aboutsummaryrefslogtreecommitdiffstats
path: root/lib/stdlib
diff options
context:
space:
mode:
Diffstat (limited to 'lib/stdlib')
-rw-r--r--lib/stdlib/doc/src/erl_tar.xml2
-rw-r--r--lib/stdlib/doc/src/ets.xml31
-rw-r--r--lib/stdlib/doc/src/timer.xml2
-rw-r--r--lib/stdlib/doc/src/uri_string.xml57
-rw-r--r--lib/stdlib/src/beam_lib.erl3
-rw-r--r--lib/stdlib/src/binary.erl28
-rw-r--r--lib/stdlib/src/ets.erl11
-rw-r--r--lib/stdlib/src/string.erl8
-rw-r--r--lib/stdlib/src/uri_string.erl65
-rw-r--r--lib/stdlib/test/ets_SUITE.erl35
-rw-r--r--lib/stdlib/test/re_SUITE.erl15
-rw-r--r--lib/stdlib/test/string_SUITE.erl4
-rw-r--r--lib/stdlib/test/uri_string_SUITE.erl55
13 files changed, 259 insertions, 57 deletions
diff --git a/lib/stdlib/doc/src/erl_tar.xml b/lib/stdlib/doc/src/erl_tar.xml
index caf8f4a96d..14c543ee2b 100644
--- a/lib/stdlib/doc/src/erl_tar.xml
+++ b/lib/stdlib/doc/src/erl_tar.xml
@@ -417,7 +417,7 @@
<v>Reason = term()</v>
</type>
<desc>
- <p>Cconverts an error reason term to a human-readable error message
+ <p>Converts an error reason term to a human-readable error message
string.</p>
</desc>
</func>
diff --git a/lib/stdlib/doc/src/ets.xml b/lib/stdlib/doc/src/ets.xml
index 1b31a1ec9d..305376a425 100644
--- a/lib/stdlib/doc/src/ets.xml
+++ b/lib/stdlib/doc/src/ets.xml
@@ -487,6 +487,11 @@ Error: fun containing local Erlang function calls
<p>The pid of the heir of the table, or <c>none</c> if no heir
is set.</p>
</item>
+ <tag><c>{id,</c><seealso marker="#type-tid">
+ <c>tid()</c></seealso><c>}</c></tag>
+ <item>
+ <p>The table identifier.</p>
+ </item>
<tag><c>{keypos, integer() >= 1}</c></tag>
<item>
<p>The key position.</p>
@@ -1074,10 +1079,13 @@ ets:select(Table, MatchSpec),</code>
</item>
<tag><c>named_table</c></tag>
<item>
- <p>If this option is present, name <c><anno>Name</anno></c> is
- associated with the table identifier. The name can then
- be used instead of the table identifier in subsequent
- operations.</p>
+ <p>If this option is present, the table is registered under its
+ <c><anno>Name</anno></c> which can then be used instead of the
+ table identifier in subsequent operations.</p>
+ <p>The function will also return the <c><anno>Name</anno></c>
+ instead of the table identifier. To get the table identifier of a
+ named table, use
+ <seealso marker="#whereis/1"><c>whereis/1</c></seealso>.</p>
</item>
<tag><c>{keypos,<anno>Pos</anno>}</c></tag>
<item>
@@ -2037,6 +2045,21 @@ true</pre>
</list>
</desc>
</func>
+
+ <func>
+ <name name="whereis" arity="1"/>
+ <fsummary>Retrieves the tid() of a named table.</fsummary>
+ <desc>
+ <p>This function returns the
+ <seealso marker="#type-tid"><c>tid()</c></seealso> of the named table
+ identified by <c><anno>TableName</anno></c>, or <c>undefined</c> if
+ no such table exists. The <c>tid()</c> can be used in place of the
+ table name in all operations, which is slightly faster since the name
+ does not have to be resolved on each call.</p>
+ <p>If the table is deleted, the <c>tid()</c> will be invalid even if
+ another named table is created with the same name.</p>
+ </desc>
+ </func>
</funcs>
</erlref>
diff --git a/lib/stdlib/doc/src/timer.xml b/lib/stdlib/doc/src/timer.xml
index fcaccdb2cb..350847bf7d 100644
--- a/lib/stdlib/doc/src/timer.xml
+++ b/lib/stdlib/doc/src/timer.xml
@@ -270,7 +270,7 @@
<item>
<p>Evaluates <c>apply(<anno>Module</anno>, <anno>Function</anno>,
<anno>Arguments</anno>)</c> and measures the elapsed real time as
