Merge pull request #121 from anweiss/120-group-type-choice-parsing-va…

…lidation-errors

Fix group and type choice parsing and validation errors

.github/workflows/ci.yml

@@ -26,7 +26,7 @@ jobs:
   minimum-version-check:
     strategy:
       matrix:
-        rust_toolchain: [1.56.0]
+        rust_toolchain: [1.56.1]
         os: [ubuntu-latest, macOS-latest, windows-latest]
     name: minimum version check using Rust ${{ matrix.rust_toolchain }} on ${{ matrix.os }}
     runs-on: ${{ matrix.os }}

README.md

@@ -8,7 +8,7 @@ A Rust implementation of the Concise data definition language (CDDL). CDDL is an
 
 This crate includes a handwritten parser and lexer for CDDL, and its development has been heavily inspired by the techniques outlined in Thorsten Ball's book ["Writing An Interpretor In Go"](https://interpreterbook.com/). The AST has been built to closely match the rules defined by the ABNF grammar in [Appendix B.](https://tools.ietf.org/html/rfc8610#appendix-B) of the spec. All CDDL must use UTF-8 for its encoding per the spec.
 
-This crate supports validation of both CBOR and JSON data structures. The minimum supported Rust version (MSRV) is 1.56.0.
+This crate supports validation of both CBOR and JSON data structures. The minimum supported Rust version (MSRV) is 1.56.1.
 
 Also bundled into this repository is a basic language server implementation and extension for Visual Studio Code for editing CDDL. The implementation is backed by the compiled WebAssembly target included in this crate.
 
@@ -36,7 +36,7 @@ Rust is a systems programming language designed around safety and is ideally-sui
 
 ## CLI
 
-A CLI is available for various platforms. The tool supports parsing of `.cddl` files for verifying conformance against RFC 8610. It can also be used to validate `.json` documents and `.cbor` binary files against `.cddl` documents. Detailed information about the JSON and CBOR validation implementation can be found in the sections below.
+A CLI is available for various platforms. The tool supports parsing of CDDL files for verifying conformance against RFC 8610. It can also be used to validate JSON documents and CBOR binary files against CDDL documents. Detailed information about the JSON and CBOR validation implementation can be found in the sections below.
 
 ### Installation
 
@@ -66,7 +66,7 @@ cddl help
 
 If using Docker:
 
