diff options
Diffstat (limited to 'lib/stdlib/doc')
| -rw-r--r-- | lib/stdlib/doc/src/Makefile | 4 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/digraph.xml | 4 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/ets.xml | 8 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/filelib.xml | 4 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/filename.xml | 19 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/gen_statem.xml | 56 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/io.xml | 14 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/maps.xml | 94 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/notes.xml | 43 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/ref_man.xml | 1 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/specs.xml | 1 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/unicode.xml | 9 | ||||
| -rw-r--r-- | lib/stdlib/doc/src/uri_string.xml | 326 |
13 files changed, 542 insertions, 41 deletions
diff --git a/lib/stdlib/doc/src/Makefile b/lib/stdlib/doc/src/Makefile index 93eac8220d..af27efa6c1 100644 --- a/lib/stdlib/doc/src/Makefile +++ b/lib/stdlib/doc/src/Makefile @@ -98,13 +98,15 @@ XML_REF3_FILES = \ sys.xml \ timer.xml \ unicode.xml \ + uri_string.xml \ win32reg.xml \ zip.xml XML_REF6_FILES = stdlib_app.xml XML_PART_FILES = part.xml -XML_CHAPTER_FILES = io_protocol.xml unicode_usage.xml notes.xml notes_history.xml assert_hrl.xml +XML_CHAPTER_FILES = introduction.xml io_protocol.xml unicode_usage.xml \ + notes.xml assert_hrl.xml BOOK_FILES = book.xml diff --git a/lib/stdlib/doc/src/digraph.xml b/lib/stdlib/doc/src/digraph.xml index 5332d7aba5..db96beed6c 100644 --- a/lib/stdlib/doc/src/digraph.xml +++ b/lib/stdlib/doc/src/digraph.xml @@ -170,6 +170,10 @@ <p>If the edge would create a cycle in an <seealso marker="#acyclic_digraph">acyclic digraph</seealso>, <c>{error, {bad_edge, <anno>Path</anno>}}</c> is returned. + If <c><anno>G</anno></c> already has an edge with value + <c><anno>E</anno></c> connecting a different pair of vertices, + <c>{error, {bad_edge, [<anno>V1</anno>, <anno>V2</anno>]}}</c> + is returned. If either of <c><anno>V1</anno></c> or <c><anno>V2</anno></c> is not a vertex of digraph <c><anno>G</anno></c>, <c>{error, {bad_vertex, </c><anno>V</anno><c>}}</c> is diff --git a/lib/stdlib/doc/src/ets.xml b/lib/stdlib/doc/src/ets.xml index 576959b1c8..1b31a1ec9d 100644 --- a/lib/stdlib/doc/src/ets.xml +++ b/lib/stdlib/doc/src/ets.xml @@ -963,11 +963,11 @@ ets:is_compiled_ms(Broken).</code> <func> <name name="match_spec_run" arity="2"/> <fsummary>Perform matching, using a compiled match specification on a - list of tuples.</fsummary> + list of terms.</fsummary> <desc> <p>Executes the matching specified in a compiled <seealso marker="#match_spec">match specification</seealso> on a list - of tuples. Term <c><anno>CompiledMatchSpec</anno></c> is to be + of terms. Term <c><anno>CompiledMatchSpec</anno></c> is to be the result of a call to <seealso marker="#match_spec_compile/1"> <c>match_spec_compile/1</c></seealso> and is hence the internal representation of the match specification one wants to use.</p> @@ -985,7 +985,7 @@ Table = ets:new... MatchSpec = ... % The following call... ets:match_spec_run(ets:tab2list(Table), -ets:match_spec_compile(MatchSpec)), + ets:match_spec_compile(MatchSpec)), % ...gives the same result as the more common (and more efficient) ets:select(Table, MatchSpec),</code> <note> @@ -1961,7 +1961,7 @@ true</pre> The return value is a list of the new counter values from each update operation in the same order as in the operation list. If an empty list is specified, nothing is updated and an empty list is - returned. If the function fails, no updates is done.</p> + returned. If the function fails, no updates are done.