Avoid allocating redundant Strings (apache#13085)

buildSrc/src/main/java/org/apache/lucene/gradle/ErrorReportingTestListener.java

@@ -113,7 +113,7 @@ public void afterSuite(final TestDescriptor suite, TestResult result) {
 
             if (echoOutput && !verboseMode) {
                synchronized (this) {
-                  System.out.println("");
+                  System.out.println();
                   System.out.println(suite.getClassName() + " > test suite's output saved to " + outputLog + ", copied below:");
                   try (BufferedReader reader = Files.newBufferedReader(outputLog, StandardCharsets.UTF_8)) {
                      char[] buf = new char[1024];

lucene/CHANGES.txt

@@ -25,6 +25,8 @@ Optimizations
 
 * GITHUB#13115: Short circuit queued flush check when flush on update is disabled (Prabhat Sharma)
 
+* GITHUB#13085: Remove unnecessary toString() / substring() calls to save some String allocations (Dmitry Cherniachenko)
+
 Bug Fixes
 ---------------------
 (No changes)

lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianStemmer.java

@@ -278,7 +278,7 @@ private boolean suffix(String value, String suffix) {
       return false;
     }
 
-    return value.substring(value.length() - suffix.length()).equals(suffix);
+    return value.endsWith(suffix);
   }
 
   /**

lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/hyphenation/PatternParser.java

@@ -142,7 +142,7 @@ protected String readToken(StringBuilder chars) {
         break;
       }
     }
-    token.append(chars.toString().substring(0, i));
+    token.append(chars, 0, i);
     // chars.delete(0,i);
     for (int countr = i; countr < chars.length(); countr++) {
       chars.setCharAt(countr - i, chars.charAt(countr));

lucene/analysis/common/src/test/org/apache/lucene/analysis/charfilter/TestHTMLStripCharFilter.java

@@ -669,7 +669,7 @@ public static void assertHTMLStripsTo(Reader input, String gold, Set<String> esc
         builder.append((char) ch);
       }
     } catch (Exception e) {
-      if (gold.equals(builder.toString())) {
+      if (gold.contentEquals(builder)) {
         throw e;
       }
       throw new Exception(

lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java

@@ -30,19 +30,13 @@
 public class TestTrimFilter extends BaseTokenStreamTestCase {
 
   public void testTrim() throws Exception {
-    char[] a = " a ".toCharArray();
-    char[] b = "b   ".toCharArray();
-    char[] ccc = "cCc".toCharArray();
-    char[] whitespace = "   ".toCharArray();
-    char[] empty = "".toCharArray();
-
     TokenStream ts =
         new CannedTokenStream(
-            new Token(new String(a, 0, a.length), 1, 5),
-            new Token(new String(b, 0, b.length), 6, 10),
-            new Token(new String(ccc, 0, ccc.length), 11, 15),
-            new Token(new String(whitespace, 0, whitespace.length), 16, 20),
-            new Token(new String(empty, 0, empty.length), 21, 21));
+            new Token(" a ", 1, 5),
+            new Token("b   ", 6, 10),
+            new Token("cCc", 11, 15),
+            new Token("   ", 16, 20),
+            new Token("", 21, 21));
     ts = new TrimFilter(ts);
 
     assertTokenStreamContents(ts, new String[] {"a", "b", "cCc", "", ""});

lucene/analysis/common/src/test/org/apache/lucene/analysis/pattern/TestPatternReplaceCharFilter.java

@@ -82,8 +82,8 @@ private void checkOutput(
       indexMatched.append((cs.correctOffset(i) < 0 ? "-" : input.charAt(cs.correctOffset(i))));
     }
 
-    boolean outputGood = expectedOutput.equals(output.toString());
-    boolean indexMatchedGood = expectedIndexMatchedOutput.equals(indexMatched.toString());
+    boolean outputGood = expectedOutput.contentEquals(output);
+    boolean indexMatchedGood = expectedIndexMatchedOutput.contentEquals(indexMatched);
 
     if (!outputGood || !indexMatchedGood || false) {
       System.out.println("Pattern : " + pattern);

