Date: Thu, 22 Apr 2004 16:08:49 -0500 (CDT)
From: Gilles Detillieux <grdetil@scrc.umanitoba.ca>
To: "ht://Dig developers list" <htdig-dev@lists.sourceforge.net>
Subject: [htdig-dev] PATCH: 3.2.0b5 config parser fixes

Hi, folks.  I was going to take another crack at the performance
optimizations in HtRegexList, but before that, I got down to tackling
some of the config parser bugs that had been nagging at us for quite
some time.  Please have a look at this patch, and test it as much as
possible, to see if it causes any problems.  The fixes in there are:

- improved error handling, gives file name and correct line number, even
  if using include files
- allows space before comment, because otherwise it would just complain
  about the "#" character and go on to parse the text after it as a
  definition
- allows config file with an unterminated line at end of file, by pushing
  an extra newline token to the parser at EOF
- parser correctly handles extra newline tokens, by moving this handling
  out of simple_expression, and into simple_expression_list and block, as
  simple_expression must return a new ConfigDefaults object and a newline
  token doesn't cut it (caused segfaults when dealing with fix above)

Apply using "patch -p0 < this-message-file".

-- 
Gilles R. Detillieux              E-mail: <grdetil@scrc.umanitoba.ca>
Spinal Cord Research Centre       WWW:    http://www.scrc.umanitoba.ca/
Dept. Physiology, U. of Manitoba  Winnipeg, MB  R3E 3J7  (Canada)


--- htcommon/conf_lexer.lxx.orig	2003-12-14 07:40:12.000000000 -0600
+++ htcommon/conf_lexer.lxx	2004-04-22 15:47:48.000000000 -0500
@@ -41,6 +41,7 @@
 #define MAX_INCLUDE_DEPTH 10
 YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH];
 String *name_stack[MAX_INCLUDE_DEPTH];
+int lineno_stack[MAX_INCLUDE_DEPTH];
 int include_stack_ptr = 0;
 %}
 
@@ -50,7 +51,7 @@ STRING			[\x21-\xff]+
 BR_STRING		[^ \n\t<>]+
 %%
 
-^#.*\n			/*   Ignore comments     */
+^[[:space:]]*#.*\n	/*   Ignore comments     */
 ^[[:space:]]*\n		/*   Ignore emty lines   */
 <*>[ \t]+		/*   Ignore spaces       */
 include[ \t]*:		BEGIN(incl);
@@ -157,6 +158,8 @@ include[ \t]*:		BEGIN(incl);
 			}
 			name_stack[include_stack_ptr-1] =
 					new String(ParsedFilename.get());
+			lineno_stack[include_stack_ptr-1] = yylineno;
+			yylineno = 1;
 		        yy_switch_to_buffer( yy_create_buffer( yyin, YY_BUF_SIZE ) );
 
 		        BEGIN(INITIAL);
@@ -164,10 +167,18 @@ include[ \t]*:		BEGIN(incl);
 
 <<EOF>> 		{
 		        if ( include_stack_ptr <= 0 )
+			    {
+			    static int termnext = 0;
+			    // fix to allow unterminated final line
+			    if (++termnext <= 1)
+				return(T_NEWLINE);
+			    termnext = 0;	// in case we're called again
 		            yyterminate();
+			    }
 		        else
 		            {
 			    delete name_stack[include_stack_ptr-1];
+			    yylineno = lineno_stack[include_stack_ptr-1];
 		            yy_delete_buffer( YY_CURRENT_BUFFER );
 		            yy_switch_to_buffer(
 		                 include_stack[--include_stack_ptr] );
@@ -183,7 +194,13 @@ include[ \t]*:		BEGIN(incl);
 
 \n			
 <*>.|\n		{ 
-	fprintf(stderr,"Unknown char in line %d: %s",yylineno,yytext);
-	// exit(1); // Seems to harsh!
+	HtConfiguration* config= HtConfiguration::config();
+	String str;
+	if (include_stack_ptr > 0)
+	    str = *name_stack[include_stack_ptr-1];
+	else	// still at top level config
+	    str = config->getFileName();
+	fprintf(stderr,"Unknown char in file %s line %d: %s\n",str.get(),yylineno,yytext);
+	// exit(1); // Seems too harsh!
 	}
 %%
--- htcommon/conf_parser.yxx.orig	2003-11-22 07:40:17.000000000 -0600
+++ htcommon/conf_parser.yxx	2004-04-22 15:48:54.000000000 -0500
@@ -84,6 +84,7 @@ block:        simple_expression		{   
           //    ... : ...
           // </server>
 	}
+        | T_NEWLINE	{ /* Ignore empty lines */  }
 ;
 
 simple_expression:      T_KEYWORD T_DELIMITER T_STRING T_NEWLINE	{ 
@@ -116,7 +117,6 @@ simple_expression:      T_KEYWORD T_DELI
 				    $$->value=new char[1];
 				    *$$->value='\0';
 					}
-        | T_NEWLINE	{ /* Ignore empty lines */  }
 ;
 
 complex_expression:	T_LEFT_BR T_KEYWORD T_DELIMITER T_STRING T_RIGHT_BR T_NEWLINE simple_expression_list T_LEFT_BR T_SLASH T_KEYWORD T_RIGHT_BR T_NEWLINE {
@@ -170,6 +170,7 @@ simple_expression_list:   simple_express
 				delete $2;
 				//$$=$1; //I think $$==$1
 			}
+			| T_NEWLINE	{ /* Ignore empty lines */  }
                       ;
 
 list:	  T_STRING T_STRING			{ 
@@ -253,8 +254,17 @@ list:	  T_STRING T_STRING			{ 
 int
 yyerror (char *s)  /* Called by yyparse on error */
 {
-extern int yylineno;	// I don't know what about included files
-   fprintf (stderr, "%s\nIn line %d\n",s,yylineno);
+extern int yylineno;
+extern int include_stack_ptr;
+extern String *name_stack[];
+   HtConfiguration* config= HtConfiguration::config();
+   String str;
+   if (include_stack_ptr > 0)
+	str = *name_stack[include_stack_ptr-1];
+   else	// still at top level config
+	str = config->getFileName();
+   //fprintf (stderr, "%s\nIn line %d\n",s,yylineno);
+   fprintf(stderr,"Error in file %s line %d: %s\n",str.get(),yylineno,s);
    // exit(1);
    return -1;
 }