2007-04-03 Pierre Peiffer <pierre.peiffer@bull.net>

	* parse.cxx, parse.h (lexer::scan): Add $# and @# identifiers.
	(eval_pp_conditional, scan_pp): Allow the use of $x and @x identifiers.
	Produce more accurate error messages.
	* stap.1.in: Document $# and @# identifiers.

2007-04-04  Pierre Peiffer  <pierre.peiffer@bull.net>

	* parseok/fourteen.stp: Add test about $# and @# usage during
	the preprocessing.
	* parseko/preprocess10.stp: New test.
	* parseko/preprocess11.stp: New test.
	* parseko/preprocess12.stp: New test.

9 files changed, 155 insertions, 40 deletions

diff --git a/ChangeLog b/ChangeLog
index ef96a87d..886d35bb 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2007-04-03  Pierre Peiffer  <pierre.peiffer@bull.net>
+
+	* parse.cxx, parse.h (lexer::scan): Add $# and @# identifiers.
+	(eval_pp_conditional, scan_pp): Allow the use of $x and @x identifiers.
+	Produce more accurate error messages.
+	* stap.1.in: Document $# and @# identifiers.
+
 2007-04-04  Frank Ch. Eigler  <fche@elastic.org>
 
 	GCC 4.3 compatibility patches from Debian.
diff --git a/parse.cxx b/parse.cxx
index 74cb72d0..a960e249 100644
--- a/parse.cxx
+++ b/parse.cxx
@@ -1,6 +1,7 @@
 // recursive descent parser for systemtap scripts
 // Copyright (C) 2005-2007 Red Hat Inc.
 // Copyright (C) 2006 Intel Corporation.
+// Copyright (C) 2007 Bull S.A.S
 //
 // This file is part of systemtap, and is free software.  You can
 // redistribute it and/or modify it under the terms of the GNU General
@@ -146,6 +147,8 @@ parser::last ()
 // The basic form is %( CONDITION %? THEN-TOKENS %: ELSE-TOKENS %)
 // where CONDITION is: kernel_v[r] COMPARISON-OP "version-string"
 //                 or: arch COMPARISON-OP "arch-string"
+//                 or: "string1" COMPARISON-OP "string2"
+//                 or: number1 COMPARISON-OP number2
 // The %: ELSE-TOKENS part is optional.
 //
 // e.g. %( kernel_v > "2.5" %? "foo" %: "baz" %)
@@ -212,14 +215,51 @@ bool eval_pp_conditional (systemtap_session& s,
       
       return result;
     }  
+  else if ((l->type == tok_string && r->type == tok_string)
+	   || (l->type == tok_number && r->type == tok_number))
+    {
+      // collect acceptable strverscmp results.
+      int rvc_ok1, rvc_ok2;
+      if (op->type == tok_operator && op->content == "<=")
+        { rvc_ok1 = -1; rvc_ok2 = 0; }
+      else if (op->type == tok_operator && op->content == ">=")
+        { rvc_ok1 = 1; rvc_ok2 = 0; }
+      else if (op->type == tok_operator && op->content == "<")
+        { rvc_ok1 = -1; rvc_ok2 = -1; }
+      else if (op->type == tok_operator && op->content == ">")
+        { rvc_ok1 = 1; rvc_ok2 = 1; }
+      else if (op->type == tok_operator && op->content == "==")
+        { rvc_ok1 = 0; rvc_ok2 = 0; }
+      else if (op->type == tok_operator && op->content == "!=")
+        { rvc_ok1 = -1; rvc_ok2 = 1; }
+      else
+        throw parse_error ("expected comparison operator", op);
+
+      int rvc_result = l->content.compare(r->content);
+
+      // normalize rvc_result
+      if (rvc_result < 0) rvc_result = -1;
+      if (rvc_result > 0) rvc_result = 1;
+
+      return (rvc_result == rvc_ok1 || rvc_result == rvc_ok2);
+    }
+  else if (l->type == tok_string && r->type == tok_number
+	    && op->type == tok_operator)
+    throw parse_error ("expected string literal as right value", r);
+  else if (l->type == tok_number && r->type == tok_string
+	    && op->type == tok_operator)
+    throw parse_error ("expected number literal as right value", r);
   // XXX: support other forms?  "CONFIG_SMP" ?
   else
-    throw parse_error ("expected 'arch' or 'kernel_v' or 'kernel_vr'", l);
+    throw parse_error ("expected 'arch' or 'kernel_v' or 'kernel_vr'\n"
+		       "             or comparison between strings or integers", l);
 }
 
