diff options
Diffstat (limited to 'lib/stdlib')
| -rw-r--r-- | lib/stdlib/doc/src/filelib.xml | 2 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/notes.xml | 18 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/unicode_usage.xml | 12 | ||||
| -rw-r--r-- | lib/stdlib/src/base64.erl | 113 | ||||
| -rw-r--r-- | lib/stdlib/src/escript.erl | 4 | ||||
| -rw-r--r-- | lib/stdlib/src/filename.erl | 14 | ||||
| -rw-r--r-- | lib/stdlib/src/io.erl | 20 | ||||
| -rw-r--r-- | lib/stdlib/src/re.erl | 42 | ||||
| -rw-r--r-- | lib/stdlib/test/base64_SUITE.erl | 89 | ||||
| -rw-r--r-- | lib/stdlib/test/erl_eval_SUITE.erl | 16 | ||||
| -rw-r--r-- | lib/stdlib/test/ets_SUITE.erl | 18 |
11 files changed, 251 insertions, 97 deletions
diff --git a/lib/stdlib/doc/src/filelib.xml b/lib/stdlib/doc/src/filelib.xml index 969aff4fcb..47d64f245c 100644 --- a/lib/stdlib/doc/src/filelib.xml +++ b/lib/stdlib/doc/src/filelib.xml @@ -105,7 +105,7 @@ dirname() = filename()</code> interpreted as Unicode may be encountered, in which case the <c>fun()</c> must be prepared to handle raw file names (i.e. binaries). If the regular expression contains - codepoints beyond 255, it will not match file names that does + codepoints beyond 255, it will not match file names that do not conform to the expected character encoding (i.e. are not encoded in valid UTF-8).</p> diff --git a/lib/stdlib/doc/src/notes.xml b/lib/stdlib/doc/src/notes.xml index 940044d0a8..a8fe41f000 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -30,6 +30,24 @@ </header> <p>This document describes the changes made to the STDLIB application.</p> +<section><title>STDLIB 1.17.2.1</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> + Several type specifications for standard libraries were + wrong in the R14B01 release. This is now corrected. The + corrections concern types in re,io,filename and the + module erlang itself.</p> + <p> + Own Id: OTP-9008</p> + </item> + </list> + </section> + +</section> + <section><title>STDLIB 1.17.2</title> <section><title>Fixed Bugs and Malfunctions</title> diff --git a/lib/stdlib/doc/src/unicode_usage.xml b/lib/stdlib/doc/src/unicode_usage.xml index c02ea3cbcb..416df1f02c 100644 --- a/lib/stdlib/doc/src/unicode_usage.xml +++ b/lib/stdlib/doc/src/unicode_usage.xml @@ -173,19 +173,19 @@ Eshell V5.7 (abort with ^G) <taglist> <tag>Mandatory Unicode file naming</tag> <item> -<p>Windows and, for most common uses, MacOSX enforces Unicode support for file names. All files created in the filesystem has names that can consistently be interpreted. In MacOSX, all file names are retrieved in UTF-8 encoding, while Windows have selected an approach where each system call handling file names has a special Unicode aware variant, giving much the same effect. There are no file names on these systems that are not Unicode file names, why the default behavior of the Erlang VM is to work in "Unicode file name translation mode", meaning that a file name can be given as a Unicode list and that will be automatically translated to the proper name encoding for the underlying operating and file system.</p> +<p>Windows and, for most common uses, MacOSX enforces Unicode support for file names. All files created in the filesystem have names that can consistently be interpreted. In MacOSX, all file names are retrieved in UTF-8 encoding, while Windows has selected an approach where each system call handling file names has a special Unicode aware variant, giving much the same effect. There are no file names on these systems that are not Unicode file names, why the default behavior of the Erlang VM is to work in "Unicode file name translation mode", meaning that a file name can be given as a Unicode list and that will be automatically translated to the proper name encoding for the underlying operating and file system.</p> <p>Doing i.e. a <c>file:list_dir/1</c> on one of these systems may return Unicode lists with codepoints beyond 255, depending on the content of the actual filesystem.</p> <p>As the feature is fairly new, you may still stumble upon non core applications that cannot handle being provided with file names containing characters with codepoints larger than 255, but the core Erlang system should have no problems with Unicode file names.