- reported by <seealso marker="os:timestamp/0">
+ reported by <seealso marker="kernel:os#timestamp/0">
<c>os:timestamp/0</c></seealso>.</p>
<p>Returns <c>{<anno>Time</anno>, <anno>Value</anno>}</c>, where
<c><anno>Time</anno></c> is the elapsed real time in
diff --git a/lib/stdlib/doc/src/uri_string.xml b/lib/stdlib/doc/src/uri_string.xml
index 21f470e763..88d4600611 100644
--- a/lib/stdlib/doc/src/uri_string.xml
+++ b/lib/stdlib/doc/src/uri_string.xml
@@ -4,7 +4,7 @@
<erlref>
<header>
<copyright>
- <year>2017</year><year>2017</year>
+ <year>2017</year><year>2018</year>
<holder>Ericsson AB. All Rights Reserved.</holder>
</copyright>
<legalnotice>
@@ -24,7 +24,7 @@
<title>uri_string</title>
<prepared>Péter Dimitrov</prepared>
<docno>1</docno>
- <date>2017-10-24</date>
+ <date>2018-02-07</date>
<rev>A</rev>
</header>
<module>uri_string</module>
@@ -32,7 +32,11 @@
<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>).
+ form-urlencoded query strings (<url href="https://www.w3.org/TR/html52/">HTML 5.2</url>).
+ </p>
+ <p>
+ Parsing and serializing non-UTF-8 form-urlencoded query strings are also supported
+ (<url href="https://www.w3.org/TR/html50/">HTML 5.0</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>.
@@ -70,7 +74,8 @@
<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>
+ <seealso marker="#normalize/1"><c>normalize/1</c></seealso><br></br>
+ <seealso marker="#normalize/2"><c>normalize/2</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>
@@ -151,8 +156,10 @@
<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.
+ 4.10.21.6 of the <url href="https://www.w3.org/TR/html52/">HTML 5.2</url>
+ specification and in section 4.10.22.6 of the
+ <url href="https://www.w3.org/TR/html50/">HTML 5.0</url> specification for
+ non-UTF-8 encodings.
</p>
<p>See also the opposite operation <seealso marker="#dissect_query/1">
<c>dissect_query/1</c></seealso>.
@@ -209,12 +216,11 @@
<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.
+ 4.10.21.6 of the <url href="https://www.w3.org/TR/html52/">HTML 5.2</url>
+ specification and in section 4.10.22.6 of the
+ <url href="https://www.w3.org/TR/html50/">HTML 5.0</url> specification for
+ non-UTF-8 encodings.
</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>
@@ -233,7 +239,7 @@
<name name="normalize" arity="1"/>
<fsummary>Syntax-based normalization.</fsummary>
<desc>
- <p>Transforms <c><anno>URIString</anno></c> into a normalized form
+ <p>Transforms an <c><anno>URI</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
@@ -247,6 +253,33 @@
<![CDATA[<<"mid/6">>]]>
3> uri_string:normalize("http://localhost:80").
"https://localhost/"
+4> <input>uri_string:normalize(#{scheme => "http",port => 80,path => "/a/b/c/./../../g",</input>
+4> host => "localhost-örebro"}).
+"http://localhost-%C3%B6rebro/a/g"
+ </pre>
+ </desc>
+ </func>
+
+ <func>
+ <name name="normalize" arity="2"/>
+ <fsummary>Syntax-based normalization.</fsummary>
+ <desc>
+ <p>Same as <c>normalize/1</c> but with an additional
+ <c><anno>Options</anno></c> parameter, that controls if the normalized URI
+ shall be returned as an uri_map().
+ There is one supported option: <c>return_map</c>.
+ </p>
+ <p><em>Example:</em></p>
+ <pre>
+1> <input>uri_string:normalize("/a/b/c/./../../g", [return_map]).</input>
+#{path => "/a/g"}
+2> <![CDATA[uri_string:normalize(<<"mid/content=5/../6">>, [return_map]).]]>
+<![CDATA[#{path => <<"mid/6">>}]]>
+3> uri_string:normalize("http://localhost:80", [return_map]).
