June 2018 Update

This commit is contained in:
Ingy döt Net 2018-06-22 20:57:24 +00:00
parent ba8067c3b7
commit 22f33d4004
5278 changed files with 84726 additions and 14379 deletions

View file

@ -0,0 +1,89 @@
import Data.List
import Data.Char
import Data.String.Utils
import Data.List.Utils
import Data.Function (on)
printOutput = do
putStrLn "# Ignoring leading spaces \n"
printBlockOfMessages sample1Rule ignoringStartEndSpaces
putStrLn "\n # Ignoring multiple adjacent spaces (m.a.s) \n"
printBlockOfMessages sample2Rule ignoringMultipleAdjacentSpaces
putStrLn "\n # Equivalent whitespace characters \n"
printBlockOfMessages sample3Rule ignoringMultipleAdjacentSpaces
putStrLn "\n # Case Indepenent sorts \n"
printBlockOfMessages sample4Rule caseIndependent
putStrLn "\n # Numeric fields as numerics \n"
printBlockOfMessages sample5Rule numericFieldsAsNumbers
putStrLn "\n # Title sorts \n"
printBlockOfMessages sample6Rule removeLeadCommonWords
printMessage message content = do
putStrLn message
mapM_ print content
printBlockOfMessages list function = do
printMessage "Text strings:" list
printMessage "Normally sorted:" (sort list)
printMessage "Naturally sorted:" (sortListWith list function)
-- samples
sample1Rule = ["ignore leading spaces: 2-2", " ignore leading spaces: 2-1", " ignore leading spaces: 2+0", " ignore leading spaces: 2+1"]
sample2Rule = ["ignore m.a.s spaces: 2-2", "ignore m.a.s spaces: 2-1", "ignore m.a.s spaces: 2+0", "ignore m.a.s spaces: 2+1"]
sample3Rule = ["Equiv. spaces: 3-3", "Equiv.\rspaces: 3-2", "Equiv.\x0cspaces: 3-1", "Equiv.\x0bspaces: 3+0", "Equiv.\nspaces: 3+1", "Equiv.\tspaces: 3+2"]
sample4Rule = ["cASE INDEPENENT: 3-2", "caSE INDEPENENT: 3-1", "casE INDEPENENT: 3+0", "case INDEPENENT: 3+1"]
sample5Rule = ["foo100bar99baz0.txt", "foo100bar10baz0.txt", "foo1000bar99baz10.txt", "foo1000bar99baz9.txt"]
sample6Rule = ["The Wind in the Willows", "The 40th step more", "The 39 steps", "Wanda"]
-- function to execute all sorts
sortListWith l f = sort $ f l
-- 1. Ignore leading, trailing and multiple adjacent spaces
-- Ignoring leading spaces
-- receive a String and remove all spaces from the start and end of that String, a String is considered an List os Char
-- ex: " a string " = "a string"
ignoringStartEndSpaces :: [String] -> [String]
ignoringStartEndSpaces = map strip
-- Ignoring multiple adjacent spaces and Equivalent whitespace characters
ignoringMultipleAdjacentSpaces :: [String] -> [String]
ignoringMultipleAdjacentSpaces = map (unwords . words)
-- 2. Equivalent whitespace characters
-- 3. Case independent sort
-- lower case of an entire String
-- ex "SomeCAse" = "somecase"
caseIndependent :: [String] -> [String]
caseIndependent = map (map toLower)
-- 4. Numeric fields as numerics (deals with up to 20 digits)
numericFieldsAsNumbers :: [String] -> [[Int]]
numericFieldsAsNumbers = map findOnlyNumerics
findOnlyNumerics :: String -> [Int]
findOnlyNumerics s = convertDigitAsStringToInt $ makeListOfDigitsAsString $ extractDigitsAsString s
extractDigitsAsString :: String -> [String]
extractDigitsAsString s = map (filter isNumber) $ groupBy ((==) `on` isNumber ) s
makeListOfDigitsAsString :: [String] -> [String]
makeListOfDigitsAsString l = tail $ nub l
convertDigitAsStringToInt :: [String] -> [Int]
convertDigitAsStringToInt = map (joiner . map digitToInt)
-- join a list of numbers into a single number
-- ex [4,2] = 42
joiner :: [Int] -> Int
joiner = read . concatMap show
-- 5. Title sort
removeLeadCommonWords l = map removeLeadCommonWord $ splitList l
splitList = map words
removeLeadCommonWord a = unwords $ if f a commonWords then tail a else a
where f l1 = elem (map toLower (head l1))
commonWords = ["the","a","an","of"]

View file

@ -1,5 +1,5 @@
--
-- demo/rosetta/Natural_sorting.exw
-- demo/rosetta/Natural_sorting2.exw
--
function utf32ch(sequence s)
for i=1 to length(s) do

View file

@ -0,0 +1,62 @@
# six sorting
$Discard = '^a ', '^an ', '^the '
$List =
'ignore leading spaces: 2-2<==',
' ignore leading spaces: 2-1 <==',
' ignore leading spaces: 2+0 <==',
' ignore leading spaces: 2+1 <==',
'ignore m.a.s spaces: 2-2<==',
'ignore m.a.s spaces: 2-1<==',
'ignore m.a.s spaces: 2+0<==',
'ignore m.a.s spaces: 2+1<==',
'Equiv. spaces: 3-3<==',
"Equiv.`rspaces: 3-2<==",
"Equiv.`fspaces: 3-1<==",
"Equiv.`vspaces: 3+0<==",
"Equiv.`nspaces: 3+1<==",
"Equiv.`tspaces: 3+2<==",
'cASE INDEPENDENT: 3-2<==',
'caSE INDEPENDENT: 3-1<==',
'casE INDEPENDENT: 3+0<==',
'case INDEPENDENT: 3+1<==',
'Lâmpada accented characters<==',
'Lúdico accented characters<==',
' Lula Free !!! accented characters<==',
'Amanda accented characters<==',
'Ágata accented characters<==',
'Ångström accented characters<==',
'Ângela accented characters<==',
'À toa accented characters<==',
'ânsia accented characters<==',
'álibi accented characters<==',
'foo100bar99baz0.txt<==',
'foo100bar10baz0.txt<==',
'foo1000bar99baz10.txt<==',
'foo1000bar99baz9.txt<==',
'The Wind in the Willows<==',
'The 40th step more<==',
'The 39 steps<==',
'Wanda<=='
'List index sorting'
$List
' '
'Lexicographically sorting'
$List | Sort-Object
' '
'Natural sorting'
$List | Sort-Object -Property {
[Regex]::Replace(
(
(
& {
If ($_.Trim() -match ($Discard -join '|')) {
$_ -replace '^\s*[^\s]+\s*'
} Else {
$_.Trim()
}
}
) -replace '\s+'
), '\d+', { $args[0].Value.PadLeft(20) }
)
}