feat(dedupe): Handle Geonames 'City of' prefixes

A common cause of deduplication errors is Geonames locality/localadmin
records that start with 'City of'.

Our name comparison logic is fairly conservative: it only looks at
things like punctuation, diacriticals, etc. Otherwise, we have to
consider names that are different meaning the underlying records
represent genuinely different places.

Getting too far away from this general stance could be dangerous, but we
can handle specific outliers just fine.

Geonames records that start with 'City of' are one of these cases.
Often, there is a Geonames `locality` record with just the name, (like
'New York'), and then a Geonames `localadmin` record with the 'City of'
prefix. Usually only one of those records will have a WOF concordance,
so this is still helpful even combined with
#1606

Author: orangejulius

helper/diffPlaces.js

@@ -100,13 +100,40 @@ function isParentHierarchyDifferent(item1, item2){
   });
 }
 
+/* Generate a 'name' value for comparison
+ * This includes normalizations for specific dataset features
+ */
+function nameForComparison(name) {
+  // recurse into object properties if this is an object
+  if (_.isPlainObject(name)) {
+    const new_object = {};
+    Object.keys(name).forEach((key) => {
+      new_object[key] = nameForComparison(name[key]);
+    });
+
+    return new_object;
+  }
+
+  // otherwise, only handle strings
+  if (!_.isString(name)) {
+    return name;
+  }
+
+  // remove some common Geonames prefix/postfix values
+  return name
+    .replace(/^county\s(of\s)?(.*)$/gi, '$2')
+    .replace(/^(.*)\scounty$/gi, '$1')
+    .replace(/^city\sof(?!\s?the)\s?(.*)$/gi, '$1')
+    .replace(/^(.*\s)charter\s(township)$/gi, '$1$2');
+}
+
 /**
  * Compare the name properties if they exist.
  * Returns false if the objects are the same, else true.
  */
 function isNameDifferent(item1, item2, requestLanguage){
-  let names1 = _.get(item1, 'name');
-  let names2 = _.get(item2, 'name');
+  let names1 = nameForComparison(_.get(item1, 'name'));
+  let names2 = nameForComparison(_.get(item2, 'name'));
 
   // check if these are plain 'ol javascript objects
   let isPojo1 = _.isPlainObject(names1);

test/unit/helper/diffPlaces.js

@@ -539,6 +539,21 @@ module.exports.tests.isNameDifferent = function (test, common) {
   });
 };
 
+module.exports.tests.nameForcomparison = function (test, common) {
+  test('geonames City of', function (t) {
+    t.false(isNameDifferent(
+      { name: { default: 'City of New York' } },
+      { name: { default: 'New York' } }
+    ), 'Geonames \'City of\' prefix is ignored');
+
+    t.false(isNameDifferent(
+      { name: { en: 'City of New York' } },
+      { name: { default: 'New York' } }
+    ), 'Geonames \'City of\' prefix is ignored across languages');
+    t.end();
+  });
+};
+
 module.exports.tests.normalizeString = function (test, common) {
   test('lowercase', function (t) {
     t.equal(normalizeString('Foo Bar'), 'foo bar');