Add full UTF-8 support in RON incl. unicode identifiers

.github/workflows/ci.yaml

@@ -36,23 +36,24 @@ jobs:
       - run: cargo test --all-features
 
   clippy:
-    name: "Clippy: stable"
+    name: "Clippy: MSRV"
     runs-on: ubuntu-latest
     continue-on-error: true
     steps:
       - uses: actions/checkout@v3
       - uses: ./.github/actions/setup
         with:
-          key: clippy-stable
+          key: clippy-msrv
       - uses: actions-rs/toolchain@v1
         with:
-          toolchain: stable
+          toolchain: 1.64.0
           profile: minimal
           components: clippy
           override: true
-      - uses: actions-rs/clippy-check@v1
-        with:
-          token: ${{ github.token }}
+      - run: cargo clippy -- -D warnings
+      - run: cargo clippy --features integer128 -- -D warnings
+      - run: cargo clippy --features indexmap -- -D warnings
+      - run: cargo clippy --all-features -- -D warnings
 
   rustfmt:
     name: "Format: stable"

Cargo.toml

@@ -31,6 +31,7 @@ indexmap = { version = "2.0", features = ["serde"], optional = true }
 # serde supports i128/u128 from 1.0.60 onwards
 serde = "1.0.60"
 serde_derive = "1.0"
+unicode-ident = "1.0.8"
 
 [dev-dependencies]
 serde = { version = "1.0", features = ["derive"] }

docs/grammar.md

@@ -17,7 +17,7 @@ RON = [extensions], ws, value, ws;
 
 ```ebnf
 ws = { ws_single | comment };
-ws_single = "\n" | "\t" | "\r" | " ";
+ws_single = "\n" | "\t" | "\r" | " " | U+000B | U+000C | U+0085 | U+200E | U+200F | U+2028 | U+2029;
 comment = ["//", { no_newline }, "\n"] | ["/*", nested_block_comment, "*/"];
 nested_block_comment = { ? any characters except "/*" or "*/" ? }, [ "/*", nested_block_comment, "*/", nested_block_comment ];
 ```
@@ -179,8 +179,10 @@ enum_variant_named = ident, ws, "(", [named_field, { comma, named_field }, [comm
 ```ebnf
 ident = ident_std | ident_raw;
 ident_std = ident_std_first, { ident_std_rest };
-ident_std_first = "A" | ... | "Z" | "a" | ... | "z" | "_";
-ident_std_rest = ident_std_first | digit;
+ident_std_first = XID_Start | "_";
+ident_std_rest = XID_Continue;
 ident_raw = "r", "#", ident_raw_rest, { ident_raw_rest };
 ident_raw_rest = ident_std_rest | "." | "+" | "-";
 ```
+
+> Note: [XID_Start](http://unicode.org/cldr/utility/list-unicodeset.jsp?a=%5B%3AXID_Start%3A%5D&abb=on&g=&i=) and [XID_Continue](http://unicode.org/cldr/utility/list-unicodeset.jsp?a=%5B%3AXID_Continue%3A%5D&abb=on&g=&i=) refer to Unicode character sets.

src/de/id.rs

@@ -21,11 +21,11 @@ impl<'a, 'b: 'a, 'c> de::Deserializer<'b> for &'c mut IdDeserializer<'a, 'b> {
         V: Visitor<'b>,
     {
         if self.map_as_struct {
-            self.d.bytes.expect_byte(b'"', Error::ExpectedString)?;
+            self.d.parser.expect_char('"', Error::ExpectedString)?;
         }
         let result = self.d.deserialize_identifier(visitor);
         if self.map_as_struct {
-            self.d.bytes.expect_byte(b'"', Error::ExpectedStringEnd)?;
+            self.d.parser.expect_char('"', Error::ExpectedStringEnd)?;
         }
         result
     }