version 3.7.3

* NEWS: Record release date.

.prev-version

@@ -1 +1 @@
-3.6.93
+3.7.2

.travis.yml

@@ -50,6 +50,7 @@ jobs:
         - make -j2 dist-xz
         # Can help understanding why we get "dirty" tarballs.
         - git status
+        - git diff
         - dist=$(echo bison*.xz)
 
         # Unfortunately we cannot deterministically know the name of the tarball without the full
@@ -119,6 +120,8 @@ jobs:
         - CXX='clang++-10 -fsanitize=address -stdlib=libc++'
         - PART=2
 
+    # See https://github.com/simd-everywhere/simde/blob/master/.travis.yml
+    # and https://software.intel.com/content/www/us/en/develop/documentation/get-started-with-intel-oneapi-render-linux/top/configure-your-system.html.
     - name: "ICC"
       stage: check
       os: linux
@@ -127,7 +130,7 @@ jobs:
         - CC=icc
         - CXX=icpc
       install:
-        - source /opt/intel/inteloneapi/compiler/latest/env/vars.sh
+        - source /opt/intel/oneapi/compiler/latest/env/vars.sh
       addons:
         apt:
           sources:

NEWS

@@ -1,5 +1,55 @@
 GNU Bison NEWS
 
+* Noteworthy changes in release 3.7.3 (2020-10-13) [stable]
+
+** Bug fixes
+
+  Fix concurrent build issues.
+
+  The bison executable is no longer linked uselessly against libreadline.
+
+  Fix incorrect use of yytname in glr.cc.
+
+* Noteworthy changes in release 3.7.2 (2020-09-05) [stable]
+
+  This release of Bison fixes all known bugs reported for Bison in MITRE's
+  Common Vulnerabilities and Exposures (CVE) system.  These vulnerabilities
+  are only about bison-the-program itself, not the generated code.
+
+  Although these bugs are typically irrelevant to how Bison is used, they
+  are worth fixing if only to give users peace of mind.
+
+  There is no known vulnerability in the generated parsers.
+
+** Bug fixes
+
+  Fix concurrent build issues (introduced in Bison 3.5).
+
+  Push parsers always use YYMALLOC/YYFREE (no direct calls to malloc/free).
+
+  Fix portability issues of the test suite, and of bison itself.
+
+  Some unlikely crashes found by fuzzing have been fixed.  This is only
+  about bison itself, not the generated parsers.
+
+
+* Noteworthy changes in release 3.7.1 (2020-08-02) [stable]
+
+** Bug fixes
+
+  Crash when a token alias contains a NUL byte.
+
+  Portability issues with libtextstyle.
+
+  Portability issues of Bison itself with MSVC.
+
+** Changes
+
+  Improvements and fixes in the documentation.
+
+  More precise location about symbol type redefinitions.
+
+
 * Noteworthy changes in release 3.7 (2020-07-23) [stable]
 
 ** Deprecated features
@@ -537,7 +587,8 @@ GNU Bison NEWS
   \005) with incorrect styling.  Fixes for similar issues with unexpectedly
   short lines (e.g., the file was changed between parsing and diagnosing).
 
-  Several unlikely crashes found by fuzzing have been fixed.
+  Some unlikely crashes found by fuzzing have been fixed.  This is only
+  about bison itself, not the generated parsers.
 
 
 * Noteworthy changes in release 3.5.2 (2020-02-13) [stable]

README

@@ -42,9 +42,11 @@ installing it.  In that case, do not use `src/bison`: it would use the
 As an experimental feature, diagnostics are now colored, controlled by the
 `--color` and `--style` options.
 
-To use them, install the libtextstyle library before configuring Bison.  It
+To use them, install the libtextstyle library, 0.20.5 or newer, before
-is available from https://alpha.gnu.org/gnu/gettext/, for instance
+configuring Bison.  It is available from https://alpha.gnu.org/gnu/gettext/,
-https://alpha.gnu.org/pub/gnu/gettext/libtextstyle-0.20.5.tar.gz.
+for instance https://alpha.gnu.org/gnu/gettext/libtextstyle-0.20.5.tar.gz,
+or as part of Gettext 0.21 or newer, for instance
+https://ftp.gnu.org/gnu/gettext/gettext-0.21.tar.gz.
 
 The option --color supports the following arguments:
 - always, yes: Enable colors.
@@ -61,6 +63,13 @@ To customize the styles, create a CSS file, say `bison-bw.css`, similar to
 then invoke bison with `--style=bison-bw.css`, or set the `BISON_STYLE`
 environment variable to `bison-bw.css`.
 
+In some diagnostics, bison uses libtextstyle to emit special escapes to
+generate clickable hyperlinks.  The environment variable
+`NO_TERM_HYPERLINKS` can be used to suppress them.  This may be useful for
+terminal emulators which produce garbage output when they receive the escape
+sequence for a hyperlink. Currently (as of 2020), this affects some versions
+of emacs, guake, konsole, lxterminal, rxvt, yakuake.
+
 ## Relocatability
 If you pass `--enable-relocatable` to `configure`, Bison is relocatable.
 

THANKS

@@ -106,9 +106,11 @@ Keith Browne              [email protected]
 Ken Moffat                [email protected]
 Kiyoshi Kanazawa          [email protected]
 Lars Maier                [email protected]
+Lars Wendler              [email protected]
 László Várady             [email protected]
 Laurent Mascherpa         [email protected]
 Lie Yan                   [email protected]
+Maarten De Braekeleer     [email protected]
 Magnus Fromreide          [email protected]
 Marc Autret               [email protected]
 Marc Mendiola             [email protected]
@@ -185,6 +187,7 @@ Simon Sobisch             [email protected]
 Stefano Lattarini         [email protected]
 Stephen Cameron           [email protected]
 Steve Murphy              [email protected]
+Suhwan Song               [email protected]
 Sum Wu                    [email protected]
 Théophile Ranquet         [email protected]
 Thiru Ramakrishnan        [email protected]

TODO

@@ -1,4 +1,12 @@
-* Bison 3.7
+* Soon
+** gnulib
+Bruno notes:
+
+> I haven't looked deeply, but it strikes me that gnulib/lib/bitset/array.c
+> does not make use of the 'ffsl' function, nor or the 'integer_length_l'
+> function. Maybe because in Bison, all bitsets are so dense that it does
+> not give a performance advantage?
+
 ** Cex
 *** Improve gnulib
 Don't do this (counterexample.c):
@@ -48,13 +56,6 @@ Unless we play it dumb (little structure).
 
 - promote YYEOF rather than EOF.
 
-*** D
-- is there a way to attach yysymbol_name to the enum itself?  As we did
-  in Java.
-
-- It would be better to have TokenKind as return value.  Can we use
-  reflection to support both output types?
-
 ** YYerror
 https://git.savannah.gnu.org/gitweb/?p=gettext.git;a=blob;f=gettext-runtime/intl/plural.y;h=a712255af4f2f739c93336d4ff6556d932a426a5;hb=HEAD
 
@@ -67,7 +68,7 @@ Stop hard-coding "Calc".  Adjust local.at (look for FIXME).
 
 ** A dev warning for b4_
 Maybe we should check for m4_ and b4_ leaking out of the m4 processing, as
-Autoconf does.  It would have caught overquotation issues.
+Autoconf does.  It would have caught over-quotation issues.
 
 ** doc
 I feel it's ugly to use the GNU style to declare functions in the doc.  It
@@ -88,7 +89,7 @@ push parsers on top of pull parser.  Which is currently not relevant, since
 push parsers are measurably slower.
 
 ** %define parse.error formatted
-How about pushing bistromathics' yyreport_syntax_error as another standard
+How about pushing Bistromathic's yyreport_syntax_error as another standard
 way to generate the error message, and leave to the user the task of
 providing the message formats?  Currently in bistro, it reads:
 
@@ -202,18 +203,282 @@ The "automaton" and "set" categories are not so useful.  We should probably
 introduce lr(0) and lalr, just the way we have ielr categories.  The
 "closure" function is too verbose, it should probably have its own category.
 
-"set" can still be used for summariring the important sets.  That would make
+"set" can still be used for summarizing the important sets.  That would make
 tests easy to maintain.
 
 *** complain.*
 Rename these guys as "diagnostics.*" (or "diagnose.*"), since that's the
-name they have in gcc, clang, etc.  Likewise for the complain_* series of
+name they have in GCC, clang, etc.  Likewise for the complain_* series of
 functions.
 
 *** ritem
 states/nstates, rules/nrules, ..., ritem/nritems
 Fix the latter.
 
+* D programming language
+There's a number of features that are missing, here sorted in _suggested_
+order of implementation.
+
+When copying code from other skeletons, keep the comments exactly as they
+are.  Keep the same variable names.  If you change the wording in one place,
+do it in the others too.  In other words: make sure to keep the
+maintenance *simple* by avoiding any gratuitous difference.
+
+** Rename the D example
+Move the current content of examples/d into examples/d/simple.
+
+** Create a second example
+Duplicate examples/d/simple into examples/d/calc.
+
+** Add location tracking to d/calc
+Look at the examples in the other languages to see how to do that.
+
+** yysymbol_name
+The SymbolKind is an enum.  For a given SymbolKind we want to get its string
+representation.  Currently it's a separate table in the parser that does
+that:
+
+  /* Symbol kinds.  */
+  public enum SymbolKind
+  {
+    S_YYEMPTY = -2,  /* No symbol.  */
+    S_YYEOF = 0,                   /* "end of file"  */
+    S_YYerror = 1,                 /* error  */
+    S_YYUNDEF = 2,                 /* "invalid token"  */
+    S_EQ = 3,                      /* "="  */
+    ...
+    S_input = 14,                  /* input  */
+    S_line = 15,                   /* line  */
+    S_exp = 16,                    /* exp  */
+  };
+
+  ...
+
+  /* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+     First, the terminals, then, starting at \a yyntokens_, nonterminals.  */
+  private static immutable string[] yytname_ =
+  [
+  "\"end of file\"", "error", "\"invalid token\"", "\"=\"", "\"+\"",
+  "\"-\"", "\"*\"", "\"/\"", "\"(\"", "\")\"", "\"end of line\"",
+  "\"number\"", "UNARY", "$accept", "input", "line", "exp", null
+  ];
+
+  ...
+
+So to get a symbol kind, one runs `yytname_[yykind]`.
+
+Is there a way to attach this conversion to string to SymbolKind?  In Java
+for instance, we have:
+
+  public enum SymbolKind
+  {
+    S_YYEOF(0),                    /* "end of file"  */
+    S_YYerror(1),                  /* error  */
+    S_YYUNDEF(2),                  /* "invalid token"  */
+    ...
+    S_input(16),                   /* input  */
+    S_line(17),                    /* line  */
+    S_exp(18);                     /* exp  */
+
+    private final int yycode_;
+
+    SymbolKind (int n) {
+      this.yycode_ = n;
+    }
+    ...
+    /* YYNAMES_[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+       First, the terminals, then, starting at \a YYNTOKENS_, nonterminals.  */
+    private static final String[] yynames_ = yynames_init();
+    private static final String[] yynames_init()
+    {
+      return new String[]
+      {
+        i18n("end of file"), i18n("error"), i18n("invalid token"), "!", "+", "-", "*",
+        "/", "^", "(", ")", "=", i18n("end of line"), i18n("number"), "NEG",
+        "$accept", "input", "line", "exp", null
+      };
+    }
+
+    /* The user-facing name of this symbol.  */
+    public final String getName() {
+      return yynames_[yycode_];
+    }
+  };
+
+which allows to write more naturally `yykind.getName()` rather than
+`yytname_[yykind]`.  Is there something comparable in (idiomatic) D?
+
+** Change the return value of yylex
+Historically people were allowed to return any int from the scanner (which
+is convenient and allows `return '+'` from the scanner).  Akim tends to see
+this as an error, we should restrict the return values to TokenKind (not to
+be confused with SymbolKind).
+
+In the case of D, without the history, we have the choice to support or not
+`int`.  If we want to _keep_ `int`, is there a way, say via introspection,
+to support both signatures of yylex?  If we don't keep `int`, just move to
+TokenKind.
+
+** Documentation
+Write documentation about D support in doc/bison.texi.  Imitate the Java
+documentation.  You should be more succinct IMHO.
+
+** Complete Symbols
+The current interface from the scanner to the parser is somewhat clumsy: the
+token kind is returned by yylex, but the value and location are stored in
+the scanner.  This reflects the fact that the implementation of the parser
+uses three variables to deal with each parsed symbol: its kind, its value,
+its location.
+
+So today the scanner of examples/d/calc.d (no locations) looks like:
+
+    if (input.front.isNumber)
+      {
+        import std.conv : parse;
+        semanticVal_.ival = input.parse!int;
+        return TokenKind.NUM;
+      }
+
+and the generated parser:
+
+    /* Read a lookahead token.  */
+    if (yychar == TokenKind.YYEMPTY)
+    {
+      yychar = yylex ();
+      yylval = yylexer.semanticVal;
+    }
+
+The parser class should feature a `Symbol` type which binds together kind,
+value and location, and the scanner should be able to return an instance of
+that type.  Something like
+
+    if (input.front.isNumber)
+      {
+        import std.conv : parse;
+        return parser.Symbol (TokenKind.NUM, input.parse!int);
+      }
+
+** Token Constructors
+In the previous example it is possible to mix incorrectly kinds and values,
+and for instance:
+
+        return parser.Symbol (TokenKind.NUM, "Hello, World!\n");
+
+attaches a string value to NUM kind (wrong, of course).  When
+api.token.constructor is set, in C++, Bison generated "token constructors":
+parser.make_NUM. parser.make_PLUS, parser.make_STRING, etc.  The previous
+example becomes
+
+        return parser.make_NUM ("Hello, World!\n");
+
+which would easily be caught by the type checker.
+
+** Lookahead Correction
+Add support for LAC to the D skeleton.  It should not be too hard: look how
+this is done in lalr1.cc, and mock it.
+
+** Push Parser
+Add support for push parser.  Do not start a nice skeleton, just enhance the
+current one to support push parsers.  This is going to be a tougher nut to
+crack.
+
+First, you need to understand well how the push parser is expected to work.
+To this end:
+- read the doc
+- look at examples/c/pushcalc
+- create an example of a Java push parser.
+- have a look at the generated parser in Java, which has the advantage of
+  being already based on a parser object, instead of just a function.
+
+The C case is harder to read, but it may help too.  Keep in mind that
+because there's no object to maintain state, the C push parser uses some
+struct (yypstate) to preserve this state.  We don't need this in D, the
+parser object will suffice.
+
+I think working directly on the skeleton to add push-parser support is not
+the simplest path.  I suggest that you (1) transform a generated parser into
+a push parser by hand, and then (2) transform lalr1.d to generate such a
+parser.
+
+Use `git commit` frequently to make sure you keep track of your progress.
+
+*** (1.a) Prepare pull parser by hand
+Copy again one of the D examples into say examples/d/pushcalc.  Also
+check-in the generated parser to facilitate experimentation.
+
+- find local variables of yyparse should become members of the parser object
+  (so that we preserve state from one call to the next).
+
+- do it in your generated D parser.  We don't need an equivalent for
+  yypstate, because we already have it: that the parser object itself.
+
+- have your *pull*-parser (i.e., the good old yy::parser::parse()) work
+  properly this way.  Write and run tests.  That's one of the reasons I
+  suggest using examples/d/calc as a starting point: it already has tests,
+  you can/should add more.
+
+At this point you have a pull-parser which you prepared to turn into a
+push-parser.
+
+*** (1.b) Turn pull parser into push parser by hand
+
+- look again at how push parsers are implemented in Java/C to see what needs
+  to change in yyparse so that the control is inverted: parse() will
+  be *given* the tokens, instead of having to call yylex itself.  When I say
+  "look at C", I think your best option are (i) yacc.c (look for b4_push_if)
+  and (ii) examples/c/pushcalc.
+
+- rename parse() as push_parse(Symbol yyla) (or push_parse(TokenKind, Value,
+  Location)) that takes the symbol as argument.  That's the push parser we
+  are looking for.
+
+- define a new parse() function which has the same signature as the usual
+  pull-parser, that repeatedly calls the push_parse function.  Something
+  like this:
+
+int parse ()
+{
+ int status = 0;
+ do {
+  status = this->push_parse (yylex());
+ } while (status == YYPUSH_MORE);
+ return status;
+}
+
+- show me that parser, so that we can validate the approach.
+
+*** (2) Port that into the skeleton
+- once we agree on the API of the push parser, implement it into lalr1.d.
+  You will probaby need help on this regard, but imitation, again, should
+  help.
+
+- have example/d/pushcalc work properly and pass tests
+
+- add tests in the "real" test suite.  Do that in tests/calc.at.  I can
+  help.
+
+- document
+
+** GLR Parser
+This is very ambitious.  That's the final boss.  There are currently no
+"clean" implementation to get inspiration from.
+
+glr.c is very clean but:
+- is low-level C
+- is a different skeleton from yacc.c
+
+glr.cc is (currently) an ugly hack: a C++ shell around glr.c.  Valentin
+Tolmer is currently rewriting glr.cc to be clean C++, but he is not
+finished.  There will be a lot a common code between lalr1.cc and glr.cc, so
+eventually I would like them to be fused into a single skeleton, supporting
+both deterministic and generalized parsing.
+
+It would be great for D to also support this.
+
+The basic ideas of GLR are explained here:
+
+https://www.codeproject.com/Articles/5259825/GLR-Parsing-in-Csharp-How-to-Use-The-Most-Powerful
+
 * Better error messages
 The users are not provided with enough tools to forge their error messages.
 See for instance "Is there an option to change the message produced by
@@ -231,7 +496,7 @@ and older C++ compilers.  Currently the code defaults to defining it to
 define it to the same type as the C ptrdiff_t type.
 
