API Reference

Protocol APIs

interface BTrees.Interfaces.ICollection

clear()

Remove all of the items from the collection.

__nonzero__()

Check if the collection is non-empty.

Return a true value if the collection is non-empty and a false value otherwise.

interface BTrees.Interfaces.IReadSequence

__getitem__(index)

Return the value at the given index.

An IndexError is raised if the index cannot be found.

__getslice__(index1, index2)

Return a subsequence from the original sequence.

The subsequence includes the items from index1 up to, but not including, index2.

interface BTrees.Interfaces.IKeyed

Extends: BTrees.Interfaces.ICollection

has_key(key)

Check whether the object has an item with the given key.

Return a true value if the key is present, else a false value.

keys(min=None, max=None, excludemin=False, excludemax=False)

Return an IReadSequence containing the keys in the collection.

The type of the IReadSequence is not specified. It could be a list or a tuple or some other type.

All arguments are optional, and may be specified as keyword arguments, or by position.

If a min is specified, then output is constrained to keys greater than or equal to the given min, and, if excludemin is specified and true, is further constrained to keys strictly greater than min. A min value of None is ignored. If min is None or not specified, and excludemin is true, the smallest key is excluded.

If a max is specified, then output is constrained to keys less than or equal to the given max, and, if excludemax is specified and true, is further constrained to keys strictly less than max. A max value of None is ignored. If max is None or not specified, and excludemax is true, the largest key is excluded.

maxKey(key=None)

Return the maximum key.

If a key argument if provided and not None, return the largest key that is less than or equal to the argument. Raise an exception if no such key exists.

minKey(key=None)

Return the minimum key.

If a key argument if provided and not None, return the smallest key that is greater than or equal to the argument. Raise an exception if no such key exists.

interface BTrees.Interfaces.ISetMutable

Extends: BTrees.Interfaces.IKeyed

insert(key)

Add the key (value) to the set.

If the key was already in the set, return 0, otherwise return 1.

remove(key)

Remove the key from the set.

Raises KeyError if key is not in the set.

update(seq)

Add the items from the given sequence to the set.

interface BTrees.Interfaces.ISized

An object that supports __len__.

__len__()

Return the number of items in the container.

interface BTrees.Interfaces.IKeySequence

Extends: BTrees.Interfaces.IKeyed, BTrees.Interfaces.ISized

__getitem__(index)

Return the key in the given index position.

This allows iteration with for loops and use in functions, like map and list, that read sequences.

interface BTrees.Interfaces.IMinimalDictionary

Extends: BTrees.Interfaces.ISized, BTrees.Interfaces.IKeyed

get(key, default)

Get the value associated with the given key.

Return the default if has_key(key) is false.

__getitem__(key)

Get the value associated with the given key.

Raise KeyError if has_key(key) is false.

__setitem__(key, value)

Set the value associated with the given key.

__delitem__(key)

Delete the value associated with the given key.

Raise KeyError if has_key(key) is false.

values(min=None, max=None, excludemin=False, excludemax=False)

Return an IReadSequence containing the values in the collection.

The type of the IReadSequence is not specified. It could be a list or a tuple or some other type.

All arguments are optional, and may be specified as keyword arguments, or by position.

If a min is specified, then output is constrained to values whose keys are greater than or equal to the given min, and, if excludemin is specified and true, is further constrained to values whose keys are strictly greater than min. A min value of None is ignored. If min is None or not specified, and excludemin is true, the value corresponding to the smallest key is excluded.

If a max is specified, then output is constrained to values whose keys are less than or equal to the given max, and, if excludemax is specified and true, is further constrained to values whose keys are strictly less than max. A max value of None is ignored. If max is None or not specified, and excludemax is true, the value corresponding to the largest key is excluded.

items(min=None, max=None, excludemin=False, excludemax=False)

Return an IReadSequence containing the items in the collection.

An item is a 2-tuple, a (key, value) pair.

