jaredly / rex-json

A simple cross-target JSON parser for Reason/OCaml

Rex Json

A simple cross-target JSON library for Reason/OCaml

Works with both native and js targets (compiled with bsb-native).

Why would you want this library?

• you want minimal dependencies
• you want forgiving json parsing (comments, trailing commas allowed)
• you're fine with "good enough" performance

Installation

Add rex-json to your package.json and your bsconfig.json.

Usage:

let data = {|
{
  "some": "json", // with a comment!
  "more": [1,3,],
  /* also
  multi-line comment */
  "this": {
    "object": {
      "is": {
        "really": "nested"
      }
    }
  },
  "nested": [{
    "and": [1,2,{"stuff": 5}]
  }], // trailing commas!
}
|};
let json = Json.parse(data);
let simple = Json.get("some", json); /* == Some(String("json")) */

open Json.Infix;

let stuff = json
  |> Json.get("nested")
  |?> Json.nth(0)
  |?> Json.get("and")
  |?> Json.nth(2)
  |?> Json.get("stuff")
  |?> Json.number; /* == Some(5.) */

/** Using a json path for nested objects */
let nestedString = json
|> Json.getPath("this.object.is.really")
|?> Json.string; /* Some("nested") */

let str = Json.stringify(json); /* back to a string */
Js.log2(stuff, nestedString)

rex-json's Issues

Test suite

If you are interested, I found this test suite very useful for parsing JSON correctly: https://github.com/nst/JSONTestSuite/tree/master/test_parsing

