add multiline comments; ignore commas

brag/brag.scrbl

@@ -665,7 +665,7 @@ generates.
 @subsection[#:tag "brag-syntax"]{Syntax and terminology}
 A program in the @tt{brag} language consists of the language line
 @litchar{#lang brag}, followed by a collection of @tech{rule}s and
-@tech{line comment}s.
+possibly @tech{comment}s.
 
 A @deftech{rule} is a sequence consisting of: a @tech{rule identifier}, a separator (either @litchar{":"} or @litchar{"::="}), and a @tech{pattern}.
 
@@ -676,14 +676,15 @@ A @deftech{symbolic token identifier} is an @tech{identifier} that is in upper c
 A @deftech{line comment} begins with either @litchar{#} or @litchar{;} and
 continues till the end of the line.
 
+A @deftech{multiline comment} begins with @litchar{(*} and ends with @litchar{*)}.
+
 An @deftech{identifier} is a sequence of letters, numbers, or
 characters in the set @racket["-.!$%&/<=>?^_~@"]. It must not contain
 @litchar{*}, @litchar{+}, or @litchar|{{}| and @litchar|{}}|, as those characters are used to denote quantification.
 
-
 A @deftech{pattern} is one of the following:
 @itemize[
- @item{an implicit sequence of @tech{pattern}s separated by whitespace.}
+ @item{an implicit sequence of @tech{pattern}s separated by whitespace or commas.}
 
  @item{a @deftech{terminal}: either a literal string or a @tech{symbolic token identifier}. 
 

brag/codegen/expander.rkt

@@ -25,7 +25,7 @@
   (syntax-case rules-stx ()
     [(_) (raise-syntax-error 'brag
                              (format "The grammar does not appear to have any rules")
-                             'brag-module)]
+                             (syntax-source rules-stx))]
     [(_ . RULES)
      (let ([rules (syntax->list #'RULES)]) ;; (listof stx)
        

brag/private/colorer.rkt

@@ -12,7 +12,8 @@
          (from/to "'" "'")
          (from/to "\"" "\"")) (token 'LIT lexeme)]
    [(:or "()" "Ø" "∅") (token 'NO-COLOR lexeme)] ; empty set symbols
-   [(:or (char-set "()[]{}|+*:?") hide-char splice-char) (token 'MISC lexeme)]
+   [(:or (char-set "()[]{}|+*:?") hide-char splice-char "::=") (token 'MISC lexeme)]
+   [(from/to "(*" "*)") (token 'COMMENT lexeme)]
    [(:seq (:or "#" ";") (complement (:seq (:* any-char) NL (:* any-char))) (:or NL "")) (token 'COMMENT lexeme)]
    [id (token 'ID lexeme)]
    [any-char (token 'OTHER lexeme)]))

brag/rules/lexer.rkt

@@ -4,6 +4,7 @@
          (prefix-in : br-parser-tools/lex-sre)
          "parser.rkt"
          "rule-structs.rkt"
+         (only-in brag/support from/to)
          racket/string)
 
 (provide lex/1 tokenize)
@@ -74,14 +75,18 @@
    [(:or "+" "*" "?"
          (:: "{" (:* digit) (:? (:: "," (:* digit))) "}"))
     (token-REPEAT lexeme)]
+   ;; Skip whitespace
    [whitespace
-    ;; Skip whitespace
     (return-without-pos (lex/1 input-port))]
+   ;; skip multiline comments
+   [(from/to "(*" "*)") (return-without-pos (lex/1 input-port))]
    ;; Skip comments up to end of line
    [(:: (:or "#" ";")
         (complement (:: (:* any-char) NL (:* any-char)))
         (:or NL ""))
     (return-without-pos (lex/1 input-port))]
+   ;; skip commas (concatenation is implied)
+   ["," (return-without-pos (lex/1 input-port))]
    [(eof)
     (token-EOF lexeme)]
    [(:: id (:* whitespace) id-separator)