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 2012/07/09 17:04:04 UTC
svn commit: r1359202 [2/5] - in /lucene/dev/trunk: ./ lucene/
lucene/analysis/ lucene/analysis/common/
lucene/analysis/common/src/java/org/apache/lucene/analysis/br/
lucene/analysis/common/src/java/org/apache/lucene/analysis/de/
lucene/analysis/common/...
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersContentSource.java Mon Jul 9 15:03:56 2012
@@ -19,8 +19,9 @@ package org.apache.lucene.benchmark.byTa
import java.io.BufferedReader;
import java.io.File;
-import java.io.FileReader;
+import java.io.FileInputStream;
import java.io.IOException;
+import java.io.InputStreamReader;
import java.text.DateFormat;
import java.text.ParsePosition;
import java.text.SimpleDateFormat;
@@ -29,6 +30,7 @@ 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.
@@ -74,7 +76,7 @@ public class ReutersContentSource extend
if (dfi == null) {
dfi = new DateFormatInfo();
// date format: 30-MAR-1987 14:22:36.87
- dfi.df = new SimpleDateFormat("dd-MMM-yyyy kk:mm:ss.SSS",Locale.US);
+ dfi.df = new SimpleDateFormat("dd-MMM-yyyy kk:mm:ss.SSS",Locale.ROOT);
dfi.df.setLenient(true);
dfi.pos = new ParsePosition(0);
dateFormat.set(dfi);
@@ -112,7 +114,7 @@ public class ReutersContentSource extend
name = f.getCanonicalPath() + "_" + iteration;
}
- BufferedReader reader = new BufferedReader(new FileReader(f));
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(f), IOUtils.CHARSET_UTF_8));
try {
// First line is the date, 3rd is the title, rest is body
String dateStr = reader.readLine();
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecContentSource.java Mon Jul 9 15:03:56 2012
@@ -108,7 +108,7 @@ public class TrecContentSource extends C
dfi = new DateFormatInfo();
dfi.dfs = new SimpleDateFormat[DATE_FORMATS.length];
for (int i = 0; i < dfi.dfs.length; i++) {
- dfi.dfs[i] = new SimpleDateFormat(DATE_FORMATS[i], Locale.US);
+ dfi.dfs[i] = new SimpleDateFormat(DATE_FORMATS[i], Locale.ROOT);
dfi.dfs[i].setLenient(true);
}
dfi.pos = new ParsePosition(0);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java Mon Jul 9 15:03:56 2012
@@ -47,7 +47,7 @@ public abstract class TrecDocParser {
static final Map<String,ParsePathType> pathName2Type = new HashMap<String,ParsePathType>();
static {
for (ParsePathType ppt : ParsePathType.values()) {
- pathName2Type.put(ppt.name().toUpperCase(Locale.ENGLISH),ppt);
+ pathName2Type.put(ppt.name().toUpperCase(Locale.ROOT),ppt);
}
}
@@ -60,7 +60,7 @@ public abstract class TrecDocParser {
public static ParsePathType pathType(File f) {
int pathLength = 0;
while (f != null && ++pathLength < MAX_PATH_LENGTH) {
- ParsePathType ppt = pathName2Type.get(f.getName().toUpperCase(Locale.ENGLISH));
+ ParsePathType ppt = pathName2Type.get(f.getName().toUpperCase(Locale.ROOT));
if (ppt!=null) {
return ppt;
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.java Mon Jul 9 15:03:56 2012
@@ -29,6 +29,10 @@ public class HTMLParser implements HTMLP
private MyPipedInputStream pipeInStream = null;
private PipedOutputStream pipeOutStream = null;
+ public HTMLParser(Reader reader) {
+ this(new FastCharStream(reader));
+ }
+
private class MyPipedInputStream extends PipedInputStream{
public MyPipedInputStream(){
@@ -227,7 +231,7 @@ InterruptedException {
Token t1, t2;
boolean inImg = false;
t1 = jj_consume_token(TagName);
- String tagName = t1.image.toLowerCase(Locale.ENGLISH);
+ String tagName = t1.image.toLowerCase(Locale.ROOT);
if(Tags.WS_ELEMS.contains(tagName) ) {
addSpace();
}
@@ -264,7 +268,7 @@ InterruptedException {
)
&& t2 != null)
{
- currentMetaTag=t2.image.toLowerCase(Locale.ENGLISH);
+ currentMetaTag=t2.image.toLowerCase(Locale.ROOT);
if(currentMetaTag != null && currentMetaContent != null) {
addMetaTag();
}
@@ -272,7 +276,7 @@ InterruptedException {
if(inMetaTag && t1.image.equalsIgnoreCase("content") && t2 !=
null)
{
- currentMetaContent=t2.image.toLowerCase(Locale.ENGLISH);
+ currentMetaContent=t2.image.toLowerCase(Locale.ROOT);
if(currentMetaTag != null && currentMetaContent != null) {
addMetaTag();
}
@@ -464,7 +468,6 @@ null)
/** Generated Token Manager. */
public HTMLParserTokenManager token_source;
- SimpleCharStream jj_input_stream;
/** Current token. */
public Token token;
/** Next token. */
@@ -485,40 +488,9 @@ null)
private boolean jj_rescan = false;
private int jj_gc = 0;
- /** Constructor with InputStream. */
- public HTMLParser(java.io.InputStream stream) {
- this(stream, null);
- }
- /** Constructor with InputStream and supplied encoding */
- public HTMLParser(java.io.InputStream stream, String encoding) {
- try { jj_input_stream = new SimpleCharStream(stream, encoding, 1, 1); } catch(java.io.UnsupportedEncodingException e) { throw new RuntimeException(e); }