-> Replace `<version>` with an appropriate [release](https://github.com/anweiss/cddl/releases) tag. Requires use of the `--volume` argument for mounting `.cddl` documents into the container when executing the command. `.json` or `.cbor` files can either be included in the volume mount or passed into the command via STDIN.
+> Replace `<version>` with an appropriate [release](https://github.com/anweiss/cddl/releases) tag. Requires use of the `--volume` argument for mounting CDDL documents into the container when executing the command. JSON or CBOR files can either be included in the volume mount or passed into the command via STDIN.
 
 ```sh
 docker run -it --rm -v $PWD:/cddl -w /cddl ghcr.io/anweiss/cddl-cli:<version> help

src/ast.rs

@@ -1833,6 +1833,16 @@ pub struct Group<'a> {
   pub span: Span,
 }
 
+impl<'a> From<GroupEntry<'a>> for Group<'a> {
+  fn from(ge: GroupEntry<'a>) -> Self {
+    Group {
+      group_choices: vec![GroupChoice::new(vec![ge])],
+      #[cfg(feature = "ast-span")]
+      span: Span::default(),
+    }
+  }
+}
+
 impl<'a> fmt::Display for Group<'a> {
   fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
     let mut group_str = String::new();

src/lexer.rs

@@ -1083,39 +1083,39 @@ mod tests {
     );
 
     let expected_tok = [
-      (COMMENT(" this is a comment".into()), "; this is a comment"),
+      (COMMENT(" this is a comment"), "; this is a comment"),
       (
-        COMMENT(" this is another comment".into()),
+        COMMENT(" this is another comment"),
         "; this is another comment",
       ),
       (NEWLINE, ""),
-      (IDENT("mynumber".into(), None), "mynumber"),
+      (IDENT("mynumber", None), "mynumber"),
       (ASSIGN, "="),
       (VALUE(Value::FLOAT(10.5)), "10.5"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mytag".into(), None), "mytag"),
+      (IDENT("mytag", None), "mytag"),
       (ASSIGN, "="),
       (TAG(Some(6), Some(1234)), "#6.1234"),
       (LPAREN, "("),
       (TSTR, "tstr"),
       (RPAREN, ")"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("myfirstrule".into(), None), "myfirstrule"),
+      (IDENT("myfirstrule", None), "myfirstrule"),
       (ASSIGN, "="),
       (VALUE(Value::TEXT("myotherrule".into())), "\"myotherrule\""),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mybytestring".into(), None), "mybytestring"),
+      (IDENT("mybytestring", None), "mybytestring"),
       (ASSIGN, "="),
       (
         VALUE(Value::BYTE(ByteValue::UTF8(b"hello there".as_ref().into()))),
         "'hello there'",
       ),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mybase16rule".into(), None), "mybase16rule"),
+      (IDENT("mybase16rule", None), "mybase16rule"),
       (ASSIGN, "="),
       (
         VALUE(Value::BYTE(ByteValue::B16(
@@ -1125,7 +1125,7 @@ mod tests {
       ),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mybase64rule".into(), None), "mybase64rule"),
+      (IDENT("mybase64rule", None), "mybase64rule"),
       (ASSIGN, "="),
       (
         VALUE(Value::BYTE(ByteValue::B64(
@@ -1135,66 +1135,66 @@ mod tests {
       ),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mysecondrule".into(), None), "mysecondrule"),
+      (IDENT("mysecondrule", None), "mysecondrule"),
       (ASSIGN, "="),
-      (IDENT("mynumber".into(), None), "mynumber"),
+      (IDENT("mynumber", None), "mynumber"),
       (RANGEOP(true), ".."),
       (VALUE(Value::FLOAT(100.5)), "100.5"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("myintrule".into(), None), "myintrule"),
+      (IDENT("myintrule", None), "myintrule"),
       (ASSIGN, "="),
       (VALUE(Value::INT(-10)), "-10"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mysignedfloat".into(), None), "mysignedfloat"),
+      (IDENT("mysignedfloat", None), "mysignedfloat"),
       (ASSIGN, "="),
       (VALUE(Value::FLOAT(-10.5)), "-10.5"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("myintrange".into(), None), "myintrange"),
+      (IDENT("myintrange", None), "myintrange"),
       (ASSIGN, "="),
       (VALUE(Value::INT(-10)), "-10"),
       (RANGEOP(true), ".."),
       (VALUE(Value::UINT(10)), "10"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("mycontrol".into(), None), "mycontrol"),
+      (IDENT("mycontrol", None), "mycontrol"),
       (ASSIGN, "="),
-      (IDENT("mynumber".into(), None), "mynumber"),
+      (IDENT("mynumber", None), "mynumber"),
       (GT, ".gt"),
       (VALUE(Value::UINT(0)), "0"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("@terminal-color".into(), None), "@terminal-color"),
+      (IDENT("@terminal-color", None), "@terminal-color"),
       (ASSIGN, "="),
-      (IDENT("basecolors".into(), None), "basecolors"),
+      (IDENT("basecolors", None), "basecolors"),
       (TCHOICE, "/"),
-      (IDENT("othercolors".into(), None), "othercolors"),
-      (COMMENT(" an inline comment".into()), "; an inline comment"),
+      (IDENT("othercolors", None), "othercolors"),
+      (COMMENT(" an inline comment"), "; an inline comment"),
       (NEWLINE, ""),
-      (IDENT("messages".into(), None), "messages"),
+      (IDENT("messages", None), "messages"),
       (ASSIGN, "="),
-      (IDENT("message".into(), None), "message"),
+      (IDENT("message", None), "message"),
       (LANGLEBRACKET, "<"),
       (VALUE(Value::TEXT("reboot".into())), "\"reboot\""),
       (COMMA, ","),
       (VALUE(Value::TEXT("now".into())), "\"now\""),
       (RANGLEBRACKET, ">"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("address".into(), None), "address"),
+      (IDENT("address", None), "address"),
       (ASSIGN, "="),
       (LBRACE, "{"),
-      (IDENT("delivery".into(), None), "delivery"),
+      (IDENT("delivery", None), "delivery"),
       (RBRACE, "}"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("delivery".into(), None), "delivery"),
+      (IDENT("delivery", None), "delivery"),
