You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by us...@apache.org on 2014/03/31 14:29:47 UTC
svn commit: r1583315 [2/4] - in /lucene/dev/branches/branch_4x: ./ lucene/
lucene/analysis/
lucene/analysis/common/src/java/org/apache/lucene/analysis/br/
lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/
lucene/analysis/common/src/java/o...
Modified: lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/GenerateUTR30DataFiles.java Mon Mar 31 12:29:44 2014
@@ -35,6 +35,7 @@ import java.io.OutputStreamWriter;
import java.io.Writer;
import java.net.URL;
import java.net.URLConnection;
+import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.List;
import java.util.Locale;
@@ -106,7 +107,7 @@ public class GenerateUTR30DataFiles {
private static void expandDataFileRules(File file) throws IOException {
final FileInputStream stream = new FileInputStream(file);
- final InputStreamReader reader = new InputStreamReader(stream, "UTF-8");
+ final InputStreamReader reader = new InputStreamReader(stream, StandardCharsets.UTF_8);
final BufferedReader bufferedReader = new BufferedReader(reader);
StringBuilder builder = new StringBuilder();
String line;
@@ -154,7 +155,7 @@ public class GenerateUTR30DataFiles {
if (modified) {
System.err.println("Expanding rules in and overwriting " + file.getName());
final FileOutputStream out = new FileOutputStream(file, false);
- Writer writer = new OutputStreamWriter(out, "UTF-8");
+ Writer writer = new OutputStreamWriter(out, StandardCharsets.UTF_8);
try {
writer.write(builder.toString());
} finally {
@@ -178,8 +179,8 @@ public class GenerateUTR30DataFiles {
System.err.print("Downloading " + NFKC_CF_TXT + " and making diacritic rules one-way ... ");
URLConnection connection = openConnection(new URL(norm2url, NFC_TXT));
BufferedReader reader = new BufferedReader
- (new InputStreamReader(connection.getInputStream(), "UTF-8"));
- Writer writer = new OutputStreamWriter(new FileOutputStream(NFC_TXT), "UTF-8");
+ (new InputStreamReader(connection.getInputStream(), StandardCharsets.UTF_8));
+ Writer writer = new OutputStreamWriter(new FileOutputStream(NFC_TXT), StandardCharsets.UTF_8);
try {
String line;
Modified: lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/RBBIRuleCompiler.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/RBBIRuleCompiler.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/RBBIRuleCompiler.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/icu/src/tools/java/org/apache/lucene/analysis/icu/RBBIRuleCompiler.java Mon Mar 31 12:29:44 2014
@@ -25,6 +25,7 @@ import java.io.FilenameFilter;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import com.ibm.icu.text.RuleBasedBreakIterator;
@@ -37,7 +38,7 @@ public class RBBIRuleCompiler {
static String getRules(File ruleFile) throws IOException {
StringBuilder rules = new StringBuilder();
InputStream in = new FileInputStream(ruleFile);
- BufferedReader cin = new BufferedReader(new InputStreamReader(in, "UTF-8"));
+ BufferedReader cin = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8));
String line = null;
while ((line = cin.readLine()) != null) {
if (!line.startsWith("#"))
Modified: lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/StringMockResourceLoader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/StringMockResourceLoader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/StringMockResourceLoader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/StringMockResourceLoader.java Mon Mar 31 12:29:44 2014
@@ -20,6 +20,7 @@ package org.apache.lucene.analysis.ja;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.analysis.util.ResourceLoader;
@@ -52,6 +53,6 @@ class StringMockResourceLoader implement
@Override
public InputStream openResource(String resource) throws IOException {
- return new ByteArrayInputStream(text.getBytes("UTF-8"));
+ return new ByteArrayInputStream(text.getBytes(StandardCharsets.UTF_8));
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizer.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizer.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.LineNumberReader;
import java.io.Reader;
+import java.nio.charset.StandardCharsets;
import java.util.Random;
import org.apache.lucene.analysis.Analyzer;
@@ -49,7 +50,7 @@ public class TestJapaneseTokenizer exten
}
try {
try {
- Reader reader = new InputStreamReader(is, IOUtils.CHARSET_UTF_8);
+ Reader reader = new InputStreamReader(is, StandardCharsets.UTF_8);
return new UserDictionary(reader);
} finally {
is.close();
@@ -604,7 +605,7 @@ public class TestJapaneseTokenizer exten
/*
public void testWikipedia() throws Exception {
final FileInputStream fis = new FileInputStream("/q/lucene/jawiki-20120220-pages-articles.xml");
- final Reader r = new BufferedReader(new InputStreamReader(fis, "UTF-8"));
+ final Reader r = new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8));
final long startTimeNS = System.nanoTime();
boolean done = false;
@@ -651,7 +652,7 @@ public class TestJapaneseTokenizer exten
private void doTestBocchan(int numIterations) throws Exception {
LineNumberReader reader = new LineNumberReader(new InputStreamReader(
- this.getClass().getResourceAsStream("bocchan.utf-8"), "UTF-8"));
+ this.getClass().getResourceAsStream("bocchan.utf-8"), StandardCharsets.UTF_8));
String line = reader.readLine();
reader.close();
Modified: lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestSearchMode.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestSearchMode.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestSearchMode.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestSearchMode.java Mon Mar 31 12:29:44 2014
@@ -23,12 +23,12 @@ import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.LineNumberReader;
import java.io.Reader;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode;
-import org.apache.lucene.util.IOUtils;
public class TestSearchMode extends BaseTokenStreamTestCase {
private final static String SEGMENTATION_FILENAME = "search-segmentation-tests.txt";
@@ -47,7 +47,7 @@ public class TestSearchMode extends Base
throw new FileNotFoundException("Cannot find " + SEGMENTATION_FILENAME + " in test classpath");
}
try {
- LineNumberReader reader = new LineNumberReader(new InputStreamReader(is, IOUtils.CHARSET_UTF_8));
+ LineNumberReader reader = new LineNumberReader(new InputStreamReader(is, StandardCharsets.UTF_8));
String line = null;
while ((line = reader.readLine()) != null) {
// Remove comments
Modified: lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/tools/java/org/apache/lucene/analysis/ja/util/ConnectionCostsBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/tools/java/org/apache/lucene/analysis/ja/util/ConnectionCostsBuilder.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/tools/java/org/apache/lucene/analysis/ja/util/ConnectionCostsBuilder.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/tools/java/org/apache/lucene/analysis/ja/util/ConnectionCostsBuilder.java Mon Mar 31 12:29:44 2014
@@ -24,6 +24,7 @@ import java.io.LineNumberReader;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;
+import java.nio.charset.StandardCharsets;
public class ConnectionCostsBuilder {
@@ -32,7 +33,7 @@ public class ConnectionCostsBuilder {
public static ConnectionCostsWriter build(String filename) throws IOException {
FileInputStream inputStream = new FileInputStream(filename);
- Charset cs = Charset.forName("US-ASCII");
+ Charset cs = StandardCharsets.US_ASCII;
CharsetDecoder decoder = cs.newDecoder()
.onMalformedInput(CodingErrorAction.REPORT)
