如何在OCaml中下载,解压缩和处理gzip文件?

gru*_*ewa 3 ocaml

我希望我的ocaml应用程序能够直接下载,解压缩(gzip),然后逐行处理生成的文本文件,而不使用临时文件和外部程序.

我看过的库是cohttp,ocurl和camlzip.不幸的是,我找不到让他们一起工作的好方法.

OCaml实现这一目标的方式是什么?

Sté*_*ndu 5

您可以使用管道和线程使ocurl和camlzip一起工作.概念证明:

#use "topfind";;
#thread;;
#require "unix";;
#require "curl";;
#require "zip";;

let () = Curl.(global_init CURLINIT_GLOBALALL)

let download url oc =
  let open Curl in
  let h = init () in
  setopt h (CURLOPT_URL url);
  setopt h (CURLOPT_WRITEFUNCTION (fun x -> output_string oc x; String.length x));
  perform h;
  cleanup h

let read_line really_input =
  let buf = Buffer.create 256 in
  try
    while true do
      let x = " " in
      let () = really_input x 0 1 in
      if x = "\n" then raise Exit else Buffer.add_string buf x;
    done;
    assert false
  with
  | Exit -> Buffer.contents buf
  | End_of_file -> if Buffer.length buf = 0 then raise End_of_file else Buffer.contents buf

let curl_gzip_iter f url =
  let ic, oc = Unix.pipe () in
  let ic = Unix.in_channel_of_descr ic and oc = Unix.out_channel_of_descr oc in
  let t = Thread.create (fun () -> download url oc; close_out oc) () in
  let zic = Gzip.open_in_chan ic in
  let zii = Gzip.really_input zic in
  let () =
    try
      while true do
        let () = f (read_line zii) in ()
      done;
      assert false
    with
    | End_of_file -> ()
  in
  Gzip.close_in zic;
  Thread.join t

let () = curl_gzip_iter print_endline "file:///tmp/toto.gz"
Run Code Online (Sandbox Code Playgroud)

但是,当必须处理错误时,它会变得很痛苦.