</p> <p>The specified <c><anno>Key</anno></c> is used to identify the object by either <em>matching</em> the key of an object in a <c>set</c> table, or <em>compare equal</em> to the key of an object in an diff --git a/lib/stdlib/doc/src/filelib.xml b/lib/stdlib/doc/src/filelib.xml index 5e631aac21..3b5be75bc0 100644 --- a/lib/stdlib/doc/src/filelib.xml +++ b/lib/stdlib/doc/src/filelib.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>2003</year><year>2017</year> + <year>2003</year><year>2018</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -296,7 +296,7 @@ filelib:wildcard("lib/**/*.{erl,hrl}")</code> for a file with the extension <c>.beam</c>, the default rule is to look for a file with a corresponding extension <c>.erl</c> by replacing the suffix <c>"ebin"</c> of the object directory path with - <c>"src"</c>. + <c>"src"</c> or <c>"src/*"</c>. The file search is done through <seealso marker="#find_file/3"><c>find_file/3</c></seealso>. The directory of the object file is always tried before any other directory specified diff --git a/lib/stdlib/doc/src/filename.xml b/lib/stdlib/doc/src/filename.xml index d2608ad542..ce19f70df0 100644 --- a/lib/stdlib/doc/src/filename.xml +++ b/lib/stdlib/doc/src/filename.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>1997</year><year>2017</year> + <year>1997</year><year>2018</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -399,15 +399,18 @@ true tuples <c>{<anno>BinSuffix</anno>, <anno>SourceSuffix</anno>}</c> and is interpreted as follows: if the end of the directory name where the object is located matches <c><anno>BinSuffix</anno></c>, then the - source code directory has the same name, but with - <c><anno>BinSuffix</anno></c> replaced by - <c><anno>SourceSuffix</anno></c>. <c><anno>Rules</anno></c> defaults + name created by replacing <c><anno>BinSuffix</anno></c> with + <c><anno>SourceSuffix</anno></c> is expanded by calling + <seealso marker="filelib#wildcard/1"> + <c>filelib:wildcard/1</c></seealso>. + If a regular file is found among the matches, the function + returns that location together with <c><anno>Options</anno></c>. + Otherwise the next rule is tried, and so on.</p> + <p><c><anno>Rules</anno></c> defaults to:</p> <code type="none"> -[{"", ""}, {"ebin", "src"}, {"ebin", "esrc"}]</code> - <p>If the source file is found in the resulting directory, the function - returns that location together with <c><anno>Options</anno></c>. - Otherwise the next rule is tried, and so on.</p> +[{"", ""}, {"ebin", "src"}, {"ebin", "esrc"}, + {"ebin", "src/*"}, {"ebin", "esrc/*"}]</code> <p>The function returns <c>{<anno>SourceFile</anno>, <anno>Options</anno>}</c> if it succeeds. <c><anno>SourceFile</anno></c> is the absolute path to the source diff --git a/lib/stdlib/doc/src/gen_statem.xml b/lib/stdlib/doc/src/gen_statem.xml index 4a824f073e..be0d64feba 100644 --- a/lib/stdlib/doc/src/gen_statem.xml +++ b/lib/stdlib/doc/src/gen_statem.xml @@ -4,7 +4,7 @@ <erlref> <header> <copyright> - <year>2016</year><year>2017</year> + <year>2016</year><year>2018</year> <holder>Ericsson AB. All Rights Reserved.</holder> </copyright> <legalnotice> @@ -543,7 +543,23 @@ handle_event(_, _, State, Data) -> <name name="event_type"/> <desc> <p> - External events are of three types: + There are 3 categories of events: + <seealso marker="#type-external_event_type">external</seealso>, + <seealso marker="#type-timeout_event_type">timeout</seealso>, + and <c>internal</c>. + </p> + <p> + <c>internal</c> events can only be generated by the + state machine itself through the state transition action + <seealso marker="#type-action"><c>next_event</c></seealso>. + </p> + </desc> + </datatype> + <datatype> + <name name="external_event_type"/> + <desc> + <p> + External events are of 3 types: <c>{call,<anno>From</anno>}</c>, <c>cast</c>, or <c>info</c>. <seealso marker="#call/2">Calls</seealso> (synchronous) and @@ -551,12 +567,17 @@ handle_event(_, _, State, Data) -> originate from the corresponding API functions. For calls, the event contains whom to reply to. Type <c>info</c> originates from regular process