aboutsummaryrefslogtreecommitdiffstats
path: root/lib/stdlib
diff options
context:
space:
mode:
Diffstat (limited to 'lib/stdlib')
-rw-r--r--lib/stdlib/doc/src/gen_statem.xml2
-rw-r--r--lib/stdlib/doc/src/string.xml8
-rw-r--r--lib/stdlib/src/erl_parse.yrl3
-rw-r--r--lib/stdlib/src/erl_tar.erl47
-rw-r--r--lib/stdlib/src/erl_tar.hrl8
-rw-r--r--lib/stdlib/src/string.erl14
-rw-r--r--lib/stdlib/src/unicode.erl109
-rw-r--r--lib/stdlib/test/erl_lint_SUITE.erl6
-rw-r--r--lib/stdlib/test/string_SUITE.erl4
-rw-r--r--lib/stdlib/test/tar_SUITE.erl41
-rw-r--r--lib/stdlib/test/unicode_SUITE.erl24
-rw-r--r--lib/stdlib/test/unicode_util_SUITE.erl4
-rwxr-xr-xlib/stdlib/uc_spec/gen_unicode_mod.escript49
13 files changed, 217 insertions, 102 deletions
diff --git a/lib/stdlib/doc/src/gen_statem.xml b/lib/stdlib/doc/src/gen_statem.xml
index 1aac88c308..ad7f2f2e95 100644
--- a/lib/stdlib/doc/src/gen_statem.xml
+++ b/lib/stdlib/doc/src/gen_statem.xml
@@ -346,7 +346,7 @@ ok
<p>
To compare styles, here follows the same example using
<seealso marker="#type-callback_mode"><em>callback mode</em></seealso>
- <c>state_functions</c>, or rather the code to replace
+ <c>handle_event_function</c>, or rather the code to replace
after function <c>init/1</c> of the <c>pushbutton.erl</c>
example file above:
</p>
diff --git a/lib/stdlib/doc/src/string.xml b/lib/stdlib/doc/src/string.xml
index 343904a49a..9d5edd9ecf 100644
--- a/lib/stdlib/doc/src/string.xml
+++ b/lib/stdlib/doc/src/string.xml
@@ -311,7 +311,9 @@ true</pre>
<desc>
<p>
Returns the first codepoint in <c><anno>String</anno></c>
- and the rest of <c><anno>String</anno></c> in the tail.
+ and the rest of <c><anno>String</anno></c> in the tail. Returns
+ an empty list if <c><anno>String</anno></c> is empty or an
+ <c>{error, String}</c> tuple if the next byte is invalid.
</p>
<p><em>Example:</em></p>
<pre>
@@ -326,7 +328,9 @@ true</pre>
<desc>
<p>
Returns the first grapheme cluster in <c><anno>String</anno></c>
- and the rest of <c><anno>String</anno></c> in the tail.
+ and the rest of <c><anno>String</anno></c> in the tail. Returns
+ an empty list if <c><anno>String</anno></c> is empty or an
+ <c>{error, String}</c> tuple if the next byte is invalid.
</p>
<p><em>Example:</em></p>
<pre>
diff --git a/lib/stdlib/src/erl_parse.yrl b/lib/stdlib/src/erl_parse.yrl
index 2dcddeb8c2..733932e711 100644
--- a/lib/stdlib/src/erl_parse.yrl
+++ b/lib/stdlib/src/erl_parse.yrl
@@ -1052,6 +1052,9 @@ build_typed_attribute({atom,Aa,record},
build_typed_attribute({atom,Aa,Attr},
{type_def, {call,_,{atom,_,TypeName},Args}, Type})
when Attr =:= 'type' ; Attr =:= 'opaque' ->
+ lists:foreach(fun({var, A, '_'}) -> ret_err(A, "bad type variable");
+ (_) -> ok
+ end, Args),
case lists:all(fun({var, _, _}) -> true;
(_) -> false
end, Args) of
diff --git a/lib/stdlib/src/erl_tar.erl b/lib/stdlib/src/erl_tar.erl
index 168ea4002c..76f0b38108 100644
--- a/lib/stdlib/src/erl_tar.erl
+++ b/lib/stdlib/src/erl_tar.erl
@@ -176,7 +176,7 @@ check_extract(Name, #read_opts{files=Files}) ->
-type tar_entry() :: {filename(),
typeflag(),
non_neg_integer(),
- calendar:datetime(),
+ tar_time(),
mode(),
uid(),
gid()}.
@@ -274,8 +274,13 @@ mode_to_string(Mode, [_|T], Acc) ->
mode_to_string(_, [], Acc) ->
Acc.
