Rename IOUtils.CHARSET_UTF_8 to ENCODING_UTF_8_NO_BOM

src/Lucene.Net.Benchmark/Quality/Trec/QueryDriver.cs

@@ -71,7 +71,7 @@ public static void Main(string[] args)
 
             FileInfo topicsFile = new FileInfo(args[0]);
             FileInfo qrelsFile = new FileInfo(args[1]);
-            SubmissionReport submitLog = new SubmissionReport(new StreamWriter(new FileStream(args[2], FileMode.Create, FileAccess.Write), IOUtils.CHARSET_UTF_8 /* huh, no nio.Charset ctor? */), "lucene");
+            SubmissionReport submitLog = new SubmissionReport(new StreamWriter(new FileStream(args[2], FileMode.Create, FileAccess.Write), IOUtils.ENCODING_UTF_8_NO_BOM /* huh, no nio.Charset ctor? */), "lucene");
             using Store.FSDirectory dir = Store.FSDirectory.Open(new DirectoryInfo(args[3]));
             using IndexReader reader = DirectoryReader.Open(dir);
             string fieldSpec = args.Length == 5 ? args[4] : "T"; // default to Title-only if not specified.

src/Lucene.Net.TestFramework/Util/TestUtil.cs

@@ -167,7 +167,7 @@ public static CheckIndex.Status CheckIndex(Directory dir, bool crossCheckTermVec
             ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
             CheckIndex checker = new CheckIndex(dir);
             checker.CrossCheckTermVectors = crossCheckTermVectors;
-            checker.InfoStream = new StreamWriter(bos, IOUtils.CHARSET_UTF_8);
+            checker.InfoStream = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM);
             CheckIndex.Status indexStatus = checker.DoCheckIndex(null);
             if (indexStatus is null || indexStatus.Clean == false)
             {
@@ -203,7 +203,7 @@ public static void CheckReader(AtomicReader reader, bool crossCheckTermVectors)
         {
             // LUCENENET: dispose the StreamWriter and ByteArrayOutputStream when done
             using ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
-            using StreamWriter infoStream = new StreamWriter(bos, IOUtils.CHARSET_UTF_8, leaveOpen: true, bufferSize: 1024);
+            using StreamWriter infoStream = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM, leaveOpen: true, bufferSize: 1024);
 
             reader.CheckIntegrity();
             CheckIndex.Status.FieldNormStatus fieldNormStatus = Index.CheckIndex.TestFieldNorms(reader, infoStream);

src/Lucene.Net.Tests.Benchmark/ByTask/Feeds/DocMakerTest.cs

@@ -171,7 +171,7 @@ public void TestDocMakerLeak()
             // DocMaker did not close its ContentSource if resetInputs was called twice,
             // leading to a file handle leak.
             FileInfo f = new FileInfo(Path.Combine(getWorkDir().FullName, "docMakerLeak.txt"));
-            TextWriter ps = new StreamWriter(new FileStream(f.FullName, FileMode.Create, FileAccess.Write), IOUtils.CHARSET_UTF_8);
+            TextWriter ps = new StreamWriter(new FileStream(f.FullName, FileMode.Create, FileAccess.Write), IOUtils.ENCODING_UTF_8_NO_BOM);
             ps.WriteLine("one title\t" + (J2N.Time.NanoTime() / J2N.Time.MillisecondsPerNanosecond) + "\tsome content"); // LUCENENET: Use NanoTime() rather than CurrentTimeMilliseconds() for more accurate/reliable results
             ps.Dispose();
 

src/Lucene.Net.Tests.Facet/Taxonomy/TestTaxonomyFacetCounts.cs

@@ -134,7 +134,7 @@ public virtual void TestBasic()
             string result;
             using (ByteArrayOutputStream bos = new ByteArrayOutputStream())
             {
-                using (StreamWriter w = new StreamWriter(bos, IOUtils.CHARSET_UTF_8, 2048, true) { AutoFlush = true })
+                using (StreamWriter w = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM, 2048, true) { AutoFlush = true })
                 {
                     PrintTaxonomyStats.PrintStats(taxoReader, w, true);
                 }

src/Lucene.Net.Tests/Index/TestCheckIndex.cs

@@ -64,7 +64,7 @@ public virtual void TestDeletedDocs()
 
             ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
             CheckIndex checker = new CheckIndex(dir);
-            checker.InfoStream = new StreamWriter(bos, IOUtils.CHARSET_UTF_8);
+            checker.InfoStream = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM);
             if (Verbose)
             {
                 checker.InfoStream = Console.Out;

src/Lucene.Net.Tests/Index/TestDocInverterPerFieldErrorInfo.cs

@@ -91,7 +91,7 @@ public virtual void TestInfoStreamGetsFieldName()
             IndexWriter writer;
             IndexWriterConfig c = new IndexWriterConfig(TEST_VERSION_CURRENT, new ThrowingAnalyzer());
             ByteArrayOutputStream infoBytes = new ByteArrayOutputStream();
-            StreamWriter infoPrintStream = new StreamWriter(infoBytes, IOUtils.CHARSET_UTF_8);
+            StreamWriter infoPrintStream = new StreamWriter(infoBytes, IOUtils.ENCODING_UTF_8_NO_BOM);
             TextWriterInfoStream printStreamInfoStream = new TextWriterInfoStream(infoPrintStream);
             c.SetInfoStream(printStreamInfoStream);
             writer = new IndexWriter(dir, c);
@@ -120,7 +120,7 @@ public virtual void TestNoExtraNoise()
             IndexWriter writer;
             IndexWriterConfig c = new IndexWriterConfig(TEST_VERSION_CURRENT, new ThrowingAnalyzer());
             ByteArrayOutputStream infoBytes = new ByteArrayOutputStream();
-            StreamWriter infoPrintStream = new StreamWriter(infoBytes, IOUtils.CHARSET_UTF_8);
+            StreamWriter infoPrintStream = new StreamWriter(infoBytes, IOUtils.ENCODING_UTF_8_NO_BOM);
             TextWriterInfoStream printStreamInfoStream = new TextWriterInfoStream(infoPrintStream);
             c.SetInfoStream(printStreamInfoStream);
             writer = new IndexWriter(dir, c);

src/Lucene.Net.Tests/Index/TestIndexWriterDelete.cs

@@ -1400,7 +1400,7 @@ public virtual void TestDeletesCheckIndexOutput()
             ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
             //MemoryStream bos = new MemoryStream(1024);
             CheckIndex checker = new CheckIndex(dir);
-            checker.InfoStream = new StreamWriter(bos, IOUtils.CHARSET_UTF_8);
+            checker.InfoStream = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM);
             CheckIndex.Status indexStatus = checker.DoCheckIndex(null);
             Assert.IsTrue(indexStatus.Clean);
             checker.FlushInfoStream();
@@ -1413,7 +1413,7 @@ public virtual void TestDeletesCheckIndexOutput()
             w.Dispose();
 
             bos = new ByteArrayOutputStream(1024);
-            checker.InfoStream = new StreamWriter(bos, IOUtils.CHARSET_UTF_8);
+            checker.InfoStream = new StreamWriter(bos, IOUtils.ENCODING_UTF_8_NO_BOM);
             indexStatus = checker.DoCheckIndex(null);
             Assert.IsTrue(indexStatus.Clean);
             checker.FlushInfoStream();

src/Lucene.Net.Tests/Index/TestPayloads.cs

@@ -84,7 +84,7 @@ public virtual void TestPayloadFieldBit()
             // enabled in only some documents
             d.Add(NewTextField("f3", "this field has payloads in some docs", Field.Store.NO));
             // only add payload data for field f2
-            analyzer.SetPayloadData("f2", "somedata".GetBytes(IOUtils.CHARSET_UTF_8), 0, 1);
+            analyzer.SetPayloadData("f2", "somedata".GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM), 0, 1);
             writer.AddDocument(d);
             // flush
             writer.Dispose();
@@ -106,8 +106,8 @@ public virtual void TestPayloadFieldBit()
             d.Add(NewTextField("f2", "this field has payloads in all docs", Field.Store.NO));
             d.Add(NewTextField("f3", "this field has payloads in some docs", Field.Store.NO));
             // add payload data for field f2 and f3
-            analyzer.SetPayloadData("f2", "somedata".GetBytes(IOUtils.CHARSET_UTF_8), 0, 1);
-            analyzer.SetPayloadData("f3", "somedata".GetBytes(IOUtils.CHARSET_UTF_8), 0, 3);
+            analyzer.SetPayloadData("f2", "somedata".GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM), 0, 1);
+            analyzer.SetPayloadData("f3", "somedata".GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM), 0, 3);
             writer.AddDocument(d);
 
