Skip to main content
5 of 5
added 71 characters in body
Chao Xu
  • 201
  • 1
  • 7

Haskell 2063+2*151=2365

It's guaranteed the generated regex has length O(log n log log n).

matchIntRange 12345 7654321

1(2(3(4(5[6-9]|[6-9]\d)|[5-9]\d\d)|[4-9]\d{3})|[3-9]\d{4})|[2-9]\d{5}|[1-6]\d{6}|7([0-5]\d{5}|6([0-4]\d{4}|5([0-3]\d{3}|4([012]\d\d|3([01]\d|2[01])))))

import Data.Digits

data RegEx = Range Int Int | MatchNone | All Int
            | Or RegEx RegEx | Concat [RegEx] 

alphabet = "\\d"

instance Show RegEx where
  show (Range i j)
   | i == j    = show i
   | i+1 == j  = concat ["[",show i,show j,"]"]
   | i+2 == j  = concat ["[",show i,show (i+1), show (i+2),"]"]
   | otherwise = concat ["[",show i,"-",show j,"]"]
  show (Or a b)  = show a ++ "|" ++ show b
  show MatchNone = "^$"
  show (All n) 
   | n < 3     = concat $ replicate n alphabet
   | otherwise = concat [alphabet,"{",show n,"}"] 
  show e@(Concat xs) 
   | atomic e  = concatMap show xs
   | otherwise = concatMap show' xs
   where show' (Or a b) = "("++show (Or a b)++")"
         show' x = show x
         atomic (Concat xs) = all atomic xs
         atomic (Or _ _)    = False
         atomic _           = True

-- Match integers in a certain range
matchIntRange :: Int->Int->RegEx
matchIntRange a b
 | 0 > min a b = error "Negative input"
 | a > b       = MatchNone
 | otherwise = build (d a) (d b)
 where build :: [Int]->[Int]->RegEx
       build [] [] = Concat [] 
       build (a@(x:xs)) (b@(y:ys))
         | sl && x == y       = Concat [Range x x, build xs ys]
         | sl && all9 && all0 = Concat [Range x y, All n]
         | sl && all0         = Or (Concat [Range x (y-1), All n]) upper
         | sl && all9         = Or lower (Concat [Range (x+1) y, All n])
         | sl && x+1 <= y-1   = Or (Or lower middle) upper
         | sl                 = Or lower upper
         | otherwise          = Or (build a (nines la)) (build (1:zeros la) b)
         where (la,lb) = (length a, length b)
               sl      = la == lb
               n       = length xs
               upper   = Concat [Range y y, build (zeros n) ys]
               lower   = Concat [Range x x, build xs (nines n)]
               middle  = Concat [Range (x+1) (y-1), All n]
               all9    = all (==9) ys
               all0    = all (==0) xs
       zeros n   = replicate n 0
       nines n   = replicate n 9
       d 0 = [0]
       d n = digits 10 n

The code below is a simple version that helps with understanding the algorithm, but it doesn't do any optimization to improve the regex size.

matchIntRange 123 4321

(((1((2((3|[4-8])|9)|[3-8]((0|[1-8])|9))|9((0|[1-8])|9))|[2-8]((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|9((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|((1((0((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9))|[1-8]((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|9((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|[2-3]((0((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9))|[1-8]((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|9((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9))))|4((0((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9))|[1-2]((0((0|[1-8])|9)|[1-8]((0|[1-8])|9))|9((0|[1-8])|9)))|3((0((0|[1-8])|9)|1((0|[1-8])|9))|2(0|1)))))

The regular expression has 680 characters. Here is the code

import Data.Digits

data RegEx = Range Int Int | MatchNone | Or RegEx RegEx | Concat [RegEx] 

alphabet = "\\d"

instance Show RegEx where
  show (Range i j)
   | i == j    = show i
   | otherwise = concat ["[",show i,"-",show j,"]"]
  show (Or a b)  = concat ["(",show a,"|",show b,")"]
  show MatchNone = "^$"
  show (Concat xs) = concatMap show xs

matchIntRange :: Int->Int->RegEx
matchIntRange a b
 | 0 > min a b = error "Negative input"
 | a > b       = MatchNone
 | otherwise = build (d a) (d b)
 where build :: [Int]->[Int]->RegEx
       build [] [] = Concat [] 
       build (a@(x:xs)) (b@(y:ys))
         | sl && x == y     = Concat [Range x x, build xs ys]
         | sl && x+1 <= y-1 = Or (Or lower middle) upper
         | sl               = Or lower upper
         | otherwise        = Or (build a (nines la)) (build (1:zeros la) b)
         where (la,lb) = (length a, length b)
               sl      = la == lb
               n       = length xs
               upper   = Concat [Range y y, build (zeros n) ys]
               lower   = Concat [Range x x, build xs (nines n)]
               middle  = Concat [Range (x+1) (y-1), build (zeros n) (nines n)]
       zeros n = replicate n 0
       nines n = replicate n 9
       d 0 = [0]
       d n = digits 10 n
Chao Xu
  • 201
  • 1
  • 7