 
+// expand_args is used to know if we must expand $x and @x identifiers.
+// Only tokens corresponding to the TRUE statement must be expanded
 const token*
-parser::scan_pp ()
+parser::scan_pp (bool expand_args)
 {
   while (true)
     {
@@ -230,7 +270,7 @@ parser::scan_pp ()
           return t;
         }
 
-      const token* t = input.scan (); // NB: not recursive!
+      const token* t = input.scan (expand_args); // NB: not recursive!
       if (t == 0) // EOF
         return t;
       
@@ -240,15 +280,17 @@ parser::scan_pp ()
       // We have a %( - it's time to throw a preprocessing party!
 
       const token *l, *op, *r;
-      l = input.scan (); // NB: not recursive, though perhaps could be
-      op = input.scan ();
-      r = input.scan ();
+      l = input.scan (expand_args); // NB: not recursive, though perhaps could be
+      op = input.scan (expand_args);
+      r = input.scan (expand_args);
       if (l == 0 || op == 0 || r == 0)
         throw parse_error ("incomplete condition after '%('", t);
       // NB: consider generalizing to consume all tokens until %?, and
       // passing that as a vector to an evaluator.
 
-      bool result = eval_pp_conditional (session, l, op, r);
+      // Do not evaluate the condition if we haven't expanded everything.
+      // This may occured when having several recursive conditionals.
+      bool result = expand_args && eval_pp_conditional (session, l, op, r);
       delete l;
       delete op;
       delete r;
@@ -259,13 +301,18 @@ parser::scan_pp ()
       delete m; // "%?"
 
       vector<const token*> my_enqueued_pp;
+      bool have_token = false;
       
       while (true) // consume THEN tokens
         {
-          m = scan_pp (); // NB: recursive
+          m = scan_pp (result); // NB: recursive
           if (m == 0)
-            throw parse_error ("missing THEN tokens for conditional", t);
-          
+	    if (have_token)
+	      throw parse_error ("incomplete conditional - missing %: or %)", t);
+	    else
+	      throw parse_error ("missing THEN tokens for conditional", t);
+
+	  have_token = true;
           if (m->type == tok_operator && (m->content == "%:" || // ELSE
                                           m->content == "%)")) // END
             break;
@@ -277,15 +324,20 @@ parser::scan_pp ()
           // continue
         }
       
+      have_token = false;
       if (m && m->type == tok_operator && m->content == "%:") // ELSE
         {
           delete m; // "%:"
           while (true)
             {
-              m = scan_pp (); // NB: recursive
+              m = scan_pp (expand_args && !result); // NB: recursive
               if (m == 0)
-                throw parse_error ("missing ELSE tokens for conditional", t);
+		if (have_token)
+		  throw parse_error ("incomplete conditional - missing %)", t);
+		else
+		  throw parse_error ("missing ELSE tokens for conditional", t);
               
