1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
-- |
-- Module : Data.ByteString.Search.KMP
-- Copyright : Justin Bailey
-- Chris Kuklewicz
-- Daniel Fischer
-- Licence : BSD3
-- Maintainer : Daniel Fischer <daniel.is.fischer@googlemail.com>
-- Stability : Provisional
-- Portability : non-portable (BangPatterns)
--
-- Fast search of strict 'S.ByteString' values using the
-- Knuth-Morris-Pratt algorithm.
--
-- A description of the algorithm can be found at
-- <http://en.wikipedia.org/wiki/Knuth-Morris-Pratt_algorithm>.
--
-- Original authors: Justin Bailey (jgbailey at gmail.com) and
-- Chris Kuklewicz (haskell at list.mightyreason.com).
module Data.ByteString.Search.KMP ( -- * Overview
-- $overview
-- ** Complexity and Performance
-- $complexity
-- ** Partial application
-- $partial
-- * Functions
indices
, nonOverlappingIndices
) where
import Data.ByteString.Search.Internal.KnuthMorrisPratt (matchSS, indicesS)
import qualified Data.ByteString as S
-- $overview
--
-- This module provides two functions for finding the occurrences of a
-- pattern in a target string using the Knuth-Morris-Pratt algorithm.
-- It exists only for systematic reasons, the functions from
-- "Data.ByteString.Search" are much faster, except for very short patterns,
-- in which case "Data.ByteString.Search.DFA" provides better functions.
-- $complexity
--
-- The preprocessing of the pattern is /O/(@patternLength@) in time and space.
-- The time complexity of the searching phase is /O/(@targetLength@) for both
-- functions.
--
-- In most cases, these functions are considerably slower than the
-- Boyer-Moore variants, performance is close to that of those from
-- "Data.ByteString.Search.DFA".
-- $partial
--
-- Both functions can be usefully partially applied. Given only a
-- pattern, the auxiliary data will be computed only once, allowing for
-- efficient re-use.
-- | @'indices'@ finds the starting indices of all possibly overlapping
-- occurrences of the pattern in the target string.
-- If the pattern is empty, the result is @[0 .. 'length' target]@.
{-# INLINE indices #-}
indices :: S.ByteString -- ^ Pattern to find
-> S.ByteString -- ^ String to search
-> [Int] -- ^ Offsets of matches
indices = indicesS
-- | @'nonOverlappingIndices'@ finds the starting indices of all
-- non-overlapping occurrences of the pattern in the target string.
-- It is more efficient than removing indices from the list produced
-- by 'indices'.
{-# INLINE nonOverlappingIndices #-}
nonOverlappingIndices :: S.ByteString -- ^ Pattern to find
-> S.ByteString -- ^ String to search
-> [Int] -- ^ Offsets of matches
nonOverlappingIndices = matchSS
|