messages sent - to the <c>gen_statem</c>. The state machine - implementation can, in addition to the above, - generate - <seealso marker="#type-event_type"><c>events of types</c></seealso> - <c>timeout</c>, <c>{timeout,<anno>Name</anno>}</c>, - <c>state_timeout</c>, and <c>internal</c> to itself. + to the <c>gen_statem</c>. + </p> + </desc> + </datatype> + <datatype> + <name name="timeout_event_type"/> + <desc> + <p> + There are 3 types of timeout events that the state machine + can generate for itself with the corresponding + <seealso marker="#type-timeout_action">timeout_action()</seealso>s. </p> </desc> </datatype> @@ -1026,6 +1047,25 @@ handle_event(_, _, State, Data) -> for this state transition. </p> </item> + </taglist> + </desc> + </datatype> + <datatype> + <name name="timeout_action"/> + <desc> + <p> + These state transition actions can be invoked by + returning them from the + <seealso marker="#state callback">state callback</seealso>, from + <seealso marker="#Module:init/1"><c>Module:init/1</c></seealso> + or by giving them to + <seealso marker="#enter_loop/5"><c>enter_loop/5,6</c></seealso>. + </p> + <p> + These timeout actions sets timeout + <seealso marker="#type-transition_option">transition options</seealso>. + </p> + <taglist> <tag><c>Timeout</c></tag> <item> <p> diff --git a/lib/stdlib/doc/src/io.xml b/lib/stdlib/doc/src/io.xml index 64fcf4379f..72c774e6ef 100644 --- a/lib/stdlib/doc/src/io.xml +++ b/lib/stdlib/doc/src/io.xml @@ -257,8 +257,9 @@ ok</pre> \x{400} ok 5> <input>io:fwrite("~s~n",[[1024]]).</input> -** exception exit: {badarg,[{io,format,[<0.26.0>,"~s~n",[[1024]]]}, - ...</pre> +** exception error: bad argument + in function io:format/3 + called as io:format(<0.53.0>,"~s~n",[[1024]])</pre> </item> <tag><c>w</c></tag> <item> @@ -454,12 +455,9 @@ ok</pre> abc def 'abc def' {foo,1} A ok 2> <input>io:fwrite("~s", [65]).</input> -** exception exit: {badarg,[{io,format,[<0.22.0>,"~s","A"]}, - {erl_eval,do_apply,5}, - {shell,exprs,6}, - {shell,eval_exprs,6}, - {shell,eval_loop,3}]} - in function io:o_request/2</pre> +** exception error: bad argument + in function io:format/3 + called as io:format(<0.53.0>,"~s","A")</pre> <p>In this example, an attempt was made to output the single character 65 with the aid of the string formatting directive <c>"~s"</c>.</p> diff --git a/lib/stdlib/doc/src/maps.xml b/lib/stdlib/doc/src/maps.xml index 8c7270816b..987d92989d 100644 --- a/lib/stdlib/doc/src/maps.xml +++ b/lib/stdlib/doc/src/maps.xml @@ -33,16 +33,31 @@ <p>This module contains functions for maps processing.</p> </description> + <datatypes> + <datatype> + <name name="iterator"/> + <desc> + <p>An iterator representing the key value associations in a map.</p> + <p>Created using <seealso marker="#iterator-1"><c>maps:iterator/1</c></seealso>.</p> + <p>Consumed by <seealso marker="#next-1"><c>maps:next/1</c></seealso>, + <seealso marker="#filter-2"><c>maps:filter/2</c></seealso>, + <seealso marker="#fold-3"><c>maps:fold/3</c></seealso> and + <seealso marker="#map-2"><c>maps:map/2</c></seealso>.</p> + </desc> + </datatype> + </datatypes> + <funcs> <func> <name name="filter" arity="2"/> <fsummary>Select pairs that satisfy a predicate.</fsummary> <desc> - <p>Returns a map <c><anno>Map2</anno></c> for which predicate - <c><anno>Pred</anno></c> holds true in <c><anno>Map1</anno></c>.</p> + <p>Returns a map <c><anno>Map</anno></c> for which predicate + <c><anno>Pred</anno></c> holds true in <c><anno>MapOrIter</anno></c>.</p> <p>The call fails with a <c>{badmap,Map}</c> exception if - <c><anno>Map1</anno></c> is not a map, or with <c>badarg</c> if - <c><anno>Pred</anno></c> is not a function of arity 2.</p> + <c><anno>MapOrIter</anno></c> is not a map or valid iterator, + or with <c>badarg</c> if <c><anno>Pred</anno></c> is not a + function of arity 2.