Merge dev

fix #14

CHANGES.md

@@ -1,3 +1,8 @@
+## v0.7.0 - 2024=07-03
+- support for EBNF output ([#14](https://github.com/Lelio-Brun/Obelisk/issues/14)) 
+- rewriting of the printers
+- switch to Github Actions for CI
+
 ## v0.6.0 - 2021-02-09
 This version adds support for the Menhir standard rules `endrule`, `midrule`, `rev`, `flatten` and `append`.
 

Makefile

@@ -7,7 +7,7 @@ PREFIX=my
 MAIN=main
 EXE=dune exec $(SRC)/main.exe --
 
-.PHONY: all latex htmlcss html default reco readme tests clean
+.PHONY: all latex htmlcss html default ebnf reco readme tests clean
 
 all:
 	@dune build
@@ -16,7 +16,7 @@ all:
 	@$(EXE) latex -prefix $(PREFIX) -$* $(PARSER) -o $@
 
 %.pdf: %.tex
-	@pdflatex -interaction batchmode $<
+	pdflatex -interaction batchmode $<
 
 %.png: %.pdf
 	@convert -quiet -density 150 $< -format png $(MISC)/$@
@@ -38,13 +38,21 @@ default:
 	@printf "\nDefault output on $(PARSER):\n"
 	@$(EXE) $(PARSER)
 
+ebnf:
+	@printf "\nEBNF output on $(PARSER):\n"
+	@$(EXE) ebnf $(PARSER)
+
 reco:
 	@printf "Default output on $(RECO):\n"
 	@$(EXE) $(RECO)
 	@printf "Default output on $(RECO) with '-i' switch:\n"
 	@$(EXE) -i $(RECO)
+	@printf "EBNF output on $(RECO):\n"
+	@$(EXE) ebnf $(RECO)
+	@printf "EBNF output on $(RECO) with '-i' switch:\n"
+	@$(EXE) ebnf -i $(RECO)
 
-readme: latex htmlcss html default reco
+readme: latex htmlcss html default ebnf reco
 
 tests:
 	@dune test

README.md

@@ -1,5 +1,10 @@
+<<<<<<< HEAD
 # Obelisk ![Build Status](https://github.com/Lelio-Brun/Obelisk/actions/workflows/main.yml/badge.svg?branch=master) [![Mentioned in Awesome OCaml](https://awesome.re/mentioned-badge.svg)](https://github.com/rizo/awesome-ocaml)
 **Obelisk** is a simple tool that produces pretty-printed output from a [Menhir] parser file (_.mly_).
+=======
+# Obelisk [![Mentioned in Awesome OCaml](https://awesome.re/mentioned-badge.svg)](https://github.com/rizo/awesome-ocaml) ![workflow badge](https://github.com/Lelio-Brun/Obelisk/actions/workflows/workflow.yml/badge.svg?branch=dev)
+**Obelisk** is a simple tool which produces pretty-printed output from a [Menhir] parser file (_.mly_).
+>>>>>>> origin/dev
 
 It is inspired from [yacc2latex] and is also written in [OCaml], but is aimed at supporting features from Menhir instead of only those of [ocamlyacc].
 
@@ -11,10 +16,12 @@ It is inspired from [yacc2latex] and is also written in [OCaml], but is aimed at
 * [Usage](#usage)
   + [Pattern recognition](#pattern-recognition)
   + [Multi-format output](#multi-format-output)
+    - [EBNF](#ebnf)
     - [LaTeX](#latex)
     - [HTML](#html)
   + [Example](#example)
     - [Default](#default)
+    - [EBNF](#ebnf-1)
     - [LaTeX](#latex-1)
       * [Tabular](#tabular)
       * [Syntax](#syntax)
@@ -61,7 +68,7 @@ dune install [--prefix <the destination directory>]
 
 ## Usage
 ```
-obelisk [latex|html] [options] <files>
+obelisk [ebnf|latex|html] [options] <files>
 ```
 
 If multiple files are specified, **Obelisk** will output a concatenated result without consistency checks. 
@@ -100,14 +107,14 @@ my_separated_list(X,S):
   |                                 {}
   | my_separated_nonempty_list(X,S) {}
 
-my_rule(E,F,S1,S2):
+my_rule:
   | my_option(E, F)                    {}
   | my_list(E)                         {}
   | my_nonempty_list(F)                {}
   | my_separated_nonempty_list(E,S1)   {}
   | my_separated_list(F,S2)            {}
 ```
-**Obelisk** outputs:
+**Obelisk** (`obelisk misc/reco.mly`) outputs:
 ```
 <my_option(X, Y)> ::= [Y X]
 
@@ -119,26 +126,66 @@ my_rule(E,F,S1,S2):
 
 <my_separated_list(X, S)> ::= [X (S X)*]
 
