diff options
Diffstat (limited to 'lib/stdlib')
36 files changed, 1297 insertions, 789 deletions
diff --git a/lib/stdlib/doc/src/filelib.xml b/lib/stdlib/doc/src/filelib.xml index ac67596f3c..bd780b2b2f 100644 --- a/lib/stdlib/doc/src/filelib.xml +++ b/lib/stdlib/doc/src/filelib.xml @@ -36,8 +36,9 @@ <description> <p>This module contains utilities on a higher level than the <c>file</c> module.</p> - <p>The module supports Unicode file names, so that it will match against regular expressions given in Unicode and that it will find and process raw file names (i.e. files named in a way that does not confirm to the expected encoding).</p> - <p>If the VM operates in Unicode file naming mode on a machine with transparent file naming, the <c>fun()</c> provided to <c>fold_files/5</c> needs to be prepared to handle binary file names.</p> + <p>This module does not support "raw" file names (i.e. files whose names + do not comply with the expected encoding). Such files will be ignored + by the functions in this module.</p> <p>For more information about raw file names, see the <seealso marker="kernel:file">file</seealso> module.</p> </description> diff --git a/lib/stdlib/doc/src/io.xml b/lib/stdlib/doc/src/io.xml index fa475804eb..90f24c4cbc 100644 --- a/lib/stdlib/doc/src/io.xml +++ b/lib/stdlib/doc/src/io.xml @@ -211,6 +211,18 @@ </desc> </func> <func> + <name name="printable_range" arity="0"/> + <fsummary>Get user requested printable character range</fsummary> + <desc> + <p>Return the user requested range of printable Unicode characters.</p> + <p>The user can request a range of characters that are to be considered printable in heuristic detection of strings by the shell and by the formatting functions. This is done by supplying <c>+pc <range></c> when starting Erlang.</p> + <p>Currently the only valid values for <c><range></c> are <c>latin1</c> and <c>unicode</c>. <c>latin1</c> means that only code points below 256 (with the exception of control characters etc) will be considered printable. <c>unicode</c> means that all printable characters in all unicode character ranges are considered printable by the io functions.</p> + <p>By default, Erlang is started so that only the <c>latin1</c> range of characters will indicate that a list of integers is a string.</p> + <p>The simplest way to utilize the setting is to call <seealso marker="io_lib#printable_list/1">io_lib:printable_list/1</seealso>, which will use the return value of this function to decide if a list is a string of printable characters or not.</p> + <note><p>In the future, this function may return more values and ranges. It is recommended to use the io_lib:printable_list/1 function to avoid compatibility problems.</p></note> + </desc> + </func> + <func> <name name="setopts" arity="1"/> <name name="setopts" arity="2"/> <fsummary>Set options</fsummary> @@ -390,10 +402,11 @@ ok</pre> applicable, it is used for both the field width and precision. The default padding character is <c>' '</c> (space).</p> <p><c>Mod</c> is the control sequence modifier. It is either a - single character (currently only <c>t</c>, for Unicode translation, - is supported) that changes the interpretation of Data.</p> - - <p>The following control sequences are available:</p> + single character (currently only <c>t</c>, for Unicode + translation, and <c>l</c>, for stopping <c>p</c> and + <c>P</c> from detecting printable characters, are supported) + that changes the interpretation of Data.</p> + <p>The following control sequences are available:</p> <taglist> <tag><c>~</c></tag> <item> @@ -407,7 +420,7 @@ ok</pre> which in turn defaults to 1. The following example illustrates:</p> <pre> -2> <input>io:fwrite("|~10.5c|~-10.5c|~5c|~n", [$a, $b, $c]).</input> +1> <input>io:fwrite("|~10.5c|~-10.5c|~5c|~n", [$a, $b, $c]).</input> | aaaaa|bbbbb |ccccc| ok</pre> <p>If the Unicode translation modifier (<c>t</c>) is in effect, @@ -415,10 +428,10 @@ ok</pre> valid Unicode codepoint, otherwise it should be an integer less than or equal to 255, otherwise it is masked with 16#FF:</p> <pre> -1> <input>io:fwrite("~tc~n",[1024]).</input> +2> <input>io:fwrite("~tc~n",[1024]).</input> \x{400} ok -2> <input>io:fwrite("~c~n",[1024]).</input> +3> <input>io:fwrite("~c~n",[1024]).</input> ^@ ok</pre> @@ -462,20 +475,20 @@ ok</pre> <p>This format can be used for printing any object and truncating the output so it fits a specified field:</p> <pre> -3> <input>io:fwrite("|~10w|~n", [{hey, hey, hey}]).</input> +1> <input>io:fwrite("|~10w|~n", [{hey, hey, hey}]).</input> |**********| ok -4> <input>io:fwrite("|~10s|~n", [io_lib:write({hey, hey, hey})]).</input> +2> <input>io:fwrite("|~10s|~n", [io_lib:write({hey, hey, hey})]).</input> |{hey,hey,h| -5> <input>io:fwrite("|~-10.8s|~n", [io_lib:write({hey, hey, hey})]).</input> +3> <input>io:fwrite("|~-10.8s|~n", [io_lib:write({hey, hey, hey})]).</input> |{hey,hey | ok</pre> <p>A list with integers larger than 255 is considered an error if the Unicode translation modifier is not given:</p> <pre> -1> <input>io:fwrite("~ts~n",[[1024]]).</input> +4> <input>io:fwrite("~ts~n",[[1024]]).</input> \x{400} ok -2> io:fwrite("~s~n",[[1024]]). +5> <input>io:fwrite("~s~n",[[1024]]).</input> ** exception exit: {badarg,[{io,format,[<0.26.0>,"~s~n",[[1024]]]}, ...</pre> </item> @@ -493,20 +506,21 @@ ok <c>~w</c>, but breaks terms whose printed representation is longer than one line into many lines and indents each line sensibly. It also tries to detect lists of - printable characters and to output these as strings. - For example:</p> + printable characters and to output these as strings. The + Unicode translation modifier is used for determining + what characters are printable. For example:</p> <pre> -5> <input>T = [{attributes,[[{id,age,1.50000},{mode,explicit},</input> +1> <input>T = [{attributes,[[{id,age,1.50000},{mode,explicit},</input> <input>{typename,"INTEGER"}], [{id,cho},{mode,explicit},{typename,'Cho'}]]},</input> <input>{typename,'Person'},{tag,{'PRIVATE',3}},{mode,implicit}].</input> ... -6> <input>io:fwrite("~w~n", [T]).</input> +2> <input>io:fwrite("~w~n", [T]).</input> [{attributes,[[{id,age,1.5},{mode,explicit},{typename, [73,78,84,69,71,69,82]}],[{id,cho},{mode,explicit},{typena me,'Cho'}]]},{typename,'Person'},{tag,{'PRIVATE',3}},{mode ,implicit}] ok -7> <input>io:fwrite("~62p~n", [T]).</input> +3> <input>io:fwrite("~62p~n", [T]).</input> [{attributes,[[{id,age,1.5}, {mode,explicit}, {typename,"INTEGER"}], @@ -522,7 +536,7 @@ ok</pre> <c>io:fwrite</c> or <c>io:format</c>. For example, using <c>T</c> above:</p> <pre> -8> <input>io:fwrite("Here T = ~62p~n", [T]).</input> +4> <input>io:fwrite("Here T = ~62p~n", [T]).</input> Here T = [{attributes,[[{id,age,1.5}, {mode,explicit}, {typename,"INTEGER"}], @@ -533,6 +547,31 @@ Here T = [{attributes,[[{id,age,1.5}, {tag,{'PRIVATE',3}}, {mode,implicit}] ok</pre> + <p>When the modifier <c>l</c> is given no detection of + printable character lists will take place. For example:</p> + <pre> +5> <input>S = [{a,"a"}, {b, "b"}].</input> +6> <input>io:fwrite("~15p~n", [S]).</input> +[{a,"a"}, + {b,"b"}] +ok +7> <input>io:fwrite("~15lp~n", [S]).</input> +[{a,[97]}, + {b,[98]}] +ok</pre> + <p>Binaries that look like UTF-8 encoded strings will be + output with the string syntax if the Unicode translation + modifier is given:</p> + <pre> +9> <input>io:fwrite("~p~n",[[1024]]).</input> +[1024] +10> <input>io:fwrite("~tp~n",[[1024]]).</input> +"\x{400}" +11> <input>io:fwrite("~tp~n", [<<128,128>>]).</input> +<<128,128>> +12> <input>io:fwrite("~tp~n", [<<208,128>>]).</input> +<<"\x{400}"/utf8>> +ok</pre> </item> <tag><c>W</c></tag> <item> @@ -541,7 +580,7 @@ ok</pre> are printed. Anything below this depth is replaced with <c>...</c>. For example, using <c>T</c> above:</p> <pre> -9> <input>io:fwrite("~W~n", [T,9]).</input> +8> <input>io:fwrite("~W~n", [T,9]).</input> [{attributes,[[{id,age,1.5},{mode,explicit},{typename,...}], [{id,cho},{mode,...},{...}]]},{typename,'Person'}, {tag,{'PRIVATE',3}},{mode,implicit}] @@ -558,7 +597,7 @@ ok</pre> are printed. Anything below this depth is replaced with <c>...</c>. For example:</p> <pre> -10> <input>io:fwrite("~62P~n", [T,9]).</input> +9> <input>io:fwrite("~62P~n", [T,9]).</input> [{attributes,[[{id,age,1.5},{mode,explicit},{typename,...}], [{id,cho},{mode,...},{...}]]}, {typename,'Person'}, @@ -572,13 +611,13 @@ ok</pre> 10. A leading dash is printed for negative integers.</p> <p>The precision field selects base. For example:</p> <pre> -11> <input>io:fwrite("~.16B~n", [31]).</input> +1> <input>io:fwrite("~.16B~n", [31]).</input> 1F ok -12> <input>io:fwrite("~.2B~n", [-19]).</input> +2> <input>io:fwrite("~.2B~n", [-19]).</input> -10011 ok -13> <input>io:fwrite("~.36B~n", [5*36+35]).</input> +3> <input>io:fwrite("~.36B~n", [5*36+35]).</input> 5Z ok</pre> </item> @@ -590,10 +629,10 @@ ok</pre> <p>The prefix can be a possibly deep list of characters or an atom.</p> <pre> -14> <input>io:fwrite("~X~n", [31,"10#"]).</input> +1> <input>io:fwrite("~X~n", [31,"10#"]).</input> 10#31 ok -15> <input>io:fwrite("~.16X~n", [-31,"0x"]).</input> +2> <input>io:fwrite("~.16X~n", [-31,"0x"]).</input> -0x1F ok</pre> </item> @@ -602,10 +641,10 @@ ok</pre> <p>Like <c>B</c>, but prints the number with an Erlang style <c>#</c>-separated base prefix.</p> <pre> -16> <input>io:fwrite("~.10#~n", [31]).</input> +1> <input>io:fwrite("~.10#~n", [31]).</input> 10#31 ok -17> <input>io:fwrite("~.16#~n", [-31]).</input> +2> <input>io:fwrite("~.16#~n", [-31]).</input> -16#1F ok</pre> </item> @@ -639,10 +678,10 @@ ok</pre> </taglist> <p>If an error occurs, there is no output. For example:</p> <pre> -18> <input>io:fwrite("~s ~w ~i ~w ~c ~n",['abc def', 'abc def', {foo, 1},{foo, 1}, 65]).</input> +1> <input>io:fwrite("~s ~w ~i ~w ~c ~n",['abc def', 'abc def', {foo, 1},{foo, 1}, 65]).</input> abc def 'abc def' {foo,1} A ok -19> <input>io:fwrite("~s", [65]).</input> +2> <input>io:fwrite("~s", [65]).</input> ** exception exit: {badarg,[{io,format,[<0.22.0>,"~s","A"]}, {erl_eval,do_apply,5}, {shell,exprs,6}, diff --git a/lib/stdlib/doc/src/io_lib.xml b/lib/stdlib/doc/src/io_lib.xml index 001d34a7c2..3dac259477 100644 --- a/lib/stdlib/doc/src/io_lib.xml +++ b/lib/stdlib/doc/src/io_lib.xml @@ -301,7 +301,11 @@ <fsummary>Test for a list of printable characters</fsummary> <desc> <p>Returns <c>true</c> if <c><anno>Term</anno></c> is a flat list of - printable Unicode characters, otherwise it returns <c>false</c>.</p> + printable characters, otherwise it returns <c>false</c>.</p> + <p>What is a printable character in this case is determined by the + <c>+pc</c> start up flag to the Erlang VM. See + <seealso marker="io#printable_range/0">io:printable_range/0</seealso> + and <seealso marker="erts:erl#erl">erl(1)</seealso>.</p> </desc> </func> <func> @@ -312,6 +316,14 @@ printable ISO-latin-1 characters, otherwise it returns <c>false</c>.</p> </desc> </func> + <func> + <name name="printable_unicode_list" arity="1"/> + <fsummary>Test for a list of printable Unicode characters</fsummary> + <desc> + <p>Returns <c>true</c> if <c><anno>Term</anno></c> is a flat list of + printable Unicode characters, otherwise it returns <c>false</c>.</p> + </desc> + </func> </funcs> </erlref> diff --git a/lib/stdlib/doc/src/shell.xml b/lib/stdlib/doc/src/shell.xml index bc2120c37d..7f251c863e 100644 --- a/lib/stdlib/doc/src/shell.xml +++ b/lib/stdlib/doc/src/shell.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2011</year> + <year>1996</year><year>2013</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -781,7 +781,7 @@ loop(N) -> </desc> </func> <func> - <name>catch_exception(Bool) -> Bool</name> + <name>catch_exception(Bool) -> boolean()</name> <fsummary>Sets the exception handling of the shell</fsummary> <type> <v>Bool = boolean()</v> @@ -801,8 +801,8 @@ loop(N) -> <name name="prompt_func" arity="1"/> <fsummary>Sets the shell prompt</fsummary> <desc> - <p>Sets the shell prompt function to <c>PromptFunc</c>. The - previous prompt function is returned.</p> + <p>Sets the shell prompt function to <c><anno>PromptFunc</anno></c>. + The previous prompt function is returned.</p> </desc> </func> <func> @@ -827,6 +827,20 @@ loop(N) -> is meant to be called from the shell.</p> </desc> </func> + <func> + <name name="strings" arity="1"/> + <fsummary>Sets the shell's string recognition flag.</fsummary> + <desc> + <p>Sets pretty printing of lists to <c><anno>Strings</anno></c>. + The previous value of the flag is returned.</p> + <p>The flag can also be set by the STDLIB application variable + <c>shell_strings</c>. The default is + <c>true</c> which means that lists of integers will be + printed using the string syntax, when possible. The value + <c>false</c> means that no lists will be printed using the + string syntax.</p> + </desc> + </func> </funcs> </erlref> diff --git a/lib/stdlib/doc/src/stdlib_app.xml b/lib/stdlib/doc/src/stdlib_app.xml index a615c1bf88..2391bb6f03 100644 --- a/lib/stdlib/doc/src/stdlib_app.xml +++ b/lib/stdlib/doc/src/stdlib_app.xml @@ -4,7 +4,7 @@ <appref> <header> <copyright> - <year>2005</year><year>2010</year> + <year>2005</year><year>2013</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -51,7 +51,7 @@ <p>This parameter can be used to run the Erlang shell in restricted mode.</p> </item> - <tag><c>shell_catch_exception = bool()</c></tag> + <tag><c>shell_catch_exception = boolean()</c></tag> <item> <p>This parameter can be used to set the exception handling of the Erlang shell's evaluator process.</p> @@ -76,6 +76,11 @@ <p>This parameter can be used to determine how many results are saved by the Erlang shell.</p> </item> + <tag><c>shell_strings = boolean()</c></tag> + <item> + <p>This parameter can be used to determine how the Erlang + shell outputs lists of integers.</p> + </item> </taglist> </section> diff --git a/lib/stdlib/doc/src/unicode_usage.xml b/lib/stdlib/doc/src/unicode_usage.xml index 0a75fbeec0..354ec58df3 100644 --- a/lib/stdlib/doc/src/unicode_usage.xml +++ b/lib/stdlib/doc/src/unicode_usage.xml @@ -69,12 +69,11 @@ strings.</p> <p>Character data may be combined from several sources, sometimes available in a mix of strings and binaries. Erlang has for long had the concept of <c>iodata</c> or <c>iolists</c>, where binaries and lists can be combined to represent a sequence of bytes. In the same way, the Unicode aware modules often allow for combinations of binaries and lists where the binaries have characters encoded in UTF-8 and the lists contain such binaries or numbers representing Unicode codepoints:</p> <code type="none"> unicode_binary() = binary() with characters encoded in UTF-8 coding standard -unicode_char() = integer() >= 0 representing valid Unicode codepoint chardata() = charlist() | unicode_binary() -charlist() = [unicode_char() | unicode_binary() | charlist()] - a unicode_binary is allowed as the tail of the list</code> +charlist() = maybe_improper_list(char() | unicode_binary() | charlist(), + unicode_binary() | nil())</code> <p>The module <c>unicode</c> in STDLIB even supports similar mixes with binaries containing other encodings than UTF-8, but that is a special case to allow for conversions to and from external data:</p> <code type="none"> external_unicode_binary() = binary() with characters coded in @@ -82,10 +81,10 @@ external_unicode_binary() = binary() with characters coded in external_chardata() = external_charlist() | external_unicode_binary() -external_charlist() = [unicode_char() | - external_unicode_binary() | - external_charlist()] - an external_unicode_binary() is allowed as the tail of the list</code> +external_charlist() = maybe_improper_list(char() | + external_unicode_binary() | + external_charlist(), + external_unicode_binary() | nil())</code> </section> <section> <title>Basic Language Support for Unicode</title> diff --git a/lib/stdlib/src/binary.erl b/lib/stdlib/src/binary.erl index 41b6ab1d5f..1fb241fd1d 100644 --- a/lib/stdlib/src/binary.erl +++ b/lib/stdlib/src/binary.erl @@ -58,7 +58,7 @@ bin_to_list(_, _) -> -spec bin_to_list(Subject, Pos, Len) -> [byte()] when Subject :: binary(), Pos :: non_neg_integer(), - Len :: non_neg_integer(). + Len :: integer(). bin_to_list(_, _, _) -> erlang:nif_error(undef). @@ -186,7 +186,7 @@ part(_, _) -> -spec part(Subject, Pos, Len) -> binary() when Subject :: binary(), Pos :: non_neg_integer(), - Len :: non_neg_integer(). + Len :: integer(). part(_, _, _) -> erlang:nif_error(undef). diff --git a/lib/stdlib/src/c.erl b/lib/stdlib/src/c.erl index 535f2d5174..91d317489c 100644 --- a/lib/stdlib/src/c.erl +++ b/lib/stdlib/src/c.erl @@ -512,7 +512,7 @@ m(M) -> print_object_file(Mod) -> case code:is_loaded(Mod) of {file,File} -> - format("Object file: ~s\n", [File]); + format("Object file: ~ts\n", [File]); _ -> ignore end. @@ -685,7 +685,7 @@ portformat(Name, Id, Cmd) -> pwd() -> case file:get_cwd() of {ok, Str} -> - ok = io:format("~ts\n", [fixup_one_bin(Str)]); + ok = io:format("~ts\n", [Str]); {error, _} -> ok = io:format("Cannot determine current directory\n") end. @@ -712,27 +712,11 @@ ls() -> ls(Dir) -> case file:list_dir(Dir) of {ok, Entries} -> - ls_print(sort(fixup_bin(Entries))); + ls_print(sort(Entries)); {error,_E} -> format("Invalid directory\n") end. -fixup_one_bin(X) when is_binary(X) -> - L = binary_to_list(X), - [ if - El > 127 -> - $?; - true -> - El - end || El <- L]; -fixup_one_bin(X) -> - X. -fixup_bin([H|T]) -> - [fixup_one_bin(H) | fixup_bin(T)]; -fixup_bin([]) -> - []. - - ls_print([]) -> ok; ls_print(L) -> Width = min([max(lengths(L, [])), 40]) + 5, diff --git a/lib/stdlib/src/epp.erl b/lib/stdlib/src/epp.erl index afa39c3fb9..0a1caa7178 100644 --- a/lib/stdlib/src/epp.erl +++ b/lib/stdlib/src/epp.erl @@ -614,7 +614,7 @@ enter_file_reply(From, Name, Location, AtLocation) -> %% Flatten filename to a string. Must be a valid filename. -file_name([C | T]) when is_integer(C), C > 0, C =< 255 -> +file_name([C | T]) when is_integer(C), C > 0 -> [C | file_name(T)]; file_name([H|T]) -> file_name(H) ++ file_name(T); @@ -661,7 +661,7 @@ leave_file(From, St) -> %% scan_toks(Tokens, From, EppState) scan_toks(From, St) -> - case io:scan_erl_form(St#epp.file, '', St#epp.location, [unicode]) of + case io:scan_erl_form(St#epp.file, '', St#epp.location) of {ok,Toks,Cl} -> scan_toks(Toks, From, St#epp{location=Cl}); {error,E,Cl} -> @@ -1035,7 +1035,7 @@ new_location(Ln, {Le,_}, {Lf,_}) -> %% nested conditionals and repeated 'else's. skip_toks(From, St, [I|Sis]) -> - case io:scan_erl_form(St#epp.file, '', St#epp.location, [unicode]) of + case io:scan_erl_form(St#epp.file, '', St#epp.location) of {ok,[{'-',_Lh},{atom,_Li,ifdef}|_Toks],Cl} -> skip_toks(From, St#epp{location=Cl}, [ifdef,I|Sis]); {ok,[{'-',_Lh},{atom,_Li,ifndef}|_Toks],Cl} -> diff --git a/lib/stdlib/src/erl_eval.erl b/lib/stdlib/src/erl_eval.erl index 1c3f91cbfc..0b57af1b6d 100644 --- a/lib/stdlib/src/erl_eval.erl +++ b/lib/stdlib/src/erl_eval.erl @@ -346,7 +346,12 @@ expr({call,_,{atom,_,Func},As0}, Bs0, Lf, Ef, RBs) -> expr({call,_,Func0,As0}, Bs0, Lf, Ef, RBs) -> % function or {Mod,Fun} {value,Func,Bs1} = expr(Func0, Bs0, Lf, Ef, none), {As,Bs2} = expr_list(As0, Bs1, Lf, Ef), - do_apply(Func, As, Bs2, Ef, RBs); + case Func of + {M,F} when is_atom(M), is_atom(F) -> + erlang:raise(error, {badfun,Func}, stacktrace()); + _ -> + do_apply(Func, As, Bs2, Ef, RBs) + end; expr({'catch',_,Expr}, Bs0, Lf, Ef, RBs) -> Ref = make_ref(), case catch {Ref,expr(Expr, Bs0, Lf, Ef, none)} of diff --git a/lib/stdlib/src/erl_internal.erl b/lib/stdlib/src/erl_internal.erl index 254384e877..378e629ac9 100644 --- a/lib/stdlib/src/erl_internal.erl +++ b/lib/stdlib/src/erl_internal.erl @@ -254,6 +254,9 @@ bif(binary_part, 2) -> true; bif(binary_part, 3) -> true; bif(binary_to_atom, 2) -> true; bif(binary_to_existing_atom, 2) -> true; +bif(binary_to_integer, 1) -> true; +bif(binary_to_integer, 2) -> true; +bif(binary_to_float, 1) -> true; bif(binary_to_list, 1) -> true; bif(binary_to_list, 3) -> true; bif(binary_to_term, 1) -> true; @@ -279,6 +282,8 @@ bif(exit, 2) -> true; bif(float, 1) -> true; bif(float_to_list, 1) -> true; bif(float_to_list, 2) -> true; +bif(float_to_binary, 1) -> true; +bif(float_to_binary, 2) -> true; bif(garbage_collect, 0) -> true; bif(garbage_collect, 1) -> true; bif(get, 0) -> true; @@ -290,6 +295,8 @@ bif(halt, 0) -> true; bif(halt, 1) -> true; bif(halt, 2) -> true; bif(hd, 1) -> true; +bif(integer_to_binary, 1) -> true; +bif(integer_to_binary, 2) -> true; bif(integer_to_list, 1) -> true; bif(integer_to_list, 2) -> true; bif(iolist_size, 1) -> true; diff --git a/lib/stdlib/src/erl_lint.erl b/lib/stdlib/src/erl_lint.erl index deae9640f5..68a8534f15 100644 --- a/lib/stdlib/src/erl_lint.erl +++ b/lib/stdlib/src/erl_lint.erl @@ -152,8 +152,6 @@ format_error({attribute,A}) -> io_lib:format("attribute '~w' after function definitions", [A]); format_error({missing_qlc_hrl,A}) -> io_lib:format("qlc:q/~w called, but \"qlc.hrl\" not included", [A]); -format_error({redefine_import,{bif,{F,A},M}}) -> - io_lib:format("function ~w/~w already auto-imported from ~w", [F,A,M]); format_error({redefine_import,{{F,A},M}}) -> io_lib:format("function ~w/~w already imported from ~w", [F,A,M]); format_error({bad_inline,{F,A}}) -> @@ -222,8 +220,6 @@ format_error({removed, MFA, String}) when is_list(String) -> io_lib:format("~s: ~s", [format_mfa(MFA), String]); format_error({obsolete_guard, {F, A}}) -> io_lib:format("~p/~p obsolete", [F, A]); -format_error({reserved_for_future,K}) -> - io_lib:format("atom ~w: future reserved keyword - rename or quote", [K]); format_error({too_many_arguments,Arity}) -> io_lib:format("too many arguments (~w) - " "maximum allowed is ~w", [Arity,?MAX_ARGUMENTS]); @@ -236,11 +232,6 @@ format_error({illegal_guard_local_call, {F,A}}) -> io_lib:format("call to local/imported function ~w/~w is illegal in guard", [F,A]); format_error(illegal_guard_expr) -> "illegal guard expression"; -%% --- exports --- -format_error({explicit_export,F,A}) -> - io_lib:format("in this release, the call to ~w/~w must be written " - "like this: erlang:~w/~w", - [F,A,F,A]); %% --- records --- format_error({undefined_record,T}) -> io_lib:format("record ~w undefined", [T]); @@ -278,8 +269,6 @@ format_error({variable_in_record_def,V}) -> %% --- binaries --- format_error({undefined_bittype,Type}) -> io_lib:format("bit type ~w undefined", [Type]); -format_error({bittype_mismatch,T1,T2,What}) -> - io_lib:format("bit type mismatch (~s) between ~p and ~p", [What,T1,T2]); format_error(bittype_unit) -> "a bit unit size must not be specified unless a size is specified too"; format_error(illegal_bitsize) -> @@ -1798,11 +1787,9 @@ gexpr({call,Line,{atom,_La,F},As}, Vt, St0) -> %% BifClash - Function called in guard case erl_internal:guard_bif(F, A) andalso no_guard_bif_clash(St1,{F,A}) of true -> - %% Also check that it is auto-imported. - case erl_internal:bif(F, A) of - true -> {Asvt,St1}; - false -> {Asvt,add_error(Line, {explicit_export,F,A}, St1)} - end; + %% Assert that it is auto-imported. + true = erl_internal:bif(F, A), + {Asvt,St1}; false -> case is_local_function(St1#lint.locals,{F,A}) orelse is_imported_function(St1#lint.imports,{F,A}) of @@ -3496,6 +3483,12 @@ extract_sequence(4, [$t, $P | Fmt], Need) -> extract_sequence(5, [$P|Fmt], Need); extract_sequence(4, [$t, C | _Fmt], _Need) -> {error,"invalid control ~t" ++ [C]}; +extract_sequence(4, [$l, $p | Fmt], Need) -> + extract_sequence(5, [$p|Fmt], Need); +extract_sequence(4, [$l, $P | Fmt], Need) -> + extract_sequence(5, [$P|Fmt], Need); +extract_sequence(4, [$l, C | _Fmt], _Need) -> + {error,"invalid control ~l" ++ [C]}; extract_sequence(4, Fmt, Need) -> extract_sequence(5, Fmt, Need); extract_sequence(5, [C|Fmt], Need0) -> diff --git a/lib/stdlib/src/erl_pp.erl b/lib/stdlib/src/erl_pp.erl index a868867a81..7c7566e4ec 100644 --- a/lib/stdlib/src/erl_pp.erl +++ b/lib/stdlib/src/erl_pp.erl @@ -61,7 +61,8 @@ form(Thing) -> Options :: options()). form(Thing, Options) -> - frmt(lform(Thing, options(Options)), state(Options)). + State = state(Options), + frmt(lform(Thing, options(Options), State), State). -spec(attribute(Attribute) -> io_lib:chars() when Attribute :: erl_parse:abstract_form()). @@ -74,7 +75,8 @@ attribute(Thing) -> Options :: options()). attribute(Thing, Options) -> - frmt(lattribute(Thing, options(Options)), state(Options)). + State = state(Options), + frmt(lattribute(Thing, options(Options), State), State). -spec(function(Function) -> io_lib:chars() when Function :: erl_parse:abstract_form()). @@ -193,47 +195,47 @@ encoding(Options) -> unicode -> unicode end. -lform({attribute,Line,Name,Arg}, Opts) -> - lattribute({attribute,Line,Name,Arg}, Opts); -lform({function,Line,Name,Arity,Clauses}, Opts) -> +lform({attribute,Line,Name,Arg}, Opts, State) -> + lattribute({attribute,Line,Name,Arg}, Opts, State); +lform({function,Line,Name,Arity,Clauses}, Opts, _State) -> lfunction({function,Line,Name,Arity,Clauses}, Opts); -lform({rule,Line,Name,Arity,Clauses}, Opts) -> +lform({rule,Line,Name,Arity,Clauses}, Opts, _State) -> lrule({rule,Line,Name,Arity,Clauses}, Opts); %% These are specials to make it easier for the compiler. -lform({error,E}, _Opts) -> +lform({error,E}, _Opts, _State) -> leaf(format("~p\n", [{error,E}])); -lform({warning,W}, _Opts) -> +lform({warning,W}, _Opts, _State) -> leaf(format("~p\n", [{warning,W}])); -lform({eof,_Line}, _Opts) -> +lform({eof,_Line}, _Opts, _State) -> $\n. -lattribute({attribute,_Line,type,Type}, Opts) -> +lattribute({attribute,_Line,type,Type}, Opts, _State) -> [typeattr(type, Type, Opts),leaf(".\n")]; -lattribute({attribute,_Line,opaque,Type}, Opts) -> +lattribute({attribute,_Line,opaque,Type}, Opts, _State) -> [typeattr(opaque, Type, Opts),leaf(".\n")]; -lattribute({attribute,_Line,spec,Arg}, _Opts) -> +lattribute({attribute,_Line,spec,Arg}, _Opts, _State) -> [specattr(Arg),leaf(".\n")]; -lattribute({attribute,_Line,Name,Arg}, Opts) -> - [lattribute(Name, Arg, Opts),leaf(".\n")]. +lattribute({attribute,_Line,Name,Arg}, Opts, State) -> + [lattribute(Name, Arg, Opts, State),leaf(".\n")]. -lattribute(module, {M,Vs}, _Opts) -> +lattribute(module, {M,Vs}, _Opts, _State) -> attr("module",[{var,0,pname(M)}, foldr(fun(V, C) -> {cons,0,{var,0,V},C} end, {nil,0}, Vs)]); -lattribute(module, M, _Opts) -> +lattribute(module, M, _Opts, _State) -> attr("module", [{var,0,pname(M)}]); -lattribute(export, Falist, _Opts) -> +lattribute(export, Falist, _Opts, _State) -> call({var,0,"-export"}, [falist(Falist)], 0, none); -lattribute(import, Name, _Opts) when is_list(Name) -> +lattribute(import, Name, _Opts, _State) when is_list(Name) -> attr("import", [{var,0,pname(Name)}]); -lattribute(import, {From,Falist}, _Opts) -> +lattribute(import, {From,Falist}, _Opts, _State) -> attr("import",[{var,0,pname(From)},falist(Falist)]); -lattribute(file, {Name,Line}, _Opts) -> - attr("file", [{var,0,format("~p", [Name])},{integer,0,Line}]); -lattribute(record, {Name,Is}, Opts) -> +lattribute(file, {Name,Line}, _Opts, State) -> + attr("file", [{var,0,(State#pp.string_fun)(Name)},{integer,0,Line}]); +lattribute(record, {Name,Is}, Opts, _State) -> Nl = leaf(format("-record(~w,", [Name])), [{first,Nl,record_fields(Is, Opts)},$)]; -lattribute(Name, Arg, #options{encoding = Encoding}) -> +lattribute(Name, Arg, #options{encoding = Encoding}, _State) -> attr(write(Name), [erl_parse:abstract(Arg, [{encoding,Encoding}])]). typeattr(Tag, {TypeName,Type,Args}, _Opts) -> @@ -423,7 +425,7 @@ lexpr(E, Opts) -> lexpr({var,_,V}, _, _) when is_integer(V) -> %Special hack for Robert leaf(format("_~w", [V])); -lexpr({var,_,V}, _, _) -> leaf(format("~s", [V])); +lexpr({var,_,V}, _, _) -> leaf(format("~ts", [V])); lexpr({char,_,C}, _, _) -> {char,C}; lexpr({integer,_,N}, _, _) -> leaf(write(N)); lexpr({float,_,F}, _, _) -> leaf(write(F)); @@ -799,7 +801,7 @@ maybe_paren(_P, _Prec, Expr) -> Expr. leaf(S) -> - {leaf,iolist_size(S),S}. + {leaf,chars_size(S),S}. %%% Do the formatting. Currently nothing fancy. Could probably have %%% done it in one single pass. @@ -1009,7 +1011,7 @@ incr(I, Incr) -> I+Incr. indentation(E, I) when I < 0 -> - iolist_size(E); + chars_size(E); indentation(E, I0) -> I = io_lib_format:indentation(E, I0), case has_nl(E) of @@ -1064,6 +1066,15 @@ write_char(C, PP) -> %% Utilities %% +chars_size([C | Es]) when is_integer(C) -> + 1 + chars_size(Es); +chars_size([E | Es]) -> + chars_size(E) + chars_size(Es); +chars_size([]) -> + 0; +chars_size(B) when is_binary(B) -> + byte_size(B). + -define(N_SPACES, 30). spacetab() -> diff --git a/lib/stdlib/src/erl_scan.erl b/lib/stdlib/src/erl_scan.erl index 26d5747ee7..3651f608bc 100644 --- a/lib/stdlib/src/erl_scan.erl +++ b/lib/stdlib/src/erl_scan.erl @@ -84,8 +84,7 @@ -type location() :: line() | {line(),column()}. -type resword_fun() :: fun((atom()) -> boolean()). -type option() :: 'return' | 'return_white_spaces' | 'return_comments' - | 'text' | {'reserved_word_fun', resword_fun()} - | 'unicode'. + | 'text' | {'reserved_word_fun', resword_fun()}. -type options() :: option() | [option()]. -type symbol() :: atom() | float() | integer() | string(). -type info_line() :: integer() | term(). @@ -106,8 +105,7 @@ {resword_fun = fun reserved_word/1 :: resword_fun(), ws = false :: boolean(), comment = false :: boolean(), - text = false :: boolean(), - unicode = true :: boolean()}). + text = false :: boolean()}). %%---------------------------------------------------------------------------- @@ -344,20 +342,12 @@ string_thing(_) -> "string". C > 16#DFFF andalso C < 16#FFFE orelse C > 16#FFFF andalso C =< 16#10FFFF)). -%% When the option 'unicode' is false: return Unicode strings as lists -%% of integers and Unicode characters as integers. For instance, -%% erl_scan:string("\"b\x{aaa}c\".") is equivalent to -%% erl_scan:string("[98,2730,99]."). This is to protect the caller -%% from character codes greater than 255. Search for UNI to find code -%% implementing this "feature". The 'unicode' option is undocumented -%% and will be removed later. --define(NO_UNICODE, 0). --define(UNI255(C), (C =< 16#ff)). +-define(UNI255(C), C >= 0, C =< 16#ff). options(Opts0) when is_list(Opts0) -> Opts = lists:foldr(fun expand_opt/2, [], Opts0), - [RW_fun, Unicode] = - case opts(Opts, [reserved_word_fun, unicode], []) of + [RW_fun] = + case opts(Opts, [reserved_word_fun], []) of badarg -> erlang:error(badarg, [Opts0]); R -> @@ -369,8 +359,7 @@ options(Opts0) when is_list(Opts0) -> #erl_scan{resword_fun = RW_fun, comment = Comment, ws = WS, - text = Txt, - unicode = Unicode}; + text = Txt}; options(Opt) -> options([Opt]). @@ -378,8 +367,6 @@ opts(Options, [Key|Keys], L) -> V = case lists:keyfind(Key, 1, Options) of {reserved_word_fun,F} when ?RESWORDFUN(F) -> {ok,F}; - {unicode, Bool} when is_boolean(Bool) -> - {ok,Bool}; {Key,_} -> badarg; false -> @@ -395,9 +382,7 @@ opts(_Options, [], L) -> lists:reverse(L). default_option(reserved_word_fun) -> - fun reserved_word/1; -default_option(unicode) -> - true. + fun reserved_word/1. expand_opt(return, Os) -> [return_comments,return_white_spaces|Os]; @@ -531,10 +516,10 @@ scan1("."=Cs, _St, Line, Col, Toks) -> scan1([$.=C|Cs], St, Line, Col, Toks) -> scan_dot(Cs, St, Line, Col, Toks, [C]); scan1([$"|Cs], St, Line, Col, Toks) -> %" Emacs - State0 = {[],[],Line,Col,?NO_UNICODE}, + State0 = {[],[],Line,Col}, scan_string(Cs, St, Line, incr_column(Col, 1), Toks, State0); scan1([$'|Cs], St, Line, Col, Toks) -> %' Emacs - State0 = {[],[],Line,Col,?NO_UNICODE}, + State0 = {[],[],Line,Col}, scan_qatom(Cs, St, Line, incr_column(Col, 1), Toks, State0); scan1([$$|Cs], St, Line, Col, Toks) -> scan_char(Cs, St, Line, Col, Toks); @@ -655,7 +640,7 @@ scan1([$~|Cs], St, Line, Col, Toks) -> scan1([$&|Cs], St, Line, Col, Toks) -> tok2(Cs, St, Line, Col, Toks, "&", '&', 1); %% End of optimization. -scan1([C|Cs], St, Line, Col, Toks) when ?CHAR(C), ?UNI255(C) -> +scan1([C|Cs], St, Line, Col, Toks) when ?UNI255(C) -> Str = [C], tok2(Cs, St, Line, Col, Toks, Str, list_to_atom(Str), 1); scan1([C|Cs], _St, Line, Col, _Toks) when ?CHAR(C) -> @@ -718,14 +703,16 @@ scan_name([], Ncs) -> scan_name(Cs, Ncs) -> {lists:reverse(Ncs),Cs}. +-define(STR(St, S), if St#erl_scan.text -> S; true -> [] end). + scan_dot([$%|_]=Cs, St, Line, Col, Toks, Ncs) -> Attrs = attributes(Line, Col, St, Ncs), {ok,[{dot,Attrs}|Toks],Cs,Line,incr_column(Col, 1)}; scan_dot([$\n=C|Cs], St, Line, Col, Toks, Ncs) -> - Attrs = attributes(Line, Col, St, Ncs++[C]), + Attrs = attributes(Line, Col, St, ?STR(St, Ncs++[C])), {ok,[{dot,Attrs}|Toks],Cs,Line+1,new_column(Col, 1)}; scan_dot([C|Cs], St, Line, Col, Toks, Ncs) when ?WHITE_SPACE(C) -> - Attrs = attributes(Line, Col, St, Ncs++[C]), + Attrs = attributes(Line, Col, St, ?STR(St, Ncs++[C])), {ok,[{dot,Attrs}|Toks],Cs,Line,incr_column(Col, 2)}; scan_dot(eof=Cs, St, Line, Col, Toks, Ncs) -> Attrs = attributes(Line, Col, St, Ncs), @@ -858,26 +845,20 @@ scan_char([$\\|Cs]=Cs0, St, Line, Col, Toks) -> {eof,Ncol} -> scan_error(char, Line, Col, Line, Ncol, eof); {nl,Val,Str,Ncs,Ncol} -> - Attrs = attributes(Line, Col, St, "$\\"++Str), %" + Attrs = attributes(Line, Col, St, ?STR(St, "$\\"++Str)), %" Ntoks = [{char,Attrs,Val}|Toks], scan1(Ncs, St, Line+1, Ncol, Ntoks); - {unicode,Val,Str,Ncs,Ncol} -> - Attrs = attributes(Line, Col, St, "$\\"++Str), %" - Tag = char_tag(Val, St), % UNI - Ntoks = [{Tag,Attrs,Val}|Toks], - scan1(Ncs, St, Line, Ncol, Ntoks); {Val,Str,Ncs,Ncol} -> - Attrs = attributes(Line, Col, St, "$\\"++Str), %" + Attrs = attributes(Line, Col, St, ?STR(St, "$\\"++Str)), %" Ntoks = [{char,Attrs,Val}|Toks], scan1(Ncs, St, Line, Ncol, Ntoks) end; scan_char([$\n=C|Cs], St, Line, Col, Toks) -> - Attrs = attributes(Line, Col, St, [$$,C]), + Attrs = attributes(Line, Col, St, ?STR(St, [$$,C])), scan1(Cs, St, Line+1, new_column(Col, 1), [{char,Attrs,C}|Toks]); scan_char([C|Cs], St, Line, Col, Toks) when ?UNICODE(C) -> - Tag = char_tag(C, St), % UNI - Attrs = attributes(Line, Col, St, [$$,C]), - scan1(Cs, St, Line, incr_column(Col, 2), [{Tag,Attrs,C}|Toks]); + Attrs = attributes(Line, Col, St, ?STR(St, [$$,C])), + scan1(Cs, St, Line, incr_column(Col, 2), [{char,Attrs,C}|Toks]); scan_char([C|_Cs], _St, Line, Col, _Toks) when ?CHAR(C) -> scan_error({illegal,character}, Line, Col, Line, incr_column(Col, 1), eof); scan_char([], _St, Line, Col, Toks) -> @@ -885,90 +866,32 @@ scan_char([], _St, Line, Col, Toks) -> scan_char(eof, _St, Line, Col, _Toks) -> scan_error(char, Line, Col, Line, incr_column(Col, 1), eof). --compile({inline,[char_tag/2]}). - -char_tag(C, _St) when ?UNI255(C) -> - char; -char_tag(_C, #erl_scan{unicode = true}) -> - char; -char_tag(_C, _St) -> - integer. - -scan_string(Cs, St, Line, Col, Toks, {Wcs,Str,Line0,Col0,Uni0}) -> - case scan_string0(Cs, St, Line, Col, $\", true, Str, Wcs, Uni0) of %" - {more,Ncs,Nline,Ncol,Nstr,Nwcs,Uni} -> - State = {Nwcs,Nstr,Line0,Col0,Uni}, +scan_string(Cs, St, Line, Col, Toks, {Wcs,Str,Line0,Col0}) -> + case scan_string0(Cs, St, Line, Col, $\", Str, Wcs) of %" + {more,Ncs,Nline,Ncol,Nstr,Nwcs} -> + State = {Nwcs,Nstr,Line0,Col0}, {more,{Ncs,Ncol,Toks,Nline,State,fun scan_string/6}}; {char_error,Ncs,Error,Nline,Ncol,EndCol} -> scan_error(Error, Nline, Ncol, Nline, EndCol, Ncs); {error,Nline,Ncol,Nwcs,Ncs} -> Estr = string:substr(Nwcs, 1, 16), % Expanded escape chars. scan_error({string,$\",Estr}, Line0, Col0, Nline, Ncol, Ncs); %" - {Ncs,Nline,Ncol,Nstr,Nwcs,Uni} when Uni =:= ?NO_UNICODE; - St#erl_scan.unicode -> + {Ncs,Nline,Ncol,Nstr,Nwcs} -> Attrs = attributes(Line0, Col0, St, Nstr), - scan1(Ncs, St, Nline, Ncol, [{string,Attrs,Nwcs}|Toks]); - {Ncs,Nline,Ncol,Nstr,_Nwcs,_Uni} -> - Ntoks = unicode_string_to_list(Line0, Col0, St, Nstr, Toks), - scan1(Ncs, St, Nline, Ncol, Ntoks) + scan1(Ncs, St, Nline, Ncol, [{string,Attrs,Nwcs}|Toks]) end. -%% UNI -unicode_string_to_list(Line, Col, St, [$"=C|Nstr], Toks) -> %" Emacs - Paren = {'[',attributes(Line, Col, St, [C])}, - u2l(Nstr, Line, incr_column(Col, 1), St, [Paren|Toks]). - -u2l([$"]=Cs, Line, Col, St, Toks) -> %" Emacs - [{']',attributes(Line, Col, St, Cs)}|Toks]; -u2l([$\n=C|Cs], Line, Col, St, Toks) -> - Ntoks = unicode_nl_tokens(Line, Col, [C], C, St, Toks, Cs), - u2l(Cs, Line+1, new_column(Col, 1), St, Ntoks); -u2l([$\\|Cs], Line, Col, St, Toks) -> - case scan_escape(Cs, Col) of - {nl,Val,ValStr,Ncs,Ncol} -> - Nstr = [$\\|ValStr], - Ntoks = unicode_nl_tokens(Line, Col, Nstr, Val, St, Toks, Ncs), - u2l(Ncs, Line+1, Ncol, St, Ntoks); - {unicode,Val,ValStr,Ncs,Ncol} -> - Nstr = [$\\|ValStr], - Ntoks = unicode_tokens(Line, Col, Nstr, Val, St, Toks, Ncs), - u2l(Ncs, Line, incr_column(Ncol, 1), St, Ntoks); - {Val,ValStr,Ncs,Ncol} -> - Nstr = [$\\|ValStr], - Ntoks = unicode_tokens(Line, Col, Nstr, Val, St, Toks, Ncs), - u2l(Ncs, Line, incr_column(Ncol, 1), St, Ntoks) - end; -u2l([C|Cs], Line, Col, St, Toks) -> - Ntoks = unicode_tokens(Line, Col, [C], C, St, Toks, Cs), - u2l(Cs, Line, incr_column(Col, 1), St, Ntoks). - -unicode_nl_tokens(Line, Col, Str, Val, St, Toks, Cs) -> - Ccol = new_column(Col, 1), - unicode_tokens(Line, Col, Str, Val, St, Toks, Cs, Line+1, Ccol). - -unicode_tokens(Line, Col, Str, Val, St, Toks, Cs) -> - Ccol = incr_column(Col, length(Str)), - unicode_tokens(Line, Col, Str, Val, St, Toks, Cs, Line, Ccol). - -unicode_tokens(Line, Col, Str, Val, St, Toks, Cs, Cline, Ccol) -> - Attrs = attributes(Line, Col, St, Str), - Tag = if ?UNI255(Val) -> char; true -> integer end, - Token = {Tag,Attrs,Val}, - [{',',attributes(Cline, Ccol, St, "")} || Cs =/= "\""] ++ [Token|Toks]. - -scan_qatom(Cs, St, Line, Col, Toks, {Wcs,Str,Line0,Col0,Uni0}) -> - AllowUni = St#erl_scan.unicode, - case scan_string0(Cs, St, Line, Col, $\', AllowUni, Str, Wcs, Uni0) of %' - {more,Ncs,Nline,Ncol,Nstr,Nwcs,Uni} -> - State = {Nwcs,Nstr,Line0,Col0,Uni}, +scan_qatom(Cs, St, Line, Col, Toks, {Wcs,Str,Line0,Col0}) -> + case scan_string0(Cs, St, Line, Col, $\', Str, Wcs) of %' + {more,Ncs,Nline,Ncol,Nstr,Nwcs} -> + State = {Nwcs,Nstr,Line0,Col0}, {more,{Ncs,Ncol,Toks,Nline,State,fun scan_qatom/6}}; {char_error,Ncs,Error,Nline,Ncol,EndCol} -> scan_error(Error, Nline, Ncol, Nline, EndCol, Ncs); {error,Nline,Ncol,Nwcs,Ncs} -> Estr = string:substr(Nwcs, 1, 16), % Expanded escape chars. scan_error({string,$\',Estr}, Line0, Col0, Nline, Ncol, Ncs); %' - {Ncs,Nline,Ncol,Nstr,Nwcs,Uni} -> - true = Uni =:= ?NO_UNICODE orelse AllowUni, + {Ncs,Nline,Ncol,Nstr,Nwcs} -> case catch list_to_atom(Nwcs) of A when is_atom(A) -> Attrs = attributes(Line0, Col0, St, Nstr), @@ -978,95 +901,75 @@ scan_qatom(Cs, St, Line, Col, Toks, {Wcs,Str,Line0,Col0,Uni0}) -> end end. -scan_string0(Cs, #erl_scan{text=false}, Line, no_col=Col, Q, U, [], Wcs, Uni) -> - scan_string_no_col(Cs, Line, Col, Q, U, Wcs, Uni); -scan_string0(Cs, #erl_scan{text=true}, Line, no_col=Col, Q, U, Str, Wcs, Uni) -> - scan_string1(Cs, Line, Col, Q, U, Str, Wcs, Uni); -scan_string0(Cs, _St, Line, Col, Q, U, [], Wcs, Uni) -> - scan_string_col(Cs, Line, Col, Q, U, Wcs, Uni); -scan_string0(Cs, _St, Line, Col, Q, U, Str, Wcs, Uni) -> - scan_string1(Cs, Line, Col, Q, U, Str, Wcs, Uni). +scan_string0(Cs, #erl_scan{text=false}, Line, no_col=Col, Q, [], Wcs) -> + scan_string_no_col(Cs, Line, Col, Q, Wcs); +scan_string0(Cs, #erl_scan{text=true}, Line, no_col=Col, Q, Str, Wcs) -> + scan_string1(Cs, Line, Col, Q, Str, Wcs); +scan_string0(Cs, St, Line, Col, Q, [], Wcs) -> + scan_string_col(Cs, St, Line, Col, Q, Wcs); +scan_string0(Cs, _St, Line, Col, Q, Str, Wcs) -> + scan_string1(Cs, Line, Col, Q, Str, Wcs). %% Optimization. Col =:= no_col. -scan_string_no_col([Q|Cs], Line, Col, Q, _U, Wcs, Uni) -> - {Cs,Line,Col,_DontCare=[],lists:reverse(Wcs),Uni}; -scan_string_no_col([$\n=C|Cs], Line, Col, Q, U, Wcs, Uni) -> - scan_string_no_col(Cs, Line+1, Col, Q, U, [C|Wcs], Uni); -scan_string_no_col([C|Cs], Line, Col, Q, U, Wcs, Uni) when C =/= $\\, - ?CHAR(C), - ?UNI255(C) -> - scan_string_no_col(Cs, Line, Col, Q, U, [C|Wcs], Uni); -scan_string_no_col(Cs, Line, Col, Q, U, Wcs, Uni) -> - scan_string1(Cs, Line, Col, Q, U, Wcs, Wcs, Uni). +scan_string_no_col([Q|Cs], Line, Col, Q, Wcs) -> + {Cs,Line,Col,_DontCare=[],lists:reverse(Wcs)}; +scan_string_no_col([$\n=C|Cs], Line, Col, Q, Wcs) -> + scan_string_no_col(Cs, Line+1, Col, Q, [C|Wcs]); +scan_string_no_col([C|Cs], Line, Col, Q, Wcs) when C =/= $\\, ?UNICODE(C) -> + scan_string_no_col(Cs, Line, Col, Q, [C|Wcs]); +scan_string_no_col(Cs, Line, Col, Q, Wcs) -> + scan_string1(Cs, Line, Col, Q, Wcs, Wcs). %% Optimization. Col =/= no_col. -scan_string_col([Q|Cs], Line, Col, Q, _U, Wcs0, Uni) -> +scan_string_col([Q|Cs], St, Line, Col, Q, Wcs0) -> Wcs = lists:reverse(Wcs0), - Str = [Q|Wcs++[Q]], - {Cs,Line,Col+1,Str,Wcs,Uni}; -scan_string_col([$\n=C|Cs], Line, _xCol, Q, U, Wcs, Uni) -> - scan_string_col(Cs, Line+1, 1, Q, U, [C|Wcs], Uni); -scan_string_col([C|Cs], Line, Col, Q, U, Wcs, Uni) when C =/= $\\, - ?CHAR(C), - ?UNI255(C) -> - scan_string_col(Cs, Line, Col+1, Q, U, [C|Wcs], Uni); -scan_string_col(Cs, Line, Col, Q, U, Wcs, Uni) -> - scan_string1(Cs, Line, Col, Q, U, Wcs, Wcs, Uni). - -%% UNI_STR is to be replaced by STR when the Unicode-string-to-list -%% workaround is eventually removed. --define(UNI_STR(Col, S), S). + Str = ?STR(St, [Q|Wcs++[Q]]), + {Cs,Line,Col+1,Str,Wcs}; +scan_string_col([$\n=C|Cs], St, Line, _xCol, Q, Wcs) -> + scan_string_col(Cs, St, Line+1, 1, Q, [C|Wcs]); +scan_string_col([C|Cs], St, Line, Col, Q, Wcs) when C =/= $\\, ?UNICODE(C) -> + scan_string_col(Cs, St, Line, Col+1, Q, [C|Wcs]); +scan_string_col(Cs, _St, Line, Col, Q, Wcs) -> + scan_string1(Cs, Line, Col, Q, Wcs, Wcs). %% Note: in those cases when a 'char_error' tuple is returned below it %% is tempting to skip over characters up to the first Q character, %% but then the end location of the error tuple would not correspond %% to the start location of the returned Rest string. (Maybe the end %% location could be modified, but that too is ugly.) -scan_string1([Q|Cs], Line, Col, Q, _U, Str0, Wcs0, Uni) -> +scan_string1([Q|Cs], Line, Col, Q, Str0, Wcs0) -> Wcs = lists:reverse(Wcs0), - Str = ?UNI_STR(Col, [Q|lists:reverse(Str0, [Q])]), - {Cs,Line,incr_column(Col, 1),Str,Wcs,Uni}; -scan_string1([$\n=C|Cs], Line, Col, Q, U, Str, Wcs, Uni) -> + Str = [Q|lists:reverse(Str0, [Q])], + {Cs,Line,incr_column(Col, 1),Str,Wcs}; +scan_string1([$\n=C|Cs], Line, Col, Q, Str, Wcs) -> Ncol = new_column(Col, 1), - scan_string1(Cs, Line+1, Ncol, Q, U, ?UNI_STR(Col, [C|Str]), [C|Wcs], Uni); -scan_string1([$\\|Cs]=Cs0, Line, Col, Q, U, Str, Wcs, Uni) -> + scan_string1(Cs, Line+1, Ncol, Q, [C|Str], [C|Wcs]); +scan_string1([$\\|Cs]=Cs0, Line, Col, Q, Str, Wcs) -> case scan_escape(Cs, Col) of more -> - {more,Cs0,Line,Col,Str,Wcs,Uni}; + {more,Cs0,Line,Col,Str,Wcs}; {error,Ncs,Error,Ncol} -> {char_error,Ncs,Error,Line,Col,incr_column(Ncol, 1)}; {eof,Ncol} -> {error,Line,incr_column(Ncol, 1),lists:reverse(Wcs),eof}; {nl,Val,ValStr,Ncs,Ncol} -> - Nstr = ?UNI_STR(Ncol, lists:reverse(ValStr, [$\\|Str])), + Nstr = lists:reverse(ValStr, [$\\|Str]), Nwcs = [Val|Wcs], - scan_string1(Ncs, Line+1, Ncol, Q, U, Nstr, Nwcs, Uni); - {unicode,_Val,_ValStr,Ncs,Ncol} when not U -> %' Emacs - {char_error,Ncs,{illegal,character},Line,Col,incr_column(Ncol, 1)}; - {unicode,Val,ValStr,Ncs,Ncol} -> % UNI. Uni is set to Val. - Nstr = ?UNI_STR(Ncol, lists:reverse(ValStr, [$\\|Str])), - Nwcs = [Val|Wcs], % not used - scan_string1(Ncs, Line, incr_column(Ncol, 1), Q, U, Nstr, Nwcs, Val); + scan_string1(Ncs, Line+1, Ncol, Q, Nstr, Nwcs); {Val,ValStr,Ncs,Ncol} -> - Nstr = ?UNI_STR(Ncol, lists:reverse(ValStr, [$\\|Str])), + Nstr = lists:reverse(ValStr, [$\\|Str]), Nwcs = [Val|Wcs], - scan_string1(Ncs, Line, incr_column(Ncol, 1), Q, U, Nstr, Nwcs, Uni) + scan_string1(Ncs, Line, incr_column(Ncol, 1), Q, Nstr, Nwcs) end; -scan_string1([C|Cs], Line, no_col=Col, Q, U, Str, Wcs, Uni) when ?CHAR(C), - ?UNI255(C) -> - %% scan_string1(Cs, Line, Col, Q, U, Str, [C|Wcs], Uni); - scan_string1(Cs, Line, Col, Q, U, [C|Str], [C|Wcs], Uni); % UNI -scan_string1([C|Cs], Line, Col, Q, U, Str, Wcs, Uni) when ?CHAR(C), ?UNI255(C) -> - scan_string1(Cs, Line, Col+1, Q, U, [C|Str], [C|Wcs], Uni); -scan_string1([C|Cs], Line, Col, _Q, false, _Str, _Wcs, _Uni) when ?CHAR(C) -> %' UNI - {char_error,Cs,{illegal,character},Line,Col,incr_column(Col, 1)}; -scan_string1([C|Cs], Line, Col, Q, U, Str, Wcs, _Uni) when ?UNICODE(C) -> - scan_string1(Cs, Line, incr_column(Col, 1), Q, U, [C|Str], [C|Wcs], C); -scan_string1([C|Cs], Line, Col, _Q, _U, _Str, _Wcs, _Uni) when ?CHAR(C) -> % UNI +scan_string1([C|Cs], Line, no_col=Col, Q, Str, Wcs) when ?UNICODE(C) -> + scan_string1(Cs, Line, Col, Q, [C|Str], [C|Wcs]); +scan_string1([C|Cs], Line, Col, Q, Str, Wcs) when ?UNICODE(C) -> + scan_string1(Cs, Line, Col+1, Q, [C|Str], [C|Wcs]); +scan_string1([C|Cs], Line, Col, _Q, _Str, _Wcs) when ?CHAR(C) -> {char_error,Cs,{illegal,character},Line,Col,incr_column(Col, 1)}; -scan_string1([]=Cs, Line, Col, _Q, _U, Str, Wcs, Uni) -> - {more,Cs,Line,Col,Str,Wcs,Uni}; -scan_string1(eof, Line, Col, _Q, _U, _Str, Wcs, _Uni) -> +scan_string1([]=Cs, Line, Col, _Q, Str, Wcs) -> + {more,Cs,Line,Col,Str,Wcs}; +scan_string1(eof, Line, Col, _Q, _Str, Wcs) -> {error,Line,Col,lists:reverse(Wcs),eof}. -define(OCT(C), C >= $0, C =< $7). @@ -1077,16 +980,16 @@ scan_string1(eof, Line, Col, _Q, _U, _Str, Wcs, _Uni) -> %% \<1-3> octal digits scan_escape([O1,O2,O3|Cs], Col) when ?OCT(O1), ?OCT(O2), ?OCT(O3) -> Val = (O1*8 + O2)*8 + O3 - 73*$0, - {Val,?UNI_STR(Col, [O1,O2,O3]),Cs,incr_column(Col, 3)}; + {Val,[O1,O2,O3],Cs,incr_column(Col, 3)}; scan_escape([O1,O2], _Col) when ?OCT(O1), ?OCT(O2) -> more; scan_escape([O1,O2|Cs], Col) when ?OCT(O1), ?OCT(O2) -> Val = (O1*8 + O2) - 9*$0, - {Val,?UNI_STR(Col, [O1,O2]),Cs,incr_column(Col, 2)}; + {Val,[O1,O2],Cs,incr_column(Col, 2)}; scan_escape([O1], _Col) when ?OCT(O1) -> more; scan_escape([O1|Cs], Col) when ?OCT(O1) -> - {O1 - $0,?UNI_STR(Col, [O1]),Cs,incr_column(Col, 1)}; + {O1 - $0,[O1],Cs,incr_column(Col, 1)}; %% \x{<hex digits>} scan_escape([$x,${|Cs], Col) -> scan_hex(Cs, incr_column(Col, 2), []); @@ -1097,29 +1000,27 @@ scan_escape([$x|eof], Col) -> %% \x<2> hexadecimal digits scan_escape([$x,H1,H2|Cs], Col) when ?HEX(H1), ?HEX(H2) -> Val = erlang:list_to_integer([H1,H2], 16), - {Val,?UNI_STR(Col, [$x,H1,H2]),Cs,incr_column(Col, 3)}; + {Val,[$x,H1,H2],Cs,incr_column(Col, 3)}; scan_escape([$x,H1], _Col) when ?HEX(H1) -> more; scan_escape([$x|Cs], Col) -> {error,Cs,{illegal,character},incr_column(Col, 1)}; %% \^X -> CTL-X scan_escape([$^=C0,$\n=C|Cs], Col) -> - {nl,C,?UNI_STR(Col, [C0,C]),Cs,new_column(Col, 1)}; + {nl,C,[C0,C],Cs,new_column(Col, 1)}; scan_escape([$^=C0,C|Cs], Col) when ?CHAR(C) -> Val = C band 31, - {Val,?UNI_STR(Col, [C0,C]),Cs,incr_column(Col, 2)}; + {Val,[C0,C],Cs,incr_column(Col, 2)}; scan_escape([$^], _Col) -> more; scan_escape([$^|eof], Col) -> {eof,incr_column(Col, 1)}; scan_escape([$\n=C|Cs], Col) -> - {nl,C,?UNI_STR(Col, [C]),Cs,new_column(Col, 1)}; -scan_escape([C0|Cs], Col) when ?CHAR(C0), ?UNI255(C0) -> + {nl,C,[C],Cs,new_column(Col, 1)}; +scan_escape([C0|Cs], Col) when ?UNICODE(C0) -> C = escape_char(C0), - {C,?UNI_STR(Col, [C0]),Cs,incr_column(Col, 1)}; -scan_escape([C|Cs], Col) when ?UNICODE(C) -> - {unicode,C,?UNI_STR(Col, [C]),Cs,incr_column(Col, 1)}; -scan_escape([C|Cs], Col) when ?CHAR(C) -> % UNI + {C,[C0],Cs,incr_column(Col, 1)}; +scan_escape([C|Cs], Col) when ?CHAR(C) -> {error,Cs,{illegal,character},incr_column(Col, 1)}; scan_escape([], _Col) -> more; @@ -1136,10 +1037,8 @@ scan_hex(Cs, Col, Wcs) -> scan_esc_end([$}|Cs], Col, Wcs0, B, Str0) -> Wcs = lists:reverse(Wcs0), case catch erlang:list_to_integer(Wcs, B) of - Val when Val =< 16#FF -> - {Val,?UNI_STR(Col, Str0++Wcs++[$}]),Cs,incr_column(Col, 1)}; Val when ?UNICODE(Val) -> - {unicode,Val,?UNI_STR(Col, Str0++Wcs++[$}]),Cs,incr_column(Col,1)}; + {Val,Str0++Wcs++[$}],Cs,incr_column(Col, 1)}; _ -> {error,Cs,{illegal,character},incr_column(Col, 1)} end; @@ -1171,7 +1070,7 @@ scan_number([$#|Cs]=Cs0, St, Line, Col, Toks, Ncs0) -> Ncs = lists:reverse(Ncs0), case catch list_to_integer(Ncs) of B when B >= 2, B =< 1+$Z-$A+10 -> - Bcs = Ncs++[$#], + Bcs = ?STR(St, Ncs++[$#]), scan_based_int(Cs, St, Line, Col, Toks, {B,[],Bcs}); B -> Len = length(Ncs), @@ -1204,7 +1103,7 @@ scan_based_int(Cs, St, Line, Col, Toks, {B,Ncs0,Bcs}) -> Ncs = lists:reverse(Ncs0), case catch erlang:list_to_integer(Ncs, B) of N when is_integer(N) -> - tok3(Cs, St, Line, Col, Toks, integer, Bcs++Ncs, N); + tok3(Cs, St, Line, Col, Toks, integer, ?STR(St, Bcs++Ncs), N); _ -> Len = length(Bcs)+length(Ncs), Ncol = incr_column(Col, Len), @@ -1244,36 +1143,30 @@ float_end(Cs, St, Line, Col, Toks, Ncs0) -> scan_error({illegal,float}, Line, Col, Line, Ncol, Cs) end. -skip_comment(Cs, St, Line, Col, Toks, N) -> - skip_comment(Cs, St, Line, Col, Toks, N, St#erl_scan.unicode). - -skip_comment([C|Cs], St, Line, Col, Toks, N, U) when C =/= $\n, ?CHAR(C) -> - case ?UNI255(C) orelse U andalso ?UNICODE(C) of +skip_comment([C|Cs], St, Line, Col, Toks, N) when C =/= $\n, ?CHAR(C) -> + case ?UNICODE(C) of true -> - skip_comment(Cs, St, Line, Col, Toks, N+1, U); + skip_comment(Cs, St, Line, Col, Toks, N+1); false -> Ncol = incr_column(Col, N+1), scan_error({illegal,character}, Line, Col, Line, Ncol, Cs) end; -skip_comment([]=Cs, _St, Line, Col, Toks, N, _U) -> +skip_comment([]=Cs, _St, Line, Col, Toks, N) -> {more,{Cs,Col,Toks,Line,N,fun skip_comment/6}}; -skip_comment(Cs, St, Line, Col, Toks, N, _U) -> +skip_comment(Cs, St, Line, Col, Toks, N) -> scan1(Cs, St, Line, incr_column(Col, N), Toks). -scan_comment(Cs, St, Line, Col, Toks, Ncs) -> - scan_comment(Cs, St, Line, Col, Toks, Ncs, St#erl_scan.unicode). - -scan_comment([C|Cs], St, Line, Col, Toks, Ncs, U) when C =/= $\n, ?CHAR(C) -> - case ?UNI255(C) orelse U andalso ?UNICODE(C) of +scan_comment([C|Cs], St, Line, Col, Toks, Ncs) when C =/= $\n, ?CHAR(C) -> + case ?UNICODE(C) of true -> - scan_comment(Cs, St, Line, Col, Toks, [C|Ncs], U); + scan_comment(Cs, St, Line, Col, Toks, [C|Ncs]); false -> Ncol = incr_column(Col, length(Ncs)+1), scan_error({illegal,character}, Line, Col, Line, Ncol, Cs) end; -scan_comment([]=Cs, _St, Line, Col, Toks, Ncs, _U) -> +scan_comment([]=Cs, _St, Line, Col, Toks, Ncs) -> {more,{Cs,Col,Toks,Line,Ncs,fun scan_comment/6}}; -scan_comment(Cs, St, Line, Col, Toks, Ncs0, _U) -> +scan_comment(Cs, St, Line, Col, Toks, Ncs0) -> Ncs = lists:reverse(Ncs0), tok3(Cs, St, Line, Col, Toks, comment, Ncs, Ncs). diff --git a/lib/stdlib/src/eval_bits.erl b/lib/stdlib/src/eval_bits.erl index f40904df1c..e49cbc1fd1 100644 --- a/lib/stdlib/src/eval_bits.erl +++ b/lib/stdlib/src/eval_bits.erl @@ -2,7 +2,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1999-2011. All Rights Reserved. +%% Copyright Ericsson AB 1999-2013. All Rights Reserved. %% %% The contents of this file are subject to the Erlang Public License, %% Version 1.1, (the "License"); you may not use this file except in @@ -67,7 +67,8 @@ expr_grp([], Bs0, _Lf, Acc) -> {value,Acc,Bs0}. eval_field({bin_element, _, {string, _, S}, default, default}, Bs0, _Fun) -> - {list_to_binary(S),Bs0}; + Latin1 = [C band 16#FF || C <- S], + {list_to_binary(Latin1),Bs0}; eval_field({bin_element, Line, {string, _, S}, Size0, Options0}, Bs, _Fun) -> {_Size,[Type,_Unit,_Sign,Endian]} = make_bit_type(Line, Size0, Options0), @@ -162,8 +163,10 @@ bin_gen([], Bin, _Bs0, _BBs0, _Mfun, _Efun, false) -> bin_gen_field({bin_element,_,{string,_,S},default,default}, Bin, Bs, BBs, _Mfun, _Efun) -> - Bits = list_to_binary(S), - Size = byte_size(Bits), + Bits = try list_to_binary(S) + catch _:_ -> <<>> + end, + Size = length(S), case Bin of <<Bits:Size/binary,Rest/bitstring>> -> {match,Bs,BBs,Rest}; @@ -172,16 +175,42 @@ bin_gen_field({bin_element,_,{string,_,S},default,default}, _ -> done end; +bin_gen_field({bin_element,Line,{string,SLine,S},Size0,Options0}, + Bin0, Bs0, BBs0, Mfun, Efun) -> + {Size1, [Type,{unit,Unit},Sign,Endian]} = + make_bit_type(Line, Size0, Options0), + match_check_size(Mfun, Size1, BBs0), + {value, Size, _BBs} = Efun(Size1, BBs0), + F = fun(C, Bin, Bs, BBs) -> + bin_gen_field1(Bin, Type, Size, Unit, Sign, Endian, + {integer,SLine,C}, Bs, BBs, Mfun) + end, + bin_gen_field_string(S, Bin0, Bs0, BBs0, F); bin_gen_field({bin_element,Line,VE,Size0,Options0}, Bin, Bs0, BBs0, Mfun, Efun) -> {Size1, [Type,{unit,Unit},Sign,Endian]} = make_bit_type(Line, Size0, Options0), V = erl_eval:partial_eval(VE), + NewV = coerce_to_float(V, Type), match_check_size(Mfun, Size1, BBs0), {value, Size, _BBs} = Efun(Size1, BBs0), + bin_gen_field1(Bin, Type, Size, Unit, Sign, Endian, NewV, Bs0, BBs0, Mfun). + +bin_gen_field_string([], Rest, Bs, BBs, _F) -> + {match,Bs,BBs,Rest}; +bin_gen_field_string([C|Cs], Bin0, Bs0, BBs0, Fun) -> + case Fun(C, Bin0, Bs0, BBs0) of + {match,Bs,BBs,Rest} -> + bin_gen_field_string(Cs, Rest, Bs, BBs, Fun); + {nomatch,Rest} -> + {nomatch,Rest}; + done -> + done + end. + +bin_gen_field1(Bin, Type, Size, Unit, Sign, Endian, NewV, Bs0, BBs0, Mfun) -> case catch get_value(Bin, Type, Size, Unit, Sign, Endian) of {Val,<<_/bitstring>>=Rest} -> - NewV = coerce_to_float(V, Type), case catch Mfun(match, {NewV,Val,Bs0}) of {match,Bs} -> BBs = add_bin_binding(Mfun, NewV, Bs, BBs0), @@ -223,20 +252,41 @@ match_bits_1([F|Fs], Bits0, Bs0, BBs0, Mfun, Efun) -> match_field_1({bin_element,_,{string,_,S},default,default}, Bin, Bs, BBs, _Mfun, _Efun) -> - Bits = list_to_binary(S), + Bits = list_to_binary(S), % fails if there are characters > 255 Size = byte_size(Bits), <<Bits:Size/binary,Rest/binary-unit:1>> = Bin, {Bs,BBs,Rest}; +match_field_1({bin_element,Line,{string,SLine,S},Size0,Options0}, + Bin0, Bs0, BBs0, Mfun, Efun) -> + {Size1, [Type,{unit,Unit},Sign,Endian]} = + make_bit_type(Line, Size0, Options0), + Size2 = erl_eval:partial_eval(Size1), + match_check_size(Mfun, Size2, BBs0), + {value, Size, _BBs} = Efun(Size2, BBs0), + F = fun(C, Bin, Bs, BBs) -> + match_field(Bin, Type, Size, Unit, Sign, Endian, + {integer,SLine,C}, Bs, BBs, Mfun) + end, + match_field_string(S, Bin0, Bs0, BBs0, F); match_field_1({bin_element,Line,VE,Size0,Options0}, Bin, Bs0, BBs0, Mfun, Efun) -> {Size1, [Type,{unit,Unit},Sign,Endian]} = make_bit_type(Line, Size0, Options0), V = erl_eval:partial_eval(VE), + NewV = coerce_to_float(V, Type), Size2 = erl_eval:partial_eval(Size1), match_check_size(Mfun, Size2, BBs0), {value, Size, _BBs} = Efun(Size2, BBs0), + match_field(Bin, Type, Size, Unit, Sign, Endian, NewV, Bs0, BBs0, Mfun). + +match_field_string([], Rest, Bs, BBs, _Fun) -> + {Bs,BBs,Rest}; +match_field_string([C|Cs], Bin0, Bs0, BBs0, Fun) -> + {Bs,BBs,Bin} = Fun(C, Bin0, Bs0, BBs0), + match_field_string(Cs, Bin, Bs, BBs, Fun). + +match_field(Bin, Type, Size, Unit, Sign, Endian, NewV, Bs0, BBs0, Mfun) -> {Val,Rest} = get_value(Bin, Type, Size, Unit, Sign, Endian), - NewV = coerce_to_float(V, Type), {match,Bs} = Mfun(match, {NewV,Val,Bs0}), BBs = add_bin_binding(Mfun, NewV, Bs, BBs0), {Bs,BBs,Rest}. diff --git a/lib/stdlib/src/filelib.erl b/lib/stdlib/src/filelib.erl index 318f3b87b8..7df72a93e5 100644 --- a/lib/stdlib/src/filelib.erl +++ b/lib/stdlib/src/filelib.erl @@ -19,16 +19,14 @@ -module(filelib). %% File utilities. - -%% Avoid warning for local function error/1 clashing with autoimported BIF. --compile({no_auto_import,[error/1]}). --export([wildcard/1, wildcard/2, is_dir/1, is_file/1, is_regular/1, - compile_wildcard/1]). +-export([wildcard/1, wildcard/2, is_dir/1, is_file/1, is_regular/1]). -export([fold_files/5, last_modified/1, file_size/1, ensure_dir/1]). - -export([wildcard/3, is_dir/2, is_file/2, is_regular/2]). -export([fold_files/6, last_modified/2, file_size/2]). +%% For debugging/testing. +-export([compile_wildcard/1]). + -include_lib("kernel/include/file.hrl"). -define(HANDLE_ERROR(Expr), @@ -37,7 +35,7 @@ catch error:{badpattern,_}=UnUsUalVaRiAbLeNaMe -> %% Get the stack backtrace correct. - erlang:error(UnUsUalVaRiAbLeNaMe) + error(UnUsUalVaRiAbLeNaMe) end). -type filename() :: file:name(). @@ -48,19 +46,19 @@ -spec wildcard(Wildcard) -> [file:filename()] when Wildcard :: filename() | dirname(). wildcard(Pattern) when is_list(Pattern) -> - ?HANDLE_ERROR(do_wildcard(Pattern, file)). + ?HANDLE_ERROR(do_wildcard(Pattern, ".", file)). -spec wildcard(Wildcard, Cwd) -> [file:filename()] when Wildcard :: filename() | dirname(), Cwd :: dirname(). -wildcard(Pattern, Cwd) when is_list(Pattern), (is_list(Cwd) or is_binary(Cwd)) -> +wildcard(Pattern, Cwd) when is_list(Pattern), is_list(Cwd) -> ?HANDLE_ERROR(do_wildcard(Pattern, Cwd, file)); wildcard(Pattern, Mod) when is_list(Pattern), is_atom(Mod) -> - ?HANDLE_ERROR(do_wildcard(Pattern, Mod)). + ?HANDLE_ERROR(do_wildcard(Pattern, ".", Mod)). -spec wildcard(file:name(), file:name(), atom()) -> [file:filename()]. wildcard(Pattern, Cwd, Mod) - when is_list(Pattern), (is_list(Cwd) or is_binary(Cwd)), is_atom(Mod) -> + when is_list(Pattern), is_list(Cwd), is_atom(Mod) -> ?HANDLE_ERROR(do_wildcard(Pattern, Cwd, Mod)). -spec is_dir(Name) -> boolean() when @@ -124,47 +122,6 @@ file_size(File, Mod) when is_atom(Mod) -> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% -do_wildcard(Pattern, Mod) when is_list(Pattern) -> - do_wildcard_comp(do_compile_wildcard(Pattern), Mod). - -do_wildcard_comp({compiled_wildcard,{exists,File}}, Mod) -> - case eval_read_file_info(File, Mod) of - {ok,_} -> [File]; - _ -> [] - end; -do_wildcard_comp({compiled_wildcard,[cwd,Base|Rest]}, Mod) -> - do_wildcard_1([Base], Rest, Mod); -do_wildcard_comp({compiled_wildcard,[Base|Rest]}, Mod) -> - do_wildcard_1([Base], Rest, Mod). - -do_wildcard(Pattern, Cwd, Mod) when is_list(Pattern), (is_list(Cwd) or is_binary(Cwd)) -> - do_wildcard_comp(do_compile_wildcard(Pattern), Cwd, Mod). - -do_wildcard_comp({compiled_wildcard,{exists,File}}, Cwd, Mod) -> - case eval_read_file_info(filename:absname(File, Cwd), Mod) of - {ok,_} -> [File]; - _ -> [] - end; -do_wildcard_comp({compiled_wildcard,[cwd|Rest0]}, Cwd0, Mod) -> - case Rest0 of - [current|Rest] -> ok; - Rest -> ok - end, - {Cwd,PrefixLen} = case filename:join([Cwd0]) of - Bin when is_binary(Bin) -> {Bin,byte_size(Bin)+1}; - Other -> {Other,length(Other)+1} - end, %Slash away redundant slashes. - [ - if - is_binary(N) -> - <<_:PrefixLen/binary,Res/binary>> = N, - Res; - true -> - lists:nthtail(PrefixLen, N) - end || N <- do_wildcard_1([Cwd], Rest, Mod)]; -do_wildcard_comp({compiled_wildcard,[Base|Rest]}, _Cwd, Mod) -> - do_wildcard_1([Base], Rest, Mod). - do_is_dir(Dir, Mod) -> case eval_read_file_info(Dir, Mod) of {ok, #file_info{type=directory}} -> @@ -293,8 +250,24 @@ ensure_dir(F) -> %%% Pattern matching using a compiled wildcard. %%% -do_wildcard_1(Files, Pattern, Mod) -> - do_wildcard_2(Files, Pattern, [], Mod). +do_wildcard(Pattern, Cwd, Mod) -> + {Compiled,PrefixLen} = compile_wildcard(Pattern, Cwd), + Files0 = do_wildcard_1(Compiled, Mod), + Files = if + PrefixLen =:= 0 -> + Files0; + true -> + [lists:nthtail(PrefixLen, File) || File <- Files0] + end, + lists:sort(Files). + +do_wildcard_1({exists,File}, Mod) -> + case eval_read_file_info(File, Mod) of + {ok,_} -> [File]; + _ -> [] + end; +do_wildcard_1([Base|Rest], Mod) -> + do_wildcard_2([Base], Rest, [], Mod). do_wildcard_2([File|Rest], Pattern, Result, Mod) -> do_wildcard_2(Rest, Pattern, do_wildcard_3(File, Pattern, Result, Mod), Mod); @@ -302,12 +275,12 @@ do_wildcard_2([], _, Result, _Mod) -> Result. do_wildcard_3(Base, [[double_star]|Rest], Result, Mod) -> - lists:sort(do_double_star(current, [Base], Rest, Result, Mod, true)); -do_wildcard_3(Base, [Pattern|Rest], Result, Mod) -> - case do_list_dir(Base, Mod) of - {ok, Files0} -> - Files = lists:sort(Files0), - Matches = wildcard_4(Pattern, Files, Base, []), + do_double_star(".", [Base], Rest, Result, Mod, true); +do_wildcard_3(Base0, [Pattern|Rest], Result, Mod) -> + case do_list_dir(Base0, Mod) of + {ok, Files} -> + Base = prepare_base(Base0), + Matches = do_wildcard_4(Pattern, Base, Files), do_wildcard_2(Matches, Rest, Result, Mod); _ -> Result @@ -315,51 +288,50 @@ do_wildcard_3(Base, [Pattern|Rest], Result, Mod) -> do_wildcard_3(Base, [], Result, _Mod) -> [Base|Result]. -wildcard_4(Pattern, [File|Rest], Base, Result) when is_binary(File) -> - case wildcard_5(Pattern, binary_to_list(File)) of - true -> - wildcard_4(Pattern, Rest, Base, [join(Base, File)|Result]); +do_wildcard_4(Pattern, Base, Files) -> + case will_always_match(Pattern) of false -> - wildcard_4(Pattern, Rest, Base, Result) - end; -wildcard_4(Pattern, [File|Rest], Base, Result) -> - case wildcard_5(Pattern, File) of + [Base++F || F <- Files, match_part(Pattern, F)]; true -> - wildcard_4(Pattern, Rest, Base, [join(Base, File)|Result]); - false -> - wildcard_4(Pattern, Rest, Base, Result) - end; -wildcard_4(_Patt, [], _Base, Result) -> - Result. + [Base++F || F <- Files] + end. -wildcard_5([question|Rest1], [_|Rest2]) -> - wildcard_5(Rest1, Rest2); -wildcard_5([accept], _) -> +match_part([question|Rest1], [_|Rest2]) -> + match_part(Rest1, Rest2); +match_part([accept], _) -> true; -wildcard_5([double_star], _) -> +match_part([double_star], _) -> true; -wildcard_5([star|Rest], File) -> +match_part([star|Rest], File) -> do_star(Rest, File); -wildcard_5([{one_of, Ordset}|Rest], [C|File]) -> - case ordsets:is_element(C, Ordset) of - true -> wildcard_5(Rest, File); - false -> false - end; -wildcard_5([{alt, Alts}], File) -> +match_part([{one_of, Ordset}|Rest], [C|File]) -> + gb_sets:is_element(C, Ordset) andalso match_part(Rest, File); +match_part([{alt, Alts}], File) -> do_alt(Alts, File); -wildcard_5([C|Rest1], [C|Rest2]) when is_integer(C) -> - wildcard_5(Rest1, Rest2); -wildcard_5([X|_], [Y|_]) when is_integer(X), is_integer(Y) -> +match_part([C|Rest1], [C|Rest2]) when is_integer(C) -> + match_part(Rest1, Rest2); +match_part([X|_], [Y|_]) when is_integer(X), is_integer(Y) -> false; -wildcard_5([], []) -> +match_part([], []) -> true; -wildcard_5([], [_|_]) -> +match_part([], [_|_]) -> false; -wildcard_5([_|_], []) -> +match_part([_|_], []) -> false. +will_always_match([accept]) -> true; +will_always_match(_) -> false. + +prepare_base(Base0) -> + Base1 = filename:join(Base0, "x"), + "x"++Base2 = lists:reverse(Base1), + lists:reverse(Base2). + do_double_star(Base, [H|T], Rest, Result, Mod, Root) -> - Full = join(Base, H), + Full = case Root of + false -> filename:join(Base, H); + true -> H + end, Result1 = case do_list_dir(Full, Mod) of {ok, Files} -> do_double_star(Full, Files, Rest, Result, Mod, false); @@ -373,62 +345,64 @@ do_double_star(Base, [H|T], Rest, Result, Mod, Root) -> do_double_star(_Base, [], _Rest, Result, _Mod, _Root) -> Result. -do_star(Pattern, [X|Rest]) -> - case wildcard_5(Pattern, [X|Rest]) of - true -> true; - false -> do_star(Pattern, Rest) - end; +do_star(Pattern, [_|Rest]=File) -> + match_part(Pattern, File) orelse do_star(Pattern, Rest); do_star(Pattern, []) -> - wildcard_5(Pattern, []). + match_part(Pattern, []). do_alt([Alt|Rest], File) -> - case wildcard_5(Alt, File) of - true -> true; - false -> do_alt(Rest, File) - end; + match_part(Alt, File) orelse do_alt(Rest, File); do_alt([], _File) -> false. -do_list_dir(current, Mod) -> eval_list_dir(".", Mod); do_list_dir(Dir, Mod) -> eval_list_dir(Dir, Mod). -join(current, File) -> File; -join(Base, File) -> filename:join(Base, File). - %%% Compiling a wildcard. -compile_wildcard(Pattern) -> - ?HANDLE_ERROR(do_compile_wildcard(Pattern)). - -do_compile_wildcard(Pattern) -> - {compiled_wildcard,compile_wildcard_1(Pattern)}. +%% Only for debugging. +compile_wildcard(Pattern) when is_list(Pattern) -> + {compiled_wildcard,?HANDLE_ERROR(compile_wildcard(Pattern, "."))}. -compile_wildcard_1(Pattern) -> +compile_wildcard(Pattern, Cwd0) -> [Root|Rest] = filename:split(Pattern), case filename:pathtype(Root) of relative -> - case compile_wildcard_2([Root|Rest], current) of - {exists,_}=Wc -> Wc; - [_|_]=Wc -> [cwd|Wc] - end; + Cwd = filename:join([Cwd0]), + compile_wildcard_2([Root|Rest], {cwd,Cwd}); _ -> - compile_wildcard_2(Rest, [Root]) + compile_wildcard_2(Rest, {root,0,Root}) end. compile_wildcard_2([Part|Rest], Root) -> case compile_part(Part) of Part -> - compile_wildcard_2(Rest, join(Root, Part)); + compile_wildcard_2(Rest, compile_join(Root, Part)); Pattern -> compile_wildcard_3(Rest, [Pattern,Root]) end; -compile_wildcard_2([], Root) -> {exists,Root}. +compile_wildcard_2([], {root,PrefixLen,Root}) -> + {{exists,Root},PrefixLen}. compile_wildcard_3([Part|Rest], Result) -> compile_wildcard_3(Rest, [compile_part(Part)|Result]); compile_wildcard_3([], Result) -> - lists:reverse(Result). + case lists:reverse(Result) of + [{root,PrefixLen,Root}|Compiled] -> + {[Root|Compiled],PrefixLen}; + [{cwd,Root}|Compiled] -> + {[Root|Compiled],length(filename:join(Root, "x"))-1} + end. + +compile_join({cwd,"."}, File) -> + {root,0,File}; +compile_join({cwd,Cwd}, File0) -> + File = filename:join([File0]), + Root = filename:join(Cwd, File), + PrefixLen = length(Root) - length(File), + {root,PrefixLen,Root}; +compile_join({root,PrefixLen,Root}, File) -> + {root,PrefixLen,filename:join(Root, File)}. compile_part(Part) -> compile_part(Part, false, []). @@ -437,7 +411,7 @@ compile_part_to_sep(Part) -> compile_part(Part, true, []). compile_part([], true, _) -> - error(missing_delimiter); + badpattern(missing_delimiter); compile_part([$,|Rest], true, Result) -> {ok, $,, lists:reverse(Result), Rest}; compile_part([$}|Rest], true, Result) -> @@ -473,8 +447,6 @@ compile_part([], _Upto, Result) -> compile_charset([$]|Rest], Ordset) -> compile_charset1(Rest, ordsets:add_element($], Ordset)); -compile_charset([$-|Rest], Ordset) -> - compile_charset1(Rest, ordsets:add_element($-, Ordset)); compile_charset([], _Ordset) -> error; compile_charset(List, Ordset) -> @@ -483,7 +455,7 @@ compile_charset(List, Ordset) -> compile_charset1([Lower, $-, Upper|Rest], Ordset) when Lower =< Upper -> compile_charset1(Rest, compile_range(Lower, Upper, Ordset)); compile_charset1([$]|Rest], Ordset) -> - {ok, {one_of, Ordset}, Rest}; + {ok, {one_of, gb_sets:from_ordset(Ordset)}, Rest}; compile_charset1([X|Rest], Ordset) -> compile_charset1(Rest, ordsets:add_element(X, Ordset)); compile_charset1([], _Ordset) -> @@ -509,8 +481,8 @@ compile_alt(Pattern, Result) -> error end. -error(Reason) -> - erlang:error({badpattern,Reason}). +badpattern(Reason) -> + error({badpattern,Reason}). eval_read_file_info(File, file) -> file:read_file_info(File); diff --git a/lib/stdlib/src/filename.erl b/lib/stdlib/src/filename.erl index 0c50eb34e6..66e54ef221 100644 --- a/lib/stdlib/src/filename.erl +++ b/lib/stdlib/src/filename.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1997-2012. All Rights Reserved. +%% Copyright Ericsson AB 1997-2013. All Rights Reserved. %% %% The contents of this file are subject to the Erlang Public License, %% Version 1.1, (the "License"); you may not use this file except in @@ -61,15 +61,15 @@ %% (for WIN32): absname("/") -> "D:/" --spec absname(Filename) -> file:filename() when - Filename :: file:name(). +-spec absname(Filename) -> file:filename_all() when + Filename :: file:name_all(). absname(Name) -> {ok, Cwd} = file:get_cwd(), absname(Name, Cwd). --spec absname(Filename, Dir) -> file:filename() when - Filename :: file:name(), - Dir :: file:name(). +-spec absname(Filename, Dir) -> file:filename_all() when + Filename :: file:name_all(), + Dir :: file:name_all(). absname(Name, AbsBase) when is_binary(Name), is_list(AbsBase) -> absname(Name,filename_string_to_binary(AbsBase)); absname(Name, AbsBase) when is_list(Name), is_binary(AbsBase) -> @@ -122,9 +122,9 @@ absname_vr([[X, $:]|Name], _, _AbsBase) -> %% This is just a join/2, but assumes that %% AbsBase must be absolute and Name must be relative. --spec absname_join(Dir, Filename) -> file:filename() when - Dir :: file:name(), - Filename :: file:name(). +-spec absname_join(Dir, Filename) -> file:filename_all() when + Dir :: file:name_all(), + Filename :: file:name_all(). absname_join(AbsBase, Name) -> join(AbsBase, flatten(Name)). @@ -136,8 +136,8 @@ absname_join(AbsBase, Name) -> %% basename("/usr/foo/") -> "foo" (trailing slashes ignored) %% basename("/") -> [] --spec basename(Filename) -> file:filename() when - Filename :: file:name(). +-spec basename(Filename) -> file:filename_all() when + Filename :: file:name_all(). basename(Name) when is_binary(Name) -> case os:type() of {win32,_} -> @@ -201,9 +201,9 @@ skip_prefix(Name, _) -> %% rootname(basename("xxx.jam")) -> "xxx" %% rootname(basename("xxx.erl")) -> "xxx" --spec basename(Filename, Ext) -> file:filename() when - Filename :: file:name(), - Ext :: file:name(). +-spec basename(Filename, Ext) -> file:filename_all() when + Filename :: file:name_all(), + Ext :: file:name_all(). basename(Name, Ext) when is_binary(Name), is_list(Ext) -> basename(Name,filename_string_to_binary(Ext)); basename(Name, Ext) when is_list(Name), is_binary(Ext) -> @@ -251,8 +251,8 @@ basename([], _Ext, Tail, _DrvSep2) -> %% Example: dirname("/usr/src/kalle.erl") -> "/usr/src", %% dirname("kalle.erl") -> "." --spec dirname(Filename) -> file:filename() when - Filename :: file:name(). +-spec dirname(Filename) -> file:filename_all() when + Filename :: file:name_all(). dirname(Name) when is_binary(Name) -> {Dsep,Drivesep} = separators(), SList = case Dsep of @@ -344,8 +344,8 @@ dirjoin1([H|T],Acc,Sep) -> %% %% On Windows: fn:dirname("\\usr\\src/kalle.erl") -> "/usr/src" --spec extension(Filename) -> file:filename() when - Filename :: file:name(). +-spec extension(Filename) -> file:filename_all() when + Filename :: file:name_all(). extension(Name) when is_binary(Name) -> {Dsep,_} = separators(), SList = case Dsep of @@ -387,8 +387,8 @@ extension([], Result, _OsType) -> %% Joins a list of filenames with directory separators. --spec join(Components) -> file:filename() when - Components :: [file:name()]. +-spec join(Components) -> file:filename_all() when + Components :: [file:name_all()]. join([Name1, Name2|Rest]) -> join([join(Name1, Name2)|Rest]); join([Name]) when is_list(Name) -> @@ -400,9 +400,9 @@ join([Name]) when is_atom(Name) -> %% Joins two filenames with directory separators. --spec join(Name1, Name2) -> file:filename() when - Name1 :: file:name(), - Name2 :: file:name(). +-spec join(Name1, Name2) -> file:filename_all() when + Name1 :: file:name_all(), + Name2 :: file:name_all(). join(Name1, Name2) when is_list(Name1), is_list(Name2) -> OsType = major_os_type(), case pathtype(Name2) of @@ -488,7 +488,7 @@ maybe_remove_dirsep(Name, _) -> %% a given base directory, which is is assumed to be normalised %% by a previous call to join/{1,2}. --spec append(file:filename(), file:name()) -> file:filename(). +-spec append(file:filename_all(), file:name_all()) -> file:filename_all(). append(Dir, Name) when is_binary(Dir), is_binary(Name) -> <<Dir/binary,$/:8,Name/binary>>; append(Dir, Name) when is_binary(Dir) -> @@ -511,7 +511,7 @@ append(Dir, Name) -> %% Example: a:bar.erl, /temp/foo.erl -spec pathtype(Path) -> 'absolute' | 'relative' | 'volumerelative' when - Path :: file:name(). + Path :: file:name_all(). pathtype(Atom) when is_atom(Atom) -> pathtype(atom_to_list(Atom)); pathtype(Name) when is_list(Name) or is_binary(Name) -> @@ -564,8 +564,8 @@ win32_pathtype(_) -> relative. %% Examples: rootname("/jam.src/kalle") -> "/jam.src/kalle" %% rootname("/jam.src/foo.erl") -> "/jam.src/foo" --spec rootname(Filename) -> file:filename() when - Filename :: file:name(). +-spec rootname(Filename) -> file:filename_all() when + Filename :: file:name_all(). rootname(Name) when is_binary(Name) -> list_to_binary(rootname(binary_to_list(Name))); % No need to handle unicode, . is < 128 rootname(Name0) -> @@ -594,9 +594,9 @@ rootname([], Root, _Ext, _OsType) -> %% Examples: rootname("/jam.src/kalle.jam", ".erl") -> "/jam.src/kalle.jam" %% rootname("/jam.src/foo.erl", ".erl") -> "/jam.src/foo" --spec rootname(Filename, Ext) -> file:filename() when - Filename :: file:name(), - Ext :: file:name(). +-spec rootname(Filename, Ext) -> file:filename_all() when + Filename :: file:name_all(), + Ext :: file:name_all(). rootname(Name, Ext) when is_binary(Name), is_binary(Ext) -> list_to_binary(rootname(binary_to_list(Name),binary_to_list(Ext))); rootname(Name, Ext) when is_binary(Name) -> @@ -623,8 +623,8 @@ rootname2([Char|Rest], Ext, Result) when is_integer(Char) -> %% split("a:\\msdev\\include") -> ["a:/", "msdev", "include"] -spec split(Filename) -> Components when - Filename :: file:name(), - Components :: [file:name()]. + Filename :: file:name_all(), + Components :: [file:name_all()]. split(Name) when is_binary(Name) -> case os:type() of {win32, _} -> win32_splitb(Name); @@ -717,8 +717,8 @@ split([], Comp, Components, OsType) -> %% will be converted to backslashes. On all platforms, the %% name will be normalized as done by join/1. --spec nativename(Path) -> file:filename() when - Path :: file:name(). +-spec nativename(Path) -> file:filename_all() when + Path :: file:name_all(). nativename(Name0) -> Name = join([Name0]), %Normalize. case os:type() of @@ -921,8 +921,8 @@ major_os_type() -> %% flatten(List) %% Flatten a list, also accepting atoms. --spec flatten(Filename) -> file:filename() when - Filename :: file:name(). +-spec flatten(Filename) -> file:filename_all() when + Filename :: file:name_all(). flatten(Bin) when is_binary(Bin) -> Bin; flatten(List) -> diff --git a/lib/stdlib/src/io.erl b/lib/stdlib/src/io.erl index 3dddb0d6e7..c92e9e3ade 100644 --- a/lib/stdlib/src/io.erl +++ b/lib/stdlib/src/io.erl @@ -32,6 +32,8 @@ parse_erl_exprs/4,parse_erl_form/1,parse_erl_form/2, parse_erl_form/3,parse_erl_form/4]). -export([request/1,request/2,requests/1,requests/2]). +%% Implemented in native code +-export([printable_range/0]). -export_type([device/0, format/0, server_no_data/0]). @@ -66,6 +68,11 @@ o_request(Io, Request, Func) -> Other end. +%% Request what the user considers printable characters +-spec printable_range() -> 'unicode' | 'latin1'. +printable_range() -> + erlang:nif_error(undefined). + %% Put chars takes mixed *unicode* list from R13 onwards. -spec put_chars(CharData) -> 'ok' when CharData :: unicode:chardata(). diff --git a/lib/stdlib/src/io_lib.erl b/lib/stdlib/src/io_lib.erl index b7ec848e1e..a9b6d4131e 100644 --- a/lib/stdlib/src/io_lib.erl +++ b/lib/stdlib/src/io_lib.erl @@ -72,7 +72,7 @@ -export([quote_atom/2, char_list/1, latin1_char_list/1, deep_char_list/1, deep_latin1_char_list/1, - printable_list/1, printable_latin1_list/1]). + printable_list/1, printable_latin1_list/1, printable_unicode_list/1]). %% Utilities for collecting characters. -export([collect_chars/3, collect_chars/4, @@ -533,27 +533,45 @@ printable_latin1_list(_) -> false. %Everything else is false %% Return true if CharList is a list of printable characters, else %% false. The notion of printable in Unicode terms is somewhat floating. %% Everything that is not a control character and not invalid unicode -%% will be considered printable. +%% will be considered printable. +%% What the user has noted as printable characters is what actually +%% specifies when this function will return true. If the VM is started +%% with +pc latin1, only the latin1 range will be deemed as printable +%% if on the other hand +pc unicode is given, all characters in the Unicode +%% character set are deemed printable. latin1 is default. -spec printable_list(Term) -> boolean() when Term :: term(). -printable_list([C|Cs]) when is_integer(C), C >= $\040, C =< $\176 -> - printable_list(Cs); -printable_list([C|Cs]) +printable_list(L) -> + %% There will be more alternatives returns from io:printable range + %% in the future. To not have a catch-all clause is deliberate. + case io:printable_range() of + latin1 -> + printable_latin1_list(L); + unicode -> + printable_unicode_list(L) + end. + +-spec printable_unicode_list(Term) -> boolean() when + Term :: term(). + +printable_unicode_list([C|Cs]) when is_integer(C), C >= $\040, C =< $\176 -> + printable_unicode_list(Cs); +printable_unicode_list([C|Cs]) when is_integer(C), C >= 16#A0, C < 16#D800; is_integer(C), C > 16#DFFF, C < 16#FFFE; is_integer(C), C > 16#FFFF, C =< 16#10FFFF -> - printable_list(Cs); -printable_list([$\n|Cs]) -> printable_list(Cs); -printable_list([$\r|Cs]) -> printable_list(Cs); -printable_list([$\t|Cs]) -> printable_list(Cs); -printable_list([$\v|Cs]) -> printable_list(Cs); -printable_list([$\b|Cs]) -> printable_list(Cs); -printable_list([$\f|Cs]) -> printable_list(Cs); -printable_list([$\e|Cs]) -> printable_list(Cs); -printable_list([]) -> true; -printable_list(_) -> false. %Everything else is false + printable_unicode_list(Cs); +printable_unicode_list([$\n|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\r|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\t|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\v|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\b|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\f|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([$\e|Cs]) -> printable_unicode_list(Cs); +printable_unicode_list([]) -> true; +printable_unicode_list(_) -> false. %Everything else is false %% List = nl() %% Return a list of characters to generate a newline. diff --git a/lib/stdlib/src/io_lib_format.erl b/lib/stdlib/src/io_lib_format.erl index 6a06d9448b..56e15a17ec 100644 --- a/lib/stdlib/src/io_lib_format.erl +++ b/lib/stdlib/src/io_lib_format.erl @@ -58,14 +58,22 @@ collect_cseq(Fmt0, Args0) -> {P,Fmt2,Args2} = precision(Fmt1, Args1), {Pad,Fmt3,Args3} = pad_char(Fmt2, Args2), {Encoding,Fmt4,Args4} = encoding(Fmt3, Args3), - {C,As,Fmt5,Args5} = collect_cc(Fmt4, Args4), - {{C,As,F,Ad,P,Pad,Encoding},Fmt5,Args5}. + {Strings,Fmt5,Args5} = strings(Fmt4, Args4), + {C,As,Fmt6,Args6} = collect_cc(Fmt5, Args5), + {{C,As,F,Ad,P,Pad,Encoding,Strings},Fmt6,Args6}. encoding([$t|Fmt],Args) -> + true = hd(Fmt) =/= $l, {unicode,Fmt,Args}; encoding(Fmt,Args) -> {latin1,Fmt,Args}. +strings([$l|Fmt],Args) -> + true = hd(Fmt) =/= $t, + {false,Fmt,Args}; +strings(Fmt,Args) -> + {true,Fmt,Args}. + field_width([$-|Fmt0], Args0) -> {F,Fmt,Args} = field_value(Fmt0, Args0), field_width(-F, Fmt, Args); @@ -128,8 +136,8 @@ collect_cc([$i|Fmt], [A|Args]) -> {$i,[A],Fmt,Args}. pcount(Cs) -> pcount(Cs, 0). -pcount([{$p,_As,_F,_Ad,_P,_Pad,_Enc}|Cs], Acc) -> pcount(Cs, Acc+1); -pcount([{$P,_As,_F,_Ad,_P,_Pad,_Enc}|Cs], Acc) -> pcount(Cs, Acc+1); +pcount([{$p,_As,_F,_Ad,_P,_Pad,_Enc,_Str}|Cs], Acc) -> pcount(Cs, Acc+1); +pcount([{$P,_As,_F,_Ad,_P,_Pad,_Enc,_Str}|Cs], Acc) -> pcount(Cs, Acc+1); pcount([_|Cs], Acc) -> pcount(Cs, Acc); pcount([], Acc) -> Acc. @@ -138,8 +146,8 @@ pcount([], Acc) -> Acc. %% remaining and only calculate indentation when necessary. Must also %% be smart when calculating indentation for characters in format. -build([{C,As,F,Ad,P,Pad,Enc}|Cs], Pc0, I) -> - S = control(C, As, F, Ad, P, Pad, Enc, I), +build([{C,As,F,Ad,P,Pad,Enc,Str}|Cs], Pc0, I) -> + S = control(C, As, F, Ad, P, Pad, Enc, Str, I), Pc1 = decr_pc(C, Pc0), if Pc1 > 0 -> [S|build(Cs, Pc1, indentation(S, I))]; @@ -171,60 +179,59 @@ indentation([], I) -> I. %% This is the main dispatch function for the various formatting commands. %% Field widths and precisions have already been calculated. -control($w, [A], F, Adj, P, Pad, _Enc,_I) -> +control($w, [A], F, Adj, P, Pad, _Enc, _Str, _I) -> term(io_lib:write(A, -1), F, Adj, P, Pad); -control($p, [A], F, Adj, P, Pad, Enc, I) -> - print(A, -1, F, Adj, P, Pad, Enc, I); -control($W, [A,Depth], F, Adj, P, Pad, _Enc, _I) when is_integer(Depth) -> +control($p, [A], F, Adj, P, Pad, Enc, Str, I) -> + print(A, -1, F, Adj, P, Pad, Enc, Str, I); +control($W, [A,Depth], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(Depth) -> term(io_lib:write(A, Depth), F, Adj, P, Pad); -control($P, [A,Depth], F, Adj, P, Pad, Enc, I) when is_integer(Depth) -> - print(A, Depth, F, Adj, P, Pad, Enc, I); -control($s, [A], F, Adj, P, Pad, _Enc, _I) when is_atom(A) -> +control($P, [A,Depth], F, Adj, P, Pad, Enc, Str, I) when is_integer(Depth) -> + print(A, Depth, F, Adj, P, Pad, Enc, Str, I); +control($s, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_atom(A) -> string(atom_to_list(A), F, Adj, P, Pad); -control($s, [L0], F, Adj, P, Pad, latin1, _I) -> +control($s, [L0], F, Adj, P, Pad, latin1, _Str, _I) -> L = iolist_to_chars(L0), string(L, F, Adj, P, Pad); -control($s, [L0], F, Adj, P, Pad, unicode, _I) -> - L = unicode:characters_to_list(L0), - true = is_list(L), +control($s, [L0], F, Adj, P, Pad, unicode, _Str, _I) -> + L = cdata_to_chars(L0), uniconv(string(L, F, Adj, P, Pad)); -control($e, [A], F, Adj, P, Pad, _Enc, _I) when is_float(A) -> +control($e, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_float(A) -> fwrite_e(A, F, Adj, P, Pad); -control($f, [A], F, Adj, P, Pad, _Enc, _I) when is_float(A) -> +control($f, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_float(A) -> fwrite_f(A, F, Adj, P, Pad); -control($g, [A], F, Adj, P, Pad, _Enc, _I) when is_float(A) -> +control($g, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_float(A) -> fwrite_g(A, F, Adj, P, Pad); -control($b, [A], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($b, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> unprefixed_integer(A, F, Adj, base(P), Pad, true); -control($B, [A], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($B, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> unprefixed_integer(A, F, Adj, base(P), Pad, false); -control($x, [A,Prefix], F, Adj, P, Pad, _Enc, _I) when is_integer(A), +control($x, [A,Prefix], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A), is_atom(Prefix) -> prefixed_integer(A, F, Adj, base(P), Pad, atom_to_list(Prefix), true); -control($x, [A,Prefix], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($x, [A,Prefix], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> true = io_lib:deep_char_list(Prefix), %Check if Prefix a character list prefixed_integer(A, F, Adj, base(P), Pad, Prefix, true); -control($X, [A,Prefix], F, Adj, P, Pad, _Enc, _I) when is_integer(A), +control($X, [A,Prefix], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A), is_atom(Prefix) -> prefixed_integer(A, F, Adj, base(P), Pad, atom_to_list(Prefix), false); -control($X, [A,Prefix], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($X, [A,Prefix], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> true = io_lib:deep_char_list(Prefix), %Check if Prefix a character list prefixed_integer(A, F, Adj, base(P), Pad, Prefix, false); -control($+, [A], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($+, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> Base = base(P), Prefix = [integer_to_list(Base), $#], prefixed_integer(A, F, Adj, Base, Pad, Prefix, true); -control($#, [A], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($#, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> Base = base(P), Prefix = [integer_to_list(Base), $#], prefixed_integer(A, F, Adj, Base, Pad, Prefix, false); -control($c, [A], F, Adj, P, Pad, unicode, _I) when is_integer(A) -> +control($c, [A], F, Adj, P, Pad, unicode, _Str, _I) when is_integer(A) -> char(A, F, Adj, P, Pad); -control($c, [A], F, Adj, P, Pad, _Enc, _I) when is_integer(A) -> +control($c, [A], F, Adj, P, Pad, _Enc, _Str, _I) when is_integer(A) -> char(A band 255, F, Adj, P, Pad); -control($~, [], F, Adj, P, Pad, _Enc, _I) -> char($~, F, Adj, P, Pad); -control($n, [], F, Adj, P, Pad, _Enc, _I) -> newline(F, Adj, P, Pad); -control($i, [_A], _F, _Adj, _P, _Pad, _Enc, _I) -> []. +control($~, [], F, Adj, P, Pad, _Enc, _Str, _I) -> char($~, F, Adj, P, Pad); +control($n, [], F, Adj, P, Pad, _Enc, _Str, _I) -> newline(F, Adj, P, Pad); +control($i, [_A], _F, _Adj, _P, _Pad, _Enc, _Str, _I) -> []. -ifdef(UNICODE_AS_BINARIES). uniconv(C) -> @@ -260,12 +267,16 @@ term(T, F, Adj, P0, Pad) -> %% Indentation) %% Print a term. -print(T, D, none, Adj, P, Pad, E, I) -> print(T, D, 80, Adj, P, Pad, E, I); -print(T, D, F, Adj, none, Pad, E, I) -> print(T, D, F, Adj, I+1, Pad, E, I); -print(T, D, F, right, P, _Pad, latin1, _I) -> - io_lib_pretty:print(T, P, F, D); -print(T, D, F, right, P, _Pad, Enc, _I) -> - Options = [{column, P}, {line_length, F}, {depth, D}, {encoding, Enc}], +print(T, D, none, Adj, P, Pad, E, Str, I) -> + print(T, D, 80, Adj, P, Pad, E, Str, I); +print(T, D, F, Adj, none, Pad, E, Str, I) -> + print(T, D, F, Adj, I+1, Pad, E, Str, I); +print(T, D, F, right, P, _Pad, Enc, Str, _I) -> + Options = [{column, P}, + {line_length, F}, + {depth, D}, + {encoding, Enc}, + {strings, Str}], io_lib_pretty:print(T, Options). %% fwrite_e(Float, Field, Adjust, Precision, PadChar) @@ -558,6 +569,25 @@ 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() + +%% cdata_to_chars(cdata()) -> io_lib:deep_char_list() + +cdata_to_chars([C|Cs]) when is_integer(C), C >= $\000 -> + [C | cdata_to_chars(Cs)]; +cdata_to_chars([I|Cs]) -> + [cdata_to_chars(I) | cdata_to_chars(Cs)]; +cdata_to_chars([]) -> + []; +cdata_to_chars(B) when is_binary(B) -> + case catch unicode:characters_to_list(B) of + L when is_list(L) -> L; + _ -> binary_to_list(B) + end. + %% string(String, Field, Adjust, Precision, PadChar) string(S, none, _Adj, none, _Pad) -> S; diff --git a/lib/stdlib/src/io_lib_pretty.erl b/lib/stdlib/src/io_lib_pretty.erl index a8f610558a..7637ad7a3d 100644 --- a/lib/stdlib/src/io_lib_pretty.erl +++ b/lib/stdlib/src/io_lib_pretty.erl @@ -56,6 +56,7 @@ print(Term) -> | {depth, depth()} | {max_chars, max_chars()} | {record_print_fun, rec_print_fun()} + | {strings, boolean()} | {encoding, latin1 | utf8 | unicode}. -type options() :: [option()]. @@ -69,7 +70,8 @@ print(Term, Options) when is_list(Options) -> M = proplists:get_value(max_chars, Options, -1), RecDefFun = proplists:get_value(record_print_fun, Options, no_fun), Encoding = proplists:get_value(encoding, Options, epp:default_encoding()), - print(Term, Col, Ll, D, M, RecDefFun, Encoding); + Strings = proplists:get_value(strings, Options, true), + print(Term, Col, Ll, D, M, RecDefFun, Encoding, Strings); print(Term, RecDefFun) -> print(Term, -1, RecDefFun). @@ -81,7 +83,7 @@ print(Term, Depth, RecDefFun) -> -spec print(term(), column(), line_length(), depth()) -> chars(). print(Term, Col, Ll, D) -> - print(Term, Col, Ll, D, _M=-1, no_fun, latin1). + print(Term, Col, Ll, D, _M=-1, no_fun, latin1, true). -spec print(term(), column(), line_length(), depth(), rec_print_fun()) -> chars(). @@ -92,15 +94,15 @@ print(Term, Col, Ll, D, RecDefFun) -> rec_print_fun()) -> chars(). print(Term, Col, Ll, D, M, RecDefFun) -> - print(Term, Col, Ll, D, M, RecDefFun, latin1). - -print(_, _, _, 0, _M, _RF, _Enc) -> "..."; -print(Term, Col, Ll, D, M, RecDefFun, Enc) when Col =< 0 -> - print(Term, 1, Ll, D, M, RecDefFun, Enc); -print(Term, Col, Ll, D, M0, RecDefFun, Enc) when is_tuple(Term); - is_list(Term); - is_bitstring(Term) -> - If = {_S, Len} = print_length(Term, D, RecDefFun, Enc), + print(Term, Col, Ll, D, M, RecDefFun, latin1, true). + +print(_, _, _, 0, _M, _RF, _Enc, _Str) -> "..."; +print(Term, Col, Ll, D, M, RecDefFun, Enc, Str) when Col =< 0 -> + print(Term, 1, Ll, D, M, RecDefFun, Enc, Str); +print(Term, Col, Ll, D, M0, RecDefFun, Enc, Str) when is_tuple(Term); + is_list(Term); + is_bitstring(Term) -> + If = {_S, Len} = print_length(Term, D, RecDefFun, Enc, Str), M = max_cs(M0, Len), if Len < Ll - Col, Len =< M -> @@ -111,7 +113,7 @@ print(Term, Col, Ll, D, M0, RecDefFun, Enc) when is_tuple(Term); 1), pp(If, Col, Ll, M, TInd, indent(Col), 0, 0) end; -print(Term, _Col, _Ll, _D, _M, _RF, _Enc) -> +print(Term, _Col, _Ll, _D, _M, _RF, _Enc, _Str) -> io_lib:write(Term). %%% @@ -325,12 +327,12 @@ write_tail(E, S) -> %% counted but need to be added later. %% D =/= 0 -print_length([], _D, _RF, _Enc) -> +print_length([], _D, _RF, _Enc, _Str) -> {"[]", 2}; -print_length({}, _D, _RF, _Enc) -> +print_length({}, _D, _RF, _Enc, _Str) -> {"{}", 2}; -print_length(List, D, RF, Enc) when is_list(List) -> - case printable_list(List, D, Enc) of +print_length(List, D, RF, Enc, Str) when is_list(List) -> + case Str andalso printable_list(List, D, Enc) of true -> S = write_string(List, Enc), {S, length(S)}; @@ -339,30 +341,30 @@ print_length(List, D, RF, Enc) when is_list(List) -> % S = write_string(Prefix, Enc), % {[S | "..."], 3 + length(S)}; false -> - print_length_list(List, D, RF, Enc) + print_length_list(List, D, RF, Enc, Str) end; -print_length(Fun, _D, _RF, _Enc) when is_function(Fun) -> +print_length(Fun, _D, _RF, _Enc, _Str) when is_function(Fun) -> S = io_lib:write(Fun), {S, iolist_size(S)}; -print_length(R, D, RF, Enc) when is_atom(element(1, R)), - is_function(RF) -> +print_length(R, D, RF, Enc, Str) when is_atom(element(1, R)), + is_function(RF) -> case RF(element(1, R), tuple_size(R) - 1) of no -> - print_length_tuple(R, D, RF, Enc); + print_length_tuple(R, D, RF, Enc, Str); RDefs -> - print_length_record(R, D, RF, RDefs, Enc) + print_length_record(R, D, RF, RDefs, Enc, Str) end; -print_length(Tuple, D, RF, Enc) when is_tuple(Tuple) -> - print_length_tuple(Tuple, D, RF, Enc); -print_length(<<>>, _D, _RF, _Enc) -> +print_length(Tuple, D, RF, Enc, Str) when is_tuple(Tuple) -> + print_length_tuple(Tuple, D, RF, Enc, Str); +print_length(<<>>, _D, _RF, _Enc, _Str) -> {"<<>>", 4}; -print_length(<<_/bitstring>>, 1, _RF, _Enc) -> +print_length(<<_/bitstring>>, 1, _RF, _Enc, _Str) -> {"<<...