- token_source = new HTMLParserTokenManager(jj_input_stream);
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 14; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- /** Reinitialise. */
- public void ReInit(java.io.InputStream stream) {
- ReInit(stream, null);
- }
- /** Reinitialise. */
- public void ReInit(java.io.InputStream stream, String encoding) {
- try { jj_input_stream.ReInit(stream, encoding, 1, 1); } catch(java.io.UnsupportedEncodingException e) { throw new RuntimeException(e); }
- token_source.ReInit(jj_input_stream);
- token = new Token();
- jj_ntk = -1;
- jj_gen = 0;
- for (int i = 0; i < 14; i++) jj_la1[i] = -1;
- for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls();
- }
-
- /** Constructor. */
- public HTMLParser(java.io.Reader stream) {
- jj_input_stream = new SimpleCharStream(stream, 1, 1);
- token_source = new HTMLParserTokenManager(jj_input_stream);
+ /** Constructor with user supplied CharStream. */
+ public HTMLParser(CharStream stream) {
+ token_source = new HTMLParserTokenManager(stream);
token = new Token();
jj_ntk = -1;
jj_gen = 0;
@@ -527,9 +499,8 @@ null)
}
/** Reinitialise. */
- public void ReInit(java.io.Reader stream) {
- jj_input_stream.ReInit(stream, 1, 1);
- token_source.ReInit(jj_input_stream);
+ public void ReInit(CharStream stream) {
+ token_source.ReInit(stream);
token = new Token();
jj_ntk = -1;
jj_gen = 0;
@@ -631,7 +602,7 @@ null)
return (jj_ntk = jj_nt.kind);
}
- private java.util.List<int[]> jj_expentries = new java.util.ArrayList<int[]>();
+ private java.util.List jj_expentries = new java.util.ArrayList();
private int[] jj_expentry;
private int jj_kind = -1;
private int[] jj_lasttokens = new int[100];
@@ -691,7 +662,7 @@ null)
jj_add_error_token(0, 0);
int[][] exptokseq = new int[jj_expentries.size()][];
for (int i = 0; i < jj_expentries.size(); i++) {
- exptokseq[i] = jj_expentries.get(i);
+ exptokseq[i] = (int[])jj_expentries.get(i);
}
return new ParseException(token, exptokseq, tokenImage);
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.jj
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.jj?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.jj (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParser.jj Mon Jul 9 15:03:56 2012
@@ -22,6 +22,7 @@ options {
//DEBUG_LOOKAHEAD = true;
//DEBUG_TOKEN_MANAGER = true;
UNICODE_INPUT = true;
+ USER_CHAR_STREAM=true;
}
PARSER_BEGIN(HTMLParser)
@@ -56,6 +57,10 @@ public class HTMLParser {
private MyPipedInputStream pipeInStream = null;
private PipedOutputStream pipeOutStream = null;
+ public HTMLParser(Reader reader) {
+ this(new FastCharStream(reader));
+ }
+
private class MyPipedInputStream extends PipedInputStream{
public MyPipedInputStream(){
@@ -227,7 +232,7 @@ void Tag() throws IOException :
}
{
t1=<TagName> {
- String tagName = t1.image.toLowerCase(Locale.ENGLISH);
+ String tagName = t1.image.toLowerCase(Locale.ROOT);
if(Tags.WS_ELEMS.contains(tagName) ) {
addSpace();
}
@@ -249,7 +254,7 @@ void Tag() throws IOException :
)
&& t2 != null)
{
- currentMetaTag=t2.image.toLowerCase(Locale.ENGLISH);
+ currentMetaTag=t2.image.toLowerCase(Locale.ROOT);
if(currentMetaTag != null && currentMetaContent != null) {
addMetaTag();
}
@@ -257,7 +262,7 @@ void Tag() throws IOException :
if(inMetaTag && t1.image.equalsIgnoreCase("content") && t2 !=
null)
{
- currentMetaContent=t2.image.toLowerCase(Locale.ENGLISH);
+ currentMetaContent=t2.image.toLowerCase(Locale.ROOT);
if(currentMetaTag != null && currentMetaContent != null) {
addMetaTag();
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParserTokenManager.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParserTokenManager.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParserTokenManager.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/HTMLParserTokenManager.java Mon Jul 9 15:03:56 2012
@@ -464,7 +464,7 @@ private int jjMoveNfa_0(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -569,7 +569,7 @@ private int jjMoveNfa_5(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -670,7 +670,7 @@ private int jjMoveNfa_7(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -766,7 +766,7 @@ private int jjMoveNfa_4(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -892,7 +892,7 @@ private int jjMoveNfa_3(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -1061,7 +1061,7 @@ private int jjMoveNfa_6(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -1205,7 +1205,7 @@ private int jjMoveNfa_1(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -1361,7 +1361,7 @@ private int jjMoveNfa_2(int startState,
}
else
{
- int hiByte = (curChar >> 8);
+ int hiByte = (int)(curChar >> 8);
int i1 = hiByte >> 6;
