From 70f99d49a8ec65c713f6b8a45c84d4d93d9f2030 Mon Sep 17 00:00:00 2001
From: Leonard Ehrenfried <mail@leonard.io>
Date: Fri, 9 Aug 2024 10:37:08 +0200
Subject: [PATCH] Improve regexes and test names

---
 .../ext/geocoder/EnglishNgramAnalyzerTest.java              | 6 ++++++
 .../org/opentripplanner/ext/geocoder/LuceneIndexTest.java   | 2 +-
 .../opentripplanner/ext/geocoder/EnglishNGramAnalyzer.java  | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/src/ext-test/java/org/opentripplanner/ext/geocoder/EnglishNgramAnalyzerTest.java b/src/ext-test/java/org/opentripplanner/ext/geocoder/EnglishNgramAnalyzerTest.java
index 77917399647..398dfb59630 100644
--- a/src/ext-test/java/org/opentripplanner/ext/geocoder/EnglishNgramAnalyzerTest.java
+++ b/src/ext-test/java/org/opentripplanner/ext/geocoder/EnglishNgramAnalyzerTest.java
@@ -135,6 +135,12 @@ void numberSuffixes(String input, String expected) {
     assertEquals(List.of(expected), result);
   }
 
+  @Test
+  void wordBoundary() {
+    var result = tokenize("1stst");
+    assertEquals(List.of("1sts", "1stst", "stst"), result);
+  }
+
   public List<String> tokenize(String text) {
     try (var analyzer = new EnglishNGramAnalyzer()) {
       List<String> result;
diff --git a/src/ext-test/java/org/opentripplanner/ext/geocoder/LuceneIndexTest.java b/src/ext-test/java/org/opentripplanner/ext/geocoder/LuceneIndexTest.java
index f3af08f29fe..910c5080331 100644
--- a/src/ext-test/java/org/opentripplanner/ext/geocoder/LuceneIndexTest.java
+++ b/src/ext-test/java/org/opentripplanner/ext/geocoder/LuceneIndexTest.java
@@ -316,7 +316,7 @@ void agenciesAndFeedPublisher() {
         "meridian av 148",
       }
     )
-    void shortTokens(String query) {
+    void numericAdjectives(String query) {
       var names = index.queryStopClusters(query).map(c -> c.primary().name()).toList();
       assertEquals(
         Stream.of(MERIDIAN_AVE, MERIDIAN_N2, MERIDIAN_N1).map(s -> s.getName().toString()).toList(),
diff --git a/src/ext/java/org/opentripplanner/ext/geocoder/EnglishNGramAnalyzer.java b/src/ext/java/org/opentripplanner/ext/geocoder/EnglishNGramAnalyzer.java
index 922108427e8..a3ef8440a18 100644
--- a/src/ext/java/org/opentripplanner/ext/geocoder/EnglishNGramAnalyzer.java
+++ b/src/ext/java/org/opentripplanner/ext/geocoder/EnglishNGramAnalyzer.java
@@ -26,7 +26,7 @@
 class EnglishNGramAnalyzer extends Analyzer {
 
   // matches one or more numbers followed by the English suffixes "st", "nd", "rd", "th"
-  private static final Pattern NUMBER_SUFFIX_PATTERN = Pattern.compile("(\\d+)[st|nd|rd|th]+");
+  private static final Pattern NUMBER_SUFFIX_PATTERN = Pattern.compile("(\\d+)(st|nd|rd|th)\\b");
 
   @Override
   protected TokenStreamComponents createComponents(String fieldName) {