</p> </item> <tag>Transparent file naming</tag> <item> <p>Most Unix operating systems have adopted a simpler approach, namely that Unicode file naming is not enforced, but by convention. Those systems usually use UTF-8 encoding for Unicode file names, but do not enforce it. On such a system, a file name containing characters having codepoints between 128 and 255 may be named either as plain ISO-latin-1 or using UTF-8 encoding. As no consistency is enforced, the Erlang VM can do no consistent translation of all file names. If the VM would automatically select encoding based on heuristics, one could get unexpected behavior on these systems, therefore file names not being encoded in UTF-8 are returned as "raw file names" if Unicode file naming support is turned on.</p> -<p>A raw file name is not a list, but a binary. Many non core applications still does not handle file names given as binaries, why such raw names are avoided by default. This means that systems having implemented Unicode file naming through transparent file systems and an UTF-8 convention, does not by default have Unicode file naming turned on. Explicitly turning Unicode file name handling on for these types of systems is considered experimental.</p> +<p>A raw file name is not a list, but a binary. Many non core applications still do not handle file names given as binaries, why such raw names are avoided by default. This means that systems having implemented Unicode file naming through transparent file systems and an UTF-8 convention, do not by default have Unicode file naming turned on. Explicitly turning Unicode file name handling on for these types of systems is considered experimental.</p> </item> </taglist> <p>The Unicode file naming support was introduced with OTP release R14B01. A VM operating in Unicode file mode can work with files having names in any language or character set (as long as it's supported by the underlying OS and file system). The Unicode character list is used to denote file or directory names and if the file system content is listed, you will also be able to get Unicode lists as return value. The support lies in the kernel and stdlib modules, why most applications (that does not explicitly require the file names to be in the ISO-latin-1 range) will benefit from the Unicode support without change.</p> -<p>On Operating systems with mandatory Unicode file names, this means that you more easily conform to the file names of other (non Erlang) applications, and you can also process file names that, at least on Windows, where completely inaccessible (due to having names that could not be represented in ISO-latin-1). Also you will avoid creating incomprehensible file names on MacOSX as the vfs layer of the OS will accept all your file names as UTF-8 and will not rewrite them.</p> +<p>On Operating systems with mandatory Unicode file names, this means that you more easily conform to the file names of other (non Erlang) applications, and you can also process file names that, at least on Windows, were completely inaccessible (due to having names that could not be represented in ISO-latin-1). Also you will avoid creating incomprehensible file names on MacOSX as the vfs layer of the OS will accept all your file names as UTF-8 and will not rewrite them.</p> <p>For most systems, turning on Unicode file name translation is no problem even if it uses transparent file naming. Very few systems have mixed file name encodings. A consistent UTF-8 named system will work perfectly in Unicode file name mode. It is still however considered experimental in R14B01. Unicode file name translation is turned on with the <c>+fnu</c> switch to the <c>erl</c> program. If the VM is started in Unicode file name translation mode, <c>file:native_name_encoding/0</c> will return the atom <c>utf8</c>.