             // force merge

src/Lucene.Net.Tests/Search/Spans/TestBasics.cs

@@ -77,7 +77,7 @@ public override bool IncrementToken()
                 if (m_input.IncrementToken())
                 {
 #pragma warning disable 612, 618
-                    payloadAttr.Payload = new BytesRef(("pos: " + pos).GetBytes(IOUtils.CHARSET_UTF_8));
+                    payloadAttr.Payload = new BytesRef(("pos: " + pos).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
 #pragma warning restore 612, 618
                     pos++;
                     return true;
@@ -533,7 +533,7 @@ public virtual void TestSpanPayloadCheck()
         {
             SpanTermQuery term1 = new SpanTermQuery(new Term("field", "five"));
 #pragma warning disable 612, 618
-            BytesRef pay = new BytesRef(("pos: " + 5).GetBytes(IOUtils.CHARSET_UTF_8));
+            BytesRef pay = new BytesRef(("pos: " + 5).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
 #pragma warning restore 612, 618
             SpanQuery query = new SpanPayloadCheckQuery(term1, new JCG.List<byte[]>() { pay.Bytes });
             CheckHits(query, new int[] { 1125, 1135, 1145, 1155, 1165, 1175, 1185, 1195, 1225, 1235, 1245, 1255, 1265, 1275, 1285, 1295, 1325, 1335, 1345, 1355, 1365, 1375, 1385, 1395, 1425, 1435, 1445, 1455, 1465, 1475, 1485, 1495, 1525, 1535, 1545, 1555, 1565, 1575, 1585, 1595, 1625, 1635, 1645, 1655, 1665, 1675, 1685, 1695, 1725, 1735, 1745, 1755, 1765, 1775, 1785, 1795, 1825, 1835, 1845, 1855, 1865, 1875, 1885, 1895, 1925, 1935, 1945, 1955, 1965, 1975, 1985, 1995 });
@@ -549,8 +549,8 @@ public virtual void TestSpanPayloadCheck()
             clauses[1] = term2;
             snq = new SpanNearQuery(clauses, 0, true);
 #pragma warning disable 612, 618
-            pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.CHARSET_UTF_8));
-            pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.CHARSET_UTF_8));
+            pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
 #pragma warning restore 612, 618
             list = new JCG.List<byte[]>();
             list.Add(pay.Bytes);
@@ -563,9 +563,9 @@ public virtual void TestSpanPayloadCheck()
             clauses[2] = new SpanTermQuery(new Term("field", "five"));
             snq = new SpanNearQuery(clauses, 0, true);
 #pragma warning disable 612, 618
-            pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.CHARSET_UTF_8));
-            pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.CHARSET_UTF_8));
-            BytesRef pay3 = new BytesRef(("pos: " + 2).GetBytes(IOUtils.CHARSET_UTF_8));
+            pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            BytesRef pay3 = new BytesRef(("pos: " + 2).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
 #pragma warning restore 612, 618
             list = new JCG.List<byte[]>();
             list.Add(pay.Bytes);
@@ -597,10 +597,10 @@ public virtual void TestComplexSpanChecks()
 
             var payloads = new JCG.List<byte[]>();
 #pragma warning disable 612, 618
-            BytesRef pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.CHARSET_UTF_8));
-            BytesRef pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.CHARSET_UTF_8));
-            BytesRef pay3 = new BytesRef(("pos: " + 3).GetBytes(IOUtils.CHARSET_UTF_8));
-            BytesRef pay4 = new BytesRef(("pos: " + 4).GetBytes(IOUtils.CHARSET_UTF_8));
+            BytesRef pay = new BytesRef(("pos: " + 0).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            BytesRef pay2 = new BytesRef(("pos: " + 1).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            BytesRef pay3 = new BytesRef(("pos: " + 3).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
+            BytesRef pay4 = new BytesRef(("pos: " + 4).GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM));
 #pragma warning restore 612, 618
             payloads.Add(pay.Bytes);
             payloads.Add(pay2.Bytes);

src/Lucene.Net.Tests/Util/TestOfflineSorter.cs

@@ -86,7 +86,7 @@ public virtual void TestEmpty_AsStream()
         public virtual void TestSingleLine()
         {
 #pragma warning disable 612, 618
-            CheckSort(new OfflineSorter(), new byte[][] { "Single line only.".GetBytes(IOUtils.CHARSET_UTF_8) });
+            CheckSort(new OfflineSorter(), new byte[][] { "Single line only.".GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM) });
 #pragma warning restore 612, 618
         }
 