+#{scheme => "http",path => "/",host => "localhost"}
+4> <input>uri_string:normalize(#{scheme => "http",port => 80,path => "/a/b/c/./../../g",</input>
+4> host => "localhost-örebro"}, [return_map]).
+#{scheme => "http",path => "/a/g",host => "localhost-örebro"}
</pre>
</desc>
</func>
diff --git a/lib/stdlib/src/beam_lib.erl b/lib/stdlib/src/beam_lib.erl
index 06c15fceda..24349c74e8 100644
--- a/lib/stdlib/src/beam_lib.erl
+++ b/lib/stdlib/src/beam_lib.erl
@@ -148,7 +148,8 @@ chunks(File, Chunks, Options) ->
try read_chunk_data(File, Chunks, Options)
catch Error -> Error end.
--spec all_chunks(beam()) -> {'ok', 'beam_lib', [{chunkid(), dataB()}]}.
+-spec all_chunks(beam()) ->
+ {'ok', 'beam_lib', [{chunkid(), dataB()}]} | {'error', 'beam_lib', info_rsn()}.
all_chunks(File) ->
read_all_chunks(File).
diff --git a/lib/stdlib/src/binary.erl b/lib/stdlib/src/binary.erl
index 6a64133b45..7d0e42489e 100644
--- a/lib/stdlib/src/binary.erl
+++ b/lib/stdlib/src/binary.erl
@@ -47,23 +47,39 @@ at(_, _) ->
-spec bin_to_list(Subject) -> [byte()] when
Subject :: binary().
-bin_to_list(_) ->
- erlang:nif_error(undef).
+bin_to_list(Subject) ->
+ binary_to_list(Subject).
-spec bin_to_list(Subject, PosLen) -> [byte()] when
Subject :: binary(),
PosLen :: part().
-bin_to_list(_, _) ->
- erlang:nif_error(undef).
+bin_to_list(Subject, {Pos, Len}) ->
+ bin_to_list(Subject, Pos, Len);
+bin_to_list(_Subject, _BadArg) ->
+ erlang:error(badarg).
-spec bin_to_list(Subject, Pos, Len) -> [byte()] when
Subject :: binary(),
Pos :: non_neg_integer(),
Len :: integer().
-bin_to_list(_, _, _) ->
- erlang:nif_error(undef).
+bin_to_list(Subject, Pos, Len) when not is_binary(Subject);
+ not is_integer(Pos);
+ not is_integer(Len) ->
+ %% binary_to_list/3 allows bitstrings as long as the slice fits, and we
+ %% want to badarg when Pos/Len aren't integers instead of raising badarith
+ %% when adjusting args for binary_to_list/3.
+ erlang:error(badarg);
+bin_to_list(Subject, Pos, 0) when Pos >= 0, Pos =< byte_size(Subject) ->
+ %% binary_to_list/3 doesn't handle this case.
+ [];
+bin_to_list(_Subject, _Pos, 0) ->
+ erlang:error(badarg);
+bin_to_list(Subject, Pos, Len) when Len < 0 ->
+ bin_to_list(Subject, Pos + Len, -Len);
+bin_to_list(Subject, Pos, Len) when Len > 0 ->
+ binary_to_list(Subject, Pos + 1, Pos + Len).
-spec compile_pattern(Pattern) -> cp() when
Pattern :: binary() | [binary()].
diff --git a/lib/stdlib/src/ets.erl b/lib/stdlib/src/ets.erl
index 039ab45868..6a559f0be5 100644
--- a/lib/stdlib/src/ets.erl
+++ b/lib/stdlib/src/ets.erl
@@ -73,7 +73,8 @@
select_count/2, select_delete/2, select_replace/2, select_reverse/1,
select_reverse/2, select_reverse/3, setopts/2, slot/2,
take/2,
- update_counter/3, update_counter/4, update_element/3]).
+ update_counter/3, update_counter/4, update_element/3,
+ whereis/1]).
%% internal exports
-export([internal_request_all/0]).