-%% Converts a datetime tuple to a readable string
-time_to_string({{Y, Mon, Day}, {H, Min, _}}) ->
+%% Converts a tar_time() (POSIX time) to a readable string
+time_to_string(Secs0) ->
+ Epoch = calendar:datetime_to_gregorian_seconds(?EPOCH),
+ Secs = Epoch + Secs0,
+ DateTime0 = calendar:gregorian_seconds_to_datetime(Secs),
+ DateTime = calendar:universal_time_to_local_time(DateTime0),
+ {{Y, Mon, Day}, {H, Min, _}} = DateTime,
io_lib:format("~s ~2w ~s:~s ~w", [month(Mon), Day, two_d(H), two_d(Min), Y]).
two_d(N) ->
@@ -452,7 +457,8 @@ add(Reader, NameOrBin, NameInArchive, Options)
do_add(#reader{access=write}=Reader, Name, NameInArchive, Options)
when is_list(NameInArchive), is_list(Options) ->
- Opts = #add_opts{read_info=fun(F) -> file:read_link_info(F) end},
+ RF = fun(F) -> file:read_link_info(F, [{time, posix}]) end,
+ Opts = #add_opts{read_info=RF},
add1(Reader, Name, NameInArchive, add_opts(Options, Opts));
do_add(#reader{access=read},_,_,_) ->
{error, eacces};
@@ -460,7 +466,8 @@ do_add(Reader,_,_,_) ->
{error, {badarg, Reader}}.
add_opts([dereference|T], Opts) ->
- add_opts(T, Opts#add_opts{read_info=fun(F) -> file:read_file_info(F) end});
+ RF = fun(F) -> file:read_file_info(F, [{time, posix}]) end,
+ add_opts(T, Opts#add_opts{read_info=RF});
add_opts([verbose|T], Opts) ->
add_opts(T, Opts#add_opts{verbose=true});
add_opts([{chunks,N}|T], Opts) ->
@@ -503,7 +510,7 @@ add1(#reader{}=Reader, Name, NameInArchive, #add_opts{read_info=ReadInfo}=Opts)
end;
add1(Reader, Bin, NameInArchive, Opts) when is_binary(Bin) ->
add_verbose(Opts, "a ~ts~n", [NameInArchive]),
- Now = calendar:now_to_local_time(erlang:timestamp()),
+ Now = os:system_time(seconds),
Header = #tar_header{
name = NameInArchive,
size = byte_size(Bin),
@@ -612,7 +619,7 @@ build_header(#tar_header{}=Header, Opts) ->
devmajor=Devmaj,
devminor=Devmin
} = Header,
- Mtime = datetime_to_posix(Header#tar_header.mtime),
+ Mtime = Header#tar_header.mtime,
Block0 = ?ZERO_BLOCK,
{Block1, Pax0} = write_string(Block0, ?V7_NAME, ?V7_NAME_LEN, Name, ?PAX_PATH, #{}),
@@ -770,14 +777,6 @@ join_split_ustar_path([Part|Rest], {ok, Name, nil}) ->
join_split_ustar_path([Part|Rest], {ok, Name, Acc}) ->
join_split_ustar_path(Rest, {ok, Name, <<Acc/binary,$/,Part/binary>>}).
-datetime_to_posix(DateTime) ->
- Epoch = calendar:datetime_to_gregorian_seconds(?EPOCH),
- Secs = calendar:datetime_to_gregorian_seconds(DateTime),
- case Secs - Epoch of
- N when N < 0 -> 0;
- N -> N
- end.
-
write_octal(Block, Pos, Size, X) ->
Octal = zero_pad(format_octal(X), Size-1),
if byte_size(Octal) < Size ->
@@ -984,7 +983,7 @@ do_get_format(#header_v7{}=V7, Bin)
unpack_format(Format, #header_v7{}=V7, Bin, Reader)
when is_binary(Bin), byte_size(Bin) =:= ?BLOCK_SIZE ->
- Mtime = posix_to_erlang_time(parse_numeric(V7#header_v7.mtime)),
+ Mtime = parse_numeric(V7#header_v7.mtime),
Header0 = #tar_header{
name=parse_string(V7#header_v7.name),
mode=parse_numeric(V7#header_v7.mode),
@@ -1051,9 +1050,9 @@ unpack_modern(Format, #header_v7{}=V7, Bin, #tar_header{}=Header0)
Star = to_star(V7, Bin),
Prefix0 = parse_string(Star#header_star.prefix),
Atime0 = Star#header_star.atime,
- Atime = posix_to_erlang_time(parse_numeric(Atime0)),
+ Atime = parse_numeric(Atime0),
Ctime0 = Star#header_star.ctime,
- Ctime = posix_to_erlang_time(parse_numeric(Ctime0)),
+ Ctime = parse_numeric(Ctime0),
{Prefix0, H1#tar_header{
atime=Atime,
ctime=Ctime
@@ -1313,11 +1312,6 @@ is_header_only_type(?TYPE_LINK) -> true;
is_header_only_type(?TYPE_DIR) -> true;
is_header_only_type(_) -> false.
-posix_to_erlang_time(Sec) ->
- OneMillion = 1000000,
- Time = calendar:now_to_datetime({Sec div OneMillion, Sec rem OneMillion, 0}),
- erlang:universaltime_to_localtime(Time).
-
foldl_read(#reader{access=read}=Reader, Fun, Accu, #read_opts{}=Opts)
when is_function(Fun,4) ->
case foldl_read0(Reader, Fun, Accu, Opts) of
@@ -1423,7 +1417,7 @@ do_merge_pax(Header, [_Ignore|Rest]) ->
do_merge_pax(Header, Rest).
%% Returns the time since UNIX epoch as a datetime
--spec parse_pax_time(binary()) -> calendar:datetime().
+-spec parse_pax_time(binary()) -> tar_time().
parse_pax_time(Bin) when is_binary(Bin) ->
TotalNano = case binary:split(Bin, [<<$.>>]) of
[SecondsStr, NanoStr0] ->
@@ -1450,8 +1444,7 @@ parse_pax_time(Bin) when is_binary(Bin) ->
Micro = TotalNano div 1000,
Mega = Micro div 1000000000000,
Secs = Micro div 1000000 - (Mega*1000000),
- Micro2 = Micro rem 1000000,
- calendar:now_to_datetime({Mega, Secs, Micro2}).