</p> @@ -197,10 +197,10 @@ Eshell V5.7 (abort with ^G) <section> <title>Notes about raw file names and automatic file name conversion</title> -<p>Raw file names is introduced together with Unicode file name support in erts-5.8.2 (OTP R14B01). The reason the "raw file names" is introduced in the system is to be able to consistently represent file names given in different encodings on the same system. Having the VM automatically translate a file name that is not in UTF-8 when to a list of Unicode characters might seem practical, but this would open up for both duplicate file names and other inconsistent behavior. Consider a directory containing a file named "bj�rn" in ISO-latin-1, while the Erlang VM is operating in Unicode file name mode (and therefore expecting UTF-8 file naming). The ISO-latin-1 name is not valid UTF-8 and one could be tempted to think that automatic conversion in for example <c>file:list_dir/1</c> is a good idea. But what would happen if we later tried to open the file and has the name as a Unicode list (magically converted from the ISO-latin-1 file name)? The VM will convert the file name given to UTF-8, as this is the encoding expected. Effectively this means trying to open the file named <<"bj�rn"/utf8>>. This file does not exist, and even if it existed it would not be the same file as the one that was listed. We could even create two files named "bj�rn", one named in the UTF-8 encoding and one not. If <c>file:list_dir/1</c> would automatically convert the ISO-latin-1 file name to a list, we would get two identical file names as the result. To avoid this, we need to differentiate between file names being properly encoded according to the Unicode file naming convention (i.e. UTF-8) and file names being invalid under the encoding. This is done by representing invalid encoding as "raw" file names, i.e. as binaries.</p> -<p>The core system of Erlang (kernel and stdlib) accept raw file names except for loadable drivers and executables invoked using <c>open_port({spawn, ...} ...)</c>. <c>open_port({spawn_executable, ...} ...)</c> however does accept them. As mentioned earlier, the arguments given in the option list to <c>open_port({spawn_executable, ...} ...)</c> undergo the same conversion as the file names, meaning that the executable will be provided with arguments in UTF-8 as well. This translation is avoided consistently with how the file names are treated, by giving the argument as a binary.</p> +<p>Raw file names is introduced together with Unicode file name support in erts-5.8.2 (OTP R14B01). The reason "raw file names" is introduced in the system is to be able to consistently represent file names given in different encodings on the same system. Having the VM automatically translate a file name that is not in UTF-8 to a list of Unicode characters might seem practical, but this would open up for both duplicate file names and other inconsistent behavior. Consider a directory containing a file named "bj�rn" in ISO-latin-1, while the Erlang VM is operating in Unicode file name mode (and therefore expecting UTF-8 file naming). The ISO-latin-1 name is not valid UTF-8 and one could be tempted to think that automatic conversion in for example <c>file:list_dir/1</c> is a good idea. But what would happen if we later tried to open the file and have the name as a Unicode list (magically converted from the ISO-latin-1 file name)? The VM will convert the file name given to UTF-8, as this is the encoding expected. Effectively this means trying to open the file named <<"bj�rn"/utf8>>. This file does not exist, and even if it existed it would not be the same file as the one that was listed. We could even create two files named "bj�rn", one named in the UTF-8 encoding and one not. If <c>file:list_dir/1</c> would automatically convert the ISO-latin-1 file name to a list, we would get two identical file names as the result. To avoid this, we need to differentiate between file names being properly encoded according to the Unicode file naming convention (i.e. UTF-8) and file names being invalid under the encoding. This is done by representing invalid encoding as "raw" file names, i.e. as binaries.</p> +<p>The core system of Erlang (kernel and stdlib) accepts raw file names except for loadable drivers and executables invoked using <c>open_port({spawn, ...} ...)</c>. <c>open_port({spawn_executable, ...} ...)</c> however does accept them. As mentioned earlier, the arguments given in the option list to <c>open_port({spawn_executable, ...} ...)</c> undergo the same conversion as the file names, meaning that the executable will be provided with arguments in UTF-8 as well. This translation is avoided consistently with how the file names are treated, by giving the argument as a binary.