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
)
Run this command across the source:
perl -pi.bak -e 's/(20[012][0-9])-20[12][012]/$1-2023/g' `git ls-files`
and remove changes to po{,-docs}/*.po{,t} (these will be regenerated
later when we run 'make dist').
Before this change the tests ran in about 12m34 and afterwards in
about 6m20, although the real change is more dramatic if you only run
tests from the tests/ subdirectory (as language tests still run serially).
This breaks valgrinding for now, which I intend to fix properly later.
hivex has a function hivex_value_string. We were not calling it under
the mistaken belief that because hivex implements this using iconv,
the function wouldn't work inside the daemon. Instead we
reimplemented the functionality in the library.
This commit deprecates hivex_value_utf8 and removes the library side
code. It replaces it with a plain wrapper around hivex_value_string.
Thanks: Pino Toscano
Previously the generator did not change any string returned from the
daemon. Thus guestfs_list_devices (for example) might return internal
device names like /dev/vda (if virtio-blk was in use).
This changes calls to the daemon so that returned strings are
annotated as plain strings, devices or mountables:
old ---> new
RString "uuid" RString (RPlainString "uuid")
RString "device" RString (RDevice "device")
RString "fs" RString (RMountable "fs")
For hash tables, keys and values must be annotated separately. For
example a hash table of mountables (keys) -> plain strings (values)
would be annotated like this:
old ---> new
RHashtable "fses" RHashtable (RMountable, RPlainString, "fses")
The daemon calls reverse_device_name_translation (currently a no-op)
for devices and mountables.
Note that this has no effect for calls which are handled on the
library side.
(cherry picked from commit 6b77cc196ecb8d7e1d73592ef65a189a7412c97c)
Previously we had lots of types like String, Device, StringList,
DeviceList, etc. where Device was just a String with magical
properties (but only inside the daemon), and DeviceList was just a
list of Device strings.
Replace these with some simple top-level types:
String
StringList
and move the magic into a subtype.
The change is mechanical, for example:
old ---> new
FileIn "filename" String (FileIn, "filename")
DeviceList "devices" StringList (Device, "devices")
Handling BufferIn is sufficiently different from a plain String
throughout all the bindings that it still uses a top-level type.
(Compare with FileIn/FileOut where the only difference is in the
protocol, but the bindings can uniformly treat it as a plain String.)
There is no semantic change, and the generated files are identical
except for a minor change in the (deprecated) Perl
%guestfs_introspection table.
Daemon 'proc_nr's have to be assigned monotonically and uniquely to
each daemon function. However in practice it can be difficult to work
out which is the next free proc_nr. Placing all of them into a single
table in a new file (proc_nr.ml) should make this easier.
Group the APIs logically and move them into new modules:
Actions_core:
Core APIs and anything that doesn't fit into another group, eg. launch.
(With some more effort this could be split further.)
Actions_augeas:
Augeas APIs, eg. aug-init.
Actions_debug:
Debug APIs.
Actions_hivex:
Hivex APIs, eg. hivex-open.
Actions_inspection:
Inspection APIs, eg. inspect-get-type.
Actions_properties:
Handle properties, eg. set-hv, get-hv.
Actions_tsk:
SleuthKit APIs, eg. filesystem-walk.
*_deprecated:
All of the above modules have deprecated variants, where we
place the deprecated actions.
