Use the more modern English stemmer

sphinx/search/da.py

@@ -1,4 +1,4 @@
-"""Danish search language: includes the JS Danish stemmer."""
+"""Danish search language."""
 
 from __future__ import annotations
 

sphinx/search/de.py

@@ -1,4 +1,4 @@
-"""German search language: includes the JS German stemmer."""
+"""German search language."""
 
 from __future__ import annotations
 

sphinx/search/en.py

@@ -1,4 +1,4 @@
-"""English search language: includes the JS porter stemmer."""
+"""English search language."""
 
 from __future__ import annotations
 
@@ -7,202 +7,16 @@
 from sphinx.search import SearchLanguage
 from sphinx.search._stopwords.en import ENGLISH_STOPWORDS
 
-js_porter_stemmer = """
-/**
- * Porter Stemmer
- */
-var Stemmer = function() {
-
-  var step2list = {
-    ational: 'ate',
-    tional: 'tion',
-    enci: 'ence',
-    anci: 'ance',
-    izer: 'ize',
-    bli: 'ble',
-    alli: 'al',
-    entli: 'ent',
-    eli: 'e',
-    ousli: 'ous',
-    ization: 'ize',
-    ation: 'ate',
-    ator: 'ate',
-    alism: 'al',
-    iveness: 'ive',
-    fulness: 'ful',
-    ousness: 'ous',
-    aliti: 'al',
-    iviti: 'ive',
-    biliti: 'ble',
-    logi: 'log'
-  };
-
-  var step3list = {
-    icate: 'ic',
-    ative: '',
-    alize: 'al',
-    iciti: 'ic',
-    ical: 'ic',
-    ful: '',
-    ness: ''
-  };
-
-  var c = "[^aeiou]";          // consonant
-  var v = "[aeiouy]";          // vowel
-  var C = c + "[^aeiouy]*";    // consonant sequence
-  var V = v + "[aeiou]*";      // vowel sequence
-
-  var mgr0 = "^(" + C + ")?" + V + C;                      // [C]VC... is m>0
-  var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$";    // [C]VC[V] is m=1
-  var mgr1 = "^(" + C + ")?" + V + C + V + C;              // [C]VCVC... is m>1
-  var s_v   = "^(" + C + ")?" + v;                         // vowel in stem
-
-  this.stemWord = function (w) {
-    var stem;
-    var suffix;
-    var firstch;
-    var origword = w;
-
-    if (w.length < 3)
-      return w;
-
-    var re;
-    var re2;
-    var re3;
-    var re4;
-
-    firstch = w.substr(0,1);
-    if (firstch == "y")
-      w = firstch.toUpperCase() + w.substr(1);
-
-    // Step 1a
-    re = /^(.+?)(ss|i)es$/;
-    re2 = /^(.+?)([^s])s$/;
-
-    if (re.test(w))
-      w = w.replace(re,"$1$2");
-    else if (re2.test(w))
-      w = w.replace(re2,"$1$2");
-
-    // Step 1b
-    re = /^(.+?)eed$/;
-    re2 = /^(.+?)(ed|ing)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      re = new RegExp(mgr0);
-      if (re.test(fp[1])) {
-        re = /.$/;
-        w = w.replace(re,"");
-      }
-    }
-    else if (re2.test(w)) {
-      var fp = re2.exec(w);
-      stem = fp[1];
-      re2 = new RegExp(s_v);
-      if (re2.test(stem)) {
-        w = stem;
-        re2 = /(at|bl|iz)$/;
-        re3 = new RegExp("([^aeiouylsz])\\\\1$");
-        re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
-        if (re2.test(w))
-          w = w + "e";
-        else if (re3.test(w)) {
-          re = /.$/;
-          w = w.replace(re,"");
-        }
-        else if (re4.test(w))
-          w = w + "e";
-      }
-    }
-
-    // Step 1c
-    re = /^(.+?)y$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(s_v);
-      if (re.test(stem))
-        w = stem + "i";
-    }
-
-    // Step 2
-    re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|\
-ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      suffix = fp[2];
-      re = new RegExp(mgr0);
-      if (re.test(stem))
-        w = stem + step2list[suffix];
-    }
-
-    // Step 3
-    re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      suffix = fp[2];
-      re = new RegExp(mgr0);
-      if (re.test(stem))
-        w = stem + step3list[suffix];
-    }
-
-    // Step 4
-    re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|\
-iti|ous|ive|ize)$/;
-    re2 = /^(.+?)(s|t)(ion)$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(mgr1);
-      if (re.test(stem))
-        w = stem;
-    }
-    else if (re2.test(w)) {
-      var fp = re2.exec(w);
-      stem = fp[1] + fp[2];
-      re2 = new RegExp(mgr1);
-      if (re2.test(stem))
-        w = stem;
-    }
-
-    // Step 5
-    re = /^(.+?)e$/;
-    if (re.test(w)) {
-      var fp = re.exec(w);
-      stem = fp[1];
-      re = new RegExp(mgr1);
-      re2 = new RegExp(meq1);
-      re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
-      if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
-        w = stem;
-    }
-    re = /ll$/;
-    re2 = new RegExp(mgr1);
-    if (re.test(w) && re2.test(w)) {
-      re = /.$/;
-      w = w.replace(re,"");
-    }
-
-    // and turn initial Y back to y
-    if (firstch == "y")
-      w = firstch.toLowerCase() + w.substr(1);
-    return w;
-  }
-}
-"""
-
 