@@ -95,7 +95,7 @@ public virtual void TestSingleLine()
         public virtual void TestSingleLine_AsStream()
         {
 #pragma warning disable 612, 618
-            CheckSortAsStream(new OfflineSorter(), new byte[][] { "Single line only.".GetBytes(IOUtils.CHARSET_UTF_8) });
+            CheckSortAsStream(new OfflineSorter(), new byte[][] { "Single line only.".GetBytes(IOUtils.ENCODING_UTF_8_NO_BOM) });
 #pragma warning restore 612, 618
         }
 

src/Lucene.Net/Codecs/Compressing/CompressingStoredFieldsReader.cs

@@ -205,7 +205,7 @@ private static void ReadField(DataInput @in, StoredFieldVisitor visitor, FieldIn
                     data = new byte[length];
                     @in.ReadBytes(data, 0, length);
 #pragma warning disable 612, 618
-                    visitor.StringField(info, IOUtils.CHARSET_UTF_8.GetString(data));
+                    visitor.StringField(info, IOUtils.ENCODING_UTF_8_NO_BOM.GetString(data));
 #pragma warning restore 612, 618
                     break;
 

src/Lucene.Net/Codecs/Lucene3x/Lucene3xStoredFieldsReader.cs

@@ -334,7 +334,7 @@ private void ReadField(StoredFieldVisitor visitor, FieldInfo info, int bits)
                 }
                 else
                 {
-                    visitor.StringField(info, IOUtils.CHARSET_UTF_8.GetString(bytes));
+                    visitor.StringField(info, IOUtils.ENCODING_UTF_8_NO_BOM.GetString(bytes));
                 }
             }
         }

src/Lucene.Net/Codecs/Lucene40/Lucene40StoredFieldsReader.cs

@@ -239,7 +239,7 @@ private void ReadField(StoredFieldVisitor visitor, FieldInfo info, int bits)
                 else
                 {
 #pragma warning disable 612, 618
-                    visitor.StringField(info, IOUtils.CHARSET_UTF_8.GetString(bytes));
+                    visitor.StringField(info, IOUtils.ENCODING_UTF_8_NO_BOM.GetString(bytes));
 #pragma warning restore 612, 618
                 }
             }

src/Lucene.Net/Support/StandardCharsets.cs

@@ -22,9 +22,9 @@ namespace Lucene.Net.Support;
 
 internal static class StandardCharsets
 {
-    /// <inheritdoc cref="IOUtils.CHARSET_UTF_8"/>
+    /// <inheritdoc cref="IOUtils.ENCODING_UTF_8_NO_BOM"/>
     /// <remarks>
-    /// This is a convenience reference to <see cref="IOUtils.CHARSET_UTF_8"/>.
+    /// This is a convenience reference to <see cref="IOUtils.ENCODING_UTF_8_NO_BOM"/>.
     /// </remarks>
-    public static readonly Encoding UTF_8 = IOUtils.CHARSET_UTF_8;
+    public static readonly Encoding UTF_8 = IOUtils.ENCODING_UTF_8_NO_BOM;
 }

src/Lucene.Net/Util/IOUtils.cs

@@ -51,15 +51,15 @@ public static class IOUtils // LUCENENET specific - made static
         /// For reading data, either this or <see cref="Encoding.UTF8"/> can be used,
         /// as both will correctly interpret data with or without a BOM.
         /// </summary>
-        public static readonly Encoding CHARSET_UTF_8 = new UTF8Encoding(
+        public static readonly Encoding ENCODING_UTF_8_NO_BOM = new UTF8Encoding(
             encoderShouldEmitUTF8Identifier: false,
             throwOnInvalidBytes: true);
 