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java

@@ -112,13 +112,13 @@ String[] next() throws NoMoreDataException {
     String time(String original) {
       StringBuilder buffer = new StringBuilder();
 
-      buffer.append(original.substring(8, 10));
+      buffer.append(original, 8, 10);
       buffer.append('-');
       buffer.append(months[Integer.parseInt(original.substring(5, 7)) - 1]);
       buffer.append('-');
-      buffer.append(original.substring(0, 4));
+      buffer.append(original, 0, 4);
       buffer.append(' ');
-      buffer.append(original.substring(11, 19));
+      buffer.append(original, 11, 19);
       buffer.append(".000");
 
       return buffer.toString();

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecFBISParser.java

@@ -60,7 +60,7 @@ public DocData parse(
     docData.setName(name);
     docData.setDate(date);
     docData.setTitle(title);
-    docData.setBody(stripTags(docBuf, mark).toString());
+    docData.setBody(stripTags(docBuf, mark));
     return docData;
   }
 }

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecFR94Parser.java

@@ -53,14 +53,14 @@ public DocData parse(
       // date...
       String dateStr = extract(docBuf, DATE, DATE_END, h2, DATE_NOISE_PREFIXES);
       if (dateStr != null) {
-        dateStr = stripTags(dateStr, 0).toString();
+        dateStr = stripTags(dateStr, 0);
         date = trecSrc.parseDate(dateStr.trim());
       }
     }
     docData.clear();
     docData.setName(name);
     docData.setDate(date);
-    docData.setBody(stripTags(docBuf, mark).toString());
+    docData.setBody(stripTags(docBuf, mark));
     return docData;
   }
 }

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecFTParser.java

@@ -52,7 +52,7 @@ public DocData parse(
     docData.setName(name);
     docData.setDate(date);
     docData.setTitle(title);
-    docData.setBody(stripTags(docBuf, mark).toString());
+    docData.setBody(stripTags(docBuf, mark));
     return docData;
   }
 }

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecLATimesParser.java

@@ -49,7 +49,7 @@ public DocData parse(
       if (d2a > 0) {
         dateStr = dateStr.substring(0, d2a + 3); // we need the "day" part
       }
-      dateStr = stripTags(dateStr, 0).toString();
+      dateStr = stripTags(dateStr, 0);
       date = trecSrc.parseDate(dateStr.trim());
     }
 
@@ -59,14 +59,14 @@ public DocData parse(
       title = extract(docBuf, HEADLINE, HEADLINE_END, -1, null);
     }
     if (title != null) {
-      title = stripTags(title, 0).toString().trim();
+      title = stripTags(title, 0).trim();
     }
 
     docData.clear();
     docData.setName(name);
     docData.setDate(date);
     docData.setTitle(title);
-    docData.setBody(stripTags(docBuf, mark).toString());
+    docData.setBody(stripTags(docBuf, mark));
     return docData;
   }
 }

lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchWithSortTask.java

@@ -59,7 +59,7 @@ public void setParams(String sortField) {
         String typeString;
         if (index != -1) {
           fieldName = field.substring(0, index);
-          typeString = field.substring(1 + index, field.length());
+          typeString = field.substring(1 + index);
         } else {
           throw new RuntimeException("You must specify the sort type ie page:int,subject:string");
         }

lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextStoredFieldsReader.java

@@ -169,7 +169,7 @@ private void readField(BytesRef type, FieldInfo fieldInfo, StoredFieldVisitor vi
     if (type == TYPE_STRING) {
       byte[] bytes = new byte[scratch.length() - VALUE.length];
       System.arraycopy(scratch.bytes(), VALUE.length, bytes, 0, bytes.length);
-      visitor.stringField(fieldInfo, new String(bytes, 0, bytes.length, StandardCharsets.UTF_8));
+      visitor.stringField(fieldInfo, new String(bytes, StandardCharsets.UTF_8));
     } else if (type == TYPE_BINARY) {
       byte[] copy = new byte[scratch.length() - VALUE.length];
       System.arraycopy(scratch.bytes(), VALUE.length, copy, 0, copy.length);

