Copyright | (c) Daan Leijen 2002 (c) Joachim Breitner 2011 |
---|---|

License | BSD-style |

Maintainer | libraries@haskell.org |

Portability | portable |

Safe Haskell | Trustworthy |

Language | Haskell98 |

# WARNING

This module is considered **internal**.

The Package Versioning Policy **does not apply**.

This contents of this module may change **in any way whatsoever**
and **without any warning** between minor versions of this package.

Authors importing this module are expected to track development closely.

# Description

An efficient implementation of integer sets.

These modules are intended to be imported qualified, to avoid name clashes with Prelude functions, e.g.

import Data.IntSet (IntSet) import qualified Data.IntSet as IntSet

The implementation is based on *big-endian patricia trees*. This data
structure performs especially well on binary operations like `union`

and `intersection`

. However, my benchmarks show that it is also
(much) faster on insertions and deletions when compared to a generic
size-balanced set implementation (see Data.Set).

- Chris Okasaki and Andy Gill, "
*Fast Mergeable Integer Maps*", Workshop on ML, September 1998, pages 77-86, http://citeseer.ist.psu.edu/okasaki98fast.html - D.R. Morrison, "/PATRICIA -- Practical Algorithm To Retrieve Information Coded In Alphanumeric/", Journal of the ACM, 15(4), October 1968, pages 514-534.

Additionally, this implementation places bitmaps in the leaves of the tree. Their size is the natural size of a machine word (32 or 64 bits) and greatly reduce memory footprint and execution times for dense sets, e.g. sets where it is likely that many values lie close to each other. The asymptotics are not affected by this optimization.

Many operations have a worst-case complexity of *O(min(n,W))*.
This means that the operation can become linear in the number of
elements with a maximum of *W* -- the number of bits in an `Int`

(32 or 64).

- data IntSet
- type Key = Int
- (\\) :: IntSet -> IntSet -> IntSet
- null :: IntSet -> Bool
- size :: IntSet -> Int
- member :: Key -> IntSet -> Bool
- notMember :: Key -> IntSet -> Bool
- lookupLT :: Key -> IntSet -> Maybe Key
- lookupGT :: Key -> IntSet -> Maybe Key
- lookupLE :: Key -> IntSet -> Maybe Key
- lookupGE :: Key -> IntSet -> Maybe Key
- isSubsetOf :: IntSet -> IntSet -> Bool
- isProperSubsetOf :: IntSet -> IntSet -> Bool
- empty :: IntSet
- singleton :: Key -> IntSet
- insert :: Key -> IntSet -> IntSet
- delete :: Key -> IntSet -> IntSet
- union :: IntSet -> IntSet -> IntSet
- unions :: [IntSet] -> IntSet
- difference :: IntSet -> IntSet -> IntSet
- intersection :: IntSet -> IntSet -> IntSet
- filter :: (Key -> Bool) -> IntSet -> IntSet
- partition :: (Key -> Bool) -> IntSet -> (IntSet, IntSet)
- split :: Key -> IntSet -> (IntSet, IntSet)
- splitMember :: Key -> IntSet -> (IntSet, Bool, IntSet)
- splitRoot :: IntSet -> [IntSet]
- map :: (Key -> Key) -> IntSet -> IntSet
- foldr :: (Key -> b -> b) -> b -> IntSet -> b
- foldl :: (a -> Key -> a) -> a -> IntSet -> a
- foldr' :: (Key -> b -> b) -> b -> IntSet -> b
- foldl' :: (a -> Key -> a) -> a -> IntSet -> a
- fold :: (Key -> b -> b) -> b -> IntSet -> b
- findMin :: IntSet -> Key
- findMax :: IntSet -> Key
- deleteMin :: IntSet -> IntSet
- deleteMax :: IntSet -> IntSet
- deleteFindMin :: IntSet -> (Key, IntSet)
- deleteFindMax :: IntSet -> (Key, IntSet)
- maxView :: IntSet -> Maybe (Key, IntSet)
- minView :: IntSet -> Maybe (Key, IntSet)
- elems :: IntSet -> [Key]
- toList :: IntSet -> [Key]
- fromList :: [Key] -> IntSet
- toAscList :: IntSet -> [Key]
- toDescList :: IntSet -> [Key]
- fromAscList :: [Key] -> IntSet
- fromDistinctAscList :: [Key] -> IntSet
- showTree :: IntSet -> String
- showTreeWith :: Bool -> Bool -> IntSet -> String
- match :: Int -> Prefix -> Mask -> Bool
- suffixBitMask :: Int
- prefixBitMask :: Int
- bitmapOf :: Int -> BitMap

# Set type

A set of integers.

# Operators

# Query

lookupLT :: Key -> IntSet -> Maybe Key Source #

*O(log n)*. Find largest element smaller than the given one.

lookupLT 3 (fromList [3, 5]) == Nothing lookupLT 5 (fromList [3, 5]) == Just 3

lookupGT :: Key -> IntSet -> Maybe Key Source #

*O(log n)*. Find smallest element greater than the given one.

lookupGT 4 (fromList [3, 5]) == Just 5 lookupGT 5 (fromList [3, 5]) == Nothing

lookupLE :: Key -> IntSet -> Maybe Key Source #

*O(log n)*. Find largest element smaller or equal to the given one.

lookupLE 2 (fromList [3, 5]) == Nothing lookupLE 4 (fromList [3, 5]) == Just 3 lookupLE 5 (fromList [3, 5]) == Just 5

lookupGE :: Key -> IntSet -> Maybe Key Source #

*O(log n)*. Find smallest element greater or equal to the given one.

lookupGE 3 (fromList [3, 5]) == Just 3 lookupGE 4 (fromList [3, 5]) == Just 5 lookupGE 6 (fromList [3, 5]) == Nothing

isSubsetOf :: IntSet -> IntSet -> Bool Source #

*O(n+m)*. Is this a subset?
`(s1 `

tells whether `isSubsetOf`

s2)`s1`

is a subset of `s2`

.

isProperSubsetOf :: IntSet -> IntSet -> Bool Source #

*O(n+m)*. Is this a proper subset? (ie. a subset but not equal).