         /// <summary>
         /// UTF-8 charset string.
-        /// <para/>Where possible, use <see cref="CHARSET_UTF_8"/> instead,
+        /// <para/>Where possible, use <see cref="ENCODING_UTF_8_NO_BOM"/> instead,
         /// as using the <see cref="string"/> constant may slow things down. </summary>
-        /// <seealso cref="CHARSET_UTF_8"/>
+        /// <seealso cref="ENCODING_UTF_8_NO_BOM"/>
         public static readonly string UTF_8 = "UTF-8";
 
         /// <summary>

src/Lucene.Net/Util/OfflineSorter.cs

@@ -600,15 +600,15 @@ public class ByteSequencesWriter : IDisposable
             /// Constructs a <see cref="ByteSequencesWriter"/> to the provided <see cref="FileStream"/>. </summary>
             /// <exception cref="ArgumentNullException"><paramref name="stream"/> is <c>null</c>.</exception>
             public ByteSequencesWriter(FileStream stream)
-                : this(new BinaryWriter(stream, IOUtils.CHARSET_UTF_8, leaveOpen: false))
+                : this(new BinaryWriter(stream, IOUtils.ENCODING_UTF_8_NO_BOM, leaveOpen: false))
             {
             }
 
             /// <summary>
             /// Constructs a <see cref="ByteSequencesWriter"/> to the provided <see cref="FileStream"/>. </summary>
             /// <exception cref="ArgumentNullException"><paramref name="stream"/> is <c>null</c>.</exception>
             public ByteSequencesWriter(FileStream stream, bool leaveOpen)
-                : this(new BinaryWriter(stream, IOUtils.CHARSET_UTF_8, leaveOpen))
+                : this(new BinaryWriter(stream, IOUtils.ENCODING_UTF_8_NO_BOM, leaveOpen))
             {
             }
 
@@ -632,7 +632,7 @@ public ByteSequencesWriter(FileInfo file)
             /// <summary>
             /// Constructs a <see cref="ByteSequencesWriter"/> to the provided <see cref="BinaryWriter"/>.
             /// <b>NOTE:</b> To match Lucene, pass the <paramref name="writer"/>'s constructor the
-            /// <see cref="IOUtils.CHARSET_UTF_8"/>, which is UTF-8 without a byte order mark.
+            /// <see cref="IOUtils.ENCODING_UTF_8_NO_BOM"/>, which is UTF-8 without a byte order mark.
             /// </summary>
             /// <exception cref="ArgumentNullException"><paramref name="writer"/> is <c>null</c>.</exception>
             public ByteSequencesWriter(BinaryWriter writer)
@@ -722,15 +722,15 @@ public class ByteSequencesReader : IDisposable
             /// Constructs a <see cref="ByteSequencesReader"/> from the provided <see cref="FileStream"/>. </summary>
             /// <exception cref="ArgumentNullException"><paramref name="stream"/> is <c>null</c>.</exception>
             public ByteSequencesReader(FileStream stream)
-                : this(new BinaryReader(stream, IOUtils.CHARSET_UTF_8, leaveOpen: false))
+                : this(new BinaryReader(stream, IOUtils.ENCODING_UTF_8_NO_BOM, leaveOpen: false))
             {
             }
 
             /// <summary>
             /// Constructs a <see cref="ByteSequencesReader"/> from the provided <see cref="FileStream"/>. </summary>
             /// <exception cref="ArgumentNullException"><paramref name="stream"/> is <c>null</c>.</exception>
             public ByteSequencesReader(FileStream stream, bool leaveOpen)
-                : this(new BinaryReader(stream, IOUtils.CHARSET_UTF_8, leaveOpen))
+                : this(new BinaryReader(stream, IOUtils.ENCODING_UTF_8_NO_BOM, leaveOpen))
             {
             }
 
@@ -756,7 +756,7 @@ public ByteSequencesReader(FileInfo file)
             /// Constructs a <see cref="ByteSequencesReader"/> from the provided <see cref="BinaryReader"/>.
             /// <para/>
             /// <b>NOTE:</b> To match Lucene, pass the <paramref name="reader"/>'s constructor the
-            /// <see cref="IOUtils.CHARSET_UTF_8"/>, which is UTF-8 without a byte order mark.
+            /// <see cref="IOUtils.ENCODING_UTF_8_NO_BOM"/>, which is UTF-8 without a byte order mark.
             /// </summary>
             /// <exception cref="ArgumentNullException"><paramref name="reader"/> is <c>null</c>.</exception>
             public ByteSequencesReader(BinaryReader reader)