diff options
Diffstat (limited to 'lib/stdlib')
39 files changed, 2468 insertions, 981 deletions
diff --git a/lib/stdlib/doc/src/ets.xml b/lib/stdlib/doc/src/ets.xml index 44c050a0d3..6db1ae3aa3 100644 --- a/lib/stdlib/doc/src/ets.xml +++ b/lib/stdlib/doc/src/ets.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2012</year> + <year>1996</year><year>2013</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> 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/notes.xml b/lib/stdlib/doc/src/notes.xml index 13575588fd..a38fcb3d0b 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -4,7 +4,7 @@ <chapter> <header> <copyright> - <year>2004</year><year>2012</year> + <year>2004</year><year>2013</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> 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..c5d476e54b 100644 --- a/lib/stdlib/doc/src/unicode_usage.xml +++ b/lib/stdlib/doc/src/unicode_usage.xml @@ -32,241 +32,1084 @@ <rev>PA1</rev> <file>unicode_usage.xml</file> </header> -<p>Implementing support for Unicode character sets is an ongoing process. The Erlang Enhancement Proposal (EEP) 10 outlines the basics of Unicode support and also specifies a default encoding in binaries that all Unicode-aware modules should handle in the future.</p> -<p>The functionality described in EEP10 is implemented in Erlang/OTP as of R13A, but that is by no means the end of it. More functionality will be needed in the future and more OTP-libraries might need updating to cope with Unicode data.</p> -<p>This guide outlines the current Unicode support and gives a couple of recipes for working with Unicode data.</p> +<section> +<title>Unicode Implementation</title> + <p>Implementing support for Unicode character sets is an ongoing + process. The Erlang Enhancement Proposal (EEP) 10 outlined the + basics of Unicode support and also specified a default encoding in + binaries that all Unicode-aware modules should handle in the + future.</p> + + <p>The functionality described in EEP10 was implemented in Erlang/OTP + as of R13A, but that was by no means the end of it. In R14B01 support + for Unicode file names was added, although it was in no way complete + and was by default disabled on platforms where no guarantee was given + for the file name encoding. With R16A came support for UTF-8 encoded + source code, among with enhancements to many of the applications to + support both Unicode encoded file names as well as support for UTF-8 + encoded files in several circumstances. Most notable is the support + for UTF-8 in files read by <c>file:consult/1</c>, release handler support + for UTF-8 and more support for Unicode character sets in the + I/O-system.</p> + + <p>In R17, the encoding default for Erlang source files will be + switched to UTF-8 and in R18 Erlang will support atoms in the full + Unicode range, meaning full Unicode function and module + names</p> + + <p>This guide outlines the current Unicode support and gives a couple + of recipes for working with Unicode data.</p> +</section> +<section> +<title>Understanding Unicode</title> + <p>Experience with the Unicode support in Erlang has made it + painfully clear that understanding Unicode characters and encodings + is not as easy as one would expect. The complexity of the field as + well as the implications of the standard requires thorough + understanding of concepts rarely before thought of.</p> + + <p>Furthermore the Erlang implementation requires understanding of + concepts that never were an issue for many (Erlang) programmers. To + understand and use Unicode characters requires that you study the + subject thoroughly, even if you're an experienced programmer.</p> + + <p>As an example, one could contemplate the issue of converting + between upper and lower case letters. Reading the standard will make + you realize that, to begin with, there's not a simple one to one + mapping in all scripts. Take German as an example, where there's a + letter "ß" (Sharp s) in lower case, but the uppercase equivalent is + "SS". Or Greek, where "Σ" has two different lowercase forms: "ς" in + word-final position and "σ" elsewhere. Or Turkish where dotted and + dot-less "i" both exist in lower case and upper case forms, or + Cyrillic "I" which usually has no lowercase form. Or of course + languages that have no concept of upper case (or lower case). So, a + conversion function will need to know not only one character at a + time, but possibly the whole sentence, maybe the natural language + the translation should be in and also take into account differences + in input and output string length and so on. There is at the time of + writing no Unicode to_upper/to_lower functionality in Erlang/OTP, but + there are publicly available libraries that address these issues.</p> + + <p>Another example is the accented characters where the same glyph + has two different representations. Let's look at the Swedish + "ö". There's a code point for that in the Unicode standard, but you + can also write it as "o" followed by U+0308 (Combining Diaeresis, + with the simplified meaning that the last letter should have a "¨" + above). They have exactly the same glyph. They are for most + purposes the same, but they have completely different + representations. For example MacOS X converts all file names to use + Combining Diaeresis, while most other programs (including Erlang) + try to hide that by doing the opposite when for example listing + directories. However it's done, it's usually important to normalize + such characters to avoid utter confusion.</p> + + <p>The list of examples can be made as long as the Unicode standard, I + suspect. The point is that one need a kind of knowledge that was + never needed when programs only took one or two languages into + account. The complexity of human languages and scripts, certainly + has made this a challenge when constructing a universal + standard. Supporting Unicode properly in your program <em>will</em> require + effort.</p> + +</section> <section> <title>What Unicode Is</title> -<p>Unicode is a standard defining codepoints (numbers) for all known, living or dead, scripts. In principle, every known symbol used in any language has a Unicode codepoint.</p> -<p>Unicode codepoints are defined and published by the <em>Unicode Consortium</em>, which is a non profit organization.</p> -<p>Support for Unicode is increasing throughout the world of computing, as the benefits of one common character set are overwhelming when programs are used in a global environment.</p> -<p>Along with the base of the standard, the codepoints for all the scripts, there are a couple of encoding standards available. Different operating systems and tools support different encodings. For example Linux and MacOSX has chosen the UTF-8 encoding, which is backwards compatible with 7-bit ASCII and therefore affects programs written in plain English the least. Windows® on the other hand supports a limited version of UTF-16, namely all the code planes where the characters can be stored in one single 16-bit entity, which includes most living languages.</p> -<p>The most widely spread encodings are:</p> -<taglist> -<tag>UTF-8</tag> -<item>Each character is stored in one to four bytes depending on codepoint. The encoding is backwards compatible with 7-bit ASCII as all 7-bit characters are stored in one single byte as is. The characters beyond codepoint 127 are stored in more bytes, letting the most significant bit in the first character indicate a multi-byte character. For details on the encoding, the RFC is publicly available.</item> -<tag>UTF-16</tag> -<item>This encoding has many similarities to UTF-8, but the basic unit is a 16-bit number. This means that all characters occupy at least two bytes, some high numbers even four bytes. Some programs and operating systems claiming to use UTF-16 only allows for characters that can be stored in one 16-bit entity, which is usually sufficient to handle living languages. As the basic unit is more than one byte, byte-order issues occur, why UTF-16 exists in both a big-endian and little-endian variant.</item> -<tag>UTF-32</tag> -<item>The most straight forward representation, each character is stored in one single 32-bit number. There is no need for escapes or any variable amount of entities for one character, all Unicode codepoints can be stored in one single 32-bit entity. As with UTF-16, there are byte-order issues, UTF-32 can be both big- and little-endian.</item> -<tag>UCS-4</tag> -<item>Basically the same as UTF-32, but without some Unicode semantics, defined by IEEE and has little use as a separate encoding standard. For all normal (and possibly abnormal) usages, UTF-32 and UCS-4 are interchangeable.</item> -</taglist> -<p>Certain ranges of characters are left unused and certain ranges are even deemed invalid. The most notable invalid range is 16#D800 - 16#DFFF, as the UTF-16 encoding does not allow for encoding of these numbers. It can be speculated that the UTF-16 encoding standard was, from the beginning, expected to be able to hold all Unicode characters in one 16-bit entity, but then had to be extended, leaving a hole in the Unicode range to cope with backward compatibility.</p> -<p>Additionally, the codepoint 16#FEFF is used for byte order marks (BOM's) and use of that character is not encouraged in other contexts than that. It actually is valid though, as the character "ZWNBS" (Zero Width Non Breaking Space). BOM's are used to identify encodings and byte order for programs where such parameters are not known in advance. Byte order marks are more seldom used than one could expect, but their use is becoming more widely spread as they provide the means for programs to make educated guesses about the Unicode format of a certain file.</p> + <p>Unicode is a standard defining code points (numbers) for all + known, living or dead, scripts. In principle, every known symbol + used in any language has a Unicode code point.</p> + <p>Unicode code points are defined and published by the <em>Unicode + Consortium</em>, which is a non profit organization.</p> + <p>Support for Unicode is increasing throughout the world of + computing, as the benefits of one common character set are + overwhelming when programs are used in a global environment.</p> + <p>Along with the base of the standard: the code points for all the + scripts, there are a couple of <em>encoding standards</em> available.</p> + <p>It is vital to understand the difference between encodings and + Unicode characters. Unicode characters are code points according to + the Unicode standard, while the encodings are ways to represent such + code points. An encoding is just a standard for representation, + UTF-8 can for example be used to represent a very limited part of + the Unicode character set (e.g. ISO-Latin-1), or the full Unicode + range. It's just an encoding format.