</p> <p><em>Example:</em></p> <code type="none"> > M = #{a => 2, b => 3, c=> 4, "a" => 1, "b" => 2, "c" => 4}, @@ -76,12 +91,16 @@ <fsummary></fsummary> <desc> <p>Calls <c>F(K, V, AccIn)</c> for every <c><anno>K</anno></c> to value - <c><anno>V</anno></c> association in <c><anno>Map</anno></c> in + <c><anno>V</anno></c> association in <c><anno>MapOrIter</anno></c> in any order. Function <c>fun F/3</c> must return a new accumulator, which is passed to the next successive call. This function returns the final value of the accumulator. The initial accumulator value <c><anno>Init</anno></c> is returned if the map is empty.</p> + <p>The call fails with a <c>{badmap,Map}</c> exception if + <c><anno>MapOrIter</anno></c> is not a map or valid iterator, + or with <c>badarg</c> if <c><anno>Fun</anno></c> is not a + function of arity 3.</p> <p><em>Example:</em></p> <code type="none"> > Fun = fun(K,V,AccIn) when is_list(K) -> AccIn + V end, @@ -169,6 +188,32 @@ false</code> </func> <func> + <name name="iterator" arity="1"/> + <fsummary>Create a map iterator.</fsummary> + <desc> + <p>Returns a map iterator <c><anno>Iterator</anno></c> that can + be used by <seealso marker="#next-1"><c>maps:next/1</c></seealso> + to traverse the key-value associations in a map. When iterating + over a map, the memory usage is guaranteed to be bounded no matter + the size of the map.</p> + <p>The call fails with a <c>{badmap,Map}</c> exception if + <c><anno>Map</anno></c> is not a map.</p> + <p><em>Example:</em></p> + <code type="none"> +> M = #{ a => 1, b => 2 }. +#{a => 1,b => 2} +> I = maps:iterator(M). +[{a,1},{b,2}] +> {K1, V1, I2} = maps:next(I). +{a,1,[{b,2}]} +> {K2, V2, I3} = maps:next(I2). +{b,2,[]} +> maps:next(I3). +none</code> + </desc> + </func> + + <func> <name name="keys" arity="1"/> <fsummary></fsummary> <desc> @@ -188,12 +233,16 @@ false</code> <name name="map" arity="2"/> <fsummary></fsummary> <desc> - <p>Produces a new map <c><anno>Map2</anno></c> by calling function + <p>Produces a new map <c><anno>Map</anno></c> by calling function <c>fun F(K, V1)</c> for every <c><anno>K</anno></c> to value - <c><anno>V1</anno></c> association in <c><anno>Map1</anno></c> in + <c><anno>V1</anno></c> association in <c><anno>MapOrIter</anno></c> in any order. Function <c>fun F/2</c> must return value <c><anno>V2</anno></c> to be associated with key <c><anno>K</anno></c> - for the new map <c><anno>Map2</anno></c>.</p> + for the new map <c><anno>Map</anno></c>.</p> + <p>The call fails with a <c>{badmap,Map}</c> exception if + <c><anno>MapOrIter</anno></c> is not a map or valid iterator, + or with <c>badarg</c> if <c><anno>Fun</anno></c> is not a + function of arity 2.</p> <p><em>Example:</em></p> <code type="none"> > Fun = fun(K,V1) when is_list(K) -> V1*2 end, @@ -234,6 +283,35 @@ false</code> </func> <func> + <name name="next" arity="1"/> + <fsummary>Get the next key and value from an iterator.</fsummary> + <desc> + <p>Returns the next key-value association in + <c><anno>Iterator</anno></c> and a new iterator for the + remaining associations in the iterator. + </p> + <p> + If there are no more associations in the iterator, + <c>none</c> is returned. + </p> + <p><em>Example:</em></p> + <code type="none"> +> Map = #{a => 1, b => 2, c => 3}. +#{a => 1,b => 2,c => 3} +> Iter = maps:iterator(Map). +[{a,1},{b,2},{c,3}] +> {_, _, Iter1} = maps:next(Iter). +{a,1,[{b,2},{c,3}]} +> {_, _, Iter2} = maps:next(Iter1). +{b,2,[{c,3}]} +> {_, _, Iter3} = maps:next(Iter2). +{c,3,[]} +> maps:next(Iter3). +none</code> + </desc> + </func> + + <func> <name name="put" arity="3"/> <fsummary></fsummary> <desc> diff --git a/lib/stdlib/doc/src/notes.xml b/lib/stdlib/doc/src/notes.xml index d396f1de8f..b61e5b9b9e 100644 --- a/lib/stdlib/doc/src/notes.xml +++ b/lib/stdlib/doc/src/notes.xml @@ -31,6 +31,49 @@ </header> <p>This document describes the changes made to the STDLIB application.