>>", 7}; -print_length(<<_/bitstring>>=Bin, D, _RF, Enc) -> +print_length(<<_/bitstring>>=Bin, D, _RF, Enc, Str) -> case bit_size(Bin) rem 8 of 0 -> D1 = D - 1, - case printable_bin(Bin, D1, Enc) of + case Str andalso printable_bin(Bin, D1, Enc) of {true, List} when is_list(List) -> S = io_lib:write_string(List, $"), %" {[$<,$<,S,$>,$>], 4 + length(S)}; @@ -383,51 +385,53 @@ print_length(<<_/bitstring>>=Bin, D, _RF, Enc) -> S = io_lib:write(Bin, D), {{bin,S}, iolist_size(S)} end; -print_length(Term, _D, _RF, _Enc) -> +print_length(Term, _D, _RF, _Enc, _Str) -> S = io_lib:write(Term), {S, lists:flatlength(S)}. -print_length_tuple(_Tuple, 1, _RF, _Enc) -> +print_length_tuple(_Tuple, 1, _RF, _Enc, _Str) -> {"{...}", 5}; -print_length_tuple(Tuple, D, RF, Enc) -> - L = print_length_list1(tuple_to_list(Tuple), D, RF, Enc), +print_length_tuple(Tuple, D, RF, Enc, Str) -> + L = print_length_list1(tuple_to_list(Tuple), D, RF, Enc, Str), IsTagged = is_atom(element(1, Tuple)) and (tuple_size(Tuple) > 1), {{tuple,IsTagged,L}, list_length(L, 2)}. -print_length_record(_Tuple, 1, _RF, _RDefs, _Enc) -> +print_length_record(_Tuple, 1, _RF, _RDefs, _Enc, _Str) -> {"{...}", 5}; -print_length_record(Tuple, D, RF, RDefs, Enc) -> +print_length_record(Tuple, D, RF, RDefs, Enc, Str) -> Name = [$# | io_lib:write_atom(element(1, Tuple))], NameL = length(Name), - L = print_length_fields(RDefs, D - 1, tl(tuple_to_list(Tuple)), RF, Enc), + Elements = tl(tuple_to_list(Tuple)), + L = print_length_fields(RDefs, D - 1, Elements, RF, Enc, Str), {{record, [{Name,NameL} | L]}, list_length(L, NameL + 2)}. -print_length_fields([], _D, [], _RF, _Enc) -> +print_length_fields([], _D, [], _RF, _Enc, _Str) -> []; -print_length_fields(_, 1, _, _RF, _Enc) -> +print_length_fields(_, 1, _, _RF, _Enc, _Str) -> {dots, 3}; -print_length_fields([Def | Defs], D, [E | Es], RF, Enc) -> - [print_length_field(Def, D - 1, E, RF, Enc) | - print_length_fields(Defs, D - 1, Es, RF, Enc)]. +print_length_fields([Def | Defs], D, [E | Es], RF, Enc, Str) -> + [print_length_field(Def, D - 1, E, RF, Enc, Str) | + print_length_fields(Defs, D - 1, Es, RF, Enc, Str)]. -print_length_field(Def, D, E, RF, Enc) -> +print_length_field(Def, D, E, RF, Enc, Str) -> Name = io_lib:write_atom(Def), - {S, L} = print_length(E, D, RF, Enc), + {S, L} = print_length(E, D, RF, Enc, Str), NameL = length(Name) + 3, {{field, Name, NameL, {S, L}}, NameL + L}. -print_length_list(List, D, RF, Enc) -> - L = print_length_list1(List, D, RF, Enc), +print_length_list(List, D, RF, Enc, Str) -> + L = print_length_list1(List, D, RF, Enc, Str), {{list, L}, list_length(L, 2)}. -print_length_list1([], _D, _RF, _Enc) -> +print_length_list1([], _D, _RF, _Enc, _Str) -> []; -print_length_list1(_, 1, _RF, _Enc) -> +print_length_list1(_, 1, _RF, _Enc, _Str) -> {dots, 3}; -print_length_list1([E | Es], D, RF, Enc) -> - [print_length(E, D - 1, RF, Enc) | print_length_list1(Es, D - 1, RF, Enc)]; -print_length_list1(E, D, RF, Enc) -> - print_length(E, D - 1, RF, Enc). +print_length_list1([E | Es], D, RF, Enc, Str) -> + [print_length(E, D - 1, RF, Enc, Str) | + print_length_list1(Es, D - 1, RF, Enc, Str)]; +print_length_list1(E, D, RF, Enc, Str) -> + print_length(E, D - 1, RF, Enc, Str). list_length([], Acc) -> Acc; @@ -452,18 +456,6 @@ printable_list(L, _D, latin1) -> io_lib:printable_latin1_list(L); printable_list(L, _D, _Uni) -> io_lib:printable_list(L). -%% Truncated lists could break some existing code. -% printable_list(L, D, Enc) when D >= 0 -> -% Len = ?CHARS * (D - 1), -% case printable_list1(L, Len, Enc) of -% all -> -% true; -% N when is_integer(N), Len - N >= D - 1 -> -% {L1, _} = lists:split(Len - N, L), -% {true, L1}; -% N when is_integer(N) -> -% false -% end. printable_bin(Bin, D, Enc) when D >= 0, ?CHARS * D =< byte_size(Bin) -> printable_bin(Bin, erlang:min(?CHARS * D, byte_size(Bin)), D, Enc); @@ -473,7 +465,7 @@ printable_bin(Bin, D, Enc) -> printable_bin(Bin, Len, D, latin1) -> N = erlang:min(20, Len), L = binary_to_list(Bin, 1, N), - case printable_list1(L, N) of + case printable_latin1_list(L, N) of all when N =:= byte_size(Bin) -> {true, L}; all when N =:= Len -> % N < byte_size(Bin) @@ -493,13 +485,18 @@ printable_bin(Bin, Len, D, latin1) -> false end; printable_bin(Bin, Len, D, _Uni) -> - case printable_unicode(Bin, Len, []) of - {_, <<>>, L} -> - {byte_size(Bin) =:= length(L), L}; - {NC, Bin1, L} when D > 0, Len - NC >= D -> - {byte_size(Bin)-byte_size(Bin1) =:= length(L), true, L}; - {_NC, _Bin, _L} -> - false + case valid_utf8(Bin,Len) of + true -> + case printable_unicode(Bin, Len, [], io:printable_range()) of + {_, <<>>, L} -> + {byte_size(Bin) =:= length(L), L}; + {NC, Bin1, L} when D > 0, Len - NC >= D -> + {byte_size(Bin)-byte_size(Bin1) =:= length(L), true, L}; + {_NC, _Bin, _L} -> + false + end; + false -> + printable_bin(Bin, Len, D, latin1) end. printable_bin1(_Bin, _Start, 0) -> @@ -507,7 +504,7 @@ printable_bin1(_Bin, _Start, 0) -> printable_bin1(Bin, Start, Len) -> N = erlang:min(10000, Len), L = binary_to_list(Bin, Start, Start + N - 1), - case printable_list1(L, N) of + case printable_latin1_list(L, N) of all -> printable_bin1(Bin, Start + N, Len - N); NC when is_integer(NC) -> @@ -515,26 +512,56 @@ printable_bin1(Bin, Start, Len) -> end. %% -> all | integer() >=0. Adopted from io_lib.erl. -% printable_list1([_ | _], 0) -> 0; -printable_list1([C | Cs], N) when is_integer(C), C >= $\s, C =< $~ -> - printable_list1(Cs, N - 1); -printable_list1([C | Cs], N) when is_integer(C), C >= $\240, C =< $\377 -> - printable_list1(Cs, N - 1); -printable_list1([$\n | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\r | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\t | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\v | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\b | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\f | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([$\e | Cs], N) -> printable_list1(Cs, N - 1); -printable_list1([], _) -> all; -printable_list1(_, N) -> N. - -printable_unicode(<<C/utf8, R/binary>>, I, L) when I > 0 -> - printable_unicode(R, I - 1, [C | L]); -printable_unicode(Bin, I, L) -> +% 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 -> + printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\n | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\r | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\t | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\v | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\b | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\f | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([$\e | Cs], N) -> printable_latin1_list(Cs, N - 1); +printable_latin1_list([], _) -> all; +printable_latin1_list(_, N) -> N. + +valid_utf8(<<>>,_) -> + true; +valid_utf8(_,0) -> + true; +valid_utf8(<<_/utf8, R/binary>>,N) -> + valid_utf8(R,N-1); +valid_utf8(_,_) -> + false. + +printable_unicode(<<C/utf8, R/binary>>=Bin, I, L, Range) when I > 0 -> + case printable_char(C,Range) of + true -> + printable_unicode(R, I - 1, [C | L],Range); + false -> + {I, Bin, lists:reverse(L)} + end; +printable_unicode(Bin, I, L,_) -> {I, Bin, lists:reverse(L)}. +printable_char($\n,_) -> true; +printable_char($\r,_) -> true; +printable_char($\t,_) -> true; +printable_char($\v,_) -> true; +printable_char($\b,_) -> true; +printable_char($\f,_) -> true; +printable_char($\e,_) -> true; +printable_char(C,latin1) -> + C >= $\s andalso C =< $~ orelse + C >= 16#A0 andalso C =< 16#FF; +printable_char(C,unicode) -> + C >= $\s andalso C =< $~ orelse + C >= 16#A0 andalso C < 16#D800 orelse + C > 16#DFFF andalso C < 16#FFFE orelse + C > 16#FFFF andalso C =< 16#10FFFF. + write_string(S, latin1) -> io_lib:write_latin1_string(S, $"); %" write_string(S, _Uni) -> diff --git a/lib/stdlib/src/otp_internal.erl b/lib/stdlib/src/otp_internal.erl index 9257953071..a4f4035c79 100644 --- a/lib/stdlib/src/otp_internal.erl +++ b/lib/stdlib/src/otp_internal.erl @@ -353,7 +353,7 @@ obsolete_1(inviso, _, _) -> %% Added in R15B01. obsolete_1(gs, _, _) -> - {deprecated,"the gs application has been deprecated and will be removed in R16; use the wx application instead"}; + {deprecated,"the gs application has been deprecated and will be removed in R17; use the wx application instead"}; obsolete_1(ssh, sign_data, 2) -> {deprecated,"deprecated (will be removed in R16A); use public_key:pem_decode/1, public_key:pem_entry_decode/1 " "and public_key:sign/3 instead"}; diff --git a/lib/stdlib/src/qlc.erl b/lib/stdlib/src/qlc.erl index 6a27cff589..48f6622565 100644 --- a/lib/stdlib/src/qlc.erl +++ b/lib/stdlib/src/qlc.erl @@ -3709,7 +3709,7 @@ maybe_error_logger(Name, Why) -> Trimmer = fun(M, _F, _A) -> M =:= erl_eval end, Formater = fun(Term, I) -> io_lib:print(Term, I, 80, -1) end, X = lib:format_stacktrace(1, Stacktrace, Trimmer, Formater), - error_logger:Name("qlc: temporary file was needed for ~w\n~s\n", + error_logger:Name("qlc: temporary file was needed for ~w\n~ts\n", [Why, lists:flatten(X)]). expand_stacktrace() -> diff --git a/lib/stdlib/src/shell.erl b/lib/stdlib/src/shell.erl index 203d2a4f76..c6c706c3a7 100644 --- a/lib/stdlib/src/shell.erl +++ b/lib/stdlib/src/shell.erl @@ -22,7 +22,7 @@ -export([whereis_evaluator/0, whereis_evaluator/1]). -export([start_restricted/1, stop_restricted/0]). -export([local_allowed/3, non_local_allowed/3]). --export([prompt_func/1]). +-export([prompt_func/1, strings/1]). -define(LINEMAX, 30). -define(CHAR_MAX, 60). @@ -30,6 +30,7 @@ -define(DEF_RESULTS, 20). -define(DEF_CATCH_EXCEPTION, false). -define(DEF_PROMPT_FUNC, default). +-define(DEF_STRINGS, true). -define(RECORDS, shell_records). @@ -128,7 +129,7 @@ start_restricted(RShMod) when is_atom(RShMod) -> error_logger:error_report( lists:flatten( io_lib:fwrite( - "Restricted shell module ~w not found: ~"++cs_p() ++"\n", + "Restricted shell module ~w not found: ~tp\n", [RShMod,What]))), Error end. @@ -185,7 +186,7 @@ server(StartSync) -> %% Check if we're in user restricted mode. RShErr = case application:get_env(stdlib, restricted_shell) of - {ok,RShMod} -> + {ok,RShMod} when is_atom(RShMod) -> io:fwrite(<<"Restricted ">>, []), case code:ensure_loaded(RShMod) of {module,RShMod} -> @@ -193,6 +194,8 @@ server(StartSync) -> {error,What} -> {RShMod,What} end; + {ok, Term} -> + {Term,not_an_atom}; undefined -> undefined end, @@ -211,8 +214,7 @@ server(StartSync) -> ok; {RShMod2,What2} -> io:fwrite( - ("Warning! Restricted shell module ~w not found: ~" - ++cs_p()++".\n" + ("Warning! Restricted shell module ~w not found: ~tp.\n" "Only the commands q() and init:stop() will be allowed!\n"), [RShMod2,What2]), application:set_env(stdlib, restricted_shell, ?MODULE) @@ -281,7 +283,12 @@ get_command(Prompt, Eval, Bs, RT, Ds) -> eof; {error,ErrorInfo,_EndPos} -> %% Skip the rest of the line: + Opts = io:getopts(), + TmpOpts = lists:keyreplace(echo, 1, Opts, + {echo, false}), + _ = io:setopts(TmpOpts), _ = io:get_line(''), + _ = io:setopts(Opts), {error,ErrorInfo}; Else -> Else @@ -334,7 +341,7 @@ get_prompt_func() -> end. bad_prompt_func(M) -> - fwrite_severity(benign, "Bad prompt function: ~"++cs_p(), [M]). + fwrite_severity(benign, "Bad prompt function: ~tp", [M]). default_prompt(N) -> %% Don't bother flattening the list irrespective of what the @@ -948,7 +955,7 @@ local_func(rd, [{atom,_,RecName},RecDef0], Bs, _Shell, RT, _Lf, _Ef) -> RecDef = expand_value(RecDef0), RDs = lists:flatten(erl_pp:expr(RecDef)), Attr = lists:concat(["-record('", RecName, "',", RDs, ")."]), - {ok, Tokens, _} = erl_scan:string(Attr, 1, [unicode]), + {ok, Tokens, _} = erl_scan:string(Attr), case erl_parse:parse_form(Tokens) of {ok,AttrForm} -> [RN] = add_records([AttrForm], Bs, RT), @@ -1364,38 +1371,36 @@ pp(V, I, RT) -> pp(V, I, RT, enc()). pp(V, I, RT, Enc) -> + Strings = + case application:get_env(stdlib, shell_strings) of + {ok, false} -> + false; + _ -> + true + end, io_lib_pretty:print(V, ([{column, I}, {line_length, columns()}, {depth, ?LINEMAX}, {max_chars, ?CHAR_MAX}, + {strings, Strings}, {record_print_fun, record_print_fun(RT)}] ++ Enc)). -%% Control sequence 'p' possibly with Unicode translation modifier -cs_p() -> - case encoding() of - latin1 -> "p"; - unicode -> "tp" - end. - columns() -> case io:columns() of {ok,N} -> N; _ -> 80 end. - encoding() -> [{encoding, Encoding}] = enc(), Encoding. - enc() -> case lists:keyfind(encoding, 1, io:getopts()) of - false -> [{encoding,latin1}]; % should never happen - Enc -> [Enc] + false -> [{encoding,latin1}]; % should never happen + Enc -> [Enc] end. garb(Shell) -> erlang:garbage_collect(Shell), catch erlang:garbage_collect(whereis(user)), - catch erlang:garbage_collect(whereis(group)), catch erlang:garbage_collect(group_leader()), erlang:garbage_collect(). @@ -1414,10 +1419,9 @@ check_env(V) -> {ok, Val} when is_integer(Val), Val >= 0 -> ok; {ok, Val} -> - Txt = io_lib:fwrite( - ("Invalid value of STDLIB configuration parameter ~w: ~" - ++cs_p()++"\n"), - [V, Val]), + Txt = io_lib:fwrite + ("Invalid value of STDLIB configuration parameter" + "~w: ~tp\n", [V, Val]), error_logger:info_report(lists:flatten(Txt)) end. @@ -1443,14 +1447,22 @@ history(L) when is_integer(L), L >= 0 -> results(L) when is_integer(L), L >= 0 -> set_env(stdlib, shell_saved_results, L, ?DEF_RESULTS). --spec catch_exception(Bool) -> Bool when +-spec catch_exception(Bool) -> boolean() when Bool :: boolean(). catch_exception(Bool) -> set_env(stdlib, shell_catch_exception, Bool, ?DEF_CATCH_EXCEPTION). --spec prompt_func(PromptFunc) -> PromptFunc when - PromptFunc :: 'default' | {module(),atom()}. +-spec prompt_func(PromptFunc) -> PromptFunc2 when + PromptFunc :: 'default' | {module(),atom()}, + PromptFunc2 :: 'default' | {module(),atom()}. prompt_func(String) -> set_env(stdlib, shell_prompt_func, String, ?DEF_PROMPT_FUNC). + +-spec strings(Strings) -> Strings2 when + Strings :: boolean(), + Strings2 :: boolean(). + +strings(Strings) -> + set_env(stdlib, shell_strings, Strings, ?DEF_STRINGS). diff --git a/lib/stdlib/test/epp_SUITE.erl b/lib/stdlib/test/epp_SUITE.erl index 041d521514..b2f1aa955a 100644 --- a/lib/stdlib/test/epp_SUITE.erl +++ b/lib/stdlib/test/epp_SUITE.erl @@ -25,7 +25,7 @@ variable_1/1, otp_4870/1, otp_4871/1, otp_5362/1, pmod/1, not_circular/1, skip_header/1, otp_6277/1, otp_7702/1, otp_8130/1, overload_mac/1, otp_8388/1, otp_8470/1, otp_8503/1, - otp_8562/1, otp_8665/1, otp_8911/1, otp_10302/1]). + otp_8562/1, otp_8665/1, otp_8911/1, otp_10302/1, otp_10820/1]). -export([epp_parse_erl_form/2]). @@ -67,7 +67,7 @@ all() -> {group, variable}, otp_4870, otp_4871, otp_5362, pmod, not_circular, skip_header, otp_6277, otp_7702, otp_8130, overload_mac, otp_8388, otp_8470, otp_8503, otp_8562, - otp_8665, otp_8911, otp_10302]. + otp_8665, otp_8911, otp_10302, otp_10820]. groups() -> [{upcase_mac, [], [upcase_mac_1, upcase_mac_2]}, @@ -1359,6 +1359,30 @@ encoding_nocom(Enc, File) -> ok = file:close(Fd), E = epp:read_encoding(File, Options). +otp_10820(doc) -> + "OTP-10820. Unicode filenames."; +otp_10820(suite) -> + []; +otp_10820(Config) when is_list(Config) -> + L = [915,953,959,973,957,953,954,959,957,964], + Dir = ?config(priv_dir, Config), + File = filename:join(Dir, L++".erl"), + C1 = <<"%% coding: utf-8\n -module(any).">>, + ok = do_otp_10820(File, C1, "+pc latin1"), + ok = do_otp_10820(File, C1, "+pc unicode"), + C2 = <<"\n-module(any).">>, + ok = do_otp_10820(File, C2, "+pc latin1"), + ok = do_otp_10820(File, C2, "+pc unicode"). + +do_otp_10820(File, C, PC) -> + {ok,Node} = start_node(erl_pp_helper, "+fnu " ++ PC), + ok = rpc:call(Node, file, write_file, [File, C]), + {ok,[{attribute,1,file,{File,1}}, + {attribute,2,module,any}, + {eof,2}]} = rpc:call(Node, epp, parse_file, [File, [],[]]), + true = test_server:stop_node(Node), + ok. + check(Config, Tests) -> eval_tests(Config, fun check_test/2, Tests). @@ -1475,3 +1499,8 @@ ln2({error,M}) -> {error,ln2(M)}; ln2(M) -> M. + +%% +fnu means a peer node has to be started; slave will not do +start_node(Name, Xargs) -> + ?line PA = filename:dirname(code:which(?MODULE)), + test_server:start_node(Name, peer, [{args, "-pa " ++ PA ++ " " ++ Xargs}]). diff --git a/lib/stdlib/test/erl_eval_SUITE.erl b/lib/stdlib/test/erl_eval_SUITE.erl index 04d49770cb..7ff4c81ea6 100644 --- a/lib/stdlib/test/erl_eval_SUITE.erl +++ b/lib/stdlib/test/erl_eval_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1998-2012. All Rights Reserved. +%% Copyright Ericsson AB 1998-2013. All Rights Reserved. %% %% The contents of this file are subject to the Erlang Public License, %% Version 1.1, (the "License"); you may not use this file except in @@ -37,6 +37,7 @@ otp_6977/1, otp_7550/1, otp_8133/1, + otp_10622/1, funs/1, try_catch/1, eval_expr_5/1, @@ -79,7 +80,7 @@ all() -> pattern_expr, match_bin, guard_3, guard_4, lc, simple_cases, unary_plus, apply_atom, otp_5269, otp_6539, otp_6543, otp_6787, otp_6977, otp_7550, - otp_8133, funs, try_catch, eval_expr_5, zero_width]. + otp_8133, otp_10622, funs, try_catch, eval_expr_5, zero_width]. groups() -> []. @@ -960,6 +961,7 @@ otp_8133(Config) when is_list(Config) -> E = fun(N) -> if is_integer(N) -> <<N/integer>>; + true -> erlang:error(foo) end end, @@ -980,6 +982,48 @@ otp_8133(Config) when