Richard W.M. Jones 02b64d5cec generator: Use quoted string literals in many places ...

This change was done almost entirely automatically using the script
below.  This uses the OCaml lexer to read the source files and extract
the strings and locations.  Strings which are "candidates" (in this
case, longer than 3 lines) are replaced in the output with quoted
string literals.

Since the OCaml lexer is used, it already substitutes all escape
sequences correctly.  I diffed the output of the generator and it is
identical after this change, except for UUIDs, which change because of
how Utils.stable_uuid is implemented.

Thanks: Nicolas Ojeda Bar

$ ocamlfind opt -package unix,compiler-libs.common find_strings.ml \
                -o find_strings.opt -linkpkg
$ for f in $( git ls-files -- \*.ml ) ; do ./find_strings.opt $f ; done

open Printf

let read_whole_file path =
  let buf = Buffer.create 16384 in
  let chan = open_in path in
  let maxlen = 16384 in
  let b = Bytes.create maxlen in
  let rec loop () =
    let r = input chan b 0 maxlen in
    if r > 0 then (
      Buffer.add_substring buf (Bytes.to_string b) 0 r;
      loop ()
    )
  in
  loop ();
  close_in chan;
  Buffer.contents buf

let count_chars c str =
  let count = ref 0 in
  for i = 0 to String.length str - 1 do
    if c = String.unsafe_get str i then incr count
  done;
  !count

let subs = ref []

let consider_string str loc =
  let nr_lines = count_chars '\n' str in
  if nr_lines > 3 then
    subs := (str, loc) :: !subs

let () =
  Lexer.init ();
  let filename = Sys.argv.(1) in
  let content = read_whole_file filename in
  let lexbuf = Lexing.from_string content in
  let rec loop () =
    let token = Lexer.token lexbuf in
    (match token with
     | Parser.EOF -> ();
     | STRING (s, loc, sopt) ->
        consider_string s loc; (* sopt? *)
        loop ();
     | token ->
        loop ();
    )
  in
  loop ();

  (* The list of subs is already reversed, which is convenient
   * because we must the file substitutions in reverse order.
   *)
  let subs = !subs in
  let new_content = ref content in
  List.iter (
    fun (str, loc) ->
      let { Location.loc_start = { pos_cnum = p1 };
            loc_end = { pos_cnum = p2 } } = loc in
      let len = String.length !new_content in
      let before = String.sub !new_content 0 (p1-1) in
      let after = String.sub !new_content (p2+1) (len - p2 - 1) in
      new_content := before ^ "{|" ^ str ^ "|}" ^ after
  ) subs;

  let new_content = !new_content in

  if content <> new_content then (
    (* Update the file in place. *)
    let new_filename = filename ^ ".new"
    and backup_filename = filename ^ ".bak" in
    let chan = open_out new_filename in
    fprintf chan "%s" new_content;
    close_out chan;
    Unix.rename filename backup_filename;
    Unix.rename new_filename filename
  )

2025-09-01 17:08:52 +01:00

8.6 KiB

Raw Permalink Blame History

View Raw