@@ -145,6 +146,7 @@ give_away(_, _, _) ->
InfoList :: [InfoTuple],
InfoTuple :: {compressed, boolean()}
| {heir, pid() | none}
+ | {id, tid()}
| {keypos, pos_integer()}
| {memory, non_neg_integer()}
| {name, atom()}
@@ -162,7 +164,7 @@ info(_) ->
-spec info(Tab, Item) -> Value | undefined when
Tab :: tab(),
- Item :: compressed | fixed | heir | keypos | memory
+ Item :: compressed | fixed | heir | id | keypos | memory
| name | named_table | node | owner | protection
| safe_fixed | safe_fixed_monotonic_time | size | stats | type
| write_concurrency | read_concurrency,
@@ -512,6 +514,11 @@ update_counter(_, _, _, _) ->
update_element(_, _, _) ->
erlang:nif_error(undef).
+-spec whereis(TableName) -> tid() | undefined when
+ TableName :: atom().
+whereis(_) ->
+ erlang:nif_error(undef).
+
%%% End of BIFs
-opaque comp_match_spec() :: reference().
diff --git a/lib/stdlib/src/string.erl b/lib/stdlib/src/string.erl
index e01bb7d85e..4e89819e41 100644
--- a/lib/stdlib/src/string.erl
+++ b/lib/stdlib/src/string.erl
@@ -420,10 +420,12 @@ to_number(_, Number, Rest, _, Tail) ->
%% Return the remaining string with prefix removed or else nomatch
-spec prefix(String::unicode:chardata(), Prefix::unicode:chardata()) ->
'nomatch' | unicode:chardata().
-prefix(Str, []) -> Str;
prefix(Str, Prefix0) ->
- Prefix = unicode:characters_to_list(Prefix0),
- case prefix_1(Str, Prefix) of
+ Result = case unicode:characters_to_list(Prefix0) of
+ [] -> Str;
+ Prefix -> prefix_1(Str, Prefix)
+ end,
+ case Result of
[] when is_binary(Str) -> <<>>;
Res -> Res
end.
diff --git a/lib/stdlib/src/uri_string.erl b/lib/stdlib/src/uri_string.erl
index a84679c595..28d36ea229 100644
--- a/lib/stdlib/src/uri_string.erl
+++ b/lib/stdlib/src/uri_string.erl
@@ -227,7 +227,7 @@
%% External API
%%-------------------------------------------------------------------------
-export([compose_query/1, compose_query/2,
- dissect_query/1, normalize/1, parse/1,
+ dissect_query/1, normalize/1, normalize/2, parse/1,
recompose/1, transcode/2]).
-export_type([error/0, uri_map/0, uri_string/0]).
@@ -292,18 +292,36 @@
%%-------------------------------------------------------------------------
%% Normalize URIs
%%-------------------------------------------------------------------------
--spec normalize(URIString) -> NormalizedURI when
- URIString :: uri_string(),
- NormalizedURI :: uri_string().
-normalize(URIString) ->
- %% Percent-encoding normalization and case normalization for
- %% percent-encoded triplets are achieved by running parse and
- %% recompose on the input URI string.
- recompose(
- normalize_path_segment(
- normalize_scheme_based(
- normalize_case(
- parse(URIString))))).
+-spec normalize(URI) -> NormalizedURI when
+ URI :: uri_string() | uri_map(),
+ NormalizedURI :: uri_string()
+ | error().
+normalize(URIMap) ->
+ normalize(URIMap, []).
+
+
+-spec normalize(URI, Options) -> NormalizedURI when
+ URI :: uri_string() | uri_map(),
+ Options :: [return_map],
+ NormalizedURI :: uri_string() | uri_map().
+normalize(URIMap, []) when is_map(URIMap) ->
+ recompose(normalize_map(URIMap));
+normalize(URIMap, [return_map]) when is_map(URIMap) ->
+ normalize_map(URIMap);
+normalize(URIString, []) ->
+ case parse(URIString) of
+ Value when is_map(Value) ->
+ recompose(normalize_map(Value));
+ Error ->
+ Error
+ end;
+normalize(URIString, [return_map]) ->
+ case parse(URIString) of
+ Value when is_map(Value) ->
+ normalize_map(Value);
+ Error ->
+ Error
+ end.
%%-------------------------------------------------------------------------
@@ -385,7 +403,8 @@ transcode(URIString, Options) when is_list(URIString) ->
%%-------------------------------------------------------------------------
%% Functions for working with the query part of a URI as a list
%% of key/value pairs.
