aboutsummaryrefslogtreecommitdiffstats
path: root/lib/stdlib/src
diff options
context:
space:
mode:
Diffstat (limited to 'lib/stdlib/src')
-rw-r--r--lib/stdlib/src/binary.erl28
-rw-r--r--lib/stdlib/src/string.erl8
-rw-r--r--lib/stdlib/src/uri_string.erl65
3 files changed, 73 insertions, 28 deletions
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/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),
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-24 21:26:22 +0000