 * Completion
-Several features are not available in all the backends.
+Several features are not available in all the back-ends.
 
 - lac: D, Java (easy)
 - push parsers: glr.c, glr.cc, lalr1.cc (not very difficult)
@@ -301,7 +566,7 @@ opposite side we have some use of \l, which is graphviz-specific, in what
 should be generic code.
 
 Little effort seems to have been given to factoring these files and their
-rint{,-xml} counterpart. We would very much like to re-use the pretty format
+print{,-xml} counterpart. We would very much like to re-use the pretty format
 of states from .output for the graphs, etc.
 
 Since graphviz dies on medium-to-big grammars, maybe consider an other tool?
@@ -579,14 +844,39 @@ to bison. If you're interested, I'll work on a patch.
 Equip the parser with a means to create the (visual) parse tree.
 
 
+-----
+
+# LocalWords:  Cex gnulib gl Bistromathic TokenKinds yylex enum YYEOF EOF
+# LocalWords:  YYerror gettext af hb YYERRCODE undef calc FIXME dev yyerror
+# LocalWords:  Autoconf YYUNDEFTOK lexemes parsers Bistromathic's yyreport
+# LocalWords:  const argc yacc yyclearin lookahead destructor Rici incluent
+# LocalWords:  yydestruct yydiscardin catégories d'avertissements sr activé
+# LocalWords:  conflits défaut rr l'alias chaîne n'est attaché un symbole
+# LocalWords:  obsolète règle vide midrule valeurs de intermédiaire ou avec
+# LocalWords:  définies inutilisées priorité associativité inutiles POSIX
+# LocalWords:  incompatibilités tous les autres avertissements sauf dans rp
+# LocalWords:  désactiver CATEGORIE traiter comme des erreurs glr Akim bool
+# LocalWords:  Demaille arith lalr goto struct pathlen nullable ntokens lr
+# LocalWords:  nterm bitsetv ielr ritem nstates nrules nritems yysymbol EQ
+# LocalWords:  SymbolKind YYEMPTY YYUNDEF YYTNAME NUM yyntokens yytname sed
+# LocalWords:  nonterminals yykind yycode YYNAMES yynames init getName conv
+# LocalWords:  TokenKind semanticVal ival yychar yylval yylexer Tolmer hoc
+# LocalWords:  Sobisch YYPTRDIFF ptrdiff Autotest YYPRINT toknum yytoknum
+# LocalWords:  sym Wother stderr FP fixits xgettext fdiagnostics Graphviz
+# LocalWords:  graphviz VCG bitset xml bw maint yytoken YYABORT deps
+# LocalWords:  YYACCEPT yytranslate nonnegative destructors yyerrlab repo
+# LocalWords:  backends stmt expr yy Mardle baz qux Vadim Maslow CPP cpp
+# LocalWords:  yydebug gcc UCHAR EBCDIC gung PDP NUL Pre Florian Krohm utf
+# LocalWords:  YYACT YYLLOC YYLSP yyval yyvsp yylen yyloc yylsp endif
+# LocalWords:  ispell american
+
 Local Variables:
 mode: outline
 coding: utf-8
 fill-column: 76
+ispell-dictionary: "american"
 End:
 
------
-
 Copyright (C) 2001-2004, 2006, 2008-2015, 2018-2020 Free Software
 Foundation, Inc.
 

bootstrap.conf

@@ -45,6 +45,8 @@ gnulib_modules='
   relocatable-prog relocatable-script
   rename
   spawn-pipe stdbool stpcpy stpncpy strdup-posix strerror strverscmp
+  sys_ioctl
+  termios
   timevar
   unicodeio unistd unistd-safer unlink unlocked-io
   update-copyright unsetenv verify

cfg.mk

@@ -126,7 +126,7 @@ _sed_rm_comments_q = $(subst ','\'',$(_sed_remove_comments))
 
 _space_before_paren_exempt =? \\n\\$$
 _space_before_paren_exempt = \
-  (^ *\#|(LA)?LR\([01]\)|percent_(code|define)|b4_syncline|m4_(define|init)|symbol)
+  (^ *\#|(LA)?LR\([01]\)|percent_(code|define)|b4_syncline|m4_(define|init))
 # Ensure that there is a space before each open parenthesis in C code.
 sc_space_before_open_paren:
 	@if $(VC_LIST_EXCEPT) | grep -l '\.[ch]$$' > /dev/null; then	\
@@ -156,6 +156,7 @@ exclude = \
 $(call exclude,                                                                 \
   bindtextdomain=^lib/main.c$$                                                  \
   cast_of_argument_to_free=^src/muscle-tab.c$$                                  \
+  error_message_uppercase=etc/bench.pl.in$$                                     \
   po_check=^tests|(^po/POTFILES.in|.md)$$                                       \
   preprocessor_indentation=^data/|^lib/|^src/parse-gram.[ch]$$                  \
   program_name=^lib/main.c$$                                                    \

configure.ac

@@ -60,6 +60,9 @@ AC_PROG_CXX
 # Gnulib (early checks).
 gl_EARLY
 
+# We want ostream_printf and hyperlink support.
+gl_LIBTEXTSTYLE_OPTIONAL([0.20.5])
+
 # Gnulib uses '#pragma GCC diagnostic push' to silence some
 # warnings, but older gcc doesn't support this.
 AC_CACHE_CHECK([whether pragma GCC diagnostic push works],

data/skeletons/glr.cc

@@ -172,7 +172,7 @@ m4_pushdef([b4_parse_param], m4_defn([b4_parse_param_orig]))dnl
                            const location_type* yylocationp]])[) const
   {
     *yycdebug_ << (yykind < YYNTOKENS ? "token" : "nterm")
-               << ' ' << yytname[yykind] << " ("]b4_locations_if([[
+               << ' ' << yysymbol_name (yykind) << " ("]b4_locations_if([[
                << *yylocationp << ": "]])[;
     yy_symbol_value_print_ (yykind, yyvaluep]b4_locations_if([[, yylocationp]])[);
     *yycdebug_ << ')';

data/skeletons/yacc.c

@@ -1486,7 +1486,7 @@ yypstate_new (void)
   yypstate *yyps;]b4_pure_if([], [[
   if (yypstate_allocated)
     return YY_NULLPTR;]])[
-  yyps = YY_CAST (yypstate *, malloc (sizeof *yyps));
+  yyps = YY_CAST (yypstate *, YYMALLOC (sizeof *yyps));
   if (!yyps)
     return YY_NULLPTR;]b4_pure_if([], [[
   yypstate_allocated = 1;]])[
@@ -1515,7 +1515,7 @@ yypstate_delete (yypstate *yyps)
 #endif]b4_lac_if([[
       if (yyes != yyesa)
         YYSTACK_FREE (yyes);]])[
-      free (yyps);]b4_pure_if([], [[
+      YYFREE (yyps);]b4_pure_if([], [[
       yypstate_allocated = 0;]])[
     }
 }

doc/bison.texi

@@ -57,44 +57,57 @@
 \gdef\colorPurple{%
  \setcolor{\rgbPurple}%
 }
+\gdef\colorOff{%
+ \setcolor{\maincolor}%
+}
 
 \gdef\rgbError{0.80 0 0}
-\gdef\colorError{%
+\gdef\diagError{%
  \setcolor{\rgbError}%
 }
 \gdef\rgbNotice{0 0 0.80}
-\gdef\colorNotice{%
+\gdef\diagNotice{%
  \setcolor{\rgbNotice}%
 }
-\gdef\colorOff{%
+\gdef\rgbWarning{0.50 0 0.50}
+\gdef\diagWarning{%
+ \setcolor{\rgbWarning}%
+}
+\gdef\diagOff{%
  \setcolor{\maincolor}%
 }
 @end tex
 
 @ifnottex
 @macro colorGreen
-@inlineraw{html, <b style="color:green">}
+@inlineraw{html, <span style="color:green">}
 @end macro
 @macro colorYellow
-@inlineraw{html, <b style="color:#ff8000">}
+@inlineraw{html, <span style="color:#ff8000">}
 @end macro
 @macro colorRed
-@inlineraw{html, <b style="color:red">}
+@inlineraw{html, <span style="color:red">}
 @end macro
 @macro colorBlue
-@inlineraw{html, <b style="color:blue">}
+@inlineraw{html, <span style="color:blue">}
 @end macro
 @macro colorPurple
-@inlineraw{html, <b style="color:darkviolet">}
+@inlineraw{html, <span style="color:darkviolet">}
-@end macro
-
-@macro colorError
-@inlineraw{html, <b style="color:red">}
-@end macro
-@macro colorNotice
-@inlineraw{html, <b style="color:darkcyan">}
 @end macro
 @macro colorOff
+@inlineraw{html, </span>}
+@end macro
+
+@macro diagError
+@inlineraw{html, <b style="color:red">}
+@end macro
+@macro diagNotice
+@inlineraw{html, <b style="color:darkcyan">}
+@end macro
+@macro diagWarning
+@inlineraw{html, <b style="color:darkviolet">}
+@end macro
+@macro diagOff
 @inlineraw{html, </b>}
 @end macro
 @end ifnottex
@@ -120,15 +133,15 @@
 @end macro
 
 @macro dwarning{text}
-@purple{\text\}
+@diagWarning{}\text\@diagOff{}
 @end macro
 
 @macro derror{text}
-@colorError{}\text\@colorOff{}
+@diagError{}\text\@diagOff{}
 @end macro
 
 @macro dnotice{text}
-@colorNotice{}\text\@colorOff{}
+@diagNotice{}\text\@diagOff{}
 @end macro
 
 @finalout
@@ -6283,7 +6296,10 @@ Introduced in Bison 3.3 to replace @code{parser_class_name}.
 
