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 / "-" / "." / "_" / "~"


    

*

Parsing URIs into its components and returing a map
parse/1

*

Recomposing a map of URI components into a URI string
recompose/1

*

Changing inbound binary and percent-encoding of URIs
transcode/2

*

Transforming URIs into a normalized form
normalize/1
normalize/2

*

Composing form-urlencoded query strings from a list of key-value pairs
compose_query/1
compose_query/2

*

Dissecting form-urlencoded query strings into a list of key-value pairs
dissect_query/1

*

Decoding percent-encoded triplets in URI map or a specific component of URI
percent_decode/1

*

Preparing and retrieving application specific data included in URI components
quote/1quote/2unquote/1

*

Inbound binary encoding in binaries

*

Inbound percent-encoding in lists and binaries

*

Outbound binary encoding in binaries

*

Outbound percent-encoding in lists and binaries

error() = {error, atom(), term()}

Error tuple indicating the type of error. Possible values of the second component:

The third component is a term providing additional information about the cause of the error.

uri_map() = 


    #{fragment => unicode:chardata(),


      host => unicode:chardata(),


      path => unicode:chardata(),


      port => integer() >= 0 | undefined,


      query => unicode:chardata(),


      scheme => unicode:chardata(),


      userinfo => unicode:chardata()}

Map holding the main components of a URI.

uri_string() = iodata()

List of unicode codepoints, a UTF-8 encoded binary, or a mix of the two, representing an RFC 3986 compliant URI (percent-encoded form). 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.

allowed_characters() -> [{atom(), list()}]

This is a utility function meant to be used in the shell for printing the allowed characters in each major URI component, and also in the most important characters sets. Please note that this function does not replace the ABNF rules defined by the standards, these character sets are derived directly from those aformentioned rules. For more information see the Uniform Resource Identifiers chapter in stdlib's Users Guide.

compose_query(QueryList) -> QueryString

Types:

Composes a form-urlencoded QueryString based on a QueryList, a list of non-percent-encoded key-value pairs. Form-urlencoding is defined in section 4.10.21.6 of the HTML 5.2 specification and in section 4.10.22.6 of the HTML 5.0 specification for non-UTF-8 encodings.

See also the opposite operation dissect_query/1.

Example:

1> uri_string:compose_query([{"foo bar","1"},{"city","örebro"}]).
"foo+bar=1&city=%C3%B6rebro"
2> uri_string:compose_query([{<<"foo bar">>,<<"1">>},
2> {<<"city">>,<<"örebro"/utf8>>}]).
<<"foo+bar=1&city=%C3%B6rebro">>
	

compose_query(QueryList, Options) -> QueryString

Types:

Same as compose_query/1 but with an additional Options parameter, that controls the encoding ("charset") used by the encoding algorithm. There are two supported encodings: utf8 (or unicode) and latin1.

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 (&), 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.

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).

See also the opposite operation dissect_query/1.

Example:

1> uri_string:compose_query([{"foo bar","1"},{"city","örebro"}],
1> [{encoding, latin1}]).
"foo+bar=1&city=%F6rebro"
2> uri_string:compose_query([{<<"foo bar">>,<<"1">>},
2> {<<"city">>,<<"東京"/utf8>>}], [{encoding, latin1}]).
<<"foo+bar=1&city=%26%2326481%3B%26%2320140%3B">>
	

dissect_query(QueryString) -> QueryList

Types:

Dissects an urlencoded QueryString and returns a QueryList, a list of non-percent-encoded key-value pairs. Form-urlencoding is defined in section 4.10.21.6 of the HTML 5.2 specification and in section 4.10.22.6 of the HTML 5.0 specification for non-UTF-8 encodings.

See also the opposite operation compose_query/1.

Example:

1> uri_string:dissect_query("foo+bar=1&city=%C3%B6rebro").
[{"foo bar","1"},{"city","örebro"}]
2> uri_string:dissect_query(<<"foo+bar=1&city=%26%2326481%3B%26%2320140%3B">>).
[{<<"foo bar">>,<<"1">>},


 {<<"city">>,<<230,157,177,228,186,172>>}] 
	

normalize(URI) -> NormalizedURI

Types:

Transforms an URI into a normalized form using Syntax-Based Normalization as defined by RFC 3986.

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.

Example:

1> uri_string:normalize("/a/b/c/./../../g").
"/a/g"
2> uri_string:normalize(<<"mid/content=5/../6">>).
<<"mid/6">>
3> uri_string:normalize("http://localhost:80").
"http://localhost/"
4> uri_string:normalize(#{scheme => "http",port => 80,path => "/a/b/c/./../../g",
4> host => "localhost-örebro"}).
"http://localhost-%C3%B6rebro/a/g"
	

normalize(URI, Options) -> NormalizedURI

Types:

Same as normalize/1 but with an additional Options parameter, that controls whether the normalized URI shall be returned as an uri_map(). There is one supported option: return_map.

Example:

1> uri_string:normalize("/a/b/c/./../../g", [return_map]).
#{path => "/a/g"}
2> uri_string:normalize(<<"mid/content=5/../6">>, [return_map]).
#{path => <<"mid/6">>}
3> uri_string:normalize("http://localhost:80", [return_map]).
#{scheme => "http",path => "/",host => "localhost"}
4> uri_string:normalize(#{scheme => "http",port => 80,path => "/a/b/c/./../../g",
4> host => "localhost-örebro"}, [return_map]).
#{scheme => "http",path => "/a/g",host => "localhost-örebro"}
	

parse(URIString) -> URIMap

Types:

Parses an RFC 3986 compliant uri_string() into a uri_map(), that holds the parsed components of the URI. If parsing fails, an error tuple is returned.