long l1 = 1L << (hiByte & 077);
int i2 = (curChar & 0xff) >> 6;
@@ -1441,25 +1441,23 @@ static final long[] jjtoToken = {
static final long[] jjtoSkip = {
0x400000L,
};
-protected SimpleCharStream input_stream;
+protected CharStream input_stream;
private final int[] jjrounds = new int[28];
private final int[] jjstateSet = new int[56];
protected char curChar;
/** Constructor. */
-public HTMLParserTokenManager(SimpleCharStream stream){
- if (SimpleCharStream.staticFlag)
- throw new Error("ERROR: Cannot use a static CharStream class with a non-static lexical analyzer.");
+public HTMLParserTokenManager(CharStream stream){
input_stream = stream;
}
/** Constructor. */
-public HTMLParserTokenManager(SimpleCharStream stream, int lexState){
+public HTMLParserTokenManager(CharStream stream, int lexState){
this(stream);
SwitchTo(lexState);
}
/** Reinitialise parser. */
-public void ReInit(SimpleCharStream stream)
+public void ReInit(CharStream stream)
{
jjmatchedPos = jjnewStateCnt = 0;
curLexState = defaultLexState;
@@ -1475,7 +1473,7 @@ private void ReInitRounds()
}
/** Reinitialise parser. */
-public void ReInit(SimpleCharStream stream, int lexState)
+public void ReInit(CharStream stream, int lexState)
{
ReInit(stream);
SwitchTo(lexState);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/ParseException.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/ParseException.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/ParseException.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/ParseException.java Mon Jul 9 15:03:56 2012
@@ -195,4 +195,4 @@ public class ParseException extends Exce
}
}
-/* JavaCC - OriginalChecksum=e5376178619291bc9d2c0c6647dc3cef (do not edit this line) */
+/* JavaCC - OriginalChecksum=e449d0e43f3d85deb1260a88b7e90fcd (do not edit this line) */
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Token.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Token.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Token.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/Token.java Mon Jul 9 15:03:56 2012
@@ -121,4 +121,4 @@ public class Token {
}
}
-/* JavaCC - OriginalChecksum=e49c2a0c10d50ff2ebd0639552330ce7 (do not edit this line) */
+/* JavaCC - OriginalChecksum=24643dc85fd6daeec42ceba20b46ee61 (do not edit this line) */
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/TokenMgrError.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/TokenMgrError.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/TokenMgrError.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/demohtml/TokenMgrError.java Mon Jul 9 15:03:56 2012
@@ -138,4 +138,4 @@ public class TokenMgrError extends Error
this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason);
}
}
-/* JavaCC - OriginalChecksum=3aee554f696e5d7a18b1ad330c1de53f (do not edit this line) */
+/* JavaCC - OriginalChecksum=538f0da130356fcc0bc7db621ab0389d (do not edit this line) */
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/AddDocTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/AddDocTask.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/AddDocTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/AddDocTask.java Mon Jul 9 15:03:56 2012
@@ -18,6 +18,7 @@ package org.apache.lucene.benchmark.byTa
*/
import java.text.NumberFormat;
+import java.util.Locale;
import org.apache.lucene.benchmark.byTask.PerfRunData;
import org.apache.lucene.benchmark.byTask.feeds.DocMaker;
@@ -61,7 +62,7 @@ public class AddDocTask extends PerfTask
@Override
protected String getLogMessage(int recsCount) {
- return String.format("added %9d docs",recsCount);
+ return String.format(Locale.ROOT, "added %9d docs",recsCount);
}
@Override
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTask.java Mon Jul 9 15:03:56 2012
@@ -40,6 +40,7 @@ import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintStream;
+import java.nio.charset.Charset;
/**
* Create an index. <br>
@@ -182,7 +183,7 @@ public class CreateIndexTask extends Per
iwc.setInfoStream(System.err);
} else {
File f = new File(infoStreamVal).getAbsoluteFile();
- iwc.setInfoStream(new PrintStream(new BufferedOutputStream(new FileOutputStream(f))));
+ iwc.setInfoStream(new PrintStream(new BufferedOutputStream(new FileOutputStream(f)), false, Charset.defaultCharset().name()));
}
}
IndexWriter writer = new IndexWriter(runData.getDirectory(), iwc);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/PerfTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/PerfTask.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/PerfTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/PerfTask.java Mon Jul 9 15:03:56 2012
@@ -17,6 +17,8 @@ package org.apache.lucene.benchmark.byTa
* limitations under the License.