+ Secs.
%% Given a regular file reader, reads the whole file and
%% parses all extended attributes it contains.
@@ -1671,7 +1664,7 @@ set_extracted_file_info(Name, #tar_header{typeflag = ?TYPE_BLOCK}=Header) ->
set_device_info(Name, Header);
set_extracted_file_info(Name, #tar_header{mtime=Mtime,mode=Mode}) ->
Info = #file_info{mode=Mode, mtime=Mtime},
- file:write_file_info(Name, Info).
+ file:write_file_info(Name, Info, [{time, posix}]).
set_device_info(Name, #tar_header{}=Header) ->
Mtime = Header#tar_header.mtime,
diff --git a/lib/stdlib/src/erl_tar.hrl b/lib/stdlib/src/erl_tar.hrl
index d646d02989..cff0c2f500 100644
--- a/lib/stdlib/src/erl_tar.hrl
+++ b/lib/stdlib/src/erl_tar.hrl
@@ -55,6 +55,8 @@
{string(), binary()} |
{string(), file:filename()}].
+-type tar_time() :: non_neg_integer().
+
%% The tar header, once fully parsed.
-record(tar_header, {
name = "" :: string(), %% name of header file entry
@@ -62,15 +64,15 @@
uid = 0 :: non_neg_integer(), %% user id of owner
gid = 0 :: non_neg_integer(), %% group id of owner
size = 0 :: non_neg_integer(), %% length in bytes
- mtime :: calendar:datetime(), %% modified time
+ mtime :: tar_time(), %% modified time
typeflag :: char(), %% type of header entry
linkname = "" :: string(), %% target name of link
uname = "" :: string(), %% user name of owner
gname = "" :: string(), %% group name of owner
devmajor = 0 :: non_neg_integer(), %% major number of character or block device
devminor = 0 :: non_neg_integer(), %% minor number of character or block device
- atime :: calendar:datetime(), %% access time
- ctime :: calendar:datetime() %% status change time
+ atime :: tar_time(), %% access time
+ ctime :: tar_time() %% status change time
}).
-type tar_header() :: #tar_header{}.
diff --git a/lib/stdlib/src/string.erl b/lib/stdlib/src/string.erl
index 17135dd64a..6f7009b5d9 100644
--- a/lib/stdlib/src/string.erl
+++ b/lib/stdlib/src/string.erl
@@ -486,12 +486,14 @@ find(String, SearchPattern, trailing) ->
%% Fetch first codepoint and return rest in tail
-spec next_grapheme(String::unicode:chardata()) ->
- maybe_improper_list(grapheme_cluster(),unicode:chardata()).
+ maybe_improper_list(grapheme_cluster(),unicode:chardata()) |
+ {error,unicode:chardata()}.
next_grapheme(CD) -> unicode_util:gc(CD).
%% Fetch first grapheme cluster and return rest in tail
-spec next_codepoint(String::unicode:chardata()) ->
- maybe_improper_list(char(),unicode:chardata()).
+ maybe_improper_list(char(),unicode:chardata()) |
+ {error,unicode:chardata()}.
next_codepoint(CD) -> unicode_util:cp(CD).
%% Internals
@@ -508,7 +510,7 @@ equal_1(A0,B0) ->
case {unicode_util:cp(A0), unicode_util:cp(B0)} of
{[CP|A],[CP|B]} -> equal_1(A,B);
{[], []} -> true;
- _ -> false
+ {L1,L2} when is_list(L1), is_list(L2) -> false
end.
equal_nocase(A, A) -> true;
@@ -517,7 +519,7 @@ equal_nocase(A0, B0) ->
unicode_util:cp(unicode_util:casefold(B0))} of
{[CP|A],[CP|B]} -> equal_nocase(A,B);
{[], []} -> true;
- _ -> false
+ {L1,L2} when is_list(L1), is_list(L2) -> false
end.
equal_norm(A, A, _Norm) -> true;
@@ -526,7 +528,7 @@ equal_norm(A0, B0, Norm) ->
unicode_util:cp(unicode_util:Norm(B0))} of
{[CP|A],[CP|B]} -> equal_norm(A,B, Norm);
{[], []} -> true;
- _ -> false
+ {L1,L2} when is_list(L1), is_list(L2) -> false
end.
equal_norm_nocase(A, A, _Norm) -> true;
@@ -535,7 +537,7 @@ equal_norm_nocase(A0, B0, Norm) ->
unicode_util:cp(unicode_util:casefold(unicode_util:Norm(B0)))} of
{[CP|A],[CP|B]} -> equal_norm_nocase(A,B, Norm);
{[], []} -> true;
- _ -> false
+ {L1,L2} when is_list(L1), is_list(L2) -> false
end.
reverse_1(CD, Acc) ->
diff --git a/lib/stdlib/src/unicode.erl b/lib/stdlib/src/unicode.erl
index aa1da400ce..fbe8a94074 100644
--- a/lib/stdlib/src/unicode.erl
+++ b/lib/stdlib/src/unicode.erl
@@ -250,89 +250,110 @@ encoding_to_bom(latin1) ->
-define(GC_N, 200). %% arbitrary number
%% Canonical decompose string to list of chars
--spec characters_to_nfd_list(chardata()) -> [char()].