</p> <p>To force Unicode file name translation mode on systems where this is not the default is considered experimental in OTP R14B01 due to the raw file names possibly being a new experience to the programmer and that the non core applications of OTP are not tested for compliance with raw file names yet. Unicode file name translation is expected to be default in future releases.</p> -<p>If working with raw file names, one can still conform to the encoding convention of the Erlang VM by using the <c>file:native_name_encoding/0</c> function, which returns either the atom <c>latin1</c> or the atom <c>utf8</c> depending on the file name translation mode. On Linux, an VM started without explicitly stating the file name translation mode will default to <c>latin1</c> as the native file name encoding, why file names on the disk encoded as UTF-8 will be returned as a list of the names interpreted as ISO-latin-1. The "UTF-8 list" is not a practical type for displaying or operating on in Erlang, but it is backward compatible and usable in all functions requiring a file name. On Windows and MacOSX, the default behavior is that of file name translation, why the <c>file:native_name_encoding/0</c> by default returns <c>utf8</c> on those systems (the fact that Windows actually does not use UTF-8 on the file system level can safely be ignored by the Erlang programmer). The default behavior can be changed using the <c>+fnu</c> or <c>+fnl</c> options to the VM, see the <c>erl</c> command manual page.</p> +<p>If working with raw file names, one can still conform to the encoding convention of the Erlang VM by using the <c>file:native_name_encoding/0</c> function, which returns either the atom <c>latin1</c> or the atom <c>utf8</c> depending on the file name translation mode. On Linux, a VM started without explicitly stating the file name translation mode will default to <c>latin1</c> as the native file name encoding, why file names on the disk encoded as UTF-8 will be returned as a list of the names interpreted as ISO-latin-1. The "UTF-8 list" is not a practical type for displaying or operating on in Erlang, but it is backward compatible and usable in all functions requiring a file name. On Windows and MacOSX, the default behavior is that of file name translation, why the <c>file:native_name_encoding/0</c> by default returns <c>utf8</c> on those systems (the fact that Windows actually does not use UTF-8 on the file system level can safely be ignored by the Erlang programmer). The default behavior can be changed using the <c>+fnu</c> or <c>+fnl</c> options to the VM, see the <c>erl</c> command manual page.</p> <p>Even if you are operating without Unicode file naming translation automatically done by the VM, you can access and create files with names in UTF-8 encoding by using raw file names encoded as UTF-8. Enforcing the UTF-8 encoding regardless of the mode the Erlang VM is started in might, in some circumstances be a good idea, as the convention of using UTF-8 file names is spreading.</p> </section> <section> diff --git a/lib/stdlib/src/base64.erl b/lib/stdlib/src/base64.erl index ebef998ee1..a14a72ac6d 100644 --- a/lib/stdlib/src/base64.erl +++ b/lib/stdlib/src/base64.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2007-2009. All Rights Reserved. +%% Copyright Ericsson AB 2007-2011. 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 @@ -114,7 +114,7 @@ decode(List) when is_list(List) -> mime_decode(Bin) when is_binary(Bin) -> mime_decode_binary(<<>>, Bin); mime_decode(List) when is_list(List) -> - list_to_binary(mime_decode_l(List)). + mime_decode(list_to_binary(List)). -spec decode_l(string()) -> string(). @@ -125,7 +125,7 @@ decode_l(List) -> -spec mime_decode_l(string()) -> string(). mime_decode_l(List) -> - L = strip_illegal(List, []), + L = strip_illegal(List, [], 0), decode(L, []). %%------------------------------------------------------------------------- @@ -198,6 +198,9 @@ decode_binary(Result, <<>>) -> true = is_binary(Result), Result. +%% Skipping pad character if not at end of string. Also liberal about +%% excess padding and skipping of other illegal (non-base64 alphabet) +%% characters. See section 3.3 of RFC4648 mime_decode_binary(Result, <<0:8,T/bits>>) -> mime_decode_binary(Result, T); mime_decode_binary(Result0, <<C:8,T/bits>>) -> @@ -205,15 +208,27 @@ mime_decode_binary(Result0, <<C:8,T/bits>>) -> Bits