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

regexp2000/src/ast.cc

Index: regexp2000/src/ast.cc
diff --git a/regexp2000/src/ast.cc b/regexp2000/src/ast.cc
index 60ae5b87cb272e06c97b5e4489bb98a750ddfd7a..aa4509b016deecdbe2d991dc2f633fc938709d8c 100644
--- a/regexp2000/src/ast.cc
+++ b/regexp2000/src/ast.cc
@@ -190,19 +190,21 @@ void Visitor::VisitExpressions(ZoneList<Expression*>* expressions) {
 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;
 
@@ -252,12 +254,21 @@ void* RegExpUnparser::VisitAlternative(RegExpAlternative* that, void* data) {
   return NULL;
 }
 
+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", character);
+  }
+}
 
 void RegExpUnparser::VisitCharacterRange(CharacterRange that) {
-  if (that.IsSingleton()) {
-    stream()->Add("%c", that.from());
-  } else {
-    stream()->Add("%c-%c", that.from(), that.to());
+  AddChar(stream(), that.from());
+  if (!that.IsSingleton()) {
+    stream()->Add("-");
+    AddChar(stream(), that.to());
   }
 }
 
@@ -303,7 +314,12 @@ void* RegExpUnparser::VisitAssertion(RegExpAssertion* that, void* data) {
 
 
 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;
 }