Start on regex grammar

2 files changed, 91 insertions, 0 deletions

diff --git a/JPratt/src/examples/java/bjc/pratt/examples/regex/Destringer.java b/JPratt/src/examples/java/bjc/pratt/examples/regex/Destringer.java
new file mode 100644
index 0000000..dc9f1ba
--- /dev/null
+++ b/JPratt/src/examples/java/bjc/pratt/examples/regex/Destringer.java
@@ -0,0 +1,29 @@
+package bjc.pratt.examples.regex;
+
+import java.util.Iterator;
+import java.util.Map;
+import java.util.function.UnaryOperator;
+
+final class Destringer implements UnaryOperator<String> {
+	private final Iterator<Integer>		numbers;
+	private final Map<String, String>	stringLiterals;
+
+	public Destringer(final Iterator<Integer> nmbers, final Map<String, String> literals) {
+		numbers = nmbers;
+		stringLiterals = literals;
+	}
+
+	@Override
+	public String apply(final String token) {
+		if (token.startsWith("\"") && token.endsWith("\"")) {
+			final String symName = "stringLiteral" + Integer.toString(numbers.next());
+
+			final String dequotedString = token.substring(1, token.length() - 1);
+			stringLiterals.put(symName, dequotedString);
+
+			return symName;
+		}
+
+		return token;
+	}
+}
\ No newline at end of file
diff --git a/JPratt/src/examples/java/bjc/pratt/examples/regex/RegexGrammar.java b/JPratt/src/examples/java/bjc/pratt/examples/regex/RegexGrammar.java
new file mode 100644
index 0000000..c684f32
--- /dev/null
+++ b/JPratt/src/examples/java/bjc/pratt/examples/regex/RegexGrammar.java
@@ -0,0 +1,62 @@
+package bjc.pratt.examples.regex;
+
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.Scanner;
+
+import bjc.utils.data.GeneratingIterator;
+import bjc.utils.funcdata.IList;
+import bjc.utils.parserutils.TokenUtils;
+import bjc.utils.parserutils.splitter.ConfigurableTokenSplitter;
+import bjc.utils.parserutils.splitter.TokenSplitter;
+import bjc.utils.parserutils.splitter.TransformTokenSplitter;
+
+/**
+ * Grammar test for regular expressions.
+ *
+ * @author bjculkin
+ *
+ */
+public class RegexGrammar {
+	/**
+	 * Main method.
+	 *
+	 * @param args
+	 *                Unused CLI arguments.
+	 */
+	public static void main(final String[] args) {
+		final Scanner scn = new Scanner(System.in);
+
+		System.out.print("Enter text to parse (blank line to exit): ");
+		String ln = scn.nextLine().trim();
+
+		final Iterator<Integer> numbers = new GeneratingIterator<>(0, (num) -> num + 1, (val) -> true);
+
+		final Map<String, String> stringLiterals = new HashMap<>();
+		final Destringer destringer = new Destringer(numbers, stringLiterals);
+
+		final TokenSplitter dquoteSplitter = new TokenUtils.StringTokenSplitter();
+		final TokenSplitter dquoteRemover = new TransformTokenSplitter(dquoteSplitter, destringer);
+
+		final ConfigurableTokenSplitter regexSplitter = new ConfigurableTokenSplitter(true);
+		regexSplitter.addSimpleDelimiters("+", "|");
+
+		while (!ln.equals("")) {
+			final IList<String> quotelessTokens = dquoteRemover.split(ln);
+
+			System.out.println("\nTokens without quoted strings: " + quotelessTokens);
+
+			System.out.print("\nEnter text to parse (blank line to exit): ");
+			ln = scn.nextLine().trim();
+		}
+
+		System.out.println("\nString table: ");
+		for (final Entry<String, String> entry : stringLiterals.entrySet()) {
+			System.out.printf("\t%s\t'%s'\n", entry.getKey(), entry.getValue());
+		}
+
+		scn.close();
+	}
+}