-%% HTML5 - 4.10.22.6 URL-encoded form data
+%% HTML 5.2 - 4.10.21.6 URL-encoded form data - WHATWG URL (10 Jan 2018) - UTF-8
+%% HTML 5.0 - 4.10.22.6 URL-encoded form data - non UTF-8
%%-------------------------------------------------------------------------
%%-------------------------------------------------------------------------
@@ -393,7 +412,7 @@ transcode(URIString, Options) when is_list(URIString) ->
%% (application/x-www-form-urlencoded encoding algorithm)
%%-------------------------------------------------------------------------
-spec compose_query(QueryList) -> QueryString when
- QueryList :: [{uri_string(), uri_string()}],
+ QueryList :: [{unicode:chardata(), unicode:chardata()}],
QueryString :: uri_string()
| error().
compose_query(List) ->
@@ -401,7 +420,7 @@ compose_query(List) ->
-spec compose_query(QueryList, Options) -> QueryString when
- QueryList :: [{uri_string(), uri_string()}],
+ QueryList :: [{unicode:chardata(), unicode:chardata()}],
Options :: [{encoding, atom()}],
QueryString :: uri_string()
| error().
@@ -432,7 +451,7 @@ compose_query([], _Options, IsList, Acc) ->
%%-------------------------------------------------------------------------
-spec dissect_query(QueryString) -> QueryList when
QueryString :: uri_string(),
- QueryList :: [{uri_string(), uri_string()}]
+ QueryList :: [{unicode:chardata(), unicode:chardata()}]
| error().
dissect_query(<<>>) ->
[];
@@ -1755,7 +1774,8 @@ get_separator(_L) ->
<<"&">>.
-%% HTML5 - 4.10.22.6 URL-encoded form data - encoding
+%% HTML 5.2 - 4.10.21.6 URL-encoded form data - WHATWG URL (10 Jan 2018) - UTF-8
+%% HTML 5.0 - 4.10.22.6 URL-encoded form data - encoding (non UTF-8)
form_urlencode(Cs, [{encoding, latin1}]) when is_list(Cs) ->
B = convert_to_binary(Cs, utf8, utf8),
html5_byte_encode(base10_encode(B));
@@ -1850,7 +1870,8 @@ dissect_query_value(<<>>, IsList, Acc, Key, Value) ->
lists:reverse([{K,V}|Acc]).
-%% Form-urldecode input based on RFC 1866 [8.2.1]
+%% HTML 5.2 - 4.10.21.6 URL-encoded form data - WHATWG URL (10 Jan 2018) - UTF-8
+%% HTML 5.0 - 4.10.22.6 URL-encoded form data - decoding (non UTF-8)
form_urldecode(true, B) ->
Result = base10_decode(form_urldecode(B, <<>>)),
convert_to_list(Result, utf8);
@@ -1903,6 +1924,12 @@ base10_decode_unicode(<<H,_/binary>>, _, _) ->
%% Helper functions for normalize
%%-------------------------------------------------------------------------
+normalize_map(URIMap) ->
+ normalize_path_segment(
+ normalize_scheme_based(
+ normalize_case(URIMap))).
+
+
%% 6.2.2.1. Case Normalization
normalize_case(#{scheme := Scheme, host := Host} = Map) ->
Map#{scheme => to_lower(Scheme),
diff --git a/lib/stdlib/test/ets_SUITE.erl b/lib/stdlib/test/ets_SUITE.erl
index 0cfb1b5516..8b651f4b43 100644
--- a/lib/stdlib/test/ets_SUITE.erl
+++ b/lib/stdlib/test/ets_SUITE.erl
@@ -78,6 +78,7 @@
-export([ets_all/1]).
-export([massive_ets_all/1]).
-export([take/1]).
+-export([whereis_table/1]).
-export([init_per_testcase/2, end_per_testcase/2]).
%% Convenience for manual testing
@@ -137,7 +138,8 @@ all() ->
otp_9423,
ets_all,
massive_ets_all,
- take].
