fix: update for migrating lucene 8.11.3

Signed-off-by: Hiroshi Miura <[email protected]>
languagetool-org · Aug 6, 2024 · b3ae165 · b3ae165
1 parent 7a07955
commit b3ae165
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 10 deletions.
diff --git a/...ool-core/src/main/java/org/languagetool/languagemodel/LuceneSingleIndexLanguageModel.java b/...ool-core/src/main/java/org/languagetool/languagemodel/LuceneSingleIndexLanguageModel.java
@@ -146,10 +146,10 @@ public long getTotalTokenCount() {
     try {
       RegexpQuery query = new RegexpQuery(new Term("totalTokenCount", ".*"));
       TopDocs docs = luceneSearcher.searcher.search(query, 1000);  // Integer.MAX_VALUE might cause OOE on wrong index
-      if (docs.totalHits == 0) {
+      if (docs.totalHits.value == 0) {
         throw new RuntimeException("Expected 'totalTokenCount' meta documents not found in 1grams index: " + luceneSearcher.directory);
-      } else if (docs.totalHits > 1000) {
-        throw new RuntimeException("Did not expect more than 1000 'totalTokenCount' meta documents: " + docs.totalHits + " in " + luceneSearcher.directory);
+      } else if (docs.totalHits.value > 1000) {
+        throw new RuntimeException("Did not expect more than 1000 'totalTokenCount' meta documents: " + docs.totalHits.value + " in " + luceneSearcher.directory);
       } else {
         long result = 0;
         for (ScoreDoc scoreDoc : docs.scoreDocs) {
@@ -194,9 +194,9 @@ private long getCount(Term term, LuceneSearcher luceneSearcher) {
     long result = 0;
     try {
       TopDocs docs = luceneSearcher.searcher.search(new TermQuery(term), 2000);
-      if (docs.totalHits > 2000) {
+      if (docs.totalHits.value > 2000) {
         throw new RuntimeException("More than 2000 matches for '" + term + "' not supported for performance reasons: " +
-                                   docs.totalHits + " matches in " + luceneSearcher.directory);
+                                   docs.totalHits.value + " matches in " + luceneSearcher.directory);
       }
       for (ScoreDoc scoreDoc : docs.scoreDocs) {
         String countStr = luceneSearcher.reader.document(scoreDoc.doc).get("count");

diff --git a/languagetool-standalone/src/main/java/org/languagetool/dev/HomophoneOccurrenceDumper.java b/languagetool-standalone/src/main/java/org/languagetool/dev/HomophoneOccurrenceDumper.java
@@ -18,8 +18,7 @@
  */
 package org.languagetool.dev;
 
-import org.apache.lucene.index.Fields;
-import org.apache.lucene.index.MultiFields;
+import org.apache.lucene.index.MultiTerms;
 import org.apache.lucene.index.Terms;
 import org.apache.lucene.index.TermsEnum;
 import org.apache.lucene.util.BytesRef;
@@ -112,8 +111,7 @@ private void dumpOccurrences(Set<String> tokens) throws IOException {
 
   private TermsEnum getIterator() throws IOException {
     LuceneSearcher luceneSearcher = getLuceneSearcher(3);
-    Fields fields = MultiFields.getFields(luceneSearcher.getReader());
-    Terms terms = fields.terms("ngram");
+    Terms terms = MultiTerms.getTerms(luceneSearcher.getReader(), "ngram");
     return terms.iterator();
   }
 

diff --git a/languagetool-wikipedia/src/main/java/org/languagetool/dev/index/Searcher.java b/languagetool-wikipedia/src/main/java/org/languagetool/dev/index/Searcher.java
@@ -201,7 +201,7 @@ public SearcherResult findRuleMatchesOnIndex(PatternRule rule, Language language
   }
 
   private PossiblyLimitedTopDocs getTopDocs(Query query) throws IOException {
-    TopScoreDocCollector topCollector = TopScoreDocCollector.create(maxHits);
+    TopScoreDocCollector topCollector = TopScoreDocCollector.create(maxHits, Integer.MAX_VALUE);
     Counter clock = Counter.newCounter(true);
     int waitMillis = 1000;
     // TODO: if we interrupt the whole thread anyway, do we still need the TimeLimitingCollector?