</p> + <p>As long as all character sets were limited to 256 characters, + each character could be stored in one single byte, so there was more + or less only one practical encoding for the characters. Encoding + each character in one byte was so common that the encoding wasn't + even named. When we now, with the Unicode system, have a lot more + than 256 characters, we need a common way to represent these. The + common ways of representing the code points are the encodings. This + means a whole new concept to the programmer, the concept of + character representation, which was before a non-issue.</p> + + <p>Different operating systems and tools support different + encodings. For example Linux and MacOS X has chosen the UTF-8 + encoding, which is backwards compatible with 7-bit ASCII and + therefore affects programs written in plain English the + least. Windows on the other hand supports a limited version of + UTF-16, namely all the code planes where the characters can be + stored in one single 16-bit entity, which includes most living + languages.</p> + + <p>The most widely spread encodings are:</p> + <taglist> + <tag>Bytewise representation</tag> + <item>This is not a proper Unicode representation, but the + representation used for characters before the Unicode standard. It + can still be used to represent character code points in the Unicode + standard that have numbers below 256, which corresponds exactly to + the ISO-Latin-1 character set. In Erlang, this is commonly denoted + <c>latin1</c> encoding, which is slightly misleading as ISO-Latin-1 is + a character code range, not an encoding.</item> + <tag>UTF-8</tag> + <item>Each character is stored in one to four bytes depending on + code point. The encoding is backwards compatible with bytewise + representation of 7-bit ASCII as all 7-bit characters are stored + in one single byte in UTF-8. The characters beyond code point 127 + are stored in more bytes, letting the most significant bit in the + first character indicate a multi-byte character. For details on + the encoding, the RFC is publicly available. Note that UTF-8 is + <em>not</em> compatible with bytewise representation for + code points between 128 and 255, so a ISO-Latin-1 bytewise + representation is not generally compatible with UTF-8.</item> + <tag>UTF-16</tag> + <item>This encoding has many similarities to UTF-8, but the basic + unit is a 16-bit number. This means that all characters occupy at + least two bytes, some high numbers even four bytes. Some programs, + libraries and operating systems claiming to use UTF-16 only allows + for characters that can be stored in one 16-bit entity, which is + usually sufficient to handle living languages. As the basic unit + is more than one byte, byte-order issues occur, why UTF-16 exists + in both a big-endian and little-endian variant. In Erlang, the + full UTF-16 range is supported when applicable, like in the + <c>unicode</c> module and in the bit syntax.</item> + <tag>UTF-32</tag> + <item>The most straight forward representation. Each character is + stored in one single 32-bit number. There is no need for escapes + or any variable amount of entities for one character, all Unicode + code points can be stored in one single 32-bit entity. As with + UTF-16, there are byte-order issues, UTF-32 can be both big- and + little-endian.</item> + <tag>UCS-4</tag> + <item>Basically the same as UTF-32, but without some Unicode + semantics, defined by IEEE and has little use as a separate + encoding standard. For all normal (and possibly abnormal) usages, + UTF-32 and UCS-4 are interchangeable.</item> + </taglist> + <p>Certain ranges of numbers are left unused in the Unicode standard + and certain ranges are even deemed invalid. The most notable invalid + range is 16#D800 - 16#DFFF, as the UTF-16 encoding does not allow + for encoding of these numbers. It can be speculated that the UTF-16 + encoding standard was, from the beginning, expected to be able to + hold all Unicode characters in one 16-bit entity, but then had to be + extended, leaving a hole in the Unicode range to cope with backward + compatibility.</p> + <p>Additionally, the code point 16#FEFF is used for byte order marks + (BOM's) and use of that character is not encouraged in other + contexts than that. It actually is valid though, as the character + "ZWNBS" (Zero Width Non Breaking Space). BOM's are used to identify + encodings and byte order for programs where such parameters are not + known in advance. Byte order marks are more seldom used than one + could expect, but their use might become more widely spread as they + provide the means for programs to make educated guesses about the + Unicode format of a certain file.</p> </section> <section> -<title>Standard Unicode Representation in Erlang</title> -<p>In Erlang, strings are actually lists of integers. A string is defined to be encoded in the ISO-latin-1 (ISO8859-1) character set, which is, codepoint by codepoint, a sub-range of the Unicode character set.</p> -<p>The standard list encoding for strings is therefore easily extendible to cope with the whole Unicode range: A Unicode string in Erlang is simply a list containing integers, each integer being a valid Unicode codepoint and representing one character in the Unicode character set.</p> -<p>Regular Erlang strings in ISO-latin-1 are a subset of their Unicode -strings.</p> - -<p>Binaries on the other hand are more troublesome. For performance reasons, programs often store textual data in binaries instead of lists, mainly because they are more compact (one byte per character instead of two words per character, as is the case with lists). Using <c>erlang:list_to_binary/1</c>, a regular Erlang string can be converted into a binary, effectively using the ISO-latin-1 encoding in the binary - one byte per character. This is very convenient for those regular Erlang strings, but cannot be done for Unicode lists.</p> -<p>As the UTF-8 encoding is widely spread and provides the most compact storage, it is selected as the standard encoding of Unicode characters in binaries for Erlang.</p> -<p>The standard binary encoding is used whenever a library function in Erlang should cope with Unicode data in binaries, but is of course not enforced when communicating externally. Functions and bit-syntax exist to encode and decode both UTF-8, UTF-16 and UTF-32 in binaries. Library functions dealing with binaries and Unicode in general, however, only deal with the default encoding.</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"> + <title>Areas of Unicode Support</title> + <p>To support Unicode in Erlang, problems in several areas have been + addressed. Each area is described briefly in this section and more + thoroughly further down in this document:</p> + <taglist> + <tag>Representation</tag> + <item>To handle Unicode characters in Erlang, we have to have a + common representation both in lists and binaries. The EEP (10) and + the subsequent initial implementation in R13A settled a standard + representation of Unicode characters in Erlang.</item> + <tag>Manipulation</tag> + <item>The Unicode characters need to be processed by the Erlang + program, why library functions need to be able to handle them. In + some cases functionality was added to already existing interfaces + (as the string module now can handle lists with arbitrary code points), + in some cases new functionality or options need to be added (as in + the <c>io</c>-module, the file handling, the <c>unicode</c> module + and the bit syntax). Today most modules in kernel and STDLIB, as + well as the VM are Unicode aware.</item> + <tag>File I/O</tag> + <item>I/O is by far the most problematic area for Unicode. A file + is an entity where bytes are stored and the lore of programming + has been to treat characters and bytes as interchangeable. With + Unicode characters, you need to decide on an encoding as soon as + you want to store the data in a file. In Erlang you can open a + text file with an encoding option, so that you can read characters + from it rather than bytes, but you can also open a file for + bytewise I/O. The I/O-system of Erlang has been designed (or at + least used) in a way where you expect any I/O-server to be + able to cope with any string data, but that is no longer the case + when you work with Unicode characters. Handling the fact that you + need to know the capabilities of the device where your data ends + up is something new to the Erlang programmer. Furthermore, ports + in Erlang are byte oriented, so an arbitrary string of (Unicode) + characters can not be sent to a port without first converting it + to an encoding of choice.</item> + <tag>Terminal I/O</tag> + <item>Terminal I/O is slightly easier than file I/O. The output is + meant for human reading and is usually Erlang syntax (e.g. in the + shell). There exists syntactic representation of any Unicode + character without actually displaying the glyph (instead written + as <c>\x{</c>HHH<c>}</c>), so Unicode data can usually be displayed + even if the terminal as such do not support the whole Unicode + range.</item> + <tag>File names</tag> + <item>File names can be stored as Unicode strings, in different + ways depending on the underlying OS and file system. This can be + handled fairly easy by a program. The problems arise when the file + system is not consistent in it's encodings, like for example + Linux. Linux allows files to be named with any sequence of bytes, + leaving to each program to interpret those bytes. On systems where + these "transparent" file names are used, Erlang has to be informed + about the file name encoding by a startup flag. The default is + bytewise interpretation, which is actually usually wrong, but + allows for interpretation of <em>all</em> file names. The concept + of "raw file names" can be used to handle wrongly encoded + file names if one enables Unicode file name translation + (<c>+fnu</c>) on platforms where this is not the default.</item> + <tag>Source code encoding</tag> + <item>When it comes to the Erlang source code, there is support + for the UTF-8 encoding and bytewise encoding. The default in R16B + is bytewise (or latin1) encoding. You can control the encoding by + a comment like: +<code> +%% -*- coding: utf-8 -*- +</code> + in the beginning of the file. This of course requires your editor to + support UTF-8 as well. The same comment is also interpreted by + functions like <c>file:consult/1</c>, the release handler etc, so that + you can have all text files in your source directories in UTF-8 + encoding. + </item> + <tag>The language</tag> + <item>Having the source code in UTF-8 also allows you to write + string literals containing Unicode characters with code points > + 255, although atoms, module names and function names will be + restricted to the ISO-Latin-1 range until the R18 release. Binary + literals where you use the <c>/utf8</c> type, can also be + expressed using Unicode characters > 255. Having module names + using characters other than 7-bit ASCII can cause trouble on + operating systems with inconsistent file naming schemes, and might + also hurt portability, so it's not really recommended. It is + suggested in EEP 40 that the language should also allow for + Unicode characters > 255 in variable names. Whether to + implement that EEP or not is yet to be decided.