// Beware, there's a lot of invisible characters in there
invalid("[1 true]");
invalid("[aÂ]");
invalid("[\"\": 1]");
invalid("[\"\"],");
invalid("[,1]");
invalid("[1,,2]");
invalid("[\"x\",,]");
invalid("[\"x\"]]");
invalid("[\"\",]");
invalid("[\"x\"");
invalid("[x");
invalid("[3[4]]");
invalid("[ˇ]");
invalid("[1:2]");
invalid("[,]");
invalid("[-]");
invalid("[ , \"\"]");
invalid("[\"a\", 4 ,1,");
invalid("[1,]");
invalid("[1,,]");
invalid("[\"�a\"\\f]");
invalid("[*]");
invalid("[\"\"");
invalid("[1,");
invalid("[1, 1 ,1");
invalid("[{}");
invalid("[fals]");
invalid("[nul]");
invalid("[tru]");
invalid("[++1234]");
invalid("[+1]");
invalid("[+Inf]");
invalid("[-01]");
invalid("[-1.0.]");
invalid("[-2.]");
invalid("[-NaN]");
invalid("[.-1]");
invalid("[.2e-3]");
invalid("[0.1.2]");
invalid("[0.3e+]");
invalid("[0.3e]");
invalid("[0.e1]");
invalid("[0E+]");
invalid("[0E]");
invalid("[0e+]");
invalid("[0e]");
invalid("[1.0e+]");
invalid("[1.0e-]");
invalid("[1.0e]");
invalid("[1 000.0]");
invalid("[1eE2]");
invalid("[2.e+3]");
invalid("[2.e-3]");
invalid("[2.e3]");
invalid("[9.e+]");
invalid("[1+2]");
invalid("[0x1]");
invalid("[0x42]");
invalid("[Inf]");
invalid("[Infinity]");
invalid("[0e+-1]");
invalid("[-123.123foo]");
invalid("[123Â]");
invalid("[1e1Â]");
invalid("[0Â]");
invalid("[-Infinity]");
invalid("[-foo]");
invalid("[- 1]");
invalid("[NaN]");
invalid("[-012]");
invalid("[-.123]");
invalid("[-1x]");
invalid("[1ea]");
invalid("[1eÂ]");
invalid("[1.]");
invalid("[.123]");
invalid("[１]");
invalid("[1.2a-3]");
invalid("[1.8011670033376514H-308]");
invalid("[012]");
invalid("[\"x\", truth]");
invalid("{[: \"x\"}");
invalid("{\"x\", null}");
invalid("{\"x\"::\"b\"}");
invalid("{🇨🇭}");
invalid("{\"a\":\"a\" 123}");
invalid("{key: 'value'}");
invalid("{\"a\" b}");
invalid("{:\"b\"}");
invalid("{\"a\" \"b\"}");
invalid("{\"a\":");
invalid("{\"a\"");
invalid("{1:1}");
invalid("{9999E9999:1}");
invalid("{\"π\":\"0\",}");
invalid("{null:null,null:null}");
invalid("{\"id\":0,,,,,}");
invalid("{'a':0}");
invalid("{\"id\":0,}");
invalid("{\"a\":\"b\"}/**/");
invalid("{\"a\":\"b\"}/**//");
invalid("{\"a\":\"b\"}//");
invalid("{\"a\":\"b\"}/");
invalid("{\"a\":\"b\",,\"c\":\"d\"}");
invalid("{a: \"b\"}");
invalid("{\"a\":\"a");
invalid("{ \"foo\" : \"bar\", \"a\" }");
invalid("{\"a\":\"b\"}#");
invalid(" ");
invalid("[\"\\uD800\\\"]");
invalid("[\"\\uD800\\u\"]");
invalid("[\"\\uD800\\u1\"]");
invalid("[\"\\uD800\\u1x\"]");
invalid("[é]");
invalid("[\"\\\"]");
invalid("[\"\\x00\"]");
invalid("[\"\\\\\\\"]");
invalid("[\"\\ \"]");
invalid("[\"\\🌀\"]");
invalid("[\"\\\"]");
invalid("[\"\\u00A\"]");
invalid("[\"\\uD834\\uDd\"]");
invalid("[\"\\uD800\\uD800\\x\"]");
invalid("[\"\\uÂ\"]");
invalid("[\"\\a\"]");
invalid("[\"\\uqqqq\"]");
invalid("[\"\\Â\"]");
invalid("[\\u0020\"asd\"]");
invalid("[\\n]");
invalid("\"");
invalid("['single quote']");
invalid("abc");
invalid("[\"\\");
invalid("[\"a\fa\"]");
invalid("[\"new\nline\"]");
invalid("[\"\t\"]");
invalid("\"\\UA66D\"");
invalid("\"\"x");
// Too long
invalid("<.>");
invalid("[<null>]");
invalid("[1]x");
invalid("[1]]");
invalid("[\"asd]");
invalid("aå");
invalid("[True]");
invalid("1]");
invalid("{\"x\": true,");
invalid("[][]");
invalid("]");
invalid("Ôª{}");
invalid("Â");
invalid("[");
invalid("");
invalid("[]\0");
invalid("2@");
invalid("{}}");
invalid("{\"\":");
invalid("{\"a\":/*comment*/\"b\"}");
invalid("{\"a\": true} \"x\"");
invalid("['");
invalid("[,");
// Too long
invalid("[{");
invalid("[\"a");
invalid("[\"a\"");
invalid("{");
invalid("{]");
invalid("{,");
invalid("{[");
invalid("{\"a");
invalid("{'a'");
invalid("[\"\\{[\"\\{[\"\\{[\"\\{");
invalid("È");
invalid("*");
invalid("{\"a\":\"b\"}#{}");
invalid("[⁠]");
invalid("[\\u000A\"\"]");
invalid("[1");
invalid("[ false, nul");
invalid("[ true, fals");
invalid("[ false, tru");
invalid("{\"asd\":\"asd\"");
invalid("å");
invalid("Ôªø");
invalid("[]");
invalid("[⁠]");