+-spec characters_to_nfd_list(chardata()) -> [char()] | {error, [char()], chardata()}.
characters_to_nfd_list(CD) ->
+ characters_to_nfd_list(CD, []).
+characters_to_nfd_list(CD, Acc) ->
case unicode_util:nfd(CD) of
- [GC|Str] when is_list(GC) -> GC++characters_to_nfd_list(Str);
- [CP|Str] -> [CP|characters_to_nfd_list(Str)];
- [] -> []
+ [GC|Str] when is_list(GC) -> characters_to_nfd_list(Str, lists:reverse(GC, Acc));
+ [CP|Str] -> characters_to_nfd_list(Str, [CP | Acc]);
+ [] -> lists:reverse(Acc);
+ {error,Error} -> {error, lists:reverse(Acc), Error}
end.
--spec characters_to_nfd_binary(chardata()) -> unicode_binary().
+-spec characters_to_nfd_binary(chardata()) -> unicode_binary() | {error, unicode_binary(), chardata()}.
characters_to_nfd_binary(CD) ->
- list_to_binary(characters_to_nfd_binary(CD, ?GC_N, [])).
+ characters_to_nfd_binary(CD, ?GC_N, [], []).
-characters_to_nfd_binary(CD, N, Row) when N > 0 ->
+characters_to_nfd_binary(CD, N, Row, Acc) when N > 0 ->
case unicode_util:nfd(CD) of
- [GC|Str] -> characters_to_nfd_binary(Str, N-1, [GC|Row]);
- [] -> [characters_to_binary(lists:reverse(Row))]
+ [GC|Str] -> characters_to_nfd_binary(Str, N-1, [GC|Row], Acc);
+ [] -> acc_to_binary(prepend_row_to_acc(Row, Acc));
+ {error, Error} -> {error, acc_to_binary(prepend_row_to_acc(Row, Acc)), Error}
end;
-characters_to_nfd_binary(CD, _, Row) ->
- [characters_to_binary(lists:reverse(Row))|characters_to_nfd_binary(CD,?GC_N,[])].
+characters_to_nfd_binary(CD, _, Row, Acc) ->
+ characters_to_nfd_binary(CD, ?GC_N, [], prepend_row_to_acc(Row, Acc)).
%% Compability Canonical decompose string to list of chars.
--spec characters_to_nfkd_list(chardata()) -> [char()].
+-spec characters_to_nfkd_list(chardata()) -> [char()] | {error, [char()], chardata()}.
characters_to_nfkd_list(CD) ->
+ characters_to_nfkd_list(CD, []).
+characters_to_nfkd_list(CD, Acc) ->
case unicode_util:nfkd(CD) of
- [GC|Str] when is_list(GC) -> GC++characters_to_nfkd_list(Str);
- [CP|Str] -> [CP|characters_to_nfkd_list(Str)];
- [] -> []
+ [GC|Str] when is_list(GC) -> characters_to_nfkd_list(Str, lists:reverse(GC, Acc));
+ [CP|Str] -> characters_to_nfkd_list(Str, [CP | Acc]);
+ [] -> lists:reverse(Acc);
+ {error,Error} -> {error, lists:reverse(Acc), Error}
end.
--spec characters_to_nfkd_binary(chardata()) -> unicode_binary().
+-spec characters_to_nfkd_binary(chardata()) -> unicode_binary() | {error, unicode_binary(), chardata()}.
characters_to_nfkd_binary(CD) ->
- list_to_binary(characters_to_nfkd_binary(CD, ?GC_N, [])).
+ characters_to_nfkd_binary(CD, ?GC_N, [], []).
-characters_to_nfkd_binary(CD, N, Row) when N > 0 ->
+characters_to_nfkd_binary(CD, N, Row, Acc) when N > 0 ->
case unicode_util:nfkd(CD) of
- [GC|Str] -> characters_to_nfkd_binary(Str, N-1, [GC|Row]);
- [] -> [characters_to_binary(lists:reverse(Row))]
+ [GC|Str] -> characters_to_nfkd_binary(Str, N-1, [GC|Row], Acc);
+ [] -> acc_to_binary(prepend_row_to_acc(Row, Acc));
+ {error, Error} -> {error, acc_to_binary(prepend_row_to_acc(Row, Acc)), Error}
end;
-characters_to_nfkd_binary(CD, _, Row) ->
- [characters_to_binary(lists:reverse(Row))|characters_to_nfkd_binary(CD,?GC_N,[])].
+characters_to_nfkd_binary(CD, _, Row, Acc) ->
+ characters_to_nfkd_binary(CD, ?GC_N, [], prepend_row_to_acc(Row, Acc)).
%% Canonical compose string to list of chars
--spec characters_to_nfc_list(chardata()) -> [char()].
+-spec characters_to_nfc_list(chardata()) -> [char()] | {error, [char()], chardata()}.
characters_to_nfc_list(CD) ->
+ characters_to_nfc_list(CD, []).
+characters_to_nfc_list(CD, Acc) ->
case unicode_util:nfc(CD) of
- [CPs|Str] when is_list(CPs) -> CPs ++ characters_to_nfc_list(Str);
- [CP|Str] -> [CP|characters_to_nfc_list(Str)];
- [] -> []
+ [GC|Str] when is_list(GC) -> characters_to_nfc_list(Str, lists:reverse(GC, Acc));
+ [CP|Str] -> characters_to_nfc_list(Str, [CP | Acc]);
+ [] -> lists:reverse(Acc);
+ {error,Error} -> {error, lists:reverse(Acc), Error}
end.