lucene/core/src/java/org/apache/lucene/codecs/CodecUtil.java

@@ -380,7 +380,7 @@ public static String checkIndexHeaderSuffix(DataInput in, String expectedSuffix)
     int suffixLength = in.readByte() & 0xFF;
     byte[] suffixBytes = new byte[suffixLength];
     in.readBytes(suffixBytes, 0, suffixBytes.length);
-    String suffix = new String(suffixBytes, 0, suffixBytes.length, StandardCharsets.UTF_8);
+    String suffix = new String(suffixBytes, StandardCharsets.UTF_8);
     if (!suffix.equals(expectedSuffix)) {
       throw new CorruptIndexException(
           "file mismatch, expected suffix=" + expectedSuffix + ", got=" + suffix, in);

lucene/core/src/java/org/apache/lucene/index/IndexFileNames.java

@@ -191,7 +191,7 @@ public static String getExtension(String filename) {
     if (idx == -1) {
       return null;
     } else {
-      return filename.substring(idx + 1, filename.length());
+      return filename.substring(idx + 1);
     }
   }
 

lucene/core/src/test/org/apache/lucene/analysis/standard/TestStandardAnalyzer.java

@@ -677,16 +677,11 @@ public void testNormalize() {
   public void testMaxTokenLengthDefault() throws Exception {
     StandardAnalyzer a = new StandardAnalyzer();
 
-    StringBuilder bToken = new StringBuilder();
     // exact max length:
-    for (int i = 0; i < StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH; i++) {
-      bToken.append('b');
-    }
-
-    String bString = bToken.toString();
+    String bString = "b".repeat(StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
     // first bString is exact max default length; next one is 1 too long
     String input = "x " + bString + " " + bString + "b";
-    assertAnalyzesTo(a, input.toString(), new String[] {"x", bString, bString, "b"});
+    assertAnalyzesTo(a, input, new String[] {"x", bString, bString, "b"});
     a.close();
   }
 

lucene/core/src/test/org/apache/lucene/index/TestPayloads.java

@@ -18,7 +18,6 @@
 
 import java.io.IOException;
 import java.io.StringReader;
-import java.nio.charset.Charset;
 import java.nio.charset.StandardCharsets;
 import java.util.ArrayList;
 import java.util.HashMap;
@@ -289,12 +288,10 @@ private void performTest(Directory dir) throws Exception {
     reader.close();
   }
 
-  static final Charset utf8 = StandardCharsets.UTF_8;
-
   private void generateRandomData(byte[] data) {
     // this test needs the random data to be valid unicode
     String s = TestUtil.randomFixedByteLengthUnicodeString(random(), data.length);
-    byte[] b = s.getBytes(utf8);
+    byte[] b = s.getBytes(StandardCharsets.UTF_8);
     assert b.length == data.length;
     System.arraycopy(b, 0, data, 0, b.length);
   }
@@ -493,7 +490,7 @@ private class PoolingPayloadTokenStream extends TokenStream {
       this.pool = pool;
       payload = pool.get();
       generateRandomData(payload);
-      term = new String(payload, 0, payload.length, utf8);
+      term = new String(payload, StandardCharsets.UTF_8);
       first = true;
       payloadAtt = addAttribute(PayloadAttribute.class);
       termAtt = addAttribute(CharTermAttribute.class);

lucene/core/src/test/org/apache/lucene/search/TestPrefixRandom.java

@@ -107,7 +107,7 @@ protected AcceptStatus accept(BytesRef term) throws IOException {
 
     @Override
     public String toString(String field) {
-      return field.toString() + ":" + prefix.toString();
+      return field + ":" + prefix;
     }
 
     @Override

lucene/core/src/test/org/apache/lucene/search/TestRegexpRandom2.java

@@ -139,7 +139,7 @@ protected AcceptStatus accept(BytesRef term) throws IOException {
 
     @Override
     public String toString(String field) {
-      return field.toString() + automaton.toString();
+      return field + automaton;
     }
 
     @Override

lucene/core/src/test/org/apache/lucene/util/automaton/TestLevenshteinAutomata.java