</item> + </taglist> +</section> +<section> + <title>Standard Unicode Representation</title> + <p>In Erlang, strings are actually lists of integers. A string was + up until R13 defined to be encoded in the ISO-latin-1 (ISO8859-1) + character set, which is, code point by code point, a sub-range of + the Unicode character set.</p> + <p>The standard list encoding for strings was therefore easily + extended to cope with the whole Unicode range: A Unicode string in + Erlang is simply a list containing integers, each integer being a + valid Unicode code point and representing one character in the + Unicode character set.</p> + <p>Erlang strings in ISO-latin-1 are a subset of Unicode + strings.</p> + <p>Only if a string contains code points < 256, can it be + directly converted to a binary by using + i.e. <c>erlang:iolist_to_binary/1</c> or can be sent directly to a + port. If the string contains Unicode characters > 255, an + encoding has to be decided upon and the string should be converted + to a binary in the preferred encoding using + <c>unicode:characters_to_binary/{1,2,3}</c>. Strings are not + generally lists of bytes, as they were before R13. They are lists of + characters. Characters are not generally bytes, they are Unicode + code points.</p> + + <p>Binaries are more troublesome. For performance reasons, programs + often store textual data in binaries instead of lists, mainly + because they are more compact (one byte per character instead of two + words per character, as is the case with lists). Using + <c>erlang:list_to_binary/1</c>, an ISO-Latin-1 Erlang string could + be converted into a binary, effectively using bytewise encoding - + one byte per character. This was very convenient for those limited + Erlang strings, but cannot be done for arbitrary Unicode lists.</p> + <p>As the UTF-8 encoding is widely spread and provides some backward + compatibility in the 7-bit ASCII range, it is selected as the + standard encoding for Unicode characters in binaries for Erlang.</p> + <p>The standard binary encoding is used whenever a library function + in Erlang should cope with Unicode data in binaries, but is of + course not enforced when communicating externally. Functions and + bit-syntax exist to encode and decode both UTF-8, UTF-16 and UTF-32 + in binaries. Library functions dealing with binaries and Unicode in + general, however, only deal with the default encoding.</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>iolist</c>s, 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 code points:</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> -<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"> +charlist() = maybe_improper_list(char() | unicode_binary() | charlist(), + unicode_binary() | nil())</code> + <p>The module <seealso + marker="stdlib:unicode"><c>unicode</c></seealso> 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 a user specified Unicode encoding other than UTF-8 (UTF-16 or UTF-32) 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> -<p><marker id="unicode_in_erlang"/>As of Erlang/OTP R16 Erlang can be -written in ISO-latin-1 or Unicode (UTF-8). The details on how to state -the encoding of an Erlang source file can be found in <seealso -marker="stdlib:epp#encoding">epp(3)</seealso>. Strings and comments -can be written using Unicode, but functions still have to be named in -ISO-latin-1 and atoms are restricted to ISO-latin-1. Erlang/OTP R18 is -expected to handle functions named in Unicode as well as Unicode -atoms.</p> -<section> -<title>Bit-syntax</title> -<p>The bit-syntax contains types for coping with binary data in the three main encodings. The types are named <c>utf8</c>, <c>utf16</c> and <c>utf32</c> respectively. The <c>utf16</c> and <c>utf32</c> types can be in a big- or little-endian variant:</p> -<code> + <title>Basic Language Support</title> + <p><marker id="unicode_in_erlang"/>As of Erlang/OTP R16 Erlang + source files can be written in either UTF-8 or bytewise encoding + (a.k.a. <c>latin1</c> encoding). The details on how to state the encoding + of an Erlang source file can be found in + <seealso marker="stdlib:epp#encoding"><c>epp(3)</c></seealso>. Strings and comments + can be written using Unicode, but functions still have to be named + using characters from the ISO-latin-1 character set and atoms are + restricted to the same ISO-latin-1 range. These restrictions in the + language are of course independent of the encoding of the source + file. Erlang/OTP R18 is expected to handle functions named in + Unicode as well as Unicode atoms.</p> + <section> + <title>Bit-syntax</title> + <p>The bit-syntax contains types for coping with binary data in the + three main encodings. The types are named <c>utf8</c>, <c>utf16</c> + and <c>utf32</c> respectively. The <c>utf16</c> and <c>utf32</c> types + can be in a big- or little-endian variant:</p> + <code> <<Ch/utf8,_/binary>> = Bin1, <<Ch/utf16-little,_/binary>> = Bin2, Bin3 = <<$H/utf32-little, $e/utf32-little, $l/utf32-little, $l/utf32-little, - $o/utf32-little>>,</code> -<p>For convenience, literal strings can be encoded with a Unicode encoding in binaries using the following (or similar) syntax:</p> -<code> +$o/utf32-little>>,</code> + <p>For convenience, literal strings can be encoded with a Unicode + encoding in binaries using the following (or similar) syntax:</p> + <code> Bin4 = <<"Hello"/utf16>>,</code> -</section> -<section> -<title>String- and Character-literals</title> -<p>For source code, there is an extension to the <c>\</c>OOO (backslash -followed by three octal numbers) and <c>\x</c>HH (backslash followed by <c>x</c>, -followed by two hexadecimal characters) syntax, namely <c>\x{</c>H ...<c>}</c> (a -backslash followed by an <c>x</c>, followed by left curly bracket, any -number of hexadecimal digits and a terminating right curly bracket). -This allows for entering characters of any codepoint literally in a -string even when the encoding is ISO-latin-1.</p> -</section> -<p>In the shell, if using a Unicode input device, <c>$</c> can be followed directly by a Unicode character producing an integer. In the following example the codepoint of a Cyrillic <c>s</c> is output:</p> -<pre> + </section> + <section> + <title>String and Character Literals</title> + <p>For source code, there is an extension to the <c>\</c>OOO + (backslash followed by three octal numbers) and <c>\x</c>HH + (backslash followed by <c>x</c>, followed by two hexadecimal + characters) syntax, namely <c>\x{</c>H ...<c>}</c> (a backslash + followed by an <c>x</c>, followed by left curly bracket, any + number of hexadecimal digits and a terminating right curly + bracket). This allows for entering characters of any code point + literally in a string even when the encoding of the source file is + bytewise (<c>latin1</c>).</p> + <p>In the shell, if using a Unicode input device, or in source + code stored in UTF-8, <c>$</c> can be followed directly by a + Unicode character producing an integer. In the following example + the code point of a Cyrillic <c>с</c> is output:</p> + <pre> 7> <input>$с.</input> 1089</pre> + </section> + <section> + <title>Heuristic String Detection</title> + <p>In certain output functions and in the output of return values + in the shell, Erlang tries to heuristically detect string data in + lists and binaries. Typically you will see heuristic detection in + a situation like this:</p> + <pre> +1> <input>[97,98,99].</input> +"abc" +2> <input><<97,98,99>>.</input> +<<"abc">> +3> <input><<195,165,195,164,195,182>>.</input> +<<"åäö"/utf8>></pre> + <p>Here the shell will detect lists containing printable + characters or binaries containing printable characters either in + bytewise or UTF-8 encoding. The question here is: what is a + printable character? One view would be that anything the Unicode + standard thinks is printable, will also be printable according to + the heuristic detection. The result would be that almost any list + of integers will be deemed a string, resulting in all sorts of + characters being printed, maybe even characters your terminal does + not have in its font set (resulting in some generic output you + probably will not appreciate). Another way is to keep it backwards + compatible so that only the ISO-Latin-1 character set is used to + detect a string. A third way would be to let the user decide + exactly what Unicode ranges are to be viewed as characters. In + R16B you can select either the whole Unicode range or the + ISO-Latin-1 range by supplying the startup flag <c>+pc + </c><i>Range</i>, where <i>Range</i> is either <c>latin1</c> or + <c>unicode</c>. For backwards compatibility, the default is + <c>latin1</c>. This only controls how heuristic string detection + is done. In the future, more ranges are expected to be added, so + that one can tailor the heuristics to the language and region + relevant to the user.</p> + <p>Lets look at an example with the two different startup options:</p> +<pre> +$ <input>erl +pc latin1</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] + +Eshell V5.10.1 (abort with ^G) +1> <input>[1024].</input> +[1024] +2> <input>[1070,1085,1080,1082,1086,1076].</input> +[1070,1085,1080,1082,1086,1076] +3> <input>[229,228,246].</input> +"åäö" +4> <input><<208,174,208,189,208,184,208,186,208,190,208,180>>.</input> +<<208,174,208,189,208,184,208,186,208,190,208,180>> +5> <input><<229/utf8,228/utf8,246/utf8>>.</input> +<<"åäö"/utf8>> +</pre> +<pre> +$ <input>erl +pc unicode</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] + +Eshell V5.10.1 (abort with ^G) +1> <input>[1024].</input> +"Ѐ" +2> <input>[1070,1085,1080,1082,1086,1076].</input> +"Юникод" +3> <input>[229,228,246].</input> +"åäö" +4> <input><<208,174,208,189,208,184,208,186,208,190,208,180>>.</input> +<<"Юникод"/utf8>> +5> <input><<229/utf8,228/utf8,246/utf8>>.</input> +<<"åäö"/utf8>> +</pre> + <p>In the examples, we can see that the default Erlang shell will + only interpret characters from the ISO-Latin1 range as printable + and will only detect lists or binaries with those "printable" + characters as containing string data. The valid UTF-8 binary + containing "Юникод", will not be printed as a string. When, on the + other hand, started with all Unicode characters printable (<c>+pc + unicode</c>), the shell will output anything containing printable + Unicode data (in binaries either UTF-8 or bytewise encoded) as + string data.