-<my_rule(E, F, S1, S2)> ::= <my_option(E, F)>
-                          | <my_list(E)>
-                          | <my_nonempty_list(F)>
-                          | <my_separated_nonempty_list(E, S1)>
-                          | <my_separated_list(F, S2)>
+<my_rule> ::= <my_option(E, F)>
+            | <my_list(E)>
+            | <my_nonempty_list(F)>
+            | <my_separated_nonempty_list(E, S1)>
+            | <my_separated_list(F, S2)>
 ```
-And with the `-i` switch:
+And with the `-i` switch (`obelisk -i misc/reco.mly`):
 ```
-<my_rule(E, F, S1, S2)> ::= [F E]
-                          | E*
-                          | F+
-                          | E (S1 E)*
-                          | [F (S2 F)*]
+<my_rule> ::= [F E]  
+            | E*
+            | F+
+            | E (S1 E)*
+            | [F (S2 F)*]
 ```
 
 ### Multi-format output
+<<<<<<< HEAD
 By default, the output format is a simple text format that is close to the BNF syntax.
 You can use the subcommands `latex` or `html` to get a LaTeX (resp. HTML) file.
 
 In default and HTML mode, the option `-noaliases` avoids printing token aliases in the output.
+=======
+By default the output format is a simple text format close to the BNF syntax.
+You can use the subcommands `ebnf`, `latex` or `html` to get respectively an EBNF text output,  LaTeX output or HTML output.
+
+In default, EBNF and HTML mode, the option `-noaliases` avoid printing token aliases in the output.
+
+#### EBNF 
+In EBNF mode, parameterized rules are specialized into dedicated regular rules. 
+On the example above (`obelisk ebnf misc/reco.mly`):
+
+```
+my_rule ::= my_option_0
+          | my_list_0
+          | my_nonempty_list_0
+          | my_separated_nonempty_list_0
+          | my_separated_list_0
+
+my_option_0 ::= (F E)?
+
+my_nonempty_list_0 ::= F+
+
+my_separated_nonempty_list_1 ::= F (S2 F)*
+
+my_separated_list_0 ::= (F (S2 F)*)?
+
+my_separated_nonempty_list_0 ::= E (S1 E)*
+
+my_list_0 ::= E*
+```
+And with the `-i` switch (`obelisk ebnf -i misc/reco.mly`):
+
+```
+my_rule ::= (F E)?   
+          | E*
+          | F+
+          | E (S1 E)*
+          | (F (S2 F)*)?
+```
+>>>>>>> origin/dev
 
 #### LaTeX
 Use the following options to tweak the LaTeX:
@@ -252,6 +299,81 @@ Here are the outputs of the different formats obtained by **Obelisk** from its o
           | QID
 ```
 
+#### EBNF 
+
+```
+specification ::= rule* EOF
+
+rule ::= old_rule
+       | new_rule
+
+old_rule ::= flags? ident ATTRIBUTE* parameters_0 COLON optional_bar group
+             (BAR group)* SEMICOLON*
+
+flags ::= PUBLIC
+        | INLINE
+        | PUBLIC INLINE
+        | INLINE PUBLIC
+
+optional_bar ::= BAR?
+
+group ::= production (BAR production)* ACTION precedence?
+
+production ::= producer* precedence?
+
+producer ::= (LID EQ)? actual ATTRIBUTE* SEMICOLON*
+
+actual ::= generic_actual_0
+
+lax_actual ::= generic_actual_0
+             | group (BAR group)*
+
+new_rule ::= PUBLIC? LET LID ATTRIBUTE* parameters_0 binder expression
+
+binder ::= COLONEQ
+         | EQEQ
+
+expression ::= optional_bar seq_expression (BAR seq_expression)*
+
+seq_expression ::= (pattern EQ)? symbol_expression SEMICOLON seq_expression
+                 | symbol_expression
+                 | action_expression
+
+symbol_expression ::= ident parameters_2
+                    | symbol_expression modifier
+
+action_expression ::= action
+                    | action precedence
+                    | precedence action
+
+action ::= ACTION
+         | POINTFREEACTION
+
+pattern ::= LID
+          | UNDERSCORE
+          | TILDE
+          | LPAR (pattern (COMMA pattern)*)? RPAR
+
+modifier ::= OPT
+           | PLUS
+           | STAR
+
+precedence ::= PREC ident
+
+ident ::= UID
+        | LID
+        | QID
+
+generic_actual_0 ::= ident parameters_1
+                   | actual modifier
+
+parameters_1 ::= (LPAR (lax_actual (COMMA lax_actual)*)? RPAR)?
+
+parameters_0 ::= (LPAR (ident (COMMA ident)*)? RPAR)?
+
+parameters_2 ::= (LPAR (expression (COMMA expression)*)? RPAR)?
+```
+
 #### LaTeX
 ##### Tabular
 ![Tabular](misc/tabular.png)

dune-project

@@ -1,7 +1,7 @@
 (lang dune 2.0)
 