.onUnmappableCharacter(CodingErrorAction.REPORT);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/AnalyzerProfile.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/AnalyzerProfile.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/AnalyzerProfile.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/AnalyzerProfile.java Mon Mar 31 12:29:44 2014
@@ -21,10 +21,9 @@ import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.util.Properties;
-import org.apache.lucene.util.IOUtils;
-
/**
* Manages analysis data configuration for SmartChineseAnalyzer
* <p>
@@ -80,7 +79,7 @@ public class AnalyzerProfile {
Properties prop = new Properties();
try {
FileInputStream input = new FileInputStream(propFile);
- prop.load(new InputStreamReader(input, IOUtils.CHARSET_UTF_8));
+ prop.load(new InputStreamReader(input, StandardCharsets.UTF_8));
String dir = prop.getProperty("analysis.data.dir", "");
input.close();
return dir;
Modified: lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java Mon Mar 31 12:29:44 2014
@@ -19,17 +19,16 @@ package org.apache.lucene.analysis.cn.sm
import java.io.IOException;
import java.io.Reader;
+import java.nio.charset.StandardCharsets;
import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.en.PorterStemFilter;
-import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
-import org.apache.lucene.analysis.cn.smart.SentenceTokenizer;
-import org.apache.lucene.analysis.cn.smart.WordTokenFilter;
import org.apache.lucene.analysis.core.StopFilter;
+import org.apache.lucene.analysis.en.PorterStemFilter;
+import org.apache.lucene.analysis.util.CharArraySet;
+import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.Version;
@@ -90,7 +89,7 @@ public final class SmartChineseAnalyzer
// make sure it is unmodifiable as we expose it in the outer class
return CharArraySet.unmodifiableSet(WordlistLoader.getWordSet(IOUtils
.getDecodingReader(SmartChineseAnalyzer.class, DEFAULT_STOPWORD_FILE,
- IOUtils.CHARSET_UTF_8), STOPWORD_FILE_COMMENT,
+ StandardCharsets.UTF_8), STOPWORD_FILE_COMMENT,
Version.LUCENE_CURRENT));
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java Mon Mar 31 12:29:44 2014
@@ -19,6 +19,7 @@ package org.apache.lucene.analysis.pl;
import java.io.IOException;
import java.io.Reader;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -76,7 +77,7 @@ public final class PolishAnalyzer extend
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getWordSet(IOUtils.getDecodingReader(PolishAnalyzer.class,
- DEFAULT_STOPWORD_FILE, IOUtils.CHARSET_UTF_8), "#", Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), "#", Version.LUCENE_CURRENT);
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
Modified: lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/test/org/egothor/stemmer/TestCompile.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/test/org/egothor/stemmer/TestCompile.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/test/org/egothor/stemmer/TestCompile.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/test/org/egothor/stemmer/TestCompile.java Mon Mar 31 12:29:44 2014
@@ -65,10 +65,10 @@ import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.LineNumberReader;
+import java.nio.charset.StandardCharsets;
import java.util.Locale;
import java.util.StringTokenizer;
-import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.TestUtil;
@@ -139,7 +139,7 @@ public class TestCompile extends LuceneT
private static void assertTrie(Trie trie, String file, boolean usefull,
boolean storeorig) throws Exception {
LineNumberReader in = new LineNumberReader(new BufferedReader(
- new InputStreamReader(new FileInputStream(file), IOUtils.CHARSET_UTF_8)));
+ new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8)));
for (String line = in.readLine(); line != null; line = in.readLine()) {
try {
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/Benchmark.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/Benchmark.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/Benchmark.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/Benchmark.java Mon Mar 31 12:29:44 2014
@@ -18,8 +18,8 @@ package org.apache.lucene.benchmark.byTa
*/
import java.io.File;
-import java.io.FileReader;
import java.io.Reader;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.benchmark.byTask.utils.Algorithm;
import org.apache.lucene.benchmark.byTask.utils.Config;
@@ -107,7 +107,7 @@ public class Benchmark {
Benchmark benchmark = null;
try {
- benchmark = new Benchmark(IOUtils.getDecodingReader(algFile, IOUtils.CHARSET_UTF_8));
+ benchmark = new Benchmark(IOUtils.getDecodingReader(algFile, StandardCharsets.UTF_8));
} catch (Exception e) {
e.printStackTrace();
System.exit(1);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DirContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DirContentSource.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DirContentSource.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DirContentSource.java Mon Mar 31 12:29:44 2014
@@ -18,7 +18,6 @@ package org.apache.lucene.benchmark.byTa
*/
import org.apache.lucene.benchmark.byTask.utils.Config;
-import org.apache.lucene.util.IOUtils;
import java.io.BufferedReader;
import java.io.File;
@@ -26,6 +25,7 @@ import java.io.FileFilter;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.text.DateFormat;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
@@ -206,7 +206,7 @@ public class DirContentSource extends Co
name = f.getCanonicalPath()+"_"+iteration;
}
- BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(f), IOUtils.CHARSET_UTF_8));
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(f), StandardCharsets.UTF_8));
String line = null;
//First line is the date, 3rd is the title, rest is body
String dateStr = reader.readLine();
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DocMaker.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DocMaker.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DocMaker.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/DocMaker.java Mon Mar 31 12:29:44 2014
@@ -20,6 +20,7 @@ package org.apache.lucene.benchmark.byTa
import java.io.Closeable;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
+import java.nio.charset.StandardCharsets;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
import java.util.Calendar;
@@ -317,7 +318,7 @@ public class DocMaker implements Closeab
if (storeBytes) {
Field bytesField = ds.getField(BYTES_FIELD, StringField.TYPE_STORED);
- bytesField.setBytesValue(bdy.getBytes("UTF-8"));
+ bytesField.setBytesValue(bdy.getBytes(StandardCharsets.UTF_8));
doc.add(bytesField);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java Mon Mar 31 12:29:44 2014
@@ -20,18 +20,15 @@ package org.apache.lucene.benchmark.byTa
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
-import java.io.BufferedReader;
-import java.io.InputStreamReader;
-import java.nio.charset.CharsetDecoder;
-import java.nio.charset.CodingErrorAction;
+import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.Locale;
import java.util.Map;
import org.apache.lucene.benchmark.byTask.utils.Config;
import org.apache.lucene.benchmark.byTask.utils.StreamUtils;
-import org.apache.lucene.util.ThreadInterruptedException;
import org.apache.lucene.util.IOUtils;
+import org.apache.lucene.util.ThreadInterruptedException;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
@@ -182,10 +179,7 @@ public class EnwikiContentSource extends
if (localFileIS != null) { // null means fileIS was closed on us
try {
// To work around a bug in XERCES (XERCESJ-1257), we assume the XML is always UTF8, so we simply provide reader.