</p> + + <p>These heuristics are also used by + <c>io</c>(<c>_lib</c>)<c>:format/2</c> and friends when the + <c>t</c> modifier is used in conjunction with <c>~p</c> or + <c>~P</c>:</p> +<pre> +$ <input>erl +pc latin1</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] + +Eshell V5.10.1 (abort with ^G) +1> <input>io:format("~tp~n",[{<<"åäö">>, <<"åäö"/utf8>>, <<208,174,208,189,208,184,208,186,208,190,208,180>>}]).</input> +{<<"åäö">>,<<"åäö"/utf8>>,<<208,174,208,189,208,184,208,186,208,190,208,180>>} +ok +</pre> +<pre> +$ <input>erl +pc unicode</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] + +Eshell V5.10.1 (abort with ^G) +1> <input>io:format("~tp~n",[{<<"åäö">>, <<"åäö"/utf8>>, <<208,174,208,189,208,184,208,186,208,190,208,180>>}]).</input> +{<<"åäö">>,<<"åäö"/utf8>>,<<"Юникод"/utf8>>} +ok +</pre> + <p>Please observe that this only affects <i>heuristic</i> interpretation + of lists and binaries on output. For example the <c>~ts</c> format + sequence does always output a valid lists of characters, + regardless of the <c>+pc</c> setting, as the programmer has + explicitly requested string output.</p> + </section> </section> <section> -<title>The Interactive Shell</title> -<p>The interactive Erlang shell, when started towards a terminal or started using the <c>werl</c> command on windows, can support Unicode input and output.</p> -<p>On Windows®, proper operation requires that a suitable font is installed and selected for the Erlang application to use. If no suitable font is available on your system, try installing the DejaVu fonts (<c>dejavu-fonts.org</c>), which are freely available and then select that font in the Erlang shell application.</p> -<p>On Unix®-like operating systems, the terminal should be able to handle UTF-8 on input and output (modern versions of XTerm, KDE konsole and the Gnome terminal do for example) and your locale settings have to be proper. As an example, my <c>LANG</c> environment variable is set as this:</p> -<pre> + <title>The Interactive Shell</title> + <p>The interactive Erlang shell, when started towards a terminal or + started using the <c>werl</c> command on windows, can support + Unicode input and output.</p> + <p>On Windows, proper operation requires that a suitable font + is installed and selected for the Erlang application to use. If no + suitable font is available on your system, try installing the DejaVu + fonts (<c>dejavu-fonts.org</c>), which are freely available and then + select that font in the Erlang shell application.</p> + <p>On Unix-like operating systems, the terminal should be able + to handle UTF-8 on input and output (modern versions of XTerm, KDE + konsole and the Gnome terminal do for example) and your locale + settings have to be proper. As an example, my <c>LANG</c> + environment variable is set as this:</p> + <pre> $ <input>echo $LANG</input> en_US.UTF-8</pre> -<p>Actually, most systems handle the <c>LC_CTYPE</c> variable before <c>LANG</c>, so if that is set, it has to be set to <c>UTF-8</c>:</p> -<pre> + <p>Actually, most systems handle the <c>LC_CTYPE</c> variable before + <c>LANG</c>, so if that is set, it has to be set to + <c>UTF-8</c>:</p> + <pre> $ echo <input>$LC_CTYPE</input> en_US.UTF-8</pre> -<p>The <c>LANG</c> or <c>LC_CTYPE</c> setting should be consistent with what the terminal is capable of, there is no portable way for Erlang to ask the actual terminal about its UTF-8 capacity, we have to rely on the language and character type settings.</p> -<p>To investigate what Erlang thinks about the terminal, the <c>io:getopts()</c> call can be used when the shell is started:</p> -<pre> + <p>The <c>LANG</c> or <c>LC_CTYPE</c> setting should be consistent + with what the terminal is capable of, there is no portable way for + Erlang to ask the actual terminal about its UTF-8 capacity, we have + to rely on the language and character type settings.</p> + <p>To investigate what Erlang thinks about the terminal, the + <c>io:getopts()</c> call can be used when the shell is started:</p> + <pre> $ <input>LC_CTYPE=en_US.ISO-8859-1 erl</input> -Erlang R16B (erts-5.10) [source] [async-threads:0] [hipe] [kernel-poll:false] +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] -Eshell V5.10 (abort with ^G) +Eshell V5.10.1 (abort with ^G) 1> <input>lists:keyfind(encoding, 1, io:getopts()).</input> {encoding,latin1} 2> <input>q().</input> ok $ <input>LC_CTYPE=en_US.UTF-8 erl</input> -Erlang R16B (erts-5.10) [source] [async-threads:0] [hipe] [kernel-poll:false] +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] -Eshell V5.10 (abort with ^G) +Eshell V5.10.1 (abort with ^G) 1> <input>lists:keyfind(encoding, 1, io:getopts()).</input> {encoding,unicode} 2></pre> -<p>When (finally?) everything is in order with the locale settings, fonts and the terminal emulator, you probably also have discovered a way to input characters in the script you desire. For testing, the simplest way is to add some keyboard mappings for other languages, usually done with some applet in your desktop environment. In my KDE environment, I start the KDE Control Center (Personal Settings), select "Regional and Accessibility" and then "Keyboard Layout". On Windows XP®, I start Control Panel->Regional and Language Options, select the Language tab and click the Details... button in the square named "Text services and input Languages". Your environment probably provides similar means of changing the keyboard layout. Make sure you have a way to easily switch back and forth between keyboards if you are not used to this, entering commands using a Cyrillic character set is, as an example, not easily done in the Erlang shell.</p> -<p>Now you are set up for some Unicode input and output. The simplest thing to do is of course to enter a string in the shell:</p> -<pre> + + <p>When (finally?) everything is in order with the locale settings, + fonts and the terminal emulator, you probably also have discovered a + way to input characters in the script you desire. For testing, the + simplest way is to add some keyboard mappings for other languages, + usually done with some applet in your desktop environment. In my KDE + environment, I start the KDE Control Center (Personal Settings), + select "Regional and Accessibility" and then "Keyboard Layout". On + Windows XP, I start Control Panel->Regional and Language + Options, select the Language tab and click the Details... button in + the square named "Text services and input Languages". Your + environment probably provides similar means of changing the keyboard + layout. Make sure you have a way to easily switch back and forth + between keyboards if you are not used to this, entering commands + using a Cyrillic character set is, as an example, not easily done in + the Erlang shell.</p> + + <p>Now you are set up for some Unicode input and output. The + simplest thing to do is of course to enter a string in the + shell:</p> + + <pre> $ <input>erl</input> -Erlang R16B (erts-5.10) [source] [async-threads:0] [hipe] [kernel-poll:false] +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] -Eshell V5.10 (abort with ^G) +Eshell V5.10.1 (abort with ^G) 1> <input>lists:keyfind(encoding, 1, io:getopts()).</input> {encoding,unicode} -2> <input>"Юникод"</input> +2> <input>"Юникод".</input> "Юникод" 3> <input>io:format("~ts~n", [v(2)]).</input> Юникод ok 4> </pre> -<p>While strings can be input as Unicode characters, the language elements are still limited to the ISO-latin-1 character set. Only character constants and strings are allowed to be beyond that range:</p> -<pre> + <p>While strings can be input as Unicode characters, the language + elements are still limited to the ISO-latin-1 character set. Only + character constants and strings are allowed to be beyond that + range:</p> + <pre> $ <input>erl</input> -Erlang R16B (erts-5.10) [source] [async-threads:0] [hipe] [kernel-poll:false] +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] -Eshell V5.10 (abort with ^G) -1> <input>$ξ</input> +Eshell V5.10.1 (abort with ^G) +1> <input>$ξ.</input> 958 2> <input>Юникод.</input> * 1: illegal character 2> </pre> </section> <section> -<title>Unicode File Names</title> -<p>Most modern operating systems support Unicode file names in some way or another. There are several different ways to do this and Erlang by default treats the different approaches differently:</p> -<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 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 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 is 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> + <title>Unicode File Names</title> + <p>Most modern operating systems support Unicode file names in some + way or another. There are several different ways to do this and + Erlang by default treats the different approaches differently:</p> + <taglist> + <tag>Mandatory Unicode file naming</tag> + <item> + <p>Windows and, for most common uses, MacOS X enforces Unicode + support for file names. All files created in the file system have + names that can consistently be interpreted. In MacOS X, 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 code points beyond 255, depending + on the content of the actual file system.</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 code points 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 code points 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. By default, Erlang starts in "latin1" + file name mode on such systems, meaning bytewise encoding in file + names. This allows for list representation of all file names in + the system, but, for example, a file named "Östersund.txt", will + appear in <c>file:list_dir/1</c> as either "Östersund.txt" (if + the file name was encoded in bytewise ISO-Latin-1 by the program + creating the file, or more probably as + <c>[195,150,115,116,101,114,115,117,110,100]</c>, which is a + list containing UTF-8 bytes - not what you would want... If you + on the other hand use Unicode file name translation on such a + system, non-UTF-8 file names will simply be ignored by functions + like <c>file:list_dir/1</c>. They can be retrieved with + <c>file:list_dir_all/1</c>, but wrongly encoded file names will + appear as "raw file names".</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> + </item> + </taglist> -<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> + <p>The Unicode file naming support was introduced with OTP release + R14B01. A VM operating in Unicode file name translation mode can + work with files having names in any language or character set (as + long as it is 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 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>In Unicode file name mode, file names given to the BIF <c>open_port/2</c> with the option <c>{spawn_executable,...