From 0d97917cd2c1ff5d76215c80910c9d823c3e62c7 Mon Sep 17 00:00:00 2001
From: Andreas Abel <andreas.abel@ifi.lmu.de>
Date: Thu, 26 Dec 2019 11:02:13 +0100
Subject: [PATCH] Make sure ocamlyacc can handle 255 entry points (#9210)

The previous promised limit of ocamlyacc was 256 entry points, but
on some platforms (x86 at least) the actual limit was 127 due to representation of
bucket->entry as char.  Switching to unsigned char extends the limit to 255.

I introduced a constant MAX_ENTRY_POINT as a synonym of MAXCHAR to
handle checks against the limit consistently over the different modules
of ocamlyacc.

Extensions beyond 255 entry points would require a bit more work (which
looks unrewarding) since entry points are currently identified by a single byte
at the beginning of the input stream.

Fixes: #9207
---
 Changes       | 4 ++++
 yacc/defs.h   | 8 +++++++-
 yacc/error.c  | 4 ++--
 yacc/reader.c | 6 +++---
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/Changes b/Changes
index e05ea889c..0b7e742da 100644
--- a/Changes
+++ b/Changes
@@ -73,6 +73,10 @@ Working version
   to the toplevel.
   (Gabriel Scherer, review by Armaël Guéneau)
 
+* #9207: fix ocamlyacc to work correctly with up to 255 entry points
+  to the grammar.
+  (Andreas Abel, review by Xavier Leroy)
+
 ### Manual and documentation:
 
 - #9141: beginning of the ocamltest reference manual
diff --git a/yacc/defs.h b/yacc/defs.h
index 91aadc3e6..1fd3dc680 100644
--- a/yacc/defs.h
+++ b/yacc/defs.h
@@ -145,10 +145,16 @@ struct bucket
     short prec;
     char class;
     char assoc;
-    char entry;
+    unsigned char entry;  /* 1..MAX_ENTRY_POINT (0 for unassigned) */
     char true_token;
 };
 
+/* MAX_ENTRY_POINT is the maximal number of entry points into the grammar. */
+/* Entry points are identified by a non-zero byte in the input stream,     */
+/* so there are at most 255 entry points.                                  */
+
+#define MAX_ENTRY_POINT MAXCHAR
+
 /* TABLE_SIZE is the number of entries in the symbol table.      */
 /* TABLE_SIZE must be a power of two.                            */
 
diff --git a/yacc/error.c b/yacc/error.c
index b2750c971..a47bed9fa 100644
--- a/yacc/error.c
+++ b/yacc/error.c
@@ -177,8 +177,8 @@ token\n", virtual_input_file_name, lineno, s);
 
 void too_many_entries(void)
 {
-    fprintf(stderr, "File \"%s\", line %d: more than 256 entry points\n",
-            virtual_input_file_name, lineno);
+    fprintf(stderr, "File \"%s\", line %d: more than %u entry points\n",
+            virtual_input_file_name, lineno, MAX_ENTRY_POINT);
     done(1);
 }
 
diff --git a/yacc/reader.c b/yacc/reader.c
index 1b0a5f6b8..0ac9f340c 100644
--- a/yacc/reader.c
+++ b/yacc/reader.c
@@ -978,9 +978,9 @@ void declare_start(void)
 
       if (bp->class == TERM)
         terminal_start(bp->name);
-      bp->entry = ++entry_counter;
-      if (entry_counter == 256)
+      if (entry_counter >= MAX_ENTRY_POINT)
         too_many_entries();
+      bp->entry = ++entry_counter;
     }
 }
 
@@ -1699,7 +1699,7 @@ void make_goal(void)
       if (is_polymorphic(bp->tag))
         polymorphic_entry_point(bp->name);
       fprintf(entry_file,
-              "let %s (lexfun : Lexing.lexbuf -> token) (lexbuf : Lexing.lexbuf) =\n   (Parsing.yyparse yytables %d lexfun lexbuf : %s)\n",
+              "let %s (lexfun : Lexing.lexbuf -> token) (lexbuf : Lexing.lexbuf) =\n   (Parsing.yyparse yytables %u lexfun lexbuf : %s)\n",
               bp->name, bp->entry, bp->tag);
       fprintf(interface_file,
               "val %s :\n  (Lexing.lexbuf  -> token) -> Lexing.lexbuf -> %s\n",