--spec characters_to_nfc_binary(chardata()) -> unicode_binary().
+-spec characters_to_nfc_binary(chardata()) -> unicode_binary() | {error, unicode_binary(), chardata()}.
characters_to_nfc_binary(CD) ->
- list_to_binary(characters_to_nfc_binary(CD, ?GC_N, [])).
+ characters_to_nfc_binary(CD, ?GC_N, [], []).
-characters_to_nfc_binary(CD, N, Row) when N > 0 ->
+characters_to_nfc_binary(CD, N, Row, Acc) when N > 0 ->
case unicode_util:nfc(CD) of
- [GC|Str] -> characters_to_nfc_binary(Str, N-1, [GC|Row]);
- [] -> [characters_to_binary(lists:reverse(Row))]
+ [GC|Str] -> characters_to_nfc_binary(Str, N-1, [GC|Row], Acc);
+ [] -> acc_to_binary(prepend_row_to_acc(Row, Acc));
+ {error, Error} -> {error, acc_to_binary(prepend_row_to_acc(Row, Acc)), Error}
end;
-characters_to_nfc_binary(CD, _, Row) ->
- [characters_to_binary(lists:reverse(Row))|characters_to_nfc_binary(CD,?GC_N,[])].
+characters_to_nfc_binary(CD, _, Row, Acc) ->
+ characters_to_nfc_binary(CD, ?GC_N, [], prepend_row_to_acc(Row, Acc)).
%% Compability Canonical compose string to list of chars
--spec characters_to_nfkc_list(chardata()) -> [char()].
+-spec characters_to_nfkc_list(chardata()) -> [char()] | {error, [char()], chardata()}.
characters_to_nfkc_list(CD) ->
+ characters_to_nfkc_list(CD, []).
+characters_to_nfkc_list(CD, Acc) ->
case unicode_util:nfkc(CD) of
- [CPs|Str] when is_list(CPs) -> CPs ++ characters_to_nfkc_list(Str);
- [CP|Str] -> [CP|characters_to_nfkc_list(Str)];
- [] -> []
+ [GC|Str] when is_list(GC) -> characters_to_nfkc_list(Str, lists:reverse(GC, Acc));
+ [CP|Str] -> characters_to_nfkc_list(Str, [CP | Acc]);
+ [] -> lists:reverse(Acc);
+ {error,Error} -> {error, lists:reverse(Acc), Error}
end.
--spec characters_to_nfkc_binary(chardata()) -> unicode_binary().
+-spec characters_to_nfkc_binary(chardata()) -> unicode_binary() | {error, unicode_binary(), chardata()}.
characters_to_nfkc_binary(CD) ->
- list_to_binary(characters_to_nfkc_binary(CD, ?GC_N, [])).
+ characters_to_nfkc_binary(CD, ?GC_N, [], []).
-characters_to_nfkc_binary(CD, N, Row) when N > 0 ->
+characters_to_nfkc_binary(CD, N, Row, Acc) when N > 0 ->
case unicode_util:nfkc(CD) of
- [GC|Str] -> characters_to_nfkc_binary(Str, N-1, [GC|Row]);
- [] -> [characters_to_binary(lists:reverse(Row))]
+ [GC|Str] -> characters_to_nfkc_binary(Str, N-1, [GC|Row], Acc);
+ [] -> acc_to_binary(prepend_row_to_acc(Row, Acc));
+ {error, Error} -> {error, acc_to_binary(prepend_row_to_acc(Row, Acc)), Error}
end;
-characters_to_nfkc_binary(CD, _, Row) ->
- [characters_to_binary(lists:reverse(Row))|characters_to_nfkc_binary(CD,?GC_N,[])].
+characters_to_nfkc_binary(CD, _, Row, Acc) ->
+ characters_to_nfkc_binary(CD, ?GC_N, [], prepend_row_to_acc(Row, Acc)).
+
+acc_to_binary(Acc) ->
+ list_to_binary(lists:reverse(Acc)).
+prepend_row_to_acc(Row, Acc) ->
+ [characters_to_binary(lists:reverse(Row))|Acc].
%% internals
diff --git a/lib/stdlib/test/erl_lint_SUITE.erl b/lib/stdlib/test/erl_lint_SUITE.erl
index 02524679fa..cc3d605840 100644
--- a/lib/stdlib/test/erl_lint_SUITE.erl
+++ b/lib/stdlib/test/erl_lint_SUITE.erl
@@ -3978,7 +3978,11 @@ otp_14323(Config) ->
{13,erl_lint,{undefined_function,{a,1}}},
{14,erl_lint,{bad_dialyzer_attribute,
{nowarn_function,{a,-1}}}}],
- []}}],
+ []}},
+ {otp_14323_2,
+ <<"-type t(_) :: atom().">>,
+ [],
+ {errors,[{1,erl_parse,"bad type variable"}],[]}}],
[] = run(Config, Ts),
ok.