The type of the IReadSequence is not specified. It could be a list or a tuple or some other type.

All arguments are optional, and may be specified as keyword arguments, or by position.

If a min is specified, then output is constrained to items whose keys are greater than or equal to the given min, and, if excludemin is specified and true, is further constrained to items whose keys are strictly greater than min. A min value of None is ignored. If min is None or not specified, and excludemin is true, the item with the smallest key is excluded.

If a max is specified, then output is constrained to items whose keys are less than or equal to the given max, and, if excludemax is specified and true, is further constrained to items whose keys are strictly less than max. A max value of None is ignored. If max is None or not specified, and excludemax is true, the item with the largest key is excluded.

interface BTrees.Interfaces.IDictionaryIsh

Extends: BTrees.Interfaces.IMinimalDictionary

update(collection)

Add the items from the given collection object to the collection.

The input collection must be a sequence of (key, value) 2-tuples, or an object with an ‘items’ method that returns a sequence of (key, value) pairs.

byValue(minValue)

Return a sequence of (value, key) pairs, sorted by value.

Values < minValue are omitted and other values are “normalized” by the minimum value. This normalization may be a noop, but, for integer values, the normalization is division.

setdefault(key, d)

D.setdefault(k, d) -> D.get(k, d), also set D[k]=d if k not in D.

Return the value like get() except that if key is missing, d is both returned and inserted into the dictionary as the value of k.

Note that, unlike as for Python’s dict.setdefault(), d is not optional. Python defaults d to None, but that doesn’t make sense for mappings that can’t have None as a value (for example, an IIBTree can have only integers as values).

pop(key, d)

D.pop(k[, d]) -> v, remove key and return the corresponding value.

If key is not found, d is returned if given, otherwise KeyError is raised.

interface BTrees.Interfaces.IMerge

Object with methods for merging sets, buckets, and trees.

These methods are supplied in modules that define collection classes with particular key and value types. The operations apply only to collections from the same module. For example, the IIBTree.union can only be used with IIBTree.IIBTree, IIBTree.IIBucket, IIBTree.IISet, and IIBTree.IITreeSet.

The implementing module has a value type. The IOBTree and OOBTree modules have object value type. The IIBTree and OIBTree modules have integer value types. Other modules may be defined in the future that have other value types.

The individual types are classified into set (Set and TreeSet) and mapping (Bucket and BTree) types.

difference(c1, c2)

Return the keys or items in c1 for which there is no key in c2.

If c1 is None, then None is returned. If c2 is None, then c1 is returned.

If neither c1 nor c2 is None, the output is a Set if c1 is a Set or TreeSet, and is a Bucket if c1 is a Bucket or BTree.

union(c1, c2)

Compute the Union of c1 and c2.

If c1 is None, then c2 is returned, otherwise, if c2 is None, then c1 is returned.

The output is a Set containing keys from the input collections.

intersection(c1, c2)

Compute the intersection of c1 and c2.

If c1 is None, then c2 is returned, otherwise, if c2 is None, then c1 is returned.

The output is a Set containing matching keys from the input collections.

interface BTrees.Interfaces.IIMerge

Extends: BTrees.Interfaces.IMerge

Merge collections with integer value type.

A primary intent is to support operations with no or integer values, which are used as “scores” to rate indiviual keys. That is, in this context, a BTree or Bucket is viewed as a set with scored keys, using integer scores.

weightedUnion(c1, c2, weight1=1, weight2=1)

Compute the weighted union of c1 and c2.

If c1 and c2 are None, the output is (0, None).

If c1 is None and c2 is not None, the output is (weight2, c2).

If c1 is not None and c2 is None, the output is (weight1, c1).

Else, and hereafter, c1 is not None and c2 is not None.

If c1 and c2 are both sets, the output is 1 and the (unweighted) union of the sets.