+ take,
+ whereis_table].
groups() ->
[{new, [],
@@ -4099,6 +4101,7 @@ info_do(Opts) ->
{value, {keypos, 2}} = lists:keysearch(keypos, 1, Res),
{value, {protection, protected}} =
lists:keysearch(protection, 1, Res),
+ {value, {id, Tab}} = lists:keysearch(id, 1, Res),
true = ets:delete(Tab),
undefined = ets:info(non_existing_table_xxyy),
undefined = ets:info(non_existing_table_xxyy,type),
@@ -5892,6 +5895,36 @@ take(Config) when is_list(Config) ->
ets:delete(T3),
ok.
+whereis_table(Config) when is_list(Config) ->
+ %% Do we return 'undefined' when the named table doesn't exist?
+ undefined = ets:whereis(whereis_test),
+
+ %% Does the tid() refer to the same table as the name?
+ whereis_test = ets:new(whereis_test, [named_table]),
+ Tid = ets:whereis(whereis_test),
+
+ ets:insert(whereis_test, [{hello}, {there}]),
+
+ [[{hello}],[{there}]] = ets:match(whereis_test, '$1'),
+ [[{hello}],[{there}]] = ets:match(Tid, '$1'),
+
+ true = ets:delete_all_objects(Tid),
+
+ [] = ets:match(whereis_test, '$1'),
+ [] = ets:match(Tid, '$1'),
+
+ %% Does the name disappear when deleted through the tid()?
+ true = ets:delete(Tid),
+ undefined = ets:info(whereis_test),
+ {'EXIT',{badarg, _}} = (catch ets:match(whereis_test, '$1')),
+
+ %% Is the old tid() broken when the table is re-created with the same
+ %% name?
+ whereis_test = ets:new(whereis_test, [named_table]),
+ [] = ets:match(whereis_test, '$1'),
+ {'EXIT',{badarg, _}} = (catch ets:match(Tid, '$1')),
+
+ ok.
%%
%% Utility functions:
diff --git a/lib/stdlib/test/re_SUITE.erl b/lib/stdlib/test/re_SUITE.erl
index 71f86e32e5..7b82647416 100644
--- a/lib/stdlib/test/re_SUITE.erl
+++ b/lib/stdlib/test/re_SUITE.erl
@@ -894,10 +894,13 @@ match_limit(Config) when is_list(Config) ->
%% Test that we get sub-binaries if subject is a binary and we capture
%% binaries.
sub_binaries(Config) when is_list(Config) ->
- Bin = list_to_binary(lists:seq(1,255)),
- {match,[B,C]}=re:run(Bin,"(a)",[{capture,all,binary}]),
- 255 = binary:referenced_byte_size(B),
- 255 = binary:referenced_byte_size(C),
- {match,[D]}=re:run(Bin,"(a)",[{capture,[1],binary}]),
- 255 = binary:referenced_byte_size(D),
+ %% The GC can auto-convert tiny sub-binaries to heap binaries, so we
+ %% extract large sequences to make the test more stable.
+ Bin = << <<I>> || I <- lists:seq(1, 4096) >>,
+ {match,[B,C]}=re:run(Bin,"a(.+)$",[{capture,all,binary}]),
+ true = byte_size(B) =/= byte_size(C),
+ 4096 = binary:referenced_byte_size(B),
+ 4096 = binary:referenced_byte_size(C),
+ {match,[D]}=re:run(Bin,"a(.+)$",[{capture,[1],binary}]),
+ 4096 = binary:referenced_byte_size(D),
ok.
diff --git a/lib/stdlib/test/string_SUITE.erl b/lib/stdlib/test/string_SUITE.erl
index c4a469c251..fdff2d24b8 100644
--- a/lib/stdlib/test/string_SUITE.erl
+++ b/lib/stdlib/test/string_SUITE.erl
@@ -486,6 +486,10 @@ to_float(_) ->
prefix(_) ->
?TEST("", ["a"], nomatch),
?TEST("a", [""], "a"),
+ ?TEST("a", [[[]]], "a"),
+ ?TEST("a", [<<>>], "a"),
+ ?TEST("a", [[<<>>]], "a"),
+ ?TEST("a", [[[<<>>]]], "a"),
?TEST("b", ["a"], nomatch),
?TEST("a", ["a"], ""),
?TEST("å", ["a"], nomatch),
diff --git a/lib/stdlib/test/uri_string_SUITE.erl b/lib/stdlib/test/uri_string_SUITE.erl
index fef356355c..92f8bb3292 100644
--- a/lib/stdlib/test/uri_string_SUITE.erl
+++ b/lib/stdlib/test/uri_string_SUITE.erl
@@ -22,7 +22,7 @@
-include_lib("common_test/include/ct.hrl").