when is_integer(Bits) -> mime_decode_binary(<<Result0/bits,Bits:6>>, T); eq -> - case tail_contains_equal(T) of - true -> - Split = byte_size(Result0) - 1, - <<Result:Split/bytes,_:4>> = Result0, - Result; - false -> - Split = byte_size(Result0) - 1, - <<Result:Split/bytes,_:2>> = Result0, - Result + case tail_contains_more(T, false) of + {<<>>, Eq} -> + %% No more valid data. + case bit_size(Result0) rem 8 of + 0 -> + %% '====' is not uncommon. + Result0; + 4 when Eq -> + %% enforce at least one more '=' only ignoring illegals and spacing + Split = byte_size(Result0) - 1, + <<Result:Split/bytes,_:4>> = Result0, + Result; + 2 -> + %% remove 2 bits + Split = byte_size(Result0) - 1, + <<Result:Split/bytes,_:2>> = Result0, + Result + end; + {More, _} -> + %% More valid data, skip the eq as invalid + mime_decode_binary(Result0, More) end; _ -> mime_decode_binary(Result0, T) @@ -262,31 +277,63 @@ strip_ws(<<$\s,T/binary>>) -> strip_ws(T); strip_ws(T) -> T. -strip_illegal([0|Cs], A) -> - strip_illegal(Cs, A); -strip_illegal([C|Cs], A) -> +%% Skipping pad character if not at end of string. Also liberal about +%% excess padding and skipping of other illegal (non-base64 alphabet) +%% characters. See section 3.3 of RFC4648 +strip_illegal([], A, _Cnt) -> + A; +strip_illegal([0|Cs], A, Cnt) -> + strip_illegal(Cs, A, Cnt); +strip_illegal([C|Cs], A, Cnt) -> case element(C, ?DECODE_MAP) of - bad -> strip_illegal(Cs, A); - ws -> strip_illegal(Cs, A); - eq -> strip_illegal_end(Cs, [$=|A]); - _ -> strip_illegal(Cs, [C|A]) - end; -strip_illegal([], A) -> A. + bad -> + strip_illegal(Cs, A, Cnt); + ws -> + strip_illegal(Cs, A, Cnt); + eq -> + case {tail_contains_more(Cs, false), Cnt rem 4} of + {{[], _}, 0} -> + A; %% Ignore extra = + {{[], true}, 2} -> + [$=|[$=|A]]; %% 'XX==' + {{[], _}, 3} -> + [$=|A]; %% 'XXX=' + {{[H|T], _}, _} -> + %% more data, skip equals + strip_illegal(T, [H|A], Cnt+1) + end; + _ -> + strip_illegal(Cs, [C|A], Cnt+1) + end. -strip_illegal_end([0|Cs], A) -> - strip_illegal_end(Cs, A); -strip_illegal_end([C|Cs], A) -> +%% Search the tail for more valid data and remember if we saw +%% another equals along the way. +tail_contains_more([], Eq) -> + {[], Eq}; +tail_contains_more(<<>>, Eq) -> + {<<>>, Eq}; +tail_contains_more([C|T]=More, Eq) -> case element(C, ?DECODE_MAP) of - bad -> strip_illegal(Cs, A); - ws -> strip_illegal(Cs, A); - eq -> [C|A]; - _ -> strip_illegal(Cs, [C|A]) + bad -> + tail_contains_more(T, Eq); + ws -> + tail_contains_more(T, Eq); + eq -> + tail_contains_more(T, true); + _ -> + {More, Eq} end; -strip_illegal_end([], A) -> A. - -tail_contains_equal(<<$=,_/binary>>) -> true; -tail_contains_equal(<<_,T/binary>>) -> tail_contains_equal(T); -tail_contains_equal(<<>>) -> false. +tail_contains_more(<<C:8,T/bits>> =More, Eq) -> + case element(C, ?DECODE_MAP) of + bad -> + tail_contains_more(T, Eq); + ws -> + tail_contains_more(T, Eq); + eq -> + tail_contains_more(T, true); + _ -> + {More, Eq} + end. %% accessors b64e(X) -> diff --git a/lib/stdlib/src/escript.erl b/lib/stdlib/src/escript.erl index 99e454f593..7cb02afb11 100644 --- a/lib/stdlib/src/escript.erl +++ b/lib/stdlib/src/escript.erl @@ -570,9 +570,7 @@ parse_beam(S, File, HeaderSz, CheckOnly) -> forms_or_bin = Bin} end; {error, beam_lib, Reason} when is_tuple(Reason) -> - fatal(element(1, Reason)); - {error, beam_lib, Reason} -> - fatal(Reason) + fatal(element(1, Reason)) end. parse_source(S, File, Fd, StartLine, HeaderSz, CheckOnly) -> diff --git a/lib/stdlib/src/filename.erl b/lib/stdlib/src/filename.erl index e38b8957f2..24abf1e977 100644 --- a/lib/stdlib/src/filename.erl +++ b/lib/stdlib/src/filename.erl @@ -165,8 +165,6 @@ basename1([$/|[]], Tail, DirSep2) -> basename1([], Tail, DirSep2); basename1([$/|Rest], _Tail, DirSep2) -> basename1(Rest, [], DirSep2); -basename1([[_|_]=List|Rest], Tail, DirSep2) -> - basename1(List++Rest, Tail, DirSep2); basename1([DirSep2|Rest], Tail, DirSep2) when is_integer(DirSep2) -> basename1([$/|Rest], Tail, DirSep2); basename1([Char|Rest], Tail, DirSep2) when is_integer(Char) -> @@ -280,8 +278,6 @@ dirname(Name0) -> Name = flatten(Name0), dirname(Name, [], [], separators()). -dirname([[_|_]=List|Rest], Dir, File, Seps) -> - dirname(List++Rest, Dir, File, Seps); dirname([$/|Rest], Dir, File, Seps) -> dirname(Rest, File++Dir, [$/], Seps); dirname([DirSep|Rest], Dir, File, {DirSep,_}=Seps) when