Add sanitizeInput() and improve normalizeStreet() for edge cases

web/index.html

@@ -31,6 +31,7 @@ <h1>Pothole Dodger</h1>
   </div>
 
   <script src="https://unpkg.com/leaflet@1.9.4/dist/leaflet.js"></script>
+  <script src="js/sanitize.js"></script>
   <script src="js/geocode.js"></script>
   <script src="js/routing.js"></script>
   <script src="js/hazards.js"></script>

web/js/app.js

@@ -13,7 +13,7 @@ function attachAutocomplete(inputEl) {
 
   inputEl.addEventListener('input', function () {
     clearTimeout(debounceTimer);
-    const query = inputEl.value.trim();
+    const query = sanitizeInput(inputEl.value);
 
     if (query.length < 3) {
       hideList();
@@ -72,8 +72,8 @@ document.addEventListener('DOMContentLoaded', function () {
   }
 
   async function run() {
-    const origin = document.getElementById('origin').value.trim();
-    const destination = document.getElementById('destination').value.trim();
+    const origin = sanitizeInput(document.getElementById('origin').value);
+    const destination = sanitizeInput(document.getElementById('destination').value);
 
     if (!origin || !destination) {
       setStatus('Please enter both an origin and destination.');

web/js/hazards.js

@@ -1,6 +1,6 @@
 // hazards.js — loads hazard data and filters it to streets matching the route
 
-const ABBR_MAP = [
+const STREET_TYPE_ABBRS = [
   [/\bSt\b/g, 'Street'],
   [/\bAve\b/g, 'Avenue'],
   [/\bBlvd\b/g, 'Boulevard'],
@@ -9,21 +9,40 @@ const ABBR_MAP = [
   [/\bPkwy\b/g, 'Parkway'],
   [/\bLn\b/g, 'Lane'],
   [/\bCt\b/g, 'Court'],
-  [/\bW\b/g, 'West'],
-  [/\bE\b/g, 'East'],
-  [/\bN\b/g, 'North'],
-  [/\bS\b/g, 'South'],
 ];
 
+const DIRECTIONAL_EXPAND = {
+  W: 'West',
+  E: 'East',
+  N: 'North',
+  S: 'South',
+};
+
 function normalizeStreet(str) {
   let s = str;
-  for (const [pattern, replacement] of ABBR_MAP) {
+
+  // 1. Strip trailing ZIP code (5 digits, optionally preceded by comma and/or space)
+  s = s.replace(/[,\s]+\d{5}\s*$/, '');
+
+  // 2. Expand street type abbreviations
+  for (const [pattern, replacement] of STREET_TYPE_ABBRS) {
     s = s.replace(pattern, replacement);
   }
-  // Strip leading house numbers (including fractional like "8 1/2") but preserve
-  // street numbers that are part of the name (e.g. "1st Avenue")
+
+  // 3. Expand directionals at start of string (prefix directional)
+  s = s.replace(/^(W|E|N|S)\b\s*/, (_, d) => DIRECTIONAL_EXPAND[d] + ' ');
+
+  // 4. Expand directionals at end of string (suffix directional)
+  s = s.replace(/\s+(W|E|N|S)$/, (_, d) => ' ' + DIRECTIONAL_EXPAND[d]);
+
+  // 5. Strip leading house numbers (including fractional like "8 1/2")
   s = s.replace(/^\d+(\s+\d+\/\d+)?\s+/, '');
+
+  // 6. Strip remaining punctuation
   s = s.replace(/[^a-zA-Z0-9\s]/g, '');
+
+  // 7. Collapse whitespace and trim, lowercase
+  s = s.replace(/\s{2,}/g, ' ');
   return s.trim().toLowerCase();
 }
 

web/js/sanitize.js

@@ -0,0 +1,28 @@
+// sanitize.js — sanitizes raw user input before geocoding or internal matching
+
+/**
+ * Sanitizes a raw user-supplied address string for use as a Nominatim query.
+ *
+ * - Trims leading/trailing whitespace
+ * - Collapses multiple spaces into one
+ * - Strips parenthetical context (e.g. "(near the park)")
+ * - Removes characters that break queries: # " ' . ; : ! ? @ ^ * [ ] { } | \ ~ ` = + < > % & _
+ * - Preserves commas (Nominatim field separators), hyphens (address ranges), slashes (fractions)
+ * - Does NOT expand abbreviations (leave that to normalizeStreet in hazards.js)
+ * - Does NOT strip ZIP codes (Nominatim handles them; strip only inside normalizeStreet)
+ * - Must never be called on coordinate (lat/lng) values
+ *
+ * @param {string} str  Raw input string
+ * @returns {string}    Sanitized string safe for Nominatim queries
+ */
+function sanitizeInput(str) {
+  if (typeof str !== 'string') return '';
+  let s = str;
+  // Remove parenthetical content
+  s = s.replace(/\([^)]*\)/g, '');
+  // Keep: letters, digits, spaces, commas, hyphens, forward slashes
+  s = s.replace(/[^a-zA-Z0-9\s,\-\/]/g, '');
+  // Collapse multiple spaces
+  s = s.replace(/\s{2,}/g, ' ');
+  return s.trim();
+}