diff options
Diffstat (limited to 'lib/stdlib/doc')
24 files changed, 1437 insertions, 134 deletions
diff --git a/lib/stdlib/doc/src/Makefile b/lib/stdlib/doc/src/Makefile index 13b9b2ff18..b558697d63 100644 --- a/lib/stdlib/doc/src/Makefile +++ b/lib/stdlib/doc/src/Makefile @@ -1,19 +1,19 @@ # # %CopyrightBegin% -# -# Copyright Ericsson AB 1997-2009. All Rights Reserved. -# +# +# Copyright Ericsson AB 1997-2010. All Rights Reserved. +# # The contents of this file are subject to the Erlang Public License, # Version 1.1, (the "License"); you may not use this file except in # compliance with the License. You should have received a copy of the # Erlang Public License along with this software. If not, it can be # retrieved online at http://www.erlang.org/. -# +# # Software distributed under the License is distributed on an "AS IS" # basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See # the License for the specific language governing rights and limitations # under the License. -# +# # %CopyrightEnd% # include $(ERL_TOP)/make/target.mk @@ -40,6 +40,7 @@ XML_REF3_FILES = \ array.xml \ base64.xml \ beam_lib.xml \ + binary.xml \ c.xml \ calendar.xml \ dets.xml \ diff --git a/lib/stdlib/doc/src/beam_lib.xml b/lib/stdlib/doc/src/beam_lib.xml index b9286f1402..adc411e272 100644 --- a/lib/stdlib/doc/src/beam_lib.xml +++ b/lib/stdlib/doc/src/beam_lib.xml @@ -341,15 +341,17 @@ chunkref() = chunkname() | chunkid()</code> <v>Beam1 = Beam2 = beam()</v> <v>Reason = {modules_different, Module1, Module2}</v> <v> | {chunks_different, ChunkId}</v> + <v> | different_chunks</v> <v> | Reason1 -- see info/1</v> <v> Module1 = Module2 = atom()</v> <v> ChunkId = chunkid()</v> </type> <desc> <p>Compares the contents of two BEAM files. If the module names - are the same, and the chunks with the identifiers - <c>"Code"</c>, <c>"ExpT"</c>, <c>"ImpT"</c>, <c>"StrT"</c>, - and <c>"Atom"</c> have the same contents in both files, + are the same, and all chunks except for the <c>"CInf"</c> chunk + (the chunk containing the compilation information which is + returned by <c>Module:module_info(compile)</c>) + have the same contents in both files, <c>ok</c> is returned. Otherwise an error message is returned.</p> </desc> </func> diff --git a/lib/stdlib/doc/src/binary.xml b/lib/stdlib/doc/src/binary.xml new file mode 100644 index 0000000000..c5eb81a86a --- /dev/null +++ b/lib/stdlib/doc/src/binary.xml @@ -0,0 +1,729 @@ +<?xml version="1.0" encoding="latin1" ?> +<!DOCTYPE erlref SYSTEM "erlref.dtd"> + +<erlref> + <header> + <copyright> + <year>2009</year> + <year>2010</year> + <holder>Ericsson AB, All Rights Reserved</holder> + </copyright> + <legalnotice> + 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 + compliance with the License. You should have received a copy of the + Erlang Public License along with this software. If not, it can be + retrieved on line at http://www.erlang.org/. + + Software distributed under the License is distributed on an "AS IS" + basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See + the License for the specific language governing rights and limitations + under the License. + + The Initial Developer of the Original Code is Ericsson AB. + </legalnotice> + + <title>binary</title> + <prepared>Patrik Nyblom</prepared> + <responsible>Kenneth Lundin</responsible> + <docno>1</docno> + <approved></approved> + <checked></checked> + <date>2010-05-05</date> + <rev>A</rev> + <file>binary.xml</file> + </header> + <module>binary</module> + <modulesummary>Library for handling binary data</modulesummary> + <description> + + <p>This module contains functions for manipulating byte-oriented + binaries. Although the majority of functions could be implemented + using bit-syntax, the functions in this library are highly + optimized and are expected to either execute faster or consume + less memory (or both) than a counterpart written in pure Erlang.</p> + + <p>The module is implemented according to the EEP (Erlang Enhancement Proposal) 31.</p> + + <note> + <p> + The library handles byte-oriented data. Bitstrings that are not + binaries (does not contain whole octets of bits) will result in a <c>badarg</c> + exception being thrown from any of the functions in this + module. + </p> + </note> + + + </description> + <section> + <title>DATA TYPES</title> + <code type="none"> + cp() + - Opaque data-type representing a compiled search-pattern. Guaranteed to be a tuple() + to allow programs to distinguish it from non precompiled search patterns. + </code> + <code type="none"> + part() = {Start,Length} + Start = int() + Length = int() + - A representaion of a part (or range) in a binary. Start is a + zero-based offset into a binary() and Length is the length of + that part. As input to functions in this module, a reverse + part specification is allowed, constructed with a negative + Length, so that the part of the binary begins at Start + + Length and is -Length long. This is useful for referencing the + last N bytes of a binary as {size(Binary), -N}. The functions + in this module always return part()'s with positive Length. + </code> + </section> + <funcs> + <func> + <name>at(Subject, Pos) -> int()</name> + <fsummary>Returns the byte at a specific position in a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pos = int() >= 0</v> + </type> + <desc> + + <p>Returns the byte at position <c>Pos</c> (zero-based) in the binary + <c>Subject</c> as an integer. If <c>Pos</c> >= <c>byte_size(Subject)</c>, + a <c>badarg</c> + exception is raised.</p> + + </desc> + </func> + <func> + <name>bin_to_list(Subject) -> list()</name> + <fsummary>Convert a binary to a list of integers</fsummary> + <type> + <v>Subject = binary()</v> + </type> + <desc> + <p>The same as <c>bin_to_list(Subject,{0,byte_size(Subject)})</c>.</p> + </desc> + </func> + <func> + <name>bin_to_list(Subject, PosLen) -> list()</name> + <fsummary>Convert a binary to a list of integers</fsummary> + <type> + <v>Subject = binary()</v> + <v>PosLen = part()</v> + </type> + <desc> + + <p>Converts <c>Subject</c> to a list of <c>int()</c>s, each representing + the value of one byte. The <c>part()</c> denotes which part of the + <c>binary()</c> to convert. Example:</p> + +<code> +1> binary:bin_to_list(<<"erlang">>,{1,3}). +"rla" +%% or [114,108,97] in list notation. +</code> + <p>If <c>PosLen</c> in any way references outside the binary, a <c>badarg</c> exception is raised.</p> + </desc> + </func> + <func> + <name>bin_to_list(Subject, Pos, Len) -> list()</name> + <fsummary>Convert a binary to a list of integers</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pos = int()</v> + <v>Len = int()</v> + </type> + <desc> + <p>The same as<c> bin_to_list(Subject,{Pos,Len})</c>.</p> + </desc> + </func> + <func> + <name>compile_pattern(Pattern) -> cp()</name> + <fsummary>Pre-compiles a binary search pattern</fsummary> + <type> + <v>Pattern = binary() | [ binary() ]</v> + </type> + <desc> + + <p>Builds an internal structure representing a compilation of a + search-pattern, later to be used in the <seealso marker="#match-3">match/3</seealso>, + <seealso marker="#matches-3">matches/3</seealso>, + <seealso marker="#split-3">split/3</seealso> or + <seealso marker="#replace-4">replace/4</seealso> + functions. The <c>cp()</c> returned is guaranteed to be a + <c>tuple()</c> to allow programs to distinguish it from non + pre-compiled search patterns</p> + + <p>When a list of binaries is given, it denotes a set of + alternative binaries to search for. I.e if + <c>[<<"functional">>,<<"programming">>]</c> + is given as <c>Pattern</c>, this + means "either <c><<"functional">></c> or + <c><<"programming">></c>". The pattern is a set of + alternatives; when only a single binary is given, the set has + only one element. The order of alternatives in a pattern is not significant.</p> + + <p>The list of binaries used for search alternatives shall be flat and proper.</p> + + <p>If <c>Pattern</c> is not a binary or a flat proper list of binaries with length > 0, + a <c>badarg</c> exception will be raised.</p> + + </desc> + </func> + <func> + <name>copy(Subject) -> binary()</name> + <fsummary>Creates a duplicate of a binary</fsummary> + <type> + <v>Subject = binary()</v> + </type> + <desc> + <p>The same as <c>copy(Subject, 1)</c>.</p> + </desc> + </func> + <func> + <name>copy(Subject,N) -> binary()</name> + <fsummary>Duplicates a binary N times and creates a new</fsummary> + <type> + <v>Subject = binary()</v> + <v>N = int() >= 0</v> + </type> + <desc> + <p>Creates a binary with the content of <c>Subject</c> duplicated <c>N</c> times.</p> + + <p>This function will always create a new binary, even if <c>N = + 1</c>. By using <c>copy/1</c> on a binary referencing a larger binary, one + might free up the larger binary for garbage collection.</p> + + <note> + <p>By deliberately copying a single binary to avoid referencing + a larger binary, one might, instead of freeing up the larger + binary for later garbage collection, create much more binary + data than needed. Sharing binary data is usually good. Only in + special cases, when small parts reference large binaries and the + large binaries are no longer used in any process, deliberate + copying might be a good idea.</p> </note> + + <p>If <c>N</c> < <c>0</c>, a <c>badarg</c> exception is raised.</p> + </desc> + </func> + <func> + <name>decode_unsigned(Subject) -> Unsigned</name> + <fsummary>Decode a whole binary into an integer of arbitrary size</fsummary> + <type> + <v>Subject = binary()</v> + <v>Unsigned = int() >= 0</v> + </type> + <desc> + <p>The same as <c>decode_unsigned(Subject,big)</c>.</p> + </desc> + </func> + <func> + <name>decode_unsigned(Subject, Endianess) -> Unsigned</name> + <fsummary>Decode a whole binary into an integer of arbitrary size</fsummary> + <type> + <v>Subject = binary()</v> + <v>Endianess = big | little</v> + <v>Unsigned = int() >= 0</v> + </type> + <desc> + + <p>Converts the binary digit representation, in big or little + endian, of a positive integer in <c>Subject</c> to an Erlang <c>int()</c>.</p> + + <p>Example:</p> + + <code> +1> binary:decode_unsigned(<<169,138,199>>,big). +11111111 + </code> + </desc> + </func> + <func> + <name>encode_unsigned(Unsigned) -> binary()</name> + <fsummary>Encodes an unsigned integer into the minimal binary</fsummary> + <type> + <v>Unsigned = int() >= 0</v> + </type> + <desc> + <p>The same as <c>encode_unsigned(Unsigned,big)</c>.</p> + </desc> + </func> + <func> + <name>encode_unsigned(Unsigned,Endianess) -> binary()</name> + <fsummary>Encodes an unsigned integer into the minimal binary</fsummary> + <type> + <v>Unsigned = int() >= 0</v> + <v>Endianess = big | little</v> + </type> + <desc> + + <p>Converts a positive integer to the smallest possible + representation in a binary digit representation, either big + or little endian.</p> + + <p>Example:</p> + + <code> +1> binary:encode_unsigned(11111111,big). +<<169,138,199>> + </code> + </desc> + </func> + <func> + <name>first(Subject) -> int()</name> + <fsummary>Returns the first byte of a binary</fsummary> + <type> + <v>Subject = binary()</v> + </type> + <desc> + + <p>Returns the first byte of the binary <c>Subject</c> as an integer. If the + size of <c>Subject</c> is zero, a <c>badarg</c> exception is raised.</p> + + </desc> + </func> + <func> + <name>last(Subject) -> int()</name> + <fsummary>Returns the last byte of a binary</fsummary> + <type> + <v>Subject = binary()</v> + </type> + <desc> + + <p>Returns the last byte of the binary <c>Subject</c> as an integer. If the + size of <c>Subject</c> is zero, a <c>badarg</c> exception is raised.</p> + + </desc> + </func> + <func> + <name>list_to_bin(ByteList) -> binary()</name> + <fsummary>Convert a list of integers and binaries to a binary</fsummary> + <type> + <v>ByteList = iodata() (see module erlang)</v> + </type> + <desc> + <p>Works exactly as <c>erlang:list_to_binary/1</c>, added for completeness.</p> + </desc> + </func> + <func> + <name>longest_common_prefix(Binaries) -> int()</name> + <fsummary>Returns length of longest common prefix for a set of binaries</fsummary> + <type> + <v>Binaries = [ binary() ]</v> + </type> + <desc> + + <p>Returns the length of the longest common prefix of the + binaries in the list <c>Binaries</c>. Example:</p> + +<code> +1> binary:longest_common_prefix([<<"erlang">>,<<"ergonomy">>]). +2 +2> binary:longest_common_prefix([<<"erlang">>,<<"perl">>]). +0 +</code> + + <p>If <c>Binaries</c> is not a flat list of binaries, a <c>badarg</c> exception is raised.</p> + </desc> + </func> + <func> + <name>longest_common_suffix(Binaries) -> int()</name> + <fsummary>Returns length of longest common suffix for a set of binaries</fsummary> + <type> + <v>Binaries = [ binary() ]</v> + </type> + <desc> + + <p>Returns the length of the longest common suffix of the + binaries in the list <c>Binaries</c>. Example:</p> + +<code> +1> binary:longest_common_suffix([<<"erlang">>,<<"fang">>]). +3 +2> binary:longest_common_suffix([<<"erlang">>,<<"perl">>]). +0 +</code> + + <p>If <c>Binaries</c> is not a flat list of binaries, a <c>badarg</c> exception is raised.</p> + + </desc> + </func> + <func> + <name>match(Subject, Pattern) -> Found | <c>nomatch</c></name> + <fsummary>Searches for the first match of a pattern in a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Found = part()</v> + </type> + <desc> + <p>The same as <c>match(Subject, Pattern, [])</c>.</p> + </desc> + </func> + <func> + <name>match(Subject,Pattern,Options) -> Found | <c>nomatch</c></name> + <fsummary>Searches for the first match of a pattern in a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Found = part()</v> + <v>Options = [ Option ]</v> + <v>Option = {scope, part()}</v> + </type> + <desc> + + <p>Searches for the first occurrence of <c>Pattern</c> in <c>Subject</c> and + returns the position and length.</p> + + <p>The function will return <c>{Pos,Length}</c> for the binary + in <c>Pattern</c> starting at the lowest position in + <c>Subject</c>, Example:</p> + +<code> +1> binary:match(<<"abcde">>, [<<"bcde">>,<<"cd">>],[]). +{1,4} +</code> + + <p>Even though <c><<"cd">></c> ends before + <c><<"bcde">></c>, <c><<"bcde">></c> + begins first and is therefore the first match. If two + overlapping matches begin at the same position, the longest is + returned.</p> + + <p>Summary of the options:</p> + + <taglist> + <tag>{scope, {Start, Length}}</tag> + <item><p>Only the given part is searched. Return values still have + offsets from the beginning of <c>Subject</c>. A negative <c>Length</c> is + allowed as described in the <c>TYPES</c> section of this manual.</p></item> + </taglist> + + <p>If none of the strings in + <c>Pattern</c> is found, the atom <c>nomatch</c> is returned.</p> + + <p>For a description of <c>Pattern</c>, see + <seealso marker="#compile_pattern-1">compile_pattern/1</seealso>.</p> + + <p>If <c>{scope, {Start,Length}}</c> is given in the options + such that <c>Start</c> is larger than the size of + <c>Subject</c>, <c>Start + Length</c> is less than zero or + <c>Start + Length</c> is larger than the size of + <c>Subject</c>, a <c>badarg</c> exception is raised.</p> + + </desc> + </func> + <func> + <name>matches(Subject, Pattern) -> Found</name> + <fsummary>Searches for all matches of a pattern in a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Found = [ part() ] | []</v> + </type> + <desc> + <p>The same as <c>matches(Subject, Pattern, [])</c>.</p> + </desc> + </func> + <func> + <name>matches(Subject,Pattern,Options) -> Found</name> + <fsummary>Searches for all matches of a pattern in a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Found = [ part() ] | []</v> + <v>Options = [ Option ]</v> + <v>Option = {scope, part()}</v> + </type> + <desc> + + <p>Works like match, but the <c>Subject</c> is searched until + exhausted and a list of all non-overlapping parts matching + <c>Pattern</c> is returned (in order). </p> + + <p>The first and longest match is preferred to a shorter, + which is illustrated by the following example:</p> + +<code> +1> binary:matches(<<"abcde">>, + [<<"bcde">>,<<"bc">>>,<<"de">>],[]). +[{1,4}] +</code> + + <p>The result shows that <<bcde">> is selected instead of the + shorter match <<"bc">> (which would have given raise to one + more match,<<"de">>). This corresponds to the behavior of posix + regular expressions (and programs like awk), but is not + consistent with alternative matches in re (and Perl), where + instead lexical ordering in the search pattern selects which + string matches.</p> + + <p>If none of the strings in pattern is found, an empty list is returned.</p> + + <p>For a description of <c>Pattern</c>, see <seealso marker="#compile_pattern-1">compile_pattern/1</seealso> and for a + description of available options, see <seealso marker="#match-3">match/3</seealso>.</p> + + <p>If <c>{scope, {Start,Length}}</c> is given in the options such that + <c>Start</c> is larger than the size of <c>Subject</c>, <c>Start + Length</c> is + less than zero or <c>Start + Length</c> is larger than the size of + <c>Subject</c>, a <c>badarg</c> exception is raised.</p> + + </desc> + </func> + <func> + <name>part(Subject, PosLen) -> binary()</name> + <fsummary>Extracts a part of a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>PosLen = part()</v> + </type> + <desc> + + <p>Extracts the part of the binary <c>Subject</c> described by <c>PosLen</c>.</p> + + <p>Negative length can be used to extract bytes at the end of a binary:</p> + +<code> +1> Bin = <<1,2,3,4,5,6,7,8,9,10>>. +2> binary:part(Bin,{byte_size(Bin), -5)). +<<6,7,8,9,10>> +</code> + + <note> + <p><seealso marker="#part-2">part/2</seealso>and <seealso + marker="#part-3">part/3</seealso> are also available in the + <c>erlang</c> module under the names <c>binary_part/2</c> and + <c>binary_part/3</c>. Those BIFs are allowed in guard tests.</p> + </note> + + <p>If <c>PosLen</c> in any way references outside the binary, a <c>badarg</c> exception + is raised.</p> + + </desc> + </func> + <func> + <name>part(Subject, Pos, Len) -> binary()</name> + <fsummary>Extracts a part of a binary</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pos = int()</v> + <v>Len = int()</v> + </type> + <desc> + <p>The same as <c>part(Subject, {Pos, Len})</c>.</p> + </desc> + </func> + <func> + <name>referenced_byte_size(binary()) -> int()</name> + <fsummary>Determines the size of the actual binary pointed out by a sub-binary</fsummary> + <desc> + + <p>If a binary references a larger binary (often described as + being a sub-binary), it can be useful to get the size of the + actual referenced binary. This function can be used in a program + to trigger the use of <c>copy/1</c>. By copying a binary, one might + dereference the original, possibly large, binary which a smaller + binary is a reference to.</p> + + <p>Example:</p> + + <code> +store(Binary, GBSet) -> + NewBin = + case binary:referenced_byte_size(Binary) of + Large when Large > 2 * byte_size(Binary) -> + binary:copy(Binary); + _ -> + Binary + end, + gb_sets:insert(NewBin,GBSet). + </code> + + <p>In this example, we chose to copy the binary content before + inserting it in the <c>gb_set()</c> if it references a binary more than + twice the size of the data we're going to keep. Of course + different rules for when copying will apply to different + programs.</p> + + <p>Binary sharing will occur whenever binaries are taken apart, + this is the fundamental reason why binaries are fast, + decomposition can always be done with O(1) complexity. In rare + circumstances this data sharing is however undesirable, why this + function together with <c>copy/1</c> might be useful when optimizing + for memory use.</p> + + <p>Example of binary sharing:</p> + + <code> +1> A = binary:copy(<<1>>,100). +<<1,1,1,1,1 ... +2> byte_size(A). +100 +3> binary:referenced_byte_size(A) +100 +4> <<_:10/binary,B:10/binary,_/binary>> = A. +<<1,1,1,1,1 ... +5> byte_size(B). +10 +6> binary:referenced_byte_size(B) +100 + </code> + + <note> + <p>Binary data is shared among processes. If another process + still references the larger binary, copying the part this + process uses only consumes more memory and will not free up the + larger binary for garbage collection. Use this kind of intrusive + functions with extreme care, and only if a real problem is + detected.</p> + </note> + + </desc> + </func> + <func> + <name>replace(Subject,Pattern,Replacement) -> Result</name> + <fsummary>Replaces bytes in a binary according to a pattern</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Replacement = binary()</v> + <v>Result = binary()</v> + </type> + <desc> + <p>The same as <c>replace(Subject,Pattern,Replacement,[])</c>.</p> + </desc> + </func> + <func> + <name>replace(Subject,Pattern,Replacement,Options) -> Result</name> + <fsummary>Replaces bytes in a binary according to a pattern</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Replacement = binary()</v> + <v>Result = binary()</v> + <v>Options = [ Option ]</v> + <v>Option = global | {scope, part()} | {insert_replaced, InsPos}</v> + <v>InsPos = OnePos | [ OnePos ]</v> + <v>OnePos = int() =< byte_size(Replacement)</v> + </type> + <desc> + + <p>Constructs a new binary by replacing the parts in + <c>Subject</c> matching <c>Pattern</c> with the content of + <c>Replacement</c>.</p> + + <p>If the matching sub-part of <c>Subject</c> giving raise to the + replacement is to be inserted in the result, the option + <c>{insert_replaced, InsPos}</c> will insert the matching part into + <c>Replacement</c> at the given position (or positions) before actually + inserting <c>Replacement</c> into the <c>Subject</c>. Example:</p> + +<code> +1> binary:replace(<<"abcde">>,<<"b">>,<<"[]">>,[{insert_replaced,1}]). +<<"a[b]cde">> +2> binary:replace(<<"abcde">>,[<<"b">>,<<"d">>],<<"[]">>, + [global,{insert_replaced,1}]). +<<"a[b]c[d]e">> +3> binary:replace(<<"abcde">>,[<<"b">>,<<"d">>],<<"[]">>, + [global,{insert_replaced,[1,1]}]). +<<"a[bb]c[dd]e">> +4> binary:replace(<<"abcde">>,[<<"b">>,<<"d">>],<<"[-]">>, + [global,{insert_replaced,[1,2]}]). +<<"a[b-b]c[d-d]e">> +</code> + + <p>If any position given in <c>InsPos</c> is greater than the size of the replacement binary, a <c>badarg</c> exception is raised.</p> + + <p>The options <c>global</c> and <c>{scope, part()}</c> work as for <seealso marker="#split-3">split/3</seealso>. The return type is always a <c>binary()</c>.</p> + + <p>For a description of <c>Pattern</c>, see <seealso marker="#compile_pattern-1">compile_pattern/1</seealso>.</p> + </desc> + </func> + <func> + <name>split(Subject,Pattern) -> Parts</name> + <fsummary>Splits a binary according to a pattern</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Parts = [ binary() ]</v> + </type> + <desc> + <p>The same as <c>split(Subject, Pattern, [])</c>.</p> + </desc> + </func> + <func> + <name>split(Subject,Pattern,Options) -> Parts</name> + <fsummary>Splits a binary according to a pattern</fsummary> + <type> + <v>Subject = binary()</v> + <v>Pattern = binary() | [ binary() ] | cp()</v> + <v>Parts = [ binary() ]</v> + <v>Options = [ Option ]</v> + <v>Option = {scope, part()} | trim | global</v> + </type> + <desc> + + <p>Splits Binary into a list of binaries based on Pattern. If + the option global is not given, only the first occurrence of + Pattern in Subject will give rise to a split.</p> + + <p>The parts of Pattern actually found in Subject are not included in the result.</p> + + <p>Example:</p> + +<code> +1> binary:split(<<1,255,4,0,0,0,2,3>>, [<<0,0,0>>,<<2>>],[]). +[<<1,255,4>>, <<2,3>>] +2> binary:split(<<0,1,0,0,4,255,255,9>>, [<<0,0>>, <<255,255>>],[global]). +[<<0,1>>,<<4>>,<<9>>] +</code> + + <p>Summary of options:</p> + <taglist> + + <tag>{scope, part()}</tag> + + <item><p>Works as in <seealso marker="#match-3">match/3</seealso> and + <seealso marker="#matches-3">matches/3</seealso>. Note that + this only defines the scope of the search for matching strings, + it does not cut the binary before splitting. The bytes before + and after the scope will be kept in the result. See example + below.</p></item> + + <tag>trim</tag> + + <item><p>Removes trailing empty parts of the result (as does trim in <c>re:split/3</c>)</p></item> + + <tag>global</tag> + + <item><p>Repeats the split until the <c>Subject</c> is + exhausted. Conceptually the global option makes split work on + the positions returned by <seealso marker="#matches-3">matches/3</seealso>, + while it normally + works on the position returned by + <seealso marker="#match-3">match/3</seealso>.</p></item> + + </taglist> + + <p>Example of the difference between a scope and taking the + binary apart before splitting:</p> + +<code> +1> binary:split(<<"banana">>,[<<"a">>],[{scope,{2,3}}]). +[<<"ban">>,<<"na">>] +2> binary:split(binary:part(<<"banana">>,{2,3}),[<<"a">>],[]). +[<<"n">>,<<"n">>] +</code> + + <p>The return type is always a list of binaries that are all + referencing <c>Subject</c>. This means that the data in <c>Subject</c> is not + actually copied to new binaries and that <c>Subject</c> cannot be + garbage collected until the results of the split are no longer + referenced.</p> + + <p>For a description of <c>Pattern</c>, see <seealso marker="#compile_pattern-1">compile_pattern/1</seealso>.</p> + + </desc> + </func> + </funcs> +</erlref> diff --git a/lib/stdlib/doc/src/dets.xml b/lib/stdlib/doc/src/dets.xml index 8d1398d3b7..ad100d2cf5 100644 --- a/lib/stdlib/doc/src/dets.xml +++ b/lib/stdlib/doc/src/dets.xml @@ -109,7 +109,7 @@ bool() = true | false file() = string() int() = integer() >= 0 keypos() = integer() >= 1 -name() = atom() | ref() +name() = atom() | reference() no_slots() = integer() >= 0 | default object() = tuple() object_cont() = tuple() @@ -759,7 +759,7 @@ ok <fsummary>Open an existing Dets table.</fsummary> <type> <v>FileName = file()</v> - <v>Reference = ref()</v> + <v>Reference = reference()</v> </type> <desc> <p>Opens an existing table. If the table has not been properly diff --git a/lib/stdlib/doc/src/erl_id_trans.xml b/lib/stdlib/doc/src/erl_id_trans.xml index 7c821d2efc..cfb18ec131 100644 --- a/lib/stdlib/doc/src/erl_id_trans.xml +++ b/lib/stdlib/doc/src/erl_id_trans.xml @@ -5,7 +5,7 @@ <header> <copyright> <year>1996</year> - <year>2007</year> + <year>2010</year> <holder>Ericsson AB, All Rights Reserved</holder> </copyright> <legalnotice> @@ -70,7 +70,8 @@ <section> <title>See Also</title> - <p><seealso marker="erl_parse">erl_parse(3)</seealso>, compile(3).</p> + <p><seealso marker="erl_parse">erl_parse(3)</seealso>, + <seealso marker="compiler:compile">compile(3)</seealso>.</p> </section> </erlref> diff --git a/lib/stdlib/doc/src/erl_lint.xml b/lib/stdlib/doc/src/erl_lint.xml index 6a7d37765c..8639d678fa 100644 --- a/lib/stdlib/doc/src/erl_lint.xml +++ b/lib/stdlib/doc/src/erl_lint.xml @@ -96,8 +96,8 @@ <p>The <c>AbsForms</c> of a module which comes from a file that is read through <c>epp</c>, the Erlang pre-processor, can come from many files. This means that any references to - errors must include the file name (see <seealso marker="epp">epp(3)</seealso>, or parser <seealso marker="erl_parse">erl_parse(3)</seealso> The warnings and - errors returned have the following format: + errors must include the file name (see <seealso marker="epp">epp(3)</seealso>, or parser <seealso marker="erl_parse">erl_parse(3)</seealso>). + The warnings and errors returned have the following format: </p> <code type="none"> [{FileName2,[ErrorInfo]}] </code> diff --git a/lib/stdlib/doc/src/erl_parse.xml b/lib/stdlib/doc/src/erl_parse.xml index ae8a8afd5c..18b592deea 100644 --- a/lib/stdlib/doc/src/erl_parse.xml +++ b/lib/stdlib/doc/src/erl_parse.xml @@ -39,7 +39,7 @@ expressions, or terms. The Abstract Format is described in the ERTS User's Guide. Note that a token list must end with the <em>dot</em> token in order - to be acceptable to the parse functions (see erl_scan).</p> + to be acceptable to the parse functions (see <seealso marker="erl_scan">erl_scan(3)</seealso>).</p> </description> <funcs> <func> diff --git a/lib/stdlib/doc/src/erl_scan.xml b/lib/stdlib/doc/src/erl_scan.xml index 4175146c3c..1199c34f0f 100644 --- a/lib/stdlib/doc/src/erl_scan.xml +++ b/lib/stdlib/doc/src/erl_scan.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>erl_scan</title> @@ -103,7 +103,7 @@ attributes() = line() | list() | tuple()</code> Info, atom()}</c>, <c>{char, Info, integer()}</c>, <c>{comment, Info, string()}</c>, <c>{float, Info, float()}</c>, <c>{integer, - Info, integer()}</c>, <c>{var, Info, atom()}</c>, + Info, integer()}</c>, <c>{var, Info, atom()}</c>, and <c>{white_space, Info, string()}</c>.</p> <p>The valid options are:</p> <taglist> @@ -149,7 +149,8 @@ attributes() = line() | list() | tuple()</code> <v>StartLocation = EndLocation = location()</v> <v>Options = Option | [Option]</v> <v>Option = {reserved_word_fun,reserved_word_fun()} - | return_comments | return_white_spaces | return</v> + | return_comments | return_white_spaces | return + | text</v> </type> <desc> <p>This is the re-entrant scanner which scans characters until @@ -173,7 +174,7 @@ attributes() = line() | list() | tuple()</code> <tag><c>{error, ErrorInfo, EndLocation}</c></tag> <item> <p>An error occurred. <c>LeftOverChars</c> is the remaining - characters of the input data, + characters of the input data, starting from <c>EndLocation</c>.</p> </item> </taglist> @@ -278,7 +279,7 @@ attributes() = line() | list() | tuple()</code> <item><p>The token's symbol.</p> </item> <tag><c>{text, string()}</c></tag> - <item><p>The token's text..</p> + <item><p>The token's text.</p> </item> </taglist> </desc> @@ -315,7 +316,7 @@ attributes() = line() | list() | tuple()</code> <type> <v>Attributes = attributes()</v> <v>AttributeItemSpec = AttributeItem | [AttributeItem]</v> - <v>AttributesInfo = AttributeInfoTuple | undefined + <v>AttributesInfo = AttributeInfoTuple | undefined | [AttributeInfoTuple]</v> <v>AttributeInfoTuple = {AttributeItem, Info}</v> <v>AttributeItem = atom()</v> @@ -352,7 +353,7 @@ attributes() = line() | list() | tuple()</code> just the line if the column unknown.</p> </item> <tag><c>{text, string()}</c></tag> - <item><p>The token's text..</p> + <item><p>The token's text.</p> </item> </taglist> </desc> diff --git a/lib/stdlib/doc/src/ets.xml b/lib/stdlib/doc/src/ets.xml index 7b9f0e7772..dd4a289c61 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>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>ets</title> @@ -1039,15 +1039,22 @@ ets:select(Table,MatchSpec),</code> the owner terminates.</p> </item> <item> + <marker id="new_2_write_concurrency"></marker> <p><c>{write_concurrency,bool()}</c> - Performance tuning. Default is <c>false</c>, which means that the table - is optimized towards concurrent read access. An operation that + Performance tuning. Default is <c>false</c>. An operation that mutates (writes to) the table will obtain exclusive access, blocking any concurrent access of the same table until finished. If set to <c>true</c>, the table is optimized towards concurrent write access. Different objects of the same table can be mutated (and read) by concurrent processes. This is achieved to some degree at the expense of single access and concurrent reader performance. + The <c>write_concurrency</c> option can be combined with the + <seealso marker="#new_2_read_concurrency">read_concurrency</seealso> + option. You typically want to combine these when large concurrent + read bursts and large concurrent write bursts are common (see the + documentation of the + <seealso marker="#new_2_read_concurrency">read_concurrency</seealso> + option for more information). Note that this option does not change any guarantees about <seealso marker="#concurrency">atomicy and isolation</seealso>. Functions that makes such promises over several objects (like @@ -1055,6 +1062,29 @@ ets:select(Table,MatchSpec),</code> <p>Table type <c>ordered_set</c> is not affected by this option in current implementation.</p> </item> + <item> + <marker id="new_2_read_concurrency"></marker> + <p><c>{read_concurrency,bool()}</c> + Performance tuning. Default is <c>false</c>. When set to + <c>true</c>, the table is optimized for concurrent read + operations. When this option is enabled on a runtime system with + SMP support, read operations become much cheaper; especially on + systems with multiple physical processors. However, switching + between read and write operations becomes more expensive. You + typically want to enable this option when concurrent read + operations are much more frequent than write operations, or when + concurrent reads and writes comes in large read and write + bursts (i.e., lots of reads not interrupted by writes, and lots + of writes not interrupted by reads). You typically do + <em>not</em> want to enable this option when the common access + pattern is a few read operations interleaved with a few write + operations repeatedly. In this case you will get a performance + degradation by enabling this option. The <c>read_concurrency</c> + option can be combined with the + <seealso marker="#new_2_write_concurrency">write_concurrency</seealso> + option. You typically want to combine these when large concurrent + read bursts and large concurrent write bursts are common.</p> + </item> </list> </desc> </func> @@ -1355,6 +1385,28 @@ is_integer(X), is_integer(Y), X + Y < 4711]]></code> </desc> </func> <func> + <name>select_count(Tab, MatchSpec) -> NumMatched</name> + <fsummary>Match the objects in an ETS table against a match_spec and returns the number of objects for which the match_spec returned 'true'</fsummary> + <type> + <v>Tab = tid() | atom()</v> + <v>Object = tuple()</v> + <v>MatchSpec = match_spec()</v> + <v>NumMatched = integer()</v> + </type> + <desc> + <p>Matches the objects in the table <c>Tab</c> using a + <seealso marker="#match_spec">match_spec</seealso>. If the + match_spec returns <c>true</c> for an object, that object + considered a match and is counted. For any other result from + the match_spec the object is not considered a match and is + therefore not counted.</p> + <p>The function could be described as a <c>match_delete/2</c> + that does not actually delete any elements, but only counts + them.</p> + <p>The function returns the number of objects matched.</p> + </desc> + </func> + <func> <name>select_delete(Tab, MatchSpec) -> NumDeleted</name> <fsummary>Match the objects in an ETS table against a match_spec and deletes objects where the match_spec returns 'true'</fsummary> <type> @@ -1381,25 +1433,82 @@ is_integer(X), is_integer(Y), X + Y < 4711]]></code> </desc> </func> <func> - <name>select_count(Tab, MatchSpec) -> NumMatched</name> - <fsummary>Match the objects in an ETS table against a match_spec and returns the number of objects for which the match_spec returned 'true'</fsummary> + <name>select_reverse(Tab, MatchSpec) -> [Match]</name> + <fsummary>Match the objects in an ETS table against a match_spec.</fsummary> <type> <v>Tab = tid() | atom()</v> - <v>Object = tuple()</v> + <v>Match = term()</v> <v>MatchSpec = match_spec()</v> - <v>NumMatched = integer()</v> </type> <desc> - <p>Matches the objects in the table <c>Tab</c> using a - <seealso marker="#match_spec">match_spec</seealso>. If the - match_spec returns <c>true</c> for an object, that object - considered a match and is counted. For any other result from - the match_spec the object is not considered a match and is - therefore not counted.</p> - <p>The function could be described as a <c>match_delete/2</c> - that does not actually delete any elements, but only counts - them.</p> - <p>The function returns the number of objects matched.</p> + + <p>Works like <c>select/2</c>, but returns the list in reverse + order for the <c>ordered_set</c> table type. For all other table + types, the return value is identical to that of <c>select/2</c>.</p> + + </desc> + </func> + <func> + <name>select_reverse(Tab, MatchSpec, Limit) -> {[Match],Continuation} | '$end_of_table'</name> + <fsummary>Match the objects in an ETS table against a match_spec and returns part of the answers.</fsummary> + <type> + <v>Tab = tid() | atom()</v> + <v>Match = term()</v> + <v>MatchSpec = match_spec()</v> + <v>Continuation = term()</v> + </type> + <desc> + + <p>Works like <c>select/3</c>, but for the <c>ordered_set</c> + table type, traversing is done starting at the last object in + Erlang term order and moves towards the first. For all other + table types, the return value is identical to that of + <c>select/3</c>.</p> + + <p>Note that this is <em>not</em> equivalent to + reversing the result list of a <c>select/3</c> call, as the result list + is not only reversed, but also contains the last <c>Limit</c> + matching objects in the table, not the first.</p> + + </desc> + </func> + <func> + <name>select_reverse(Continuation) -> {[Match],Continuation} | '$end_of_table'</name> + <fsummary>Continue matching objects in an ETS table.</fsummary> + <type> + <v>Match = term()</v> + <v>Continuation = term()</v> + </type> + <desc> + + <p>Continues a match started with + <c>ets:select_reverse/3</c>. If the table is an + <c>ordered_set</c>, the traversal of the table will continue + towards objects with keys earlier in the Erlang term order. The + returned list will also contain objects with keys in reverse + order.</p> + + <p>For all other table types, the behaviour is exatly that of <c>select/1</c>.</p> + <p>Example:</p> + <code> +1> T = ets:new(x,[ordered_set]). +2> [ ets:insert(T,{N}) || N <- lists:seq(1,10) ]. +... +3> {R0,C0} = ets:select_reverse(T,[{'_',[],['$_']}],4). +... +4> R0. +[{10},{9},{8},{7}] +5> {R1,C1} = ets:select_reverse(C0). +... +6> R1. +[{6},{5},{4},{3}] +7> {R2,C2} = ets:select_reverse(C1). +... +8> R2. +[{2},{1}] +9> '$end_of_table' = ets:select_reverse(C2). +... + </code> </desc> </func> <func> @@ -1686,7 +1795,7 @@ true</pre> </desc> </func> <func> - <name>to_dets(Tab, DetsTab) -> Tab</name> + <name>to_dets(Tab, DetsTab) -> DetsTab</name> <fsummary>Fill a Dets table with objects from an ETS table.</fsummary> <type> <v>Tab = tid() | atom()</v> diff --git a/lib/stdlib/doc/src/filename.xml b/lib/stdlib/doc/src/filename.xml index 0cf82fa48b..fe6c6f898e 100644 --- a/lib/stdlib/doc/src/filename.xml +++ b/lib/stdlib/doc/src/filename.xml @@ -49,7 +49,7 @@ <title>DATA TYPES</title> <code type="none"> name() = string() | atom() | DeepList - DeepList = [char() | atom() | DeepList]</code> +DeepList = [char() | atom() | DeepList]</code> </section> <funcs> <func> diff --git a/lib/stdlib/doc/src/gen_event.xml b/lib/stdlib/doc/src/gen_event.xml index df09294de6..2234a62ac3 100644 --- a/lib/stdlib/doc/src/gen_event.xml +++ b/lib/stdlib/doc/src/gen_event.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>gen_event</title> @@ -630,12 +630,66 @@ gen_event:stop -----> Module:terminate/2 <p>The function should return the updated internal state.</p> </desc> </func> + <func> + <name>Module:format_status(Opt, [PDict, State]) -> Status</name> + <fsummary>Optional function for providing a term describing the + current event handler state.</fsummary> + <type> + <v>Opt = normal | terminate</v> + <v>PDict = [{Key, Value}]</v> + <v>State = term()</v> + <v>Status = term()</v> + </type> + <desc> + <note> + <p>This callback is optional, so event handler modules need + not export it. If a handler does not export this function, + the gen_event module uses the handler state directly for + the purposes described below.</p> + </note> + <p>This function is called by a gen_event process when:</p> + <list typed="bulleted"> + <item>One + of <seealso marker="sys#get_status/1">sys:get_status/1,2</seealso> + is invoked to get the gen_event status. <c>Opt</c> is set + to the atom <c>normal</c> for this case.</item> + <item>The event handler terminates abnormally and gen_event + logs an error. <c>Opt</c> is set to the + atom <c>terminate</c> for this case.</item> + </list> + <p>This function is useful for customising the form and + appearance of the event handler state for these cases. An + event handler callback module wishing to customise + the <c>sys:get_status/1,2</c> return value as well as how + its state appears in termination error logs exports an + instance of <c>format_status/2</c> that returns a term + describing the current state of the event handler.</p> + <p><c>PDict</c> is the current value of the gen_event's + process dictionary.</p> + <p><c>State</c> is the internal state of the event + handler.</p> + <p>The function should return <c>Status</c>, a term that + customises the details of the current state of the event + handler. Any term is allowed for <c>Status</c>. The + gen_event module uses <c>Status</c> as follows:</p> + <list typed="bulleted"> + <item>When <c>sys:get_status/1,2</c> is called, gen_event + ensures that its return value contains <c>Status</c> in + place of the event handler's actual state term.</item> + <item>When an event handler terminates abnormally, gen_event + logs <c>Status</c> in place of the event handler's actual + state term.</item> + </list> + <p>One use for this function is to return compact alternative + state representations to avoid having large state terms + printed in logfiles.</p> + </desc> + </func> </funcs> <section> <title>SEE ALSO</title> - <p><seealso marker="supervisor">supervisor(3)</seealso>, + <p><seealso marker="supervisor">supervisor(3)</seealso>, <seealso marker="sys">sys(3)</seealso></p> </section> </erlref> - diff --git a/lib/stdlib/doc/src/gen_fsm.xml b/lib/stdlib/doc/src/gen_fsm.xml index 739cd0bffd..d15383c621 100644 --- a/lib/stdlib/doc/src/gen_fsm.xml +++ b/lib/stdlib/doc/src/gen_fsm.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>gen_fsm</title> @@ -730,33 +730,58 @@ gen_fsm:sync_send_all_state_event -----> Module:handle_sync_event/4 </desc> </func> <func> - <name>Module:format_status(normal, [PDict, StateData]) -> Status</name> + <name>Module:format_status(Opt, [PDict, StateData]) -> Status</name> <fsummary>Optional function for providing a term describing the current gen_fsm status.</fsummary> <type> + <v>Opt = normal | terminate</v> <v>PDict = [{Key, Value}]</v> <v>StateData = term()</v> - <v>Status = [term()]</v> + <v>Status = term()</v> </type> <desc> - <p><em>This callback is optional, so callback modules need not - export it. The gen_fsm module provides a default - implementation of this function that returns the callback - module state data.</em></p> - <p>This function is called by a gen_fsm process when one - of <seealso marker="sys#get_status/1">sys:get_status/1,2</seealso> - is invoked to get the gen_fsm status. A callback module - wishing to customise the <c>sys:get_status/1,2</c> return - value exports an instance of <c>format_status/2</c> that - returns a term describing the current status of the - gen_fsm.</p> + <note> + <p>This callback is optional, so callback modules need not + export it. The gen_fsm module provides a default + implementation of this function that returns the callback + module state data.</p> + </note> + <p>This function is called by a gen_fsm process when:</p> + <list typed="bulleted"> + <item>One + of <seealso marker="sys#get_status/1">sys:get_status/1,2</seealso> + is invoked to get the gen_fsm status. <c>Opt</c> is set to + the atom <c>normal</c> for this case.</item> + <item>The gen_fsm terminates abnormally and logs an + error. <c>Opt</c> is set to the atom <c>terminate</c> for + this case.</item> + </list> + <p>This function is useful for customising the form and + appearance of the gen_fsm status for these cases. A callback + module wishing to customise the <c>sys:get_status/1,2</c> + return value as well as how its status appears in + termination error logs exports an instance + of <c>format_status/2</c> that returns a term describing the + current status of the gen_fsm.</p> <p><c>PDict</c> is the current value of the gen_fsm's process dictionary.</p> <p><c>StateData</c> is the internal state data of the gen_fsm.</p> - <p>The function should return <c>Status</c>, a list of one or - more terms that customise the details of the current state - and status of the gen_fsm.</p> + <p>The function should return <c>Status</c>, a term that + customises the details of the current state and status of + the gen_fsm. There are no restrictions on the + form <c>Status</c> can take, but for + the <c>sys:get_status/1,2</c> case (when <c>Opt</c> + is <c>normal</c>), the recommended form for + the <c>Status</c> value is <c>[{data, [{"StateData", + Term}]}]</c> where <c>Term</c> provides relevant details of + the gen_fsm state data. Following this recommendation isn't + required, but doing so will make the callback module status + consistent with the rest of the <c>sys:get_status/1,2</c> + return value.</p> + <p>One use for this function is to return compact alternative + state data representations to avoid having large state terms + printed in logfiles.</p> </desc> </func> </funcs> @@ -770,4 +795,3 @@ gen_fsm:sync_send_all_state_event -----> Module:handle_sync_event/4 <seealso marker="sys">sys(3)</seealso></p> </section> </erlref> - diff --git a/lib/stdlib/doc/src/gen_server.xml b/lib/stdlib/doc/src/gen_server.xml index 30c04d1d52..1045766e01 100644 --- a/lib/stdlib/doc/src/gen_server.xml +++ b/lib/stdlib/doc/src/gen_server.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1996</year><year>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>gen_server</title> @@ -599,32 +599,57 @@ gen_server:abcast -----> Module:handle_cast/2 </desc> </func> <func> - <name>Module:format_status(normal, [PDict, State]) -> Status</name> + <name>Module:format_status(Opt, [PDict, State]) -> Status</name> <fsummary>Optional function for providing a term describing the current gen_server status.</fsummary> <type> + <v>Opt = normal | terminate</v> <v>PDict = [{Key, Value}]</v> <v>State = term()</v> - <v>Status = [term()]</v> + <v>Status = term()</v> </type> <desc> - <p><em>This callback is optional, so callback modules need not - export it. The gen_server module provides a default - implementation of this function that returns the callback - module state.</em></p> - <p>This function is called by a gen_server process when one + <note> + <p>This callback is optional, so callback modules need not + export it. The gen_server module provides a default + implementation of this function that returns the callback + module state.</p> + </note> + <p>This function is called by a gen_server process when:</p> + <list typed="bulleted"> + <item>One of <seealso marker="sys#get_status/1">sys:get_status/1,2</seealso> - is invoked to get the gen_server status. A callback module - wishing to customise the <c>sys:get_status/1,2</c> return - value exports an instance of <c>format_status/2</c> that - returns a term describing the current status of the - gen_server.</p> + is invoked to get the gen_server status. <c>Opt</c> is set + to the atom <c>normal</c> for this case.</item> + <item>The gen_server terminates abnormally and logs an + error. <c>Opt</c> is set to the atom <c>terminate</c> for this + case.</item> + </list> + <p>This function is useful for customising the form and + appearance of the gen_server status for these cases. A + callback module wishing to customise + the <c>sys:get_status/1,2</c> return value as well as how + its status appears in termination error logs exports an + instance of <c>format_status/2</c> that returns a term + describing the current status of the gen_server.</p> <p><c>PDict</c> is the current value of the gen_server's process dictionary.</p> <p><c>State</c> is the internal state of the gen_server.</p> - <p>The function should return <c>Status</c>, a list of one or - more terms that customise the details of the current state - and status of the gen_server.</p> + <p>The function should return <c>Status</c>, a term that + customises the details of the current state and status of + the gen_server. There are no restrictions on the + form <c>Status</c> can take, but for + the <c>sys:get_status/1,2</c> case (when <c>Opt</c> + is <c>normal</c>), the recommended form for + the <c>Status</c> value is <c>[{data, [{"State", + Term}]}]</c> where <c>Term</c> provides relevant details of + the gen_server state. Following this recommendation isn't + required, but doing so will make the callback module status + consistent with the rest of the <c>sys:get_status/1,2</c> + return value.</p> + <p>One use for this function is to return compact alternative + state representations to avoid having large state terms + printed in logfiles.</p> </desc> </func> </funcs> diff --git a/lib/stdlib/doc/src/io_protocol.xml b/lib/stdlib/doc/src/io_protocol.xml index 201787f7b5..a97d996d98 100644 --- a/lib/stdlib/doc/src/io_protocol.xml +++ b/lib/stdlib/doc/src/io_protocol.xml @@ -79,7 +79,7 @@ sends the reply to.</item> io_reply. The io-module in the Erlang standard library simply uses the pid() of the io_server as the ReplyAs datum, but a more complicated client could have several outstanding io-requests to the same server and -would then use i.e. a ref() or something else to differentiate among +would then use i.e. a reference() or something else to differentiate among the incoming io_reply's. The ReplyAs element should be considered opaque by the io_server. Note that the pid() of the server is not explicitly present in the io_reply. The reply can be sent from any @@ -195,7 +195,7 @@ latin1, Module, Function, Args} respectively. </p> below).</p> <p>The function will be called with the data the io_server finds on - it's device, returning {done, Result, RestChars} when enough data is + its device, returning {done, Result, RestChars} when enough data is read (in which case Result is sent to the client and RestChars are kept in the io_server as a buffer for subsequent input) or {more, Continuation}, indicating that more characters are needed to @@ -741,7 +741,7 @@ optimize anything however. It is important though that the returned data is of the right type depending on the options set, so we convert the lists to binaries in the correct encoding <em>if possible</em> before returning. The function supplied in the get_until request may, -as it's final result return anything, so only functions actually +as its final result return anything, so only functions actually returning lists can get them converted to binaries. If the request contained the encoding tag unicode, the lists can contain all unicode codepoints and the binaries should be in UTF-8, if the encoding tag diff --git a/lib/stdlib/doc/src/lists.xml b/lib/stdlib/doc/src/lists.xml index 855a7e0244..92c4eb4f4c 100644 --- a/lib/stdlib/doc/src/lists.xml +++ b/lib/stdlib/doc/src/lists.xml @@ -48,7 +48,7 @@ <item><p>if x <c>F</c> y and y <c>F</c> x then x = y (<c>F</c> is antisymmetric);</p> </item> - <item><p>if x <c>F</c> y and and y <c>F</c> z then x <c>F</c> z + <item><p>if x <c>F</c> y and y <c>F</c> z then x <c>F</c> z (<c>F</c> is transitive);</p> </item> <item><p>x <c>F</c> y or y <c>F</c> x (<c>F</c> is total).</p> @@ -220,7 +220,7 @@ follows:</p> <code type="none"> flatmap(Fun, List1) -> - append(map(Fun, List1))</code> + append(map(Fun, List1)).</code> <p>Example:</p> <pre> > <input>lists:flatmap(fun(X)->[X,X] end, [a,b,c]).</input> @@ -443,7 +443,7 @@ flatmap(Fun, List1) -> <desc> <p>Returns a list containing the sorted elements of the list <c>TupleList1</c>. Sorting is performed on the <c>N</c>th - element of the tuples.</p> + element of the tuples. The sort is stable.</p> </desc> </func> <func> @@ -466,7 +466,7 @@ flatmap(Fun, List1) -> </desc> </func> <func> - <name>keytake(Key, N, TupleList1) -> {value, Tuple, TupleList2} + <name>keytake(Key, N, TupleList1) -> {value, Tuple, TupleList2} | false</name> <fsummary>Extract an element from a list of tuples</fsummary> <type> @@ -523,7 +523,7 @@ flatmap(Fun, List1) -> <v> A = B = term()</v> </type> <desc> - <p><c>mapfold</c> combines the operations of <c>map/2</c> and + <p><c>mapfoldl</c> combines the operations of <c>map/2</c> and <c>foldl/3</c> into one pass. An example, summing the elements in a list and double them at the same time:</p> <pre> @@ -543,7 +543,7 @@ flatmap(Fun, List1) -> <v> A = B = term()</v> </type> <desc> - <p><c>mapfold</c> combines the operations of <c>map/2</c> and + <p><c>mapfoldr</c> combines the operations of <c>map/2</c> and <c>foldr/3</c> into one pass.</p> </desc> </func> @@ -840,7 +840,7 @@ length(lists:seq(From, To, Incr)) == (To-From+Incr) div Incr</code> <c>Pred</c>. <c>splitwith/2</c> behaves as if it is defined as follows:</p> <code type="none"> -splitwith(Pred, List) -> +splitwith(Pred, List) -> {takewhile(Pred, List), dropwhile(Pred, List)}.</code> <p>Examples:</p> <pre> diff --git a/lib/stdlib/doc/src/ms_transform.xml b/lib/stdlib/doc/src/ms_transform.xml index 9f178b426c..ba9f89685b 100644 --- a/lib/stdlib/doc/src/ms_transform.xml +++ b/lib/stdlib/doc/src/ms_transform.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>2002</year><year>2009</year> + <year>2002</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>ms_transform</title> @@ -245,7 +245,7 @@ ets:select(emp_tab, ets:fun2ms( fun(#emp{empno = [$0 | Rest] }) -> {[$0|Rest],[$1|Rest]} end)). </code> - <p>As a matter of fact, this query hit's the feature of partially bound + <p>As a matter of fact, this query hits the feature of partially bound keys in the table type <c>ordered_set</c>, so that not the whole table need be searched, only the part of the table containing keys beginning with <c>0</c> is in fact looked into. </p> diff --git a/lib/stdlib/doc/src/notes.xml b/lib/stdlib/doc/src/notes.xml index c55eafc8b8..23d1e8b7de 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -30,6 +30,283 @@ </header> <p>This document describes the changes made to the STDLIB application.</p> +<section><title>STDLIB 1.17</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p>The Erlang code preprocessor (<c>epp</c>) sent extra + messages on the form <c>{eof,Location}</c> to the client + when parsing the <c>file</c> attribute. This bug, + introduced in R11B, has been fixed.</p> + <p> + Own Id: OTP-8470</p> + </item> + <item> + <p>The abstract type 'fun' could not be printed by the + Erlang pretty printer (<c>erl_pp</c>). This bug has been + fixed.</p> + <p> + Own Id: OTP-8473</p> + </item> + <item> + <p>The function <c>erl_scan:reserved_word/1</c> no longer + returns <c>true</c> when given the word <c>spec</c>. This + bug was introduced in STDLIB-1.15.3 (R12B-3).</p> + <p> + Own Id: OTP-8567</p> + </item> + <item> + <p>The documentation of <c>lists:keysort/2</c> states + that the sort is stable.</p> + <p> + Own Id: OTP-8628 Aux Id: seq11576 </p> + </item> + <item> + <p> + The shell's line editing has been improved to more + resemble the behaviour of readline and other shells. + (Thanks to Dave Peticolas)</p> + <p> + Own Id: OTP-8635</p> + </item> + <item> + <p>The Erlang code preprocessor (<c>epp</c>) did not + correctly handle premature end-of-input when defining + macros. This bug, introduced in STDLIB 1.16, has been + fixed.</p> + <p> + Own Id: OTP-8665 Aux Id: OTP-7810 </p> + </item> + </list> + </section> + + + <section><title>Improvements and New Features</title> + <list> + <item> + <p> + The module binary from EEP31 (and EEP9) is implemented.</p> + <p> + Own Id: OTP-8217</p> + </item> + <item> + <p>The erlang pretty printer (<c>erl_pp</c>) no longer + quotes atoms in types.</p> + <p> + Own Id: OTP-8501</p> + </item> + <item> + <p>The Erlang code preprocessor (<c>epp</c>) now + considers records with no fields as typed.</p> + <p> + Own Id: OTP-8503</p> + </item> + <item> + <p> + Added function <c>zip:foldl/3</c> to iterate over zip + archives.