diff options
Diffstat (limited to 'lib/stdlib')
-rw-r--r-- | lib/stdlib/doc/src/filelib.xml | 24 | ||||
-rw-r--r-- | lib/stdlib/doc/src/filename.xml | 30 | ||||
-rw-r--r-- | lib/stdlib/doc/src/unicode_usage.xml | 8 | ||||
-rw-r--r-- | lib/stdlib/src/filename.erl | 102 | ||||
-rw-r--r-- | lib/stdlib/src/stdlib.app.src | 2 |
5 files changed, 162 insertions, 4 deletions
diff --git a/lib/stdlib/doc/src/filelib.xml b/lib/stdlib/doc/src/filelib.xml index 158cf4b266..5e631aac21 100644 --- a/lib/stdlib/doc/src/filelib.xml +++ b/lib/stdlib/doc/src/filelib.xml @@ -45,6 +45,30 @@ <p>For more information about raw filenames, see the <seealso marker="kernel:file"><c>file</c></seealso> module.</p> + + <note> + <p> + Functionality in this module generally assumes valid input and + does not necessarily fail on input that does not use a valid + encoding, but may instead very likely produce invalid output. + </p> + <p> + File operations used to accept filenames containing + null characters (integer value zero). This caused + the name to be truncated and in some cases arguments + to primitive operations to be mixed up. Filenames + containing null characters inside the filename + are now <em>rejected</em> and will cause primitive + file operations to fail. + </p> + </note> + <warning><p> + Currently null characters at the end of the filename + will be accepted by primitive file operations. Such + filenames are however still documented as invalid. The + implementation will also change in the future and + reject such filenames. + </p></warning> </description> <datatypes> diff --git a/lib/stdlib/doc/src/filename.xml b/lib/stdlib/doc/src/filename.xml index 14fd5ef787..d2608ad542 100644 --- a/lib/stdlib/doc/src/filename.xml +++ b/lib/stdlib/doc/src/filename.xml @@ -46,7 +46,10 @@ filename by removing redundant directory separators, use <seealso marker="#join/1"><c>join/1</c></seealso>.</p> - <p>The module supports raw filenames in the way that if a binary is + <p> + The module supports + <seealso marker="unicode_usage#notes-about-raw-filenames">raw + filenames</seealso> in the way that if a binary is present, or the filename cannot be interpreted according to the return value of <seealso marker="kernel:file#native_name_encoding/0"> <c>file:native_name_encoding/0</c></seealso>, a raw filename is also @@ -56,6 +59,30 @@ (the join operation is performed of course). For more information about raw filenames, see the <seealso marker="kernel:file"><c>file</c></seealso> module.</p> + + <note> + <p> + Functionality in this module generally assumes valid input and + does not necessarily fail on input that does not use a valid + encoding, but may instead very likely produce invalid output. + </p> + <p> + File operations used to accept filenames containing + null characters (integer value zero). This caused + the name to be truncated and in some cases arguments + to primitive operations to be mixed up. Filenames + containing null characters inside the filename + are now <em>rejected</em> and will cause primitive + file operations to fail. + </p> + </note> + <warning><p> + Currently null characters at the end of the filename + will be accepted by primitive file operations. Such + filenames are however still documented as invalid. The + implementation will also change in the future and + reject such filenames. + </p></warning> </description> <datatypes> <datatype> @@ -555,6 +582,7 @@ unsafe</pre> ["a:/","msdev","include"]</pre> </desc> </func> + </funcs> </erlref> diff --git a/lib/stdlib/doc/src/unicode_usage.xml b/lib/stdlib/doc/src/unicode_usage.xml index 26dc46719e..789e063c12 100644 --- a/lib/stdlib/doc/src/unicode_usage.xml +++ b/lib/stdlib/doc/src/unicode_usage.xml @@ -719,8 +719,8 @@ Eshell V5.10.1 (abort with ^G) </section> <section> - <title>Unicode Filenames</title> <marker id="unicode_file_names"/> + <title>Unicode Filenames</title> <p>Most modern operating systems support Unicode filenames in some way. There are many different ways to do this and Erlang by default treats the different approaches differently:</p> @@ -855,8 +855,12 @@ Eshell V5.10.1 (abort with ^G) </note> <section> - <title>Notes About Raw Filenames</title> <marker id="notes-about-raw-filenames"/> + <title>Notes About Raw Filenames</title> + <note><p> + Note that raw filenames <em>not</em> necessarily are encoded the + same way as on the OS level. + </p></note> <p>Raw