See also the opposite operation recompose/1.

Example:

1> uri_string:parse("foo://user@example.com:8042/over/there?name=ferret#nose").
#{fragment => "nose",host => "example.com",


  path => "/over/there",port => 8042,query => "name=ferret",


  scheme => foo,userinfo => "user"}
2> uri_string:parse(<<"foo://user@example.com:8042/over/there?name=ferret">>).
#{host => <<"example.com">>,path => <<"/over/there">>,


  port => 8042,query => <<"name=ferret">>,scheme => <<"foo">>,


  userinfo => <<"user">>}
	

percent_decode(URI) -> Result

Types:

Decodes all percent-encoded triplets in the input that can be both a uri_string() and a uri_map(). Note, that this function performs raw decoding and it shall be used on already parsed URI components. Applying this function directly on a standard URI can effectively change it.

If the input encoding is not UTF-8, an error tuple is returned.

Example:

1> uri_string:percent_decode(#{host => "localhost-%C3%B6rebro",path => [],
1> scheme => "http"}).
#{host => "localhost-örebro",path => [],scheme => "http"}
2> uri_string:percent_decode(<<"%C3%B6rebro">>).
<<"örebro"/utf8>>
	

Using uri_string:percent_decode/1 directly on a URI is not safe. This example shows, that after each consecutive application of the function the resulting URI will be changed. None of these URIs refer to the same resource.

3> uri_string:percent_decode(<<"http://local%252Fhost/path">>).
<<"http://local%2Fhost/path">>
4> uri_string:percent_decode(<<"http://local%2Fhost/path">>).
<<"http://local/host/path">>


        

quote(Data) -> QuotedData

Types:

Replaces characters out of unreserved set with their percent encoded equivalents.

Unreserved characters defined in RFC 3986 are not quoted.

Example:

1> uri_string:quote("SomeId/04").
"SomeId%2F04"
2> uri_string:quote(<<"SomeId/04">>).
<<"SomeId%2F04">>
	

Function is not aware about any URI component context and should not be used on whole URI. If applied more than once on the same data, might produce unexpected results.

quote(Data, Safe) -> QuotedData

Types:

Same as quote/1, but Safe allows user to provide a list of characters to be protected from encoding.

Example:

1> uri_string:quote("SomeId/04", "/").
"SomeId/04"
2> uri_string:quote(<<"SomeId/04">>, "/").
<<"SomeId/04">>
	

Function is not aware about any URI component context and should not be used on whole URI. If applied more than once on the same data, might produce unexpected results.

recompose(URIMap) -> URIString

Types:

Creates an RFC 3986 compliant URIString (percent-encoded), based on the components of URIMap. If the URIMap is invalid, an error tuple is returned.

See also the opposite operation parse/1.

Example:

1> URIMap = #{fragment => "nose", host => "example.com", path => "/over/there",
1> port => 8042, query => "name=ferret", scheme => "foo", userinfo => "user"}.
#{fragment => "nose",host => "example.com",


  path => "/over/there",port => 8042,query => "name=ferret",


  scheme => "foo",userinfo => "user"}
2> uri_string:recompose(URIMap).
"foo://example.com:8042/over/there?name=ferret#nose"

resolve(RefURI, BaseURI) -> TargetURI

Types:

Convert a RefURI reference that might be relative to a given base URI into the parsed components of the reference's target, which can then be recomposed to form the target URI.

Example:

1> uri_string:resolve("/abs/ol/ute", "http://localhost/a/b/c?q").
"http://localhost/abs/ol/ute"
2> uri_string:resolve("../relative", "http://localhost/a/b/c?q").
"http://localhost/a/relative"
3> uri_string:resolve("http://localhost/full", "http://localhost/a/b/c?q").
"http://localhost/full"
4> uri_string:resolve(#{path => "path", query => "xyz"}, "http://localhost/a/b/c?q").
"http://localhost/a/b/path?xyz"
	

resolve(RefURI, BaseURI, Options) -> TargetURI

Types:

Same as resolve/2 but with an additional Options parameter, that controls whether the target URI shall be returned as an uri_map(). There is one supported option: return_map.

Example:

1> uri_string:resolve("/abs/ol/ute", "http://localhost/a/b/c?q", [return_map]).
#{host => "localhost",path => "/abs/ol/ute",scheme => "http"}
2> uri_string:resolve(#{path => "/abs/ol/ute"}, #{scheme => "http",
2> host => "localhost", path => "/a/b/c?q"}, [return_map]).
#{host => "localhost",path => "/abs/ol/ute",scheme => "http"}
	

transcode(URIString, Options) -> Result

Types:

Transcodes an RFC 3986 compliant URIString, where Options is a list of tagged tuples, specifying the inbound (in_encoding) and outbound (out_encoding) encodings. in_encoding and out_encoding 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.

Example:

1> uri_string:transcode(<<"foo%00%00%00%F6bar"/utf32>>,
1> [{in_encoding, utf32},{out_encoding, utf8}]).
<<"foo%C3%B6bar"/utf8>>
2> uri_string:transcode("foo%F6bar", [{in_encoding, latin1},
2> {out_encoding, utf8}]).
"foo%C3%B6bar"
	

unquote(QuotedData) -> Data

Types:

Percent decode characters.

Example:

1> uri_string:unquote("SomeId%2F04").
"SomeId/04"
2> uri_string:unquote(<<"SomeId%2F04">>).
<<"SomeId/04">>
	

Function is not aware about any URI component context and should not be used on whole URI. If applied more than once on the same data, might produce unexpected results.