}</c> are also interpreted as Unicode. So is the parameter list given in the <c>args</c> option available when using <c>spawn_executable</c>. The UTF-8 translation of arguments can be avoided using binaries, see the discussion about raw file names below.</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 MacOS X as the vfs layer of + the OS will accept all your file names as UTF-8 and will not rewrite + them.</p> -<p>It is worth noting that the file <c>encoding</c> options given when opening a file has nothing to do with the file <em>name</em> encoding convention. You can very well open files containing UTF-8 but having file names in ISO-latin-1 or vice versa.</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 was still however + considered experimental in R14B01 and is still not the default on + such systems. Unicode file name translation is turned on with the + <c>+fnu</c> switch to the 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. On Windows and MacOS X, the + default behavior is that of Unicode 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, as stated before, be + changed using the <c>+fnu</c> or <c>+fnl</c> options to the VM, see + the <seealso marker="erts:erl"><c>erl</c></seealso> 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>. The <c>+fnu</c> switch can be followed by <c>w</c>, + <c>i</c> or <c>e</c>, to control how wrongly encoded file names are + to be reported. <c>w</c> means that a warning is sent to the + <c>error_logger</c> whenever a wrongly encoded file name is + "skipped" in directory listings, <c>i</c> means that those wrongly + encoded file names are silently ignored and <c>e</c> means that the + API function will return an error whenever a wrongly encoded file + (or directory) name is encountered. <c>w</c> is the default. Note + that <c>file:read_link/1</c> will always return an error if the link + points to an invalid file name.</p> -<note><p>Erlang drivers and NIF shared objects still can not be named with names containing codepoints beyond 127. This is a known limitation to be removed in a future release. Erlang modules however can, but it is definitely not a good idea and is still considered experimental.</p></note> + <p>In Unicode file name mode, file names given to the BIF + <c>open_port/2</c> with the option <c>{spawn_executable,...}</c> are + also interpreted as Unicode. So is the parameter list given in the + <c>args</c> option available when using <c>spawn_executable</c>. The + UTF-8 translation of arguments can be avoided using binaries, see + the discussion about raw file names below.</p> + + <p>It is worth noting that the file <c>encoding</c> options given + when opening a file has nothing to do with the file <em>name</em> + encoding convention. You can very well open files containing data + encoded in UTF-8 but having file names in bytewise (<c>latin1</c>) encoding + or vice versa.</p> + + <note><p>Erlang drivers and NIF shared objects still can not be + named with names containing code points beyond 127. This is a known + limitation to be removed in a future release. Erlang modules however + can, but it is definitely not a good idea and is still considered + experimental.</p></note> <section> -<title>Notes About Raw File Names and Automatic File Name Conversion</title> + <title>Notes About Raw File Names</title> + + <p>Raw file names were introduced together with Unicode file name + support in erts-5.8.2 (OTP R14B01). The reason "raw file + names" was introduced in the system was 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 "björn" 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 + <<"björn"/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 "björn", + 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. By the common <c>file:list_dir/1</c> function, the wrongly + encoded file names are simply ignored in Unicode file name + translation mode, but by the <c>file:list_dir_all/1</c> function, + the file names with invalid encoding are returned as "raw" + file names, i.e. as binaries.</p> + + <p>The Erlang <c>file</c> module accepts raw file names as + input. <c>open_port({spawn_executable, ...} ...)</c> also accepts + 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 was considered experimental in OTP R14B01 due to + the fact that the initial implementation did not ignore wrongly + encoded file names, so that raw file names could spread unexpectedly + throughout the system. Beginning with R16B, the wrongly encoded file + names are only retrieved by special functions + (e.g. <c>file:list_dir_all/1</c>), so the impact on existing code is + much lower, why it is now supported. Unicode file name translation + is expected to be default in future releases.</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 "björn" 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 <<"björn"/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 "björn", 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, 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 <seealso marker="erts:erl"><c>erl(1)</c></seealso> 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> + <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> -<title>Notes About MacOSX</title> -<p>MacOSXs vfs layer enforces UTF-8 file names in a quite aggressive way. Older versions did this by simply refusing to create non UTF-8 conforming file names, while newer versions replace offending bytes with the sequence "%HH", where HH is the original character in hexadecimal notation. As Unicode translation is enabled by default on MacOSX, the only way to come up against this is to either start the VM with the <c>+fnl</c> flag or to use a raw file name in <c>latin1</c> encoding. In that case, the file can not be opened with the same name as the one used to create this. The problem is by design in newer versions of MacOSX.</p> -<p>MacOSX also reorganizes the names of files so that the representation of accents etc is denormalized, i.e. the character <c>ö</c> is represented as the codepoints [111,776], where 111 is the character <c>o</c> and 776 is a special accent character. This type of denormalized Unicode is otherwise very seldom used and Erlang normalizes those file names on retrieval, so that denormalized file names is not passed up to the Erlang application. In Erlang the file name "björn" is retrieved as [98,106,246,114,110], not as [98,106,117,776,114,110], even though the file system might think differently.</p> + <title>Notes About MacOS X</title> + <p>MacOS X's vfs layer enforces UTF-8 file names in a quite + aggressive way. Older versions did this by simply refusing to create + non UTF-8 conforming file names, while newer versions replace + offending bytes with the sequence "%HH", where HH is the + original character in hexadecimal notation. As Unicode translation + is enabled by default on MacOS X, the only way to come up against + this is to either start the VM with the <c>+fnl</c> flag or to use a + raw file name in bytewise (<c>latin1</c>) encoding. If using a raw + filename, with a bytewise encoding containing characters between 127 + and 255, to create a file, the file can not be opened using the same + name as the one used to create it. There is no remedy for this + behaviour, other than keeping the file names in the right + encoding.</p> + + <p>MacOS X also reorganizes the names of files so that the + representation of accents etc is using the "combining characters", + i.e. the character <c>ö</c> is represented as the code points + [111,776], where 111 is the character <c>o</c> and 776 is the + special accent character "combining diaeresis". This way of + normalizing Unicode is otherwise very seldom used and Erlang + normalizes those file names in the opposite way upon retrieval, so + that file names using combining accents are not passed up to the + Erlang application. In Erlang the file name "björn" is + retrieved as [98,106,246,114,110], not as [98,106,117,776,114,110], + even though the file system might think differently. The + normalization into combining accents are redone when actually + accessing files, so this can usually be ignored by the Erlang + programmer.</p> </section> </section> <section> -<title>Unicode in Environment Variables and Parameters</title> -<p>Environment variables and their interpretation is handled much in the same way as file names. If Unicode file names are enabled, environment variables as well as parameters to the Erlang VM are expected to be in Unicode.</p> -<p>If Unicode file names are enabled, the calls to <seealso marker="kernel:os#getenv/0"><c>os:getenv/0</c></seealso>, <seealso marker="kernel:os#getenv/1"><c>os:getenv/1</c></seealso> and <seealso marker="kernel:os#putenv/2"><c>os:putenv/2</c></seealso> will handle Unicode strings. On Unix-like platforms, the built-in functions will translate environment variables in UTF-8 to/from Unicode strings, possibly with codepoints > 255. On Windows the Unicode versions of the environment system API will be used, also allowing for codepoints > 255.</p> -<p>On Unix-like operating systems, parameters are expected to be UTF-8 without translation if Unicode file names are enabled.</p> + <title>Unicode in Environment and Parameters</title> + <p>Environment variables and their interpretation is handled much in + the same way as file names. If Unicode file names are enabled, + environment variables as well as parameters to the Erlang VM are + expected to be in Unicode.</p> + <p>If Unicode file names are enabled, the calls to + <seealso marker="kernel:os#getenv/0"><c>os:getenv/0</c></seealso>, + <seealso marker="kernel:os#getenv/1"><c>os:getenv/1</c></seealso> and + <seealso marker="kernel:os#putenv/2"><c>os:putenv/2</c></seealso> + will handle Unicode strings. On Unix-like platforms, the built-in + functions will translate environment variables in UTF-8 to/from + Unicode strings, possibly with code points > 255. On Windows the + Unicode versions of the environment system API will be used, also + allowing for code points > 255.</p> + <p>On Unix-like operating systems, parameters are expected to be + UTF-8 without translation if Unicode file names are enabled.</p> </section> <section> -<title>Unicode-aware Modules</title> -<p>Most of the modules in Erlang/OTP are of course Unicode-unaware in the sense that they have no notion of Unicode and really should not have. Typically they handle non-textual or byte-oriented data (like <c>gen_tcp</c> etc).</p> -<p>Modules that actually handle textual data (like <c>io_lib</c>, <c>string</c> etc) are sometimes subject to conversion or extension to be able to handle Unicode characters.</p> -<p>Fortunately, most textual data has been stored in lists and range checking has been sparse, why modules like <c>string</c> works well for Unicode lists with little need for conversion or extension.