Else the output is 1 and a Bucket whose keys are the union of c1 and c2’s keys, and whose values are:

v1*weight1 + v2*weight2

where:

  v1 is 0        if the key is not in c1
        1        if the key is in c1 and c1 is a set
        c1[key]  if the key is in c1 and c1 is a mapping

  v2 is 0        if the key is not in c2
        1        if the key is in c2 and c2 is a set
        c2[key]  if the key is in c2 and c2 is a mapping

Note that c1 and c2 must be collections.

weightedIntersection(c1, c2, weight1=1, weight2=1)

Compute the weighted intersection of c1 and c2.

If c1 and c2 are None, the output is (0, None).

If c1 is None and c2 is not None, the output is (weight2, c2).

If c1 is not None and c2 is None, the output is (weight1, c1).

Else, and hereafter, c1 is not None and c2 is not None.

If c1 and c2 are both sets, the output is the sum of the weights and the (unweighted) intersection of the sets.

Else the output is 1 and a Bucket whose keys are the intersection of c1 and c2’s keys, and whose values are:

v1*weight1 + v2*weight2

where:

  v1 is 1        if c1 is a set
        c1[key]  if c1 is a mapping

  v2 is 1        if c2 is a set
        c2[key]  if c2 is a mapping

Note that c1 and c2 must be collections.

interface BTrees.Interfaces.IMergeIntegerKey

Extends: BTrees.Interfaces.IMerge

IMerge-able objects with integer keys.

Concretely, this means the types in IOBTree and IIBTree.

multiunion(seq)

Return union of (zero or more) integer sets, as an integer set.

seq is a sequence of objects each convertible to an integer set. These objects are convertible to an integer set:

• An integer, which is added to the union.

• A Set or TreeSet from the same module (for example, an IIBTree.TreeSet for IIBTree.multiunion()). The elements of the set are added to the union.

• A Bucket or BTree from the same module (for example, an IOBTree.IOBTree for IOBTree.multiunion()). The keys of the mapping are added to the union.

The union is returned as a Set from the same module (for example, IIBTree.multiunion() returns an IIBTree.IISet).

The point to this method is that it can run much faster than doing a sequence of two-input union() calls. Under the covers, all the integers in all the inputs are sorted via a single linear-time radix sort, then duplicates are removed in a second linear-time pass.

BTree Family APIs

interface BTrees.Interfaces.ISet

Extends: BTrees.Interfaces.IKeySequence, BTrees.Interfaces.ISetMutable

interface BTrees.Interfaces.ITreeSet

Extends: BTrees.Interfaces.IKeyed, BTrees.Interfaces.ISetMutable

interface BTrees.Interfaces.IBTree

Extends: BTrees.Interfaces.IDictionaryIsh

insert(key, value)

Insert a key and value into the collection.

If the key was already in the collection, then there is no change and 0 is returned.

If the key was not already in the collection, then the item is added and 1 is returned.

This method is here to allow one to generate random keys and to insert and test whether the key was there in one operation.

A standard idiom for generating new keys will be:

key = generate_key()
while not t.insert(key, value):
    key=generate_key()

interface BTrees.Interfaces.IBTreeFamily

the 64-bit or 32-bit family

IO

The IIntegerObjectBTreeModule for this family

OI

The IObjectIntegerBTreeModule for this family

II

The IIntegerIntegerBTreeModule for this family

IF

The IIntegerFloatBTreeModule for this family

OO

The IObjectObjectBTreeModule for this family

maxint

The maximum integer storable in this family

minint

The minimum integer storable in this family

Module APIs

interface BTrees.Interfaces.IBTreeModule

These are available in all modules (IOBTree, OIBTree, OOBTree, IIBTree, IFBTree, LFBTree, LOBTree, OLBTree, and LLBTree).

BTree

The IBTree for this module.

Also available as [prefix]BTree, as in IOBTree.

Bucket

The leaf-node data buckets used by the BTree.

(IBucket is not currently defined in this file, but is essentially IDictionaryIsh, with the exception of __nonzero__, as of this writing.)