 @item Default Value: @code{YY} for Java, @code{yy} otherwise.
 
-@item History: introduced in Bison 2.6
+@item History:
+introduced in Bison 2.6, with its argument in double quotes.  Uses braces
+since Bison 3.0 (double quotes are still supported for backward
+compatibility).
 @end itemize
 @end deffn
 
@@ -8302,7 +8318,53 @@ write an unambiguous grammar, but that is very hard to do in this case.)
 This particular ambiguity was first encountered in the specifications of
 Algol 60 and is called the ``dangling @code{else}'' ambiguity.
 
-To avoid warnings from Bison about predictable, legitimate shift/reduce
+To assist the grammar author in understanding the nature of each conflict,
+Bison can be asked to generate ``counterexamples''.  In the present case it
+actually even proves that the grammar is ambiguous by exhibiting a string
+with two different parses:
+
+@macro danglingElseCex
+@group
+@ifnottex
+  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @blue{"else" stmt}
+  Shift derivation
+    @yellow{if_stmt}
+    @yellow{↳ "if" expr "then"} @green{stmt}
+                        @green{↳} @blue{if_stmt}
+                           @blue{↳ "if" expr "then" stmt} @red{•} @blue{"else" stmt}
+  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @yellow{"else" stmt}
+  Reduce derivation
+    @yellow{if_stmt}
+    @yellow{↳ "if" expr "then"} @green{stmt}                        @yellow{"else" stmt}
+                        @green{↳} @blue{if_stmt}
+                           @blue{↳ "if" expr "then" stmt} @red{•}
+@end ifnottex
+@iftex
+  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @blue{"else" stmt}
+  Shift derivation
+    @yellow{if_stmt}
+    @yellow{@arrow{} "if" expr "then"} @green{stmt}
+                        @green{@arrow{}} @blue{if_stmt}
+                           @blue{@arrow{} "if" expr "then" stmt} @red{•} @blue{"else" stmt}
+  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @yellow{"else" stmt}
+  Reduce derivation
+    @yellow{if_stmt}
+    @yellow{@arrow{} "if" expr "then"} @green{stmt}                        @yellow{"else" stmt}
+                        @green{@arrow{}} @blue{if_stmt}
+                           @blue{@arrow{} "if" expr "then" stmt} @red{•}
+@end iftex
+@end group
+@end macro
+@example
+@danglingElseCex
+@end example
+
+@noindent
+@xref{Counterexamples}, for more details.
+
+@sp 1
+
+To avoid warnings from Bison about predictable, @emph{legitimate} shift/reduce
 conflicts, you can use the @code{%expect @var{n}} declaration.
 There will be no warning as long as the number of shift/reduce conflicts
 is exactly @var{n}, and Bison will report an error if there is a
@@ -8693,7 +8755,8 @@ maybeword:
 @end example
 
 @noindent
-The error is an ambiguity: there is more than one way to parse a single
+The error is an ambiguity: as counterexample generation would demonstrate
+(@pxref{Counterexamples}), there is more than one way to parse a single
 @code{word} into a @code{sequence}.  It could be reduced to a
 @code{maybeword} and then into a @code{sequence} via the second rule.
 Alternatively, nothing-at-all could be reduced into a @code{sequence}
@@ -8890,12 +8953,14 @@ name_list:
 It would seem that this grammar can be parsed with only a single token of
 lookahead: when a @code{param_spec} is being read, an @code{"id"} is a
 @code{name} if a comma or colon follows, or a @code{type} if another
-@code{"id"} follows.  In other words, this grammar is LR(1).
+@code{"id"} follows.  In other words, this grammar is LR(1).  Yet Bison
+finds one reduce/reduce conflict, for which counterexample generation
+(@pxref{Counterexamples}) would find a @emph{nonunifying} example.
 
 @cindex LR
 @cindex LALR
-However, for historical reasons, Bison cannot by default handle all
+This is because Bison does not handle all LR(1) grammars @emph{by default},
-LR(1) grammars.
+for historical reasons.
 In this grammar, two contexts, that after an @code{"id"} at the beginning
 of a @code{param_spec} and likewise at the beginning of a
 @code{return_spec}, are similar enough that Bison assumes they are the
@@ -9870,6 +9935,9 @@ and understand the parser run-time traces (@pxref{Tracing}).
 
 @node Counterexamples
 @section Generation of Counterexamples
+@cindex cex
+@cindex counterexamples
+@cindex conflict counterexamples
 
 Solving conflicts is probably the most delicate part of the design of an LR
 parser, as demonstrated by the number of sections devoted to them in this
@@ -9886,8 +9954,8 @@ That task is made much easier thanks to the generation of counterexamples,
 initially developed by Chinawat Isradisaikul and Andrew Myers
 @pcite{Isradisaikul 2015}.
 
-As a first example, see the example grammar of @ref{Shift/Reduce}, which
+As a first example, see the grammar of @ref{Shift/Reduce}, which features
-features on shift/reduce conflict:
+one shift/reduce conflict:
 
 @c see doc/if-then-else.y
 @example
@@ -9901,49 +9969,14 @@ Let's rerun @command{bison} with the option
 @option{-Wcex}/@option{-Wcounterexamples}@inlinefmt{info, (the following
 output is actually in color)}:
 
-@ifnottex
 @example
 if-then-else.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
 if-then-else.y: @dwarning{warning}: shift/reduce conflict on token "else" [@dwarning{-Wcounterexamples}]
-@group
+@danglingElseCex
-  Example: @yellow{"if" expr "then"} "if" expr "then" stmt • "else" stmt
-  Shift derivation
-    @yellow{if_stmt}
-    @yellow{↳ "if" expr "then"} @green{stmt}
-                       @green{↳} @blue{if_stmt}
-                         @blue{↳ "if" expr "then" stmt} @red{•} @blue{"else" stmt}
-  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @yellow{"else" stmt}
-  Reduce derivation
-    @yellow{if_stmt}
-    @yellow{↳ "if" expr "then"} @green{stmt}                        @yellow{"else" stmt}
-                       @green{↳} @blue{if_stmt}
-                         @blue{↳ "if" expr "then" stmt} @red{•}
-@end group
 @end example
-@end ifnottex
-@iftex
-@example
-if-then-else.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
-if-then-else.y: @dwarning{warning}: shift/reduce conflict on token "else" [@dwarning{-Wcounterexamples}]
-@group
-  Example: @yellow{"if" expr "then"} "if" expr "then" stmt • "else" stmt
-  Shift derivation
-    @yellow{if_stmt}
-    @yellow{@arrow{} "if" expr "then"} @green{stmt}
-                        @green{@arrow{}} @blue{if_stmt}
-                          @blue{@arrow{} "if" expr "then" stmt} @red{•} @blue{"else" stmt}
-  Example: @yellow{"if" expr "then"} @blue{"if" expr "then" stmt} @red{•} @yellow{"else" stmt}
-  Reduce derivation
-    @yellow{if_stmt}
-    @yellow{@arrow{} "if" expr "then"} @green{stmt}                        @yellow{"else" stmt}
-                        @green{@arrow{}} @blue{if_stmt}
-                           @blue{@arrow{} "if" expr "then" stmt} @red{•}
-@end group
-@end example
-@end iftex
 
-This shows two different derivations for one single expression.  That
+This shows two different derivations for one single expression, which proves
-demonstrates that the grammar is ambiguous.
+that the grammar is ambiguous.
 
 @sp 1
 
@@ -9966,13 +9999,13 @@ maybeword:
 
 Bison generates the following counterexamples:
 
-@ifnottex
 @example
 @group
 $ @kbd{bison -Wcex sequence.y}
 sequence.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
 sequence.y: @dwarning{warning}: 2 reduce/reduce conflicts [@dwarning{-Wconflicts-rr}]
 @end group
+@ifnottex
 @group
 sequence.y: @dwarning{warning}: shift/reduce conflict on token "word" [@dwarning{-Wcounterexamples}]
   Example: @red{•} @green{"word"}
@@ -10017,15 +10050,8 @@ sequence.y:8.3-45: @dwarning{warning}: rule useless in parser due to conflicts [
     8 |   @dwarning{%empty    @{ printf ("empty maybeword\n"); @}}
       |   @dwarning{^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~}
 @end group
-@end example
 @end ifnottex
 @iftex
-@example
-@group
-$ @kbd{bison -Wcex sequence.y}
-sequence.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
-sequence.y: @dwarning{warning}: 2 reduce/reduce conflicts [@dwarning{-Wconflicts-rr}]
-@end group
 @group
 sequence.y: @dwarning{warning}: shift/reduce conflict on token "word" [@dwarning{-Wcounterexamples}]
   Example: @red{•} @green{"word"}
@@ -10070,8 +10096,8 @@ sequence.y:8.3-45: @dwarning{warning}: rule useless in parser due to conflicts [
     8 |   @dwarning{%empty    @{ printf ("empty maybeword\n"); @}}
       |   @dwarning{^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~}
 @end group
-@end example
 @end iftex
+@end example
 
 Each of these three conflicts, again, prove that the grammar is ambiguous.
 For instance, the second conflict (the reduce/reduce one) shows that the
@@ -10096,10 +10122,10 @@ expr: %empty | expr ID ','
 
 @command{bison} reports:
 
-@ifnottex
 @example
 ids.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
 ids.y: @dwarning{warning}: shift/reduce conflict on token ID [@dwarning{-Wcounterexamples}]
+@ifnottex
 @group
   First example: @purple{expr} @red{•} @purple{ID ','} @green{ID} @yellow{$end}
   Shift derivation
@@ -10120,12 +10146,8 @@ ids.y:4.4-7: @dwarning{warning}: rule useless in parser due to conflicts [@dwarn
     4 | a: expr
       |    ^~~~
 @end group
-@end example
 @end ifnottex
 @iftex
-@example
-ids.y: @dwarning{warning}: 1 shift/reduce conflict [@dwarning{-Wconflicts-sr}]
-ids.y: @dwarning{warning}: shift/reduce conflict on token ID [@dwarning{-Wcounterexamples}]
 @group
   First example: @purple{expr} @red{•} @purple{ID ','} @green{ID} @yellow{$end}
   Shift derivation
@@ -10146,8 +10168,8 @@ ids.y:4.4-7: @dwarning{warning}: rule useless in parser due to conflicts [@dwarn
     4 | a: expr
       |    ^~~~
 @end group
-@end example
 @end iftex
+@end example
 
 This conflict is caused by the parser not having enough information to know
 the difference between these two examples.  The parser would need an
@@ -15631,6 +15653,10 @@ permitted.  @xref{Language and Grammar}.
 A sequence of tokens and/or nonterminals, with one dot, that demonstrates a
 conflict.  The dot marks the place where the conflict occurs.
 
+@cindex unifying counterexample
+@cindex counterexample, unifying
+@cindex nonunifying counterexample
+@cindex counterexample, nonunifying
 A @emph{unifying} counterexample is a single string that has two different
 parses; its existence proves that the grammar is ambiguous.  When a unifying
 counterexample cannot be found in reasonable time, a @emph{nonunifying}

doc/local.mk

@@ -57,7 +57,7 @@ MAINTAINERCLEANFILES = $(CROSS_OPTIONS_TEXI)
 
 # Fix Info's @code in @deftype
 # https://lists.gnu.org/archive/html/help-texinfo/2019-11/msg00004.html
-all: $(srcdir)/$(%C%_bison).info.bak
+all-local: $(srcdir)/$(%C%_bison).info.bak
 $(srcdir)/$(%C%_bison).info.bak: $(srcdir)/$(%C%_bison).info
 	$(AM_V_GEN) $(PERL) -pi.bak -0777	\
 	  -e 's{(^ --.*\n(?: {10}.*\n)*)}'	\

etc/bench.pl.in

@@ -185,13 +185,13 @@ my $verbose = 1;
 
 =over 4
 
-=item C<verbose($level, $message)>
+=item C<verbose ($level, $message)>
 
 Report the C<$message> is C<$level> E<lt>= C<$verbose>.
 
 =cut
 
-sub verbose($$)
+sub verbose ($$)
 {
   my ($level, $message) = @_;
   print STDERR $message
@@ -201,13 +201,13 @@ sub verbose($$)
 
 ######################################################################
 
-=item C<directives($bench, @directive)>
+=item C<directives ($bench, @directive)>
 
 Format the list of directives for Bison for bench named C<$bench>.
 