roundtrip("[[] ]");
roundtrip("[\"\"]");
roundtrip("[]");
roundtrip("[\"a\"]");
roundtrip("[false]");
roundtrip("[null, 1, \"1\", {}]");
roundtrip("[null]");
roundtrip("[1 ]");
roundtrip(" [1]");
roundtrip("[1,null,null,null,2]");
roundtrip("[2] ");
roundtrip("[123e65]");
roundtrip("[0e+1]");
roundtrip("[0e1]");
roundtrip("[ 4]");
roundtrip("[-0.000000000000000000000000000000000000000000000000000000000000000000000000000001]");
roundtrip("[20e1]");
roundtrip("[-0]");
roundtrip("[-123]");
roundtrip("[-1]");
roundtrip("[1E22]");
roundtrip("[1E-2]");
roundtrip("[1E+2]");
roundtrip("[123e45]");
roundtrip("[123.456e78]");
roundtrip("[1e-2]");
roundtrip("[1e+2]");
roundtrip("[123]");
roundtrip("[123.456789]");
roundtrip("{\"asd\":\"sdf\", \"dfg\":\"fgh\"}");
roundtrip("{\"asd\":\"sdf\"}");
roundtrip("{\"a\":\"b\",\"a\":\"c\"}");
roundtrip("{\"a\":\"b\",\"a\":\"b\"}");
roundtrip("{}");
roundtrip("{\"\":0}");
roundtrip("{\"foo\\u0000bar\": 42}");
roundtrip("{ \"min\": -1.0e+28, \"max\": 1.0e+28 }");
roundtrip("{\"x\":[{\"id\": \"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\"}], \"id\": \"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\"}");
roundtrip("{\"a\":[]}");
roundtrip("{\"title\":\"\\u041f\\u043e\\u043b\\u0442\\u043e\\u0440\\u0430 \\u0417\\u0435\\u043c\\u043b\\u0435\\u043a\\u043e\\u043f\\u0430\" }");
roundtrip("{ \"a\": \"b\" }");
roundtrip("[\"\\u0060\\u012a\\u12AB\"]");
roundtrip("[\"\\uD801\\udc37\"]");
roundtrip("[\"\\ud83d\\ude39\\ud83d\\udc8d\"]");
roundtrip("[\"\\\"\\\\\\/\\b\\f\\n\\r\\t\"]");
roundtrip("[\"\\\\u0000\"]");
roundtrip("[\"\\\"\"]");
roundtrip("[\"a/*b*/c/*d//e\"]");
roundtrip("[\"\\\\a\"]");
roundtrip("[\"\\\\n\"]");
roundtrip("[\"\\u0012\"]");
roundtrip("[\"\\uFFFF\"]");
roundtrip("[\"asd\"]");
roundtrip("[ \"asd\"]");
roundtrip("[\"\\uDBFF\\uDFFF\"]");
roundtrip("[\"new\\u00A0line\"]");
roundtrip("[\"�\"]");
roundtrip("[\"𛿿\"]");
roundtrip("[\"�\"]");
roundtrip("[\"\\u0000\"]");
roundtrip("[\"\\u002c\"]");
roundtrip("[\"π\"]");
roundtrip("[\"asd \"]");
roundtrip("\" \"");
roundtrip("[\"\\uD834\\uDd1e\"]");
roundtrip("[\"\\u0821\"]");
roundtrip("[\"\\u0123\"]");
roundtrip("[\"
\"]");
roundtrip("[\"
\"]");
roundtrip("[\"\\u0061\\u30af\\u30EA\\u30b9\"]");
roundtrip("[\"new\\u000Aline\"]");
roundtrip("[\"�\"]");
roundtrip("[\"\\uA66D\"]");
roundtrip("[\"⍂㈴⍂\"]");
roundtrip("[\"\\u0022\"]");
roundtrip("[\"\\uDBFF\\uDFFE\"]");
roundtrip("[\"\\uD83F\\uDFFE\"]");
roundtrip("[\"\\u200B\"]");
roundtrip("[\"\\u2064\"]");
roundtrip("[\"\\uFDD0\"]");
roundtrip("[\"\\uFFFE\"]");
roundtrip("[\"\\u005C\"]");
roundtrip("[\"€𝄞\"]");
roundtrip("[\"a�a\"]");
roundtrip("42");
roundtrip("-0.1");
roundtrip("\"asd\"");
roundtrip("\"\"");
roundtrip("[\"a\"]");
roundtrip("[true]");
roundtrip(" [] ");

// number
roundtrip("123");
invalid("0.");
invalid("0.x");
invalid("0ex");
invalid("0e-x1");
invalid("0ex1");

// null
roundtrip("null");
invalid("nill");
invalid("nu1l");
invalid("nul1");

// true
roundtrip("true");
invalid("txue");
invalid("trxe");
invalid("trux");

// false
roundtrip("false");
invalid("fxlse");
invalid("faxse");
invalid("falxe");
invalid("falsx");

// string escapes
roundtrip("\"\\u1234\"");
roundtrip("\"\\uabcd\"");
roundtrip("\"\\uCDEF\"");
invalid("\"\\x\"");
invalid("\"\\u123\"");
invalid("\"\\uabcx\"");

Parsing of long string literals with escaped characters is slow

If you try to parse a long string value with a lot of escape sequences, the parser uses String.sub for getting 2-character substring like \" from the long string. Unfortunately, JavaScript implementation of String.sub works the way it converts the WHOLE string to bytes (one byte at a time), gets requested range from the bytes array and converts it back to string.

