On Tue, 29 Aug 2006, Gerd Stolpmann wrote:

> Am Dienstag, den 29.08.2006, 15:15 -0400 schrieb Sam Steingold:
>> at any rate, do you really expect that using Gzip.input and then
>> searching the result for a newline, slicing and dicing to get the
>> individual input lines, &c &c would be faster?
>
> Ah yes, and there is an easy solution with ocamlnet:

[..snip..]

> This adds a buffering layer.

The Netchannels buffering looks very elegant, but my (admittedly rather
cursory) testing shows that it's also rather slow.

Following code implements 4 line readers:
Sam's original [char]
Netchannels [net]
open_process_in [zcat]
and buffered (trying to stay compatible with original interface) [block]

While Netchannels do win over original implementation it looses to all
other methods (on my machine).

let buf = Buffer.create 1024
let gz_input_line gz_in char_counter line_counter =
   Buffer.clear buf;
   let finish () = incr line_counter; Buffer.contents buf in
   let rec loop () =
     let ch = Gzip.input_char gz_in in
     char_counter := Int64.succ !char_counter;
     if ch = '\n' then finish () else ( Buffer.add_char buf ch; loop (); ) in
   try loop ()
   with End_of_file ->
     if Buffer.length buf = 0 then raise End_of_file else finish ()

class input_gzip_rec gzip_ch : Netchannels.rec_in_channel =
object(self)
   method input s p l =
     let n = Gzip.input gzip_ch s p l in
     if n = 0 then raise End_of_file;
     n
   method close_in() =
     Gzip.close_in gzip_ch
end

let wrap_gz gz_in =
   let s = String.create 4096 in
   let b = Buffer.create 1024 in
   let r = ref (fun _ _ -> assert false) in
   let findlf s start finish =
     let rec loop pos = if pos >= finish then None
     else if String.unsafe_get s pos = '\n' then Some pos else loop (succ pos)
     in loop start
   in
   let rec cont pos char_counter line_counter =
     let n = Gzip.input gz_in s pos (String.length s - pos) in
     let rec subcont pos len char_counter line_counter =
       let finish = pos + len in
       match findlf s pos finish with
       | None ->
           Buffer.add_substring b s pos len;
           cont 0 char_counter line_counter

       | Some lfpos ->
           let runlen = lfpos - pos in
           incr line_counter;
           Buffer.add_substring b s pos runlen;
           let s = Buffer.contents b in
           Buffer.clear b;
           r := subcont (succ lfpos) (len - succ runlen);
           s
     in
     if n = 0
     then raise End_of_file
     else (
       char_counter := Int64.add (Int64.of_int n) !char_counter;
       subcont pos n char_counter line_counter
      )
   in
   let exec c l = !r c l in
   r := cont 0;
   exec

let char () =
   let gz = Gzip.open_in_chan stdin in
   let cc = ref 0L in
   let lc = ref 0 in
   try
     while true
     do
       let _line = gz_input_line gz cc lc in
       ()
     done
   with End_of_file ->
     Format.printf "cc=%Ld lc=%d@." !cc !lc

let block () =
   let gz = Gzip.open_in_chan stdin in
   let cc = ref 0L in
   let lc = ref 0 in
   let lg = wrap_gz gz in
   try
     while true
     do
       let _line = lg cc lc in
       ()
     done
   with End_of_file ->
     Format.printf "cc=%Ld lc=%d@." !cc !lc

let zcat () =
   let ic = Unix.open_process_in "zcat" in
   let cc = ref 0L in
   let lc = ref 0 in
   try
     while true
     do
       let _line = input_line ic in
       cc := Int64.add (Int64.of_int (String.length _line + 1)) !cc;
       incr lc
     done
   with End_of_file ->
     Format.printf "cc=%Ld lc=%d@." !cc !lc

let net () =
   let gz_in = Gzip.open_in_chan stdin in
   let gz_ch = Netchannels.lift_in (`Rec (new input_gzip_rec gz_in)) in
   let cc = ref 0L in
   let lc = ref 0 in
   try
     while true
     do
       let _line = gz_ch#input_line () in
       cc := Int64.add (Int64.of_int (String.length _line + 1)) !cc;
       incr lc
     done
   with End_of_file ->
     Format.printf "cc=%Ld lc=%d@." !cc !lc

let _ =
   match Sys.argv with
   | [| _; "char" |] -> char ()
   | [| _; "zcat" |] -> zcat ()
   | [| _; "block" |] -> block ()
   | [| _; "net" |] -> net ()
   | _ -> prerr_endline (Sys.argv.(0) ^ ": [char|zcat|block|net]")

--
mailto:malc@pulsesoft.com