- CharsetDecoder decoder = IOUtils.CHARSET_UTF_8.newDecoder()
- .onMalformedInput(CodingErrorAction.REPORT)
- .onUnmappableCharacter(CodingErrorAction.REPORT);
- reader.parse(new InputSource(new BufferedReader(new InputStreamReader(localFileIS, decoder))));
+ reader.parse(new InputSource(IOUtils.getDecodingReader(localFileIS, StandardCharsets.UTF_8)));
} catch (IOException ioe) {
synchronized(EnwikiContentSource.this) {
if (localFileIS != is) {
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/FileBasedQueryMaker.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/FileBasedQueryMaker.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/FileBasedQueryMaker.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/FileBasedQueryMaker.java Mon Mar 31 12:29:44 2014
@@ -9,6 +9,7 @@ import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.Version;
import java.io.*;
+import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.List;
@@ -62,12 +63,12 @@ public class FileBasedQueryMaker extends
Reader reader = null;
// note: we use a decoding reader, so if your queries are screwed up you know
if (file.exists()) {
- reader = IOUtils.getDecodingReader(file, IOUtils.CHARSET_UTF_8);
+ reader = IOUtils.getDecodingReader(file, StandardCharsets.UTF_8);
} else {
//see if we can find it as a resource
InputStream asStream = FileBasedQueryMaker.class.getClassLoader().getResourceAsStream(fileName);
if (asStream != null) {
- reader = IOUtils.getDecodingReader(asStream, IOUtils.CHARSET_UTF_8);
+ reader = IOUtils.getDecodingReader(asStream, StandardCharsets.UTF_8);
}
}
if (reader != null) {
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/LineDocSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/LineDocSource.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/LineDocSource.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/LineDocSource.java Mon Mar 31 12:29:44 2014
@@ -29,6 +29,7 @@ import java.util.Properties;
import org.apache.lucene.benchmark.byTask.tasks.WriteLineDocTask;
import org.apache.lucene.benchmark.byTask.utils.Config;
import org.apache.lucene.benchmark.byTask.utils.StreamUtils;
+import org.apache.lucene.util.IOUtils;
/**
* A {@link ContentSource} reading one line at a time as a
@@ -277,7 +278,7 @@ public class LineDocSource extends Conte
}
file = new File(fileName).getAbsoluteFile();
if (encoding == null) {
- encoding = "UTF-8";
+ encoding = IOUtils.UTF_8;
}
}
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.text.DateFormat;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
@@ -30,7 +31,6 @@ import java.util.Date;
import java.util.Locale;
import org.apache.lucene.benchmark.byTask.utils.Config;
-import org.apache.lucene.util.IOUtils;
/**
* A {@link ContentSource} reading from the Reuters collection.
@@ -114,7 +114,7 @@ public class ReutersContentSource extend
name = f.getCanonicalPath() + "_" + iteration;
}
- BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(f), IOUtils.CHARSET_UTF_8));
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(f), StandardCharsets.UTF_8));
try {
// First line is the date, 3rd is the title, rest is body
String dateStr = reader.readLine();
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.text.DateFormat;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
@@ -320,7 +321,7 @@ public class TrecContentSource extends C
}
// encoding
if (encoding == null) {
- encoding = "ISO-8859-1";
+ encoding = StandardCharsets.ISO_8859_1.name();
}
// iteration exclusion in doc name
excludeDocnameIteration = config.get("content.source.excludeIteration", false);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTask.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTask.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTask.java Mon Mar 31 12:29:44 2014
@@ -5,6 +5,7 @@ import java.io.File;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.benchmark.byTask.PerfRunData;
import org.apache.lucene.benchmark.byTask.feeds.DocMaker;
@@ -41,7 +42,7 @@ public class WriteEnwikiLineDocTask exte
public WriteEnwikiLineDocTask(PerfRunData runData) throws Exception {
super(runData);
OutputStream out = StreamUtils.outputStream(categoriesLineFile(new File(fname)));
- categoryLineFileOut = new PrintWriter(new BufferedWriter(new OutputStreamWriter(out, "UTF-8"), StreamUtils.BUFFER_SIZE));
+ categoryLineFileOut = new PrintWriter(new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8), StreamUtils.BUFFER_SIZE));
writeHeader(categoryLineFileOut);
}
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.File;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
+import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.HashSet;
import java.util.regex.Matcher;
@@ -101,7 +102,7 @@ public class WriteLineDocTask extends Pe
throw new IllegalArgumentException("line.file.out must be set");
}
OutputStream out = StreamUtils.outputStream(new File(fname));
- lineFileOut = new PrintWriter(new BufferedWriter(new OutputStreamWriter(out, "UTF-8"), StreamUtils.BUFFER_SIZE));
+ lineFileOut = new PrintWriter(new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8), StreamUtils.BUFFER_SIZE));
docMaker = runData.getDocMaker();
// init fields
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java Mon Mar 31 12:29:44 2014
@@ -31,6 +31,7 @@ import java.io.File;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
import java.util.HashSet;
import java.util.Set;
@@ -53,7 +54,7 @@ public class QueryDriver {
File topicsFile = new File(args[0]);
File qrelsFile = new File(args[1]);
- SubmissionReport submitLog = new SubmissionReport(new PrintWriter(args[2], "UTF-8"), "lucene");
+ SubmissionReport submitLog = new SubmissionReport(new PrintWriter(args[2], IOUtils.UTF_8 /* huh, no nio.Charset ctor? */), "lucene");
FSDirectory dir = FSDirectory.open(new File(args[3]));
String fieldSpec = args.length == 5 ? args[4] : "T"; // default to Title-only if not specified.
