How do you URL encode parameters in Erlang?

Question

I\'m using httpc:request to post some data to a remote service. I have the post working but the data in the body() of the post comes through as is, without any URL-encoding

Answer 1

Here's a "fork" of the edoc_lib:escape_uri function that improves on the UTF-8 support and also supports binaries.

escape_uri(S) when is_list(S) ->
    escape_uri(unicode:characters_to_binary(S));
escape_uri(<>) when C >= $a, C =< $z ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) when C >= $A, C =< $Z ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) when C >= $0, C =< $9 ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) when C == $. ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) when C == $- ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) when C == $_ ->
    [C] ++ escape_uri(Cs);
escape_uri(<>) ->
    escape_byte(C) ++ escape_uri(Cs);
escape_uri(<<>>) ->
    "".

escape_byte(C) ->
    "%" ++ hex_octet(C).

hex_octet(N) when N =< 9 ->
    [$0 + N];
hex_octet(N) when N > 15 ->
    hex_octet(N bsr 4) ++ hex_octet(N band 15);
hex_octet(N) ->
    [N - 10 + $a].

Note that, because of the use of unicode:characters_to_binary it'll only work in R13 or newer.

Example usage is:

9> httpc:request("http://httpbin.org/get?q=" ++ mylib_app:escape_uri("☺")).
{ok,{{"HTTP/1.1",200,"OK"},
     [{"connection","keep-alive"},
      {"date","Sat, 09 Nov 2019 21:51:54 GMT"},
      {"server","nginx"},
      {"content-length","178"},
      {"content-type","application/json"},
      {"access-control-allow-credentials","true"},
      {"access-control-allow-origin","*"},
      {"referrer-policy","no-referrer-when-downgrade"},
      {"x-content-type-options","nosniff"},
      {"x-frame-options","DENY"},
      {"x-xss-protection","1; mode=block"}],
     "{\n  \"args\": {\n    \"q\": \"\\u263a\"\n  }, \n  \"headers\": {\n    \"Host\": \"httpbin.org\"\n  }, \n  \"origin\": \"11.111.111.111, 11.111.111.111\", \n  \"url\": \"https://httpbin.org/get?q=\\u263a\"\n}\n"}}

We send out a request with escaped query parameter and see that we get back the correct Unicode codepoint.