+	      have_token = true;
               if (m->type == tok_operator && m->content == "%)") // END
                 break;
               // enqueue token
@@ -473,7 +525,7 @@ lexer::input_get ()
 
 
 token*
-lexer::scan ()
+lexer::scan (bool expand_args)
 {
   token* n = new token;
   n->location.file = input_name;
@@ -501,7 +553,7 @@ lexer::scan ()
 	  int c2 = input_peek ();
 	  if (! input)
 	    break;
-	  if ((isalnum(c2) || c2 == '_' || c2 == '$'))
+	  if ((isalnum(c2) || c2 == '_' || c2 == '$' || c2 == '#' ))
 	    {
 	      n->content.push_back(c2);
 	      input_get ();
@@ -514,24 +566,36 @@ lexer::scan ()
       // numbers and @1 .. @999 as strings.
       if (n->content[0] == '@' || n->content[0] == '$')
         {
-          string idxstr = n->content.substr(1);
-          const char* startp = idxstr.c_str();
-          char *endp;
-          errno = 0;
-          unsigned long idx = strtoul (startp, &endp, 10);
-          if (endp == startp)
-            ; // no numbers at all - leave alone as identifier 
-          else
-            {
-              // Use @1/$1 as the base, not @0/$0.  Thus the idx-1.
-              if (errno == ERANGE || errno == EINVAL || *endp != '\0' ||
-                  idx == 0 || idx-1 >= session.args.size ())
-                throw parse_error ("command line argument index invalid or out of range", n);
-              
-              string arg = session.args[idx-1];
-              n->type = (n->content[0] == '@') ? tok_string : tok_number;
-              n->content = arg;
-            }
+	  if (!expand_args)
+	    return n;
+	  if (n->content[1] == '#')
+	    {
+	      stringstream converter;
+	      converter << session.args.size ();
+	      n->type = (n->content[0] == '@') ? tok_string : tok_number;
+	      n->content = converter.str();
+	    }
+	  else
+	    {
+	      string idxstr = n->content.substr(1);
+	      const char* startp = idxstr.c_str();
+	      char *endp;
+	      errno = 0;
+	      unsigned long idx = strtoul (startp, &endp, 10);
+	      if (endp == startp)
+		; // no numbers at all - leave alone as identifier
+	      else
+		{
+		  // Use @1/$1 as the base, not @0/$0.  Thus the idx-1.
+		  if (errno == ERANGE || errno == EINVAL || *endp != '\0' ||
+		      idx == 0 || idx-1 >= session.args.size ())
+		    throw parse_error ("command line argument index invalid or out of range", n);
+
+		  string arg = session.args[idx-1];
+		  n->type = (n->content[0] == '@') ? tok_string : tok_number;
+		  n->content = arg;
+		}
+	    }
         }
       else
         {
diff --git a/parse.h b/parse.h
index c6a778ca..b160b4f9 100644
--- a/parse.h
+++ b/parse.h
@@ -1,5 +1,6 @@
 // -*- C++ -*-
 // Copyright (C) 2005 Red Hat Inc.
+// Copyright (C) 2007 Bull S.A.S
 //
 // This file is part of systemtap, and is free software.  You can
 // redistribute it and/or modify it under the terms of the GNU General
@@ -68,7 +69,7 @@ struct systemtap_session;
 class lexer
 {
 public:
-  token* scan ();
+  token* scan (bool expand_args=true);
   lexer (std::istream&, const std::string&, systemtap_session&);
 
 private:
@@ -128,7 +129,7 @@ private:
 
   // preprocessing subordinate
   std::vector<const token*> enqueued_pp;
-  const token* scan_pp ();
+  const token* scan_pp (bool expand_args=true);
 