# Construction

insert :: Key -> IntSet -> IntSet Source #

*O(min(n,W))*. Add a value to the set. There is no left- or right bias for
IntSets.

delete :: Key -> IntSet -> IntSet Source #

*O(min(n,W))*. Delete a value in the set. Returns the
original set when the value was not present.

# Combine

# Filter

filter :: (Key -> Bool) -> IntSet -> IntSet Source #

*O(n)*. Filter all elements that satisfy some predicate.

partition :: (Key -> Bool) -> IntSet -> (IntSet, IntSet) Source #

*O(n)*. partition the set according to some predicate.

split :: Key -> IntSet -> (IntSet, IntSet) Source #

*O(min(n,W))*. The expression (

) is a pair `split`

x set`(set1,set2)`

where `set1`

comprises the elements of `set`

less than `x`

and `set2`

comprises the elements of `set`

greater than `x`

.

split 3 (fromList [1..5]) == (fromList [1,2], fromList [4,5])

splitMember :: Key -> IntSet -> (IntSet, Bool, IntSet) Source #

*O(min(n,W))*. Performs a `split`

but also returns whether the pivot
element was found in the original set.

splitRoot :: IntSet -> [IntSet] Source #

*O(1)*. Decompose a set into pieces based on the structure of the underlying
tree. This function is useful for consuming a set in parallel.

No guarantee is made as to the sizes of the pieces; an internal, but deterministic process determines this. However, it is guaranteed that the pieces returned will be in ascending order (all elements in the first submap less than all elements in the second, and so on).

Examples:

splitRoot (fromList [1..120]) == [fromList [1..63],fromList [64..120]] splitRoot empty == []

Note that the current implementation does not return more than two subsets, but you should not depend on this behaviour because it can change in the future without notice. Also, the current version does not continue splitting all the way to individual singleton sets -- it stops at some point.

# Map

map :: (Key -> Key) -> IntSet -> IntSet Source #

*O(n*min(n,W))*.

is the set obtained by applying `map`

f s`f`

to each element of `s`

.

It's worth noting that the size of the result may be smaller if,
for some `(x,y)`

, `x /= y && f x == f y`

# Folds

## Strict folds

foldr' :: (Key -> b -> b) -> b -> IntSet -> b Source #

*O(n)*. A strict version of `foldr`

. Each application of the operator is
evaluated before using the result in the next application. This
function is strict in the starting value.

foldl' :: (a -> Key -> a) -> a -> IntSet -> a Source #

*O(n)*. A strict version of `foldl`

. Each application of the operator is
evaluated before using the result in the next application. This
function is strict in the starting value.

## Legacy folds

fold :: (Key -> b -> b) -> b -> IntSet -> b Source #

*O(n)*. Fold the elements in the set using the given right-associative
binary operator. This function is an equivalent of `foldr`

and is present
for compatibility only.

*Please note that fold will be deprecated in the future and removed.*

# Min/Max

deleteFindMin :: IntSet -> (Key, IntSet) Source #

*O(min(n,W))*. Delete and find the minimal element.

deleteFindMin set = (findMin set, deleteMin set)

deleteFindMax :: IntSet -> (Key, IntSet) Source #

*O(min(n,W))*. Delete and find the maximal element.

deleteFindMax set = (findMax set, deleteMax set)

maxView :: IntSet -> Maybe (Key, IntSet) Source #

*O(min(n,W))*. Retrieves the maximal key of the set, and the set
stripped of that element, or `Nothing`

if passed an empty set.

minView :: IntSet -> Maybe (Key, IntSet) Source #

*O(min(n,W))*. Retrieves the minimal key of the set, and the set
stripped of that element, or `Nothing`

if passed an empty set.

# Conversion

## List

elems :: IntSet -> [Key] Source #

*O(n)*. An alias of `toAscList`

. The elements of a set in ascending order.
Subject to list fusion.

toList :: IntSet -> [Key] Source #

*O(n)*. Convert the set to a list of elements. Subject to list fusion.

## Ordered list

toAscList :: IntSet -> [Key] Source #

*O(n)*. Convert the set to an ascending list of elements. Subject to list
fusion.

toDescList :: IntSet -> [Key] Source #

*O(n)*. Convert the set to a descending list of elements. Subject to list
fusion.

fromAscList :: [Key] -> IntSet Source #

*O(n)*. Build a set from an ascending list of elements.
*The precondition (input list is ascending) is not checked.*

fromDistinctAscList :: [Key] -> IntSet Source #

*O(n)*. Build a set from an ascending list of distinct elements.
*The precondition (input list is strictly ascending) is not checked.*

# Debugging

showTree :: IntSet -> String Source #

*O(n)*. Show the tree that implements the set. The tree is shown
in a compressed, hanging format.

showTreeWith :: Bool -> Bool -> IntSet -> String Source #

*O(n)*. The expression (

) shows
the tree that implements the set. If `showTreeWith`

hang wide map`hang`

is
`True`

, a *hanging* tree is shown otherwise a rotated tree is shown. If
`wide`

is `True`

, an extra wide version is shown.

# Internals

suffixBitMask :: Int Source #

prefixBitMask :: Int Source #