       (ASSIGN, "="),
       (LPAREN, "("),
       (NEWLINE, ""),
-      (IDENT("street".into(), None), "street"),
+      (IDENT("street", None), "street"),
       (COLON, ":"),
       (TSTR, "tstr"),
       (COMMA, ","),
@@ -1204,46 +1204,43 @@ mod tests {
       (ARROWMAP, "=>"),
       (UINT, "uint"),
       (COMMA, ","),
-      (IDENT("city".into(), None), "city"),
+      (IDENT("city", None), "city"),
       (GCHOICE, "//"),
       (NEWLINE, ""),
-      (IDENT("po-box".into(), None), "po-box"),
+      (IDENT("po-box", None), "po-box"),
       (COLON, ":"),
       (UINT, "uint"),
       (COMMA, ","),
-      (IDENT("city".into(), None), "city"),
+      (IDENT("city", None), "city"),
       (GCHOICE, "//"),
       (NEWLINE, ""),
-      (IDENT("per-pickup".into(), None), "per-pickup"),
+      (IDENT("per-pickup", None), "per-pickup"),
       (COLON, ":"),
       (TRUE, "true"),
       (NEWLINE, ""),
       (RPAREN, ")"),
       (NEWLINE, ""),
       (NEWLINE, ""),
-      (IDENT("city".into(), None), "city"),
+      (IDENT("city", None), "city"),
       (ASSIGN, "="),
       (LPAREN, "("),
       (NEWLINE, ""),
-      (IDENT("name".into(), None), "name"),
+      (IDENT("name", None), "name"),
       (COLON, ":"),
       (TSTR, "tstr"),
       (NEWLINE, ""),
-      (IDENT("zip-code".into(), None), "zip-code"),
+      (IDENT("zip-code", None), "zip-code"),
       (COLON, ":"),
       (UINT, "uint"),
       (NEWLINE, ""),
       (VALUE(Value::UINT(1)), "1"),
       (ASTERISK, "*"),
       (VALUE(Value::UINT(3)), "3"),
-      (
-        IDENT("tcp-option".into(), Some(SocketPlug::GROUP)),
-        "$$tcp-option",
-      ),
+      (IDENT("tcp-option", Some(SocketPlug::GROUP)), "$$tcp-option"),
       (COMMA, ","),
       (NEWLINE, ""),
       (RPAREN, ")"),
-      (COMMENT(" test".into()), "; test"),
+      (COMMENT(" test"), "; test"),
     ];
 
     let mut l = Lexer::new(input);

src/lib.rs

@@ -30,7 +30,7 @@
 //!
 //! This crate supports validation of both CBOR and JSON data structures. An
 //! extremely basic REPL is included as well. This crate's minimum supported
-//! Rust version (MSRV) is 1.56.0.
+//! Rust version (MSRV) is 1.56.1.
 //!
 //! Also bundled into this repository is a basic language server implementation
 //! and extension for Visual Studio Code for editing CDDL. The implementation is
@@ -66,11 +66,11 @@
 //!
 //! ## CLI
 //!
-//! A CLI is available for various platforms. The tool supports parsing of
-//! `.cddl` files for verifying conformance against RFC 8610. It can also be
-//! used to validate `.json` documents and `.cbor` binary files against `.cddl`
-//! documents. Detailed information about the JSON and CBOR validation
-//! implementation can be found in the sections below.
+//! A CLI is available for various platforms. The tool supports parsing of CDDL
+//! files for verifying conformance against RFC 8610. It can also be used to
+//! validate JSON documents and CBOR binary files against CDDL documents.
+//! Detailed information about the JSON and CBOR validation implementation can
+//! be found in the sections below.
 //!
 //! ### Installation
 //!
@@ -105,8 +105,8 @@
 //! > Replace `<version>` with an appropriate
 //! > [release](https://github.com/anweiss/cddl/releases) tag. Requires use of
 //! > the `--volume` argument for mounting `.cddl` documents into the container
-//! > when executing the command. `.json` or `.cbor` files can either be
-//! > included in the volume mount or passed into the command via STDIN.
+//! > when executing the command. JSON or CBOR files can either be included in
+//! > the volume mount or passed into the command via STDIN.
 //!
 //! ```sh
 //! docker run -it --rm -v $PWD:/cddl -w /cddl ghcr.io/anweiss/cddl-cli:<version> help

src/parser.rs

@@ -349,6 +349,7 @@ impl<'a> Parser<'a> {
         Ok(r) => {
           let rule_exists =
             |existing_rule: &Rule| r.name() == existing_rule.name() && !r.is_choice_alternate();
+
           if c.rules.iter().any(rule_exists) {
             #[cfg(feature = "ast-span")]
             {
@@ -558,6 +559,45 @@ impl<'a> Parser<'a> {
     #[cfg(not(feature = "ast-comments"))]
     self.advance_newline()?;
 
+    // If token is group socket or rule is a group plug alternative, parse
+    // as group rule
+    if matches!(self.cur_token, Token::IDENT(_, Some(SocketPlug::GROUP)))
+      || is_group_choice_alternate
+    {
+      let ge = self.parse_grpent(true)?;
+
+      #[cfg(feature = "ast-comments")]
+      let comments_after_rule = self.collect_comments()?;
+      #[cfg(not(feature = "ast-comments"))]
+      self.advance_newline()?;
+
+      #[cfg(feature = "ast-span")]
+      let span = (
+        begin_rule_range,
+        self.parser_position.range.1,
+        begin_rule_line,
+      );
+
+      self.current_rule_generic_param_idents = None;
+
+      return Ok(Rule::Group {
+        rule: Box::from(GroupRule {
+          name: ident,
+          generic_params: gp,
+          is_group_choice_alternate,
+          entry: ge,
+          #[cfg(feature = "ast-comments")]
+          comments_before_assigng: comments_before_assign,
+          #[cfg(feature = "ast-comments")]
+          comments_after_assigng: comments_after_assign,
+        }),
+        #[cfg(feature = "ast-comments")]
+        comments_after_rule,
+        #[cfg(feature = "ast-span")]
+        span,
+      });
+    }
+
     match self.cur_token {
       // Check for an occurrence indicator of uint followed by an asterisk '*'
       Token::VALUE(token::Value::UINT(_)) => {
@@ -744,6 +784,7 @@ impl<'a> Parser<'a> {
       _ => {
         // If type rule is an unwrap type, advance token after parsing type
         let advance_token = matches!(self.cur_token, Token::UNWRAP);
+
         #[cfg(feature = "ast-comments")]
         let mut t = self.parse_type(None)?;
         #[cfg(not(feature = "ast-comments"))]