is_integer(DirSep) -> @@ -346,8 +342,6 @@ extension(Name) when is_binary(Name) -> [] end, case binary:matches(Name,[<<".">>]) of - nomatch -> % Bug in binary workaround :( - <<>>; [] -> <<>>; List -> @@ -479,6 +473,12 @@ maybe_remove_dirsep(Name, _) -> %% by a previous call to join/{1,2}. -spec append(file:filename(), file:name()) -> file:filename(). +append(Dir, Name) when is_binary(Dir), is_binary(Name) -> + <<Dir/binary,$/:8,Name/binary>>; +append(Dir, Name) when is_binary(Dir) -> + append(Dir,filename_string_to_binary(Name)); +append(Dir, Name) when is_binary(Name) -> + append(filename_string_to_binary(Dir),Name); append(Dir, Name) -> Dir ++ [$/|Name]. @@ -685,8 +685,6 @@ split([$/|Rest], Comp, Components, OsType) -> split(Rest, [], [lists:reverse(Comp)|Components], OsType); split([Char|Rest], Comp, Components, OsType) when is_integer(Char) -> split(Rest, [Char|Comp], Components, OsType); -split([List|Rest], Comp, Components, OsType) when is_list(List) -> - split(List++Rest, Comp, Components, OsType); split([], [], Components, _OsType) -> lists:reverse(Components); split([], Comp, Components, OsType) -> diff --git a/lib/stdlib/src/io.erl b/lib/stdlib/src/io.erl index 1d0f9374bc..78412ab2bc 100644 --- a/lib/stdlib/src/io.erl +++ b/lib/stdlib/src/io.erl @@ -39,6 +39,8 @@ -type device() :: atom() | pid(). -type prompt() :: atom() | string(). +-type error_description() :: term(). % Whatever the io-server sends. +-type request_error() :: {'error',error_description()}. %% XXX: Some uses of line() in this file may need to read erl_scan:location() -type line() :: pos_integer(). @@ -299,32 +301,32 @@ format(Io, Format, Args) -> %% Scanning Erlang code. --spec scan_erl_exprs(prompt()) -> erl_scan:tokens_result(). +-spec scan_erl_exprs(prompt()) -> erl_scan:tokens_result() | request_error(). scan_erl_exprs(Prompt) -> scan_erl_exprs(default_input(), Prompt, 1). --spec scan_erl_exprs(device(), prompt()) -> erl_scan:tokens_result(). +-spec scan_erl_exprs(device(), prompt()) -> erl_scan:tokens_result() | request_error(). scan_erl_exprs(Io, Prompt) -> scan_erl_exprs(Io, Prompt, 1). --spec scan_erl_exprs(device(), prompt(), line()) -> erl_scan:tokens_result(). +-spec scan_erl_exprs(device(), prompt(), line()) -> erl_scan:tokens_result() | request_error(). scan_erl_exprs(Io, Prompt, Pos0) -> request(Io, {get_until,unicode,Prompt,erl_scan,tokens,[Pos0]}). --spec scan_erl_form(prompt()) -> erl_scan:tokens_result(). +-spec scan_erl_form(prompt()) -> erl_scan:tokens_result() | request_error(). scan_erl_form(Prompt) -> scan_erl_form(default_input(), Prompt, 1). --spec scan_erl_form(device(), prompt()) -> erl_scan:tokens_result(). +-spec scan_erl_form(device(), prompt()) -> erl_scan:tokens_result() | request_error(). scan_erl_form(Io, Prompt) -> scan_erl_form(Io, Prompt, 1). --spec scan_erl_form(device(), prompt(), line()) -> erl_scan:tokens_result(). +-spec scan_erl_form(device(), prompt(), line()) -> erl_scan:tokens_result() | request_error(). scan_erl_form(Io, Prompt, Pos0) -> request(Io, {get_until,unicode,Prompt,erl_scan,tokens,[Pos0]}). @@ -335,7 +337,8 @@ scan_erl_form(Io, Prompt, Pos0) -> -type parse_ret() :: {'ok', erl_parse_expr_list(), line()} | {'eof', line()} - | {'error', erl_scan:error_info(), line()}. + | {'error', erl_scan:error_info(), line()} + | request_error(). -spec parse_erl_exprs(prompt()) -> parse_ret(). @@ -364,7 +367,8 @@ parse_erl_exprs(Io, Prompt, Pos0) -> -type parse_form_ret() :: {'ok', erl_parse_absform(), line()} | {'eof', line()} - | {'error', erl_scan:error_info(), line()}. + | {'error', erl_scan:error_info(), line()} + | request_error(). -spec parse_erl_form(prompt()) -> parse_form_ret(). diff --git a/lib/stdlib/src/re.erl b/lib/stdlib/src/re.erl index 296a6b3d23..9642de17b4 100644 --- a/lib/stdlib/src/re.erl +++ b/lib/stdlib/src/re.erl @@ -208,29 +208,25 @@ replace(Subject,RE,Replacement,Options) -> process_repl_params(Options,iodata,false), FlatSubject = to_binary(Subject, Unicode), FlatReplacement = to_binary(Replacement, Unicode), - case do_replace(FlatSubject,Subject,RE,FlatReplacement,NewOpt) of - {error,_Err} -> - throw(badre); - IoList -> - case Convert of - iodata -> - IoList; - binary -> - case Unicode of - false -> - iolist_to_binary(IoList); - true -> - unicode:characters_to_binary(IoList,unicode) - end; - list -> - case Unicode of - false -> - binary_to_list(iolist_to_binary(IoList)); - true -> - unicode:characters_to_list(IoList,unicode) - end - end - end + IoList = do_replace(FlatSubject,Subject,RE,FlatReplacement,NewOpt), + case Convert of + iodata -> + IoList; + binary -> + case Unicode of + false -> + iolist_to_binary(IoList); + true -> + unicode:characters_to_binary(IoList,unicode) + end; + list -> + case Unicode of + false -> + binary_to_list(iolist_to_binary(IoList)); + true -> + unicode:characters_to_list(IoList,unicode) + end + end catch throw:badopt -> erlang:error(badarg,[Subject,RE,Replacement,Options]); diff --git a/lib/stdlib/test/base64_SUITE.erl b/lib/stdlib/test/base64_SUITE.erl index 44742063b3..d8bb2dfb60 100644 --- a/lib/stdlib/test/base64_SUITE.erl +++ b/lib/stdlib/test/base64_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2007-2009. All Rights Reserved. +%% Copyright Ericsson AB 2007-2011. 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 @@ -18,7 +18,6 @@ %% -module(base64_SUITE). --author('[email protected]'). -include("test_server.hrl"). -include("test_server_line.hrl"). @@ -29,7 +28,7 @@ %% Test cases must be exported. -export([base64_encode/1, base64_decode/1, base64_otp_5635/1, base64_otp_6279/1, big/1, illegal/1, mime_decode/1, - roundtrip/1]). + mime_decode_to_string/1, roundtrip/1]). init_per_testcase(_, Config) -> Dog = test_server:timetrap(?t:minutes(2)), @@ -50,7 +49,7 @@ all(doc) -> all(suite) -> [base64_encode, base64_decode, base64_otp_5635, base64_otp_6279, big, illegal, mime_decode, - roundtrip]. + mime_decode_to_string, roundtrip]. %%------------------------------------------------------------------------- @@ -59,7 +58,7 @@ base64_encode(doc) -> base64_encode(suite) -> []; base64_encode(Config) when is_list(Config) -> - %% Two pads + %% Two pads <<"QWxhZGRpbjpvcGVuIHNlc2FtZQ==">> = base64:encode("Aladdin:open sesame"), %% One pad @@ -77,8 +76,8 @@ base64_decode(doc) -> base64_decode(suite) -> []; base64_decode(Config) when is_list(Config) -> - %% Two pads - <<"Aladdin:open sesame">> = + %% Two pads + <<"Aladdin:open sesame">> = base64:decode("QWxhZGRpbjpvcGVuIHNlc2FtZQ=="), %% One pad <<"Hello World">> = base64:decode(<<"SGVsbG8gV29ybGQ=">>), @@ -138,20 +137,85 @@ illegal(Config) when is_list(Config) -> {'EXIT',{function_clause, _}} = (catch base64:decode("()")), ok. %%------------------------------------------------------------------------- +%% mime_decode and mime_decode_to_string have different implementations +%% so test both with the same input separately. Both functions have +%% the same implementation for binary/string arguments. mime_decode(doc) -> ["Test base64:mime_decode/1."]; mime_decode(suite) -> []; mime_decode(Config) when is_list(Config) -> - %% Two pads - <<"Aladdin:open sesame">> = + %% Test correct padding + <<"one">> = base64:mime_decode(<<"b25l">>), + <<"on">> = base64:mime_decode(<<"b24=">>), + <<"o">> = base64:mime_decode(<<"bw==">>), + %% Test 1 extra padding + <<"one">> = base64:mime_decode(<<"b25l= =">>), + <<"on">> = base64:mime_decode(<<"b24== =">>), + <<"o">> = base64:mime_decode(<<"bw=== =">>), + %% Test 2 extra padding + <<"one">> = base64:mime_decode(<<"b25l===">>), + <<"on">> = base64:mime_decode(<<"b24====">>), + <<"o">> = base64:mime_decode(<<"bw=====">>), + %% Test misc embedded padding + <<"one">> = base64:mime_decode(<<"b2=5l===">>), + <<"on">> = base64:mime_decode(<<"b=24====">>), + <<"o">> = base64:mime_decode(<<"b=w=====">>), + %% Test misc white space and illegals with embedded padding + <<"one">> = base64:mime_decode(<<" b~2=\r\n5()l===">>), + <<"on">> = base64:mime_decode(<<"\tb =2\"�4=�= ==">>), + <<"o">> = base64:mime_decode(<<"\nb=w=====">>), + %% Two pads + <<"Aladdin:open sesame">> = base64:mime_decode("QWxhZGRpbjpvc()GVuIHNlc2FtZQ=="), - %% One pad, followed by ignored text - <<"Hello World">> = base64:mime_decode(<<"SGVsb)(G8gV29ybGQ=apa">>), + %% One pad to ignore, followed by more text + <<"Hello World!!">> = base64:mime_decode(<<"SGVsb)(G8gV29ybGQ=h IQ= =">>), + %% No pad + <<"Aladdin:open sesam">> = + base64:mime_decode("QWxhZGRpbjpvcG�\")(VuIHNlc2Ft"), + %% Encoded base 64 strings may be divided by non base 64 chars. + %% In this cases whitespaces. + <<"0123456789!