From 3e9bb5fae16c35938bc1f7f7669c12cc355c9331 Mon Sep 17 00:00:00 2001
From: j-james
Date: Sun, 16 Oct 2022 23:25:45 -0700
Subject: Basic prototypes of HTML/CSS lexers

---
 src/main/model/util/AbstractTree.java | 35 +++++++++++++++++++++
 src/main/model/util/Lexer.java        | 58 +++++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+)
 create mode 100644 src/main/model/util/AbstractTree.java
 create mode 100644 src/main/model/util/Lexer.java

(limited to 'src/main/model/util')

diff --git a/src/main/model/util/AbstractTree.java b/src/main/model/util/AbstractTree.java
new file mode 100644
index 0000000..4c74732
--- /dev/null
+++ b/src/main/model/util/AbstractTree.java
@@ -0,0 +1,35 @@
+package model.util;
+
+import org.javatuples.*;
+
+import java.util.*;
+
+// Utility class for a general tree: we'll be using these a lot
+public abstract class AbstractTree<T> {
+
+    // An AbstractTree holds some kind of data; we'll want this to be generic
+    // e.g. a tag, attributes, a tag and attributes, etc
+    private T data;
+    // Since it's a tree every node also has children.
+    private ArrayList<AbstractTree<T>> children;
+
+    // future implementations may want to consider adding an Optional<> parent; or an Optional<> prevSibling
+
+    public T getData() {
+        return data;
+    }
+
+    public ArrayList<AbstractTree<T>> getChildren() {
+        return children;
+    }
+
+    // god so much boilerplate
+    public AbstractTree(T data, ArrayList<AbstractTree<T>> children) {
+        this.data = data;
+        this.children = children;
+    }
+
+    public void addChild(AbstractTree<T> child) {
+        this.children.add(child);
+    }
+}
diff --git a/src/main/model/util/Lexer.java b/src/main/model/util/Lexer.java
new file mode 100644
index 0000000..b35caa6
--- /dev/null
+++ b/src/main/model/util/Lexer.java
@@ -0,0 +1,58 @@
+package model.util;
+
+import java.util.*;
+
+// General-purpose Lexer
+public class Lexer {
+
+    // private static final Set<String> whitespace = new HashSet<String>(" ", "\n");
+
+    // unused, helper function for if we implement finding identifers longer than a character
+    private static int longestDelimiter(Set<String> delimiters) {
+        int longestDelimiter = 0;
+        for (String delimiter : delimiters) {
+            if (delimiter.length() > longestDelimiter) {
+                longestDelimiter = delimiter.length();
+            }
+        }
+        return longestDelimiter;
+    }
+
+    /**
+     * Lexes a "free-form" language. "free-form" has a specific meaning here that's important to preserve:
+     * "free-form" means that _additional_ whitespace characters do not affect the language: e.g. two newlines
+     * instead of one, four spaces instead of two, etc. They are _not_ "whitespace-insensitive", which is usually
+     * a misnomer.
+     * The name's a bit of a joke: free-form languages are generally referred to as whitespace-insensitive -->
+     * insensitive == rude. Jokes are funnier when you have to explain them.
+     * Also, insensitiveLex() and freeformLex() aren't really that good of names.
+     *
+     * NOTE: This lexer only works with single-character deliminators.
+     * TODO: deduplicate whitespace
+     */
+    // public static ArrayList<String> rudeLex(String input, Set<Character> delimiters) {}
+
+    /**
+     * We might as well implement a lexer for non-free-form languages, but whatever. We won't use it.
+     */
+    public static ArrayList<String> sensitiveLex(String input, Set<Character> delimiters) {
+        // int longestDelimiter = longestDelimiter(delimiters);
+
+        ArrayList<String> tokens = new ArrayList<String>();
+        String currentToken = "";
+        // terrible c-style for loop because we may need to manipulate the index in the future
+        for (int i = 0; i < input.length(); i++) {
+            char nextToken = input.charAt(i);
+            if (delimiters.contains(nextToken)) {
+                if (!currentToken.equals("")) {
+                    tokens.add(currentToken);
+                }
+                tokens.add(Character.toString(nextToken));
+                currentToken = "";
+            } else {
+                currentToken += input.charAt(i);
+            }
+        }
+        return tokens;
+    }
+}
-- 
cgit v1.2.3-70-g09d2