diff --git a/lib/stdlib/test/string_SUITE.erl b/lib/stdlib/test/string_SUITE.erl
index 4320b735ac..90f980c0e5 100644
--- a/lib/stdlib/test/string_SUITE.erl
+++ b/lib/stdlib/test/string_SUITE.erl
@@ -582,6 +582,8 @@ cd_gc(_) ->
[$e,778] = string:next_codepoint([$e,778]),
[$e|<<204,138>>] = string:next_codepoint(<<$e,778/utf8>>),
[778|_] = string:next_codepoint(tl(string:next_codepoint(<<$e,778/utf8>>))),
+ [0|<<128,1>>] = string:next_codepoint(<<0,128,1>>),
+ {error,<<128,1>>} = string:next_codepoint(<<128,1>>),
[] = string:next_grapheme(""),
[] = string:next_grapheme(<<>>),
@@ -589,6 +591,8 @@ cd_gc(_) ->
"abcd" = string:next_grapheme("abcd"),
[[$e,778]] = string:next_grapheme([$e,778]),
[[$e,778]] = string:next_grapheme(<<$e,778/utf8>>),
+ [0|<<128,1>>] = string:next_grapheme(<<0,128,1>>),
+ {error,<<128,1>>} = string:next_grapheme(<<128,1>>),
ok.
diff --git a/lib/stdlib/test/tar_SUITE.erl b/lib/stdlib/test/tar_SUITE.erl
index e9ab12e061..4061008812 100644
--- a/lib/stdlib/test/tar_SUITE.erl
+++ b/lib/stdlib/test/tar_SUITE.erl
@@ -27,7 +27,8 @@
extract_from_binary_compressed/1, extract_filtered/1,
extract_from_open_file/1, symlinks/1, open_add_close/1, cooked_compressed/1,
memory/1,unicode/1,read_other_implementations/1,
- sparse/1, init/1, leading_slash/1, dotdot/1]).
+ sparse/1, init/1, leading_slash/1, dotdot/1,
+ roundtrip_metadata/1]).
-include_lib("common_test/include/ct.hrl").
-include_lib("kernel/include/file.hrl").
@@ -41,7 +42,7 @@ all() ->
extract_filtered,
symlinks, open_add_close, cooked_compressed, memory, unicode,
read_other_implementations,
- sparse,init,leading_slash,dotdot].
+ sparse,init,leading_slash,dotdot,roundtrip_metadata].
groups() ->
[].
@@ -953,6 +954,42 @@ dotdot(Config) ->
ok.
+roundtrip_metadata(Config) ->
+ PrivDir = proplists:get_value(priv_dir, Config),
+ Dir = filename:join(PrivDir, ?FUNCTION_NAME),
+ ok = file:make_dir(Dir),
+
+ do_roundtrip_metadata(Dir, "name-does-not-matter"),
+ ok.
+
+do_roundtrip_metadata(Dir, File) ->
+ Tar = filename:join(Dir, atom_to_list(?FUNCTION_NAME)++".tar"),
+ BeamFile = code:which(compile),
+ {ok,Fd} = erl_tar:open(Tar, [write]),
+ ok = erl_tar:add(Fd, BeamFile, File, []),
+ ok = erl_tar:close(Fd),
+
+ ok = erl_tar:extract(Tar, [{cwd,Dir}]),
+
+ %% Make sure that size and modification times are the same
+ %% on all platforms.
+ {ok,OrigInfo} = file:read_file_info(BeamFile),
+ ExtractedFile = filename:join(Dir, File),
+ {ok,ExtractedInfo} = file:read_file_info(ExtractedFile),
+ #file_info{size=Size,mtime=Mtime,type=regular} = OrigInfo,
+ #file_info{size=Size,mtime=Mtime,type=regular} = ExtractedInfo,
+
+ %% On Unix platforms more fields are expected to be the same.
+ case os:type() of
+ {unix,_} ->
+ #file_info{access=Access,mode=Mode} = OrigInfo,
+ #file_info{access=Access,mode=Mode} = ExtractedInfo,
+ ok;
+ _ ->
+ ok
+ end.
+
+
%% Delete the given list of files.
delete_files([]) -> ok;
delete_files([Item|Rest]) ->
diff --git a/lib/stdlib/test/unicode_SUITE.erl b/lib/stdlib/test/unicode_SUITE.erl
index 3d97ab93f1..e01ba3fbb0 100644
--- a/lib/stdlib/test/unicode_SUITE.erl
+++ b/lib/stdlib/test/unicode_SUITE.erl
@@ -998,6 +998,30 @@ normalize(_) ->
true = unicode:characters_to_nfkc_list("ホンダ") =:= unicode:characters_to_nfkc_list("ﾎﾝﾀﾞ"),
true = unicode:characters_to_nfkd_list("32") =:= unicode:characters_to_nfkd_list("３２"),
+
+ {error, [0], <<128>>} = unicode:characters_to_nfc_list(<<0, 128>>),
+ {error, [0], <<128>>} = unicode:characters_to_nfkc_list(<<0, 128>>),
+ {error, [0], <<128>>} = unicode:characters_to_nfd_list(<<0, 128>>),
+ {error, [0], <<128>>} = unicode:characters_to_nfkd_list(<<0, 128>>),
+
+ {error, <<0>>, <<128>>} = unicode:characters_to_nfc_binary(<<0, 128>>),
+ {error, <<0>>, <<128>>} = unicode:characters_to_nfkc_binary(<<0, 128>>),
+ {error, <<0>>, <<128>>} = unicode:characters_to_nfd_binary(<<0, 128>>),
+ {error, <<0>>, <<128>>} = unicode:characters_to_nfkd_binary(<<0, 128>>),
+
+ LargeBin = binary:copy(<<"abcde">>, 50),
+ LargeList = binary_to_list(LargeBin),
+
+ {error, LargeList, <<128>>} = unicode:characters_to_nfc_list(<<LargeBin/binary, 128>>),
+ {error, LargeList, <<128>>} = unicode:characters_to_nfkc_list(<<LargeBin/binary, 128>>),
+ {error, LargeList, <<128>>} = unicode:characters_to_nfd_list(<<LargeBin/binary, 128>>),
+ {error, LargeList, <<128>>} = unicode:characters_to_nfkd_list(<<LargeBin/binary, 128>>),
+
+ {error, LargeBin, <<128>>} = unicode:characters_to_nfc_binary(<<LargeBin/binary, 128>>),
+ {error, LargeBin, <<128>>} = unicode:characters_to_nfkc_binary(<<LargeBin/binary, 128>>),
+ {error, LargeBin, <<128>>} = unicode:characters_to_nfd_binary(<<LargeBin/binary, 128>>),
+ {error, LargeBin, <<128>>} = unicode:characters_to_nfkd_binary(<<LargeBin/binary, 128>>),
+
ok.
