diff options
Diffstat (limited to 'lib/stdlib')
-rw-r--r-- | lib/stdlib/doc/src/binary.xml | 15 | ||||
-rw-r--r-- | lib/stdlib/doc/src/gen_statem.xml | 2 | ||||
-rw-r--r-- | lib/stdlib/doc/src/notes.xml | 310 | ||||
-rw-r--r-- | lib/stdlib/src/erl_lint.erl | 12 | ||||
-rw-r--r-- | lib/stdlib/src/io_lib.erl | 23 | ||||
-rw-r--r-- | lib/stdlib/src/io_lib_format.erl | 110 | ||||
-rw-r--r-- | lib/stdlib/src/io_lib_pretty.erl | 57 | ||||
-rw-r--r-- | lib/stdlib/src/stdlib.app.src | 2 | ||||
-rw-r--r-- | lib/stdlib/src/stdlib.appup.src | 34 | ||||
-rw-r--r-- | lib/stdlib/src/string.erl | 78 | ||||
-rw-r--r-- | lib/stdlib/test/erl_lint_SUITE.erl | 24 | ||||
-rw-r--r-- | lib/stdlib/test/erl_pp_SUITE.erl | 2 | ||||
-rw-r--r-- | lib/stdlib/test/io_SUITE.erl | 46 | ||||
-rw-r--r-- | lib/stdlib/test/string_SUITE.erl | 63 | ||||
-rw-r--r-- | lib/stdlib/test/unicode_util_SUITE.erl | 10 | ||||
-rw-r--r-- | lib/stdlib/uc_spec/gen_unicode_mod.escript | 26 | ||||
-rw-r--r-- | lib/stdlib/vsn.mk | 2 |
17 files changed, 669 insertions, 147 deletions
diff --git a/lib/stdlib/doc/src/binary.xml b/lib/stdlib/doc/src/binary.xml index f3d4edd30f..fd991f258b 100644 --- a/lib/stdlib/doc/src/binary.xml +++ b/lib/stdlib/doc/src/binary.xml @@ -505,15 +505,16 @@ store(Binary, GBSet) -> <<1,1,1,1,1 ... 2> byte_size(A). 100 -3> binary:referenced_byte_size(A) +3> binary:referenced_byte_size(A). 100 -4> <<_:10/binary,B:10/binary,_/binary>> = A. +4> <<B:10/binary, C:90/binary>> = A. <<1,1,1,1,1 ... -5> byte_size(B). -10 -6> binary:referenced_byte_size(B) -100</code> - +5> {byte_size(B), binary:referenced_byte_size(B)}. +{10,10} +6> {byte_size(C), binary:referenced_byte_size(C)}. +{90,100}</code> + <p>In the above example, the small binary <c>B</c> was copied while the + larger binary <c>C</c> references binary <c>A</c>.</p> <note> <p>Binary data is shared among processes. If another process still references the larger binary, copying the part this diff --git a/lib/stdlib/doc/src/gen_statem.xml b/lib/stdlib/doc/src/gen_statem.xml index 6f6849a19d..ef548ad643 100644 --- a/lib/stdlib/doc/src/gen_statem.xml +++ b/lib/stdlib/doc/src/gen_statem.xml @@ -40,7 +40,7 @@ <p> This reference manual describes types generated from the types in the <c>gen_statem</c> source code, so they are correct. - However, the generated descriptions also reflect the type hiearchy, + However, the generated descriptions also reflect the type hierarchy, which makes them kind of hard to read. </p> <p> diff --git a/lib/stdlib/doc/src/notes.xml b/lib/stdlib/doc/src/notes.xml index 65650a25c7..5c07dd2ee6 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -31,6 +31,316 @@ </header> <p>This document describes the changes made to the STDLIB application.</p> +<section><title>STDLIB 3.9.2</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> Fix a bug that could cause a loop when formatting + terms using the control sequences <c>p</c> or <c>P</c> + and limiting the output with the option + <c>chars_limit</c>. </p> + <p> + Own Id: OTP-15875 Aux Id: ERL-967 </p> + </item> + </list> + </section> + +</section> + +<section><title>STDLIB 3.9.1</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> Fix a bug that could cause a failure when formatting + binaries using the control sequences <c>p</c> or <c>P</c> + and limiting the output with the option + <c>chars_limit</c>. </p> + <p> + Own Id: OTP-15847 Aux Id: ERL-957 </p> + </item> + </list> + </section> + +</section> + +<section><title>STDLIB 3.9</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> Fix a bug in <c>string:lexemes/2</c>. </p> <p> The + bug was found when optimizing the handling of deep lists + of Unicode characters in the <c>string</c> module. </p> + <p> + Own Id: OTP-15649</p> + </item> + <item> + <p>A bug has been fixed in the <c>maps</c> implementation + that could cause a crash or memory usage to grow until + the machine ran out of memory. This could happen when + inserting a new key-value pair with a key <c>K1</c> + containing a binary <c>B1</c> into a map <c>M</c> having + a key <c>K2</c> with a binary <c>B2</c> if the following + conditions were met:</p> <list> <item><c>B1 =/= + B2</c></item> <item><c>size(B1) >= 4294967296</c></item> + <item><c>size(B2) >= 4294967296</c></item> + <item><c>size(M) >= 32</c></item> <item><c>(size(B1) rem + 4294967296) == (size(B2) rem 4294967296)</c></item> + <item>the first <c>(size(B1) rem 4294967296)</c> bytes + are the same both in <c>B1</c> and <c>B2</c></item> + <item>substituting <c>B1</c> in <c>K1</c> with <c>B2</c> + would create a term with the same value as + <c>K2</c></item> </list> <p>The root cause of the problem + is that the <c>maps</c> implementation only hashed the + first <c>(X rem 4294967296)</c> bytes of binaries so that + different binaries could get the same hash value + independently of the hash seed.</p> + <p> + Own Id: OTP-15707</p> + </item> + <item> + <p> Since the introduction of the stack trace variable, + the Erlang Pretty Printer has left out the exception + class <c>throw</c> even when the stack trace variable + cannot be left out, which is not correct Erlang code. The + fix is to always include the exception class + <c>throw</c>. </p> + <p> + Own Id: OTP-15751</p> + </item> + <item> + <p><c>record_info/2</c> is a pseudo-function that + requires literal arguments known at compile time. + Therefore, the following usage is illegal: <c>fun + record/info/2</c>. The compiler would crash when during + compilation of that kind of code. Corrected to issue a + compilation error.</p> + <p> + Own Id: OTP-15760 Aux Id: ERL-907 </p> + </item> + </list> + </section> + + + <section><title>Improvements and New Features</title> + <list> + <item> + <p> A new <c>rand</c> module algorithm, <c>exro928ss</c> + (Xoroshiro928**), has been implemented. It has got a + really long period and good statistical quality for all + output bits, while still being only about 50% slower than + the default algorithm. </p><p> The same generator is also + used as a long period counter in a new <c>crypto</c> + plugin for the <c>rand</c> module, algorithm + <c>crypto_aes</c>. This plugin uses AES-256 to scramble + the counter which buries any detectable statistical + artifacts. Scrambling is done in chunks which are cached + to get good amortized speed (about half of the default + algorithm). </p> + <p> + Own Id: OTP-14461 Aux Id: PR-1857 </p> + </item> + <item> + <p> + Types related to server naming and starting have been + exported from <c>gen_statem</c>. These are: + <c>server_name/0</c>, <c>server_ref/0</c>, + <c>start_opt/0</c>, <c>start_ret/0</c> and + <c>enter_loop_opt/0</c>.