filenames were introduced together with Unicode filename support in ERTS 5.8.2 (Erlang/OTP R14B01). The reason "raw filenames" were introduced in the system was diff --git a/lib/stdlib/src/filename.erl b/lib/stdlib/src/filename.erl index 63cfeae57b..919f8f20e6 100644 --- a/lib/stdlib/src/filename.erl +++ b/lib/stdlib/src/filename.erl @@ -34,6 +34,38 @@ %% we flatten the arguments immediately on function entry as that makes %% it easier to ensure that the code works. +%% +%% *** Requirements on Raw Filename Format *** +%% +%% These requirements are due to the 'filename' module +%% in stdlib. This since it is documented that it +%% should be able to operate on raw filenames as well +%% as ordinary filenames. +%% +%% A raw filename *must* be a byte sequence where: +%% 1. Codepoints 0-127 (7-bit ascii) *must* be encoded +%% as a byte with the corresponding value. That is, +%% the most significant bit in the byte encoding the +%% codepoint is never set. +%% 2. Codepoints greater than 127 *must* be encoded +%% with the most significant bit set in *every* byte +%% encoding it. +%% +%% Latin1 and UTF-8 meet these requirements while +%% UTF-16 and UTF-32 don't. +%% +%% On Windows filenames are natively stored as malformed +%% UTF-16LE (lonely surrogates may appear). A more correct +%% description than UTF-16 would be an array of 16-bit +%% words... In order to meet the requirements of the +%% raw file format we convert the malformed UTF-16LE to +%% malformed UTF-8 which meet the requirements. +%% +%% Note that these requirements are today only OTP +%% internal (erts-stdlib internal) requirements that +%% could be changed. +%% + -export([absname/1, absname/2, absname_join/2, basename/1, basename/2, dirname/1, extension/1, join/1, join/2, pathtype/1, @@ -41,6 +73,7 @@ safe_relative_path/1]). -export([find_src/1, find_src/2]). % deprecated -export([basedir/2, basedir/3]). +-export([validate/1]). %% Undocumented and unsupported exports. -export([append/2]). @@ -1135,3 +1168,72 @@ basedir_os_type() -> {win32,_} -> windows; _ -> linux end. + +%% +%% validate/1 +%% + +-spec validate(FileName) -> boolean() when + FileName :: file:name_all(). + +validate(FileName) when is_binary(FileName) -> + %% Raw filename... + validate_bin(FileName); +validate(FileName) when is_list(FileName); + is_atom(FileName) -> + validate_list(FileName, + file:native_name_encoding(), + os:type()). + +validate_list(FileName, Enc, Os) -> + try + true = validate_list(FileName, Enc, Os, 0) > 0 + catch + _ : _ -> false + end. + +validate_list([], _Enc, _Os, Chars) -> + Chars; +validate_list(C, Enc, Os, Chars) when is_integer(C) -> + validate_char(C, Enc, Os), + Chars+1; +validate_list(A, Enc, Os, Chars) when is_atom(A) -> + validate_list(atom_to_list(A), Enc, Os, Chars); +validate_list([H|T], Enc, Os, Chars) -> + NewChars = validate_list(H, Enc, Os, Chars), + validate_list(T, Enc, Os, NewChars). + +%% C is always an integer... +% validate_char(C, _, _) when not is_integer(C) -> +% throw(invalid); +validate_char(C, _, _) when C < 1 -> + throw(invalid); %% No negative or null characters... +validate_char(C, latin1, _) when C > 255 -> + throw(invalid); +validate_char(C, utf8, _) when C >= 16#110000 -> + throw(invalid); +validate_char(C, utf8, {win32, _}) when C > 16#ffff -> + throw(invalid); %% invalid win wchar... +validate_char(_C, utf8, {win32, _}) -> + ok; %% Range below is accepted on windows... +validate_char(C, utf8, _) when 16#D800 =< C, C =< 16#DFFF -> + throw(invalid); %% invalid unicode range... +validate_char(_, _, _) -> + ok. + +validate_bin(Bin) -> + %% Raw filename. That is, we do not interpret + %% the encoding, but we still do not accept + %% null characters... + try + true = validate_bin(Bin, 0) > 0 + catch + _ : _ -> false + end. + +validate_bin(<<>>, Bs) -> + Bs; +validate_bin(<<0, _Rest/binary>>, _Bs) -> + throw(invalid); %% No null characters allowed... +validate_bin(<<_B, Rest/binary>>, Bs) -> + validate_bin(Rest, Bs+1). diff --git a/lib/stdlib/src/stdlib.app.src b/lib/stdlib/src/stdlib.app.src index 3c449d3cb9..ab0824ca17 100644 --- a/lib/stdlib/src/stdlib.app.src +++ b/lib/stdlib/src/stdlib.app.src @@ -107,7 +107,7 @@ dets]}, {applications, [kernel]}, {env, []}, - {runtime_dependencies, ["sasl-3.0","kernel-5.0","erts-9.0","crypto-3.3", + {runtime_dependencies, ["sasl-3.0","kernel-6.0","erts-10.0","crypto-3.3", "compiler-5.0"]} ]}. |