   // scanning state
   const token* last ();
diff --git a/stap.1.in b/stap.1.in
index 6f31f711..0c968620 100644
--- a/stap.1.in
+++ b/stap.1.in
@@ -185,10 +185,16 @@ be expanded as literals.  Use
 .B $1 ... $<NN>
 for casting as a numeric literal and
 .B @1 ... @<NN>
-for casting as string literal.  These may be used in all contexts
-where literals are accepted.  Reference to an argument number beyond
-what was actually given is an error.
-.PP
+for casting as string literal.  The number of arguments may be accessed
+through
+.B $#
+(as a numeric literal) or through
+.B @#
+(as a string literal).  These may be used in all contexts where literals
+are accepted, including preprocessing stage.  Reference to an argument
+number beyond what was actually given is an error.
+
+.SS PREPROCESSING
 A simple conditional preprocessing stage is run as a part of parsing.
 The general form is similar to the 
 .RB cond " ? " exp1 " : " exp2
@@ -197,8 +203,9 @@ ternary operator:
 .BR %( " CONDITION " %? " TRUE-TOKENS " %)
 .BR %( " CONDITION " %? " TRUE-TOKENS " %: " FALSE-TOKENS " %)
 .ESAMPLE
-The CONDITION is a very limited expression whose format is determined
-by its first keyword.
+The CONDITION is either an expression whose format is determined by its
+first keyword, or a string literals comparison or a numeric literals
+comparison.
 .PP
 If the first part is the identifier
 .BR kernel_vr " or " kernel_v
@@ -222,6 +229,10 @@ then the second part is one of the two string comparison operators
 and the third part is a string literal for matching it.  This
 comparison is simple string (in)equality.
 .PP
+Otherwise, the CONDITION is expected to be a comparison between two string
+literals or two numeric literals.  In this case, the arguments are the only
+variables usable.
+.PP
 The TRUE-TOKENS and FALSE-TOKENS are zero or more general parser
 tokens (possibly including nested preprocessor conditionals), and are
 pasted into the input stream if the condition is true or false.  For
diff --git a/testsuite/ChangeLog b/testsuite/ChangeLog
index bf9bfae6..df1144c5 100644
--- a/testsuite/ChangeLog
+++ b/testsuite/ChangeLog
@@ -1,3 +1,11 @@
+2007-04-04  Pierre Peiffer  <pierre.peiffer@bull.net>
+
+	* parseok/fourteen.stp: Add test about $# and @# usage during
+	the preprocessing.
+	* parseko/preprocess10.stp: New test.
+	* parseko/preprocess11.stp: New test.
+	* parseko/preprocess12.stp: New test.
+
 2007-04-02  Frank Ch. Eigler  <fche@elastic.org>
 
 	* systemtap.samples/poll_map.stp, profile.stp, syscalls.stp:
diff --git a/testsuite/parseko/preprocess10.stp b/testsuite/parseko/preprocess10.stp
new file mode 100755
index 00000000..5fcb7e9f
--- /dev/null
+++ b/testsuite/parseko/preprocess10.stp
@@ -0,0 +1,4 @@
+#! stap -p1
+
+# expected number as right value in comparison
+%( $# != "2" %? probe begin { } %)
diff --git a/testsuite/parseko/preprocess11.stp b/testsuite/parseko/preprocess11.stp
new file mode 100755
index 00000000..586aec1a
--- /dev/null
+++ b/testsuite/parseko/preprocess11.stp
@@ -0,0 +1,4 @@
+#! stap -p1
+
+# expected string as right value in comparison
+%( @# != 2 %? probe begin { } %)
diff --git a/testsuite/parseko/preprocess12.stp b/testsuite/parseko/preprocess12.stp
new file mode 100755
index 00000000..3ff3e34e
--- /dev/null
+++ b/testsuite/parseko/preprocess12.stp
@@ -0,0 +1,5 @@
+#! stap -p1
+
+# command line argument index invalid or out of range
+# (try to access to an unavailable argument)
+%( $# < 2 %? probe begin { print @1 } %)
diff --git a/testsuite/parseok/fourteen.stp b/testsuite/parseok/fourteen.stp
index cc51b90b..30ada648 100755
--- a/testsuite/parseok/fourteen.stp
+++ b/testsuite/parseok/fourteen.stp
@@ -15,3 +15,14 @@ global
    %: %( arch != "x86_64" %? other %: x86_64 %) 
    %)
 %)
+
+global
+%( $# != 2 %? /* and */
+   %( @# < "1" %? /* and */
+      %( @# == "0" %? /* and */
+         %( $# >= 3 %? /* and */
+            %( $2 >= "12" %? $3 FAIL5 %: $2 FAIL6 %) #This line must not be evaluated
+         %: PASS2 %)
+      %: "FAIL7" %)
+   %: "FAIL8" %)
+%: "FAIL9" %)