* Changed string-representation of regexps to handle unprintable chars.

regexp2000/src/ast.cc

 // Copyright 2006-2008 the V8 project authors. All rights reserved.
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are
 // met:
 //
 //     * Redistributions of source code must retain the above copyright
 //       notice, this list of conditions and the following disclaimer.
 //     * Redistributions in binary form must reproduce the above
 //       copyright notice, this list of conditions and the following
 //       disclaimer in the documentation and/or other materials provided
@@ skipping 172 matching lines @@
 // ----------------------------------------------------------------------------
 // Regular expressions
 
 #define MAKE_ACCEPT(Name)                                            \
   void* RegExp##Name::Accept(RegExpVisitor* visitor, void* data) {   \
     return visitor->Visit##Name(this, data);                         \
   }
 FOR_EACH_REG_EXP_TREE_TYPE(MAKE_ACCEPT)
 #undef MAKE_ACCEPT
 
-#define MAKE_CONVERSION(Name)                                        \
+#define MAKE_TYPE_CASE(Name)                                         \
   RegExp##Name* RegExpTree::As##Name() {                             \
     return NULL;                                                     \
-  }
-  FOR_EACH_REG_EXP_TREE_TYPE(MAKE_CONVERSION)
-#undef MAKE_CONVERSION
+  }                                                                  \
+  bool RegExpTree::Is##Name() { return false; }
+  FOR_EACH_REG_EXP_TREE_TYPE(MAKE_TYPE_CASE)
+#undef MAKE_TYPE_CASE
 
-#define MAKE_CONVERSION(Name)                                       \
+#define MAKE_TYPE_CASE(Name)                                        \
   RegExp##Name* RegExp##Name::As##Name() {                          \
     return this;                                                    \
-  }
-FOR_EACH_REG_EXP_TREE_TYPE(MAKE_CONVERSION)
-#undef MAKE_CONVERSION
+  }                                                                 \
+  bool RegExp##Name::Is##Name() { return true; }
+FOR_EACH_REG_EXP_TREE_TYPE(MAKE_TYPE_CASE)
+#undef MAKE_TYPE_CASE
 
 RegExpEmpty RegExpEmpty::kInstance;
 
 
 // Convert regular expression trees to a simple sexp representation.
 // This representation should be different from the input grammar
 // in as many cases as possible, to make it more difficult for incorrect
 // parses to look as correct ones which is likely if the input and
 // output formats are alike.
 class RegExpUnparser: public RegExpVisitor {
@@ skipping 29 matching lines @@
 void* RegExpUnparser::VisitAlternative(RegExpAlternative* that, void* data) {
   stream()->Add("(:");
   for (int i = 0; i <  that->nodes()->length(); i++) {
     stream()->Add(" ");
     that->nodes()->at(i)->Accept(this, data);
   }
   stream()->Add(")");
   return NULL;
 }
 
-
-void RegExpUnparser::VisitCharacterRange(CharacterRange that) {
-  if (that.IsSingleton()) {
-    stream()->Add("%c", that.from());
+static void AddChar(StringStream* stream, uc16 character) {

[Christian Plesner Hansen, 2008/11/17 10:54:35]

You could just use StringStream::Add("%k", ...).

[Lasse Reichstein, 2008/11/17 11:26:32]

"%k" uses the format "\\x%X" for anything outside of 32..255. 
For this, I prefer a format that has a fixed width, so it doesn't run into
nearby letters (i.e., something that can be parsed uniquely again). I also don't
want the range 128..255 to be treated as literals, since the interpretation
might depend on the code-page.

However, it would probably be better to add a new formatting code to
StringStream.

[Christian Plesner Hansen, 2008/11/17 11:37:45]

Just change %k to do what you want.  Nothing depends on the current behavior.

+  if (character < 32 || (character >= 128 && character < 256)) {
+    stream->Add("\\x%02x", character);
+  } else if (character >= 256) {
+    stream->Add("\\u%04x", character);
   } else {
-    stream()->Add("%c-%c", that.from(), that.to());
+    stream->Add("%c", character);
   }
 }
 
+void RegExpUnparser::VisitCharacterRange(CharacterRange that) {
+  AddChar(stream(), that.from());
+  if (!that.IsSingleton()) {
+    stream()->Add("-");
+    AddChar(stream(), that.to());
+  }
+}
+
 
 
 void* RegExpUnparser::VisitCharacterClass(RegExpCharacterClass* that,
                                           void* data) {
   if (that->is_negated())
     stream()->Add("^");
   stream()->Add("[");
   for (int i = 0; i < that->ranges()->length(); i++) {
     if (i > 0) stream()->Add(" ");
     VisitCharacterRange(that->ranges()->at(i));
@@ skipping 22 matching lines @@
       break;
     case RegExpAssertion::NON_BOUNDARY:
       stream()->Add("@B");
       break;
   }
   return NULL;
 }
 
 
 void* RegExpUnparser::VisitAtom(RegExpAtom* that, void* data) {
-  stream()->Add("'%w'", that->data());
+  stream()->Add("'");
+  Vector<const uc16> chardata = that->data();
+  for (int i = 0; i < chardata.length(); i++) {
+    AddChar(stream(), chardata[i]);

[Christian Plesner Hansen, 2008/11/17 10:54:35]

Ditto

+  }
+  stream()->Add("'");
   return NULL;
 }
 
 
 void* RegExpUnparser::VisitText(RegExpText* that, void* data) {
   if (that->elements()->length() == 1) {
     that->elements()->at(0).data.u_atom->Accept(this, data);
   } else {
     stream()->Add("(!");
     for (int i = 0; i < that->elements()->length(); i++) {
@@ skipping 51 matching lines @@
 
 
 SmartPointer<const char> RegExpTree::ToString() {
   RegExpUnparser unparser;
   Accept(&unparser, NULL);
   return unparser.ToString();
 }
 
 
 } }  // namespace v8::internal