fix: Fix uri encoding/decoding and add new tests

CHANGELOG.md

@@ -22,3 +22,7 @@
 
 - Minor performance improvement for erlang
 - Major performance improvement for js
+
+## 2.0.4
+
+- Reverted some optimisations as they are unnecessary for Gleam v1.14.0+

gleam.toml

@@ -1,12 +1,12 @@
 name = "gluri"
-version = "2.0.3"
+version = "2.0.4"
 
 # Fill out these fields if you intend to generate HTML documentation or publish
 # your project to the Hex package manager.
 #
  description = "Uri (RFC 3986) library for Gleam"
  licences = ["Apache-2.0"]
- repository = { type = "github", user = "pendletong", repo = "uri" }
+ repository = { type = "gitea", host = "git.pendleton.ie", user = "pendletong", repo = "uri" }
  links = [{ title = "RFC 3986", href = "https://www.ietf.org/rfc/rfc3986.txt" }]
 #
 # For a full reference of all the available options, you can have a look at

manifest.toml

@@ -3,7 +3,7 @@
 
 packages = [
   { name = "argv", version = "1.0.2", build_tools = ["gleam"], requirements = [], otp_app = "argv", source = "hex", outer_checksum = "BA1FF0929525DEBA1CE67256E5ADF77A7CDDFE729E3E3F57A5BDCAA031DED09D" },
-  { name = "benchee", version = "1.4.0", build_tools = ["mix"], requirements = ["deep_merge", "statistex", "table"], otp_app = "benchee", source = "hex", outer_checksum = "299CD10DD8CE51C9EA3DDB74BB150F93D25E968F93E4C1FA31698A8E4FA5D715" },
+  { name = "benchee", version = "1.5.0", build_tools = ["mix"], requirements = ["deep_merge", "statistex", "table"], otp_app = "benchee", source = "hex", outer_checksum = "5B075393AEA81B8AE74EADD1C28B1D87E8A63696C649D8293DB7C4DF3EB67535" },
   { name = "bigben", version = "1.0.1", build_tools = ["gleam"], requirements = ["birl", "gleam_erlang", "gleam_otp", "gleam_stdlib"], otp_app = "bigben", source = "hex", outer_checksum = "190E489610A80D76C48BACC75EB8314BD184FF0220AB0F251ABE760B993B91BB" },
   { name = "birl", version = "1.8.0", build_tools = ["gleam"], requirements = ["gleam_regexp", "gleam_stdlib", "ranger"], otp_app = "birl", source = "hex", outer_checksum = "2AC7BA26F998E3DFADDB657148BD5DDFE966958AD4D6D6957DD0D22E5B56C400" },
   { name = "deep_merge", version = "1.0.0", build_tools = ["mix"], requirements = [], otp_app = "deep_merge", source = "hex", outer_checksum = "CE708E5F094B9CD4E8F2BE4F00D2F4250C4095BE93F8CD6D018C753894885430" },
@@ -14,9 +14,9 @@ packages = [
   { name = "gleam_erlang", version = "1.3.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_erlang", source = "hex", outer_checksum = "1124AD3AA21143E5AF0FC5CF3D9529F6DB8CA03E43A55711B60B6B7B3874375C" },
   { name = "gleam_javascript", version = "1.0.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_javascript", source = "hex", outer_checksum = "EF6C77A506F026C6FB37941889477CD5E4234FCD4337FF0E9384E297CB8F97EB" },
   { name = "gleam_json", version = "3.0.2", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_json", source = "hex", outer_checksum = "874FA3C3BB6E22DD2BB111966BD40B3759E9094E05257899A7C08F5DE77EC049" },
-  { name = "gleam_otp", version = "1.1.0", build_tools = ["gleam"], requirements = ["gleam_erlang", "gleam_stdlib"], otp_app = "gleam_otp", source = "hex", outer_checksum = "7987CBEBC8060B88F14575DEF546253F3116EBE2A5DA6FD82F38243FCE97C54B" },
+  { name = "gleam_otp", version = "1.2.0", build_tools = ["gleam"], requirements = ["gleam_erlang", "gleam_stdlib"], otp_app = "gleam_otp", source = "hex", outer_checksum = "BA6A294E295E428EC1562DC1C11EA7530DCB981E8359134BEABC8493B7B2258E" },
   { name = "gleam_regexp", version = "1.1.1", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_regexp", source = "hex", outer_checksum = "9C215C6CA84A5B35BB934A9B61A9A306EC743153BE2B0425A0D032E477B062A9" },
-  { name = "gleam_stdlib", version = "0.63.2", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "962B25C667DA07F4CAB32001F44D3C41C1A89E58E3BBA54F183B482CF6122150" },
+  { name = "gleam_stdlib", version = "0.65.0", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "7C69C71D8C493AE11A5184828A77110EB05A7786EBF8B25B36A72F879C3EE107" },
   { name = "gleam_time", version = "1.4.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_time", source = "hex", outer_checksum = "DCDDC040CE97DA3D2A925CDBBA08D8A78681139745754A83998641C8A3F6587E" },
   { name = "gleam_yielder", version = "1.1.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_yielder", source = "hex", outer_checksum = "8E4E4ECFA7982859F430C57F549200C7749823C106759F4A19A78AEA6687717A" },
   { name = "gleeunit", version = "1.6.1", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleeunit", source = "hex", outer_checksum = "FDC68A8C492B1E9B429249062CD9BAC9B5538C6FBF584817205D0998C42E1DAC" },

src/gluri/internal/utils.gleam

@@ -109,7 +109,7 @@ pub fn parse_min_max(
   do_parse_min_max(str, "", min, max, parse_fn)
 }
 