IndexReader reader = DirectoryReader.open(dir);
@@ -66,10 +67,10 @@ public class QueryDriver {
// use trec utilities to read trec topics into quality queries
TrecTopicsReader qReader = new TrecTopicsReader();
- QualityQuery qqs[] = qReader.readQueries(new BufferedReader(IOUtils.getDecodingReader(topicsFile, IOUtils.CHARSET_UTF_8)));
+ QualityQuery qqs[] = qReader.readQueries(new BufferedReader(IOUtils.getDecodingReader(topicsFile, StandardCharsets.UTF_8)));
// prepare judge, with trec utilities that read from a QRels file
- Judge judge = new TrecJudge(new BufferedReader(IOUtils.getDecodingReader(qrelsFile, IOUtils.CHARSET_UTF_8)));
+ Judge judge = new TrecJudge(new BufferedReader(IOUtils.getDecodingReader(qrelsFile, StandardCharsets.UTF_8)));
// validate topics & judgments match each other
judge.validateData(qqs, logger);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java Mon Mar 31 12:29:44 2014
@@ -21,16 +21,13 @@ import java.io.File;
import java.io.FileFilter;
import java.io.FileInputStream;
import java.io.FileOutputStream;
-import java.io.FileReader;
-import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
+import java.nio.charset.StandardCharsets;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
-import org.apache.lucene.util.IOUtils;
-
/**
* Split the Reuters SGML documents into Simple Text files containing: Title, Date, Dateline, Body
@@ -78,7 +75,7 @@ public class ExtractReuters {
*/
protected void extractFile(File sgmFile) {
try {
- BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(sgmFile), IOUtils.CHARSET_UTF_8));
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(sgmFile), StandardCharsets.UTF_8));
StringBuilder buffer = new StringBuilder(1024);
StringBuilder outBuffer = new StringBuilder(1024);
@@ -112,7 +109,7 @@ public class ExtractReuters {
File outFile = new File(outputDir, sgmFile.getName() + "-"
+ (docNumber++) + ".txt");
// System.out.println("Writing " + outFile);
- OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(outFile), IOUtils.CHARSET_UTF_8);
+ OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(outFile), StandardCharsets.UTF_8);
writer.write(out);
writer.close();
outBuffer.setLength(0);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
+import java.nio.charset.StandardCharsets;
import java.util.Properties;
import org.apache.lucene.benchmark.byTask.feeds.ContentSource;
@@ -30,7 +31,6 @@ import org.apache.lucene.benchmark.byTas
import org.apache.lucene.benchmark.byTask.feeds.NoMoreDataException;
import org.apache.lucene.benchmark.byTask.utils.Config;
import org.apache.lucene.document.Document;
-import org.apache.lucene.util.IOUtils;
/**
* Extract the downloaded Wikipedia dump into separate files for indexing.
@@ -86,7 +86,7 @@ public class ExtractWikipedia {
contents.append("\n");
try {
- Writer writer = new OutputStreamWriter(new FileOutputStream(f), IOUtils.CHARSET_UTF_8);
+ Writer writer = new OutputStreamWriter(new FileOutputStream(f), StandardCharsets.UTF_8);
writer.write(contents.toString());
writer.close();
} catch (IOException ioe) {
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksLogic.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksLogic.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksLogic.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksLogic.java Mon Mar 31 12:29:44 2014
@@ -21,6 +21,7 @@ import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.text.Collator;
import java.util.List;
import java.util.Locale;
@@ -408,7 +409,7 @@ public class TestPerfTasksLogic extends
BufferedReader r = new BufferedReader(
new InputStreamReader(
- new FileInputStream(lineFile), "UTF-8"));
+ new FileInputStream(lineFile), StandardCharsets.UTF_8));
int numLines = 0;
String line;
while((line = r.readLine()) != null) {
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java Mon Mar 31 12:29:44 2014
@@ -25,6 +25,7 @@ import java.io.IOException;
import java.io.InputStreamReader;
import java.io.StringReader;
import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import org.apache.lucene.benchmark.byTask.feeds.AbstractQueryMaker;
@@ -120,7 +121,7 @@ public class TestPerfTasksParse extends
public boolean accept(File pathname) { return pathname.isFile() && pathname.getName().endsWith(".alg"); }
})) {
try {
- Config config = new Config(new InputStreamReader(new FileInputStream(algFile), "UTF-8"));
+ Config config = new Config(new InputStreamReader(new FileInputStream(algFile), StandardCharsets.UTF_8));
String contentSource = config.get("content.source", null);
if (contentSource != null) { Class.forName(contentSource); }
config.set("work.dir", new File(TEMP_DIR,"work").getAbsolutePath());
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java Mon Mar 31 12:29:44 2014
@@ -36,6 +36,7 @@ import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
+import org.apache.lucene.util.IOUtils;
/** Tests the functionality of {@link DocMaker}. */
public class DocMakerTest extends BenchmarkTestCase {
@@ -166,7 +167,7 @@ public class DocMakerTest extends Benchm
// DocMaker did not close its ContentSource if resetInputs was called twice,
// leading to a file handle leak.
