Python字典对象实现原理详解

>>> d = {'a': 1, 'b': 2}
>>> d['c'] = 3
>>> d
{'a': 1, 'b': 2, 'c': 3}

typedef struct {
/* Cached hash code of me_key. Note that hash codes are C longs.
* We have to use Py_ssize_t instead because dict_popitem() abuses
* me_hash to hold a search finger.
*/
Py_ssize_t me_hash;
PyObject *me_key;
PyObject *me_value;
} PyDictEntry;

typedef struct _dictobject PyDictObject;
struct _dictobject {
PyObject_HEAD
Py_ssize_t ma_fill; /* # Active + # Dummy */
Py_ssize_t ma_used; /* # Active */
/* The table contains ma_mask + 1 slots, and that's a power of 2.
* We store the mask instead of the size because the mask is more
* frequently needed.
*/
Py_ssize_t ma_mask;
/* ma_table points to ma_smalltable for small tables, else to
* additional malloc'ed memory. ma_table is never NULL! This rule
* saves repeated runtime null-tests in the workhorse getitem and
* setitem calls.
*/
PyDictEntry *ma_table;
PyDictEntry *(*ma_lookup)(PyDictObject *mp, PyObject *key, long hash);
PyDictEntry ma_smalltable[PyDict_MINSIZE];
};

PyObject *
PyDict_New(void)
{
register PyDictObject *mp;
if (dummy == NULL) { /* Auto-initialize dummy */
dummy = PyString_FromString("<dummy key>");
if (dummy == NULL)
return NULL;
}
if (numfree) {
mp = free_list[--numfree];
assert (mp != NULL);
assert (Py_TYPE(mp) == &PyDict_Type);
_Py_NewReference((PyObject *)mp);
if (mp->ma_fill) {
EMPTY_TO_MINSIZE(mp);
} else {
/* At least set ma_table and ma_mask; these are wrong
if an empty but presized dict is added to freelist */
INIT_NONZERO_DICT_SLOTS(mp);
}
assert (mp->ma_used == 0);
assert (mp->ma_table == mp->ma_smalltable);
assert (mp->ma_mask == PyDict_MINSIZE - 1);
} else {
mp = PyObject_GC_New(PyDictObject, &PyDict_Type);
if (mp == NULL)
return NULL;
EMPTY_TO_MINSIZE(mp);
}
mp->ma_lookup = lookdict_string;
return (PyObject *)mp;
}

static PyDictEntry *
lookdict(PyDictObject *mp, PyObject *key, register long hash)
{
register size_t i;
register size_t perturb;
register PyDictEntry *freeslot;
register size_t mask = (size_t)mp->ma_mask;
PyDictEntry *ep0 = mp->ma_table;
register PyDictEntry *ep;
register int cmp;
PyObject *startkey;

i = (size_t)hash & mask;
ep = &ep0[i];
if (ep->me_key == NULL || ep->me_key == key)
return ep;

if (ep->me_key == dummy)
freeslot = ep;
else {
if (ep->me_hash == hash) {
startkey = ep->me_key;
Py_INCREF(startkey);
cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
Py_DECREF(startkey);
if (cmp < 0)
return NULL;
if (ep0 == mp->ma_table && ep->me_key == startkey) {
if (cmp > 0)
return ep;
}
else {
/* The compare did major nasty stuff to the
* dict: start over.
* XXX A clever adversary could prevent this
* XXX from terminating.
*/
return lookdict(mp, key, hash);
}
}
freeslot = NULL;
}

/* In the loop, me_key == dummy is by far (factor of 100s) the
least likely outcome, so test for that last. */
for (perturb = hash; ; perturb >>= PERTURB_SHIFT) {
i = (i << 2) + i + perturb + 1;
ep = &ep0[i & mask];
if (ep->me_key == NULL)
return freeslot == NULL ? ep : freeslot;
if (ep->me_key == key)
return ep;
if (ep->me_hash == hash && ep->me_key != dummy) {
startkey = ep->me_key;
Py_INCREF(startkey);
cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
Py_DECREF(startkey);
if (cmp < 0)
return NULL;
if (ep0 == mp->ma_table && ep->me_key == startkey) {
if (cmp > 0)
return ep;
}
else {
/* The compare did major nasty stuff to the
* dict: start over.
* XXX A clever adversary could prevent this
* XXX from terminating.
*/
return lookdict(mp, key, hash);
}
}
else if (ep->me_key == dummy && freeslot == NULL)
freeslot = ep;
}
assert(0); /* NOT REACHED */
return 0;
}

static void
dict_dealloc(register PyDictObject *mp)
{
register PyDictEntry *ep;
Py_ssize_t fill = mp->ma_fill;
PyObject_GC_UnTrack(mp);
Py_TRASHCAN_SAFE_BEGIN(mp)
for (ep = mp->ma_table; fill > 0; ep++) {
if (ep->me_key) {
--fill;
Py_DECREF(ep->me_key);
Py_XDECREF(ep->me_value);
}
}
if (mp->ma_table != mp->ma_smalltable)
PyMem_DEL(mp->ma_table);
if (numfree < PyDict_MAXFREELIST && Py_TYPE(mp) == &PyDict_Type)
free_list[numfree++] = mp;
else
Py_TYPE(mp)->tp_free((PyObject *)mp);
Py_TRASHCAN_SAFE_END(mp)
}