</p> -<p>Some modules are however changed to be explicitly Unicode-aware. These modules include:</p> -<taglist> -<tag><c>unicode</c></tag> -<item> -<p>The module <seealso marker="stdlib:unicode">unicode</seealso> is obviously Unicode-aware. It contains functions for conversion between different Unicode formats as well as some utilities for identifying byte order marks. Few programs handling Unicode data will survive without this module.</p> -</item> -<tag><c>io</c></tag> -<item> -<p>The <seealso marker="stdlib:io">io</seealso> module has been extended along with the actual I/O-protocol to handle Unicode data. This means that several functions require binaries to be in UTF-8 and there are modifiers to formatting control sequences to allow for outputting of Unicode strings.</p> -</item> -<tag><c>file</c>, <c>group</c>, <c>user</c></tag> -<item> -<p>I/O-servers throughout the system are able both to handle Unicode data and has options for converting data upon actual output or input to/from the device. As shown earlier, the <seealso marker="stdlib:shell">shell</seealso> has support for Unicode terminals and the <seealso marker="kernel:file">file</seealso> module allows for translation to and from various Unicode formats on disk.</p> -<p>The actual reading and writing of files with Unicode data is however not best done with the <c>file</c> module as its interface is byte oriented. A file opened with a Unicode encoding (like UTF-8), is then best read or written using the <seealso marker="stdlib:io">io</seealso> module.</p> -</item> -<tag><c>re</c></tag> -<item> -<p>The <seealso marker="stdlib:re">re</seealso> module allows for matching Unicode strings as a special option. As the library is actually centered on matching in binaries, the Unicode support is UTF-8-centered.</p> -</item> -<tag><c>wx</c></tag> -<item> -<p>The <seealso marker="wx:wx">wx</seealso> graphical library has extensive support for Unicode text</p> -</item> -</taglist> -<p>The module <seealso marker="stdlib:string">string</seealso> works perfect for Unicode strings as well as for ISO-latin-1 strings with the exception of the language-dependent <seealso marker="stdlib:string#to_upper/1">to_upper</seealso> and <seealso marker="stdlib:string#to_lower/1">to_lower</seealso> functions, which are only correct for the ISO-latin-1 character set. Actually they can never function correctly for Unicode characters in their current form, there are language and locale issues as well as multi-character mappings to consider when conversion text between cases. Converting case in an international environment is a big subject not yet addressed in OTP.</p> + <title>Unicode-aware Modules</title> + <p>Most of the modules in Erlang/OTP are of course Unicode-unaware + in the sense that they have no notion of Unicode and really should + not have. Typically they handle non-textual or byte-oriented data + (like <c>gen_tcp</c> etc).</p> + <p>Modules that actually handle textual data (like <c>io_lib</c>, + <c>string</c> etc) are sometimes subject to conversion or extension + to be able to handle Unicode characters.</p> + <p>Fortunately, most textual data has been stored in lists and range + checking has been sparse, why modules like <c>string</c> works well + for Unicode lists with little need for conversion or extension.</p> + <p>Some modules are however changed to be explicitly + Unicode-aware. These modules include:</p> + <taglist> + <tag><c>unicode</c></tag> + <item> + <p>The module <seealso marker="stdlib:unicode"><c>unicode</c></seealso> + is obviously Unicode-aware. It contains functions for conversion + between different Unicode formats as well as some utilities for + identifying byte order marks. Few programs handling Unicode data + will survive without this module.</p> + </item> + <tag><c>io</c></tag> + <item> + <p>The <seealso marker="stdlib:io"><c>io</c></seealso> module has been + extended along with the actual I/O-protocol to handle Unicode + data. This means that several functions require binaries to be + in UTF-8 and there are modifiers to formatting control sequences + to allow for outputting of Unicode strings.</p> + </item> + <tag><c>file</c>, <c>group</c>, <c>user</c></tag> + <item> + <p>I/O-servers throughout the system are able to handle + Unicode data and has options for converting data upon actual + output or input to/from the device. As shown earlier, the + <seealso marker="stdlib:shell"><c>shell</c></seealso> has support for + Unicode terminals and the <seealso + marker="kernel:file"><c>file</c></seealso> module allows for + translation to and from various Unicode formats on disk.</p> + <p>The actual reading and writing of files with Unicode data is + however not best done with the <c>file</c> module as its + interface is byte oriented. A file opened with a Unicode + encoding (like UTF-8), is then best read or written using the + <seealso marker="stdlib:io"><c>io</c></seealso> module.</p> + </item> + <tag><c>re</c></tag> + <item> + <p>The <seealso marker="stdlib:re"><c>re</c></seealso> module allows + for matching Unicode strings as a special option. As the library + is actually centered on matching in binaries, the Unicode + support is UTF-8-centered.</p> + </item> + <tag><c>wx</c></tag> + <item> + <p>The <seealso marker="wx:wx"><c>wx</c></seealso> graphical library + has extensive support for Unicode text</p> + </item> + </taglist> + <p>The module <seealso + marker="stdlib:string"><c>string</c></seealso> works perfectly for + Unicode strings as well as for ISO-latin-1 strings with the + exception of the language-dependent <seealso + marker="stdlib:string#to_upper/1"><c>to_upper</c></seealso> and + <seealso marker="stdlib:string#to_lower/1"><c>to_lower</c></seealso> + functions, which are only correct for the ISO-latin-1 character + set. Actually they can never function correctly for Unicode + characters in their current form, as there are language and locale + issues as well as multi-character mappings to consider when + converting text between cases. Converting case in an international + environment is a big subject not yet addressed in OTP.</p> </section> <section> -<title>Unicode Recipes</title> -<p>When starting with Unicode, one often stumbles over some common issues. I try to outline some methods of dealing with Unicode data in this section.</p> + <title>Unicode Data in Files</title> + <p>The fact that Erlang as such can handle Unicode data in many forms + does not automatically mean that the content of any file can be + Unicode text. The external entities such as ports or I/O-servers are + not generally Unicode capable.</p> + <p>Ports are always byte oriented, so before sending data that you + are not sure is bytewise encoded to a port, make sure to encode it + in a proper Unicode encoding. Sometimes this will mean that only + part of the data shall be encoded as e.g. UTF-8, some parts may be + binary data (like a length indicator) or something else that shall + not undergo character encoding, so no automatic translation is + present.</p> + <p>I/O-servers behave a little differently. The I/O-servers connected + to terminals (or stdout) can usually cope with Unicode data + regardless of the <c>encoding</c> option. This is convenient when + one expects a modern environment but do not want to crash when + writing to a archaic terminal or pipe. Files on the other hand are + more picky. A file can have an encoding option which makes it + generally usable by the io-module (e.g. <c>{encoding,utf8}</c>), but + is by default opened as a byte oriented file. The <seealso + marker="kernel:file"><c>file</c></seealso> module is byte oriented, why only + ISO-Latin-1 characters can be written using that module. The + <seealso marker="stdlib:io"><c>io</c></seealso> module is the one to use if + Unicode data is to be output to a file with other <c>encoding</c> + than <c>latin1</c> (a.k.a. bytewise encoding). It is slightly + confusing that a file opened with + e.g. <c>file:open(Name,[read,{encoding,utf8}])</c>, cannot be + properly read using <c>file:read(File,N)</c> but you have to use the + <c>io</c> module to retrieve the Unicode data from it. The reason is + that <c>file:read</c> and <c>file:write</c> (and friends) are purely + byte oriented, and should so be, as that is the way to access + files other than text files - byte by byte. Just as with ports, you + can of course write encoded data into a file by "manually" converting + the data to the encoding of choice (using the <seealso + marker="stdlib:unicode"><c>unicode</c></seealso> module or the bit syntax) + and then output it on a bytewise encoded (<c>latin1</c>) file.</p> + <p>The rule of thumb is that the <seealso + marker="kernel:file"><c>file</c></seealso> module should be used for files + opened for bytewise access (<c>{encoding,latin1}</c>) and the + <seealso marker="stdlib:io"><c>io</c></seealso> module should be used when + accessing files with any other encoding + (e.g. <c>{encoding,uf8}</c>).</p> + + <p>Functions reading Erlang syntax from files generally recognize + the <c>coding:</c> comment and can therefore handle Unicode data on + input. When writing Erlang Terms to a file, you should insert + such comments when applicable:</p> + <pre> +$ <input>erl +fna +pc unicode</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] + +Eshell V5.10.1 (abort with ^G) +1> <input>file:write_file("test.term",<<"%% coding: utf-8\n[{\"Юникод\",4711}].\n"/utf8>>).</input> +ok +2> <input>file:consult("test.term").</input> +{ok,[[{"Юникод",4711}]]} + </pre> +</section> +<section> + <title><marker id="unicode_options_summary"/>Summary of Options</title> + <p>The Unicode support is controlled by both command line switches, + some standard environment variables and the version of OTP you are + using. Most options affect mainly the way Unicode data is displayed, + not the actual functionality of the API's in the standard + libraries. This means that Erlang programs usually do not + need to concern themselves with these options, they are more for the + development environment. An Erlang program can be written so that it + works well regardless of the type of system or the Unicode options + that are in effect.</p> + + <p>Here follows a summary of the settings affecting Unicode:</p> + <taglist> + <tag>The <c>LANG</c> and <c>LC_CTYPE</c> environment variables</tag> + <item> + <p>The language setting in the OS mainly affects the shell. The + terminal (i.e. the group leader) will operate with <c>{encoding, + unicode}</c> only if the environment tells it that UTF-8 is + allowed. This setting should correspond to the actual terminal + you are using.</p> + <p>The environment can also affect file name interpretation, if + Erlang is started with the <c>+fna</c> flag.</p> + <p>You can check the setting of this by calling + <c>io:getopts()</c>, which will give you an option list + containing <c>{encoding,unicode}</c> or + <c>{encoding,latin1}</c>.