File f = new File(getWorkDir(), "docMakerLeak.txt");
- PrintStream ps = new PrintStream(f, "UTF-8");
+ PrintStream ps = new PrintStream(f, IOUtils.UTF_8);
ps.println("one title\t" + System.currentTimeMillis() + "\tsome content");
ps.close();
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSourceTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSourceTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSourceTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSourceTest.java Mon Mar 31 12:29:44 2014
@@ -18,15 +18,13 @@ package org.apache.lucene.benchmark.byTa
*/
import java.io.ByteArrayInputStream;
-import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
-import java.io.OutputStreamWriter;
+import java.nio.charset.StandardCharsets;
import java.text.ParseException;
import java.util.Properties;
import org.apache.lucene.benchmark.byTask.utils.Config;
-import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.LuceneTestCase;
import org.junit.Test;
@@ -43,7 +41,7 @@ public class EnwikiContentSourceTest ext
@Override
protected InputStream openInputStream() throws IOException {
- return new ByteArrayInputStream(docs.getBytes(IOUtils.CHARSET_UTF_8));
+ return new ByteArrayInputStream(docs.getBytes(StandardCharsets.UTF_8));
}
}
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/LineDocSourceTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/LineDocSourceTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/LineDocSourceTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/LineDocSourceTest.java Mon Mar 31 12:29:44 2014
@@ -23,6 +23,7 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
+import java.nio.charset.StandardCharsets;
import java.util.Properties;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
@@ -53,7 +54,7 @@ public class LineDocSourceTest extends B
private void createBZ2LineFile(File file, boolean addHeader) throws Exception {
OutputStream out = new FileOutputStream(file);
out = csFactory.createCompressorOutputStream("bzip2", out);
- BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, "utf-8"));
+ BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8));
writeDocsToFile(writer, addHeader, null);
writer.close();
}
@@ -90,14 +91,14 @@ public class LineDocSourceTest extends B
private void createRegularLineFile(File file, boolean addHeader) throws Exception {
OutputStream out = new FileOutputStream(file);
- BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, "utf-8"));
+ BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8));
writeDocsToFile(writer, addHeader, null);
writer.close();
}
private void createRegularLineFileWithMoreFields(File file, String...extraFields) throws Exception {
OutputStream out = new FileOutputStream(file);
- BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, "utf-8"));
+ BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(out, StandardCharsets.UTF_8));
Properties p = new Properties();
for (String f : extraFields) {
p.setProperty(f, f);
@@ -209,7 +210,7 @@ public class LineDocSourceTest extends B
for (int i = 0; i < testCases.length; i++) {
File file = new File(getWorkDir(), "one-line");
- BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file), "utf-8"));
+ BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file), StandardCharsets.UTF_8));
writer.write(testCases[i]);
writer.newLine();
writer.close();
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTaskTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTaskTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTaskTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteEnwikiLineDocTaskTest.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.util.Properties;
import java.util.concurrent.atomic.AtomicInteger;
@@ -73,7 +74,7 @@ public class WriteEnwikiLineDocTaskTest
private void doReadTest(int n, File file, String expTitle, String expDate, String expBody) throws Exception {
InputStream in = new FileInputStream(file);
- BufferedReader br = new BufferedReader(new InputStreamReader(in, "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8));
try {
String line = br.readLine();
WriteLineDocTaskTest.assertHeaderLine(line);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTaskTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTaskTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTaskTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTaskTest.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.nio.charset.StandardCharsets;
import java.util.HashSet;
import java.util.Properties;
import java.util.Set;
@@ -168,7 +169,7 @@ public class WriteLineDocTaskTest extend
default:
assertFalse("Unknown file type!",true); //fail, should not happen
}
- BufferedReader br = new BufferedReader(new InputStreamReader(in, "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8));
try {
String line = br.readLine();
assertHeaderLine(line);
@@ -274,7 +275,7 @@ public class WriteLineDocTaskTest extend
wldt.doLogic();
wldt.close();
- BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8));
try {
String line = br.readLine();
assertHeaderLine(line);
@@ -292,7 +293,7 @@ public class WriteLineDocTaskTest extend
wldt.doLogic();
wldt.close();
- BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8));
try {
String line = br.readLine();
assertHeaderLine(line);
@@ -310,7 +311,7 @@ public class WriteLineDocTaskTest extend
wldt.doLogic();
wldt.close();
- BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8));
try {
String line = br.readLine();
assertHeaderLine(line);
@@ -345,7 +346,7 @@ public class WriteLineDocTaskTest extend
wldt.close();
Set<String> ids = new HashSet<>();
- BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), "utf-8"));
+ BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(file), StandardCharsets.UTF_8));
try {
String line = br.readLine();
assertHeaderLine(line); // header line is written once, no matter how many threads there are
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java Mon Mar 31 12:29:44 2014
@@ -26,10 +26,10 @@ import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
+import java.nio.charset.StandardCharsets;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
import org.apache.lucene.benchmark.BenchmarkTestCase;
-import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.TestUtil;
import org.junit.After;
import org.junit.Before;
@@ -87,7 +87,7 @@ public class StreamUtilsTest extends Ben
private File rawTextFile(String ext) throws Exception {
File f = new File(testDir,"testfile." + ext);
- BufferedWriter w = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(f), IOUtils.CHARSET_UTF_8));
+ BufferedWriter w = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(f), StandardCharsets.UTF_8));
w.write(TEXT);
w.newLine();
w.close();
@@ -116,7 +116,7 @@ public class StreamUtilsTest extends Ben
}
private void writeText(OutputStream os) throws IOException {
- BufferedWriter w = new BufferedWriter(new OutputStreamWriter(os, IOUtils.CHARSET_UTF_8));
+ BufferedWriter w = new BufferedWriter(new OutputStreamWriter(os, StandardCharsets.UTF_8));
w.write(TEXT);
w.newLine();
w.close();
@@ -124,7 +124,7 @@ public class StreamUtilsTest extends Ben
private void assertReadText(File f) throws Exception {
InputStream ir = StreamUtils.inputStream(f);
- InputStreamReader in = new InputStreamReader(ir, IOUtils.CHARSET_UTF_8);
+ InputStreamReader in = new InputStreamReader(ir, StandardCharsets.UTF_8);
BufferedReader r = new BufferedReader(in);
String line = r.readLine();
assertEquals("Wrong text found in "+f.getName(), TEXT, line);
Modified: lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java (original)
+++ lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java Mon Mar 31 12:29:44 2014
@@ -34,6 +34,7 @@ import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
/**
* Test that quality run does its job.