is_list(Config) -> ok), ok. +otp_10622(doc) -> + ["OTP-10622. Bugs."]; +otp_10622(suite) -> + []; +otp_10622(Config) when is_list(Config) -> + check(fun() -> <<0>> = <<"\x{400}">> end, + "<<0>> = <<\"\\x{400}\">>. ", + <<0>>), + check(fun() -> <<"\x{aa}ff"/utf8>> = <<"\x{aa}ff"/utf8>> end, + "<<\"\\x{aa}ff\"/utf8>> = <<\"\\x{aa}ff\"/utf8>>. ", + <<"�\xaaff">>), + %% The same bug as last example: + check(fun() -> case <<"foo"/utf8>> of + <<"foo"/utf8>> -> true + end + end, + "case <<\"foo\"/utf8>> of <<\"foo\"/utf8>> -> true end.", + true), + check(fun() -> <<"\x{400}"/utf8>> = <<"\x{400}"/utf8>> end, + "<<\"\\x{400}\"/utf8>> = <<\"\\x{400}\"/utf8>>. ", + <<208,128>>), + error_check("<<\"\\x{aaa}\">> = <<\"\\x{aaa}\">>.", + {badmatch,<<"\xaa">>}), + + check(fun() -> [a || <<"\x{aaa}">> <= <<2703:16>>] end, + "[a || <<\"\\x{aaa}\">> <= <<2703:16>>]. ", + []), + check(fun() -> [a || <<"\x{aa}"/utf8>> <= <<"\x{aa}"/utf8>>] end, + "[a || <<\"\\x{aa}\"/utf8>> <= <<\"\\x{aa}\"/utf8>>]. ", + [a]), + check(fun() -> [a || <<"\x{aa}x"/utf8>> <= <<"\x{aa}y"/utf8>>] end, + "[a || <<\"\\x{aa}x\"/utf8>> <= <<\"\\x{aa}y\"/utf8>>]. ", + []), + check(fun() -> [a || <<"\x{aaa}">> <= <<"\x{aaa}">>] end, + "[a || <<\"\\x{aaa}\">> <= <<\"\\x{aaa}\">>]. ", + []), + check(fun() -> [a || <<"\x{aaa}"/utf8>> <= <<"\x{aaa}"/utf8>>] end, + "[a || <<\"\\x{aaa}\"/utf8>> <= <<\"\\x{aaa}\"/utf8>>]. ", + [a]), + + ok. + funs(doc) -> ["Simple cases, just to cover some code."]; funs(suite) -> @@ -1042,6 +1086,10 @@ funs(Config) when is_list(Config) -> "begin M = lists, F = fun M:reverse/1," " [1,2] = F([2,1]), ok end.", ok), + + %% Test that {M,F} is not accepted as a fun. + error_check("{" ?MODULE_STRING ",module_info}().", + {badfun,{?MODULE,module_info}}), ok. run_many_args({S, As}) -> diff --git a/lib/stdlib/test/erl_lint_SUITE.erl b/lib/stdlib/test/erl_lint_SUITE.erl index 564f27a512..36229b6989 100644 --- a/lib/stdlib/test/erl_lint_SUITE.erl +++ b/lib/stdlib/test/erl_lint_SUITE.erl @@ -58,7 +58,8 @@ otp_8051/1, format_warn/1, on_load_successful/1, on_load_failing/1, - too_many_arguments/1 + too_many_arguments/1, + basic_errors/1,bin_syntax_errors/1 ]). % Default timetrap timeout (set in init_per_testcase). @@ -84,7 +85,7 @@ all() -> otp_5878, otp_5917, otp_6585, otp_6885, otp_10436, export_all, bif_clash, behaviour_basic, behaviour_multiple, otp_7550, otp_8051, format_warn, {group, on_load}, - too_many_arguments]. + too_many_arguments, basic_errors, bin_syntax_errors]. groups() -> [{unused_vars_warn, [], @@ -1351,7 +1352,17 @@ guard(Config) when is_list(Config) -> (is_record(X, apa)*2)]. ">>, [], - []}], + []}, + {guard8, + <<"t(A) when erlang:is_foobar(A) -> ok; + t(A) when A ! ok -> ok; + t(A) when A ++ [x] -> ok." + >>, + [], + {errors,[{1,erl_lint,illegal_guard_expr}, + {2,erl_lint,illegal_guard_expr}, + {3,erl_lint,illegal_guard_expr}],[]}} + ], ?line [] = run(Config, Ts1), ok. @@ -1639,6 +1650,7 @@ otp_5276(Config) when is_list(Config) -> -deprecated([{'_','_',never}]). -deprecated([{{badly,formed},1}]). -deprecated([{'_','_',next_major_release}]). + -deprecated([{atom_to_list,1}]). -export([t/0]). frutt() -> ok. t() -> ok. @@ -1649,8 +1661,9 @@ otp_5276(Config) when is_list(Config) -> {3,erl_lint,{invalid_deprecated,'foo bar'}}, {5,erl_lint,{bad_deprecated,{f,'_'}}}, {8,erl_lint,{invalid_deprecated,{'_','_',never}}}, - {9,erl_lint,{invalid_deprecated,{{badly,formed},1}}}], - [{12,erl_lint,{unused_function,{frutt,0}}}]}}], + {9,erl_lint,{invalid_deprecated,{{badly,formed},1}}}, + {11,erl_lint,{bad_deprecated,{atom_to_list,1}}}], + [{13,erl_lint,{unused_function,{frutt,0}}}]}}], ?line [] = run(Config, Ts), ok. @@ -1896,9 +1909,23 @@ otp_5362(Config) when is_list(Config) -> warn_deprecated_function, warn_bif_clash]}, {errors, - [{2,erl_lint,disallowed_nowarn_bif_clash}],[]}} + [{2,erl_lint,disallowed_nowarn_bif_clash}],[]}}, - ], + {call_deprecated_function, + <<"t(X) -> erlang:hash(X, 2000).">>, + [], + {warnings, + [{1,erl_lint,{deprecated,{erlang,hash,2}, + {erlang,phash2,2},"in a future release"}}]}}, + + {call_removed_function, + <<"t(X) -> regexp:match(X).">>, + [], + {warnings, + [{1,erl_lint,{removed,{regexp,match,1}, + "removed in R15; use the re module instead"}}]}} + + ], ?line [] = run(Config, Ts), ok. @@ -2971,6 +2998,77 @@ too_many_arguments(Config) when is_list(Config) -> ok. +%% Test some basic errors to improve coverage. +basic_errors(Config) -> + Ts = [{redefine_module, + <<"-module(redefine_module).">>, + [], + {errors,[{1,erl_lint,redefine_module}],[]}}, + + {attr_after_function, + <<"f() -> ok. + -attr(x).">>, + [], + {errors,[{2,erl_lint,{attribute,attr}}],[]}}, + + {redefine_function, + <<"f() -> ok. + f() -> ok.">>, + [], + {errors,[{2,erl_lint,{redefine_function,{f,0}}}],[]}}, + + {redefine_record, + <<"-record(r, {a}). + -record(r, {a}). + f(#r{}) -> ok.">>, + [], + {errors,[{2,erl_lint,{redefine_record,r}}],[]}}, + + {illegal_record_info, + <<"f1() -> record_info(42, record). + f2() -> record_info(shoe_size, record).">>, + [], + {errors,[{1,erl_lint,illegal_record_info}, + {2,erl_lint,illegal_record_info}],[]}}, + + {illegal_expr, + <<"f() -> a:b.">>, + [], + {errors,[{1,erl_lint,illegal_expr}],[]}}, + + {illegal_pattern, + <<"f(A+B) -> ok.">>, + [], + {errors,[{1,erl_lint,illegal_pattern}],[]}} + ], + [] = run(Config, Ts), + ok. + +%% Test binary syntax errors +bin_syntax_errors(Config) -> + Ts = [{bin_syntax_errors, + <<"t(<<X:bad_size>>) -> X; + t(<<_:(x ! y)/integer>>) -> ok; + t(<<X:all/integer>>) -> X; + t(<<X/bad_type>>) -> X; + t(<<X/unit:8>>) -> X; + t(<<X:7/float>>) -> X; + t(<< <<_:8>> >>) -> ok; + t(<<(x ! y):8/integer>>) -> ok. + ">>, + [], + {error,[{1,erl_lint,illegal_bitsize}, + {2,erl_lint,illegal_bitsize}, + {3,erl_lint,illegal_bitsize}, + {4,erl_lint,{undefined_bittype,bad_type}}, + {5,erl_lint,bittype_unit}, + {7,erl_lint,illegal_pattern}, + {8,erl_lint,illegal_pattern}], + [{6,erl_lint,{bad_bitsize,"float"}}]}} + ], + [] = run(Config, Ts), + ok. + run(Config, Tests) -> F = fun({N,P,Ws,E}, BadL) -> case catch run_test(Config, P, Ws) of diff --git a/lib/stdlib/test/erl_pp_SUITE.erl b/lib/stdlib/test/erl_pp_SUITE.erl index 37be61d665..9c0a43abcc 100644 --- a/lib/stdlib/test/erl_pp_SUITE.erl +++ b/lib/stdlib/test/erl_pp_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2006-2012. All Rights Reserved. +%% Copyright Ericsson AB 2006-2013. All Rights Reserved. %% %% The contents of this file are subject to the Erlang Public License, %% Version 1.1, (the "License"); you may not use this file except in @@ -49,7 +49,7 @@ otp_6321/1, otp_6911/1, otp_6914/1, otp_8150/1, otp_8238/1, otp_8473/1, otp_8522/1, otp_8567/1, otp_8664/1, otp_9147/1, - otp_10302/1]). + otp_10302/1, otp_10820/1]). %% Internal export. -export([ehook/6]). @@ -80,7 +80,8 @@ groups() -> {attributes, [], [misc_attrs, import_export]}, {tickets, [], [otp_6321, otp_6911, otp_6914, otp_8150, otp_8238, - otp_8473, otp_8522, otp_8567, otp_8664, otp_9147, otp_10302]}]. + otp_8473, otp_8522, otp_8567, otp_8664, otp_9147, + otp_10302, otp_10820]}]. init_per_suite(Config) -> Config. @@ -1074,6 +1075,34 @@ otp_10302(Config) when is_list(Config) -> unicode_hook({foo,E}, I, P, H) -> erl_pp:expr({call,0,{atom,0,foo},[E]}, I, P, H). +otp_10820(doc) -> + "OTP-10820. Unicode filenames."; +otp_10820(suite) -> []; +otp_10820(Config) when is_list(Config) -> + C1 = <<"%% coding: utf-8\n -module(any).">>, + ok = do_otp_10820(Config, C1, "+pc latin1"), + ok = do_otp_10820(Config, C1, "+pc unicode"), + C2 = <<"-module(any).">>, + ok = do_otp_10820(Config, C2, "+pc latin1"), + ok = do_otp_10820(Config, C2, "+pc unicode"). + +do_otp_10820(Config, C, PC) -> + {ok,Node} = start_node(erl_pp_helper, "+fnu " ++ PC), + L = [915,953,959,973,957,953,954,959,957,964], + FileName = filename(L++".erl", Config), + ok = rpc:call(Node, file, write_file, [FileName, C]), + {ok, _, []} = rpc:call(Node, compile, file, + [FileName, [return,'P',{outdir,?privdir}]]), + PFileName = filename(L++".P", Config), + {ok, Bin} = rpc:call(Node, file, read_file, [PFileName]), + true = test_server:stop_node(Node), + true = file_attr_is_string(binary_to_list(Bin)), + ok. + +file_attr_is_string("-file(\"" ++ _) -> true; +file_attr_is_string([_ | L]) -> + file_attr_is_string(L). + %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% compile(Config, Tests) -> @@ -1247,3 +1276,8 @@ filename(Name, Config) -> fail() -> io:format("failed~n"), ?t:fail(). + +%% +fnu means a peer node has to be started; slave will not do +start_node(Name, Xargs) -> + ?line PA = filename:dirname(code:which(?MODULE)), + test_server:start_node(Name, peer, [{args, "-pa " ++ PA ++ " " ++ Xargs}]). diff --git a/lib/stdlib/test/erl_scan_SUITE.erl b/lib/stdlib/test/erl_scan_SUITE.erl index 3f77d40a2e..ecd181e87c 100644 --- a/lib/stdlib/test/erl_scan_SUITE.erl +++ b/lib/stdlib/test/erl_scan_SUITE.erl @@ -118,13 +118,13 @@ check(String) -> %%% (This should be useful for all format_error functions.) check_error({error, Info, EndLine}, Module0) -> - ?line {ErrorLine, Module, Desc} = Info, - ?line true = (Module == Module0), - ?line assert_type(EndLine, integer), - ?line assert_type(ErrorLine, integer), - ?line true = (ErrorLine =< EndLine), - ?line String = lists:flatten(Module0:format_error(Desc)), - ?line true = io_lib:printable_list(String). + {ErrorLine, Module, Desc} = Info, + true = (Module == Module0), + assert_type(EndLine, integer), + assert_type(ErrorLine, integer), + true = (ErrorLine =< EndLine), + String = lists:flatten(Module0:format_error(Desc)), + true = io_lib:printable_list(String). iso88591(doc) -> ["Tests the support for ISO-8859-1 i.e Latin-1"]; iso88591(suite) -> []; @@ -809,77 +809,57 @@ white_spaces() -> unicode() -> ?line {ok,[{char,1,83},{integer,1,45}],1} = - erl_scan:string("$\\12345", 1, [{unicode,false}]), % not unicode + erl_scan:string("$\\12345"), % not unicode ?line {error,{1,erl_scan,{illegal,character}},1} = - erl_scan:string([1089], 1, [{unicode,false}]), + erl_scan:string([1089]), ?line {error,{{1,1},erl_scan,{illegal,character}},{1,2}} = - erl_scan:string([1089], {1,1}, [{unicode,false}]), - ?line {error,{1,erl_scan,{illegal,character}},1} = - %% ?line {error,{1,erl_scan,{illegal,atom}},1} = - erl_scan:string("'a"++[1089]++"b'", 1, [{unicode,false}]), - ?line {error,{{1,3},erl_scan,{illegal,character}},{1,4}} = - erl_scan:string("'a"++[1089]++"b'", {1,1}, [{unicode,false}]), + erl_scan:string([1089], {1,1}), + ?line {error,{1,erl_scan,{illegal,atom}},1} = + erl_scan:string("'a"++[1089]++"b'", 1), + ?line {error,{{1,1},erl_scan,{illegal,atom}},{1,6}} = + erl_scan:string("'a"++[1089]++"b'", {1,1}), ?line test("\"a"++[1089]++"b\""), ?line {ok,[{char,1,1}],1} = - erl_scan:string([$$,$\\,$^,1089], 1, [{unicode,false}]), + erl_scan:string([$$,$\\,$^,1089], 1), ?line {error,{1,erl_scan,Error},1} = - erl_scan:string("\"qa\x{aaa}", 1, [{unicode,false}]), + erl_scan:string("\"qa\x{aaa}", 1), ?line "unterminated string starting with \"qa"++[2730]++"\"" = erl_scan:format_error(Error), ?line {error,{{1,1},erl_scan,_},{1,11}} = - erl_scan:string("\"qa\\x{aaa}",{1,1}, [{unicode,false}]), - ?line {error,{{1,4},erl_scan,{illegal,character}},{1,11}} = - erl_scan:string("'qa\\x{aaa}'",{1,1}, [{unicode,false}]), - - Tags = [category, column, length, line, symbol, text], - - %% Workaround. No character codes greater than 255! To be changed. - %% Note: don't remove these tests, just modify them! + erl_scan:string("\"qa\\x{aaa}",{1,1}), + ?line {error,{{1,1},erl_scan,{illegal,atom}},{1,12}} = + erl_scan:string("'qa\\x{aaa}'",{1,1}), - ?line {ok,[{integer,1,1089}],1} = - erl_scan:string([$$,1089], 1, [{unicode,false}]), - ?line {ok,[{integer,1,1089}],1} = - erl_scan:string([$$,$\\,1089], 1, [{unicode,false}]), + ?line {ok,[{char,1,1089}],1} = + erl_scan:string([$$,1089], 1), + ?line {ok,[{char,1,1089}],1} = + erl_scan:string([$$,$\\,1089], 1), Qs = "$\\x{aaa}", - ?line {ok,[{integer,1,16#aaa}],1} = - erl_scan:string(Qs, 1, [{unicode,false}]), + ?line {ok,[{char,1,$\x{aaa}}],1} = + erl_scan:string(Qs, 1), ?line {ok,[Q2],{1,9}} = - erl_scan:string("$\\x{aaa}", {1,1}, [text,{unicode,false}]), - ?line [{category,integer},{column,1},{length,8}, + erl_scan:string("$\\x{aaa}", {1,1}, [text]), + ?line [{category,char},{column,1},{length,8}, {line,1},{symbol,16#aaa},{text,Qs}] = erl_scan:token_info(Q2), U1 = "\"\\x{aaa}\"", - ?line {ok,[T1,T2,T3],{1,10}} = - erl_scan:string(U1, {1,1}, [text,{unicode,false}]), - ?line [{category,'['},{column,1},{length,1},{line,1}, - {symbol,'['},{text,"\""}] = erl_scan:token_info(T1, Tags), - ?line [{category,integer},{column,2},{length,7}, - {line,1},{symbol,16#aaa},{text,"\\x{aaa}"}] = - erl_scan:token_info(T2, Tags), - ?line [{category,']'},{column,9},{length,1},{line,1}, - {symbol,']'},{text,"\""}] = erl_scan:token_info(T3, Tags), - ?line {ok,[{'[',1},{integer,1,16#aaa},{']',1}],1} = - erl_scan:string(U1, 1, [{unicode,false}]), + {ok, + [{string,[{line,1},{column,1},{text,"\"\\x{aaa}\""}],[2730]}], + {1,10}} = erl_scan:string(U1, {1,1}, [text]), + {ok,[{string,1,[2730]}],1} = erl_scan:string(U1, 1), U2 = "\"\\x41\\x{fff}\\x42\"", - ?line {ok,[{'[',1},{char,1,16#41},{',',1},{integer,1,16#fff}, - {',',1},{char,1,16#42},{']',1}],1} = - erl_scan:string(U2, 1, [{unicode,false}]), + {ok,[{string,1,[$\x41,$\x{fff},$\x42]}],1} = erl_scan:string(U2, 1), U3 = "\"a\n\\x{fff}\n\"", - ?line {ok,[{'[',1},{char,1,$a},{',',1},{char,1,$\n}, - {',',2},{integer,2,16#fff},{',',2},{char,2,$\n}, - {']',3}],3} = - erl_scan:string(U3, 1, [{unicode,false}]), + {ok,[{string,1,[$a,$\n,$\x{fff},$\n]}],3} = erl_scan:string(U3, 1), U4 = "\"\\^\n\\x{aaa}\\^\n\"", - ?line {ok,[{'[',1},{char,1,$\n},{',',2},{integer,2,16#aaa}, - {',',2},{char,2,$\n},{']',3}],3} = - erl_scan:string(U4, 1, [{unicode,false}]), + {ok,[{string,1,[$\n,$\x{aaa},$\n]}],3} = erl_scan:string(U4, 1), %% Keep these tests: ?line test(Qs), @@ -889,21 +869,15 @@ unicode() -> ?line test(U4), Str1 = "\"ab" ++ [1089] ++ "cd\"", - ?line {ok,[{'[',1},{char,1,$a},{',',1},{char,1,$b},{',',1}, - {integer,1,1089},{',',1},{char,1,$c},{',',1}, - {char,1,$d},{']',1}],1} = - erl_scan:string(Str1, 1, [{unicode,false}]), - ?line {ok,[{'[',_},{char,_,$a},{',',_},{char,_,$b},{',',_}, - {integer,_,1089},{',',_},{char,_,$c},{',',_}, - {char,_,$d},{']',_}],{1,8}} = - erl_scan:string(Str1, {1,1}, [{unicode,false}]), + {ok,[{string,1,[$a,$b,1089,$c,$d]}],1} = erl_scan:string(Str1, 1), + {ok,[{string,{1,1},[$a,$b,1089,$c,$d]}],{1,8}} = + erl_scan:string(Str1, {1,1}), ?line test(Str1), Comment = "%% "++[1089], - %% Returned a comment In R15B03: - {error,{1,erl_scan,{illegal,character}},1} = - erl_scan:string(Comment, 1, [return,{unicode,false}]), - {error,{{1,1},erl_scan,{illegal,character}},{1,5}} = - erl_scan:string(Comment, {1,1}, [return,{unicode,false}]), + {ok,[{comment,1,[$%,$%,$\s,1089]}],1} = + erl_scan:string(Comment, 1, [return]), + {ok,[{comment,{1,1},[$%,$%,$\s,1089]}],{1,5}} = + erl_scan:string(Comment, {1,1}, [return]), ok. more_chars() -> diff --git a/lib/stdlib/test/escript_SUITE.erl b/lib/stdlib/test/escript_SUITE.erl index be8fb1b37a..cf5fb12686 100644 --- a/lib/stdlib/test/escript_SUITE.erl +++ b/lib/stdlib/test/escript_SUITE.erl @@ -913,7 +913,7 @@ unicode(Config) when is_list(Config) -> run(Dir, "unicode1", [<<"escript: exception error: an error occurred when evaluating" " an arithmetic expression\n in operator '/'/2\n " - "called as <<170>> / <<170>>\nExitCode:127">>]), + "called as <<224,170,170>> / <<224,170,170>>\nExitCode:127">>]), run(Dir, "unicode2", [<<"escript: exception error: an error occurred when evaluating" " an arithmetic expression\n in operator '/'/2\n " diff --git a/lib/stdlib/test/escript_SUITE_data/unicode1 b/lib/stdlib/test/escript_SUITE_data/unicode1 index a77574625e..351bb785e5 100755 --- a/lib/stdlib/test/escript_SUITE_data/unicode1 +++ b/lib/stdlib/test/escript_SUITE_data/unicode1 @@ -6,7 +6,7 @@ main(_) -> ok = io:setopts([{encoding,unicode}]), _D = erlang:system_flag(backtrace_depth, 0), - A = <<"\x{aa}">>, + A = <<"\x{aaa}"/utf8>>, S = lists:flatten(io_lib:format("~p/~p.", [A, A])), {ok, Ts, _} = erl_scan:string(S, 1, [unicode]), {ok, Es} = erl_parse:parse_exprs(Ts), diff --git a/lib/stdlib/test/ets_SUITE.erl b/lib/stdlib/test/ets_SUITE.erl index dc17e5d33c..4a51ef564c 100644 --- a/lib/stdlib/test/ets_SUITE.erl +++ b/lib/stdlib/test/ets_SUITE.erl @@ -96,7 +96,7 @@ misc1_do/1, safe_fixtable_do/1, info_do/1, dups_do/1, heavy_lookup_do/1, heavy_lookup_element_do/1, member_do/1, otp_5340_do/1, otp_7665_do/1, meta_wb_do/1, do_heavy_concurrent/1, tab2file2_do/2, exit_large_table_owner_do/2, - types_do/1, sleeper/0, rpc_externals/0, memory_do/1, + types_do/1, sleeper/0, memory_do/1, ms_tracee_dummy/1, ms_tracee_dummy/2, ms_tracee_dummy/3, ms_tracee_dummy/4 ]). @@ -5989,33 +5989,103 @@ make_ext_ref() -> init_externals() -> case get(externals) of undefined -> - SysDistSz = ets:info(sys_dist,size), - ?line Pa = filename:dirname(code:which(?MODULE)), - ?line {ok, Node} = test_server:start_node(plopp, slave, [{args, " -pa " ++ Pa}]), - ?line Res = case rpc:call(Node, ?MODULE, rpc_externals, []) of - {badrpc, {'EXIT', E}} -> - test_server:fail({rpcresult, E}); - R -> R - end, - ?line test_server:stop_node(Node), - - %% Wait for table 'sys_dist' to stabilize - repeat_while(fun() -> - case ets:info(sys_dist,size) of - SysDistSz -> false; - Sz -> - io:format("Waiting for sys_dist to revert size from ~p to size ~p\n", - [Sz, SysDistSz]), - receive after 1000 -> true end - end - end), + OtherNode = {gurka@sallad, 1}, + Res = {mk_pid(OtherNode, 7645, 8123), + mk_port(OtherNode, 187489773), + mk_ref(OtherNode, [262143, 1293964255, 3291964278])}, put(externals, Res); {_,_,_} -> ok end. -rpc_externals() -> - {self(), make_port(), make_ref()}. +%% +%% Node container