 (name obelisk)
-(version 0.6.0)
+(version 0.7.0)
 
 (using menhir 2.0)
 (generate_opam_files true)
@@ -11,7 +11,7 @@
 (documentation https://github.com/Lelio-Brun/Obelisk/blob/master/README.md)
 (license MIT)
 (authors "Lélio Brun")
-(maintainers "Lélio Brun <lelio.brun@inria.fr>")
+(maintainers "Lélio Brun <lb@leliobrun.net>")
 
 (package
  (name obelisk)

misc/reco.mly

@@ -19,7 +19,7 @@ my_separated_list(X,S):
   |                                 {}
   | my_separated_nonempty_list(X,S) {}
 
-my_rule(E,F,S1,S2):
+my_rule:
   | my_option(E, F)                    {}
   | my_list(E)                         {}
   | my_nonempty_list(F)                {}

obelisk.opam

@@ -1,11 +1,11 @@
 # This file is generated by dune, edit dune-project instead
 opam-version: "2.0"
-version: "0.6.0"
+version: "0.7.0"
 synopsis: "Pretty-printing for Menhir files"
 description: """
 Obelisk is a simple tool which produces pretty-printed output from a Menhir parser file (.mly).
 It is inspired from yacc2latex and is also written in OCaml, but is aimed at supporting features from Menhir instead of only those of ocamlyacc."""
-maintainer: ["Lélio Brun <lelio.brun@inria.fr>"]
+maintainer: ["Lélio Brun <lb@leliobrun.net>"]
 authors: ["Lélio Brun"]
 license: "MIT"
 homepage: "https://github.com/Lelio-Brun/Obelisk"

src/common.ml

@@ -1,5 +1,10 @@
 (** Some common facilities.  *)
 
+(** Find a rule by its left-hand side (name) in the grammar. *)
+let find_rule r rules =
+  let open ExtendedAst in
+  List.find_opt (fun { name; _ } -> name = r) rules
+
 (** The signature for the set of symbols appearing in a grammar. *)
 module type SYMBOLS = sig
   (** The set of symbols. *)
@@ -41,6 +46,9 @@ module type SYMBOLS = sig
       See {!defined}. *)
   val is_defined: string -> t -> string list option
 
+  (** Test if the given symbol actually appears as a symbol. *)
+  val is_symbol: string -> t -> bool
+
 end
 
 (** The actual implementation for the set of symbols, see {!SYMBOLS}.  *)
@@ -116,4 +124,8 @@ module Symbols : SYMBOLS = struct
     end
     with Not_found -> None
 
+  (** See {!SYMBOLS.is_symbol}. *)
+  let is_symbol x m =
+    M.mem x m
+
 end

src/dune

@@ -2,7 +2,7 @@
   (name main)
   (public_name obelisk)
   (package obelisk)
-  (modules_without_implementation ast extendedAst helper printer)
+  (modules_without_implementation ast helper printer)
   (libraries re))
 
 (include_subdirs unqualified)

src/extendedAst.mli → src/extendedAst.ml

@@ -42,3 +42,46 @@ and pattern =
   | NEList of actual                      (** [nonempty_list(x)] *)
   | SepList of actual * actual            (** [separated_list(x)] *)
   | SepNEList of actual * actual          (** [separated_nonempty_list(sep, x)] *)
+
+let fold_map_pattern f acc = function
+  | Option x ->
+    let acc, x = f acc x in
+    acc, Option x
+  | Pair (x, y) ->
+    let acc, x = f acc x in
+    let acc, y = f acc y in
+    acc, Pair (x, y)
+  | SepPair (x, sep, y) ->
+    let acc, x = f acc x in
+    let acc, sep = f acc sep in
+    let acc, y = f acc y in
+    acc, SepPair (x, sep, y)
+  | Preceded (o, x) ->
+    let acc, o = f acc o in
+    let acc, x = f acc x in
+    acc, Preceded (o, x)
+  | Terminated (x, c) ->
+    let acc, x = f acc x in
+    let acc, c = f acc c in
+    acc, Terminated (x, c)
+  | Delimited (o, x, c) ->
+    let acc, o = f acc o in
+    let acc, x = f acc x in
+    let acc, c = f acc c in
+    acc, Delimited (o, x, c)
+  | List x ->
+    let acc, x = f acc x in
+    acc, List x
+  | NEList x ->
+    let acc, x = f acc x in
+    acc, NEList x
+  | SepList (sep, x) ->
+    let acc, sep = f acc sep in
+    let acc, x = f acc x in
+    acc, SepList (sep, x)
+  | SepNEList (sep, x) ->
+    let acc, sep = f acc sep in
+    let acc, x = f acc x in
+    acc, SepNEList (sep, x)
+
+let map_pattern f p = fold_map_pattern (fun o p -> o, f p) None p |> snd