Makefile.menhir

#**************************************************************************
#*                                                                        *
#*                                 OCaml                                  *
#*                                                                        *
#*            Gabriel Scherer, projet Parsifal, INRIA Saclay              *
#*                                                                        *
#*   Copyright 2018 Institut National de Recherche en Informatique et     *
#*     en Automatique.                                                    *
#*                                                                        *
#*   All rights reserved.  This file is distributed under the terms of    *
#*   the GNU Lesser General Public License version 2.1, with the          *
#*   special exception on linking described in the file LICENSE.          *
#*                                                                        *
#**************************************************************************

# The rules in this Makefile use Menhir to rebuild the OCaml compiler
# parser. They are included in the main Makefile, so should be invoked
# directly, for example 'make promote-menhir'. They must be called
# after any modification to parsing/parser.mly, for the modification
# to affect the parser linked in the produced compiler:
#
# - promote-menhir builds the parser from parser.mly and stores it in
#   the boot/ directory, so that future builds of the compiler use the
#   updated result. Use it to make permanent changes to the compiler
#   parser.
#
# - demote-menhir undoes the effect of promote-menhir. The files in
#   the boot/ directory that are affected by promote-menhir and are
#   under version control are restored to their normal state (HEAD).
#
# - test-menhir builds the parser from parser.mly without storing it
#   in the boot/ directory, and only checks that the generated parser
#   builds correctly. Use it to quickly check if a parser.mly change
#   breaks the build. If you want to test a compiler produced with
#   the new parser, you must use promote-menhir instead.
#   (Using this rule requires a partial compiler build as obtained
#    by 'make core' or 'make world'.)
#
# - clean-menhir removes the files generated by Menhir from parsing/,
#   keeping only the reference sources for the grammar.
#
# - depend-menhir updates the dependency information for the
#   Menhir-generated parser, which is versioned in the OCaml repository
#   like all other .depend files. It should be used when the dependencies
#   (of the OCaml code in the grammar semantic actions) change.

MENHIR ?= menhir

## Unused tokens

# The tokens COMMENT, DOCSTRING and EOL are produced by special lexer
# modes used by other consumers than the parser.

# GREATERBRACKET ">]" was added by the parser by symmetry with "[<"
# (which is used in polymorphic variant), but is not currently used by
# the grammar.

unused_tokens := COMMENT DOCSTRING EOL GREATERRBRACKET

## Menhir's flags.

# The basic flags influence the analysis of the grammar and the construction
# of the automaton. The complete set of flags includes extra flags that
# influence type inference and code production.

MENHIRBASICFLAGS := \
  --lalr \
  --explain \
  --dump \
  --require-aliases \
  --strict \
  -lg 1 \
  -la 1 \
  $(addprefix --unused-token ,$(unused_tokens)) \

MENHIRFLAGS := \
  $(MENHIRBASICFLAGS) \
  --infer \
  --ocamlc "$(CAMLC) $(OC_COMMON_COMPFLAGS) $(INCLUDES)" \
  --fixed-exception \
  --table \
  --strategy simplified \

## promote-menhir

.PHONY: promote-menhir
promote-menhir: parsing/parser.mly
	@ $(MAKE) import-menhirLib
	$(MENHIR) $(MENHIRFLAGS) parsing/parser.mly
# The generated parser.ml may contain lexer directives containing
# the absolute path to Menhir's standard library on the promoter's machine.
# This is benign but will generate pointless churn if another developer
# rebuilds the same grammar (from the same Menhir version).
	@ for f in $(addprefix parser.,ml mli) ; do \
	  sed \
	    's,^#\(.*\)"[^"]*/menhir/standard.mly",#\1"menhir/standard.mly",g' \
	    parsing/$$f \
	    > boot/menhir/$$f; \
	  rm parsing/$$f; \
	done

# The import-menhirLib invocation in promote-menhir ensures that each
# update of the boot/ parser is paired with an update of the imported
# menhirLib; otherwise it would be easy to generate a parser and keep
# an incompatible version of menhirLib, which would fail at
# compile-time.