diff --git a/lib/stdlib/test/unicode_util_SUITE.erl b/lib/stdlib/test/unicode_util_SUITE.erl
index e9b3d7f98d..03c24c7027 100644
--- a/lib/stdlib/test/unicode_util_SUITE.erl
+++ b/lib/stdlib/test/unicode_util_SUITE.erl
@@ -97,6 +97,8 @@ cp(_) ->
"hejsan" = fetch(<<"hejsan">>, Get),
"hejsan" = fetch(["hej",<<"san">>], Get),
"hejsan" = fetch(["hej"|<<"san">>], Get),
+ {error, <<128>>} = Get(<<128>>),
+ {error, [<<128>>, 0]} = Get([<<128>>, 0]),
ok.
gc(Config) ->
@@ -106,6 +108,8 @@ gc(Config) ->
"hejsan" = fetch(<<"hejsan">>, Get),
"hejsan" = fetch(["hej",<<"san">>], Get),
"hejsan" = fetch(["hej"|<<"san">>], Get),
+ {error, <<128>>} = Get(<<128>>),
+ {error, [<<128>>, 0]} = Get([<<128>>, 0]),
0 = fold(fun verify_gc/3, 0, DataDir ++ "/GraphemeBreakTest.txt"),
ok.
diff --git a/lib/stdlib/uc_spec/gen_unicode_mod.escript b/lib/stdlib/uc_spec/gen_unicode_mod.escript
index c8b815e435..fefd7d3b70 100755
--- a/lib/stdlib/uc_spec/gen_unicode_mod.escript
+++ b/lib/stdlib/uc_spec/gen_unicode_mod.escript
@@ -170,7 +170,7 @@ gen_header(Fd) ->
io:put_chars(Fd, "-export([spec_version/0, lookup/1, get_case/1]).\n"),
io:put_chars(Fd, "-inline([class/1]).\n"),
io:put_chars(Fd, "-compile(nowarn_unused_vars).\n"),
- io:put_chars(Fd, "-dialyzer({no_improper_lists, cp/1}).\n"),
+ io:put_chars(Fd, "-dialyzer({no_improper_lists, [cp/1, gc_prepend/2, gc_e_cont/2]}).\n"),
io:put_chars(Fd, "-type gc() :: char()|[char()].\n\n\n"),
ok.
@@ -237,39 +237,43 @@ gen_static(Fd) ->
gen_norm(Fd) ->
io:put_chars(Fd,
- "-spec nfd(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()).\n"
+ "-spec nfd(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()) | {error, unicode:chardata()}.\n"
"nfd(Str0) ->\n"
" case gc(Str0) of\n"
" [GC|R] when GC < 127 -> [GC|R];\n"
" [GC|Str] -> [decompose(GC)|Str];\n"
- " [] -> []\n end.\n\n"
+ " [] -> [];\n"
+ " {error,_}=Error -> Error\n end.\n\n"
),
io:put_chars(Fd,
- "-spec nfkd(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()).\n"
+ "-spec nfkd(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()) | {error, unicode:chardata()}.\n"
"nfkd(Str0) ->\n"
" case gc(Str0) of\n"
" [GC|R] when GC < 127 -> [GC|R];\n"
" [GC|Str] -> [decompose_compat(GC)|Str];\n"
- " [] -> []\n end.\n\n"
+ " [] -> [];\n"
+ " {error,_}=Error -> Error\n end.\n\n"
),
io:put_chars(Fd,
- "-spec nfc(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()).\n"
+ "-spec nfc(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()) | {error, unicode:chardata()}.\n"
"nfc(Str0) ->\n"
" case gc(Str0) of\n"
" [GC|R] when GC < 255 -> [GC|R];\n"
" [GC|Str] -> [compose(decompose(GC))|Str];\n"
- " [] -> []\n end.\n\n"
+ " [] -> [];\n"
+ " {error,_}=Error -> Error\n end.\n\n"
),
io:put_chars(Fd,
- "-spec nfkc(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()).\n"
+ "-spec nfkc(unicode:chardata()) -> maybe_improper_list(gc(),unicode:chardata()) | {error, unicode:chardata()}.\n"
"nfkc(Str0) ->\n"
" case gc(Str0) of\n"
" [GC|R] when GC < 127 -> [GC|R];\n"
" [GC|Str] -> [compose_compat_0(decompose_compat(GC))|Str];\n"
- " [] -> []\n end.\n\n"
+ " [] -> [];\n"
