/// <summary>
/// This is the one of the only two functions that should be called from outside.
/// It takes a RegexTree and computes the set of chars that can start it.
/// </summary>
public static RegexPrefix?FirstChars(RegexTree t)
{
RegexFCD s = new RegexFCD();
RegexFC fc = s.RegexFCFromRegexTree(t);
if (fc == null || fc._nullable)
{
return(null);
}
CultureInfo culture = ((t.Options & RegexOptions.CultureInvariant) != 0) ? CultureInfo.InvariantCulture : CultureInfo.CurrentCulture;
return(new RegexPrefix(fc.GetFirstChars(culture), fc.CaseInsensitive));
}
public void Dump()
{
int i;
Debug.WriteLine("Direction: " + (RightToLeft ? "right-to-left" : "left-to-right"));
Debug.WriteLine("Firstchars: " + (FCPrefix == null ? "n/a" : RegexCharClass.SetDescription(FCPrefix.GetValueOrDefault().Prefix)));
Debug.WriteLine("Prefix: " + (BMPrefix == null ? "n/a" : RegexParser.Escape(BMPrefix.ToString())));
Debug.WriteLine("Anchors: " + RegexFCD.AnchorDescription(Anchors));
Debug.WriteLine("");
if (BMPrefix != null)
{
Debug.WriteLine("BoyerMoore:");
Debug.WriteLine(BMPrefix.Dump(" "));
}
for (i = 0; i < Codes.Length;)
{
Debug.WriteLine(OpcodeDescription(i));
i += OpcodeSize(Codes[i]);
}
Debug.WriteLine("");
}
/// <summary>
/// The top level RegexCode generator. It does a depth-first walk
/// through the tree and calls EmitFragment to emits code before
/// and after each child of an interior node, and at each leaf.
/// </summary>
public RegexCode RegexCodeFromRegexTree(RegexTree tree)
{
// construct sparse capnum mapping if some numbers are unused
int capsize;
if (tree.CapNumList == null || tree.CapTop == tree.CapNumList.Length)
{
capsize = tree.CapTop;
_caps = null;
}
else
{
capsize = tree.CapNumList.Length;
_caps = tree.Caps;
for (int i = 0; i < tree.CapNumList.Length; i++)
{
_caps[tree.CapNumList[i]] = i;
}
}
RegexNode curNode = tree.Root;
int curChild = 0;
Emit(RegexCode.Lazybranch, 0);
for (; ;)
{
if (curNode.Children == null)
{
EmitFragment(curNode.NType, curNode, 0);
}
else if (curChild < curNode.Children.Count)
{
EmitFragment(curNode.NType | BeforeChild, curNode, curChild);
curNode = curNode.Children[curChild];
_intStack.Push(curChild);
curChild = 0;
continue;
}
if (_intStack.Count == 0)
{
break;
}
curChild = _intStack.Pop();
curNode = curNode.Next;
EmitFragment(curNode.NType | AfterChild, curNode, curChild);
curChild++;
}
PatchJump(0, _emitted.Count);
Emit(RegexCode.Stop);
RegexPrefix?fcPrefix = RegexFCD.FirstChars(tree);
RegexPrefix prefix = RegexFCD.Prefix(tree);
bool rtl = ((tree.Options & RegexOptions.RightToLeft) != 0);
CultureInfo culture = (tree.Options & RegexOptions.CultureInvariant) != 0 ? CultureInfo.InvariantCulture : CultureInfo.CurrentCulture;
RegexBoyerMoore bmPrefix;
if (prefix.Prefix.Length > 0)
{
bmPrefix = new RegexBoyerMoore(prefix.Prefix, prefix.CaseInsensitive, rtl, culture);
}
else
{
bmPrefix = null;
}
int anchors = RegexFCD.Anchors(tree);
int[] emitted = _emitted.ToArray();
return(new RegexCode(emitted, _stringTable, _trackCount, _caps, capsize, bmPrefix, fcPrefix, anchors, rtl));
}