</p> + </item> + <tag>The <c>+pc </c>{<c>unicode</c>|<c>latin1</c>} flag to + <seealso marker="erts:erl"><c>erl(1)</c></seealso></tag> + <item> + <p>This flag affects what is interpreted as string data when + doing heuristic string detection in the shell and in + <c>io</c>/<c>io_lib:format</c> with the <c>"~tp"</c> and + <c>~tP</c> formatting instructions, as described above.</p> + <p>You can check this option by calling io:printable_range/0, + which in R16B will return <c>unicode</c> or <c>latin1</c>. To be + compatible with future (expected) extensions to the settings, + one should rather use <c>io_lib:printable_list/1</c> to check if + a list is printable according to the setting. That function will + take into account new possible settings returned from + <c>io:printable_range/0</c>.</p> + </item> + <tag>The <c>+fn</c>{<c>l</c>|<c>a</c>|<c>u</c>} + [{<c>w</c>|<c>i</c>|<c>e</c>}] + flag to <seealso marker="erts:erl"><c>erl(1)</c></seealso></tag> + <item> + <p>This flag affects how the file names are to be interpreted. On + operating systems with transparent file naming, this has to be + specified to allow for file naming in Unicode characters (and + for correct interpretation of file names containing characters + > 255.</p> + <p><c>+fnl</c> means bytewise interpretation of file names, which + was the usual way to represent ISO-Latin-1 file names before + UTF-8 file naming got widespread. This is the default on all + Unix-like operating systems except MacOS X.</p> + <p><c>+fnu</c> means that file names are encoded in UTF-8, which + is nowadays the common scheme (although not enforced).</p> + <p><c>+fna</c> means that you automatically select between + <c>+fnl</c> and <c>+fnu</c>, based on the <c>LANG</c> and + <c>LC_CTYPE</c> environment variables. This is optimistic + heuristics indeed, nothing enforces a user to have a terminal + with the same encoding as the file system, but usually, this is + the case. This might be the default behavior in a future + release.</p> + + <p>The file name translation mode can be read with the + <c>file:native_name_encoding/0</c> function, which returns + <c>latin1</c> (meaning bytewise encoding) or <c>utf8</c>.</p> + </item> + <tag><seealso marker="stdlib:epp#default_encoding/0"> + <c>epp:default_encoding/0</c></seealso></tag> + <item> + <p>This function returns the default encoding for Erlang source + files (if no encoding comment is present) in the currently + running release. For R16 this returns <c>latin1</c> (meaning + bytewise encoding). In R17 and forward it is expected to return + <c>utf8</c>.</p> + <p>The encoding of each file can be specified using comments as + described in + <seealso marker="stdlib:epp#encoding"><c>epp(3)</c></seealso>.</p> + </item> + <tag><seealso marker="stdlib:io#setopts/1"><c>io:setopts/</c>{<c>1</c>,<c>2</c>}</seealso> and the <c>-oldshell</c>/<c>-noshell</c> flags.</tag> + <item> + <p>When Erlang is started with <c>-oldshell</c> or + <c>-noshell</c>, the I/O-server for <c>standard_io</c> is default + set to bytewise encoding, while an interactive shell defaults to + what the environment variables says.</p> + <p>With the <c>io:setopts/2</c> function you can set the + encoding of a file or other I/O-server. This can also be set when + opening a file. Setting the terminal (or other + <c>standard_io</c> server) unconditionally to the option + <c>{encoding,utf8}</c> will for example make UTF-8 encoded characters + being written to the device regardless of how Erlang was started or + the users environment.</p> + <p>Opening files with <c>encoding</c> option is convenient when + writing or reading text files in a known encoding.</p> + <p>You can retrieve the <c>encoding</c> setting for an I/O-server + using <seealso + marker="stdlib:io#getopts/1"><c>io:getopts()</c></seealso>.</p> + </item> + </taglist> +</section> <section> -<title>Byte Order Marks</title> -<p>A common method of identifying encoding in text-files is to put a byte order mark (BOM) first in the file. The BOM is the codepoint 16#FEFF encoded in the same way as the rest of the file. If such a file is to be read, the first few bytes (depending on encoding) is not part of the actual text. This code outlines how to open a file which is believed to have a BOM and set the files encoding and position for further sequential reading (preferably using the <seealso marker="stdlib:io">io</seealso> module). Note that error handling is omitted from the code:</p> + <title>Recipes</title> + <p>When starting with Unicode, one often stumbles over some common + issues. I try to outline some methods of dealing with Unicode data + in this section.</p> + <section> + <title>Byte Order Marks</title> + <p>A common method of identifying encoding in text-files is to put + a byte order mark (BOM) first in the file. The BOM is the + code point 16#FEFF encoded in the same way as the rest of the + file. If such a file is to be read, the first few bytes (depending + on encoding) is not part of the actual text. This code outlines + how to open a file which is believed to have a BOM and set the + files encoding and position for further sequential reading + (preferably using the <seealso marker="stdlib:io"><c>io</c></seealso> + module). Note that error handling is omitted from the code:</p> <code> open_bom_file_for_reading(File) -> {ok,F} = file:open(File,[read,binary]), @@ -276,8 +1119,15 @@ open_bom_file_for_reading(File) -> io:setopts(F,[{encoding,Type}]), {ok,F}. </code> -<p>The <c>unicode:bom_to_encoding/1</c> function identifies the encoding from a binary of at least four bytes. It returns, along with an term suitable for setting the encoding of the file, the actual length of the BOM, so that the file position can be set accordingly. Note that <c>file:position/2</c> always works on byte-offsets, so that the actual byte-length of the BOM is needed.</p> -<p>To open a file for writing and putting the BOM first is even simpler:</p> + <p>The <c>unicode:bom_to_encoding/1</c> function identifies the + encoding from a binary of at least four bytes. It returns, along + with an term suitable for setting the encoding of the file, the + actual length of the BOM, so that the file position can be set + accordingly. Note that <c>file:position/2</c> always works on + byte-offsets, so that the actual byte-length of the BOM is + needed.</p> + <p>To open a file for writing and putting the BOM first is even + simpler:</p> <code> open_bom_file_for_writing(File,Encoding) -> {ok,F} = file:open(File,[write,binary]), @@ -285,38 +1135,95 @@ open_bom_file_for_writing(File,Encoding) -> io:setopts(F,[{encoding,Encoding}]), {ok,F}. </code> -<p>In both cases the file is then best processed using the <c>io</c> module, as the functions in <c>io</c> can handle codepoints beyond the ISO-latin-1 range.</p> -</section> -<section> -<title>Formatted Input and Output</title> -<p>When reading and writing to Unicode-aware entities, like the User or a file opened for Unicode translation, you will probably want to format text strings using the functions in <seealso marker="stdlib:io">io</seealso> or <seealso marker="stdlib:io_lib">io_lib</seealso>. For backward compatibility reasons, these functions do not accept just any list as a string, but require a special <em>translation modifier</em> when working with Unicode texts. The modifier is <c>t</c>. When applied to the <c>s</c> control character in a formatting string, it accepts all Unicode codepoints and expect binaries to be in UTF-8:</p> -<pre> + <p>In both cases the file is then best processed using the + <c>io</c> module, as the functions in <c>io</c> can handle code + points beyond the ISO-latin-1 range.</p> + </section> + <section> + <title>Formatted I/O</title> + <p>When reading and writing to Unicode-aware entities, like the + User or a file opened for Unicode translation, you will probably + want to format text strings using the functions in <seealso + marker="stdlib:io"><c>io</c></seealso> or <seealso + marker="stdlib:io_lib"><c>io_lib</c></seealso>. For backward + compatibility reasons, these functions do not accept just any list + as a string, but require a special <em>translation modifier</em> + when working with Unicode texts. The modifier is <c>t</c>. When + applied to the <c>s</c> control character in a formatting string, + it accepts all Unicode code points and expect binaries to be in + UTF-8:</p> + <pre> 1> <input>io:format("~ts~n",[<<"åäö"/utf8>>]).</input> åäö ok 2> <input>io:format("~s~n",[<<"åäö"/utf8>>]).</input> åäö ok</pre> -<p>Obviously the second <c>io:format/2</c> gives undesired output because the UTF-8 binary is not in latin1. Because ISO-latin-1 is still the defined character set of Erlang, the non prefixed <c>s</c> control character expects ISO-latin-1 in binaries as well as lists.</p> -<p>As long as the data is always lists, the <c>t</c> modifier can be used for any string, but when binary data is involved, care must be taken to make the right choice of formatting characters.</p> -<p>The function <c>format/2</c> in <c>io_lib</c> behaves similarly. This function is defined to return a deep list of characters and the output could easily be converted to binary data for outputting on a device of any kind by a simple <c>erlang:list_to_binary/1</c>. When the translation modifier is used, the list can however contain characters that cannot be stored in one byte. The call to <c>erlang:list_to_binary/1</c> will in that case fail. However, if the I/O server you want to communicate with is Unicode-aware, the list returned can still be used directly:</p> + <p>Obviously the second <c>io:format/2</c> gives undesired output + because the UTF-8 binary is not in latin1. For backward + compatibility, the non prefixed <c>s</c> control character expects + bytewise encoded ISO-latin-1 characters in binaries and lists + containing only code points < 256.</p> + <p>As long as the data is always lists, the <c>t</c> modifier can + be used for any string, but when binary data is involved, care + must be taken to make the right choice of formatting characters. A + bytewise encoded binary will also be interpreted as a string and + printed even when using <c>~ts</c>, but it might be mistaken for a + valid UTF-8 string and one should therefore avoid using the + <c>~ts</c> control if the binary contains bytewise encoded + characters and not UTF-8.