 =cut
 
-sub directives($@)
+sub directives ($@)
 {
   my ($bench, @directive) = @_;
   my $res = "/* Directives for bench '$bench'. */\n";
@@ -218,6 +218,27 @@ sub directives($@)
 
 ######################################################################
 
+=item C<is_pure (@directive)>
+
+Whether api.pure is set.
+
+=cut
+
+sub is_pure (@)
+{
+  my (@directive) = @_;
+  for my $dir (@directive)
+    {
+      if ($dir =~ /\A%define api.pure/)
+        {
+          return 1;
+        }
+    }
+  return 0;
+}
+
+######################################################################
+
 =item C<generate_grammar_triangular ($base, $max, @directive)>
 
 Create a large triangular grammar which looks like :
@@ -389,18 +410,14 @@ sub generate_grammar_calc ($$@)
 %define api.value.type union
 $directives
 
-%{
+%code provides {
 static int power (int base, int exponent);
 /* yyerror receives the location if:
    - %location & %pure & %glr
    - %location & %pure & %yacc & %parse-param. */
 static void yyerror (const char *s);
-#if YYPURE
+static int yylex (@{[is_pure (@directive) ? "YYSTYPE *yylvalp" : "void"]});
-static int yylex (YYSTYPE* yylvalp);
+}
-#else
-static int yylex (void);
-#endif
-%}
 
 /* Bison Declarations */
 %token
@@ -467,12 +484,7 @@ yyerror (const char *s)
 }
 
 static int
-#if YYPURE
+yylex (@{[is_pure (@directive) ? "YYSTYPE *yylvalp" : "void"]})
-# define yylval (*yylvalp)
-yylex (YYSTYPE* yylvalp)
-#else
-yylex (void)
-#endif
 {
   int c;
 
@@ -498,7 +510,7 @@ yylex (void)
     case '5': case '6': case '7': case '8': case '9':
       {
         int nchars = 0;
-        int n = sscanf (input - 1, "%d%n", &yylval.NUM, &nchars);
+        int n = sscanf (input - 1, "%d%n", &@{[is_pure (@directive) ? "yylvalp->" : "yylval."]}NUM, &nchars);
         assert (n == 1);
         input += nchars - 1;
         return NUM;
@@ -506,7 +518,7 @@ yylex (void)
 
     default:
       yyerror ("error: invalid character");
-      return yylex ();
+      return yylex (@{[is_pure (@directive) ? "yylvalp" : ""]});
     }
 }
 EOF
@@ -592,10 +604,10 @@ $directives
   // Prototype of the yylex function providing subsequent tokens.
   static
 #if USE_TOKEN_CTOR
-  yy::parser::symbol_type yylex();
+  yy::parser::symbol_type yylex ();
 #else
-  yy::parser::token_type yylex(yy::parser::semantic_type* yylvalp,
+  yy::parser::token_type yylex (yy::parser::semantic_type *yylvalp,
-                               yy::parser::location_type* yyllocp);
+                                yy::parser::location_type *yyllocp);
 #endif
 
   // Conversion to string.
@@ -618,8 +630,8 @@ EOF
       print $out <<'EOF';
 %token <std::string> TEXT
 %token <int> NUMBER
-%printer { std::cerr << "Number: " << $$; } <int>
+%printer { yyo << "Number: " << $$; } <int>
-%printer { std::cerr << "Text: " << $$; } <std::string>
+%printer { yyo << "Text: " << $$; } <std::string>
 %type <std::string> text result
 
 %%
@@ -641,8 +653,8 @@ EOF
 %union {int ival; std::string* sval;}
 %token <sval> TEXT
 %token <ival> NUMBER
-%printer { std::cerr << "Number: " << $$; } <ival>
+%printer { yyo << "Number: " << $$; } <ival>
-%printer { std::cerr << "Text: " << *$$; } <sval>
+%printer { yyo << "Text: " << *$$; } <sval>
 %type <sval> text result
 
 %%
@@ -664,10 +676,10 @@ EOF
 
 static
 #if USE_TOKEN_CTOR
-yy::parser::symbol_type yylex()
+yy::parser::symbol_type yylex ()
 #else
-yy::parser::token_type yylex(yy::parser::semantic_type* yylvalp,
+yy::parser::token_type yylex (yy::parser::semantic_type *yylvalp,
-                             yy::parser::location_type* yyllocp)
+                              yy::parser::location_type *yyllocp)
 #endif
 {
   typedef yy::parser::location_type location_type;

examples/c/bistromathic/bistromathic.test

@@ -251,29 +251,29 @@ err: Next token is token ) (1.4: )
 err: Shifting token ) (1.4: )
 err: Entering state 20
 err: Stack now 0 2 10 20
-err: Reducing stack by rule 15 (line 151):
+err: Reducing stack by rule XX (line XXX):
 err:    $1 = token ( (1.1: )
 err:    $2 = token error (1.2-3: )
 err:    $3 = token ) (1.4: )
 err: -> $$ = nterm exp (1.1-4: 666)
-err: Entering state 7
+err: Entering state 8
-err: Stack now 0 7
+err: Stack now 0 8
 err: Return for a new token:
 err: Reading a token
 err: Now at end of input.
 err: LAC: initial context established for end of file
-err: LAC: checking lookahead end of file: R2 G8 S19
+err: LAC: checking lookahead end of file: R2 G7 S14
-err: Reducing stack by rule 2 (line 126):
+err: Reducing stack by rule XX (line XXX):
 err:    $1 = nterm exp (1.1-4: 666)
 err: -> $$ = nterm input (1.1-4: )
-err: Entering state 8
+err: Entering state 7
-err: Stack now 0 8
+err: Stack now 0 7
 err: Now at end of input.
 err: Shifting token end of file (1.5: )
 err: LAC: initial context discarded due to shift
-err: Entering state 19
+err: Entering state 14
-err: Stack now 0 8 19
+err: Stack now 0 7 14
-err: Stack now 0 8 19
+err: Stack now 0 7 14
 err: Cleanup: popping token end of file (1.5: )
 err: Cleanup: popping nterm input (1.1-4: )' -p
 

examples/c/lexcalc/local.mk

@@ -31,6 +31,13 @@ endif FLEX_WORKS
 
 %D%/parse.c: $(dependencies)
 
+# Tell Make scan.o depends on parse.h, except that Make sees only
+# parse.c, not parse.h.  We can't use BUILT_SOURCES to this end, since
+# we use the built bison.
+%D%/lexcalc$(DASH)scan.o: %D%/parse.c
+# Likewise, but for Automake before 1.16.
+%D%/examples_c_lexcalc_lexcalc$(DASH)scan.o: %D%/parse.c
+
 EXTRA_DIST += %D%/lexcalc.test
 dist_lexcalc_DATA = %D%/parse.y %D%/scan.l %D%/Makefile %D%/README.md
 CLEANFILES += %D%/parse.[ch] %D%/scan.c %D%/parse.output

examples/d/local.mk

@@ -27,7 +27,7 @@ EXTRA_DIST += %D%/calc.test
 
 %D%/calc.d: %D%/calc.y $(dependencies)
 	$(AM_V_GEN)$(MKDIR_P) %D%
-	$(AM_V_at)$(BISON) $(srcdir)/%D%/calc.y -o $@
+	$(AM_V_at)$(BISON) -o $@ $(srcdir)/%D%/calc.y
 
 %D%/calc: %D%/calc.d
 	$(AM_V_GEN) $(DC) $(DCFLAGS) -of$@ %D%/calc.d

examples/java/calc/local.mk

@@ -27,7 +27,7 @@ EXTRA_DIST += %D%/Calc.test
 
 %D%/Calc.java: %D%/Calc.y $(dependencies)
 	$(AM_V_GEN)$(MKDIR_P) %D%
-	$(AM_V_at)$(BISON) $(srcdir)/%D%/Calc.y -o $@
+	$(AM_V_at)$(BISON) -o $@ $(srcdir)/%D%/Calc.y
 
 %D%/Calc.class: %D%/Calc.java
 	$(AM_V_GEN) $(SHELL) $(top_builddir)/javacomp.sh %D%/Calc.java

examples/java/simple/local.mk

@@ -27,7 +27,7 @@ EXTRA_DIST += %D%/Calc.test
 
 %D%/Calc.java: %D%/Calc.y $(dependencies)
 	$(AM_V_GEN)$(MKDIR_P) %D%
-	$(AM_V_at)$(BISON) $(srcdir)/%D%/Calc.y -o $@
+	$(AM_V_at)$(BISON) -o $@ $(srcdir)/%D%/Calc.y
 
 %D%/Calc.class: %D%/Calc.java
 	$(AM_V_GEN) $(SHELL) $(top_builddir)/javacomp.sh %D%/Calc.java

lib/.gitignore

@@ -192,8 +192,6 @@
 /localcharset.h
 /locale.h
 /locale.in.h
-/localtime-buffer.c
-/localtime-buffer.h
 /lstat.c
 /malloc.c
 /malloca.c
@@ -338,8 +336,11 @@
 /sys_types.in.h
 /sys_wait.in.h
 /sysexits.in.h
+/termios.h
+/termios.in.h
 /textstyle.h
 /textstyle.in.h
+/thread-optim.h
 /time.h
 /time.in.h
 /timespec.c

m4/.gitignore

@@ -97,7 +97,6 @@
 /locale-ja.m4
 /locale-zh.m4
 /locale_h.m4
-/localtime-buffer.m4
 /lock.m4
 /longlong.m4
 /lstat.m4
@@ -117,6 +116,7 @@
 /msvc-inval.m4
 /msvc-nothrow.m4
 /multiarch.m4
+/musl.m4
 /nls.m4
 /nocrash.m4
 /non-recursive-gnulib-prefix-hack.m4
@@ -128,6 +128,7 @@
 /open.m4
 /pathmax.m4
 /perror.m4
+/pid_t.m4
 /pipe2.m4
 /po.m4
 /posix_spawn.m4
@@ -184,6 +185,7 @@
 /strndup.m4
 /strnlen.m4
 /strverscmp.m4
+/sys_ioctl_h.m4
 /sys_resource_h.m4
 /sys_socket_h.m4
 /sys_stat_h.m4
@@ -191,6 +193,7 @@
 /sys_times_h.m4
 /sys_types_h.m4
 /sys_wait_h.m4
+/termios_h.m4
 /threadlib.m4
 /time_h.m4
 /timespec.m4

src/counterexample.c

@@ -113,13 +113,8 @@ free_counterexample (counterexample *cex)
   free (cex);
 }
 
-static int max (int a, int b)
-{
-  return a < b ? b : a;
-}
-
 static void
-print_counterexample (const counterexample *cex, FILE *out, const char *prefix)
+counterexample_print (const counterexample *cex, FILE *out, const char *prefix)
 {
   const bool flat = getenv ("YYFLAT");
   const char *example1_label
@@ -131,8 +126,8 @@ print_counterexample (const counterexample *cex, FILE *out, const char *prefix)
   const char *deriv2_label
     = cex->shift_reduce ? _("Reduce derivation") : _("Second reduce derivation");
   const int width =
-    max (max (mbswidth (example1_label, 0), mbswidth (example2_label, 0)),
+    max_int (max_int (mbswidth (example1_label, 0), mbswidth (example2_label, 0)),
-         max (mbswidth (deriv1_label, 0),   mbswidth (deriv2_label, 0)));
+             max_int (mbswidth (deriv1_label, 0),   mbswidth (deriv2_label, 0)));
   if (flat)
     fprintf (out, "  %s%s%*s ", prefix,
              example1_label, width - mbswidth (example1_label, 0), "");
@@ -526,7 +521,7 @@ nonunifying_shift_path (state_item_list reduce_path, state_item *shift_conflict)
       for (gl_list_iterator_t it = gl_list_iterator (result);
            state_item_list_next (&it, &sip);
            )
-        print_state_item (sip, stderr, "");
+        state_item_print (sip, stderr, "");
     }
   return result;
 }
@@ -717,10 +712,10 @@ ssb_equals (const search_state_bundle *s1, const search_state_bundle *s2)
 typedef gl_list_t ssb_list;
 
 static size_t
-visited_hasher (const search_state *ss, size_t maximum)
+visited_hasher (const search_state *ss, size_t max)
 {
-  return (parse_state_hasher (ss->states[0], maximum)
+  return (parse_state_hasher (ss->states[0], max)
-          + parse_state_hasher (ss->states[1], maximum)) % maximum;
+          + parse_state_hasher (ss->states[1], max)) % max;
 }
 
 static bool
@@ -1267,7 +1262,7 @@ counterexample_report (state_item_number itm1, state_item_number itm2,
     : example_from_path (shift_reduce, itm2, shortest_path, next_sym);
 
   gl_list_free (shortest_path);
-  print_counterexample (cex, out, prefix);
+  counterexample_print (cex, out, prefix);
   free_counterexample (cex);
 }
 