.PHONY: import-menhirLib
import-menhirLib:
	@ mkdir -p boot/menhir
	@ cp \
           $(addprefix `$(MENHIR) --suggest-menhirLib`/menhirLib.,ml mli) \
           boot/menhir


## demote-menhir

DEMOTE:=menhirLib.ml menhirLib.mli parser.ml parser.mli

.PHONY: demote-menhir
demote-menhir:
	git checkout HEAD -- $(addprefix boot/menhir/,$(DEMOTE))

## test-menhir

# This rule assumes that the `parsing/` sources and its dependencies
# have already been compiled; 'make core' suffices to be in that
# state. We don't make 'core' an explicit dependency, as building
# 'test-menhir' repeatedly would rebuild the compiler each time
# (parser.ml has changed), without actually taking the changes from
# parser.mly into account ('core' uses the parser from boot/).

# The test-menhir target does not read or write the boot directory,
# it directly builds the parser in parsing/. In particular, it must
# duplicate the MenhirLib->CamlinternalMenhirlib renaming usually
# performed by the parsing/parser.ml import rule in the main
# Makefile.
.PHONY: test-menhir
test-menhir: parsing/parser.mly
	$(MENHIR) $(MENHIRFLAGS) parsing/parser.mly
	for f in $(addprefix parsing/parser.,ml mli) ; do \
	  cat $$f | sed "s/MenhirLib/CamlinternalMenhirLib/g" > $$f.tmp && \
	  mv $$f.tmp $$f ; \
	done
	$(MAKE) parsing/parser.cmo


## clean-menhir

partialclean-menhir::
	rm -f \
	  $(addprefix parsing/parser.,ml mli) \
	  $(addprefix parsing/camlinternalMenhirLib.,ml mli) \
	  $(addprefix parsing/parser.,automaton conflicts) \
	  $(addprefix parsing/parser.,auto.messages) \

clean-menhir: partialclean-menhir


## depend-menhir

# The following rule depends on the OCAMLDEP_CMD variable defined in
# Makefile.common, so it can only be invoked from the main (root) Makefile

.PHONY: depend-menhir
depend-menhir:
	$(MENHIR) --depend --ocamldep "$(OCAMLDEP_CMD)" \
	  parsing/parser.mly > .depend.menhir

include .depend.menhir

## interpret-menhir

# This rule runs Menhir in interactive mode.
# The user can enter sentences, such as:
#   implementation: TYPE LIDENT EQUAL LIDENT EOF
# and see how Menhir interprets them.

interpret-menhir:
	@ echo "Please wait, I am building the LALR automaton..."
	@ $(MENHIR) $(MENHIRBASICFLAGS) parsing/parser.mly \
	    --interpret \
	    --interpret-show-cst \
	    --trace \

## list-parse-errors

# This rule runs Menhir's reachability analysis, which produces a list of all
# states where a syntax error can be detected (and a corresponding list of of
# erroneous sentences). This data is stored in parsing/parser.auto.messages.
# This analysis requires about 3 minutes and 6GB of RAM.

# The analysis is performed on a copy of the grammar where every block
# of text comprised between the markers BEGIN AVOID and END AVOID has
# been removed. This allows us to avoid certain syntactic forms in the
# sentences that we produce. See parser.mly for more explanations.

# Because of this, we must run Menhir twice: once on a modified copy of the
# grammar to produce the sentences, and once on the original grammar to update
# the auto-comments (which would otherwise be incorrect).

.PHONY: list-parse-errors
list-parse-errors:
	@ tmp=`mktemp -d /tmp/parser.XXXX` && \
	  sed -e '/BEGIN AVOID/,/END AVOID/d' \
	    parsing/parser.mly > $$tmp/parser.mly && \
	  $(MENHIR) $(MENHIRBASICFLAGS) $$tmp/parser.mly \
	    --list-errors -la 2 \
	    > parsing/parser.auto.messages && \
	  rm -rf $$tmp
	@ cp parsing/parser.auto.messages parsing/parser.auto.messages.bak
	@ $(MENHIR) $(MENHIRBASICFLAGS) parsing/parser.mly \
	    --update-errors parsing/parser.auto.messages.bak \
	    > parsing/parser.auto.messages
	@ rm -f parsing/parser.auto.messages.bak

## generate-parse-errors

# This rule assumes that [make list-parse-errors] has been run first.

# This rule turns the error sentences stored in parsing/parser.auto.messages
# into one .ml file.

# (It would in principle be preferable to create one file per sentence, but
# that would be much slower. We abuse the ability of the OCaml toplevel to
# resynchronize after an error, and put all sentences into a single file.)