-export([all/0, suite/0,groups/0,
- normalize/1,
+ normalize/1, normalize_map/1, normalize_return_map/1, normalize_negative/1,
parse_binary_fragment/1, parse_binary_host/1, parse_binary_host_ipv4/1,
parse_binary_host_ipv6/1,
parse_binary_path/1, parse_binary_pct_encoded_fragment/1, parse_binary_pct_encoded_query/1,
@@ -68,6 +68,9 @@ suite() ->
all() ->
[
normalize,
+ normalize_map,
+ normalize_return_map,
+ normalize_negative,
parse_binary_scheme,
parse_binary_userinfo,
parse_binary_pct_encoded_userinfo,
@@ -912,6 +915,56 @@ normalize(_Config) ->
<<"tftp://localhost">> =
uri_string:normalize(<<"tftp://localhost:69">>).
+normalize_map(_Config) ->
+ "/a/g" = uri_string:normalize(#{path => "/a/b/c/./../../g"}),
+ <<"mid/6">> = uri_string:normalize(#{path => <<"mid/content=5/../6">>}),
+ "http://localhost-%C3%B6rebro/a/g" =
+ uri_string:normalize(#{scheme => "http",port => 80,path => "/a/b/c/./../../g",
+ host => "localhost-örebro"}),
+ <<"http://localhost-%C3%B6rebro/a/g">> =
+ uri_string:normalize(#{scheme => <<"http">>,port => 80,
+ path => <<"/a/b/c/./../../g">>,
+ host => <<"localhost-örebro"/utf8>>}),
+ <<"https://localhost/">> =
+ uri_string:normalize(#{scheme => <<"https">>,port => 443,path => <<>>,
+ host => <<"localhost">>}),
+ <<"https://localhost:445/">> =
+ uri_string:normalize(#{scheme => <<"https">>,port => 445,path => <<>>,
+ host => <<"localhost">>}),
+ <<"ftp://localhost">> =
+ uri_string:normalize(#{scheme => <<"ftp">>,port => 21,path => <<>>,
+ host => <<"localhost">>}),
+ <<"ssh://localhost">> =
+ uri_string:normalize(#{scheme => <<"ssh">>,port => 22,path => <<>>,
+ host => <<"localhost">>}),
+ <<"sftp://localhost">> =
+ uri_string:normalize(#{scheme => <<"sftp">>,port => 22,path => <<>>,
+ host => <<"localhost">>}),
+ <<"tftp://localhost">> =
+ uri_string:normalize(#{scheme => <<"tftp">>,port => 69,path => <<>>,
+ host => <<"localhost">>}).
+
+normalize_return_map(_Config) ->
+ #{scheme := "http",path := "/a/g",host := "localhost-örebro"} =
+ uri_string:normalize("http://localhos%74-%c3%b6rebro:80/a/b/c/./../../g",
+ [return_map]),
+ #{scheme := <<"http">>,path := <<"/a/g">>, host := <<"localhost-örebro"/utf8>>} =
+ uri_string:normalize(<<"http://localhos%74-%c3%b6rebro:80/a/b/c/./../../g">>,
+ [return_map]),
+ #{scheme := <<"https">>,path := <<"/">>, host := <<"localhost">>} =
+ uri_string:normalize(#{scheme => <<"https">>,port => 443,path => <<>>,
+ host => <<"localhost">>}, [return_map]).
+
+normalize_negative(_Config) ->
+ {error,invalid_uri,":"} =
+ uri_string:normalize("http://local>host"),
+ {error,invalid_uri,":"} =
+ uri_string:normalize(<<"http://local>host">>),
+ {error,invalid_uri,":"} =
+ uri_string:normalize("http://[192.168.0.1]", [return_map]),
+ {error,invalid_uri,":"} =
+ uri_string:normalize(<<"http://[192.168.0.1]">>, [return_map]).
+
interop_query_utf8(_Config) ->
Q = uri_string:compose_query([{"foo bar","1"}, {"合", "2"}]),
Uri = uri_string:recompose(#{path => "/", query => Q}),
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-12 14:13:45 +0000