首先讓我爲這個問題的規模道歉,但我真的想在功能上考慮,這是我不得不合作的更具挑戰性的問題之一。如何寫一個功能文件「掃描儀」
我想獲得一些建議,說明如何以功能方式處理問題,特別是在F#中。我正在編寫一個程序來檢查目錄列表,並使用正則表達式列表來過濾從目錄中檢索到的文件列表,並使用第二個正則表達式列表來查找被檢索文件的文本中的匹配項。我希望這件事能夠爲每個匹配給定正則表達式模式的文本返回文件名,行索引,列索引,模式和匹配值。另外,需要記錄異常,並且有3種可能的異常情況:無法打開目錄,無法打開文件,從文件中讀取內容失敗。這樣做的最終要求是「掃描」匹配的文件量可能非常大,所以整個事情需要懶散。我並不太擔心「純」功能解決方案,因爲我對「良好」的解決方案很感興趣,而且解決方案的讀取效果很好,並且運行良好。最後一個挑戰是使它與C#互操作,因爲我想使用winform工具將此算法附加到UI。這是我的第一次嘗試,希望這將澄清問題:
open System.Text.RegularExpressions
open System.IO
type Reader<'t, 'a> = 't -> 'a //=M['a], result varies
let returnM x _ = x
let map f m = fun t -> t |> m |> f
let apply f m = fun t -> t |> m |> (t |> f)
let bind f m = fun t -> t |> (t |> m |> f)
let Scanner dirs =
returnM dirs
|> apply (fun dirExHandler ->
Seq.collect (fun directory ->
try
Directory.GetFiles(directory, "*", SearchOption.AllDirectories)
with | e ->
dirExHandler e directory
Array.empty))
|> map (fun filenames ->
returnM filenames
|> apply (fun (filenamepatterns, lineExHandler, fileExHandler) ->
Seq.filter (fun filename ->
filenamepatterns |> Seq.exists (fun pattern ->
let regex = new Regex(pattern)
regex.IsMatch(filename)))
>> Seq.map (fun filename ->
let fileinfo = new FileInfo(filename)
try
use reader = fileinfo.OpenText()
Seq.unfold (fun ((reader : StreamReader), index) ->
if not reader.EndOfStream then
try
let line = reader.ReadLine()
Some((line, index), (reader, index + 1))
with | e ->
lineExHandler e filename index
None
else
None) (reader, 0)
|> (fun lines -> (filename, lines))
with | e ->
fileExHandler e filename
(filename, Seq.empty))
>> (fun files ->
returnM files
|> apply (fun contentpatterns ->
Seq.collect (fun file ->
let filename, lines = file
lines |>
Seq.collect (fun line ->
let content, index = line
contentpatterns
|> Seq.collect (fun pattern ->
let regex = new Regex(pattern)
regex.Matches(content)
|> (Seq.cast<Match>
>> Seq.map (fun contentmatch ->
(filename,
index,
contentmatch.Index,
pattern,
contentmatch.Value))))))))))
感謝您的任何輸入。
更新 - 這裏是一個基於反饋的任何更新的解決方案,我收到:
open System.Text.RegularExpressions
open System.IO
type ScannerConfiguration = {
FileNamePatterns : seq<string>
ContentPatterns : seq<string>
FileExceptionHandler : exn -> string -> unit
LineExceptionHandler : exn -> string -> int -> unit
DirectoryExceptionHandler : exn -> string -> unit }
let scanner specifiedDirectories (configuration : ScannerConfiguration) = seq {
let ToCachedRegexList = Seq.map (fun pattern -> new Regex(pattern)) >> Seq.cache
let contentRegexes = configuration.ContentPatterns |> ToCachedRegexList
let filenameRegexes = configuration.FileNamePatterns |> ToCachedRegexList
let getLines exHandler reader =
Seq.unfold (fun ((reader : StreamReader), index) ->
if not reader.EndOfStream then
try
let line = reader.ReadLine()
Some((line, index), (reader, index + 1))
with | e -> exHandler e index; None
else
None) (reader, 0)
for specifiedDirectory in specifiedDirectories do
let files =
try Directory.GetFiles(specifiedDirectory, "*", SearchOption.AllDirectories)
with e -> configuration.DirectoryExceptionHandler e specifiedDirectory; [||]
for file in files do
if filenameRegexes |> Seq.exists (fun (regex : Regex) -> regex.IsMatch(file)) then
let lines =
let fileinfo = new FileInfo(file)
try
use reader = fileinfo.OpenText()
reader |> getLines (fun e index -> configuration.LineExceptionHandler e file index)
with | e -> configuration.FileExceptionHandler e file; Seq.empty
for line in lines do
let content, index = line
for contentregex in contentRegexes do
for mmatch in content |> contentregex.Matches do
yield (file, index, mmatch.Index, contentregex.ToString(), mmatch.Value) }
同樣,任何投入是值得歡迎的。
你見過像Parsec這樣的函數解析器嗎? – 2012-01-10 15:58:39
這是很多文字。試着把它分解成更容易閱讀。 – Marcin 2012-01-10 16:02:22
我只是簡單地使用接口和對象表達式來創建一個實例並將其暴露給C#代碼。 – 2012-01-10 18:02:47