</p> + <p> + Own Id: OTP-14724 Aux Id: PR-2056 </p> + </item> + <item> + <p> + The default algorithm for the <c>rand</c> module has been + changed to <c>exsss</c> (Xorshift116**) which is a + combination of the Xorshift116 (<c>exsp</c>) state update + and a new scrambler "StarStar" from the 2018 paper + "Scrambled Linear Pseudorandom Number Generators" by + David Blackman and Sebastiano Vigna. This combination + should not have the caveat of weak low bits that the + previous default algorithm(s) have had, with the cost of + about 10% lower speed. See GitHub pull request #1969.</p> + <p> + Own Id: OTP-14731 Aux Id: PR-1969 </p> + </item> + <item> + <p> + The generic state machine behaviour <c>gen_statem</c> has + gotten code cleanup and documentation improvements from + GitHub Pull Request #1855, even though the PR itself was + rejected.</p> + <p> + Own Id: OTP-14737 Aux Id: PR-1855 </p> + </item> + <item> + <p> + Update Unicode specification to version 11.0.</p> + <p> + Own Id: OTP-15111</p> + </item> + <item> + <p> + ETS option <c>write_concurrency</c> now also affects and + improves the scalability of <c>ordered_set</c> tables. + The implementation is based on a data structure called + contention adapting search tree, where the lock + granularity adapts to the actual amount of concurrency + exploited by the applications in runtime.</p> + <p> + Own Id: OTP-15128</p> + </item> + <item> + <p> + Optimized <c>maps:new/0</c> with trivial Erlang + implementation, making use of literal terms (the empty + map) not needing dynamic heap allocation.</p> + <p> + Own Id: OTP-15200 Aux Id: PR-1878 </p> + </item> + <item> + <p>The <c>gen_*</c> behaviours have been changed so that + if logging of the last N messages through + <c>sys:log/2,3</c> is active for the server, this log is + included in the terminate report.</p> <p>To accomplish + this the format of "System Events" as defined in the man + page for <c>sys</c> has been clarified and cleaned up, a + new function <c>sys:get_log/1</c> has been added, and + <c>sys:get_debug/3</c> has been deprecated. Due to these + changes, code that relies on the internal badly + documented format of "System Events", need to be + corrected.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-15381</p> + </item> + <item> + <p> + The <c>gen_statem</c> behaviour engine loop has been + optimized for better performance in particular when the + callback module returns some actions, that is better + performance for more realistic applications than the Echo + Benchmark.</p> + <p> + Own Id: OTP-15452</p> + </item> + <item> + <p> Do not allow function specifications for functions + residing in other modules. </p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-15563 Aux Id: ERL-845, OTP-15562 </p> + </item> + <item> + <p> + The <c>persistent_term</c> functions <c>put/2</c> and + <c>erase/1</c> are now yielding.</p> + <p> + Own Id: OTP-15615</p> + </item> + <item> + <p>Previously, all ETS tables used centralized counter + variables to keep track of the number of items stored and + the amount of memory consumed. These counters can cause + scalability problems (especially on big NUMA systems). + This change adds an implementation of a decentralized + counter and modifies the implementation of ETS so that + ETS tables of type <c>ordered_set</c> with + <c>write_concurrency</c> enabled use the decentralized + counter. Experiments indicate that this change + substantially improves the scalability of ETS + <c>ordered_set</c> tables with <c>write_concurrency</c> + enabled in scenarios with frequent <c>ets:insert/2</c> + and <c>ets:delete/2</c> calls.</p> + <p> + Own Id: OTP-15623 Aux Id: PR-2190 </p> + </item> + <item> + <p> Use <c>ssh</c> instead of <c>rsh</c> as the default + remote shell. </p> + <p> + Own Id: OTP-15633 Aux Id: PR-1787 </p> + </item> + <item> + <p>Added <c>beam_lib:strip/2</c> and friends, which + accept a list of chunks that should be preserved when + stripping.</p> + <p> + Own Id: OTP-15680 Aux Id: PR-2114 </p> + </item> + <item> + <p> Optimize printing of maps with <c>io_lib:write()</c>. + Also optimize pretty printing of strings (<c>~s</c> and + <c>~ts</c>) when limiting the output with the + <c>chars_limit</c> option. </p> + <p> + Own Id: OTP-15705</p> + </item> + <item> + <p> There are new compiler options <c>nowarn_removed</c> + and <c>{nowarn_removed,Items}</c> to suppress warnings + for functions and modules that have been removed from + OTP.</p> + <p> + Own Id: OTP-15749 Aux Id: ERL-904 </p> + </item> + <item> + <p> Let the Erlang Pretty Printer put atomic parts on the + same line. </p> + <p> + Own Id: OTP-15755</p> + </item> + <item> + <p> Add option <c>quote_singleton_atom_types</c> to the + Erlang Pretty Printer's functions. Setting the option to + <c>true</c> adds quotes to all singleton atom types. </p> + <p> + Own Id: OTP-15756</p> + </item> + </list> + </section> + +</section> + +<section><title>STDLIB 3.8.2.1</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> Fix a bug that could cause a failure when formatting + binaries using the control sequences <c>p</c> or <c>P</c> + and limiting the output with the option + <c>chars_limit</c>. </p> + <p> + Own Id: OTP-15847 Aux Id: ERL-957 </p> + </item> + </list> + </section> + +</section> + +<section><title>STDLIB 3.8.2</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> + A bug in gen_statem has been fixed where the internal + timeout message could arrive as an info to the callback + module during high load due to incorrect use of + asynchronous timer cancel.