@@ -62,11 +63,11 @@ public class TestQualityRun extends Benc
// prepare topics
InputStream topics = getClass().getResourceAsStream("trecTopics.txt");
TrecTopicsReader qReader = new TrecTopicsReader();
- QualityQuery qqs[] = qReader.readQueries(new BufferedReader(new InputStreamReader(topics, "UTF-8")));
+ QualityQuery qqs[] = qReader.readQueries(new BufferedReader(new InputStreamReader(topics, StandardCharsets.UTF_8)));
// prepare judge
InputStream qrels = getClass().getResourceAsStream("trecQRels.txt");
- Judge judge = new TrecJudge(new BufferedReader(new InputStreamReader(qrels, "UTF-8")));
+ Judge judge = new TrecJudge(new BufferedReader(new InputStreamReader(qrels, StandardCharsets.UTF_8)));
// validate topics & judgments match each other
judge.validateData(qqs, logger);
@@ -147,7 +148,7 @@ public class TestQualityRun extends Benc
InputStream topicsFile = getClass().getResourceAsStream("trecTopics.txt");
TrecTopicsReader qReader = new TrecTopicsReader();
QualityQuery qqs[] = qReader.readQueries(
- new BufferedReader(new InputStreamReader(topicsFile, "UTF-8")));
+ new BufferedReader(new InputStreamReader(topicsFile, StandardCharsets.UTF_8)));
assertEquals(20, qqs.length);
Modified: lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextDocValuesReader.java Mon Mar 31 12:29:44 2014
@@ -30,6 +30,7 @@ import static org.apache.lucene.codecs.s
import java.io.IOException;
import java.math.BigDecimal;
import java.math.BigInteger;
+import java.nio.charset.StandardCharsets;
import java.text.DecimalFormat;
import java.text.DecimalFormatSymbols;
import java.text.ParseException;
@@ -225,7 +226,7 @@ class SimpleTextDocValuesReader extends
assert StringHelper.startsWith(scratch, LENGTH);
int len;
try {
- len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, "UTF-8")).intValue();
+ len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, StandardCharsets.UTF_8)).intValue();
} catch (ParseException pe) {
CorruptIndexException e = new CorruptIndexException("failed to parse int length (resource=" + in + ")");
e.initCause(pe);
@@ -257,7 +258,7 @@ class SimpleTextDocValuesReader extends
assert StringHelper.startsWith(scratch, LENGTH);
int len;
try {
- len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, "UTF-8")).intValue();
+ len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, StandardCharsets.UTF_8)).intValue();
} catch (ParseException pe) {
CorruptIndexException e = new CorruptIndexException("failed to parse int length (resource=" + in + ")");
e.initCause(pe);
@@ -326,7 +327,7 @@ class SimpleTextDocValuesReader extends
assert StringHelper.startsWith(scratch, LENGTH): "got " + scratch.utf8ToString() + " in=" + in;
int len;
try {
- len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, "UTF-8")).intValue();
+ len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, StandardCharsets.UTF_8)).intValue();
} catch (ParseException pe) {
CorruptIndexException e = new CorruptIndexException("failed to parse int length (resource=" + in + ")");
e.initCause(pe);
@@ -404,7 +405,7 @@ class SimpleTextDocValuesReader extends
assert StringHelper.startsWith(scratch, LENGTH): "got " + scratch.utf8ToString() + " in=" + in;
int len;
try {
- len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, "UTF-8")).intValue();
+ len = decoder.parse(new String(scratch.bytes, scratch.offset + LENGTH.length, scratch.length - LENGTH.length, StandardCharsets.UTF_8)).intValue();
} catch (ParseException pe) {
CorruptIndexException e = new CorruptIndexException("failed to parse int length (resource=" + in + ")");
e.initCause(pe);
@@ -460,7 +461,7 @@ class SimpleTextDocValuesReader extends
/** Used only in ctor: */
private String stripPrefix(BytesRef prefix) throws IOException {
- return new String(scratch.bytes, scratch.offset + prefix.length, scratch.length - prefix.length, "UTF-8");
+ return new String(scratch.bytes, scratch.offset + prefix.length, scratch.length - prefix.length, StandardCharsets.UTF_8);
}
@Override
Modified: lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldInfosReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldInfosReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldInfosReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldInfosReader.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,7 @@ package org.apache.lucene.codecs.simplet
*/
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;
@@ -154,6 +155,6 @@ public class SimpleTextFieldInfosReader
}
private String readString(int offset, BytesRef scratch) {
- return new String(scratch.bytes, scratch.offset+offset, scratch.length-offset, IOUtils.CHARSET_UTF_8);
+ return new String(scratch.bytes, scratch.offset+offset, scratch.length-offset, StandardCharsets.UTF_8);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextFieldsReader.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,7 @@ package org.apache.lucene.codecs.simplet
*/
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
@@ -91,7 +92,7 @@ class SimpleTextFieldsReader extends Fie
if (scratch.equals(END)) {
return fields;
} else if (StringHelper.startsWith(scratch, FIELD)) {
- String fieldName = new String(scratch.bytes, scratch.offset + FIELD.length, scratch.length - FIELD.length, "UTF-8");
+ String fieldName = new String(scratch.bytes, scratch.offset + FIELD.length, scratch.length - FIELD.length, StandardCharsets.UTF_8);
fields.put(fieldName, in.getFilePointer());
}
}
Modified: lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextSegmentInfoReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextSegmentInfoReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextSegmentInfoReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextSegmentInfoReader.java Mon Mar 31 12:29:44 2014
@@ -27,6 +27,7 @@ import static org.apache.lucene.codecs.s
import static org.apache.lucene.codecs.simpletext.SimpleTextSegmentInfoWriter.SI_VERSION;
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Map;
@@ -112,6 +113,6 @@ public class SimpleTextSegmentInfoReader
}
private String readString(int offset, BytesRef scratch) {
- return new String(scratch.bytes, scratch.offset+offset, scratch.length-offset, IOUtils.CHARSET_UTF_8);
+ return new String(scratch.bytes, scratch.offset+offset, scratch.length-offset, StandardCharsets.UTF_8);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextStoredFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextStoredFieldsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextStoredFieldsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/codecs/src/java/org/apache/lucene/codecs/simpletext/SimpleTextStoredFieldsReader.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,7 @@ package org.apache.lucene.codecs.simplet
*/
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.codecs.StoredFieldsReader;
import org.apache.lucene.index.FieldInfo;
@@ -141,7 +142,7 @@ public class SimpleTextStoredFieldsReade
readLine();
assert StringHelper.startsWith(scratch, VALUE);
if (type == TYPE_STRING) {
- visitor.stringField(fieldInfo, new String(scratch.bytes, scratch.offset+VALUE.length, scratch.length-VALUE.length, "UTF-8"));
+ visitor.stringField(fieldInfo, new String(scratch.bytes, scratch.offset+VALUE.length, scratch.length-VALUE.length, StandardCharsets.UTF_8));
} else if (type == TYPE_BINARY) {
byte[] copy = new byte[scratch.length-VALUE.length];
System.arraycopy(scratch.bytes, scratch.offset+VALUE.length, copy, 0, copy.length);
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java Mon Mar 31 12:29:44 2014
@@ -398,7 +398,7 @@ public class BlockTreeTermsReader extend
final ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
PrintStream out;
try {
- out = new PrintStream(bos, false, "UTF-8");
+ out = new PrintStream(bos, false, IOUtils.UTF_8);
} catch (UnsupportedEncodingException bogus) {
throw new RuntimeException(bogus);
}
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/compressing/CompressingStoredFieldsReader.java Mon Mar 31 12:29:44 2014
@@ -35,6 +35,7 @@ import static org.apache.lucene.codecs.l
import java.io.EOFException;
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import org.apache.lucene.codecs.CodecUtil;
@@ -187,7 +188,7 @@ public final class CompressingStoredFiel
length = in.readVInt();
data = new byte[length];
in.readBytes(data, 0, length);
- visitor.stringField(info, new String(data, IOUtils.CHARSET_UTF_8));
+ visitor.stringField(info, new String(data, StandardCharsets.UTF_8));
break;
case NUMERIC_INT:
visitor.intField(info, in.readInt());
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene3x/Lucene3xStoredFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene3x/Lucene3xStoredFieldsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene3x/Lucene3xStoredFieldsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene3x/Lucene3xStoredFieldsReader.java Mon Mar 31 12:29:44 2014
@@ -37,6 +37,7 @@ import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.RamUsageEstimator;
import java.io.Closeable;
+import java.nio.charset.StandardCharsets;
/**
* Class responsible for access to stored document fields.
