fixed stemming words ending with letter 'y' according to Porter2 algo…

…rithm (step 1c)
olivernn · Apr 15, 2014 · a5268cc · a5268cc
1 parent 1489c02
commit a5268cc
Show file tree

Hide file tree

Showing 4 changed files with 8 additions and 10 deletions.
diff --git a/lib/stemmer.js b/lib/stemmer.js
@@ -106,13 +106,12 @@ lunr.stemmer = (function(){
       }
     }
 
-    // Step 1c
-    re = /^(.+?)y$/;
+    // Step 1c - replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say)
+    re = /^(.+?[^aeiou])y$/;
     if (re.test(w)) {
       var fp = re.exec(w);
       stem = fp[1];
-      re = new RegExp(s_v);
-      if (re.test(stem)) { w = stem + "i"; }
+      w = stem + "i";
     }
 
     // Step 2

diff --git a/lunr.js b/lunr.js
@@ -1400,13 +1400,12 @@ lunr.stemmer = (function(){
       }
     }
 
-    // Step 1c
-    re = /^(.+?)y$/;
+    // Step 1c - replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say)
+    re = /^(.+?[^aeiou])y$/;
     if (re.test(w)) {
       var fp = re.exec(w);
       stem = fp[1];
-      re = new RegExp(s_v);
-      if (re.test(stem)) { w = stem + "i"; }
+      w = stem + "i";
     }
 
     // Step 2