This necessarily means that if you have 200,000 char JSON string with 10,000 escape sequences, the whole string is traversed 10,000x 🙁

rex-json/src/Json.re

Line 274 in c929cb4

Buffer.add_string(buffer, Scanf.unescaped(String.sub(text, i, 2)));

Solutions I've come up with:

• Make sure that Js.String.substrAtMost is used when targeting JavaScript
  • Or do you expect the OCaml-way of handling strings? (String.sub working on bytes instead of UTF8 characters)
  • Usage: Js.String.substrAtMost(~from=i, ~length=2, text)
• Create or use some existing library for UTF8 strings that compiles to Js.String in case of JavaScript.
  • Do you know some? I've just started with Reason/BS/OCaml so I'm not really sure if there is some "industry standard" of handling UTF strings in Ocaml...

Otherwise thank you for making this fantastically ergonomic library, the infix operators are great!

getting json from path in directory

Trying to see if I can use this to dynamically encode lab.json and theme.json files produced by c8r/lab output. Example in that repo here

I get the following error:

/Users/prisc_000/code/BHYV/lab-rex-json/node_modules/bs-platform/lib/js/pervasives.js:14
  throw [
  ^
Failure,-2,Error "unexpected character" at 1:5 ->   

Running this code with rex-json:

[@bs.module] external theme : string = "./theme.json";

/* let theme = ThemeJs.theme; */
let data = {|
    theme
    |};

/* let data = {|
   {
       "fonts": ["-apple-system, BlinkMacSystemFont, sans-serif"],
       "space": [0, 4, 8, 16, 32, 64, 128, 256],
       "fontSizes": [12, 14, 16, 20, 24, 32, 48, 64, 72, 96],
       "colors": {
         "black": "#000",
         "blue": "#07c",
         "lightgray": "#eee"
       },
       "primary": "red"
     }
   |}; */
/* [@bs.module] external theme : Js.Json.t = "./theme.json"; */
let json = Json.parse(data);

Js.log(data);

Js.log(json);

It works logging if i paste the json right in. Am i doing something stupid?

Thank you.

Json.getPath signature

Hi,

I'll begin by saying, amazing library, thank you!

I've looked at the getPath signature and started wondering whether it wouldn't be nicer if it had the following signature: list(string) => option(string) = <fun>;

It would mean less parsing in the library and support for crazy json authors who include . in their keys.

This is all a bit inspired, by how Ramda does it: https://ramdajs.com/docs/#path

Thanks!

Handle Unicode escapes

Strings in JSON can contain escaped Unicode characters (i.e. \uXXXX) and the spec says that it's legal for any character to be escaped (even though technically you only need to escape a few of them).

The Java LSP client library (lsp4j) is particularly aggressive about escaping characters, so it immediately runs into this issue. For example, it sends:

{
  "jsonrpc": "2.0",
  "method": "textDocument/didOpen",
  "params": {
    "textDocument": {
      "uri": "file:///Users/mdb/ops/langs/reason/a-reason-react-tutorial/src/Main.re",
      "languageId": "re",
      "version": 1,
      "text": "ReactDOMRe.renderToElementWithId(\u003cTodoApp /\u003e, \"root\");\n"
    }
  }
}

(which escapes < and >) and this fails thusly:

Scanf.Scan_failure(\"scanf: bad input at char number 35: \\\"illegal escape character 'u'\\\"\")

I hacked the code to turn \u00XX into \xXX just to work around this for now (it would still fail on any non-ASCII escaped Unicode characters). I don't name my variables with UTF-8 smileys. 😁 But a proper decoding of Unicode escapes will be needed at some point.