summaryrefslogtreecommitdiffstats
path: root/Include/dictobject.h
diff options
context:
space:
mode:
Diffstat (limited to 'Include/dictobject.h')
-rw-r--r--Include/dictobject.h136
1 files changed, 101 insertions, 35 deletions
diff --git a/Include/dictobject.h b/Include/dictobject.h
index b37573a..5a1e9fe 100644
--- a/Include/dictobject.h
+++ b/Include/dictobject.h
@@ -4,6 +4,7 @@
extern "C" {
#endif
+
/* Dictionary object type -- mapping from hashable object to object */
/* The distribution includes a separate file, Objects/dictnotes.txt,
@@ -12,26 +13,121 @@ extern "C" {
tuning dictionaries, and several ideas for possible optimizations.
*/
+/*
+There are three kinds of slots in the table:
+
+1. Unused. me_key == me_value == NULL
+ Does not hold an active (key, value) pair now and never did. Unused can
+ transition to Active upon key insertion. This is the only case in which
+ me_key is NULL, and is each slot's initial state.
+
+2. Active. me_key != NULL and me_key != dummy and me_value != NULL
+ Holds an active (key, value) pair. Active can transition to Dummy upon
+ key deletion. This is the only case in which me_value != NULL.
+
+3. Dummy. me_key == dummy and me_value == NULL
+ Previously held an active (key, value) pair, but that was deleted and an
+ active pair has not yet overwritten the slot. Dummy can transition to
+ Active upon key insertion. Dummy slots cannot be made Unused again
+ (cannot have me_key set to NULL), else the probe sequence in case of
+ collision would have no way to know they were once active.
+
+Note: .popitem() abuses the me_hash field of an Unused or Dummy slot to
+hold a search finger. The me_hash field of Unused or Dummy slots has no
+meaning otherwise.
+*/
+
+/* PyDict_MINSIZE is the minimum size of a dictionary. This many slots are
+ * allocated directly in the dict object (in the ma_smalltable member).
+ * It must be a power of 2, and at least 4. 8 allows dicts with no more
+ * than 5 active entries to live in ma_smalltable (and so avoid an
+ * additional malloc); instrumentation suggested this suffices for the
+ * majority of dicts (consisting mostly of usually-small instance dicts and
+ * usually-small dicts created to pass keyword arguments).
+ */
+#define PyDict_MINSIZE 8
+
+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;
+
+/*
+To ensure the lookup algorithm terminates, there must be at least one Unused
+slot (NULL key) in the table.
+The value ma_fill is the number of non-NULL keys (sum of Active and Dummy);
+ma_used is the number of non-NULL, non-dummy keys (== the number of non-NULL
+values == the number of Active items).
+To avoid slowing down lookups on a near-full table, we resize the table when
+it's two-thirds full.
+*/
+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];
+};
+
PyAPI_DATA(PyTypeObject) PyDict_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterKey_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterValue_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterItem_Type;
+PyAPI_DATA(PyTypeObject) PyDictKeys_Type;
+PyAPI_DATA(PyTypeObject) PyDictItems_Type;
+PyAPI_DATA(PyTypeObject) PyDictValues_Type;
#define PyDict_Check(op) \
PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_DICT_SUBCLASS)
#define PyDict_CheckExact(op) (Py_TYPE(op) == &PyDict_Type)
+#define PyDictKeys_Check(op) (Py_TYPE(op) == &PyDictKeys_Type)
+#define PyDictItems_Check(op) (Py_TYPE(op) == &PyDictItems_Type)
+#define PyDictValues_Check(op) (Py_TYPE(op) == &PyDictValues_Type)
