Created
February 22, 2011 13:48
-
-
Save jskripsky/838678 to your computer and use it in GitHub Desktop.
Extract columns from Apache access logs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
open System | |
open System.Text.RegularExpressions | |
let separator = Regex(@" (?=(?:[^\""]*\""[^\""]*\"")*(?![^\""]*\""))") | |
let split s = separator.Split s | |
let matches = Regex(@"([^\s""\[]\S*|"".*?""|\[.*?\])").Matches | |
let value (m: Match) = m.Value | |
let trim (separator: char) (s: string) = s.Trim separator;; | |
let split s = matches s |> Seq.cast |> Seq.map (value >> trim '"') |> Seq.toList | |
let toMap (keys: string list) (vals: string list) = Map.ofList (List.zip keys vals) | |
let apacheLogKeys = ["vhost"; "client"; "u1"; "u2"; "time"; "req"; "code"; "bytes"; "ref"; "agent"] | |
let apacheLogToMap = toMap apacheLogKeys | |
let test = "www.text.ch 217.69.134.177 - - [13/Feb/2011:02:08:03 +0100] \"GET / HTTP/1.0\" 200 26682 \"-\" \"Mail.Ru/1.0\"" | |
apacheLogToMap test | |
(* %v %h %l %u %t \"%r\" %>s %b "%{Referer}i" "%{User-Agent}i" *) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment