diff options
Diffstat (limited to 'lib/stdlib/doc')
| -rw-r--r-- | lib/stdlib/doc/src/Makefile | 11 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/beam_lib.xml | 7 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/binary.xml | 729 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/erl_scan.xml | 19 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/ets.xml | 8 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/io_protocol.xml | 4 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/lists.xml | 6 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/ms_transform.xml | 8 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/notes.xml | 2 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/ref_man.xml | 7 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/unicode_usage.xml | 4 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/zip.xml | 96 |
12 files changed, 847 insertions, 54 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..27308e02f3 100644 --- a/lib/stdlib/doc/src/beam_lib.xml +++ b/lib/stdlib/doc/src/beam_lib.xml @@ -347,9 +347,10 @@ chunkref() = chunkname() | chunkid()</code> </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..05ec4406c6 --- /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 begins 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> works 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/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..ee1befc882 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> @@ -1686,7 +1686,7 @@ 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/io_protocol.xml b/lib/stdlib/doc/src/io_protocol.xml index 201787f7b5..b52e862a5c 100644 --- a/lib/stdlib/doc/src/io_protocol.xml +++ b/lib/stdlib/doc/src/io_protocol.xml @@ -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..a273a2301f 100644 --- a/lib/stdlib/doc/src/lists.xml +++ b/lib/stdlib/doc/src/lists.xml @@ -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> @@ -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..28a3719d38 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -50,7 +50,7 @@ <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/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/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> |