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
)
The new module ‘Std_utils’ contains only functions which are pure
OCaml and depend only on the OCaml stdlib. Therefore these functions
may be used by the generator.
The new module is moved to ‘common/mlstdutils’.
This also removes the "<stdlib>" hack, and the code which copied the
library around.
Also ‘Guestfs_config’, ‘Libdir’ and ‘StringMap’ modules are moved
since these are essentially the same.
The bulk of this change is just updating files which use
‘open Common_utils’ to add ‘open Std_utils’ where necessary.
The prototype of the hash function changed in gperf 3.1:
* The 'len' parameter of the hash function and of the lookup function is now
of type 'size_t' instead of 'unsigned int'. This makes it safe to call these
functions with strings of length > 4 GB, on 64-bit machines.
This commit moves the guestfs_int_string_to_errno function into the
third (functions) section of the gperf file so it is able to use the
lookup function without needing a prototype.
Thanks: Marius Cirsta
The prototype of the hash function changed in gperf 3.1:
* The 'len' parameter of the hash function and of the lookup function is now
of type 'size_t' instead of 'unsigned int'. This makes it safe to call these
functions with strings of length > 4 GB, on 64-bit machines.
This change tries to detect the required type in ./configure
Thanks: Marius Cirsta
For a very long time we have maintained two sets of utility functions,
in mllib/common_utils.ml and generator/utils.ml. This changes things
so that the same set of utility functions can be shared with both
directories.
It's not possible to use common_utils.ml directly in the generator
because it provides several functions that use modules outside the
OCaml stdlib. Therefore we add some lightweight post-processing which
extracts the functions using only the stdlib:
(*<stdlib>*)
...
(*</stdlib>*)
and creates generator/common_utils.ml and generator/common_utils.mli
from that. The effect is we only need to write utility functions
once.
As with other tools, we still have generator-specific utility
functions in generator/utils.ml.
Also in this change:
- Use String.uppercase_ascii and String.lowercase_ascii in place
of deprecated String.uppercase/String.lowercase.
- Implement String.capitalize_ascii to replace deprecated
String.capitalize.
- Move isspace, isdigit, isxdigit functions to Char module.
libguestfs has used double and triple underscores in identifiers.
These aren't valid for global names in C++.
The first step is to replace all guestfs___* (3 underscores) with
guestfs_int_*. We've used guestfs_int_* elsewhere already as a prefix
for internal identifiers.
This is an entirely mechanical change done using:
git ls-files | xargs perl -pi.bak -e 's/guestfs___/guestfs_int_/g'
Reference: http://stackoverflow.com/a/228797
This is a simple renaming of the files/modules.
Note that in OCaml, module names are derived from filenames by
capitalizing the first letter. Thus the old module names had the form
"Generator_api_versions". The new modules names have the form
"Api_versions".
