public RegexCharClass(RegexBuffer buffer)
{
int startLoc = buffer.Offset;
buffer.MoveNext();
Regex regex;
Match match;
regex = new Regex(@"(?<Negated>\^?)(?<Class>.+?)\]");
match = regex.Match(buffer.String);
if (match.Success)
{
if (match.Groups["Negated"].ToString() == "^")
{
description = String.Format("Any character not in \"{0}\"",
match.Groups["Class"]);
}
else
{
description = String.Format("Any character in \"{0}\"",
match.Groups["Class"]);
}
buffer.Offset += match.Groups[0].Length;
}
else
{
description = "missing ']' in character class";
}
buffer.AddLookup(this, startLoc, buffer.Offset - 1);
}
public RegexCapture(RegexBuffer buffer)
{
startLocation = buffer.Offset;
buffer.MoveNext();
// we're not in a series of normal characters, so clear
buffer.ClearInSeries();
// if the first character of the capture is a '?',
// we need to decode what comes after it.
if (buffer.Current == '?')
{
bool decoded = CheckNamed(buffer);
if (!decoded)
{
decoded = CheckBalancedGroup(buffer);
}
if (!decoded)
{
decoded = CheckNonCapturing(buffer);
}
if (!decoded)
{
decoded = CheckOptions(buffer);
}
if (!decoded)
{
decoded = CheckLookahead(buffer);
}
if (!decoded)
{
decoded = CheckNonBacktracking(buffer);
}
if (!decoded)
{
decoded = CheckConditional(buffer);
}
}
else
// plain old capture...
{
if (!HandlePlainOldCapture(buffer))
{
throw new Exception(
String.Format("Unrecognized capture: {0}", buffer.String));
}
}
buffer.AddLookup(this, startLocation, buffer.Offset - 1);
}
// Handle (?(expression)yes|no)
// when we get called, we're pointing to the first character of the expression
public RegexConditional(RegexBuffer buffer)
{
startLocation = buffer.Offset;
expression = new RegexExpression(buffer);
CheckClosingParen(buffer);
yesNo = new RegexExpression(buffer);
CheckClosingParen(buffer);
buffer.AddLookup(this, startLocation, buffer.Offset - 1);
}
public RegexQuantifier(RegexBuffer buffer)
{
int startLoc = buffer.Offset;
buffer.MoveNext();
Regex regex;
Match match;
// look for "n}", "n,}", or "n,m}"
regex = new Regex(@"(?<n>\d+)(?<Comma>,?)(?<m>\d*)\}");
match = regex.Match(buffer.String);
if (match.Success)
{
if (match.Groups["m"].Length != 0)
{
description = String.Format("At least {0}, but not more than {1} times",
match.Groups["n"], match.Groups["m"]);
}
else if (match.Groups["Comma"].Length != 0)
{
description = String.Format("At least {0} times",
match.Groups["n"]);
}
else
{
description = String.Format("Exactly {0} times",
match.Groups["n"]);
}
buffer.Offset += match.Groups[0].Length;
if (!buffer.AtEnd && buffer.Current == '?')
{
description += " (non-greedy)";
buffer.MoveNext();
}
}
else
{
description = "missing '}' in quantifier";
}
buffer.AddLookup(this, startLoc, buffer.Offset - 1);
}
public RegexCharacter(RegexBuffer buffer)
{
int startLoc = buffer.Offset;
bool quantifier = false;
switch (buffer.Current)
{
case '.':
character = ". (any character)";
buffer.MoveNext();
special = true;
break;
case '+':
character = "+ (one or more times)";
buffer.MoveNext();
special = true;
quantifier = true;
break;
case '*':
character = "* (zero or more times)";
buffer.MoveNext();
special = true;
quantifier = true;
break;
case '?':
character = "? (zero or one time)";
buffer.MoveNext();
special = true;
quantifier = true;
break;
case '^':
character = "^ (anchor to start of string)";
buffer.MoveNext();
break;
case '$':
character = "$ (anchor to end of string)";
buffer.MoveNext();
break;
case ' ':
character = "' ' (space)";
buffer.MoveNext();
break;
case '\\':
DecodeEscape(buffer);
break;
default:
character = buffer.Current.ToString();
buffer.MoveNext();
special = false;
break;
}
if (quantifier)
{
if (!buffer.AtEnd && buffer.Current == '?')
{
character += " (non-greedy)";
buffer.MoveNext();
}
}
buffer.AddLookup(this, startLoc, buffer.Offset - 1, (character.Length == 1));
}
public RegexAlternate(RegexBuffer buffer)
{
buffer.AddLookup(this, buffer.Offset, buffer.Offset);
buffer.MoveNext(); // skip "|"
}