</p> + <p> + Own Id: OTP-15295</p> + </item> + </list> + </section> + +</section> + <section><title>STDLIB 3.8.1</title> <section><title>Fixed Bugs and Malfunctions</title> diff --git a/lib/stdlib/src/erl_lint.erl b/lib/stdlib/src/erl_lint.erl index e0c37ca030..0cd0aef124 100644 --- a/lib/stdlib/src/erl_lint.erl +++ b/lib/stdlib/src/erl_lint.erl @@ -2,7 +2,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1996-2018. All Rights Reserved. +%% Copyright Ericsson AB 1996-2019. All Rights Reserved. %% %% Licensed under the Apache License, Version 2.0 (the "License"); %% you may not use this file except in compliance with the License. @@ -386,6 +386,8 @@ format_error({redefine_callback, {F, A}}) -> format_error({bad_callback, {M, F, A}}) -> io_lib:format("explicit module not allowed for callback ~tw:~tw/~w", [M, F, A]); +format_error({bad_module, {M, F, A}}) -> + io_lib:format("spec for function ~w:~tw/~w from other module", [M, F, A]); format_error({spec_fun_undefined, {F, A}}) -> io_lib:format("spec for undefined function ~tw/~w", [F, A]); format_error({missing_spec, {F,A}}) -> @@ -3010,7 +3012,13 @@ spec_decl(Line, MFA0, TypeSpecs, St00 = #lint{specs = Specs, module = Mod}) -> St1 = St0#lint{specs = dict:store(MFA, Line, Specs)}, case dict:is_key(MFA, Specs) of true -> add_error(Line, {redefine_spec, MFA0}, St1); - false -> check_specs(TypeSpecs, spec_wrong_arity, Arity, St1) + false -> + case MFA of + {Mod, _, _} -> + check_specs(TypeSpecs, spec_wrong_arity, Arity, St1); + _ -> + add_error(Line, {bad_module, MFA}, St1) + end end. %% callback_decl(Line, Fun, Types, State) -> State. diff --git a/lib/stdlib/src/io_lib.erl b/lib/stdlib/src/io_lib.erl index 2b5a374cf2..21d66c5529 100644 --- a/lib/stdlib/src/io_lib.erl +++ b/lib/stdlib/src/io_lib.erl @@ -412,14 +412,25 @@ write_port(Port) -> write_ref(Ref) -> erlang:ref_to_list(Ref). +write_map(_, 1, _E) -> "#{}"; write_map(Map, D, E) when is_integer(D) -> - [$#,${,write_map_body(maps:to_list(Map), D, D - 1, E),$}]. + I = maps:iterator(Map), + case maps:next(I) of + {K, V, NextI} -> + D0 = D - 1, + W = write_map_assoc(K, V, D0, E), + [$#,${,[W | write_map_body(NextI, D0, D0, E)],$}]; + none -> "#{}" + end. -write_map_body(_, 1, _D0, _E) -> "..."; -write_map_body([], _, _D0, _E) -> []; -write_map_body([{K,V}], _D, D0, E) -> write_map_assoc(K, V, D0, E); -write_map_body([{K,V}|KVs], D, D0, E) -> - [write_map_assoc(K, V, D0, E),$, | write_map_body(KVs, D - 1, D0, E)]. +write_map_body(_, 1, _D0, _E) -> ",..."; +write_map_body(I, D, D0, E) -> + case maps:next(I) of + {K, V, NextI} -> + W = write_map_assoc(K, V, D0, E), + [$,,W|write_map_body(NextI, D - 1, D0, E)]; + none -> "" + end. write_map_assoc(K, V, D, E) -> [write1(K, D, E)," => ",write1(V, D, E)]. diff --git a/lib/stdlib/src/io_lib_format.erl b/lib/stdlib/src/io_lib_format.erl index d1aa4cd157..157cc07e19 100644 --- a/lib/stdlib/src/io_lib_format.erl +++ b/lib/stdlib/src/io_lib_format.erl @@ -327,11 +327,11 @@ indentation([], I) -> I. %% PadChar, Encoding, StringP, ChrsLim, Indentation) -> String %% These are the dispatch functions for the various formatting controls. -control_small($s, [A], F, Adj, P, Pad, latin1) when is_atom(A) -> +control_small($s, [A], F, Adj, P, Pad, latin1=Enc) when is_atom(A) -> L = iolist_to_chars(atom_to_list(A)), - string(L, F, Adj, P, Pad); -control_small($s, [A], F, Adj, P, Pad, unicode) when is_atom(A) -> - string(atom_to_list(A), F, Adj, P, Pad); + string(L, F, Adj, P, Pad, Enc); +control_small($s, [A], F, Adj, P, Pad, unicode=Enc) when is_atom(A) -> + string(atom_to_list(A), F, Adj, P, Pad, Enc); control_small($e, [A], F, Adj, P, Pad, _Enc) when is_float(A) -> fwrite_e(A, F, Adj, P, Pad); control_small($f, [A], F, Adj, P, Pad, _Enc) when is_float(A) -> @@ -371,12 +371,12 @@ control_small($n, [], F, Adj, P, Pad, _Enc) -> newline(F, Adj, P, Pad); control_small($i, [_A], _F, _Adj, _P, _Pad, _Enc) -> []; control_small(_C, _As, _F, _Adj, _P, _Pad, _Enc) -> not_small. -control_limited($s, [L0], F, Adj, P, Pad, latin1, _Str, CL, _I) -> - L = iolist_to_chars(L0), - string(limit_string(L, F, CL), limit_field(F, CL), Adj, P, Pad); -control_limited($s, [L0], F, Adj, P, Pad, unicode, _Str, CL, _I) -> - L = cdata_to_chars(L0), - uniconv(string(limit_string(L, F, CL), limit_field(F, CL), Adj, P, Pad)); +control_limited($s, [L0], F, Adj, P, Pad, latin1=Enc, _Str, CL, _I) -> + L = iolist_to_chars(L0, F, CL), + string(L, limit_field(F, CL), Adj, P, Pad, Enc); +control_limited($s, [L0], F, Adj, P, Pad, unicode=Enc, _Str, CL, _I) -> + L = cdata_to_chars(L0, F, CL), + uniconv(string(L, limit_field(F, CL), Adj, P, Pad, Enc)); control_limited($w, [A], F, Adj, P, Pad, Enc, _Str, CL, _I) -> Chars = io_lib:write(A, [{depth, -1}, {encoding, Enc}, {chars_limit, CL}]), term(Chars, F, Adj, P, Pad); @@ -718,7 +718,10 @@ fwrite_g(Fl, F, Adj, P, Pad) when P >= 1 -> end. -%% iolist_to_chars(iolist()) -> io_lib:chars() +iolist_to_chars(Cs, F, CharsLimit) when CharsLimit < 0; CharsLimit >= F -> + iolist_to_chars(Cs); +iolist_to_chars(Cs, _, CharsLimit) -> + limit_iolist_to_chars(Cs, sub(CharsLimit, 3), [], normal). % three dots iolist_to_chars([C|Cs]) when is_integer(C), C >= $\000, C =< $\377 -> [C | iolist_to_chars(Cs)]; @@ -729,12 +732,34 @@ iolist_to_chars([]) -> iolist_to_chars(B) when is_binary(B) -> binary_to_list(B). -%% cdata() :: clist() | cbinary() -%% clist() :: maybe_improper_list(char() | cbinary() | clist(), -%% cbinary() | nil()) -%% cbinary() :: unicode:unicode_binary() | unicode:latin1_binary() +limit_iolist_to_chars(Cs, 0, S, normal) -> + L = limit_iolist_to_chars(Cs, 4, S, final), + case iolist_size(L) of + N when N < 4 -> L; + 4 -> "..." + end; +limit_iolist_to_chars(_Cs, 0, _S, final) -> []; +limit_iolist_to_chars([C|Cs], Limit, S, Mode) when C >= $\000, C =< $\377 -> + [C | limit_iolist_to_chars(Cs, Limit - 1, S, Mode)]; +limit_iolist_to_chars([I|Cs], Limit, S, Mode) -> + limit_iolist_to_chars(I, Limit, [Cs|S], Mode); +limit_iolist_to_chars([], _Limit, [], _Mode) -> + []; +limit_iolist_to_chars([], Limit, [Cs|S], Mode) -> + limit_iolist_to_chars(Cs, Limit, S, Mode); +limit_iolist_to_chars(B, Limit, S, Mode) when is_binary(B) -> + case byte_size(B) of + Sz when Sz > Limit -> + {B1, B2} = split_binary(B, Limit), + [binary_to_list(B1) | limit_iolist_to_chars(B2, 0, S, Mode)]; + Sz -> + [binary_to_list(B) | limit_iolist_to_chars([], Limit-Sz, S, Mode)] + end. -%% cdata_to_chars(cdata()) -> io_lib:chars() +cdata_to_chars(Cs, F, CharsLimit) when CharsLimit < 0; CharsLimit >= F -> + cdata_to_chars(Cs); +cdata_to_chars(Cs, _, CharsLimit) -> + limit_cdata_to_chars(Cs, sub(CharsLimit, 3), normal). % three dots cdata_to_chars([C|Cs]) when is_integer(C), C >= $\000 -> [C | cdata_to_chars(Cs)]; @@ -748,11 +773,25 @@ cdata_to_chars(B) when is_binary(B) -> _ -> binary_to_list(B) end. -limit_string(S, F, CharsLimit) when CharsLimit < 0; CharsLimit >= F -> S; -limit_string(S, _F, CharsLimit) -> - case io_lib:chars_length(S) =< CharsLimit of - true -> S; - false -> [string:slice(S, 0, sub(CharsLimit, 3)), "..."] +limit_cdata_to_chars(Cs, 0, normal) -> + L = limit_cdata_to_chars(Cs, 4, final), + case string:length(L) of + N when N < 4 -> L; + 4 -> "..." + end; +limit_cdata_to_chars(_Cs, 0, final) -> []; +limit_cdata_to_chars(Cs, Limit, Mode) -> + case string:next_grapheme(Cs) of + {error, <<C,Cs1/binary>>} -> + %% This is how ~ts handles Latin1 binaries with option + %% chars_limit. + [C | limit_cdata_to_chars(Cs1, Limit - 1, Mode)]; + {error, [C|Cs1]} -> % not all versions of module string return this + [C | limit_cdata_to_chars(Cs1, Limit - 1, Mode)]; + [] -> + []; + [GC|Cs1] -> + [GC | limit_cdata_to_chars(Cs1, Limit - 1, Mode)] end. limit_field(F, CharsLimit) when CharsLimit < 0; F =:= none -> @@ -762,30 +801,30 @@ limit_field(F, CharsLimit) -> %% string(String, Field, Adjust, Precision, PadChar) -string(S, none, _Adj, none, _Pad) -> S; -string(S, F, Adj, none, Pad) -> - string_field(S, F, Adj, io_lib:chars_length(S), Pad); -string(S, none, _Adj, P, Pad) -> - string_field(S, P, left, io_lib:chars_length(S), Pad); -string(S, F, Adj, P, Pad) when F >= P -> +string(S, none, _Adj, none, _Pad, _Enc) -> S; +string(S, F, Adj, none, Pad, Enc) -> + string_field(S, F, Adj, io_lib:chars_length(S), Pad, Enc); +string(S, none, _Adj, P, Pad, Enc) -> + string_field(S, P, left, io_lib:chars_length(S), Pad, Enc); +string(S, F, Adj, P, Pad, Enc) when F >= P -> N = io_lib:chars_length(S), if F > P -> if N > P -> - adjust(flat_trunc(S, P), chars(Pad, F-P), Adj); + adjust(flat_trunc(S, P, Enc), chars(Pad, F-P), Adj); N < P -> adjust([S|chars(Pad, P-N)], chars(Pad, F-P), Adj); true -> % N == P adjust(S, chars(Pad, F-P), Adj) end; true -> % F == P - string_field(S, F, Adj, N, Pad) + string_field(S, F, Adj, N, Pad, Enc) end. -string_field(S, F, _Adj, N, _Pad) when N > F -> - flat_trunc(S, F); -string_field(S, F, Adj, N, Pad) when N < F -> +string_field(S, F, _Adj, N, _Pad, Enc) when N > F -> + flat_trunc(S, F, Enc); +string_field(S, F, Adj, N, Pad, _Enc) when N < F -> adjust(S, chars(Pad, F-N), Adj); -string_field(S, _, _, _, _) -> % N == F +string_field(S, _, _, _, _, _) -> % N == F S. %% unprefixed_integer(Int, Field, Adjust, Base, PadChar, Lowercase) @@ -837,7 +876,10 @@ adjust(Data, Pad, right) -> [Pad|Data]. %% Flatten and truncate a deep list to at most N elements. -flat_trunc(List, N) when is_integer(N), N >= 0 -> +flat_trunc(List, N, latin1) when is_integer(N), N >= 0 -> + {S, _} = lists:split(N, lists:flatten(List)), + S; +flat_trunc(List, N, unicode) when is_integer(N), N >= 0 -> string:slice(List, 0, N). %% A deep version of lists:duplicate/2 diff --git a/lib/stdlib/src/io_lib_pretty.erl b/lib/stdlib/src/io_lib_pretty.erl index 8f2fd7ea8f..77f02eafe0 100644 --- a/lib/stdlib/src/io_lib_pretty.erl +++ b/lib/stdlib/src/io_lib_pretty.erl @@ -462,7 +462,9 @@ find_upper(Lower, Term, T, Dl, Dd, D, RF, Enc, Str) -> case If of {_, _, _Dots=0, _} -> % even if Len > T If; - {_, Len, _, _} when Len =< T, D1 < D orelse D < 0 -> + {_, _Len=T, _, _} -> % increasing the depth is meaningless + If; + {_, Len, _, _} when Len < T, D1 < D orelse D < 0 -> find_upper(If, Term, T, D1, Dd2, D, RF, Enc, Str); _ -> search_depth(Lower, If, Term, T, Dl, D1, RF, Enc, Str) @@ -720,55 +722,40 @@ printable_list(_L, 1, _T, _Enc) -> false; printable_list(L, _D, T, latin1) when T < 0 -> io_lib:printable_latin1_list(L); -printable_list(L, _D, T, Enc) when T >= 0 -> - case slice(L, tsub(T, 2), Enc) of - false -> - false; - {prefix, Prefix} when Enc =:= latin1 -> - io_lib:printable_latin1_list(Prefix) andalso {true, Prefix}; - {prefix, Prefix} -> - %% Probably an overestimation. - io_lib:printable_list(Prefix) andalso {true, Prefix}; - all when Enc =:= latin1 -> - io_lib:printable_latin1_list(L); +printable_list(L, _D, T, latin1) when T >= 0 -> + N = tsub(T, 2), + case printable_latin1_list(L, N) of all -> - io_lib:printable_list(L) - end; -printable_list(L, _D, T, _Uni) when T < 0-> - io_lib:printable_list(L). - -slice(L, N, latin1) -> - try lists:split(N, L) of - {_, []} -> - all; - {[], _} -> - false; - {L1, _} -> - {prefix, L1} - catch - _:_ -> - all + true; + 0 -> + {L1, _} = lists:split(N, L), + {true, L1}; + _NC -> + false end; -slice(L, N, _Uni) -> +printable_list(L, _D, T, _Unicode) when T >= 0 -> + N = tsub(T, 2), %% Be careful not to traverse more of L than necessary. try string:slice(L, 0, N) of "" -> false; Prefix -> - %% Assume no binaries are introduced by string:slice(). case is_flat(L, lists:flatlength(Prefix)) of true -> case string:equal(Prefix, L) of true -> - all; + io_lib:printable_list(L); false -> - {prefix, Prefix} + io_lib:printable_list(Prefix) + andalso {true, Prefix} end; false -> false end catch _:_ -> false - end. + end; +printable_list(L, _D, T, _Uni) when T < 0-> + io_lib:printable_list(L). is_flat(_L, 0) -> true; @@ -795,6 +782,8 @@ printable_bin0(Bin, D, T, Enc) -> end, printable_bin(Bin, Len, D, Enc). +printable_bin(_Bin, 0, _D, _Enc) -> + false; printable_bin(Bin, Len, D, latin1) -> N = erlang:min(20, Len), L = binary_to_list(Bin, 1, N), @@ -845,7 +834,7 @@ printable_bin1(Bin, Start, Len) -> end. %% -> all | integer() >=0. Adopted from io_lib.erl. -% printable_latin1_list([_ | _], 0) -> 0; +printable_latin1_list([_ | _], 0) -> 0; printable_latin1_list([C | Cs], N) when C >= $\s, C =< $~ -> printable_latin1_list(Cs, N - 