wet-pancake/WetPancake/DataProcessing.fs

module internal DataProcessing

    open System.Text.RegularExpressions
    open DataCleaning
    open System

    let MatchText pattern text = Regex.IsMatch(text, pattern)

    let ConcatToString words = String.concat " " words

    let SortIntoGroups groupSize text =
        SplitText @"\s+" text // Splits text where there is a space.
        |> Seq.windowed groupSize

    let BisectWords words =
        let length = Array.length words
        let start =
            words
            |> Seq.take (length - 1)
            |> ConcatToString
        (start, words.[length - 1])

    let CombineWords prev next =
        [prev; next]
        |> List.filter(fun s -> not (String.IsNullOrWhiteSpace s))
        |> ConcatToString