</p> +<section><title>STDLIB 3.4.3</title> + + <section><title>Fixed Bugs and Malfunctions</title> + <list> + <item> + <p> Make <c>ets:i/1</c> exit cleaner when ^D is input + while browsing a table. Only the old Erlang shell is + affected (<c>erl(1)</c> flag <c>-oldshell</c>). </p> + <p> + Own Id: OTP-14663</p> + </item> + <item> + <p> + Fixed handling of windows UNC paths in module + <c>filename</c>.</p> + <p> + Own Id: OTP-14693</p> + </item> + </list> + </section> + + + <section><title>Improvements and New Features</title> + <list> + <item> + <p> + Improve performance of the new string functionality when + handling ASCII characters.</p> + <p> + Own Id: OTP-14670</p> + </item> + <item> + <p> + Added a clarification to the documentation of + <c>unicode:characters_to_list/2</c>.</p> + <p> + Own Id: OTP-14798</p> + </item> + </list> + </section> + +</section> + <section><title>STDLIB 3.4.2</title> <section><title>Fixed Bugs and Malfunctions</title> diff --git a/lib/stdlib/doc/src/ref_man.xml b/lib/stdlib/doc/src/ref_man.xml index 878a3babc5..68bfddbc71 100644 --- a/lib/stdlib/doc/src/ref_man.xml +++ b/lib/stdlib/doc/src/ref_man.xml @@ -93,6 +93,7 @@ <xi:include href="sys.xml"/> <xi:include href="timer.xml"/> <xi:include href="unicode.xml"/> + <xi:include href="uri_string.xml"/> <xi:include href="win32reg.xml"/> <xi:include href="zip.xml"/> </application> diff --git a/lib/stdlib/doc/src/specs.xml b/lib/stdlib/doc/src/specs.xml index 45b207b13d..d559adf9b6 100644 --- a/lib/stdlib/doc/src/specs.xml +++ b/lib/stdlib/doc/src/specs.xml @@ -60,6 +60,7 @@ <xi:include href="../specs/specs_sys.xml"/> <xi:include href="../specs/specs_timer.xml"/> <xi:include href="../specs/specs_unicode.xml"/> + <xi:include href="../specs/specs_uri_string.xml"/> <xi:include href="../specs/specs_win32reg.xml"/> <xi:include href="../specs/specs_zip.xml"/> </specs> diff --git a/lib/stdlib/doc/src/unicode.xml b/lib/stdlib/doc/src/unicode.xml index e86f45431f..d822aca89c 100644 --- a/lib/stdlib/doc/src/unicode.xml +++ b/lib/stdlib/doc/src/unicode.xml @@ -239,8 +239,13 @@ <c><anno>InEncoding</anno></c>.</p> </item> </list> - <p>Only when <c><anno>InEncoding</anno></c> is one of the UTF - encodings, integers in the list are allowed to be > 255.</p> + <p> + Note that integers in the list always represent code points + regardless of <c><anno>InEncoding</anno></c> passed. If + <c><anno>InEncoding</anno> latin1</c> is passed, only code + points < 256 are allowed; otherwise, all valid unicode code + points are allowed. + </p> <p>If <c><anno>InEncoding</anno></c> is <c>latin1</c>, parameter <c><anno>Data</anno></c> corresponds to the <c>iodata()</c> type, but for <c>unicode</c>, parameter <c><anno>Data</anno></c> can diff --git a/lib/stdlib/doc/src/uri_string.xml b/lib/stdlib/doc/src/uri_string.xml new file mode 100644 index 0000000000..21f470e763 --- /dev/null +++ b/lib/stdlib/doc/src/uri_string.xml @@ -0,0 +1,326 @@ +<?xml version="1.0" encoding="utf-8" ?> +<!DOCTYPE erlref SYSTEM "erlref.dtd"> + +<erlref> + <header> + <copyright> + <year>2017</year><year>2017</year> + <holder>Ericsson AB. All Rights Reserved.</holder> + </copyright> + <legalnotice> + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + </legalnotice> + + <title>uri_string</title> + <prepared>Péter Dimitrov</prepared> + <docno>1</docno> + <date>2017-10-24</date> + <rev>A</rev> + </header> + <module>uri_string</module> + <modulesummary>URI processing functions.</modulesummary> + <description> + <p>This module contains functions for parsing and handling URIs + (<url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url>) and + form-urlencoded query strings (<url href="https://www.w3.org/TR/html5/forms.html">HTML5</url>). + </p> + <p>A URI is an identifier consisting of a sequence of characters matching the syntax + rule named <em>URI</em> in <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url>. + </p> + <p> The generic URI syntax consists of a hierarchical sequence of components referred + to as the scheme, authority, path, query, and fragment:</p> + <pre> + URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ] + hier-part = "//" authority path-abempty + / path-absolute + / path-rootless + / path-empty + scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." ) + authority = [ userinfo "@" ] host [ ":" port ] + userinfo = *( unreserved / pct-encoded / sub-delims / ":" ) + + reserved = gen-delims / sub-delims + gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@" + sub-delims = "!" / "$" / "&" / "'" / "(" / ")" + / "*" / "+" / "," / ";" / "=" + + unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" + </pre><br></br> + <p>The interpretation of a URI depends only on the characters used and not on how those + characters are represented in a network protocol.</p> + <p>The functions implemented by this module cover the following use cases:</p> + <list type="bulleted"> + <item>Parsing URIs into its components and returing a map<br></br> + <seealso marker="#parse/1"><c>parse/1</c></seealso> + </item> + <item>Recomposing a map of URI components into a URI string<br></br> + <seealso marker="#recompose/1"><c>recompose/1</c></seealso> + </item> + <item>Changing inbound binary and percent-encoding of URIs<br></br> + <seealso marker="#transcode/2"><c>transcode/2</c></seealso> + </item> + <item>Transforming URIs into a normalized form<br></br> + <seealso marker="#normalize/1"><c>normalize/1</c></seealso> + </item> + <item>Composing form-urlencoded query strings from a list of key-value pairs<br></br> + <seealso marker="#compose_query/1"><c>compose_query/1</c></seealso><br></br> + <seealso marker="#compose_query/2"><c>compose_query/2</c></seealso> + </item> + <item>Dissecting form-urlencoded query strings into a list of key-value pairs<br></br> + <seealso marker="#dissect_query/1"><c>dissect_query/1</c></seealso> + </item> + </list> + <p>There are four different encodings present during the handling of URIs:</p> + <list type="bulleted"> + <item>Inbound binary encoding in binaries</item> + <item>Inbound percent-encoding in lists and binaries</item> + <item>Outbound binary encoding in binaries</item> + <item>Outbound percent-encoding in lists and binaries</item> + </list> + <p>Functions with <c>uri_string()</c> argument accept lists, binaries and + mixed lists (lists with binary elements) as input type. All of the functions but + <c>transcode/2</c> expects input as lists of unicode codepoints, UTF-8 encoded binaries + and UTF-8 percent-encoded URI parts ("%C3%B6" corresponds to the unicode character "ö").</p> + <p>Unless otherwise specified the return value type and encoding are the same as the input + type and encoding. That is, binary input returns binary output, list input returns a list + output but mixed input returns list output.</p> + <p>In case of lists there is only percent-encoding. In binaries, however, both binary encoding + and percent-encoding shall be considered. <c>transcode/2</c> provides the means to convert + between the supported encodings, it takes a <c>uri_string()</c> and a list of options + specifying inbound and outbound encodings.</p> + <p><url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url> does not mandate any specific + character encoding and it is usually defined by the protocol or surrounding text. This library + takes the same assumption, binary and percent-encoding are handled as one configuration unit, + they cannot be set to different values.</p> + </description> + + <datatypes> + <datatype> + <name name="error"/> + <desc> + <p>Error tuple indicating the type of error. Possible values of the second component:</p> + <list type="bulleted"> + <item><c>invalid_character</c></item> + <item><c>invalid_encoding</c></item> + <item><c>invalid_input</c></item> + <item><c>invalid_map</c></item> + <item><c>invalid_percent_encoding</c></item> + <item><c>invalid_scheme</c></item> + <item><c>invalid_uri</c></item> + <item><c>invalid_utf8</c></item> + <item><c>missing_value</c></item> + </list> + <p>The third component is a term providing additional information about the + cause of the error.