From 49cf5556a29e6ece3287edbdad5db44a404d9082 Mon Sep 17 00:00:00 2001
From: Stephen Williams <steve@icarus.com>
Date: Sun, 2 Feb 2014 10:57:53 -0800
Subject: [PATCH] Fix primitive table lexical analysis.

Sequences of digits in the table of a primitive may be matched
as decimal numbers instead of digits, and this breaks some
primitives.
---
 lexor.lex | 27 ++++++++++++++++++---------
 parse.y   | 27 ++++++++++++++++++++++-----
 2 files changed, 40 insertions(+), 14 deletions(-)

diff --git a/lexor.lex b/lexor.lex
index 7c7a79649..68435444c 100644
--- a/lexor.lex
+++ b/lexor.lex
@@ -229,6 +229,8 @@ TU [munpf]
 		return STRING; }
 <CSTRING>.    { yymore(); }
 
+  /* The UDP Table is a unique lexical environment. These are most
+     tokens that we can expect in a table. */
 <UDPTABLE>\(\?0\)    { return '_'; }
 <UDPTABLE>\(\?1\)    { return '+'; }
 <UDPTABLE>\(\?[xX]\) { return '%'; }
@@ -253,7 +255,7 @@ TU [munpf]
 <UDPTABLE>[xX]     { return 'x'; }
 <UDPTABLE>[nN]     { return 'n'; }
 <UDPTABLE>[pP]     { return 'p'; }
-<UDPTABLE>[01\?\*\-] { return yytext[0]; }
+<UDPTABLE>[01\?\*\-:;] { return yytext[0]; }
 
 <EDGES>"01" { return K_edge_descriptor; }
 <EDGES>"0x" { return K_edge_descriptor; }
@@ -296,6 +298,10 @@ TU [munpf]
 	    in_UDP = false;
 	    break;
 
+	  case K_table:
+	    BEGIN(UDPTABLE);
+	    break;
+
 	    /* Translate these to checks if we already have or are
 	     * outside the declaration region. */
 	  case K_timeunit:
@@ -440,10 +446,18 @@ TU [munpf]
       generation_flag = generation_save;
       return UNBASED_NUMBER; }
 
+  /* Decimal numbers are the usual. But watch out for the UDPTABLE
+     mode, where there are no decimal numbers. Reject the match if we
+     are in the UDPTABLE state. */
 [0-9][0-9_]* {
-      yylval.number = make_unsized_dec(yytext);
-      based_size = yylval.number->as_ulong();
-      return DEC_NUMBER; }
+      if (YY_START==UDPTABLE) {
+	    REJECT;
+      } else {
+	    yylval.number = make_unsized_dec(yytext);
+	    based_size = yylval.number->as_ulong();
+	    return DEC_NUMBER;
+      }
+}
 
   /* This rule handles scaled time values for SystemVerilog. */
 [0-9][0-9_]*(\.[0-9][0-9_]*)?{TU}?s {
@@ -791,11 +805,6 @@ TU [munpf]
  * lexor. The level characters are normally accepted as other things,
  * so the parser needs to switch my mode when it believes in needs to.
  */
-void lex_start_table()
-{
-      BEGIN(UDPTABLE);
-}
-
 void lex_end_table()
 {
       BEGIN(INITIAL);
diff --git a/parse.y b/parse.y
index 15e4a9814..aeb6c6007 100644
--- a/parse.y
+++ b/parse.y
@@ -33,7 +33,6 @@
 
 class PSpecPath;
 
-extern void lex_start_table();
 extern void lex_end_table();
 
 bool have_timeunit_decl = false;
@@ -6076,11 +6075,27 @@ tf_port_list_opt
   |                     { $$ = 0; }
   ;
 
+  /* Note that the lexor notices the "table" keyword and starts
+     the UDPTABLE state. It needs to happen there so that all the
+     characters in the table are interpreted in that mode. It is still
+     up to this rule to take us out of the UDPTABLE state. */
 udp_body
-	: K_table { lex_start_table(); }
-	    udp_entry_list
-	  K_endtable { lex_end_table(); $$ = $3; }
-	;
+  : K_table udp_entry_list K_endtable
+      { lex_end_table();
+	$$ = $2;
+      }
+  | K_table K_endtable
+      { lex_end_table();
+	yyerror(@1, "error: Empty UDP table.");
+	$$ = 0;
+      }
+  | K_table error K_endtable
+      { lex_end_table();
+	yyerror(@2, "Errors in UDP table");
+	yyerrok;
+	$$ = 0;
+      }
+  ;
 
 udp_entry_list
 	: udp_comb_entry_list
@@ -6202,6 +6217,7 @@ udp_input_sym
 	| 'q' { $$ = 'q'; }
 	| '_' { $$ = '_'; }
 	| '+' { $$ = '+'; }
+        | DEC_NUMBER { yyerror(@1, "internal error: Input digits parse as decimal number!"); $$ = '0'; }
 	;
 
 udp_output_sym
@@ -6209,6 +6225,7 @@ udp_output_sym
 	| '1' { $$ = '1'; }
 	| 'x' { $$ = 'x'; }
 	| '-' { $$ = '-'; }
+        | DEC_NUMBER { yyerror(@1, "internal error: Output digits parse as decimal number!"); $$ = '0'; }
 	;
 
   /* Port declarations create wires for the inputs and the output. The