+ " {error,_}=Error -> Error\n end.\n\n"
),
io:put_chars(Fd,
@@ -448,18 +452,20 @@ gen_ws(Fd, Props) ->
gen_cp(Fd) ->
io:put_chars(Fd, "-spec cp(String::unicode:chardata()) ->"
- " maybe_improper_list().\n"),
+ " maybe_improper_list() | {error, unicode:chardata()}.\n"),
io:put_chars(Fd, "cp([C|_]=L) when is_integer(C) -> L;\n"),
io:put_chars(Fd, "cp([List]) -> cp(List);\n"),
io:put_chars(Fd, "cp([List|R]) ->\n"),
io:put_chars(Fd, " case cp(List) of\n"),
io:put_chars(Fd, " [] -> cp(R);\n"),
io:put_chars(Fd, " [CP] -> [CP|R];\n"),
- io:put_chars(Fd, " [C|R0] -> [C|[R0|R]]\n"),
+ io:put_chars(Fd, " [C|R0] -> [C|[R0|R]];\n"),
+ io:put_chars(Fd, " {error,Error} -> {error,[Error|R]}\n"),
io:put_chars(Fd, " end;\n"),
io:put_chars(Fd, "cp([]) -> [];\n"),
io:put_chars(Fd, "cp(<<C/utf8, R/binary>>) -> [C|R];\n"),
- io:put_chars(Fd, "cp(<<>>) -> [].\n\n"),
+ io:put_chars(Fd, "cp(<<>>) -> [];\n"),
+ io:put_chars(Fd, "cp(<<R/binary>>) -> {error,R}.\n\n"),
ok.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@@ -468,7 +474,7 @@ gen_gc(Fd, GBP) ->
%% see http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundary_Rules
io:put_chars(Fd,
"-spec gc(String::unicode:chardata()) ->"
- " maybe_improper_list().\n"),
+ " maybe_improper_list() | {error, unicode:chardata()}.\n"),
io:put_chars(Fd,
"gc(Str) ->\n"
" gc_1(cp(Str)).\n\n"
@@ -521,7 +527,8 @@ gen_gc(Fd, GBP) ->
[GenEBG(CP) || CP <- merge_ranges(maps:get(e_base_gaz,GBP))],
io:put_chars(Fd, "gc_1([CP|R]) -> gc_extend(R, CP);\n"),
- io:put_chars(Fd, "gc_1([]) -> [].\n\n"),
+ io:put_chars(Fd, "gc_1([]) -> [];\n"),
+ io:put_chars(Fd, "gc_1({error,_}=Error) -> Error.\n\n"),
io:put_chars(Fd, "%% Handle Prepend\n"),
io:put_chars(Fd,
@@ -536,7 +543,8 @@ gen_gc(Fd, GBP) ->
" [GC|R1] -> [[CP0|GC]|R1]\n"
" end\n"
" end;\n"
- " [] -> [CP0]\n"
+ " [] -> [CP0];\n"
+ " {error,R} -> [CP0|R]\n"
" end.\n\n"),
IsCtrl = fun(Range) -> io:format(Fd, "is_control~s true;\n", [gen_single_clause(Range)]) end,
@@ -574,7 +582,10 @@ gen_gc(Fd, GBP) ->
" [_]=Acc -> Acc;\n"
" [_|_]=Acc -> [lists:reverse(Acc)];\n"
" Acc -> [Acc]\n"
- " end.\n\n"),
+ " end;\n"
+ "gc_extend({error,R}, T, Acc0) ->\n"
+ " gc_extend([], T, Acc0) ++ [R].\n\n"
+ ),
[ZWJ] = maps:get(zwj, GBP),
GenExtend = fun(R) when R =:= ZWJ -> io:format(Fd, "is_extend~s zwj;\n", [gen_single_clause(ZWJ)]);
(Range) -> io:format(Fd, "is_extend~s true;\n", [gen_single_clause(Range)])
@@ -604,6 +615,11 @@ gen_gc(Fd, GBP) ->
" case Acc of\n"
" [A] -> [A];\n"
" _ -> [lists:reverse(Acc)]\n"
+ " end;\n"
+ " {error,R} ->\n"
+ " case Acc of\n"
+ " [A] -> [A|R];\n"
+ " _ -> [lists:reverse(Acc)|R]\n"
" end\n"
" end.\n\n"),
@@ -660,6 +676,7 @@ gen_gc(Fd, GBP) ->
[GenHangulT_1(CP) || CP <- merge_ranges(maps:get(t,GBP))],
io:put_chars(Fd, " R1 -> gc_extend(R1, R0, Acc)\n end.\n\n"),
+ io:put_chars(Fd, "gc_h_lv_lvt({error,_}=Error, Acc) -> gc_extend(Error, [], Acc);\n"),
io:put_chars(Fd, "%% Handle Hangul LV\n"),
GenHangulLV = fun(Range) -> io:format(Fd, "gc_h_lv_lvt~s gc_h_V(R1,[CP|Acc]);\n",
[gen_clause2(Range)]) end,
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-23 23:10:26 +0000