</p> + </desc> + </datatype> + <datatype> + <name name="uri_map"/> + <desc> + <p>Map holding the main components of a URI.</p> + </desc> + </datatype> + <datatype> + <name name="uri_string"/> + <desc> + <p>List of unicode codepoints, a UTF-8 encoded binary, or a mix of the two, + representing an <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url> + compliant URI (<em>percent-encoded form</em>). + A URI is a sequence of characters from a very limited set: the letters of + the basic Latin alphabet, digits, and a few special characters.</p> + </desc> + </datatype> + </datatypes> + + <funcs> + + <func> + <name name="compose_query" arity="1"/> + <fsummary>Compose urlencoded query string.</fsummary> + <desc> + <p>Composes a form-urlencoded <c><anno>QueryString</anno></c> based on a + <c><anno>QueryList</anno></c>, a list of non-percent-encoded key-value pairs. + Form-urlencoding is defined in section + 4.10.22.6 of the <url href="https://www.w3.org/TR/html5/forms.html">HTML5</url> + specification. + </p> + <p>See also the opposite operation <seealso marker="#dissect_query/1"> + <c>dissect_query/1</c></seealso>. + </p> + <p><em>Example:</em></p> + <pre> +1> <input>uri_string:compose_query([{"foo bar","1"},{"city","örebro"}]).</input> +<![CDATA["foo+bar=1&city=%C3%B6rebro"]]> +2> <![CDATA[uri_string:compose_query([{<<"foo bar">>,<<"1">>}, +2> {<<"city">>,<<"örebro"/utf8>>}]).]]> +<![CDATA[<<"foo+bar=1&city=%C3%B6rebro">>]]> + </pre> + </desc> + </func> + + <func> + <name name="compose_query" arity="2"/> + <fsummary>Compose urlencoded query string.</fsummary> + <desc> + <p>Same as <c>compose_query/1</c> but with an additional + <c><anno>Options</anno></c> parameter, that controls the encoding ("charset") + used by the encoding algorithm. There are two supported encodings: <c>utf8</c> + (or <c>unicode</c>) and <c>latin1</c>. + </p> + <p>Each character in the entry's name and value that cannot be expressed using + the selected character encoding, is replaced by a string consisting of a U+0026 + AMPERSAND character (<![CDATA[&]]>), a "#" (U+0023) character, one or more ASCII + digits representing the Unicode code point of the character in base ten, and + finally a ";" (U+003B) character. + </p> + <p>Bytes that are out of the range 0x2A, 0x2D, 0x2E, 0x30 to 0x39, 0x41 to 0x5A, 0x5F, + 0x61 to 0x7A, are percent-encoded (U+0025 PERCENT SIGN character (%) followed by + uppercase ASCII hex digits representing the hexadecimal value of the byte). + </p> + <p>See also the opposite operation <seealso marker="#dissect_query/1"> + <c>dissect_query/1</c></seealso>. + </p> + <p><em>Example:</em></p> + <pre> +1> <input>uri_string:compose_query([{"foo bar","1"},{"city","örebro"}],</input> +1> [{encoding, latin1}]). +<![CDATA["foo+bar=1&city=%F6rebro" +2> uri_string:compose_query([{<<"foo bar">>,<<"1">>}, +2> {<<"city">>,<<"東京"/utf8>>}], [{encoding, latin1}]).]]> +<![CDATA[<<"foo+bar=1&city=%26%2326481%3B%26%2320140%3B">>]]> + </pre> + </desc> + </func> + + <func> + <name name="dissect_query" arity="1"/> + <fsummary>Dissect query string.</fsummary> + <desc> + <p>Dissects an urlencoded <c><anno>QueryString</anno></c> and returns a + <c><anno>QueryList</anno></c>, a list of non-percent-encoded key-value pairs. + Form-urlencoding is defined in section + 4.10.22.6 of the <url href="https://www.w3.org/TR/html5/forms.html">HTML5</url> + specification. + </p> + <p>It is not as strict for its input as the decoding algorithm defined by + <url href="https://www.w3.org/TR/html5/forms.html">HTML5</url> + and accepts all unicode characters.</p> + <p>See also the opposite operation <seealso marker="#compose_query/1"> + <c>compose_query/1</c></seealso>. + </p> + <p><em>Example:</em></p> + <pre> +1> <input><![CDATA[uri_string:dissect_query("foo+bar=1&city=%C3%B6rebro").]]></input> +[{"foo bar","1"},{"city","örebro"}] +2> <![CDATA[uri_string:dissect_query(<<"foo+bar=1&city=%26%2326481%3B%26%2320140%3B">>).]]