@@ -212,10 +212,10 @@ private Automaton transpositionsOf(String s) {
     List<Automaton> list = new ArrayList<>();
     for (int i = 0; i < s.length() - 1; i++) {
       StringBuilder sb = new StringBuilder();
-      sb.append(s.substring(0, i));
+      sb.append(s, 0, i);
       sb.append(s.charAt(i + 1));
       sb.append(s.charAt(i));
-      sb.append(s.substring(i + 2, s.length()));
+      sb.append(s, i + 2, s.length());
       String st = sb.toString();
       if (!st.equals(s)) {
         list.add(Automata.makeString(st));

lucene/core/src/test/org/apache/lucene/util/automaton/TestRegExp.java

@@ -159,7 +159,7 @@ protected String checkRandomExpression(String docValue) {
 
     // Add any head to the result, unchanged
     if (substitutionPoint > 0) {
-      result.append(docValue.substring(0, substitutionPoint));
+      result.append(docValue, 0, substitutionPoint);
     }
 
     // Modify the middle...

lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/UnifiedHighlighter.java

@@ -1398,7 +1398,7 @@ public void stringField(FieldInfo fieldInfo, String value) throws IOException {
         curValueBuilder.append(curValue);
       }
       curValueBuilder.append(valueSeparator);
-      curValueBuilder.append(value.substring(0, Math.min(lengthBudget - 1, value.length())));
+      curValueBuilder.append(value, 0, Math.min(lengthBudget - 1, value.length()));
       values[currentField] = curValueBuilder;
     }
 

lucene/queryparser/src/test/org/apache/lucene/queryparser/surround/query/BooleanQueryTestFacade.java

@@ -114,7 +114,7 @@ void checkNrHits() {
   public void doTest() throws Exception {
 
     if (verbose) {
-      System.out.println("");
+      System.out.println();
       System.out.println("Query: " + queryText);
     }
 

lucene/spatial-extras/src/java/org/apache/lucene/spatial/prefix/RecursivePrefixTreeStrategy.java

@@ -113,7 +113,7 @@ public String toString() {
     if (pointsOnly) str.append(",pointsOnly");
     if (pruneLeafyBranches) str.append(",pruneLeafyBranches");
     if (prefixGridScanLevel != grid.getMaxLevels() - 4)
-      str.append(",prefixGridScanLevel:").append("").append(prefixGridScanLevel);
+      str.append(",prefixGridScanLevel:").append(prefixGridScanLevel);
     if (!multiOverlappingIndexedShapes) str.append(",!multiOverlappingIndexedShapes");
     return str.append(')').toString();
   }

lucene/suggest/src/java/org/apache/lucene/search/suggest/analyzing/AnalyzingInfixSuggester.java

@@ -927,7 +927,7 @@ protected void addPrefixMatch(
       return;
     }
     sb.append("<b>");
-    sb.append(surface.substring(0, prefixToken.length()));
+    sb.append(surface, 0, prefixToken.length());
     sb.append("</b>");
     sb.append(surface.substring(prefixToken.length()));
   }

lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/TestAnalyzingInfixSuggester.java

@@ -892,7 +892,7 @@ private static String hilite(boolean lastPrefix, String[] inputTerms, String[] q
           b.append("<b>");
           b.append(queryTerm);
           b.append("</b>");
-          b.append(inputTerm.substring(queryTerm.length(), inputTerm.length()));
+          b.append(inputTerm.substring(queryTerm.length()));
           matched = true;
           break;
         }

lucene/test-framework/src/java/org/apache/lucene/tests/util/English.java

@@ -166,7 +166,6 @@ public static void longToEnglish(long i, StringBuilder result) {
         result.append("one ");
         break;
       case 0:
-        result.append("");
         break;
     }
   }

lucene/test-framework/src/java/org/apache/lucene/tests/util/LineFileDocs.java

@@ -307,7 +307,7 @@ public Document nextDoc() throws IOException {
       throw new RuntimeException("line: [" + line + "] is in an invalid format !");
     }
 
-    docState.body.setStringValue(line.substring(1 + spot2, line.length()));
+    docState.body.setStringValue(line.substring(1 + spot2));
     final String title = line.substring(0, spot);
     docState.title.setStringValue(title);
     docState.titleTokenized.setStringValue(title);