@@ -1290,8 +1285,8 @@ counterexample_report_shift_reduce (state_item_number itm1, state_item_number it
   // In the report, print the items.
   if (out != stderr || trace_flag & trace_cex)
     {
-      print_state_item (&state_items[itm1], out, prefix);
+      state_item_print (&state_items[itm1], out, prefix);
-      print_state_item (&state_items[itm2], out, prefix);
+      state_item_print (&state_items[itm2], out, prefix);
     }
   counterexample_report (itm1, itm2, next_sym, true, out, prefix);
 }
@@ -1334,8 +1329,8 @@ counterexample_report_reduce_reduce (state_item_number itm1, state_item_number i
   // In the report, print the items.
   if (out != stderr || trace_flag & trace_cex)
     {
-      print_state_item (&state_items[itm1], out, prefix);
+      state_item_print (&state_items[itm1], out, prefix);
-      print_state_item (&state_items[itm2], out, prefix);
+      state_item_print (&state_items[itm2], out, prefix);
     }
   counterexample_report (itm1, itm2, bitset_first (conflict_syms),
                          false, out, prefix);

src/derivation.c

@@ -76,12 +76,12 @@ void derivation_list_free (derivation_list dl)
 derivation *
 derivation_new (symbol_number sym, derivation_list children)
 {
-  derivation *deriv = xmalloc (sizeof (derivation));
+  derivation *res = xmalloc (sizeof *res);
-  deriv->sym = sym;
+  res->sym = sym;
-  deriv->children = children;
+  res->children = children;
-  deriv->reference_count = 0;
+  res->reference_count = 0;
-  deriv->color = -1;
+  res->color = -1;
-  return deriv;
+  return res;
 }
 
 void
@@ -135,12 +135,6 @@ derivation_size (const derivation *deriv)
 }
 
 
-static int
-max (int a, int b)
-{
-  return a < b ? b : a;
-}
-
 // Longest distance from root to leaf.
 static int
 derivation_depth (const derivation *deriv)
@@ -154,7 +148,7 @@ derivation_depth (const derivation *deriv)
       for (gl_list_iterator_t it = gl_list_iterator (deriv->children);
            derivation_list_next (&it, &child);
            )
-        res = max (res, derivation_depth (child));
+        res = max_int (res, derivation_depth (child));
       return res + 1;
     }
   else
@@ -237,7 +231,7 @@ derivation_width (const derivation *deriv)
           // No separator at the beginning.
           children_width -= derivation_separator_width;
         }
-      return max (self_width, children_width);
+      return max_int (self_width, children_width);
     }
   else if (deriv == &d_dot)
     {

src/flex-scanner.h

@@ -112,7 +112,15 @@ static struct obstack obstack_for_string;
 # define STRING_1GROW(Char)                     \
   obstack_1grow (&obstack_for_string, Char)
 
-# define STRING_FREE()                                  \
+# ifdef NDEBUG
+#  define STRING_FREE()                                 \
   obstack_free (&obstack_for_string, last_string)
+# else
+#  define STRING_FREE()                                  \
+  do {                                                   \
+    obstack_free (&obstack_for_string, last_string);     \
+    last_string = NULL;                                  \
+  } while (0)
+# endif
 
 #endif

src/ielr.c

@@ -423,7 +423,7 @@ ielr_item_has_lookahead (state *s, symbol_number lhs, size_t item,
              check all predecessors' goto follows for the LHS.  */
           if (item_number_is_rule_number (ritem[s->items[item] - 2]))
             {
-              aver (lhs != accept->content->number);
+              aver (lhs != acceptsymbol->content->number);
               for (state **predecessor = predecessors[s->number];
                    *predecessor;
                    ++predecessor)

src/local.mk

@@ -143,7 +143,6 @@ src_bison_LDADD =                               \
   $(LIB_SETLOCALE_NULL)                         \
   $(LIBICONV)                                   \
   $(LIBINTL)                                    \
-  $(LIBREADLINE)                                \
   $(LIBTEXTSTYLE)
 
 

src/location.c

@@ -40,18 +40,6 @@
 
 location const empty_loc = EMPTY_LOCATION_INIT;
 
-static int
-min_int (int a, int b)
-{
-  return a < b ? a : b;
-}
-
-static int
-max_int (int a, int b)
-{
-  return a >= b ? a : b;
-}
-
 /* The terminal width.  Not less than 40.  */
 static int
 columns (void)
@@ -167,7 +155,9 @@ int
 location_print (location loc, FILE *out)
 {
   int res = 0;
-  if (trace_flag & trace_locations)
+  if (location_empty (loc))
+    res += fprintf (out, "(empty location)");
+  else if (trace_flag & trace_locations)
     {
       res += boundary_print (&loc.start, out);
       res += fprintf (out, "-");

src/lssi.c

@@ -256,7 +256,7 @@ shortest_path_from_start (state_item_number target, symbol_number next_sym)
       gl_list_iterator_t it = gl_list_iterator (res);
       const void *sip;
       while (gl_list_iterator_next (&it, &sip, NULL))
-        print_state_item ((state_item *) sip, stdout, "");
+        state_item_print ((state_item *) sip, stdout, "");
     }
   return res;
 }

src/output.c

@@ -249,7 +249,7 @@ prepare_symbol_names (char const *muscle_name)
       if (i)
         obstack_1grow (&format_obstack, ' ');
       if (translatable)
-        obstack_sgrow (&format_obstack, "]b4_symbol_translate([");
+        obstack_sgrow (&format_obstack, "]b4_symbol_translate""([");
       obstack_escape (&format_obstack, cp);
       if (translatable)
         obstack_sgrow (&format_obstack, "])[");
@@ -554,7 +554,7 @@ prepare_symbol_definitions (void)
   /* Map "orig NUM" to new numbers.  See data/README.  */
   for (symbol_number i = ntokens; i < nsyms + nuseless_nonterminals; ++i)
     {
-      obstack_printf (&format_obstack, "symbol(orig %d, number)", i);
+      obstack_printf (&format_obstack, "symbol""(orig %d, number)", i);
       const char *key = obstack_finish0 (&format_obstack);
       MUSCLE_INSERT_INT (key, nterm_map ? nterm_map[i - ntokens] : i);
     }
@@ -565,12 +565,12 @@ prepare_symbol_definitions (void)
       const char *key;
 
 #define SET_KEY(Entry)                                          \
-      obstack_printf (&format_obstack, "symbol(%d, %s)",        \
+      obstack_printf (&format_obstack, "symbol""(%d, %s)",        \
                       i, Entry);                                \
       key = obstack_finish0 (&format_obstack);
 
 #define SET_KEY2(Entry, Suffix)                                 \
-      obstack_printf (&format_obstack, "symbol(%d, %s_%s)",     \
+      obstack_printf (&format_obstack, "symbol""(%d, %s_%s)",     \
                       i, Entry, Suffix);                        \
       key = obstack_finish0 (&format_obstack);
 

src/parse-gram.c

@@ -1,4 +1,4 @@
-/* A Bison parser, made by GNU Bison 3.6.90.  */
+/* A Bison parser, made by GNU Bison 3.7.14-eb26-dirty.  */
 
 /* Bison implementation for Yacc-like parsers in C
 
@@ -49,7 +49,7 @@
 #define YYBISON 1
 
 /* Bison version.  */
-#define YYBISON_VERSION "3.6.90"
+#define YYBISON_VERSION "3.7.14-eb26-dirty"
 
 /* Skeleton name.  */
 #define YYSKELETON_NAME "yacc.c"
@@ -149,7 +149,7 @@ enum yysymbol_kind_t
   YYSYMBOL_BRACED_CODE = 41,               /* "{...}"  */
   YYSYMBOL_BRACED_PREDICATE = 42,          /* "%?{...}"  */
   YYSYMBOL_BRACKETED_ID = 43,              /* "[identifier]"  */
-  YYSYMBOL_CHAR = 44,                      /* "character literal"  */
+  YYSYMBOL_CHAR_LITERAL = 44,              /* "character literal"  */
   YYSYMBOL_COLON = 45,                     /* ":"  */
   YYSYMBOL_EPILOGUE = 46,                  /* "epilogue"  */
   YYSYMBOL_EQUAL = 47,                     /* "="  */
@@ -162,7 +162,7 @@ enum yysymbol_kind_t
   YYSYMBOL_TAG = 54,                       /* "<tag>"  */
   YYSYMBOL_TAG_ANY = 55,                   /* "<*>"  */
   YYSYMBOL_TAG_NONE = 56,                  /* "<>"  */
-  YYSYMBOL_INT = 57,                       /* "integer literal"  */
+  YYSYMBOL_INT_LITERAL = 57,               /* "integer literal"  */
   YYSYMBOL_PERCENT_PARAM = 58,             /* "%param"  */
   YYSYMBOL_PERCENT_UNION = 59,             /* "%union"  */
   YYSYMBOL_PERCENT_EMPTY = 60,             /* "%empty"  */
@@ -1115,8 +1115,8 @@ tron (yyo);
          { fprintf (yyo, "[%s]", ((*yyvaluep).BRACKETED_ID)); }
         break;
 
-    case YYSYMBOL_CHAR: /* "character literal"  */
+    case YYSYMBOL_CHAR_LITERAL: /* "character literal"  */
-         { fputs (char_name (((*yyvaluep).CHAR)), yyo); }
+         { fputs (char_name (((*yyvaluep).CHAR_LITERAL)), yyo); }
         break;
 
     case YYSYMBOL_EPILOGUE: /* "epilogue"  */
@@ -1139,8 +1139,8 @@ tron (yyo);
          { fprintf (yyo, "<%s>", ((*yyvaluep).TAG)); }
         break;
 
-    case YYSYMBOL_INT: /* "integer literal"  */
+    case YYSYMBOL_INT_LITERAL: /* "integer literal"  */
-         { fprintf (yyo, "%d", ((*yyvaluep).INT)); }
+         { fprintf (yyo, "%d", ((*yyvaluep).INT_LITERAL)); }
         break;
 
     case YYSYMBOL_PERCENT_PARAM: /* "%param"  */
@@ -2087,11 +2087,11 @@ yyreduce:
     break;
 
   case 12: /* prologue_declaration: "%expect" "integer literal"  */
-                                   { expected_sr_conflicts = (yyvsp[0].INT); }
+                                   { expected_sr_conflicts = (yyvsp[0].INT_LITERAL); }
     break;
 
   case 13: /* prologue_declaration: "%expect-rr" "integer literal"  */
-                                   { expected_rr_conflicts = (yyvsp[0].INT); }
+                                   { expected_rr_conflicts = (yyvsp[0].INT_LITERAL); }
     break;
 
   case 14: /* prologue_declaration: "%file-prefix" "string"  */
@@ -2339,13 +2339,13 @@ yyreduce:
 
   case 67: /* token_decls: "<tag>" token_decl.1  */
     {
-      (yyval.token_decls) = symbol_list_type_set ((yyvsp[0].yykind_80), (yyvsp[-1].TAG), (yylsp[-1]));
+      (yyval.token_decls) = symbol_list_type_set ((yyvsp[0].yykind_80), (yyvsp[-1].TAG));
     }
     break;
 
   case 68: /* token_decls: token_decls "<tag>" token_decl.1  */
     {
-      (yyval.token_decls) = symbol_list_append ((yyvsp[-2].token_decls), symbol_list_type_set ((yyvsp[0].yykind_80), (yyvsp[-1].TAG), (yylsp[-1])));
+      (yyval.token_decls) = symbol_list_append ((yyvsp[-2].token_decls), symbol_list_type_set ((yyvsp[0].yykind_80), (yyvsp[-1].TAG)));
     }
     break;
 
@@ -2396,13 +2396,13 @@ yyreduce:
 
   case 78: /* token_decls_for_prec: "<tag>" token_decl_for_prec.1  */
     {
-      (yyval.token_decls_for_prec) = symbol_list_type_set ((yyvsp[0].yykind_85), (yyvsp[-1].TAG), (yylsp[-1]));
+      (yyval.token_decls_for_prec) = symbol_list_type_set ((yyvsp[0].yykind_85), (yyvsp[-1].TAG));
     }
     break;
 
   case 79: /* token_decls_for_prec: token_decls_for_prec "<tag>" token_decl_for_prec.1  */
     {
-      (yyval.token_decls_for_prec) = symbol_list_append ((yyvsp[-2].token_decls_for_prec), symbol_list_type_set ((yyvsp[0].yykind_85), (yyvsp[-1].TAG), (yylsp[-1])));
+      (yyval.token_decls_for_prec) = symbol_list_append ((yyvsp[-2].token_decls_for_prec), symbol_list_type_set ((yyvsp[0].yykind_85), (yyvsp[-1].TAG)));
     }
     break;
 
@@ -2431,13 +2431,13 @@ yyreduce:
 
   case 85: /* symbol_decls: "<tag>" symbol_decl.1  */
     {
-      (yyval.symbol_decls) = symbol_list_type_set ((yyvsp[0].yykind_88), (yyvsp[-1].TAG), (yylsp[-1]));
+      (yyval.symbol_decls) = symbol_list_type_set ((yyvsp[0].yykind_88), (yyvsp[-1].TAG));
     }
     break;
 
   case 86: /* symbol_decls: symbol_decls "<tag>" symbol_decl.1  */
     {
-      (yyval.symbol_decls) = symbol_list_append ((yyvsp[-2].symbol_decls), symbol_list_type_set ((yyvsp[0].yykind_88), (yyvsp[-1].TAG), (yylsp[-1])));
+      (yyval.symbol_decls) = symbol_list_append ((yyvsp[-2].symbol_decls), symbol_list_type_set ((yyvsp[0].yykind_88), (yyvsp[-1].TAG)));
     }
     break;
 