> +<![CDATA[[{<<"foo bar">>,<<"1">>}, + {<<"city">>,<<230,157,177,228,186,172>>}] ]]> + </pre> + </desc> + </func> + + <func> + <name name="normalize" arity="1"/> + <fsummary>Syntax-based normalization.</fsummary> + <desc> + <p>Transforms <c><anno>URIString</anno></c> into a normalized form + using Syntax-Based Normalization as defined by + <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url>.</p> + <p>This function implements case normalization, percent-encoding + normalization, path segment normalization and scheme based normalization + for HTTP(S) with basic support for FTP, SSH, SFTP and TFTP.</p> + <p><em>Example:</em></p> + <pre> +1> <input>uri_string:normalize("/a/b/c/./../../g").</input> +"/a/g" +2> <![CDATA[uri_string:normalize(<<"mid/content=5/../6">>).]]> +<![CDATA[<<"mid/6">>]]> +3> uri_string:normalize("http://localhost:80"). +"https://localhost/" + </pre> + </desc> + </func> + + <func> + <name name="parse" arity="1"/> + <fsummary>Parse URI into a map.</fsummary> + <desc> + <p>Parses an <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url> + compliant <c>uri_string()</c> into a <c>uri_map()</c>, that holds the parsed + components of the <c>URI</c>. + If parsing fails, an error tuple is returned.</p> + <p>See also the opposite operation <seealso marker="#recompose/1"> + <c>recompose/1</c></seealso>.</p> + <p><em>Example:</em></p> + <pre> +1> <input>uri_string:parse("foo://[email protected]:8042/over/there?name=ferret#nose").</input> +#{fragment => "nose",host => "example.com", + path => "/over/there",port => 8042,query => "name=ferret", + scheme => foo,userinfo => "user"} +2> <![CDATA[uri_string:parse(<<"foo://[email protected]:8042/over/there?name=ferret">>).]]> +<![CDATA[#{host => <<"example.com">>,path => <<"/over/there">>, + port => 8042,query => <<"name=ferret">>,scheme => <<"foo">>, + userinfo => <<"user">>}]]> + </pre> + </desc> + </func> + + <func> + <name name="recompose" arity="1"/> + <fsummary>Recompose URI.</fsummary> + <desc> + <p>Creates an <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url> compliant + <c><anno>URIString</anno></c> (percent-encoded), based on the components of + <c><anno>URIMap</anno></c>. + If the <c><anno>URIMap</anno></c> is invalid, an error tuple is returned.</p> + <p>See also the opposite operation <seealso marker="#parse/1"> + <c>parse/1</c></seealso>.</p> + <p><em>Example:</em></p> + <pre> +1> <input>URIMap = #{fragment => "nose", host => "example.com", path => "/over/there",</input> +1> port => 8042, query => "name=ferret", scheme => "foo", userinfo => "user"}. +#{fragment => "top",host => "example.com", + path => "/over/there",port => 8042,query => "?name=ferret", + scheme => foo,userinfo => "user"} + +2> <input>uri_string:recompose(URIMap).</input> +"foo://example.com:8042/over/there?name=ferret#nose"</pre> + </desc> + </func> + + <func> + <name name="transcode" arity="2"/> + <fsummary>Transcode URI.</fsummary> + <desc> + <p>Transcodes an <url href="https://www.ietf.org/rfc/rfc3986.txt">RFC 3986</url> + compliant <c><anno>URIString</anno></c>, + where <c><anno>Options</anno></c> is a list of tagged tuples, specifying the inbound + (<c>in_encoding</c>) and outbound (<c>out_encoding</c>) encodings. <c>in_encoding</c> + and <c>out_encoding</c> specifies both binary encoding and percent-encoding for the + input and output data. Mixed encoding, where binary encoding is not the same as + percent-encoding, is not supported. + If an argument is invalid, an error tuple is returned.</p> + <p><em>Example:</em></p> + <pre> +1> <input><![CDATA[uri_string:transcode(<<"foo%00%00%00%F6bar"/utf32>>,]]></input> +1> [{in_encoding, utf32},{out_encoding, utf8}]). +<![CDATA[<<"foo%C3%B6bar"/utf8>>]]> +2> uri_string:transcode("foo%F6bar", [{in_encoding, latin1}, +2> {out_encoding, utf8}]). +"foo%C3%B6bar" + </pre> + </desc> + </func> + + </funcs> +</erlref> |