 class SearchEnglish(SearchLanguage):
     lang = 'en'
     language_name = 'English'
-    js_stemmer_code = js_porter_stemmer
+    js_stemmer_rawcode = 'english-stemmer.js'
     stopwords = ENGLISH_STOPWORDS
 
     def __init__(self, options: dict[str, str]) -> None:
         super().__init__(options)
-        self.stemmer = snowballstemmer.stemmer('porter')
+        self.stemmer = snowballstemmer.stemmer('english')
 
     def stem(self, word: str) -> str:
         return self.stemmer.stemWord(word.lower())

sphinx/search/es.py

@@ -1,4 +1,4 @@
-"""Spanish search language: includes the JS Spanish stemmer."""
+"""Spanish search language."""
 
 from __future__ import annotations
 

sphinx/search/fi.py

@@ -1,4 +1,4 @@
-"""Finnish search language: includes the JS Finnish stemmer."""
+"""Finnish search language."""
 
 from __future__ import annotations
 

sphinx/search/fr.py

@@ -1,4 +1,4 @@
-"""French search language: includes the JS French stemmer."""
+"""French search language."""
 
 from __future__ import annotations
 

sphinx/search/hu.py

@@ -1,4 +1,4 @@
-"""Hungarian search language: includes the JS Hungarian stemmer."""
+"""Hungarian search language."""
 
 from __future__ import annotations
 

sphinx/search/it.py

@@ -1,4 +1,4 @@
-"""Italian search language: includes the JS Italian stemmer."""
+"""Italian search language."""
 
 from __future__ import annotations
 

sphinx/search/nl.py

@@ -1,4 +1,4 @@
-"""Dutch search language: includes the JS porter stemmer."""
+"""Dutch search language."""
 
 from __future__ import annotations
 

sphinx/search/no.py

@@ -1,4 +1,4 @@
-"""Norwegian search language: includes the JS Norwegian stemmer."""
+"""Norwegian search language."""
 
 from __future__ import annotations
 

sphinx/search/pt.py

@@ -1,4 +1,4 @@
-"""Portuguese search language: includes the JS Portuguese stemmer."""
+"""Portuguese search language."""
 
 from __future__ import annotations
 

sphinx/search/ro.py

@@ -1,4 +1,4 @@
-"""Romanian search language: includes the JS Romanian stemmer."""
+"""Romanian search language."""
 
 from __future__ import annotations
 

sphinx/search/ru.py

@@ -1,4 +1,4 @@
-"""Russian search language: includes the JS Russian stemmer."""
+"""Russian search language."""
 
 from __future__ import annotations
 

sphinx/search/sv.py

@@ -1,4 +1,4 @@
-"""Swedish search language: includes the JS Swedish stemmer."""
+"""Swedish search language."""
 
 from __future__ import annotations
 

sphinx/search/tr.py

@@ -1,4 +1,4 @@
-"""Turkish search language: includes the JS Turkish stemmer."""
+"""Turkish search language."""
 
 from __future__ import annotations