@@ -2506,7 +2506,7 @@ yyreduce:
     break;
 
   case 105: /* rhs: rhs "%dprec" "integer literal"  */
-    { grammar_current_rule_dprec_set ((yyvsp[0].INT), (yylsp[0])); }
+    { grammar_current_rule_dprec_set ((yyvsp[0].INT_LITERAL), (yylsp[0])); }
     break;
 
   case 106: /* rhs: rhs "%merge" "<tag>"  */
@@ -2514,11 +2514,11 @@ yyreduce:
     break;
 
   case 107: /* rhs: rhs "%expect" "integer literal"  */
-    { grammar_current_rule_expect_sr ((yyvsp[0].INT), (yylsp[0])); }
+    { grammar_current_rule_expect_sr ((yyvsp[0].INT_LITERAL), (yylsp[0])); }
     break;
 
   case 108: /* rhs: rhs "%expect-rr" "integer literal"  */
-    { grammar_current_rule_expect_rr ((yyvsp[0].INT), (yylsp[0])); }
+    { grammar_current_rule_expect_rr ((yyvsp[0].INT_LITERAL), (yylsp[0])); }
     break;
 
   case 109: /* named_ref.opt: %empty  */
@@ -2566,9 +2566,9 @@ yyreduce:
           location loc = muscle_percent_define_get_loc (var);
           subcomplain (&loc, complaint, _("definition of %s"), var);
         }
-      (yyval.id) = symbol_get (char_name ((yyvsp[0].CHAR)), (yylsp[0]));
+      (yyval.id) = symbol_get (char_name ((yyvsp[0].CHAR_LITERAL)), (yylsp[0]));
       symbol_class_set ((yyval.id), token_sym, (yylsp[0]), false);
-      symbol_code_set ((yyval.id), (yyvsp[0].CHAR), (yylsp[0]));
+      symbol_code_set ((yyval.id), (yyvsp[0].CHAR_LITERAL), (yylsp[0]));
     }
     break;
 
@@ -3147,8 +3147,7 @@ char_name (char c)
     }
 }
 
-static
+static void
-void
 current_lhs (symbol *sym, location loc, named_ref *ref)
 {
   current_lhs_symbol = sym;

src/parse-gram.h

@@ -1,4 +1,4 @@
-/* A Bison parser, made by GNU Bison 3.6.90.  */
+/* A Bison parser, made by GNU Bison 3.7.14-eb26-dirty.  */
 
 /* Bison interface for Yacc-like parsers in C
 
@@ -123,7 +123,7 @@ extern int gram_debug;
     BRACED_CODE = 41,              /* "{...}"  */
     BRACED_PREDICATE = 42,         /* "%?{...}"  */
     BRACKETED_ID = 43,             /* "[identifier]"  */
-    CHAR = 44,                     /* "character literal"  */
+    CHAR_LITERAL = 44,             /* "character literal"  */
     COLON = 45,                    /* ":"  */
     EPILOGUE = 46,                 /* "epilogue"  */
     EQUAL = 47,                    /* "="  */
@@ -136,7 +136,7 @@ extern int gram_debug;
     TAG = 54,                      /* "<tag>"  */
     TAG_ANY = 55,                  /* "<*>"  */
     TAG_NONE = 56,                 /* "<>"  */
-    INT = 57,                      /* "integer literal"  */
+    INT_LITERAL = 57,              /* "integer literal"  */
     PERCENT_PARAM = 58,            /* "%param"  */
     PERCENT_UNION = 59,            /* "%union"  */
     PERCENT_EMPTY = 60             /* "%empty"  */
@@ -156,7 +156,7 @@ union GRAM_STYPE
   char* EPILOGUE;                          /* "epilogue"  */
   char* PROLOGUE;                          /* "%{...%}"  */
   code_props_type code_props_type;         /* code_props_type  */
-  int INT;                                 /* "integer literal"  */
+  int INT_LITERAL;                         /* "integer literal"  */
   int yykind_82;                           /* int.opt  */
   named_ref* yykind_95;                    /* named_ref.opt  */
   param_type PERCENT_PARAM;                /* "%param"  */
@@ -188,7 +188,7 @@ union GRAM_STYPE
   uniqstr yykind_74;                       /* tag.opt  */
   uniqstr tag;                             /* tag  */
   uniqstr variable;                        /* variable  */
-  unsigned char CHAR;                      /* "character literal"  */
+  unsigned char CHAR_LITERAL;              /* "character literal"  */
   value_type value;                        /* value  */
 
 

src/parse-gram.y

@@ -214,7 +214,7 @@
   BRACED_CODE       "{...}"
   BRACED_PREDICATE  "%?{...}"
   BRACKETED_ID      _("[identifier]")
-  CHAR              _("character literal")
+  CHAR_LITERAL      _("character literal")
   COLON             ":"
   EPILOGUE          _("epilogue")
   EQUAL             "="
@@ -232,7 +232,7 @@
 %code pre-printer  {tron (yyo);}
 %code post-printer {troff (yyo);}
 
-%type <unsigned char> CHAR
+%type <unsigned char> CHAR_LITERAL
 %printer { fputs (char_name ($$), yyo); } <unsigned char>
 
 %type <char*> "{...}" "%?{...}" "%{...%}" EPILOGUE STRING TSTRING
@@ -249,7 +249,7 @@
 %printer { fprintf (yyo, "%%%s", $$); } PERCENT_FLAG
 %printer { fprintf (yyo, "<%s>", $$); } TAG tag
 
-%token <int> INT _("integer literal")
+%token <int> INT_LITERAL _("integer literal")
 %printer { fprintf (yyo, "%d", $$); } <int>
 
 %type <symbol*> id id_colon string_as_id symbol token_decl token_decl_for_prec
@@ -342,8 +342,8 @@ prologue_declaration:
 | "%defines"                       { defines_flag = true; }
 | "%defines" STRING                { handle_defines ($2); }
 | "%error-verbose"                 { handle_error_verbose (&@$, $1); }
-| "%expect" INT                    { expected_sr_conflicts = $2; }
+| "%expect" INT_LITERAL            { expected_sr_conflicts = $2; }
-| "%expect-rr" INT                 { expected_rr_conflicts = $2; }
+| "%expect-rr" INT_LITERAL         { expected_rr_conflicts = $2; }
 | "%file-prefix" STRING            { handle_file_prefix (&@$, &@1, $1, $2); }
 | "%glr-parser"
     {
@@ -532,11 +532,11 @@ token_decls:
     }
 | TAG token_decl.1[syms]
     {
-      $$ = symbol_list_type_set ($syms, $TAG, @TAG);
+      $$ = symbol_list_type_set ($syms, $TAG);
     }
 | token_decls TAG token_decl.1[syms]
     {
-      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG, @TAG));
+      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG));
     }
 ;
 
@@ -561,7 +561,7 @@ token_decl:
 %type <int> int.opt;
 int.opt:
   %empty  { $$ = -1; }
-| INT
+| INT_LITERAL
 ;
 
 %type <symbol*> alias;
@@ -592,11 +592,11 @@ token_decls_for_prec:
     }
 | TAG token_decl_for_prec.1[syms]
     {
-      $$ = symbol_list_type_set ($syms, $TAG, @TAG);
+      $$ = symbol_list_type_set ($syms, $TAG);
     }
 | token_decls_for_prec TAG token_decl_for_prec.1[syms]
     {
-      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG, @TAG));
+      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG));
     }
 ;
 
@@ -632,11 +632,11 @@ symbol_decls:
     }
 | TAG symbol_decl.1[syms]
     {
-      $$ = symbol_list_type_set ($syms, $TAG, @TAG);
+      $$ = symbol_list_type_set ($syms, $TAG);
     }
 | symbol_decls TAG symbol_decl.1[syms]
     {
-      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG, @TAG));
+      $$ = symbol_list_append ($1, symbol_list_type_set ($syms, $TAG));
     }
 ;
 
@@ -703,13 +703,13 @@ rhs:
     { grammar_current_rule_empty_set (@2); }
 | rhs "%prec" symbol
     { grammar_current_rule_prec_set ($3, @3); }
-| rhs "%dprec" INT
+| rhs "%dprec" INT_LITERAL
     { grammar_current_rule_dprec_set ($3, @3); }
 | rhs "%merge" TAG
     { grammar_current_rule_merge_set ($3, @3); }
-| rhs "%expect" INT
+| rhs "%expect" INT_LITERAL
     { grammar_current_rule_expect_sr ($3, @3); }
-| rhs "%expect-rr" INT
+| rhs "%expect-rr" INT_LITERAL
     { grammar_current_rule_expect_rr ($3, @3); }
 ;
 
@@ -765,7 +765,7 @@ value:
 id:
   ID
     { $$ = symbol_from_uniqstr ($1, @1); }
-| CHAR
+| CHAR_LITERAL
     {
       const char *var = "api.token.raw";
       if (current_class == nterm_sym)
@@ -1158,8 +1158,7 @@ char_name (char c)
     }
 }
 
-static
+static void
-void
 current_lhs (symbol *sym, location loc, named_ref *ref)
 {
   current_lhs_symbol = sym;

src/parse-simulation.c

@@ -28,19 +28,19 @@
 #include "lssi.h"
 #include "nullable.h"
 
-typedef struct parse_state
+struct parse_state
 {
-  // path of state-items the parser has traversed
+  // Path of state-items the parser has traversed.
   struct si_chunk
   {
-    // elements newly added in this chunk
+    // Elements newly added in this chunk.
     state_item_list contents;
-    // properties of the linked list this chunk represents
+    // Properties of the linked list this chunk represents.
     const state_item *head_elt;
     const state_item *tail_elt;
     size_t total_size;
   } state_items;
-  // list of derivations of the symbols
+  // List of derivations of the symbols.
   struct deriv_chunk
   {
     derivation_list contents;
@@ -50,18 +50,15 @@ typedef struct parse_state
   } derivs;
   struct parse_state *parent;
   int reference_count;
-  // incremented during productions,
+  // Incremented during productions, decremented during reductions.
-  // decremented during reductions
   int depth;
-  // whether the contents of the chunks should be
+  // Whether the contents of the chunks should be prepended or
-  // prepended or appended to the list the chunks
+  // appended to the list the chunks represent.
-  // represent
   bool prepend;
-  // causes chunk contents to be freed when the
+  // Causes chunk contents to be freed when the reference count is
-  // reference count is one. Used when only the chunk metadata
+  // one. Used when only the chunk metadata will be needed.
-  // will be needed.
   bool free_contents_early;
-} parse_state;
+};
 
 
 static void
@@ -438,9 +435,8 @@ simulate_transition (parse_state *ps)
   // symbols into account.
   parse_state_list result = parse_state_list_new ();
   state_item_number si_next = si->trans;
-  // check for disabled transition, shouldn't happen
+  // Check for disabled transition, shouldn't happen as any
-  // as any state_items that lead to these should be
+  // state_items that lead to these should be disabled.
-  // disabled.
   if (si_next < 0)
     return result;
   parse_state *next_ps = copy_parse_state (false, ps);
@@ -594,8 +590,8 @@ print_parse_state (parse_state *ps)
   FILE *out = stderr;
   fprintf (out, "(size %zu depth %d rc %d)\n",
           ps->state_items.total_size, ps->depth, ps->reference_count);
-  print_state_item (ps->state_items.head_elt, out, "");
+  state_item_print (ps->state_items.head_elt, out, "");
-  print_state_item (ps->state_items.tail_elt, out, "");
+  state_item_print (ps->state_items.tail_elt, out, "");
   if (ps->derivs.total_size > 0)
     derivation_print (ps->derivs.head_elt, out, "");
   putc ('\n', out);

src/reader.c

@@ -406,8 +406,8 @@ grammar_midrule_action (void)
      action.  Create the MIDRULE.  */
   location dummy_loc = current_rule->action_props.location;
   symbol *dummy = dummy_symbol_get (dummy_loc);
-  symbol_type_set(dummy,
+  symbol_type_set (dummy,
-                  current_rule->action_props.type, current_rule->action_props.location);
+                   current_rule->action_props.type, current_rule->action_props.location);
   symbol_list *midrule = symbol_list_sym_new (dummy, dummy_loc);
 
   /* Remember named_ref of previous action. */
@@ -804,7 +804,7 @@ check_and_convert_grammar (void)
 
      $accept: %start $end.  */
   {
-    symbol_list *p = symbol_list_sym_new (accept, empty_loc);
+    symbol_list *p = symbol_list_sym_new (acceptsymbol, empty_loc);
     p->rhs_loc = grammar->rhs_loc;
     p->next = symbol_list_sym_new (startsymbol, empty_loc);
     p->next->next = symbol_list_sym_new (eoftoken, empty_loc);
@@ -815,8 +815,11 @@ check_and_convert_grammar (void)
     grammar = p;
   }
 