+/* This excludes Values, since they are not sets. */
+# define PyDictViewSet_Check(op) \
+ (PyDictKeys_Check(op) || PyDictItems_Check(op))
PyAPI_FUNC(PyObject *) PyDict_New(void);
PyAPI_FUNC(PyObject *) PyDict_GetItem(PyObject *mp, PyObject *key);
-PyAPI_FUNC(PyObject *) PyDict_GetItemWithError(PyObject *mp, PyObject *key);
+PyAPI_FUNC(PyObject *) _PyDict_GetItemWithError(PyObject *mp, PyObject *key);
PyAPI_FUNC(int) PyDict_SetItem(PyObject *mp, PyObject *key, PyObject *item);
PyAPI_FUNC(int) PyDict_DelItem(PyObject *mp, PyObject *key);
+PyAPI_FUNC(int) _PyDict_DelItemIf(PyObject *mp, PyObject *key,
+ int (*predicate)(PyObject *value));
+
PyAPI_FUNC(void) PyDict_Clear(PyObject *mp);
PyAPI_FUNC(int) PyDict_Next(
PyObject *mp, Py_ssize_t *pos, PyObject **key, PyObject **value);
+PyAPI_FUNC(int) _PyDict_Next(
+ PyObject *mp, Py_ssize_t *pos, PyObject **key, PyObject **value, long *hash);
PyAPI_FUNC(PyObject *) PyDict_Keys(PyObject *mp);
PyAPI_FUNC(PyObject *) PyDict_Values(PyObject *mp);
PyAPI_FUNC(PyObject *) PyDict_Items(PyObject *mp);
PyAPI_FUNC(Py_ssize_t) PyDict_Size(PyObject *mp);
PyAPI_FUNC(PyObject *) PyDict_Copy(PyObject *mp);
PyAPI_FUNC(int) PyDict_Contains(PyObject *mp, PyObject *key);
+PyAPI_FUNC(int) _PyDict_Contains(PyObject *mp, PyObject *key, long hash);
+PyAPI_FUNC(PyObject *) _PyDict_NewPresized(Py_ssize_t minused);
+PyAPI_FUNC(void) _PyDict_MaybeUntrack(PyObject *mp);
/* PyDict_Update(mp, other) is equivalent to PyDict_Merge(mp, other, 1). */
PyAPI_FUNC(int) PyDict_Update(PyObject *mp, PyObject *other);
@@ -42,8 +138,8 @@ PyAPI_FUNC(int) PyDict_Update(PyObject *mp, PyObject *other);
dict.update(other) is equivalent to PyDict_Merge(dict, other, 1).
*/
PyAPI_FUNC(int) PyDict_Merge(PyObject *mp,
- PyObject *other,
- int override);
+ PyObject *other,
+ int override);
/* PyDict_MergeFromSeq2 updates/merges from an iterable object producing
iterable objects of length 2. If override is true, the last occurrence
@@ -51,43 +147,13 @@ PyAPI_FUNC(int) PyDict_Merge(PyObject *mp,
is equivalent to dict={}; PyDict_MergeFromSeq(dict, seq2, 1).
*/
PyAPI_FUNC(int) PyDict_MergeFromSeq2(PyObject *d,
- PyObject *seq2,
- int override);
+ PyObject *seq2,
+ int override);
PyAPI_FUNC(PyObject *) PyDict_GetItemString(PyObject *dp, const char *key);
PyAPI_FUNC(int) PyDict_SetItemString(PyObject *dp, const char *key, PyObject *item);
PyAPI_FUNC(int) PyDict_DelItemString(PyObject *dp, const char *key);
-/* Dictionary (keys, values, items) views */
-
-PyAPI_DATA(PyTypeObject) PyDictKeys_Type;
-PyAPI_DATA(PyTypeObject) PyDictValues_Type;
-PyAPI_DATA(PyTypeObject) PyDictItems_Type;
-
-#define PyDictKeys_Check(op) PyObject_TypeCheck(op, &PyDictKeys_Type)
-#define PyDictValues_Check(op) PyObject_TypeCheck(op, &PyDictValues_Type)
-#define PyDictItems_Check(op) PyObject_TypeCheck(op, &PyDictItems_Type)
-/* This excludes Values, since they are not sets. */
-# define PyDictViewSet_Check(op) \
- (PyDictKeys_Check(op) || PyDictItems_Check(op))
-
-/* Dictionary (key, value, items) iterators */
-
-PyAPI_DATA(PyTypeObject) PyDictIterKey_Type;
-PyAPI_DATA(PyTypeObject) PyDictIterValue_Type;
-PyAPI_DATA(PyTypeObject) PyDictIterItem_Type;
-
-PyAPI_DATA(PyTypeObject) PyDictRevIterKey_Type;
-PyAPI_DATA(PyTypeObject) PyDictRevIterItem_Type;
-PyAPI_DATA(PyTypeObject) PyDictRevIterValue_Type;
-
-
-#ifndef Py_LIMITED_API
-# define Py_CPYTHON_DICTOBJECT_H
-# include "cpython/dictobject.h"
-# undef Py_CPYTHON_DICTOBJECT_H
-#endif
-
#ifdef __cplusplus
}
#endif