@#0^&*();:<>,. []{}">> = + base64:mime_decode( + <<"MDEy MzQ1Njc4 \tOSFAIzBeJ \nio)(oKTs6 PD4sLi \r\nBbXXt9">>), + ok. + +%%------------------------------------------------------------------------- + +%% Repeat of mime_decode() tests +mime_decode_to_string(doc) -> + ["Test base64:mime_decode_to_string/1."]; +mime_decode_to_string(suite) -> + []; +mime_decode_to_string(Config) when is_list(Config) -> + %% Test correct padding + "one" = base64:mime_decode_to_string(<<"b25l">>), + "on" = base64:mime_decode_to_string(<<"b24=">>), + "o" = base64:mime_decode_to_string(<<"bw==">>), + %% Test 1 extra padding + "one" = base64:mime_decode_to_string(<<"b25l= =">>), + "on" = base64:mime_decode_to_string(<<"b24== =">>), + "o" = base64:mime_decode_to_string(<<"bw=== =">>), + %% Test 2 extra padding + "one" = base64:mime_decode_to_string(<<"b25l===">>), + "on" = base64:mime_decode_to_string(<<"b24====">>), + "o" = base64:mime_decode_to_string(<<"bw=====">>), + %% Test misc embedded padding + "one" = base64:mime_decode_to_string(<<"b2=5l===">>), + "on" = base64:mime_decode_to_string(<<"b=24====">>), + "o" = base64:mime_decode_to_string(<<"b=w=====">>), + %% Test misc white space and illegals with embedded padding + "one" = base64:mime_decode_to_string(<<" b~2=\r\n5()l===">>), + "on" = base64:mime_decode_to_string(<<"\tb =2\"�4=�= ==">>), + "o" = base64:mime_decode_to_string(<<"\nb=w=====">>), + %% Two pads + "Aladdin:open sesame" = + base64:mime_decode_to_string("QWxhZGRpbjpvc()GVuIHNlc2FtZQ=="), + %% One pad to ignore, followed by more text + "Hello World!!" = base64:mime_decode_to_string(<<"SGVsb)(G8gV29ybGQ=h IQ= =">>), %% No pad "Aladdin:open sesam" = base64:mime_decode_to_string("QWxhZGRpbjpvcG�\")(VuIHNlc2Ft"), - %% Encoded base 64 strings may be divided by non base 64 chars. %% In this cases whitespaces. "0123456789!@#0^&*();:<>,. []{}" = @@ -159,6 +223,7 @@ mime_decode(Config) when is_list(Config) -> <<"MDEy MzQ1Njc4 \tOSFAIzBeJ \nio)(oKTs6 PD4sLi \r\nBbXXt9">>), ok. +%%------------------------------------------------------------------------- roundtrip(Config) when is_list(Config) -> Sizes = lists:seq(1, 255) ++ lists:seq(2400-5, 2440), diff --git a/lib/stdlib/test/erl_eval_SUITE.erl b/lib/stdlib/test/erl_eval_SUITE.erl index c60a558fa1..254ce0095d 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 1998-2009. All Rights Reserved. +%% Copyright Ericsson AB 1998-2010. 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 @@ -38,7 +38,8 @@ otp_8133/1, funs/1, try_catch/1, - eval_expr_5/1]). + eval_expr_5/1, + zero_width/1]). %% %% Define to run outside of test server @@ -76,7 +77,8 @@ all(suite) -> [guard_1, guard_2, match_pattern, string_plusplus, 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]. + otp_6787, otp_6977, otp_7550, otp_8133, funs, try_catch, eval_expr_5, + zero_width]. guard_1(doc) -> ["(OTP-2405)"]; @@ -1326,6 +1328,14 @@ eval_expr_5(Config) when is_list(Config) -> ok end. +zero_width(Config) when is_list(Config) -> + ?line check(fun() -> + {'EXIT',{badarg,_}} = (catch <<not_a_number:0>>), + ok + end, "begin {'EXIT',{badarg,_}} = (catch <<not_a_number:0>>), " + "ok end.", ok), + ok. + %% Check the string in different contexts: as is; in fun; from compiled code. check(F, String, Result) -> check1(F, String, Result), diff --git a/lib/stdlib/test/ets_SUITE.erl b/lib/stdlib/test/ets_SUITE.erl index 620848003c..4e789790f6 100644 --- a/lib/stdlib/test/ets_SUITE.erl +++ b/lib/stdlib/test/ets_SUITE.erl @@ -5325,7 +5325,25 @@ my_tab_to_list(_Ts,'$end_of_table', Acc) -> lists:reverse(Acc); my_tab_to_list(Ts,Key, Acc) -> my_tab_to_list(Ts,ets:next(Ts,Key),[ets:lookup(Ts, Key)| Acc]). +wait_for_all_schedulers_online_to_execute() -> + PMs = lists:map(fun (Sched) -> + spawn_opt(fun () -> ok end, + [monitor, {scheduler, Sched}]) + end, + lists:seq(1,erlang:system_info(schedulers_online))), + lists:foreach(fun ({P, M}) -> + receive + {'DOWN', M, process, P, _} -> ok + end + end, + PMs), + ok. + etsmem() -> + %% Wait until it is guaranteed that all already scheduled + %% deallocations of DbTable structures have completed. + wait_for_all_schedulers_online_to_execute(), + AllTabs = lists:map(fun(T) -> {T,ets:info(T,name),ets:info(T,size), ets:info(T,memory),ets:info(T,type)} end, ets:all()), |