Attempt to get subgroups working

1 files changed, 110 insertions, 31 deletions

diff --git a/BJC-Utils2/src/main/java/bjc/utils/parserutils/TokenSplitter.java b/BJC-Utils2/src/main/java/bjc/utils/parserutils/TokenSplitter.java
index e6191b9..ec69ade 100644
--- a/BJC-Utils2/src/main/java/bjc/utils/parserutils/TokenSplitter.java
+++ b/BJC-Utils2/src/main/java/bjc/utils/parserutils/TokenSplitter.java
@@ -1,5 +1,7 @@
 package bjc.utils.parserutils;
 
+import java.util.HashSet;
+import java.util.Set;
 import java.util.regex.Pattern;
 
 /**
@@ -13,10 +15,9 @@ public class TokenSplitter {
 	 *
 	 * It does two things:
 	 * 
-	 * <ol>
-	 * <li> Match to the left of the provided delimiter by positive lookahead </li>
-	 * <li> Match to the right of the provided delimiter by positive lookbehind </li>
-	 * </ol>
+	 * <ol> <li> Match to the left of the provided delimiter by positive
+	 * lookahead </li> <li> Match to the right of the provided delimiter by
+	 * positive lookbehind </li> </ol>
 	 *
 	 * Thus, it will only match in places where the delimiter is, but won't
 	 * actually match the delimiter, leaving split to put it into the stream
@@ -47,10 +48,20 @@ public class TokenSplitter {
 	private Pattern	compPatt;
 	private Pattern	exclusionPatt;
 
+	/*
+	 * These represent info for debugging.
+	 */
+	private Set<String>	delimSet;
+	private Set<String>	multidelimSet;
+	private Set<String>	exclusionSet;
+
 	/**
 	 * Create a new token splitter.
 	 */
 	public TokenSplitter() {
+		delimSet = new HashSet<>();
+		multidelimSet = new HashSet<>();
+		exclusionSet = new HashSet<>();
 	}
 
 	/**
@@ -73,7 +84,8 @@ public class TokenSplitter {
 		if(compPatt == null) throw new IllegalStateException("Token splitter has not been compiled yet");
 
 		/*
-		 * Don't split something that we should exclude from being split.
+		 * Don't split something that we should exclude from being
+		 * split.
 		 */
 		if(exclusionPatt.matcher(inp).matches()) return new String[] { inp };
 
@@ -93,18 +105,20 @@ public class TokenSplitter {
 	public void addDelimiter(String... delims) {
 		for(String delim : delims) {
 			String quoteDelim = Pattern.quote(delim);
-			String delimPat   = String.format(WITH_DELIM, quoteDelim);
-	
+			String delimPat = String.format(WITH_DELIM, quoteDelim);
+
 			if(currPatt == null) {
-				currPatt          = new StringBuilder();
+				currPatt = new StringBuilder();
 				currExclusionPatt = new StringBuilder();
-	
+
 				currPatt.append("(?:" + delimPat + ")");
 				currExclusionPatt.append("(?:" + quoteDelim + ")");
 			} else {
 				currPatt.append("|(?:" + delimPat + ")");
 				currExclusionPatt.append("|(?:" + quoteDelim + ")");
 			}
+
+			delimSet.add(delim);
 		}
 	}
 
@@ -114,48 +128,113 @@ public class TokenSplitter {
 	 * The provided string should be a pattern to match one or more
 	 * occurances of.
 	 *
-	 * @param delim
+	 * @param delims
 	 *                The delimiter to split on.
 	 */
-	public void addMultiDelimiter(String delim) {
-		String delimPat = String.format(WITH_MULTI_DELIM, "(?:" + delim + ")");
+	public void addMultiDelimiter(String... delims) {
+		for(String delim : delims) {
+			String delimPat = String.format(WITH_MULTI_DELIM, "(?:" + delim + ")");
+
+			if(currPatt == null) {
+				currPatt = new StringBuilder();
+				currExclusionPatt = new StringBuilder();
 
-		if(currPatt == null) {
-			currPatt          = new StringBuilder();
-			currExclusionPatt = new StringBuilder();
+				currPatt.append("(?:" + delimPat + ")");
+				currExclusionPatt.append("(?:(?:" + delim + ")+)");
 
-			currPatt.append("(?:" + delimPat + ")");
-			currExclusionPatt.append("(?:(?:" + delim + ")+)");
+			} else {
+				currPatt.append("|(?:" + delimPat + ")");
+				currExclusionPatt.append("|(?:(?:" + delim + ")+)");
+			}
 
-		} else {
-			currPatt.append("|(?:" + delimPat + ")");
-			currExclusionPatt.append("|(?:(?:" + delim + ")+)");
+			multidelimSet.add(delim);
 		}
 	}
 
 	/**
 	 * Marks strings matching the pattern delim as non-splittable.
 	 *
-	 * @param delim
-	 * 		The regex to not splitting matching strings.
+	 * @param delimSet
+	 *                The regex to not splitting matching strings.
 	 */
-	public void addNonMatcher(String delim) {
-		if(currPatt == null) {
-			currPatt          = new StringBuilder();
-			currExclusionPatt = new StringBuilder();
-
-			currExclusionPatt.append("(?:" + delim + ")");
-		} else {
-			currExclusionPatt.append("|(?:" + delim + ")");
+	public void addNonMatcher(String... delims) {
+		for(String delim : delims) {
+			if(currPatt == null) {
+				currPatt = new StringBuilder();
+				currExclusionPatt = new StringBuilder();
+
+				currExclusionPatt.append("(?:" + delim + ")");
+			} else {
+				currExclusionPatt.append("|(?:" + delim + ")");
+			}
+
+			exclusionSet.add(delim);
 		}
 	}
+
 	/**
 	 * Compiles the current set of delimiters to a pattern.
 	 *
 	 * Makes this splitter ready to use.
 	 */
 	public void compile() {
-		compPatt      = Pattern.compile(currPatt.toString());
+		compPatt = Pattern.compile(currPatt.toString());
 		exclusionPatt = Pattern.compile(currExclusionPatt.toString());
 	}
+
+	/*
+	 * (non-Javadoc)
+	 * 
+	 * @see java.lang.Object#toString()
+	 */
+	@Override
+	public String toString() {
+		StringBuilder builder = new StringBuilder();
+
+		builder.append("TokenSplitter [");
+
+		if(currPatt != null) {
+			builder.append("currPatt=");
+			builder.append(currPatt);
+			builder.append("\n\t, ");
+		}
+
+		if(currExclusionPatt != null) {
+			builder.append("currExclusionPatt=");
+			builder.append(currExclusionPatt);
+			builder.append("\n\t, ");
+		}
+
+		if(compPatt != null) {
+			builder.append("compPatt=");
+			builder.append(compPatt);
+			builder.append("\n\t, ");
+		}
+
+		if(exclusionPatt != null) {
+			builder.append("exclusionPatt=");
+			builder.append(exclusionPatt);
+			builder.append("\n\t, ");
+		}
+
+		if(delimSet != null) {
+			builder.append("delimSet=");
+			builder.append(delimSet);
+			builder.append("\n\t, ");
+		}
+
+		if(multidelimSet != null) {
+			builder.append("multidelimSet=");
+			builder.append(multidelimSet);
+			builder.append("\n\t, ");
+		}
+
+		if(exclusionSet != null) {
+			builder.append("exclusionSet=");
+			builder.append(exclusionSet);
+		}
+
+		builder.append("]");
+		return builder.toString();
+	}
 }