constructor functions +%% + +-define(VERSION_MAGIC, 131). +-define(PORT_EXT, 102). +-define(PID_EXT, 103). +-define(NEW_REFERENCE_EXT, 114). + +uint32_be(Uint) when is_integer(Uint), 0 =< Uint, Uint < 1 bsl 32 -> + [(Uint bsr 24) band 16#ff, + (Uint bsr 16) band 16#ff, + (Uint bsr 8) band 16#ff, + Uint band 16#ff]; +uint32_be(Uint) -> + exit({badarg, uint32_be, [Uint]}). + +uint16_be(Uint) when is_integer(Uint), 0 =< Uint, Uint < 1 bsl 16 -> + [(Uint bsr 8) band 16#ff, + Uint band 16#ff]; +uint16_be(Uint) -> + exit({badarg, uint16_be, [Uint]}). + +uint8(Uint) when is_integer(Uint), 0 =< Uint, Uint < 1 bsl 8 -> + Uint band 16#ff; +uint8(Uint) -> + exit({badarg, uint8, [Uint]}). + +mk_pid({NodeName, Creation}, Number, Serial) when is_atom(NodeName) -> + <<?VERSION_MAGIC, NodeNameExt/binary>> = term_to_binary(NodeName), + mk_pid({NodeNameExt, Creation}, Number, Serial); +mk_pid({NodeNameExt, Creation}, Number, Serial) -> + case catch binary_to_term(list_to_binary([?VERSION_MAGIC, + ?PID_EXT, + NodeNameExt, + uint32_be(Number), + uint32_be(Serial), + uint8(Creation)])) of + Pid when is_pid(Pid) -> + Pid; + {'EXIT', {badarg, _}} -> + exit({badarg, mk_pid, [{NodeNameExt, Creation}, Number, Serial]}); + Other -> + exit({unexpected_binary_to_term_result, Other}) + end. + +mk_port({NodeName, Creation}, Number) when is_atom(NodeName) -> + <<?VERSION_MAGIC, NodeNameExt/binary>> = term_to_binary(NodeName), + mk_port({NodeNameExt, Creation}, Number); +mk_port({NodeNameExt, Creation}, Number) -> + case catch binary_to_term(list_to_binary([?VERSION_MAGIC, + ?PORT_EXT, + NodeNameExt, + uint32_be(Number), + uint8(Creation)])) of + Port when is_port(Port) -> + Port; + {'EXIT', {badarg, _}} -> + exit({badarg, mk_port, [{NodeNameExt, Creation}, Number]}); + Other -> + exit({unexpected_binary_to_term_result, Other}) + end. + +mk_ref({NodeName, Creation}, Numbers) when is_atom(NodeName), + is_integer(Creation), + is_list(Numbers) -> + <<?VERSION_MAGIC, NodeNameExt/binary>> = term_to_binary(NodeName), + mk_ref({NodeNameExt, Creation}, Numbers); +mk_ref({NodeNameExt, Creation}, Numbers) when is_binary(NodeNameExt), + is_integer(Creation), + is_list(Numbers) -> + case catch binary_to_term(list_to_binary([?VERSION_MAGIC, + ?NEW_REFERENCE_EXT, + uint16_be(length(Numbers)), + NodeNameExt, + uint8(Creation), + lists:map(fun (N) -> + uint32_be(N) + end, + Numbers)])) of + Ref when is_reference(Ref) -> + Ref; + {'EXIT', {badarg, _}} -> + exit({badarg, mk_ref, [{NodeNameExt, Creation}, Numbers]}); + Other -> + exit({unexpected_binary_to_term_result, Other}) + end. + make_sub_binary(Bin) when is_binary(Bin) -> {_,B} = split_binary(list_to_binary([0,1,3,Bin]), 3), diff --git a/lib/stdlib/test/filelib_SUITE.erl b/lib/stdlib/test/filelib_SUITE.erl index 27078f0914..4a67d68428 100644 --- a/lib/stdlib/test/filelib_SUITE.erl +++ b/lib/stdlib/test/filelib_SUITE.erl @@ -65,19 +65,26 @@ wildcard_one(Config) when is_list(Config) -> ?line {ok,OldCwd} = file:get_cwd(), ?line Dir = filename:join(?config(priv_dir, Config), "wildcard_one"), ?line ok = file:make_dir(Dir), + do_wildcard_1(Dir, + fun(Wc) -> + filelib:wildcard(Wc, Dir, erl_prim_loader) + end), ?line file:set_cwd(Dir), - ?line do_wildcard_1(Dir, fun(Wc) -> filelib:wildcard(Wc) end), + do_wildcard_1(Dir, + fun(Wc) -> + L = filelib:wildcard(Wc), + L = filelib:wildcard(Wc, erl_prim_loader), + L = filelib:wildcard(Wc, "."), + L = filelib:wildcard(Wc, Dir) + end), ?line file:set_cwd(OldCwd), ?line ok = file:del_dir(Dir), ok. wildcard_two(Config) when is_list(Config) -> ?line Dir = filename:join(?config(priv_dir, Config), "wildcard_two"), - ?line DirB = unicode:characters_to_binary(Dir, file:native_name_encoding()), ?line ok = file:make_dir(Dir), ?line do_wildcard_1(Dir, fun(Wc) -> io:format("~p~n",[{Wc,Dir, X = filelib:wildcard(Wc, Dir)}]),X end), - ?line do_wildcard_1(Dir, fun(Wc) -> io:format("~p~n",[{Wc,DirB, X = filelib:wildcard(Wc, DirB)}]), - [unicode:characters_to_list(Y,file:native_name_encoding()) || Y <- X] end), ?line do_wildcard_1(Dir, fun(Wc) -> filelib:wildcard(Wc, Dir++"/") end), case os:type() of {win32,_} -> @@ -130,6 +137,9 @@ do_wildcard_2(Dir, Wcf) -> ?line ["abc","abcdef"] = Wcf("a*{def,}"), ?line ["abc","abcdef"] = Wcf("a*{,def}"), + %% Constant wildcard. + ["abcdef"] = Wcf("abcdef"), + %% Negative tests. ?line [] = Wcf("b*"), ?line [] = Wcf("bufflig"), @@ -157,6 +167,8 @@ do_wildcard_4(Dir, Wcf) -> All = ["a-","aA","aB","aC","a[","a]"], ?line Files = mkfiles(lists:reverse(All), Dir), ?line All = Wcf("a[][A-C-]"), + ["a-"] = Wcf("a[-]"), + ["a["] = Wcf("a["), ?line del(Files), do_wildcard_5(Dir, Wcf). @@ -173,6 +185,7 @@ do_wildcard_5(Dir, Wcf) -> ?line ["blurf/nisse"] = Wcf("*/nisse"), ?line [] = Wcf("mountain/*"), ?line [] = Wcf("xa/gurka"), + ["blurf/nisse"] = Wcf("blurf/nisse"), %% Cleanup ?line del(Files), @@ -233,7 +246,24 @@ do_wildcard_8(Dir, Wcf) -> del(Files), foreach(fun(D) -> ok = file:del_dir(filename:join(Dir, D)) - end, Dirs2 ++ Dirs1 ++ Dirs0). + end, Dirs2 ++ Dirs1 ++ Dirs0), + do_wildcard_9(Dir, Wcf). + +do_wildcard_9(Dir, Wcf) -> + Dirs0 = ["lib","lib/app","lib/app/ebin"], + Dirs = [filename:join(Dir, D) || D <- Dirs0], + [ok = file:make_dir(D) || D <- Dirs], + Files0 = [filename:join("lib/app/ebin", F++".bar") || + F <- ["abc","foo","foobar"]], + Files = [filename:join(Dir, F) || F <- Files0], + [ok = file:write_file(F, <<"some content\n">>) || F <- Files], + Files0 = Wcf("lib/app/ebin/*.bar"), + + %% Cleanup. + del(Files), + [ok = file:del_dir(D) || D <- lists:reverse(Dirs)], + ok. + fold_files(Config) when is_list(Config) -> ?line Dir = filename:join(?config(priv_dir, Config), "fold_files"), diff --git a/lib/stdlib/test/io_SUITE.erl b/lib/stdlib/test/io_SUITE.erl index 4d2b53b265..9f828c6d2d 100644 --- a/lib/stdlib/test/io_SUITE.erl +++ b/lib/stdlib/test/io_SUITE.erl @@ -29,7 +29,11 @@ manpage/1, otp_6708/1, otp_7084/1, otp_7421/1, io_lib_collect_line_3_wb/1, cr_whitespace_in_string/1, io_fread_newlines/1, otp_8989/1, io_lib_fread_literal/1, - io_lib_print_binary_depth_one/1, otp_10302/1]). + printable_range/1, + io_lib_print_binary_depth_one/1, otp_10302/1, otp_10755/1, + otp_10836/1]). + +-export([pretty/2]). %-define(debug, true). @@ -65,7 +69,8 @@ all() -> manpage, otp_6708, otp_7084, otp_7421, io_lib_collect_line_3_wb, cr_whitespace_in_string, io_fread_newlines, otp_8989, io_lib_fread_literal, - io_lib_print_binary_depth_one, otp_10302]. + printable_range, + io_lib_print_binary_depth_one, otp_10302, otp_10755, otp_10836]. groups() -> []. @@ -2025,6 +2030,79 @@ io_lib_fread_literal(Suite) when is_list(Suite) -> ?line {done,{ok,[]},[]} = io_lib:fread(C2, "d\n", " d"), ok. + +printable_range(doc) -> + "Check that the printable range set by the user actually works"; +printable_range(Suite) when is_list(Suite) -> + Pa = filename:dirname(code:which(?MODULE)), + {ok, UNode} = test_server:start_node(printable_range_unicode, slave, + [{args, " +pc unicode -pa " ++ Pa}]), + {ok, LNode} = test_server:start_node(printable_range_latin1, slave, + [{args, " +pc latin1 -pa " ++ Pa}]), + {ok, DNode} = test_server:start_node(printable_range_default, slave, + [{args, " -pa " ++ Pa}]), + unicode = rpc:call(UNode,io,printable_range,[]), + latin1 = rpc:call(LNode,io,printable_range,[]), + latin1 = rpc:call(DNode,io,printable_range,[]), + test_server:stop_node(UNode), + test_server:stop_node(LNode), + {ok, UNode} = test_server:start_node(printable_range_unicode, slave, + [{args, " +pcunicode -pa " ++ Pa}]), + {ok, LNode} = test_server:start_node(printable_range_latin1, slave, + [{args, " +pclatin1 -pa " ++ Pa}]), + unicode = rpc:call(UNode,io,printable_range,[]), + latin1 = rpc:call(LNode,io,printable_range,[]), + {error, _} = test_server:start_node(printable_range_unnicode, slave, + [{args, " +pcunnicode -pa " ++ Pa}]), + PrettyOptions = [{column,1}, + {line_length,109}, + {depth,30}, + {max_chars,60}, + {record_print_fun, + fun(_,_) -> no end}, + {encoding,unicode}], + 1025 = lists:max(lists:flatten(rpc:call(UNode,io_lib_pretty,print, + [{hello, [1024,1025]}, + PrettyOptions]))), + 125 = lists:max(lists:flatten(rpc:call(LNode,io_lib_pretty,print, + [{hello, [1024,1025]}, + PrettyOptions]))), + 125 = lists:max(lists:flatten(rpc:call(DNode,io_lib_pretty,print, + [{hello, [1024,1025]}, + PrettyOptions]))), + 1025 = lists:max(lists:flatten(rpc:call(UNode,io_lib_pretty,print, + [{hello, <<1024/utf8,1025/utf8>>}, + PrettyOptions]))), + 125 = lists:max(lists:flatten(rpc:call(LNode,io_lib_pretty,print, + [{hello, <<1024/utf8,1025/utf8>>}, + PrettyOptions]))), + 125 = lists:max(lists:flatten(rpc:call(DNode,io_lib_pretty,print, + [{hello, <<1024/utf8,1025/utf8>>}, + PrettyOptions]))), + + 1025 = lists:max(lists:flatten(rpc:call(UNode,io_lib,format, + ["~tp",[{hello, [1024,1025]}]]))), + 125 = lists:max(lists:flatten(rpc:call(LNode,io_lib,format, + ["~tp",[{hello, [1024,1025]}]]))), + 125 = lists:max(lists:flatten(rpc:call(DNode,io_lib,format, + ["~tp",[{hello, [1024,1025]}]]))), + 1025 = lists:max(lists:flatten(rpc:call(UNode,io_lib,format, + ["~tp", + [{hello, + <<1024/utf8,1025/utf8>>}]]))), + 125 = lists:max(lists:flatten(rpc:call(LNode,io_lib,format, + ["~tp", + [{hello, + <<1024/utf8,1025/utf8>>}]]))), + 125 = lists:max(lists:flatten(rpc:call(DNode,io_lib,format, + ["~tp", + [{hello, + <<1024/utf8,1025/utf8>>}]]))), + test_server:stop_node(UNode), + test_server:stop_node(LNode), + test_server:stop_node(DNode), + ok. + io_lib_print_binary_depth_one(doc) -> "Test binaries printed with a depth of one behave correctly"; io_lib_print_binary_depth_one(Suite) when is_list(Suite) -> @@ -2039,16 +2117,32 @@ io_lib_print_binary_depth_one(Suite) when is_list(Suite) -> otp_10302(doc) -> "OTP-10302. Unicode"; otp_10302(Suite) when is_list(Suite) -> - "\"\x{400}\"" = pretty("\x{400}", -1), - "<<\"\x{400}\"/utf8>>" = pretty(<<"\x{400}"/utf8>>, -1), + Pa = filename:dirname(code:which(?MODULE)), + {ok, UNode} = test_server:start_node(printable_range_unicode, slave, + [{args, " +pc unicode -pa " ++ Pa}]), + {ok, LNode} = test_server:start_node(printable_range_latin1, slave, + [{args, " +pc latin1 -pa " ++ Pa}]), + "\"\x{400}\"" = rpc:call(UNode,?MODULE,pretty,["\x{400}", -1]), + "<<\"\x{400}\"/utf8>>" = rpc:call(UNode,?MODULE,pretty, + [<<"\x{400}"/utf8>>, -1]), + + "<<\"\x{400}foo\"/utf8>>" = rpc:call(UNode,?MODULE,pretty, + [<<"\x{400}foo"/utf8>>, 2]), + "[1024]" = rpc:call(LNode,?MODULE,pretty,["\x{400}", -1]), + "<<208,128>>" = rpc:call(LNode,?MODULE,pretty,[<<"\x{400}"/utf8>>, -1]), + + "<<208,...>>" = rpc:call(LNode,?MODULE,pretty,[<<"\x{400}foo"/utf8>>, 2]), + test_server:stop_node(UNode), + test_server:stop_node(LNode), - "<<\"\x{400}foo\"/utf8>>" = pretty(<<"\x{400}foo"/utf8>>, 2), "<<\"äppl\"/utf8>>" = pretty(<<"äppl"/utf8>>, 2), "<<\"äppl\"/utf8...>>" = pretty(<<"äpple"/utf8>>, 2), "<<\"apel\">>" = pretty(<<"apel">>, 2), "<<\"apel\"...>>" = pretty(<<"apelsin">>, 2), - "<<228,112,112,108>>" = fmt("~tp", [<<"äppl">>]), - "<<228,...>>" = fmt("~tP", [<<"äppl">>, 2]), + "<<\"äppl\">>" = fmt("~tp", [<<"äppl">>]), + "<<\"äppl\"...>>" = fmt("~tP", [<<"äpple">>, 2]), + "<<0,0,0,0,0,0,1,0>>" = fmt("~p", [<<256:64/unsigned-integer>>]), + "<<0,0,0,0,0,0,1,0>>" = fmt("~tp", [<<256:64/unsigned-integer>>]), Chars = lists:seq(0, 512), % just a few... [] = [C || C <- Chars, S <- io_lib:write_char_as_latin1(C), @@ -2076,3 +2170,47 @@ pretty(Term, Opts) when is_list(Opts) -> is_latin1(S) -> S >= 0 andalso S =< 255. + +otp_10836(doc) -> + "OTP-10836. ~ts extended to latin1"; +otp_10836(Suite) when is_list(Suite) -> + S = io_lib:format("~ts", [[<<"äpple"/utf8>>, <<"äpple">>]]), + "äppleäpple" = lists:flatten(S), + ok. + +otp_10755(doc) -> + "OTP-10755. The 'l' modifier"; +otp_10755(Suite) when is_list(Suite) -> + S = "string", + "\"string\"" = fmt("~p", [S]), + "[115,116,114,105,110,103]" = fmt("~lp", [S]), + "\"string\"" = fmt("~P", [S, 2]), + "[115|...]" = fmt("~lP", [S, 2]), + {'EXIT',{badarg,_}} = (catch fmt("~ltp", [S])), + {'EXIT',{badarg,_}} = (catch fmt("~tlp", [S])), + {'EXIT',{badarg,_}} = (catch fmt("~ltP", [S])), + {'EXIT',{badarg,_}} = (catch fmt("~tlP", [S])), + Text = + "-module(l_mod).\n" + "-export([t/0]).\n" + "t() ->\n" + " S = \"string\",\n" + " io:format(\"~ltp\", [S]),\n" + " io:format(\"~tlp\", [S]),\n" + " io:format(\"~ltP\", [S, 1]),\n" + " io:format(\"~tlP\", [S, 1]).\n", + {ok,l_mod,[{_File,Ws}]} = compile_file("l_mod.erl", Text, Suite), + ["format string invalid (invalid control ~lt)", + "format string invalid (invalid control ~tl)", + "format string invalid (invalid control ~lt)", + "format string invalid (invalid control ~tl)"] = + [lists:flatten(M:format_error(E)) || {_L,M,E} <- Ws], + ok. + +compile_file(File, Text, Config) -> + PrivDir = ?privdir(Config), + Fname = filename:join(PrivDir, File), + ok = file:write_file(Fname, Text), + try compile:file(Fname, [return]) + after ok %file:delete(Fname) + end. diff --git a/lib/stdlib/test/io_proto_SUITE.erl b/lib/stdlib/test/io_proto_SUITE.erl index 299daf0e42..ddcc8dfdab 100644 --- a/lib/stdlib/test/io_proto_SUITE.erl +++ b/lib/stdlib/test/io_proto_SUITE.erl @@ -716,7 +716,7 @@ binary_options(Config) when is_list(Config) -> {getline, "<<\"hej\\n\">>"}, {putline, "io:get_line('')."}, {putline, binary_to_list(<<"\345\344\366"/utf8>>)}, - {getline, "<<\""++binary_to_list(unicode:characters_to_binary(<<"\345\344\366"/utf8>>,latin1,utf8))++"\\n\">>"} + {getline, "<<\""++binary_to_list(<<"\345\344\366"/utf8>>)++"\\n\"/utf8>>"} ],[]) end, %% And one with oldshell @@ -1784,8 +1784,8 @@ get_default_shell() -> {putline, "whereis(user_drv)."}, {getline, "undefined"}],[]), old - catch E:R -> - ?dbg({E,R}), + catch _E:_R -> + ?dbg({_E,_R}), new end. diff --git a/lib/stdlib/test/shell_SUITE.erl b/lib/stdlib/test/shell_SUITE.erl index f22df96697..990b1f5eb2 100644 --- a/lib/stdlib/test/shell_SUITE.erl +++ b/lib/stdlib/test/shell_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2004-2012. All Rights Reserved. +%% Copyright Ericsson AB 2004-2013. All Rights Reserved. %% %% The contents of this file are subject to the Erlang Public License, %% Version 1.1, (the "License"); you may not use this file except in @@ -2742,6 +2742,9 @@ otp_10302(doc) -> "OTP-10302. Unicode."; otp_10302(suite) -> []; otp_10302(Config) when is_list(Config) -> + {ok,Node} = start_node(shell_suite_helper_2, + "-pa "++?config(priv_dir,Config)++ + " +pc unicode"), Test1 = <<"begin io:setopts([{encoding,utf8}]), @@ -2749,13 +2752,13 @@ otp_10302(Config) when is_list(Config) -> rd(rec, {a = \"\\x{400}\"}), ok = rl(rec) end.">>, - "-record(rec,{a = \"\x{400}\"}).\nok.\n" = t(Test1), + "-record(rec,{a = \"\x{400}\"}).\nok.\n" = t({Node,Test1}), Test3 = <<"io:setopts([{encoding,utf8}]). rd(rec, {a = \"\\x{400}\"}). ok = rp(#rec{}).">>, - "ok.\nrec\n#rec{a = \"\x{400}\"}.\nok.\n" = t(Test3), + "ok.\nrec\n#rec{a = \"\x{400}\"}.\nok.\n" = t({Node,Test3}), Test4 = <<"io:setopts([{encoding,utf8}]). @@ -2766,7 +2769,7 @@ otp_10302(Config) when is_list(Config) -> "ok.\n\"\x{400}\"\nA = \"\x{400}\".\nok.\n" "1: io:setopts([{encoding,utf8}])\n-> ok.\n" "2: A = [1024] = \"\x{400}\"\n-> \"\x{400}\"\n" - "3: b()\n-> ok.\nok.\n" = t(Test4), + "3: b()\n-> ok.\nok.\n" = t({Node,Test4}), Test5 = <<"begin @@ -2776,18 +2779,20 @@ otp_10302(Config) when is_list(Config) -> b(), h() end.">>, - "A = \"\x{400}\".\nok.\n" = t(Test5), + "A = \"\x{400}\".\nok.\n" = t({Node,Test5}), %% One $" is "lost": true = "\x{400}\": command not found" =:= - prompt_err({<<"io:setopts([{encoding,utf8}]). v(\"\x{400}\")."/utf8>>, + prompt_err({Node, + <<"io:setopts([{encoding,utf8}]). v(\"\x{400}\")."/utf8>>, unicode}), "ok.\ndefault\n* Bad prompt function: \"\x{400}\".\n" = - t({<<"io:setopts([{encoding,utf8}]). " + t({Node,<<"io:setopts([{encoding,utf8}]). " "shell:prompt_func(\"\x{400}\")."/utf8>>, unicode}), + rpc:call(Node,shell, prompt_func, [default]), _ = shell:prompt_func(default), %% Test lib:format_exception() (cf. OTP-6554) @@ -2812,10 +2817,10 @@ otp_10302(Config) when is_list(Config) -> {ok, Es} = erl_parse:parse_exprs(Ts), B = erl_eval:new_bindings(), erl_eval:exprs(Es, B).">>, - + "ok.\n** exception error: an error occurred when evaluating" " an arithmetic expression\n in operator '/'/2\n" - " called as <<170>> / <<170>>.\n" = t(Test7), + " called as <<\"�\">> / <<\"�\">>.\n" = t({Node,Test7}), Test8 = <<"begin A = [1089], @@ -2839,7 +2844,7 @@ otp_10302(Config) when is_list(Config) -> "ok.\n** exception error: an error occurred when evaluating" " an arithmetic expression\n in operator '/'/2\n" - " called as \"\x{441}\" / \"\x{441}\".\n" = t(Test9), + " called as \"\x{441}\" / \"\x{441}\".\n" = t({Node,Test9}), Test10 = <<"A = {\"1\\xaa\", $\\xaa, @@ -2861,7 +2866,7 @@ otp_10302(Config) when is_list(Config) -> "ok.\n** exception error: no function clause matching \n" " erl_eval:'-inside-an-interpreted-fun-'" "({\"1\xaa\",170,<<\"hi\">>,\n " - " <<\"1\xaa\"/utf8>>}) .\n" = t(Test11), + " <<\"1\xaa\"/utf8>>}) .\n" = t({Node,Test11}), Test12 = <<"fun(a, b) -> false end(65, [1089]).">>, "** exception error: no function clause matching \n" " erl_eval:'-inside-an-interpreted-fun-'(65,[1089])" @@ -2871,8 +2876,9 @@ otp_10302(Config) when is_list(Config) -> fun(a, b) -> false end(65, [1089]).">>, "ok.\n** exception error: no function clause matching \n" " erl_eval:'-inside-an-interpreted-fun-'(65,\"\x{441}\")" - " .\n" = t(Test13), + " .\n" = t({Node,Test13}), + test_server:stop_node(Node), ok. scan(B) -> @@ -2895,6 +2901,8 @@ scan(S0, F) -> [] end. +t({Node,Bin,Enc}) when is_atom(Node),is_binary(Bin), is_atom(Enc) -> + t0({Bin,Enc}, fun() -> start_new_shell(Node) end); t({Node,Bin}) when is_atom(Node),is_binary(Bin) -> t0({Bin,latin1}, fun() -> start_new_shell(Node) end); t(Bin) when is_binary(Bin) -> |