</p> + <p> + Added functions to create and extract escripts. See + <c>escript:create/2</c> and <c>escript:extract/2</c>.</p> + <p> + The undocumented function <c>escript:foldl/3</c> has been + removed. The same functionality can be achieved with the + more flexible functions <c>escript:extract/2</c> and + <c>zip:foldl/3</c>.</p> + <p> + Record fields has been annotated with type info. Source + files as been adapted to fit within 80 chars and trailing + whitespace has been removed.</p> + <p> + Own Id: OTP-8521</p> + </item> + <item> + <p>The Erlang parser no longer duplicates the singleton + type <c>undefined</c> in the type of record fields + without initial value.</p> + <p> + Own Id: OTP-8522</p> + </item> + <item> + <p>A regular expression with many levels of parenthesis + could cause a buffer overflow. That has been corrected. + (Thanks to Michael Santos.)</p> + <p> + Own Id: OTP-8539</p> + </item> + <item> + <p>When defining macros the closing right parenthesis + before the dot is now mandatory.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-8562</p> + </item> + <item> + <p> + Some properties of a compiled re pattern are defined to + allow for guard tests.</p> + <p> + Own Id: OTP-8577</p> + </item> + <item> + <p>Local and imported functions now override the + auto-imported BIFs when the names clash. The pre R14 + behaviour was that auto-imported BIFs would override + local functions. To avoid that old programs change + behaviour, the following will generate an error:</p> + <list><item><p>Doing a call without explicit module name + to a local function having a name clashing with the name + of an auto-imported BIF that was present (and + auto-imported) before OTP R14A</p></item> + <item><p>Explicitly importing a function having a name + clashing with the name of an autoimported BIF that was + present (and autoimported) before OTP R14A</p></item> + <item><p>Using any form of the old compiler directive + <c>nowarn_bif_clash</c></p></item> </list> <p>If the BIF + was added or auto-imported in OTP R14A or later, + overriding it with an import or a local function will + only result in a warning,</p> <p>To resolve clashes, you + can either use the explicit module name <c>erlang</c> to + call the BIF, or you can remove the auto-import of that + specific BIF by using the new compiler directive + <c>-compile({no_auto_import,[F/A]}).</c>, which makes all + calls to the local or imported function without explicit + module name pass without warnings or errors.</p> <p>The + change makes it possible to add auto-imported BIFs + without breaking or silently changing old code in the + future. However some current code ingeniously utilizing + the old behaviour or the <c>nowarn_bif_clash</c> compiler + directive, might need changing to be accepted by the + compiler.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-8579</p> + </item> + <item> + <p>The undocumented, unsupport, and deprecated function + <c>lists:flat_length/1</c> has been removed.</p> + <p> + Own Id: OTP-8584</p> + </item> + <item> + <p> + A bug in re that could cause certain regular expression + matches never to terminate is corrected. (Thanks to + Michael Santos and Gordon Guthrie.)</p> + <p> + Own Id: OTP-8589</p> + </item> + <item> + <p>Nested records can now be accessed without + parenthesis. See the Reference Manual for examples. + (Thanks to YAMASHINA Hio and Tuncer Ayaz.)</p> + <p> + Own Id: OTP-8597</p> + </item> + <item> + <p><c>receive</c> statements that can only read out a + newly created reference are now specially optimized so + that it will execute in constant time regardless of the + number of messages in the receive queue for the process. + That optimization will benefit calls to + <c>gen_server:call()</c>. (See <c>gen:do_call/4</c> for + an example of a receive statement that will be + optimized.)</p> + <p> + Own Id: OTP-8623</p> + </item> + <item> + <p>The beam_lib:cmp/2 function now compares BEAM files in + stricter way. The BEAM files will be considered different + if there are any changes except in the compilation + information ("CInf") chunk. beam_lib:cmp/2 used to ignore + differences in the debug information (significant for + Dialyzer) and other chunks that did not directly change + the run-time behavior.</p> + <p> + Own Id: OTP-8625</p> + </item> + <item> + <p> + When a gen_server, gen_fsm process, or gen_event + terminates abnormally, sometimes the text representation + of the process state can occupy many lines of the error + log, depending on the definition of the state term. A + mechanism to trim out parts of the state from the log has + been added (using a format_status/2 callback). See the + documentation.</p> + <p> + Own Id: OTP-8630</p> + </item> + <item> + <p> + Calling <c>sys:get_status()</c> for processes that have + globally registered names that were not atoms would cause + a crash. Corrected. (Thanks to Steve Vinoski.)</p> + <p> + Own Id: OTP-8656</p> + </item> + <item> + <p>The Erlang scanner has been augmented with two new + tokens: <c>..</c> and <c>...</c>.</p> + <p> + Own Id: OTP-8657</p> + </item> + <item> + <p>Expressions evaluating to integers can now be used in + types and function specifications where hitherto only + integers were allowed ("Erlang_Integer").</p> + <p> + Own Id: OTP-8664</p> + </item> + <item> + <p>The compiler optimizes record operations better.</p> + <p> + Own Id: OTP-8668</p> + </item> + <item> + <p> + The recently added BIFs erlang:min/2, erlang:max/2 and + erlang:port_command/3 are now auto-imported (as they were + originally intended to be). Due to the recent compiler + change (OTP-8579), the only impact on old code defining + it's own min/2, max/2 or port_command/3 functions will be + a warning, the local functions will still be used. The + warning can be removed by using + -compile({no_auto_import,[min/2,max/2,port_command/3]}). + in the source file.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-8669 Aux Id: OTP-8579 </p> + </item> + <item> + <p> + Now, binary_to_term/2 is auto-imported. This will cause a + compile warning if and only if a module has got a local + function with that name.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-8671</p> + </item> + <item> + <p> + The predefined builtin type tid() has been removed. + Instead, ets:tid() should be used.</p> + <p> + *** POTENTIAL INCOMPATIBILITY ***</p> + <p> + Own Id: OTP-8687</p> + </item> + </list> + </section> + +</section> + <section><title>STDLIB 1.16.5</title> <section><title>Fixed Bugs and Malfunctions</title> @@ -50,7 +327,7 @@ <item> <p>A number of bugs concerning re and unicode are corrected:</p> - <p>re:compile no longer looses unicode option, which also + <p>re:compile no longer loses unicode option, which also fixes bug in re:split.</p> <p>re:replace now handles unicode charlist replacement argument</p> diff --git a/lib/stdlib/doc/src/re.xml b/lib/stdlib/doc/src/re.xml index 4d2a0e0995..80adc3e347 100644 --- a/lib/stdlib/doc/src/re.xml +++ b/lib/stdlib/doc/src/re.xml @@ -80,7 +80,11 @@ - a unicode_binary is allowed as the tail of the list</code> <code type="none"> - mp() = Opaque datatype containing a compiled regular expression.</code> + mp() = Opaque datatype containing a compiled regular expression. + - The mp() is guaranteed to be a tuple() having the atom + 're_pattern' as it's first element, to allow for matching in + guards. The arity of the tuple() or the content of the other fields + is however not to be trusted.</code> </section> <funcs> <func> diff --git a/lib/stdlib/doc/src/ref_man.xml b/lib/stdlib/doc/src/ref_man.xml index f6ae368e92..85aae6151d 100644 --- a/lib/stdlib/doc/src/ref_man.xml +++ b/lib/stdlib/doc/src/ref_man.xml @@ -4,7 +4,7 @@ <application xmlns:xi="http://www.w3.org/2001/XInclude"> <header> <copyright> - <year>1996</year><year>2009</year> + <year>1996</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>STDLIB Reference Manual</title> @@ -37,6 +37,7 @@ <xi:include href="array.xml"/> <xi:include href="base64.xml"/> <xi:include href="beam_lib.xml"/> + <xi:include href="binary.xml"/> <xi:include href="c.xml"/> <xi:include href="calendar.xml"/> <xi:include href="dets.xml"/> diff --git a/lib/stdlib/doc/src/sofs.xml b/lib/stdlib/doc/src/sofs.xml index 8c8ae51262..729df1e678 100644 --- a/lib/stdlib/doc/src/sofs.xml +++ b/lib/stdlib/doc/src/sofs.xml @@ -210,7 +210,7 @@ X[i] to Y[i] and S a subset of X[1] × ... × X[n]. The <marker id="multiple_relative_product"></marker><em>multiple - relative product</em> of TR and and S is defined to be the + relative product</em> of TR and S is defined to be the set {z : z = ((x[1], ..., x[n]), (y[1],...,y[n])) for some (x[1], ..., x[n]) in S and for some (x[i], y[i]) in R[i], diff --git a/lib/stdlib/doc/src/sys.xml b/lib/stdlib/doc/src/sys.xml index 10ead62073..8cbfb9387b 100644 --- a/lib/stdlib/doc/src/sys.xml +++ b/lib/stdlib/doc/src/sys.xml @@ -34,7 +34,7 @@ <module>sys</module> <modulesummary>A Functional Interface to System Messages</modulesummary> <description> - <p>This module contains functions for sending system messages used by programs, and messaged used for debugging purposes. + <p>This module contains functions for sending system messages used by programs, and messages used for debugging purposes. </p> <p>Functions used for implementation of processes should also understand system messages such as debugging diff --git a/lib/stdlib/doc/src/timer.xml b/lib/stdlib/doc/src/timer.xml index 0b6807dd6c..1b34e71490 100644 --- a/lib/stdlib/doc/src/timer.xml +++ b/lib/stdlib/doc/src/timer.xml @@ -202,18 +202,33 @@ </func> <func> <name>tc(Module, Function, Arguments) -> {Time, Value}</name> - <fsummary>Measure the real time it takes to evaluate <c>apply(Module, Function, Arguments)</c></fsummary> + <name>tc(Fun, Arguments) -> {Time, Value}</name> + <fsummary>Measure the real time it takes to evaluate <c>apply(Module, + Function, Arguments)</c> or <c>apply(Fun, Arguments)</c></fsummary> <type> <v>Module = Function = atom()</v> + <v>Fun = fun()</v> <v>Arguments = [term()]</v> <v>Time = integer() in microseconds</v> <v>Value = term()</v> </type> <desc> - <p>Evaluates <c>apply(Module, Function, Arguments)</c> and measures - the elapsed real time. Returns <c>{Time, Value}</c>, where - <c>Time</c> is the elapsed real time in <em>microseconds</em>, - and <c>Value</c> is what is returned from the apply.