-  aver (nsyms <= SYMBOL_NUMBER_MAXIMUM);
+  if (SYMBOL_NUMBER_MAXIMUM - nnterms < ntokens)
-  aver (nsyms == ntokens + nnterms);
+    complain (NULL, fatal, "too many symbols in input grammar (limit is %d)",
+              SYMBOL_NUMBER_MAXIMUM);
+
+  nsyms = ntokens + nnterms;
 
   /* Assign the symbols their symbol numbers.  */
   symbols_pack ();

src/reduce.c

@@ -160,9 +160,9 @@ inaccessable_symbols (void)
   bitset Pp = bitset_create (nrules, BITSET_FIXED);
 
   /* If the start symbol isn't useful, then nothing will be useful. */
-  if (bitset_test (N, accept->content->number - ntokens))
+  if (bitset_test (N, acceptsymbol->content->number - ntokens))
     {
-      bitset_set (V, accept->content->number);
+      bitset_set (V, acceptsymbol->content->number);
 
       while (1)
         {
@@ -301,7 +301,7 @@ nonterminals_reduce (void)
       for (item_number *rhsp = rules[r].rhs; 0 <= *rhsp; ++rhsp)
         if (ISVAR (*rhsp))
           *rhsp = symbol_number_as_item_number (nterm_map[*rhsp - ntokens]);
-    accept->content->number = nterm_map[accept->content->number - ntokens];
+    acceptsymbol->content->number = nterm_map[acceptsymbol->content->number - ntokens];
   }
 
   nsyms -= nuseless_nonterminals;
@@ -381,7 +381,7 @@ reduce_grammar (void)
     {
       reduce_print ();
 
-      if (!bitset_test (N, accept->content->number - ntokens))
+      if (!bitset_test (N, acceptsymbol->content->number - ntokens))
         complain (&startsymbol_loc, fatal,
                   _("start symbol %s does not derive any sentence"),
                   startsymbol->tag);

src/scan-gram.l

@@ -322,8 +322,8 @@ eqopt    ({sp}=)?
     BEGIN SC_AFTER_IDENTIFIER;
   }
 
-  {int}      RETURN_VALUE (INT, scan_integer (yytext, 10, *loc));
+  {int}      RETURN_VALUE (INT_LITERAL, scan_integer (yytext, 10, *loc));
-  {xint}     RETURN_VALUE (INT, scan_integer (yytext, 16, *loc));
+  {xint}     RETURN_VALUE (INT_LITERAL, scan_integer (yytext, 16, *loc));
 
   /* Identifiers may not start with a digit.  Yet, don't silently
      accept "1FOO" as "1 FOO".  */
@@ -403,6 +403,7 @@ eqopt    ({sp}=)?
 {
   \0         {
     complain (loc, complaint, _("invalid null character"));
+    STRING_FINISH ();
     STRING_FREE ();
     return GRAM_error;
   }
@@ -566,6 +567,8 @@ eqopt    ({sp}=)?
               _("POSIX Yacc does not support string literals"));
     RETURN_VALUE (STRING, last_string);
   }
+  <<EOF>>   unexpected_eof (token_start, "\"");
+  "\n"      unexpected_newline (token_start, "\"");
 }
 
 <SC_ESCAPED_TSTRING>
@@ -579,13 +582,10 @@ eqopt    ({sp}=)?
               _("POSIX Yacc does not support string literals"));
     RETURN_VALUE (TSTRING, last_string);
   }
+  <<EOF>>   unexpected_eof (token_start, "\")");
+  "\n"      unexpected_newline (token_start, "\")");
 }
 
-<SC_ESCAPED_STRING,SC_ESCAPED_TSTRING>
-{
-  <<EOF>>   unexpected_eof (token_start, "\"");
-  "\n"      unexpected_newline (token_start, "\"");
-}
 
 
   /*----------------------------------------------------------.
@@ -599,7 +599,6 @@ eqopt    ({sp}=)?
     STRING_FINISH ();
     BEGIN INITIAL;
     loc->start = token_start;
-    val->CHAR = last_string[0];
 
     if (last_string[0] == '\0')
       {
@@ -615,8 +614,9 @@ eqopt    ({sp}=)?
       }
     else
       {
+        val->CHAR_LITERAL = last_string[0];
         STRING_FREE ();
-        return CHAR;
+        return CHAR_LITERAL;
       }
   }
   {eol}     unexpected_newline (token_start, "'");
@@ -691,6 +691,15 @@ eqopt    ({sp}=)?
               p);
     STRING_1GROW ('?');
   }
+
+  "\\"             {
+    // None of the other rules matched: the last character of this
+    // file is "\".  But Flex does not support "\\<<EOF>>".
+    unexpected_eof (token_start,
+                    YY_START == SC_ESCAPED_CHARACTER ? "?'"
+                    : YY_START == SC_ESCAPED_STRING ? "?\""
+                    : "?\")");
+  }
 }
 
   /*--------------------------------------------.
@@ -933,9 +942,9 @@ convert_ucn_to_byte (char const *ucn)
 }
 
 
-/*---------------------------------------------------------------------.
+/*----------------------------------------------------------------------------.
-| Handle '#line INT( "FILE")?\n'.  ARGS has already skipped '#line '.  |
+| Handle '#line INT_LITERAL( "FILE")?\n'.  ARGS has already skipped '#line '. |
-`---------------------------------------------------------------------*/
+`----------------------------------------------------------------------------*/
 
 static void
 handle_syncline (char *args, location loc)

src/state-item.c

@@ -475,7 +475,7 @@ prune_disabled_paths (void)
 }
 
 void
-print_state_item (const state_item *si, FILE *out, const char *prefix)
+state_item_print (const state_item *si, FILE *out, const char *prefix)
 {
   fputs (prefix, out);
   item_print (si->item, NULL, out);
@@ -506,7 +506,7 @@ state_items_report (void)
           if (si->trans >= 0)
             {
               fputs ("    -> ", stdout);
-              print_state_item (&state_items[si->trans], stdout, "");
+              state_item_print (&state_items[si->trans], stdout, "");
             }
 
           bitset sets[2] = { si->prods, si->revs };
@@ -521,7 +521,7 @@ state_items_report (void)
                   BITSET_FOR_EACH (biter, b, sin, 0)
                     {
                       fputs (txt[seti], stdout);
-                      print_state_item (&state_items[sin], stdout, "");
+                      state_item_print (&state_items[sin], stdout, "");
                     }
                 }
             }

src/state-item.h

@@ -90,9 +90,10 @@ state_item_index_lookup (state_number s, state_item_number off)
 }
 
 void state_items_init (void);
-void print_state_item (const state_item *si, FILE *out, const char *prefix);
 void state_items_free (void);
 
+void state_item_print (const state_item *si, FILE *out, const char *prefix);
+
 bool production_allowed (const state_item *si, const state_item *next);
 
 // Iterating on a state_item_list.

src/symlist.c

@@ -83,10 +83,10 @@ symbol_list_type_new (uniqstr type_name, location loc)
 
 
 symbol_list *
-symbol_list_type_set (symbol_list *syms, uniqstr type_name, location loc)
+symbol_list_type_set (symbol_list *syms, uniqstr type_name)
 {
   for (symbol_list *l = syms; l; l = l->next)
-    symbol_type_set (l->content.sym, type_name, loc);
+    symbol_type_set (l->content.sym, type_name, l->sym_loc);
   return syms;
 }
 

src/symlist.h

@@ -110,8 +110,7 @@ symbol_list *symbol_list_type_new (uniqstr type_name, location loc);
 
 /** Assign the type \c type_name to all the members of \c syms.
  ** \returns \c syms */
-symbol_list *symbol_list_type_set (symbol_list *syms,
+symbol_list *symbol_list_type_set (symbol_list *syms, uniqstr type_name);
-                                   uniqstr type_name, location loc);
 
 /** Print this list.
 

src/symtab.c

@@ -59,7 +59,7 @@ static semantic_type **semantic_types_sorted = NULL;
 symbol *errtoken = NULL;
 symbol *undeftoken = NULL;
 symbol *eoftoken = NULL;
-symbol *accept = NULL;
+symbol *acceptsymbol = NULL;
 symbol *startsymbol = NULL;
 location startsymbol_loc;
 
@@ -137,11 +137,6 @@ symbol_new (uniqstr tag, location loc)
   res->alias = NULL;
   res->content = sym_content_new (res);
   res->is_alias = false;
-
-  if (nsyms == SYMBOL_NUMBER_MAXIMUM)
-    complain (NULL, fatal, _("too many symbols in input grammar (limit is %d)"),
-              SYMBOL_NUMBER_MAXIMUM);
-  nsyms++;
   return res;
 }
 
@@ -182,11 +177,11 @@ symbol_free (void *ptr)
 */
 
 static void
-symbols_sort (symbol **first, symbol **second)
+symbols_sort (const symbol **first, const symbol **second)
 {
   if (0 < location_cmp ((*first)->location, (*second)->location))
     {
-      symbol* tmp = *first;
+      const symbol* tmp = *first;
       *first = *second;
       *second = tmp;
     }
@@ -243,7 +238,11 @@ semantic_type_new (uniqstr tag, const location *loc)
 | Print a symbol.  |
 `-----------------*/
 
-#define SYMBOL_ATTR_PRINT(Attr)                         \
+#define SYMBOL_INT_ATTR_PRINT(Attr)                     \
+  if (s->content)                                       \
+    fprintf (f, " %s = %d", #Attr, s->content->Attr)
+
+#define SYMBOL_STR_ATTR_PRINT(Attr)                     \
   if (s->content && s->content->Attr)                   \
     fprintf (f, " %s { %s }", #Attr, s->content->Attr)
 
@@ -264,7 +263,11 @@ symbol_print (symbol const *s, FILE *f)
                : c == nterm_sym    ? "nterm"
                : NULL, /* abort.  */
                s->tag);
-      SYMBOL_ATTR_PRINT (type_name);
+      putc (' ', f);
+      location_print (s->location, f);
+      SYMBOL_INT_ATTR_PRINT (code);
+      SYMBOL_INT_ATTR_PRINT (number);
+      SYMBOL_STR_ATTR_PRINT (type_name);
       SYMBOL_CODE_PRINT (destructor);
       SYMBOL_CODE_PRINT (printer);
     }
@@ -371,7 +374,7 @@ symbol_from_uniqstr_fuzzy (const uniqstr key)
 }
 
 static void
-complain_symbol_undeclared (symbol *sym)
+complain_symbol_undeclared (const symbol *sym)
 {
   assert (sym->content->status != declared);
   const symbol *best = symbol_from_uniqstr_fuzzy (sym->tag);
@@ -398,7 +401,10 @@ void
 symbol_location_as_lhs_set (symbol *sym, location loc)
 {
   if (!sym->location_of_lhs)
-    sym->location = loc;
+    {
+      sym->location = loc;
+      sym->location_of_lhs = true;
+    }
 }
 
 
@@ -548,10 +554,6 @@ symbol_class_set (symbol *sym, symbol_class class, location loc, bool declaring)
       if (class == token_sym && s->class == pct_type_sym)
         complain_pct_type_on_token (&sym->location);
 
-      if (class == nterm_sym && s->class != nterm_sym)
-        s->number = nnterms++;
-      else if (class == token_sym && s->number == NUMBER_UNDEFINED)
-        s->number = ntokens++;
       s->class = class;
 
       if (declaring)
@@ -573,9 +575,9 @@ symbol_class_set (symbol *sym, symbol_class class, location loc, bool declaring)
 }
 
 
-/*------------------------------------------------.
+/*----------------------------.
-| Set the USER_TOKEN_NUMBER associated with SYM.  |
+| Set the token code of SYM.  |
-`------------------------------------------------*/
+`----------------------------*/
 
 void
 symbol_code_set (symbol *sym, int code, location loc)
@@ -598,10 +600,6 @@ symbol_code_set (symbol *sym, int code, location loc)
       if (code == 0 && !eoftoken)
         {
           eoftoken = sym->content->symbol;
-          /* It is always mapped to 0, so it was already counted in
-             NTOKENS.  */
-          if (eoftoken->content->number != NUMBER_UNDEFINED)
-            --ntokens;
           eoftoken->content->number = 0;
         }
     }
@@ -621,9 +619,11 @@ symbol_check_defined (symbol *sym)
     {
       complain_symbol_undeclared (sym);
       s->class = nterm_sym;
-      s->number = nnterms++;
     }
 
+  if (s->number == NUMBER_UNDEFINED)
+    s->number = s->class == token_sym ? ntokens++ : nnterms++;
+
   if (s->class == token_sym
       && sym->tag[0] == '"'
       && !sym->is_alias)
@@ -742,7 +742,7 @@ symbol_pack (symbol *sym)
 }
 
 static void
-complain_code_redeclared (int num, symbol *first, symbol *second)
+complain_code_redeclared (int num, const symbol *first, const symbol *second)
 {
   symbols_sort (&first, &second);
   complain (&second->location, complaint,
@@ -758,13 +758,11 @@ complain_code_redeclared (int num, symbol *first, symbol *second)
 `-------------------------------------------------*/
 
 static void
-symbol_translation (symbol *sym)
+symbol_translation (const symbol *sym)
 {
-  /* Nonterminal? */
+  if (sym->content->class == token_sym && !sym->is_alias)
-  if (sym->content->class == token_sym
-      && !sym->is_alias)
     {
-      /* A token which translation has already been set?*/
+      /* A token whose translation has already been set? */
       if (token_translations[sym->content->code]
           != undeftoken->content->number)
         complain_code_redeclared
@@ -849,10 +847,10 @@ symbols_new (void)
                                    hash_symbol_comparator,
                                    symbol_free);
 
-  /* Construct the accept symbol. */
+  /* Construct the acceptsymbol symbol. */
-  accept = symbol_get ("$accept", empty_loc);
+  acceptsymbol = symbol_get ("$accept", empty_loc);
-  accept->content->class = nterm_sym;
+  acceptsymbol->content->class = nterm_sym;
-  accept->content->number = nnterms++;
+  acceptsymbol->content->number = nnterms++;
 
   /* Construct the YYerror/"error" token */
   errtoken = symbol_get ("YYerror", empty_loc);
@@ -969,7 +967,6 @@ dummy_symbol_get (location loc)
   assure (len < sizeof buf);
   symbol *sym = symbol_get (buf, loc);
   sym->content->class = nterm_sym;
-  sym->content->number = nnterms++;
   return sym;
 }
 
@@ -1002,7 +999,7 @@ symbol_cmp (void const *a, void const *b)
 }
 
 /* Store in *SORTED an array of pointers to the symbols contained in
-   TABLE, sorted (alphabetically) by tag. */
+   TABLE, sorted by order of appearance (i.e., by location). */
 
 static void
 table_sort (struct hash_table *table, symbol ***sorted)

src/symtab.h

@@ -227,7 +227,7 @@ void symbol_precedence_set (symbol *sym, int prec, assoc a, location loc);
 void symbol_class_set (symbol *sym, symbol_class class, location loc,
                        bool declaring);
 
-/** Set the \c code associated with \c sym.  */
+/** Set the token \c code of \c sym, specified by the user at \c loc.  */
 void symbol_code_set (symbol *sym, int code, location loc);
 
 
@@ -245,7 +245,7 @@ extern symbol *eoftoken;
 /** The genuine start symbol.
 