1); printable_latin1_list([C | Cs], N) when C >= $\240, C =< $\377 -> diff --git a/lib/stdlib/src/stdlib.app.src b/lib/stdlib/src/stdlib.app.src index 9cd425db9a..ecb514e9f3 100644 --- a/lib/stdlib/src/stdlib.app.src +++ b/lib/stdlib/src/stdlib.app.src @@ -108,7 +108,7 @@ dets]}, {applications, [kernel]}, {env, []}, - {runtime_dependencies, ["sasl-3.0","kernel-6.0","erts-@OTP-15128@","crypto-3.3", + {runtime_dependencies, ["sasl-3.0","kernel-6.0","erts-10.4","crypto-3.3", "compiler-5.0"]} ]}. diff --git a/lib/stdlib/src/stdlib.appup.src b/lib/stdlib/src/stdlib.appup.src index 08612ed17f..0c270e9dd5 100644 --- a/lib/stdlib/src/stdlib.appup.src +++ b/lib/stdlib/src/stdlib.appup.src @@ -19,22 +19,15 @@ %% %% We allow upgrade from, and downgrade to all previous %% versions from the following OTP releases: -%% - OTP 20 %% - OTP 21 +%% - OTP 22 %% %% We also allow upgrade from, and downgrade to all %% versions that have branched off from the above %% stated previous versions. %% {"%VSN%", - [{<<"^3\\.4$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.2(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.3(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.4(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.5(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.5$">>,[restart_new_emulator]}, + [{<<"^3\\.5$">>,[restart_new_emulator]}, {<<"^3\\.5\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, {<<"^3\\.5\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, {<<"^3\\.6$">>,[restart_new_emulator]}, @@ -43,15 +36,13 @@ {<<"^3\\.7\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, {<<"^3\\.7\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, {<<"^3\\.8$">>,[restart_new_emulator]}, - {<<"^3\\.8\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}], - [{<<"^3\\.4$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.2(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.3(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.4(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.4\\.5(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, - {<<"^3\\.5$">>,[restart_new_emulator]}, + {<<"^3\\.8\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, + {<<"^3\\.8\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, + {<<"^3\\.8\\.2(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, + {<<"^3\\.9$">>,[restart_new_emulator]}, + {<<"^3\\.9\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, + {<<"^3\\.9\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}], + [{<<"^3\\.5$">>,[restart_new_emulator]}, {<<"^3\\.5\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, {<<"^3\\.5\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, {<<"^3\\.6$">>,[restart_new_emulator]}, @@ -60,4 +51,9 @@ {<<"^3\\.7\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, {<<"^3\\.7\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, {<<"^3\\.8$">>,[restart_new_emulator]}, - {<<"^3\\.8\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}]}. + {<<"^3\\.8\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, + {<<"^3\\.8\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, + {<<"^3\\.8\\.2(?:\\.[0-9]+)*$">>,[restart_new_emulator]}, + {<<"^3\\.9$">>,[restart_new_emulator]}, + {<<"^3\\.9\\.0(?:\\.[0-9]+)+$">>,[restart_new_emulator]}, + {<<"^3\\.9\\.1(?:\\.[0-9]+)*$">>,[restart_new_emulator]}]}. diff --git a/lib/stdlib/src/string.erl b/lib/stdlib/src/string.erl index 1f8bdc5432..a418754caf 100644 --- a/lib/stdlib/src/string.erl +++ b/lib/stdlib/src/string.erl @@ -128,7 +128,8 @@ length(CD) -> to_graphemes(CD0) -> case unicode_util:gc(CD0) of [GC|CD] -> [GC|to_graphemes(CD)]; - [] -> [] + [] -> []; + {error, Err} -> error({badarg, Err}) end. %% Compare two strings return boolean, assumes that the input are @@ -332,7 +333,10 @@ uppercase(<<CP1/utf8, Rest/binary>>=Orig) -> catch unchanged -> Orig end; uppercase(<<>>) -> - <<>>. + <<>>; +uppercase(Bin) -> + error({badarg, Bin}). + %% Lowercase all chars in Str -spec lowercase(String::unicode:chardata()) -> unicode:chardata(). @@ -346,7 +350,10 @@ lowercase(<<CP1/utf8, Rest/binary>>=Orig) -> catch unchanged -> Orig end; lowercase(<<>>) -> - <<>>. + <<>>; +lowercase(Bin) -> + error({badarg, Bin}). + %% Make a titlecase of the first char in Str -spec titlecase(String::unicode:chardata()) -> unicode:chardata(). @@ -375,7 +382,9 @@ casefold(<<CP1/utf8, Rest/binary>>=Orig) -> catch unchanged -> Orig end; casefold(<<>>) -> - <<>>. + <<>>; +casefold(Bin) -> + error({badarg, Bin}). -spec to_integer(String) -> {Int, Rest} | {'error', Reason} when String :: unicode:chardata(), @@ -544,7 +553,8 @@ length_1([CP1|[CP2|_]=Cont], N) when ?ASCII_LIST(CP1,CP2) -> length_1(Str, N) -> case unicode_util:gc(Str) of [] -> N; - [_|Rest] -> length_1(Rest, N+1) + [_|Rest] -> length_1(Rest, N+1); + {error, Err} -> error({badarg, Err}) end. length_b(<<CP2/utf8, Rest/binary>>, CP1, N) @@ -554,7 +564,8 @@ length_b(Bin0, CP1, N) -> [_|Bin1] = unicode_util:gc([CP1|Bin0]), case unicode_util:cp(Bin1) of [] -> N+1; - [CP3|Bin] -> length_b(Bin, CP3, N+1) + [CP3|Bin] -> length_b(Bin, CP3, N+1); + {error, Err} -> error({badarg, Err}) end. equal_1([A|AR], [B|BR]) when is_integer(A), is_integer(B) -> @@ -599,7 +610,8 @@ reverse_1([CP1|[CP2|_]=Cont], Acc) when ?ASCII_LIST(CP1,CP2) -> reverse_1(CD, Acc) -> case unicode_util:gc(CD) of [GC|Rest] -> reverse_1(Rest, [GC|Acc]); - [] -> Acc + [] -> Acc; + {error, Err} -> error({badarg, Err}) end. reverse_b(<<CP2/utf8, Rest/binary>>, CP1, Acc) @@ -609,7 +621,8 @@ reverse_b(Bin0, CP1, Acc) -> [GC|Bin1] = unicode_util:gc([CP1|Bin0]), case unicode_util:cp(Bin1) of [] -> [GC|Acc]; - [CP3|Bin] -> reverse_b(Bin, CP3, [GC|Acc]) + [CP3|Bin] -> reverse_b(Bin, CP3, [GC|Acc]); + {error, Err} -> error({badarg, Err}) end. slice_l0(<<CP1/utf8, Bin/binary>>, N) when N > 0 -> @@ -622,7 +635,8 @@ slice_l([CP1|[CP2|_]=Cont], N) when ?ASCII_LIST(CP1,CP2),N > 0 -> slice_l(CD, N) when N > 0 -> case unicode_util:gc(CD) of [_|Cont] -> slice_l(Cont, N-1); - [] -> [] + [] -> []; + {error, Err} -> error({badarg, Err}) end; slice_l(Cont, 0) -> Cont. @@ -634,7 +648,8 @@ slice_lb(Bin, CP1, N) -> if