey(n), key))
          return gval(n);  /* that's it */
        else {
          int nx = gnext(n);
          if (nx == 0) break;
          n += nx;
        }
      };
      return luaO_nilobject;
    }
  }
}


/*
** beware: when using this function you probably need to check a GC
** barrier and invalidate the TM cache.
*/
TValue *luaH_set (lua_State *L, Table *t, const TValue *key) {
  const TValue *p = luaH_get(t, key);
  if (p != luaO_nilobject)
    return cast(TValue *, p);
  else return luaH_newkey(L, t, key);
}


void luaH_setint (lua_State *L, Table *t, lua_Integer key, TValue *value) {
  const TValue *p = luaH_getint(t, key);
  TValue *cell;
  if (p != luaO_nilobject)
    cell = cast(TValue *, p);
  else {
    TValue k;
    setivalue(&k, key);
    cell = luaH_newkey(L, t, &k);
  }
  setobj2t(L, cell, value);
}


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_getint(t, j))) {
    i = j;
    if (j > cast(unsigned int, MAX_INT)/2) {  /* overflow? */
      /* table was built with bad purposes: resort to linear search */
      i = 1;
      while (!ttisnil(luaH_getint(t, i))) i++;
      return i - 1;
    }
    j *= 2;
  }
  /* now do a binary search between them */
  while (j - i > 1) {
    unsigned int m = (i+j)/2;
    if (ttisnil(luaH_getint(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 (isdummy(t->node))  /* hash part is empty? */
    return j;  /* that is easy... */
  else return unbound_search(t, j);
}



#if defined(LUA_DEBUG)

Node *luaH_mainposition (const Table *t, const TValue *key) {
  return mainposition(t, key);
}

int luaH_isdummy (Node *n) { return isdummy(n); }

#endif