    $accept: start-symbol $end */
-extern symbol *accept;
+extern symbol *acceptsymbol;
 
 /** The user start symbol. */
 extern symbol *startsymbol;

src/system.h

@@ -131,6 +131,22 @@ typedef size_t uintptr_t;
 # include <stdbool.h>
 
 
+/*-----------.
+| Integers.  |
+`-----------*/
+
+static inline int
+min_int (int a, int b)
+{
+  return a < b ? a : b;
+}
+
+static inline int
+max_int (int a, int b)
+{
+  return a >= b ? a : b;
+}
+
 
 /*-------------.
 | Assertions.  |

tests/calc.at

@@ -915,6 +915,12 @@ AT_BISON_OPTION_PUSHDEFS([$1])
 
 AT_DATA_CALC_Y([$1])
 AT_FULL_COMPILE(AT_JAVA_IF([[Calc]], [[calc]]), AT_DEFINES_IF([[lex], [main]], [[], []]), [$2], [-Wno-deprecated])
+
+AT_YACC_IF(
+  [# No direct calls to malloc/free.
+  AT_CHECK([[$EGREP '(malloc|free) *\(' calc.[ch] | $EGREP -v 'INFRINGES ON USER NAME SPACE']],
+           [1])])
+
 AT_PUSH_IF([AT_JAVA_IF(
  [# Verify that this is a push parser.
   AT_CHECK_JAVA_GREP([[Calc.java]],

tests/input.at

@@ -1,4 +1,4 @@
-# Checking the Bison scanner.                    -*- Autotest -*-
+# Checking the Bison reader.                    -*- Autotest -*-
 
 # Copyright (C) 2002-2015, 2018-2020 Free Software Foundation, Inc.
 
@@ -78,10 +78,13 @@ AT_CLEANUP
 ## Invalid inputs.  ##
 ## ---------------- ##
 
+# The truly bad guys no human would write, but easily uncovered by
+# fuzzers.
 AT_SETUP([Invalid inputs])
 
 AT_DATA([input.y],
 [[\000\001\002\377?
+"\000"
 %%
 ?
 default: 'a' }
@@ -92,21 +95,50 @@ default: 'a' }
 ]])
 AT_PERL_REQUIRE([[-pi -e 's/\\(\d{3})/chr(oct($1))/ge' input.y]])
 
-AT_BISON_CHECK([input.y], [1], [],
+AT_BISON_CHECK([-fcaret input.y], [1], [], [stderr])
+
+# Autotest's diffing, when there are NUL bytes, just reports "binary
+# files differ".  So don't leave NUL bytes.
+AT_PERL_CHECK([[-p -e 's{([\0\377])}{sprintf "\\x%02x", ord($1)}ge' stderr]], [],
 [[input.y:1.1-2: error: invalid characters: '\0\001\002\377?'
-input.y:3.1: error: invalid character: '?'
+    1 | \x00
\xff?
-input.y:4.14: error: invalid character: '}'
+      | ^~
-input.y:5.1: error: invalid character: '%'
+input.y:2.2: error: invalid null character
-input.y:5.2: error: invalid character: '&'
+    2 | "\x00"
-input.y:6.1-17: error: invalid directive: '%a-does-not-exist'
+      |  ^
-input.y:7.1: error: invalid character: '%'
+input.y:4.1: error: invalid character: '?'
-input.y:7.2: error: invalid character: '-'
+    4 | ?
-input.y:8.1-9.0: error: missing '%}' at end of file
+      | ^
+input.y:5.14: error: invalid character: '}'
+    5 | default: 'a' }
+      |              ^
+input.y:6.1: error: invalid character: '%'
+    6 | %&
+      | ^
+input.y:6.2: error: invalid character: '&'
+    6 | %&
+      |  ^
+input.y:7.1-17: error: invalid directive: '%a-does-not-exist'
+    7 | %a-does-not-exist
+      | ^~~~~~~~~~~~~~~~~
+input.y:8.1: error: invalid character: '%'
+    8 | %-
+      | ^
+input.y:8.2: error: invalid character: '-'
+    8 | %-
+      |  ^
+input.y:9.1-10.0: error: missing '%}' at end of file
+    9 | %{
+      | ^~
 ]])
 
 AT_CLEANUP
 
 
+## ------------------------ ##
+## Invalid inputs with {}.  ##
+## ------------------------ ##
+
 AT_SETUP([Invalid inputs with {}])
 
 # We used to SEGV here.  See
@@ -788,6 +820,33 @@ input.y:3.8-10: note: previous declaration
 AT_CLEANUP
 
 
+## ---------------- ##
+## EOF redeclared.  ##
+## ---------------- ##
+
+AT_SETUP([EOF redeclared])
+
+# We used to crash when redefining a token after having defined EOF.
+# See https://lists.gnu.org/r/bug-bison/2020-08/msg00008.html.
+
+AT_DATA([[input.y]],
+[[%token FOO BAR FOO 0
+%%
+input: %empty
+]])
+
+AT_BISON_CHECK([-fcaret input.y], [0], [],
+[[input.y:1.16-18: warning: symbol FOO redeclared [-Wother]
+    1 | %token FOO BAR FOO 0
+      |                ^~~
+input.y:1.8-10: note: previous declaration
+    1 | %token FOO BAR FOO 0
+      |        ^~~
+]])
+
+AT_CLEANUP
+
+
 ## --------------------------- ##
 ## Symbol class redefinition.  ##
 ## --------------------------- ##
@@ -1224,12 +1283,12 @@ AT_TEST([[%token foo "foo"
 %%
 exp: foo;
 ]],
-[[input.y:3.7-11: error: %type redeclaration for foo
+[[input.y:3.13-15: error: %type redeclaration for foo
     3 | %type <baz> foo
-      |       ^~~~~
+      |             ^~~
-input.y:2.7-11: note: previous declaration
+input.y:2.13-17: note: previous declaration
     2 | %type <bar> "foo"
-      |       ^~~~~
+      |             ^~~~~
 ]])
 
 AT_TEST([[%token foo "foo"
@@ -1336,11 +1395,6 @@ AT_CLEANUP
 AT_SETUP([Torturing the Scanner])
 
 AT_BISON_OPTION_PUSHDEFS
-AT_DATA([input.y], [])
-AT_BISON_CHECK([input.y], [1], [],
-[[input.y:1.1: error: unexpected end of file
-]])
-
 
 AT_DATA([input.y],
 [{}
@@ -2447,6 +2501,99 @@ input.y:5.19: error: invalid character after \-escape: \001
 AT_CLEANUP
 
 
+## ------------------------ ##
+## Unexpected end of file.  ##
+## ------------------------ ##
+
+AT_SETUP([[Unexpected end of file]])
+
+
+AT_DATA([input.y], [])
+AT_BISON_CHECK([-fcaret input.y], [1], [],
+[[input.y:1.1: error: unexpected end of file
+]])
+
+
+AT_DATA_NO_FINAL_EOL([char.y],
+[[%token FOO ']])
+
+AT_BISON_CHECK([-fcaret char.y], [1], [],
+[[char.y:1.12: error: missing "'" at end of file
+    1 | %token FOO '
+      |            ^
+char.y:1.12: error: empty character literal
+    1 | %token FOO '
+      |            ^
+]])
+
+
+AT_DATA_NO_FINAL_EOL([escape-in-char.y],
+[[%token FOO '\]])
+
+AT_BISON_CHECK([-fcaret escape-in-char.y], [1], [],
+[[escape-in-char.y:1.12-13: error: missing '?\'' at end of file
+    1 | %token FOO '\
+      |            ^~
+escape-in-char.y:1.14: error: unexpected end of file
+    1 | %token FOO '\
+      |              ^
+]])
+
+
+AT_DATA_NO_FINAL_EOL([string.y],
+[[%token FOO "]])
+
+AT_BISON_CHECK([-fcaret string.y], [1], [],
+[[string.y:1.12: error: missing '"' at end of file
+    1 | %token FOO "
+      |            ^
+string.y:1.13: error: unexpected end of file
+    1 | %token FOO "
+      |             ^
+]])
+
+
+AT_DATA_NO_FINAL_EOL([escape-in-string.y],
+[[%token FOO "\]])
+
+AT_BISON_CHECK([-fcaret escape-in-string.y], [1], [],
+[[escape-in-string.y:1.12-13: error: missing '?"' at end of file
+    1 | %token FOO "\
+      |            ^~
+escape-in-string.y:1.14: error: unexpected end of file
+    1 | %token FOO "\
+      |              ^
+]])
+
+
+AT_DATA_NO_FINAL_EOL([tstring.y],
+[[%token FOO _("]])
+
+AT_BISON_CHECK([-fcaret tstring.y], [1], [],
+[[tstring.y:1.12-14: error: missing '")' at end of file
+    1 | %token FOO _("
+      |            ^~~
+tstring.y:1.15: error: unexpected end of file
+    1 | %token FOO _("
+      |               ^
+]])
+
+
+AT_DATA_NO_FINAL_EOL([escape-in-tstring.y],
+[[%token FOO _("\]])
+
+AT_BISON_CHECK([-fcaret escape-in-tstring.y], [1], [],
+[[escape-in-tstring.y:1.12-15: error: missing '?")' at end of file
+    1 | %token FOO _("\
+      |            ^~~~
+escape-in-tstring.y:1.16: error: unexpected end of file
+    1 | %token FOO _("\
+      |                ^
+]])
+
+AT_CLEANUP
+
+
 ## ------------------------- ##
 ## LAC: Errors for %define.  ##
 ## ------------------------- ##

tests/local.at

@@ -390,6 +390,7 @@ AT_LOCATION_TYPE_SPAN_IF(
 
 
 AT_GLR_IF([AT_KEYWORDS([glr])])
+AT_PUSH_IF([AT_KEYWORDS([push])])
 ])# _AT_BISON_OPTION_PUSHDEFS
 
 

tests/output.at

@@ -759,7 +759,7 @@ AT_TEST([x1],
          ])
 
 # Check the CPP guard and Doxyen comments.
-AT_CHECK([sed -ne 's/#line [0-9]\+ "/#line "/p;/INCLUDED/p;/\\file/{p;n;p;}' out/include/ast/loc.hh], [],
+AT_CHECK([[sed -ne 's/#line [0-9][0-9]* "/#line "/p;/INCLUDED/p;/\\file/{p;n;p;}' out/include/ast/loc.hh]], [],
 [[ ** \file bar/include/ast/loc.hh
  ** Define the x1::location class.
 #ifndef YY_YY_BAR_INCLUDE_AST_LOC_HH_INCLUDED
@@ -771,7 +771,7 @@ AT_CHECK([sed -ne 's/#line [0-9]\+ "/#line "/p;/INCLUDED/p;/\\file/{p;n;p;}' out
 #endif // !YY_YY_BAR_INCLUDE_AST_LOC_HH_INCLUDED
 ]])
 
-AT_CHECK([sed -ne 's/^#line [0-9]\+ "/#line "/p;/INCLUDED/p;/\\file/{p;n;p;}' out/x1.hh], [],
+AT_CHECK([[sed -ne 's/^#line [0-9][0-9]* "/#line "/p;/INCLUDED/p;/\\file/{p;n;p;}' out/x1.hh]], [],
 [[ ** \file bar/x1.hh
  ** Define the x1::parser class.
 #ifndef YY_YY_BAR_X1_HH_INCLUDED