N > 1 -> case unicode_util:cp(Rest) of [CP2|Cont] -> slice_lb(Cont, CP2, N-1); - [] -> <<>> + [] -> <<>>; + {error, Err} -> error({badarg, Err}) end; N =:= 1 -> Rest @@ -647,7 +662,10 @@ slice_trail(Orig, N) when is_binary(Orig) -> Sz = byte_size(Orig) - Length, <<Keep:Sz/binary, _/binary>> = Orig, Keep; - _ -> <<>> + <<_, _/binary>> when N > 0 -> + error({badarg, Orig}); + _ -> + <<>> end; slice_trail(CD, N) when is_list(CD) -> slice_list(CD, N). @@ -657,7 +675,8 @@ slice_list([CP1|[CP2|_]=Cont], N) when ?ASCII_LIST(CP1,CP2),N > 0 -> slice_list(CD, N) when N > 0 -> case unicode_util:gc(CD) of [GC|Cont] -> append(GC, slice_list(Cont, N-1)); - [] -> [] + [] -> []; + {error, Err} -> error({badarg, Err}) end; slice_list(_, 0) -> []. @@ -668,7 +687,8 @@ slice_bin(CD, CP1, N) when N > 0 -> [_|Bin] = unicode_util:gc([CP1|CD]), case unicode_util:cp(Bin) of [CP2|Cont] -> slice_bin(Cont, CP2, N-1); - [] -> 0 + [] -> 0; + {error, Err} -> error({badarg, Err}) end; slice_bin(CD, CP1, 0) -> byte_size(CD)+byte_size(<<CP1/utf8>>). @@ -703,14 +723,18 @@ uppercase_bin(CP1, Bin, Changed) -> [] when Changed -> [CP1]; [] -> - throw(unchanged) + throw(unchanged); + {error, Err} -> + error({badarg, Err}) end; [Char|CPs] -> case unicode_util:cp(CPs) of [Next|Rest] -> [Char|uppercase_bin(Next, Rest, true)]; [] -> - [Char] + [Char]; + {error, Err} -> + error({badarg, Err}) end end. @@ -744,14 +768,18 @@ lowercase_bin(CP1, Bin, Changed) -> [] when Changed -> [CP1]; [] -> - throw(unchanged) + throw(unchanged); + {error, Err} -> + error({badarg, Err}) end; [Char|CPs] -> case unicode_util:cp(CPs) of [Next|Rest] -> [Char|lowercase_bin(Next, Rest, true)]; [] -> - [Char] + [Char]; + {error, Err} -> + error({badarg, Err}) end end. @@ -785,14 +813,18 @@ casefold_bin(CP1, Bin, Changed) -> [] when Changed -> [CP1]; [] -> - throw(unchanged) + throw(unchanged); + {error, Err} -> + error({badarg, Err}) end; [Char|CPs] -> case unicode_util:cp(CPs) of [Next|Rest] -> [Char|casefold_bin(Next, Rest, true)]; [] -> - [Char] + [Char]; + {error, Err} -> + error({badarg, Err}) end end. @@ -1634,7 +1666,9 @@ bin_search_inv_1(<<CP1/utf8, BinRest/binary>>=Bin0, Cont, Sep) -> bin_search_inv_1(<<>>, Cont, _Sep) -> {nomatch, Cont}; bin_search_inv_1([], Cont, _Sep) -> - {nomatch, Cont}. + {nomatch, Cont}; +bin_search_inv_1(Bin, _, _) -> + error({badarg, Bin}). bin_search_inv_n(<<CP1/utf8, BinRest/binary>>=Bin0, Cont, Seps) -> @@ -1666,7 +1700,9 @@ bin_search_inv_n(<<CP1/utf8, BinRest/binary>>=Bin0, Cont, Seps) -> bin_search_inv_n(<<>>, Cont, _Sep) -> {nomatch, Cont}; bin_search_inv_n([], Cont, _Sep) -> - {nomatch, Cont}. + {nomatch, Cont}; +bin_search_inv_n(Bin, _, _) -> + error({badarg, Bin}). bin_search_str(Bin0, Start, [], SearchCPs) -> Compiled = binary:compile_pattern(unicode:characters_to_binary(SearchCPs)), diff --git a/lib/stdlib/test/erl_lint_SUITE.erl b/lib/stdlib/test/erl_lint_SUITE.erl index fe98a3796d..e7882e0daf 100644 --- a/lib/stdlib/test/erl_lint_SUITE.erl +++ b/lib/stdlib/test/erl_lint_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1999-2018. All Rights Reserved. +%% Copyright Ericsson AB 1999-2019. All Rights Reserved. %% %% Licensed under the Apache License, Version 2.0 (the "License"); %% you may not use this file except in compliance with the License. @@ -68,7 +68,7 @@ non_latin1_module/1, otp_14323/1, stacktrace_syntax/1, otp_14285/1, otp_14378/1, - external_funs/1,otp_15456/1]). + external_funs/1,otp_15456/1,otp_15563/1]). suite() -> [{ct_hooks,[ts_install_cth]}, @@ -90,7 +90,7 @@ all() -> otp_11851, otp_11879, otp_13230, record_errors, otp_11879_cont, non_latin1_module, otp_14323, stacktrace_syntax, otp_14285, otp_14378, external_funs, - otp_15456]. + otp_15456, otp_15563]. groups() -> [{unused_vars_warn, [], @@ -4010,6 +4010,8 @@ non_latin1_module(Config) -> format_error(non_latin1_module_unsupported), BadCallback = {bad_callback,{'кирилли́ческий атом','кирилли́ческий атом',0}}, + BadModule = + {bad_module,{'кирилли́ческий атом','кирилли́ческий атом',0}}, "explicit module not allowed for callback " "'кирилли́ческий атом':'кирилли́ческий атом'/0" = format_error(BadCallback), @@ -4052,6 +4054,7 @@ non_latin1_module(Config) -> {11,erl_lint,illegal_guard_expr}, {15,erl_lint,non_latin1_module_unsupported}, {17,erl_lint,non_latin1_module_unsupported}, + {17,erl_lint,BadModule}, {20,erl_lint,non_latin1_module_unsupported}, {23,erl_lint,non_latin1_module_unsupported}, {25,erl_lint,non_latin1_module_unsupported}], @@ -4229,6 +4232,21 @@ external_funs(Config) when is_list(Config) -> run(Config, Ts), ok. +otp_15563(Config) when is_list(Config) -> + Ts = [{otp_15563, + <<"-type deep_list(A) :: [A | deep_list(A)]. + -spec lists:flatten(deep_list(A)) -> [A]. + -callback lists:concat([_]) -> string(). + -spec ?MODULE:foo() -> any(). + foo() -> a. + ">>, + [warn_unused_vars], + {errors,[{2,erl_lint,{bad_module,{lists,flatten,1}}}, + {3,erl_lint,{bad_callback,{lists,concat,1}}}], + []}}], + [] = run(Config, Ts), + ok. + format_error(E) -> lists:flatten(erl_lint:format_error(E)). diff --git a/lib/stdlib/test/erl_pp_SUITE.erl b/lib/stdlib/test/erl_pp_SUITE.erl index 3eb1670806..c0cfd26925 100644 --- a/lib/stdlib/test/erl_pp_SUITE.erl +++ b/lib/stdlib/test/erl_pp_SUITE.erl @@ -829,7 +829,7 @@ type_examples() -> "(t24()) -> D when is_subtype(D, atom())," " is_subtype(D, t14())," " is_subtype(D, '\\'t::4'()).">>}, - {ex32,<<"-spec mod:t2() -> any(). ">>}, + {ex32,<<"-spec erl_pp_test:t2() -> any(). ">>}, {ex33,<<"-opaque attributes_data() :: " "[{'column', column()} | {'line', info_line()} |" " {'text', string()}] | {line(),column()}. ">>}, diff --git a/lib/stdlib/test/io_SUITE.erl b/lib/stdlib/test/io_SUITE.erl index 824f5d19f2..4eb5b1772c 100644 --- a/lib/stdlib/test/io_SUITE.erl +++ b/lib/stdlib/test/io_SUITE.erl @@ -32,7 +32,7 @@ io_with_huge_message_queue/1, format_string/1, maps/1, coverage/1, otp_14178_unicode_atoms/1, otp_14175/1, otp_14285/1, limit_term/1, otp_14983/1, otp_15103/1, otp_15076/1, - otp_15159/1, otp_15639/1]). + otp_15159/1, otp_15639/1, otp_15705/1, otp_15847/1, otp_15875/1]). -export([pretty/2, trf/3]). @@ -65,7 +65,7 @@ all() -> io_lib_width_too_small, io_with_huge_message_queue, format_string, maps, coverage, otp_14178_unicode_atoms, otp_14175, otp_14285, limit_term, otp_14983, otp_15103, otp_15076, otp_15159, - otp_15639]. + otp_15639, otp_15705, otp_15847, otp_15875]. %% Error cases for output. error_1(Config) when is_list(Config) -> @@ -2504,9 +2504,11 @@ otp_14983(_Config) -> trunc_string() -> "str " = trf("str ", [], 10), - "str ..." = trf("str ~s", ["str"], 6), + "str str" = trf("str ~s", ["str"], 6), + "str ..." = trf("str ~s", ["str1"], 6), "str str" = trf("str ~s", ["str"], 7), - "str ..." = trf("str ~8s", ["str"], 6), + "str str" = trf("str ~8s", ["str"], 6), + "str ..." = trf("str ~8s", ["str1"], 6), Pa = filename:dirname(code:which(?MODULE)), {ok, UNode} = test_server:start_node(printable_range_unicode, slave, [{args, " +pc unicode -pa " ++ Pa}]), @@ -2680,3 +2682,39 @@ otp_15639(_Config) -> "\"12345678\"..." = pretty("123456789"++[x], UOpts), "[[...]|...]" = pretty(["1","2","3","4","5","6","7","8"], UOpts), ok. + +otp_15705(_Config) -> + L = [<<"an">>,["at"],[["om"]]], + "..." = trf("~s", [L], 0), + "..." = trf("~s", [L], 1), + "..." = trf("~s", [L], 2), + "..." = trf("~s", [L], 3), + "a..." = trf("~s", [L], 4), + "an..." = trf("~s", [L], 5), + "anatom" = trf("~s", [L], 6), + L2 = ["a",[<<"na">>],[["tom"]]], + "..." = trf("~s", [L2], 3), + "a..." = trf("~s", [L2], 4), + "an..." = trf("~s", [L2], 5), + "anatom" = trf("~s", [L2], 6), + + A = [[<<"äpple"/utf8>>, "plus", <<"äpple">>]], + "äp..." = trf("~ts", [A], 5), + "äppleplusäpple" = trf("~ts", [A], 14), + U = [["ки"],"рилл","и́ческий атом"], + "ки..." = trf("~ts", [U], 5), + "кирилли́ческий..." = trf("~ts", [U], 16), + "кирилли́ческий атом" = trf("~ts", [U], 20), + + "|кирилли́чес|" = trf("|~10ts|", [U], -1), + ok. + +otp_15847(_Config) -> + T = {someRecord,<<"1234567890">>,some,more}, + "{someRecord,<<...>>,...}" = + pretty(T, [{chars_limit,20}, {encoding,latin1}]), + ok. + +otp_15875(_Config) -> + S = io_lib:format("~tp", [[{0, [<<"00">>]}]], [{chars_limit, 18}]), + "[{0,[<<48,...>>]}]" = lists:flatten(S). diff --git a/lib/stdlib/test/string_SUITE.erl b/lib/stdlib/test/string_SUITE.erl index 248912c3f2..c9aadd7f10 100644 --- a/lib/stdlib/test/string_SUITE.erl +++ b/lib/stdlib/test/string_SUITE.erl @@ -103,6 +103,15 @@ debug() -> test(?LINE,?FUNCTION_NAME,B,C,D, false), test(?LINE,?FUNCTION_NAME,hd(C),[B|tl(C)],D, false)). +-define(TRY(Exp), + fun() -> + try Exp + catch _E:Reason:_ST -> + %% io:format("~p:~w: ~p: ~.0p ~p~n", + %% [?FUNCTION_NAME, ?LINE,_E,Reason, hd(_ST)]), + {'EXIT', Reason} + end + end()). is_empty(_) -> ?TEST("", [], true), @@ -126,6 +135,10 @@ length(_) -> ?TEST(["abc"|<<"abc">>], [], 6), ?TEST(["abc",["def"]], [], 6), ?TEST([<<97/utf8, 778/utf8, 98/utf8>>, [776,111,776]], [], 3), %% åäö in nfd + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:length(InvalidUTF8)), + {'EXIT', {badarg, _}} = ?TRY(string:length(<<$a, InvalidUTF8/binary, $z>>)), ok. equal(_) -> @@ -226,6 +239,8 @@ to_graphemes(_) -> true = erlang:length(GCs) =:= erlang:length(string:to_graphemes(NFD)), true = erlang:length(GCs) =:= erlang:length(string:to_graphemes(unicode:characters_to_nfc_list(String))), + + {'EXIT', {badarg, _}} = ?TRY(string:to_graphemes(<<$a,192,192,$z>>)), ok. reverse(_) -> @@ -238,6 +253,11 @@ reverse(_) -> ?TEST(Str2, [], lists:reverse(Str2)), ?TEST(Str3, [], lists:reverse(Str3)), true = string:reverse(Str3) =:= lists:reverse(string:to_graphemes(Str3)), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:reverse(InvalidUTF8)), + {'EXIT', {badarg, _}} = ?TRY(string:reverse(<<$a, InvalidUTF8/binary, $z>>)), + ok. slice(_) -> @@ -258,6 +278,14 @@ slice(_) -> ?TEST([<<"aå"/utf8>>,"äöbcd"], [3,3], "öbc"), ?TEST([<<"aåä"/utf8>>,"öbcd"], [3,10], "öbcd"), + InvalidUTF8 = <<192,192>>, + [$b, $c|InvalidUTF8] = string:slice(["abc", InvalidUTF8], 1), + InvalidUTF8 = string:slice(["abc", InvalidUTF8], 3), + {'EXIT', {badarg, _}} = ?TRY(string:slice(["abc", InvalidUTF8], 1, 5)), + BadUtf8 = <<$a, InvalidUTF8/binary, "teststring">>, + {'EXIT', {badarg, _}} = ?TRY(string:slice(BadUtf8, 2)), + {'EXIT', {badarg, _}} = ?TRY(string:slice(BadUtf8, 1, 5)), + {'EXIT', {badarg, _}} = ?TRY(string:slice(BadUtf8, 0, 5)), ok. pad(_) -> @@ -270,6 +298,10 @@ pad(_) -> ?TEST(Str, [10, trailing, $.], "Hallå....."), ?TEST(Str++["f"], [10, trailing, $.], "Hallåf...."), ?TEST(Str++[" flåwer"], [10, trailing, $.], "Hallå flåwer"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:pad(InvalidUTF8, 10, both, $.)), + {'EXIT', {badarg, _}} = ?TRY(string:pad(<<$a, InvalidUTF8/binary, $z>>, 10, both, $.)), ok. trim(_) -> @@ -300,6 +332,11 @@ trim(_) -> ?TEST([[<<"!v">>|<<204,128,$v,204,129>>]],[trailing, [[$v,769]]], [$!,$v,768]), ?TEST([[[<<"v">>|<<204,129,118,204,128,118>>],769,118,769]], [trailing, [[118,769]]], [$v,769,$v,768]), ?TEST([<<"vv">>|<<204,128,118,204,128>>], [trailing, [[118,768]]], "v"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:trim(InvalidUTF8, both, "az")), + %% Not checked (using binary search) + %% {'EXIT', {badarg, _}} = ?TRY(string:trim(<<$a, $b, InvalidUTF8/binary, $z>>, both, "az")), ok. chomp(_) -> @@ -400,6 +437,13 @@ take(_) -> ?TEST([<<"e">>,778,"åäöe", <<778/utf8>>, $e, 779], [[[$e,778]], true, trailing], {[$e,778]++"åäöe"++[778], [$e,779]}), + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:take(InvalidUTF8, [$.], false, leading)), + %% Not checked (using binary search) + %% {'EXIT', {badarg, _}} = ?TRY(string:take(InvalidUTF8, [$.], true, leading)), + %% {'EXIT', {badarg, _}} = ?TRY(string:take(InvalidUTF8, [$.], false, trailing)), + {'EXIT', {badarg, _}} = ?TRY(string:take(InvalidUTF8, [$.], true, trailing)), + ok. @@ -416,6 +460,11 @@ uppercase(_) -> ?TEST("ljLJ", [], "LJLJ"), ?TEST("LJlj", [], "LJLJ"), ?TEST("ß sharp s", [], "SS SHARP S"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:uppercase(InvalidUTF8)), + {'EXIT', {badarg, _}} = ?TRY(string:uppercase(<<$a, InvalidUTF8/binary, $z>>)), + ok. lowercase(_) -> @@ -429,6 +478,10 @@ lowercase(_) -> ?TEST(["Mic",<<"HAŁ"/utf8>>], [], "michał"), ?TEST("ß SHARP S", [], "ß sharp s"), ?TEST("İ I WITH DOT