Also available as [prefix]Bucket, as in IOBucket.

TreeSet

The ITreeSet for this module.

Also available as [prefix]TreeSet, as in IOTreeSet.

Set

The ISet for this module: the leaf-node data buckets used by the TreeSet.

Also available as [prefix]BTree, as in IOSet.

interface BTrees.Interfaces.IObjectObjectBTreeModule

Extends: BTrees.Interfaces.IBTreeModule, BTrees.Interfaces.IMerge

keys, or set values, are objects; values are also objects.

Object keys (and set values) must sort reliably (for instance, not on object id)! Homogenous key types recommended.

describes OOBTree

interface BTrees.Interfaces.IIntegerObjectBTreeModule

Extends: BTrees.Interfaces.IBTreeModule, BTrees.Interfaces.IMerge

keys, or set values, are integers; values are objects.

describes IOBTree and LOBTree

family

The IBTreeFamily of this module

interface BTrees.Interfaces.IObjectIntegerBTreeModule

Extends: BTrees.Interfaces.IBTreeModule, BTrees.Interfaces.IIMerge

keys, or set values, are objects; values are integers.

Object keys (and set values) must sort reliably (for instance, not on object id)! Homogenous key types recommended.

describes OIBTree and LOBTree

family

The IBTreeFamily of this module

interface BTrees.Interfaces.IIntegerIntegerBTreeModule

Extends: BTrees.Interfaces.IBTreeModule, BTrees.Interfaces.IIMerge, BTrees.Interfaces.IMergeIntegerKey

keys, or set values, are integers; values are also integers.

describes IIBTree and LLBTree

family

The IBTreeFamily of this module

interface BTrees.Interfaces.IIntegerFloatBTreeModule

Extends: BTrees.Interfaces.IBTreeModule, BTrees.Interfaces.IMerge

keys, or set values, are integers; values are floats.

describes IFBTree and LFBTree

family

The IBTreeFamily of this module

Utilities

class BTrees.Length.Length(v=0)

BTree lengths are often too expensive to compute.

Objects that use BTrees need to keep track of lengths themselves. This class provides an object for doing this.

As a bonus, the object support application-level conflict resolution.

It is tempting to to assign length objects to __len__ attributes to provide instance-specific __len__ methods. However, this no longer works as expected, because new-style classes cache class-defined slot methods (like __len__) in C type slots. Thus, instance-defined slot fillers are ignored.

__call__(*args)

Return the current length value.

change(delta)

Add delta to the length value.

set(v)

Set the length value to v.

Utilities for working with BTrees (TreeSets, Buckets, and Sets) at a low level.

The primary function is check(btree), which performs value-based consistency checks of a kind btree._check() does not perform. See the function docstring for details.

display(btree) displays the internal structure of a BTree (TreeSet, etc) to stdout.

CAUTION: When a BTree node has only a single bucket child, it can be impossible to get at the bucket from Python code (__getstate__() may squash the bucket object out of existence, as a pickling storage optimization). In such a case, the code here synthesizes a temporary bucket with the same keys (and values, if the bucket is of a mapping type). This has no first-order consequences, but can mislead if you pay close attention to reported object addresses and/or object identity (the synthesized bucket has an address that doesn’t exist in the actual BTree).

BTrees.check.check(btree)

Check internal value-based invariants in a BTree or TreeSet.

The btree._check() method checks internal C-level pointer consistency. The check() function here checks value-based invariants: whether the keys in leaf bucket and internal nodes are in strictly increasing order, and whether they all lie in their expected range. The latter is a subtle invariant that can’t be checked locally – it requires propagating range info down from the root of the tree, and modifying it at each level for each child.

Raises AssertionError if anything is wrong, with a string detail explaining the problems. The entire tree is checked before AssertionError is raised, and the string detail may be large (depending on how much went wrong).

BTrees.check.display(btree)

Display the internal structure of a BTree, Bucket, TreeSet or Set.