@@ -273,7 +274,7 @@ final class Lucene3xStoredFieldsReader e
if ((bits & FIELD_IS_BINARY) != 0) {
visitor.binaryField(info, bytes);
} else {
- visitor.stringField(info, new String(bytes, 0, bytes.length, IOUtils.CHARSET_UTF_8));
+ visitor.stringField(info, new String(bytes, 0, bytes.length, StandardCharsets.UTF_8));
}
}
}
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/codecs/lucene40/Lucene40StoredFieldsReader.java Mon Mar 31 12:29:44 2014
@@ -34,6 +34,7 @@ import org.apache.lucene.store.IndexInpu
import org.apache.lucene.util.IOUtils;
import java.io.Closeable;
+import java.nio.charset.StandardCharsets;
import static org.apache.lucene.codecs.lucene40.Lucene40StoredFieldsWriter.*;
@@ -193,7 +194,7 @@ public final class Lucene40StoredFieldsR
if ((bits & FIELD_IS_BINARY) != 0) {
visitor.binaryField(info, bytes);
} else {
- visitor.stringField(info, new String(bytes, 0, bytes.length, IOUtils.CHARSET_UTF_8));
+ visitor.stringField(info, new String(bytes, 0, bytes.length, StandardCharsets.UTF_8));
}
}
}
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/index/Term.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/index/Term.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/index/Term.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/index/Term.java Mon Mar 31 12:29:44 2014
@@ -21,9 +21,9 @@ import java.nio.ByteBuffer;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;
+import java.nio.charset.StandardCharsets;
import org.apache.lucene.util.BytesRef;
-import org.apache.lucene.util.IOUtils;
/**
A Term represents a word from text. This is the unit of search. It is
@@ -83,7 +83,7 @@ public final class Term implements Compa
* the raw bytes will be printed instead. */
public static final String toString(BytesRef termText) {
// the term might not be text, but usually is. so we make a best effort
- CharsetDecoder decoder = IOUtils.CHARSET_UTF_8.newDecoder()
+ CharsetDecoder decoder = StandardCharsets.UTF_8.newDecoder()
.onMalformedInput(CodingErrorAction.REPORT)
.onUnmappableCharacter(CodingErrorAction.REPORT);
try {
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/store/DataInput.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/store/DataInput.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/store/DataInput.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/store/DataInput.java Mon Mar 31 12:29:44 2014
@@ -18,13 +18,12 @@ package org.apache.lucene.store;
*/
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Map;
import java.util.Set;
-import org.apache.lucene.util.IOUtils;
-
/**
* Abstract base class for performing read operations of Lucene's low-level
* data types.
@@ -188,7 +187,7 @@ public abstract class DataInput implemen
int length = readVInt();
final byte[] bytes = new byte[length];
readBytes(bytes, 0, length);
- return new String(bytes, 0, length, IOUtils.CHARSET_UTF_8);
+ return new String(bytes, 0, length, StandardCharsets.UTF_8);
}
/** Returns a clone of this stream.
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/IOUtils.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/IOUtils.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/IOUtils.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/IOUtils.java Mon Mar 31 12:29:44 2014
@@ -28,10 +28,10 @@ import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
-import java.lang.reflect.Method;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CodingErrorAction;
+import java.nio.charset.StandardCharsets;
/** This class emulates the new Java 7 "Try-With-Resources" statement.
* Remove once Lucene is on Java 7.
@@ -39,16 +39,21 @@ import java.nio.charset.CodingErrorActio
public final class IOUtils {
/**
- * UTF-8 charset string
- * @see Charset#forName(String)
+ * UTF-8 {@link Charset} instance to prevent repeated
+ * {@link Charset#forName(String)} lookups
+ * @deprecated Use {@link StandardCharsets#UTF_8} instead.
*/
- public static final String UTF_8 = "UTF-8";
+ @Deprecated
+ public static final Charset CHARSET_UTF_8 = StandardCharsets.UTF_8;
/**
- * UTF-8 {@link Charset} instance to prevent repeated
- * {@link Charset#forName(String)} lookups
+ * UTF-8 charset string.
+ * <p>Where possible, use {@link StandardCharsets#UTF_8} instead,
+ * as using the String constant may slow things down.
+ * @see StandardCharsets#UTF_8
*/
- public static final Charset CHARSET_UTF_8 = Charset.forName("UTF-8");
+ public static final String UTF_8 = StandardCharsets.UTF_8.name();
+
private IOUtils() {} // no instance
/**
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java Mon Mar 31 12:29:44 2014
@@ -22,6 +22,7 @@ import java.io.InputStream;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
+import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Enumeration;
@@ -91,7 +92,7 @@ public final class SPIClassIterator<S> i
final InputStream in = url.openStream();
IOException priorE = null;
try {
- final BufferedReader reader = new BufferedReader(new InputStreamReader(in, IOUtils.CHARSET_UTF_8));
+ final BufferedReader reader = new BufferedReader(new InputStreamReader(in, StandardCharsets.UTF_8));
String line;
while ((line = reader.readLine()) != null) {
final int pos = line.indexOf('#');
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/UnicodeUtil.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/UnicodeUtil.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/UnicodeUtil.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/UnicodeUtil.java Mon Mar 31 12:29:44 2014
@@ -1,5 +1,7 @@
package org.apache.lucene.util;
+import java.nio.charset.StandardCharsets;
+
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
@@ -88,7 +90,7 @@ package org.apache.lucene.util;
/**
* Class to encode java's UTF16 char[] into UTF8 byte[]
* without always allocating a new byte[] as
- * String.getBytes("UTF-8") does.
+ * String.getBytes(StandardCharsets.UTF_8) does.