</p> + <p></p> + <taglist> + <tag><c>tc/3</c></tag> + <item> + <p>Evaluates <c>apply(Module, Function, Arguments)</c> and measures + the elapsed real time as reported by <c>now/0</c>. + Returns <c>{Time, Value}</c>, where + <c>Time</c> is the elapsed real time in <em>microseconds</em>, + and <c>Value</c> is what is returned from the apply.</p> + </item> + <tag><c>tc/2</c></tag> + <item> + <p>Evaluates <c>apply(Fun, Arguments)</c>. Otherwise works + like <c>tc/3</c>.</p> + </item> + </taglist> </desc> </func> <func> diff --git a/lib/stdlib/doc/src/unicode_usage.xml b/lib/stdlib/doc/src/unicode_usage.xml index c5bf10b63d..f1b0659ea2 100644 --- a/lib/stdlib/doc/src/unicode_usage.xml +++ b/lib/stdlib/doc/src/unicode_usage.xml @@ -143,7 +143,7 @@ en_US.UTF-8</pre> <pre> $ echo <input>$LC_CTYPE</input> en_US.UTF-8</pre> -<p>The LANG or LC_CTYPE setting should be consistent with what the terminal is capable of, there is no portable way for Erlang to ask the actual terminal about it's UTF-8 capacity, we have to rely on the language and character type settings.</p> +<p>The LANG or LC_CTYPE 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> @@ -185,7 +185,7 @@ Eshell V5.7 (abort with ^G) <tag><c>file</c>, <c>group</c> and <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 it's 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> +<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> diff --git a/lib/stdlib/doc/src/zip.xml b/lib/stdlib/doc/src/zip.xml index e2ecfec8f0..4d98a20206 100644 --- a/lib/stdlib/doc/src/zip.xml +++ b/lib/stdlib/doc/src/zip.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>2006</year><year>2009</year> + <year>2006</year><year>2010</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -13,12 +13,12 @@ compliance with the License. You should have received a copy of the Erlang Public License along with this software. If not, it can be retrieved online at http://www.erlang.org/. - + Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific language governing rights and limitations under the License. - + </legalnotice> <title>zip</title> @@ -42,16 +42,18 @@ <p>By convention, the name of a zip file should end in "<c>.zip</c>". To abide to the convention, you'll need to add "<c>.zip</c>" yourself to the name.</p> - <p>Zip archives are created with the - <seealso marker="#zip_2">zip/2</seealso> or the + <p>Zip archives are created with the + <seealso marker="#zip_2">zip/2</seealso> or the <seealso marker="#zip_2">zip/3</seealso> function. (They are also available as <c>create</c>, to resemble the <c>erl_tar</c> module.)</p> - <p>To extract files from a zip archive, use the - <seealso marker="#unzip_1">unzip/1</seealso> or the + <p>To extract files from a zip archive, use the + <seealso marker="#unzip_1">unzip/1</seealso> or the <seealso marker="#unzip_2">unzip/2</seealso> function. (They are also available as <c>extract</c>.)</p> - <p>To return a list of the files in a zip archive, use the + <p>To fold a function over all files in a zip archive, use the + <seealso marker="#foldl_3">foldl_3</seealso>.</p> + <p>To return a list of the files in a zip archive, use the <seealso marker="#list_dir_1">list_dir/1</seealso> or the <seealso marker="#list_dir_2">list_dir/2</seealso> function. (They are also available as <c>table</c>.)</p> @@ -132,7 +134,7 @@ zip_file() </code> <type> <v>Name = filename()</v> <v>FileList = [FileSpec]</v> - <v>FileSpec = filename() | {filename(), binary()}</v> + <v>FileSpec = filename() | {filename(), binary()} | {filename(), binary(), #file_info{}}</v> <v>Options = [Option]</v> <v>Option = memory | cooked | verbose | {comment, Comment} | {cwd, CWD} | {compress, What} | {uncompress, What}</v> <v>What = all | [Extension] | {add, [Extension]} | {del, [Extension]}</v> @@ -212,16 +214,16 @@ zip_file() </code> <taglist> <tag><c>all</c></tag> <item><p> means that all files will be compressed (as long - as they pass the <c>uncompress</c> condition).</p></item> + as they pass the <c>uncompress</c> condition).</p></item> <tag><c>[Extension]</c></tag> <item><p>means that only files with exactly these extensions - will be compressed.</p></item> + will be compressed.</p></item> <tag><c>{add,[Extension]}</c></tag> <item><p>adds these extensions to the list of compress - extensions.</p></item> + extensions.</p></item> <tag><c>{del,[Extension]}</c></tag> <item><p>deletes these extensions from the list of compress - extensions.</p></item> + extensions.</p></item> </taglist> </item> <tag><c>{uncompress, What}</c></tag> @@ -231,16 +233,16 @@ zip_file() </code> The following values of <c>What</c> are allowed:</p> <taglist> <tag><c>all</c></tag> - <item><p> means that no files will be compressed.</p></item> + <item><p> means that no files will be compressed.</p></item> <tag><c>[Extension]</c></tag> <item><p>means that files with these extensions will be - uncompressed.</p></item> + uncompressed.</p></item> <tag><c>{add,[Extension]}</c></tag> <item><p>adds these extensions to the list of uncompress - extensions.</p></item> + extensions.</p></item> <tag><c>{del,[Extension]}</c></tag> <item><p>deletes these extensions from the list of uncompress - extensions.</p></item> + extensions.</p></item> </taglist> </item> </taglist> @@ -283,7 +285,7 @@ zip_file() </code> the <c>unzip/2</c> function will only extract the files whose names are included in <c>FileList</c>. The full paths, including the names of all sub directories within - the zip archive, must be specified.</p> + the zip archive, must be specified.</p> </item> <tag><c>cooked</c></tag> <item> @@ -327,6 +329,64 @@ zip_file() </code> </desc> </func> <func> + <name>foldl(Fun, Acc0, Archive) -> {ok, Acc1} | {error, Reason}</name> + <fsummary>Fold a function over all files in a zip archive</fsummary> + <type> + <v>Fun = fun(FileInArchive, GetInfo, GetBin, AccIn) -> AccOut</v> + <v>FileInArchive = filename()</v> + <v>GetInfo = fun() -> #file_info{}</v> + <v>GetBin = fun() -> binary()</v> + <v>Acc0 = Acc1 = AccIn = AccOut = term()</v> + <v>Archive = filename() | {filename(), binary()}</v> + </type> + <desc> + <p>The <marker id="foldl_3"></marker> <c>foldl/3</c> function + calls <c>Fun(FileInArchive, GetInfo, GetBin, AccIn)</c> on + successive files in the <c>Archive</c>, starting with <c>AccIn + == Acc0</c>. <c>FileInArchive</c> is the name that the file + has in the archive. <c>GetInfo</c> is a fun that returns info + about the the file. <c>GetBin</c> returns the contents of the + file. Both <c>GetInfo</c> and <c>GetBin</c> must be called + within the <c>Fun</c>. Their behavior is undefined if they are + called outside the context of the <c>Fun</c>. The <c>Fun</c> + must return a new accumulator which is passed to the next + call. <c>foldl/3</c> returns the final value of the + accumulator. <c>Acc0</c> is returned if the archive is + empty. It is not necessary to iterate over all files in the + archive. The iteration may be ended prematurely in a + controlled manner by throwing an exception.</p> + + <p>For example:</p> + <pre> +> <input>Name = "dummy.zip".</input> +"dummy.zip" +> <input>{ok, {Name, Bin}} = zip:create(Name, [{"foo", <<"FOO">>}, {"bar", <<"BAR">>}], [memory]).</input> +{ok,{"dummy.zip", + <<80,75,3,4,20,0,0,0,0,0,74,152,97,60,171,39,212,26,3,0, + 0,0,3,0,0,...>>}} +> <input>{ok, FileSpec} = zip:foldl(fun(N, I, B, Acc) -> [{N, B(), I()} | Acc] end, [], {Name, Bin}).</input> +{ok,[{"bar",<<"BAR">>, + {file_info,3,regular,read_write, + {{2010,3,1},{19,2,10}}, + {{2010,3,1},{19,2,10}}, + {{2010,3,1},{19,2,10}}, + 54,1,0,0,0,0,0}}, + {"foo",<<"FOO">>, + {file_info,3,regular,read_write, + {{2010,3,1},{19,2,10}}, + {{2010,3,1},{19,2,10}}, + {{2010,3,1},{19,2,10}}, + 54,1,0,0,0,0,0}}]} +> <input>{ok, {Name, Bin}} = zip:create(Name, lists:reverse(FileSpec), [memory]).</input> +{ok,{"dummy.zip", + <<80,75,3,4,20,0,0,0,0,0,74,152,97,60,171,39,212,26,3,0, + 0,0,3,0,0,...>>}} +> <input>catch zip:foldl(fun("foo", _, B, _) -> throw(B()); (_, _, _, Acc) -> Acc end, [], {Name, Bin}). </input> +<<"FOO">> +</pre> + </desc> + </func> + <func> <name>list_dir(Archive) -> RetValue</name> <name>list_dir(Archive, Options)</name> <name>table(Archive) -> RetValue</name> |