-pub fn do_parse_min_max(
+fn do_parse_min_max(
   str: d,
   acc: String,
   min: Int,
@@ -403,14 +403,6 @@ pub fn parse_hex_digits(str, min, max) {
   parse_min_max(str, min, max, parse_hex_digit)
 }
 
-fn encoding_not_needed(i: Int) -> Bool {
-  // $-_.+!*'()
-  case i {
-    36 | 45 | 95 | 46 | 43 | 33 | 42 | 39 | 40 | 41 -> True
-    _ -> False
-  }
-}
-
 fn is_unreserved_char(i: Int) -> Bool {
   case i {
     45 | 46 | 95 | 126 -> True
@@ -660,13 +652,13 @@ pub fn do_percent_encode(str: String) -> String {
 fn encode_codepoint(codepoint: Int) -> String {
   case codepoint <= 127 {
     True -> {
-      case is_unreserved_char(codepoint) || encoding_not_needed(codepoint) {
+      case is_unreserved_char(codepoint) {
         True -> {
           let assert Ok(cpnt) = string.utf_codepoint(codepoint)
           string.from_utf_codepoints([cpnt])
         }
         False -> {
-          "%" <> int.to_base16(codepoint)
+          "%" <> string.pad_start(int.to_base16(codepoint), 2, "0")
         }
       }
     }

test/benchmark.gleam

@@ -89,11 +89,15 @@ pub fn parse_benchmark() {
 pub fn pop_benchmark() {
   benchmark.run(
     [
-      benchmark.Function("pop", fn(data) { fn() { pop(data, "") } }),
-      benchmark.Function("pop2", fn(data) { fn() { pop4(data, "") } }),
-      benchmark.Function("pop3", fn(data) { fn() { pop5(data, "") } }),
-      benchmark.Function("match", fn(data) { fn() { pop2(data, "") } }),
-      benchmark.Function("match_2", fn(data) { fn() { pop3(data, "") } }),
+      benchmark.Function("pop with range", fn(data) { fn() { pop(data, "") } }),
+      benchmark.Function("pop check char", fn(data) { fn() { pop4(data, "") } }),
+      benchmark.Function("pop check result", fn(data) {
+        fn() { pop5(data, "") }
+      }),
+      benchmark.Function("letter as var <> tail", fn(data) {
+        fn() { pop2(data, "") }
+      }),
+      benchmark.Function("letter <> tail", fn(data) { fn() { pop3(data, "") } }),
     ],
     [
       // benchmark.Data("long", "abcdefghijklmnopqrstuvwxyz"),

test/gluri_test.gleam

@@ -1146,37 +1146,31 @@ pub fn equivalence_tests() {
   ])
 }
 
-const percent_codec_fixtures = [
-  #(" ", "%20"),
-  #(",", "%2C"),
-  #(";", "%3B"),
-  #(":", "%3A"),
-  #("!", "!"),
-  #("?", "%3F"),
-  #("'", "'"),
-  #("(", "("),
-  #(")", ")"),
-  #("[", "%5B"),
-  #("@", "%40"),
-  #("/", "%2F"),
-  #("\\", "%5C"),
+const percent_encode_examples = [
+  #("", ""),
+  #("%", "%25"),
+  #("%%", "%25%25"),
+  #(" \r\n\t\u{B}\f", "%20%0D%0A%09%0B%0C"),
+  #(
+    "-_.~0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
+    "-_.~0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ",
+  ),
+  #("\u{0}", "%00"),
+  #("abc\u{00}def", "abc%00def"),
   #("&", "%26"),
-  #("#", "%23"),
-  #("=", "%3D"),
-  #("~", "~"),
-  #("ñ", "%C3%B1"),
-  #("-", "-"),
-  #("_", "_"),
-  #(".", "."),
-  #("*", "*"),
-  #("+", "+"),
-  #("100% great+fun", "100%25%20great+fun"),
+  #(
+    "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
+    "%21%22%23%24%25%26%27%28%29%2A%2B%2C-.%2F%3A%3B%3C%3D%3E%3F%40%5B%5C%5D%5E_%60%7B%7C%7D~",
+  ),
+  #("“Aha”", "%E2%80%9CAha%E2%80%9D"),
+  #("\u{201C}Aha\u{201D}", "%E2%80%9CAha%E2%80%9D"),
+  #("*+,=>/", "%2A%2B%2C%3D%3E%2F"),
 ]
 
 pub fn percent_encode_tests() {
   describe("percent encoding", [
     it("encoding", fn() {
-      percent_codec_fixtures
+      percent_encode_examples
       |> list.map(fn(t) {
         let #(a, b) = t
         uri.percent_encode(a)
@@ -1185,7 +1179,7 @@ pub fn percent_encode_tests() {
       Nil
     }),
     it("decoding", fn() {
-      percent_codec_fixtures
+      percent_encode_examples
       |> list.map(fn(t) {
         let #(a, b) = t
         uri.percent_decode(b)