*
* @lucene.internal
*/
Modified: lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/fst/FST.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/fst/FST.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/fst/FST.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/util/fst/FST.java Mon Mar 31 12:29:44 2014
@@ -25,6 +25,7 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
+import java.nio.charset.StandardCharsets;
import java.util.HashMap;
import java.util.Map;
@@ -379,7 +380,7 @@ public final class FST<T> {
/*
if (bytes.length == 665) {
- Writer w = new OutputStreamWriter(new FileOutputStream("out.dot"), "UTF-8");
+ Writer w = new OutputStreamWriter(new FileOutputStream("out.dot"), StandardCharsets.UTF_8);
Util.toDot(this, w, false, false);
w.close();
System.out.println("Wrote FST to out.dot");
Modified: lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/codecs/compressing/AbstractTestLZ4CompressionMode.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/codecs/compressing/AbstractTestLZ4CompressionMode.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/codecs/compressing/AbstractTestLZ4CompressionMode.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/codecs/compressing/AbstractTestLZ4CompressionMode.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,7 @@ package org.apache.lucene.codecs.compres
*/
import java.io.IOException;
+import java.nio.charset.StandardCharsets;
import com.carrotsearch.randomizedtesting.generators.RandomInts;
@@ -81,7 +82,7 @@ public abstract class AbstractTestLZ4Com
public void testShortLiteralsAndMatchs() throws IOException {
// literals and matchs lengths <= 15
- final byte[] decompressed = "1234562345673456745678910123".getBytes("UTF-8");
+ final byte[] decompressed = "1234562345673456745678910123".getBytes(StandardCharsets.UTF_8);
test(decompressed);
}
Modified: lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java Mon Mar 31 12:29:44 2014
@@ -1,5 +1,7 @@
package org.apache.lucene.document;
+import java.nio.charset.StandardCharsets;
+
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexableField;
import org.apache.lucene.index.RandomIndexWriter;
@@ -37,7 +39,7 @@ public class TestBinaryDocument extends
{
FieldType ft = new FieldType();
ft.setStored(true);
- IndexableField binaryFldStored = new StoredField("binaryStored", binaryValStored.getBytes("UTF-8"));
+ IndexableField binaryFldStored = new StoredField("binaryStored", binaryValStored.getBytes(StandardCharsets.UTF_8));
IndexableField stringFldStored = new Field("stringStored", binaryValStored, ft);
Document doc = new Document();
@@ -62,7 +64,7 @@ public class TestBinaryDocument extends
/** fetch the binary stored field and compare it's content with the original one */
BytesRef bytes = docFromReader.getBinaryValue("binaryStored");
assertNotNull(bytes);
- String binaryFldStoredTest = new String(bytes.bytes, bytes.offset, bytes.length, "UTF-8");
+ String binaryFldStoredTest = new String(bytes.bytes, bytes.offset, bytes.length, StandardCharsets.UTF_8);
assertTrue(binaryFldStoredTest.equals(binaryValStored));
/** fetch the string field and compare it's content with the original one */
@@ -75,7 +77,7 @@ public class TestBinaryDocument extends
}
public void testCompressionTools() throws Exception {
- IndexableField binaryFldCompressed = new StoredField("binaryCompressed", CompressionTools.compress(binaryValCompressed.getBytes("UTF-8")));
+ IndexableField binaryFldCompressed = new StoredField("binaryCompressed", CompressionTools.compress(binaryValCompressed.getBytes(StandardCharsets.UTF_8)));
IndexableField stringFldCompressed = new StoredField("stringCompressed", CompressionTools.compressString(binaryValCompressed));
Document doc = new Document();
@@ -94,7 +96,7 @@ public class TestBinaryDocument extends
assertTrue(docFromReader != null);
/** fetch the binary compressed field and compare it's content with the original one */
- String binaryFldCompressedTest = new String(CompressionTools.decompress(docFromReader.getBinaryValue("binaryCompressed")), "UTF-8");
+ String binaryFldCompressedTest = new String(CompressionTools.decompress(docFromReader.getBinaryValue("binaryCompressed")), StandardCharsets.UTF_8);
assertTrue(binaryFldCompressedTest.equals(binaryValCompressed));
assertTrue(CompressionTools.decompressString(docFromReader.getBinaryValue("stringCompressed")).equals(binaryValCompressed));
Modified: lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestDocument.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestDocument.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestDocument.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestDocument.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,8 @@ package org.apache.lucene.document;
*/
import java.io.StringReader;
+import java.nio.charset.StandardCharsets;
+import java.util.List;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.index.DirectoryReader;
@@ -53,8 +55,8 @@ public class TestDocument extends Lucene
FieldType ft = new FieldType();
ft.setStored(true);
IndexableField stringFld = new Field("string", binaryVal, ft);
- IndexableField binaryFld = new StoredField("binary", binaryVal.getBytes("UTF-8"));
- IndexableField binaryFld2 = new StoredField("binary", binaryVal2.getBytes("UTF-8"));
+ IndexableField binaryFld = new StoredField("binary", binaryVal.getBytes(StandardCharsets.UTF_8));
+ IndexableField binaryFld2 = new StoredField("binary", binaryVal2.getBytes(StandardCharsets.UTF_8));
doc.add(stringFld);
doc.add(binaryFld);
Modified: lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestField.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestField.java?rev=1583315&r1=1583314&r2=1583315&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestField.java (original)
+++ lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/document/TestField.java Mon Mar 31 12:29:44 2014
@@ -18,6 +18,8 @@ package org.apache.lucene.document;
*/
import java.io.StringReader;
+import java.nio.charset.StandardCharsets;
+
import org.apache.lucene.analysis.CannedTokenStream;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.util.BytesRef;
@@ -184,7 +186,7 @@ public class TestField extends LuceneTes
trySetBoost(field);
trySetByteValue(field);
- field.setBytesValue("fubar".getBytes("UTF-8"));
+ field.setBytesValue("fubar".getBytes(StandardCharsets.UTF_8));
field.setBytesValue(new BytesRef("baz"));
trySetDoubleValue(field);
trySetIntValue(field);
@@ -203,7 +205,7 @@ public class TestField extends LuceneTes
trySetBoost(field);
trySetByteValue(field);
- field.setBytesValue("fubar".getBytes("UTF-8"));
+ field.setBytesValue("fubar".getBytes(StandardCharsets.UTF_8));
field.setBytesValue(new BytesRef("baz"));
trySetDoubleValue(field);
trySetIntValue(field);
@@ -294,15 +296,15 @@ public class TestField extends LuceneTes
public void testStoredFieldBytes() throws Exception {
Field fields[] = new Field[] {
- new StoredField("foo", "bar".getBytes("UTF-8")),
- new StoredField("foo", "bar".getBytes("UTF-8"), 0, 3),
+ new StoredField("foo", "bar".getBytes(StandardCharsets.UTF_8)),
+ new StoredField("foo", "bar".getBytes(StandardCharsets.UTF_8), 0, 3),
new StoredField("foo", new BytesRef("bar")),
};
for (Field field : fields) {
trySetBoost(field);
trySetByteValue(field);
- field.setBytesValue("baz".getBytes("UTF-8"));
+ field.setBytesValue("baz".getBytes(StandardCharsets.UTF_8));
field.setBytesValue(new BytesRef("baz"));
trySetDoubleValue(field);
trySetIntValue(field);