ABOVE", [], "i̇ i with dot above"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:lowercase(InvalidUTF8)), + {'EXIT', {badarg, _}} = ?TRY(string:lowercase(<<$a, InvalidUTF8/binary, $z>>)), ok. titlecase(_) -> @@ -442,6 +495,10 @@ titlecase(_) -> ?TEST("ljLJ", [], "LjLJ"), ?TEST("LJlj", [], "Ljlj"), ?TEST("ß sharp s", [], "Ss sharp s"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:titlecase(InvalidUTF8)), + <<$A, _/binary>> = ?TRY(string:titlecase(<<$a, InvalidUTF8/binary, $z>>)), ok. casefold(_) -> @@ -456,6 +513,10 @@ casefold(_) -> ?TEST("ß SHARP S", [], "ss sharp s"), ?TEST("ẞ SHARP S", [], "ss sharp s"), ?TEST("İ I WITH DOT ABOVE", [], "i̇ i with dot above"), + + InvalidUTF8 = <<192,192>>, + {'EXIT', {badarg, _}} = ?TRY(string:casefold(InvalidUTF8)), + {'EXIT', {badarg, _}} = ?TRY(string:casefold(<<$a, InvalidUTF8/binary, $z>>)), ok. @@ -740,7 +801,7 @@ meas(Config) -> _ -> % No scaling, run at most 1.5 min Tester = spawn(Exec), receive {test_done, Tester} -> ok - after 90000 -> + after 118000 -> io:format("Timelimit reached stopping~n",[]), exit(Tester, die) end, diff --git a/lib/stdlib/test/unicode_util_SUITE.erl b/lib/stdlib/test/unicode_util_SUITE.erl index 044b4e5834..6f55f204f4 100644 --- a/lib/stdlib/test/unicode_util_SUITE.erl +++ b/lib/stdlib/test/unicode_util_SUITE.erl @@ -428,7 +428,15 @@ mode(deep_l, Bin) -> [unicode:characters_to_list(Bin)]. fetch(Str, F) -> case F(Str) of [] -> []; - [CP|R] -> [CP|fetch(R,F)] + [CP|R] -> + %% If input is a binary R should be binary + if is_binary(Str) == false -> ok; + is_binary(R); R =:= [] -> ok; + true -> + io:format("Char: ~tc Tail:~tP~n", [CP,R,10]), + exit({bug, F}) + end, + [CP|fetch(R,F)] end. %% *Test.txt file helpers diff --git a/lib/stdlib/uc_spec/gen_unicode_mod.escript b/lib/stdlib/uc_spec/gen_unicode_mod.escript index 8636c69a0d..de67b18afc 100644 --- a/lib/stdlib/uc_spec/gen_unicode_mod.escript +++ b/lib/stdlib/uc_spec/gen_unicode_mod.escript @@ -202,7 +202,8 @@ gen_static(Fd) -> io:put_chars(Fd, " {Upper,_} -> [Upper|Str];\n"), io:put_chars(Fd, " {Upper,_,_,_} -> [Upper|Str]\n"), io:put_chars(Fd, " end;\n"), - io:put_chars(Fd, " [] -> []\n"), + io:put_chars(Fd, " [] -> [];\n"), + io:put_chars(Fd, " {error,Err} -> error({badarg, Err})\n"), io:put_chars(Fd, " end.\n\n"), io:put_chars(Fd, "-spec lowercase(unicode:chardata()) -> " "maybe_improper_list(gc(),unicode:chardata()).\n"), @@ -213,7 +214,8 @@ gen_static(Fd) -> io:put_chars(Fd, " {_,Lower} -> [Lower|Str];\n"), io:put_chars(Fd, " {_,Lower,_,_} -> [Lower|Str]\n"), io:put_chars(Fd, " end;\n"), - io:put_chars(Fd, " [] -> []\n"), + io:put_chars(Fd, " [] -> [];\n"), + io:put_chars(Fd, " {error,Err} -> error({badarg, Err})\n"), io:put_chars(Fd, " end.\n\n"), io:put_chars(Fd, "-spec titlecase(unicode:chardata()) -> " "maybe_improper_list(gc(),unicode:chardata()).\n"), @@ -224,7 +226,8 @@ gen_static(Fd) -> io:put_chars(Fd, " {_,_,Title,_} -> [Title|Str];\n"), io:put_chars(Fd, " {Upper,_} -> [Upper|Str]\n"), io:put_chars(Fd, " end;\n"), - io:put_chars(Fd, " [] -> []\n"), + io:put_chars(Fd, " [] -> [];\n"), + io:put_chars(Fd, " {error,Err} -> error({badarg, Err})\n"), io:put_chars(Fd, " end.\n\n"), io:put_chars(Fd, "-spec casefold(unicode:chardata()) -> " "maybe_improper_list(gc(),unicode:chardata()).\n"), @@ -235,7 +238,8 @@ gen_static(Fd) -> io:put_chars(Fd, " {_,_,_,Fold} -> [Fold|Str];\n"), io:put_chars(Fd, " {_,Lower} -> [Lower|Str]\n"), io:put_chars(Fd, " end;\n"), - io:put_chars(Fd, " [] -> []\n"), + io:put_chars(Fd, " [] -> [];\n"), + io:put_chars(Fd, " {error,Err} -> error({badarg, Err})\n"), io:put_chars(Fd, " end.\n\n"), ok. @@ -619,7 +623,7 @@ gen_gc(Fd, GBP) -> GenHangulT = fun(Range) -> io:format(Fd, "gc_1~s gc_h_T(R1,[CP]);\n", [gen_clause(Range)]) end, [GenHangulT(CP) || CP <- merge_ranges(maps:get(t,GBP))], io:put_chars(Fd, "%% Handle Hangul LV and LVT special, since they are large\n"), - io:put_chars(Fd, "gc_1([CP|_]=R0) when 44000 < CP, CP < 56000 -> gc_h_lv_lvt(R0, []);\n"), + io:put_chars(Fd, "gc_1([CP|_]=R0) when 44000 < CP, CP < 56000 -> gc_h_lv_lvt(R0, R0, []);\n"), io:put_chars(Fd, "\n%% Handle Regional\n"), GenRegional = fun(Range) -> io:format(Fd, "gc_1~s gc_regional(R1,CP);\n", [gen_clause(Range)]) end, @@ -748,7 +752,7 @@ gen_gc(Fd, GBP) -> GenHangulL_2 = fun(Range) -> io:format(Fd, "~8c~s gc_h_V(R1,[CP|Acc]);\n", [$\s,gen_case_clause(Range)]) end, [GenHangulL_2(CP) || CP <- merge_ranges(maps:get(v,GBP))], - io:put_chars(Fd, " R1 -> gc_h_lv_lvt(R1, Acc)\n end.\n\n"), + io:put_chars(Fd, " R1 -> gc_h_lv_lvt(R1, R0, Acc)\n end.\n\n"), io:put_chars(Fd, "%% Handle Hangul V\n"), io:put_chars(Fd, "gc_h_V(R0, Acc) ->\n case cp(R0) of\n"), @@ -783,10 +787,10 @@ gen_gc(Fd, GBP) -> GenHangulLVT = fun(Range) -> io:format(Fd, "gc_h_lv_lvt~s gc_h_T(R1,[CP|Acc]);\n", [gen_clause2(Range)]) end, [GenHangulLVT(CP) || CP <- merge_ranges(maps:get(lvt,GBP))], - io:put_chars(Fd, "gc_h_lv_lvt([CP|R], []) -> gc_extend(cp(R), R, CP);\n"), %% From gc_1/1 + io:put_chars(Fd, "gc_h_lv_lvt([CP|R1], _, []) -> gc_extend(cp(R1), R1, CP);\n"), %% From gc_1/1 io:put_chars(Fd, "%% Also handles error tuples\n"), - io:put_chars(Fd, "gc_h_lv_lvt(R, [CP]) -> gc_extend(R, R, CP);\n"), - io:put_chars(Fd, "gc_h_lv_lvt(R, Acc) -> gc_extend2(R, R, Acc).\n\n"), + io:put_chars(Fd, "gc_h_lv_lvt(R1, R0, [CP]) -> gc_extend(R1, R0, CP);\n"), + io:put_chars(Fd, "gc_h_lv_lvt(R1, R0, Acc) -> gc_extend2(R1, R0, Acc).\n\n"), ok. gen_compose_pairs(Fd, ExclData, Data) -> @@ -887,9 +891,9 @@ gen_clause({R0, R1}) -> io_lib:format("([CP|R1]=R0) when ~w =< CP, CP =< ~w ->", [R0,R1]). gen_clause2({R0, undefined}) -> - io_lib:format("([~w=CP|R1], Acc) ->", [R0]); + io_lib:format("([~w=CP|R1], R0, Acc) ->", [R0]); gen_clause2({R0, R1}) -> - io_lib:format("([CP|R1], Acc) when ~w =< CP, CP =< ~w ->", [R0,R1]). + io_lib:format("([CP|R1], R0, Acc) when ~w =< CP, CP =< ~w ->", [R0,R1]). gen_case_clause({R0, undefined}) -> io_lib:format("[~w=CP|R1] ->", [R0]); diff --git a/lib/stdlib/vsn.mk b/lib/stdlib/vsn.mk index 6471dc70e0..c2f586fef5 100644 --- a/lib/stdlib/vsn.mk +++ b/lib/stdlib/vsn.mk @@ -1 +1 @@ -STDLIB_VSN = 3.8.1 +STDLIB_VSN = 3.9.2 |