# This requires Menhir 20201214 or newer.

GPE_DIR   := tests/generated-parse-errors
GPE_ML    := errors.ml
GPE_REF   := errors.compilers.reference
GPE_START := implementation use_file toplevel_phrase

.PHONY: generate-parse-errors
generate-parse-errors:
	@ \
	mkdir -p testsuite/$(GPE_DIR) && \
	$(MENHIR) $(MENHIRBASICFLAGS) parsing/parser.mly \
	    --echo-errors-concrete parsing/parser.auto.messages 2>/dev/null | \
	(cd testsuite/$(GPE_DIR) && touch $(GPE_REF) && ( \
	  echo "(* TEST\n   * toplevel\n*)" && \
	  while IFS= read -r symbolic ; do \
	    IFS= read -r concrete ; \
	    concrete=$${concrete#### Concrete syntax: } ; \
	    : '$$symbolic is the sentence in symbolic form' ; \
	    : '$$concrete is the sentence in concrete form' ; \
	    case "$$symbolic" in \
	    *": SEMISEMI"*) \
	      : 'If the sentence begins with SEMISEMI, ignore it. Our hack' ; \
	      : 'does not support these sentences, and there are only 6 of' ; \
	      : 'them anyway.' ; \
	      continue ;; \
	    *) \
	      case "$$symbolic" in \
	      *"EOF") \
	        : 'If the sentence ends with EOF, replace it on the fly' ; \
	        : 'with some other token (say, WHEN).' ; \
	        echo "#0 \"$${symbolic%%EOF}WHEN\"" ; \
	        echo "$$concrete when"   ; \
	        echo ";;"                ;; \
	      *) \
	        : 'Emit a # directive containing the symbolic sentence.' ; \
	        echo "#0 \"$$symbolic\"" ; \
	        : 'Emit the concrete sentence.' ; \
	        echo "$$concrete"        ; \
	        : 'Emit a double semicolon to allow resynchronization.' ; \
	        echo ";;"                ;; \
	      esac \
	    esac \
	  done) \
	  > $(GPE_ML) && \
	  : 'Count how many sentences we have emitted, per start symbol.' ; \
	  for symbol in $(GPE_START) ; do \
	    count=$$(grep -h -e "$$symbol:" $(GPE_ML) | wc -l) && \
	    echo "$$count sentences whose start symbol is $$symbol." ; \
	  done \
	)
	@ \
	read -p "Re-generate the expected output for this test? " -n 1 -r && \
	echo && \
	if [[ $$REPLY =~ ^[Yy]$$ ]] ; then \
	  make -C testsuite promote DIR=$(GPE_DIR) >/dev/null 2>&1 && \
	  echo "Done." ; \
	  make classify-parse-errors ; \
	else \
	  echo "OK, stop." ; \
	fi

.PHONY: classify-parse-errors
classify-parse-errors:
	@ ( \
	cd testsuite/$(GPE_DIR) && \
	echo "The parser's output can be described as follows:" && \
	c=$$(grep "^Error: Syntax error" $(GPE_REF) | wc -l) && \
	echo "$${c} syntax errors reported." && \
	c=$$(grep "^Error: Syntax error$$" $(GPE_REF) | wc -l) && \
	echo "$${c} errors without an explanation." && \
	c=$$(grep "^Error: Syntax" $(GPE_REF) | grep expected | wc -l) && \
	echo "$${c} errors with an indication of what was expected." && \
	c=$$(grep "might be unmatched" $(GPE_REF) | wc -l) && \
	echo "$${c} errors with an indication of an unmatched delimiter." && \
	true)