</p> + <p>The function <c>format/2</c> in <c>io_lib</c> behaves + similarly. This function is defined to return a deep list of + characters and the output could easily be converted to binary data + for outputting on a device of any kind by a simple + <c>erlang:list_to_binary/1</c>. When the translation modifier is + used, the list can however contain characters that cannot be + stored in one byte. The call to <c>erlang:list_to_binary/1</c> + will in that case fail. However, if the I/O server you want to + communicate with is Unicode-aware, the list returned can still be + used directly:</p> <pre> -$ <input>erl</input> -Erlang R16B (erts-5.10) [source] [async-threads:0] [hipe] [kernel-poll:false] +$ <input>erl +pc unicode</input> +Erlang R16B (erts-5.10.1) [source] [async-threads:0] [hipe] [kernel-poll:false] -Eshell V5.10 (abort with ^G) +Eshell V5.10.1 (abort with ^G) 1> <input>io_lib:format("~ts~n", ["Γιούνικοντ"]).</input> ["Γιούνικοντ","\n"] 2> <input>io:put_chars(io_lib:format("~ts~n", ["Γιούνικοντ"])).</input> Γιούνικοντ ok</pre> -<p>The Unicode string is returned as a Unicode list, which is recognized as such since the Erlang shell uses the Unicode encoding. The Unicode list is valid input to the <seealso marker="stdlib:io#put_chars/2">io:put_chars/2</seealso> function, so data can be output on any Unicode capable device. If the device is a terminal, characters will be output in the <c>\x{</c>H ...<c>}</c> format if encoding is <c>latin1</c> otherwise in UTF-8 (for the non-interactive terminal - "oldshell" or "noshell") or whatever is suitable to show the character properly (for an interactive terminal - the regular shell). The bottom line is that you can always send Unicode data to the <c>standard_io</c> device. Files will however only accept Unicode codepoints beyond ISO-latin-1 if <c>encoding</c> is set to something else than <c>latin1</c>.</p> -</section> -<section> -<title>Heuristic Identification of UTF-8</title> -<p>While it iss strongly encouraged that the actual encoding of characters in binary data is known prior to processing, that is not always possible. On a typical Linux® system, there is a mix of UTF-8 and ISO-latin-1 text files and there are seldom any BOM's in the files to identify them.</p> -<p>UTF-8 is designed in such a way that ISO-latin-1 characters with numbers beyond the 7-bit ASCII range are seldom considered valid when decoded as UTF-8. Therefore one can usually use heuristics to determine if a file is in UTF-8 or if it is encoded in ISO-latin-1 (one byte per character) encoding. The <c>unicode</c> module can be used to determine if data can be interpreted as UTF-8:</p> -<code> + <p>The Unicode string is returned as a Unicode list, which is + recognized as such since the Erlang shell uses the Unicode + encoding (and is started with all Unicode characters considered + printable). The Unicode list is valid input to the <seealso + marker="stdlib:io#put_chars/2"><c>io:put_chars/2</c></seealso> function, + so data can be output on any Unicode capable device. If the device + is a terminal, characters will be output in the <c>\x{</c>H + ...<c>}</c> format if encoding is <c>latin1</c> otherwise in UTF-8 + (for the non-interactive terminal - "oldshell" or "noshell") or + whatever is suitable to show the character properly (for an + interactive terminal - the regular shell). The bottom line is that + you can always send Unicode data to the <c>standard_io</c> + device. Files will however only accept Unicode code points beyond + ISO-latin-1 if <c>encoding</c> is set to something else than + <c>latin1</c>.</p> + </section> + <section> + <title>Heuristic Identification of UTF-8</title> + <p>While it is + strongly encouraged that the actual encoding of characters in + binary data is known prior to processing, that is not always + possible. On a typical Linux system, there is a mix of UTF-8 + and ISO-latin-1 text files and there are seldom any BOM's in the + files to identify them.</p> + <p>UTF-8 is designed in such a way that ISO-latin-1 characters + with numbers beyond the 7-bit ASCII range are seldom considered + valid when decoded as UTF-8. Therefore one can usually use + heuristics to determine if a file is in UTF-8 or if it is encoded + in ISO-latin-1 (one byte per character) encoding. The + <c>unicode</c> module can be used to determine if data can be + interpreted as UTF-8:</p> + <code> heuristic_encoding_bin(Bin) when is_binary(Bin) -> case unicode:characters_to_binary(Bin,utf8,utf8) of Bin -> @@ -324,9 +1231,16 @@ heuristic_encoding_bin(Bin) when is_binary(Bin) -> _ -> latin1 end. -</code> -<p>If one does not have a complete binary of the file content, one could instead chunk through the file and check part by part. The return-tuple <c>{incomplete,Decoded,Rest}</c> from <c>unicode:characters_to_binary/{1,2,3}</c> comes in handy. The incomplete rest from one chunk of data read from the file is prepended to the next chunk and we therefore circumvent the problem of character boundaries when reading chunks of bytes in UTF-8 encoding:</p> -<code> + </code> + <p>If one does not have a complete binary of the file content, one + could instead chunk through the file and check part by part. The + return-tuple <c>{incomplete,Decoded,Rest}</c> from + <c>unicode:characters_to_binary/{1,2,3}</c> comes in handy. The + incomplete rest from one chunk of data read from the file is + prepended to the next chunk and we therefore circumvent the + problem of character boundaries when reading chunks of bytes in + UTF-8 encoding:</p> + <code> heuristic_encoding_file(FileName) -> {ok,F} = file:open(FileName,[read,binary]), loop_through_file(F,<<>>,file:read(F,1024)). @@ -344,9 +1258,12 @@ loop_through_file(F,Acc,{ok,Bin}) when is_binary(Bin) -> Res when is_binary(Res) -> loop_through_file(F,<<>>,file:read(F,1024)) end. -</code> -<p>Another option is to try to read the whole file in utf8 encoding and see if it fails. Here we need to read the file using <c>io:get_chars/3</c>, as we have to succeed in reading characters with a codepoint over 255:</p> -<code> + </code> + <p>Another option is to try to read the whole file in UTF-8 + encoding and see if it fails. Here we need to read the file using + <c>io:get_chars/3</c>, as we have to succeed in reading characters + with a code point over 255:</p> + <code> heuristic_encoding_file2(FileName) -> {ok,F} = file:open(FileName,[read,binary,{encoding,utf8}]), loop_through_file2(F,io:get_chars(F,'',1024)). @@ -357,7 +1274,68 @@ loop_through_file2(_,{error,_Err}) -> latin1; loop_through_file2(F,Bin) when is_binary(Bin) -> loop_through_file2(F,io:get_chars(F,'',1024)). -</code> -</section> + </code> + </section> + <section> + <title>Lists of UTF-8 Bytes</title> + <p>For various reasons, you may find yourself having a list of + UTF-8 bytes. This is not a regular string of Unicode characters as + each element in the list does not contain one character. Instead + you get the "raw" UTF-8 encoding that you have in binaries. This + is easily converted to a proper Unicode string by first converting + byte per byte into a binary and then converting the binary of + UTF-8 encoded characters back to a Unicode string:</p> + <code> + utf8_list_to_string(StrangeList) -> + unicode:characters_to_list(list_to_binary(StrangeList)). + </code> + </section> + <section> + <title>Double UTF-8 Encoding</title> + <p>When working with binaries, you may get the horrible "double + UTF-8 encoding", where strange characters are encoded in your + binaries or files that you did not expect. What you may have got, + is a UTF-8 encoded binary that is for the second time encoded as + UTF-8. A common situation is where you read a file, byte by byte, + but the actual content is already UTF-8. If you then convert the + bytes to UTF-8, using i.e. the <c>unicode</c> module or by + writing to a file opened with the <c>{encoding,utf8}</c> + option. You will have each <i>byte</i> in the in the input file + encoded as UTF-8, not each character of the original text (one + character may have been encoded in several bytes). There is no + real remedy for this other than being very sure of which data is + actually encoded in which format, and never convert UTF-8 data + (possibly read byte by byte from a file) into UTF-8 again.</p> + <p>The by far most common situation where this happens, is when + you get lists of UTF-8 instead of proper Unicode strings, and then + convert them to UTF-8 in a binary or on a file:</p> + <code> + wrong_thing_to_do() -> + {ok,Bin} = file:read_file("an_utf8_encoded_file.txt"), + MyList = binary_to_list(Bin), %% Wrong! It is an utf8 binary! + {ok,C} = file:open("catastrophe.txt",[write,{encoding,utf8}]), + io:put_chars(C,MyList), %% Expects a Unicode string, but get UTF-8 + %% bytes in a list! + file:close(C). %% The file catastrophe.txt contains more or less unreadable + %% garbage! + </code> + <p>Make very sure you know what a binary contains before + converting it to a string. If no other option exists, try + heuristics:</p> + <code> + if_you_can_not_know() -> + {ok,Bin} = file:read_file("maybe_utf8_encoded_file.txt"), + MyList = case unicode:characters_to_list(Bin) of + L when is_list(L) -> + L; + _ -> + binary_to_list(Bin) %% The file was bytewise encoded + end, + %% Now we know that the list is a Unicode string, not a list of UTF-8 bytes + {ok,G} = file:open("greatness.txt",[write,{encoding,utf8}]), + io:put_chars(G,MyList), %% Expects a Unicode string, which is what it gets! + file:close(G). %% The file contains valid UTF-8 encoded Unicode characters! + </code> + </section> </section> </chapter> diff --git a/lib/stdlib/src/binary.erl b/lib/stdlib/src/binary.erl index 41b6ab1d5f..4850a59eb6 100644 --- a/lib/stdlib/src/binary.erl +++ b/lib/stdlib/src/binary.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2010-2012. All Rights Reserved. +%% Copyright Ericsson AB 2010-2013. 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 @@ -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..42ef3679a2 100644 --- a/lib/stdlib/src/filelib.erl +++ b/lib/stdlib/src/filelib.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 @@ -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..f8345559c4 100644 --- a/lib/stdlib/test/erl_lint_SUITE.erl +++ b/lib/stdlib/test/erl_lint_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1999-2012. 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 @@ -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..b6c94a6f6d 100644 --- a/lib/stdlib/test/ets_SUITE.erl +++ b/lib/stdlib/test/ets_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 1996-2012. All Rights Reserved. +%% Copyright Ericsson AB 1996-2013. 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 @@ -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..4ca8680fc9 100644 --- a/lib/stdlib/test/io_proto_SUITE.erl +++ b/lib/stdlib/test/io_proto_SUITE.erl @@ -1,7 +1,7 @@ %% %% %CopyrightBegin% %% -%% Copyright Ericsson AB 2009-2012. All Rights Reserved. +%% Copyright Ericsson AB 2009-2013. 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 @@ -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) -> diff --git a/lib/stdlib/vsn.mk b/lib/stdlib/vsn.mk index 33d7a57cc3..c1467697e3 100644 --- a/lib/stdlib/vsn.mk +++ b/lib/stdlib/vsn.mk @@ -1 +1 @@ -STDLIB_VSN = 1.19 +STDLIB_VSN = 1.19.1 |