*/
+import java.util.Locale;
+
import org.apache.lucene.benchmark.byTask.PerfRunData;
import org.apache.lucene.benchmark.byTask.stats.Points;
import org.apache.lucene.benchmark.byTask.stats.TaskStats;
@@ -266,7 +268,7 @@ public abstract class PerfTask implement
public void tearDown() throws Exception {
if (++logStepCount % logStep == 0) {
double time = (System.currentTimeMillis() - runData.getStartTimeMillis()) / 1000.0;
- System.out.println(String.format("%7.2f",time) + " sec --> "
+ System.out.println(String.format(Locale.ROOT, "%7.2f",time) + " sec --> "
+ Thread.currentThread().getName() + " " + getLogMessage(logStepCount));
}
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchWithSortTask.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchWithSortTask.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchWithSortTask.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchWithSortTask.java Mon Jul 9 15:03:56 2012
@@ -77,7 +77,7 @@ public class SearchWithSortTask extends
} else {
throw new RuntimeException("You must specify the sort type ie page:int,subject:string");
}
- sortField0 = new SortField(fieldName, SortField.Type.valueOf(typeString.toUpperCase(Locale.ENGLISH)));
+ sortField0 = new SortField(fieldName, SortField.Type.valueOf(typeString.toUpperCase(Locale.ROOT)));
}
sortFields[upto++] = sortField0;
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/TaskSequence.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/TaskSequence.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/TaskSequence.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/TaskSequence.java Mon Jul 9 15:03:56 2012
@@ -19,6 +19,7 @@ package org.apache.lucene.benchmark.byTa
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import java.text.NumberFormat;
import org.apache.lucene.benchmark.byTask.PerfRunData;
@@ -428,7 +429,7 @@ public class TaskSequence extends PerfTa
sb.append(padd);
sb.append(!letChildReport ? ">" : (parallel ? "]" : "}"));
if (fixedTime) {
- sb.append(" " + NumberFormat.getNumberInstance().format(runTimeSec) + "s");
+ sb.append(" " + NumberFormat.getNumberInstance(Locale.ROOT).format(runTimeSec) + "s");
} else if (repetitions>1) {
sb.append(" * " + repetitions);
} else if (repetitions==REPEAT_EXHAUST) {
@@ -487,7 +488,7 @@ public class TaskSequence extends PerfTa
if (rate>0) {
seqName += "_" + rate + (perMin?"/min":"/sec");
}
- if (parallel && seqName.toLowerCase().indexOf("par")<0) {
+ if (parallel && seqName.toLowerCase(Locale.ROOT).indexOf("par")<0) {
seqName += "_Par";
}
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Algorithm.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Algorithm.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Algorithm.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Algorithm.java Mon Jul 9 15:03:56 2012
@@ -22,6 +22,7 @@ import java.io.StringReader;
import java.lang.reflect.Constructor;
import java.util.ArrayList;
import java.util.Arrays;
+import java.util.Locale;
import org.apache.lucene.benchmark.byTask.PerfRunData;
import org.apache.lucene.benchmark.byTask.tasks.PerfTask;
@@ -159,7 +160,7 @@ public class Algorithm {
} else {
stok.nextToken();
if (stok.ttype!=StreamTokenizer.TT_WORD) throw new Exception("expected rate unit: 'min' or 'sec' - "+stok.toString());
- String unit = stok.sval.toLowerCase();
+ String unit = stok.sval.toLowerCase(Locale.ROOT);
if ("min".equals(unit)) {
((TaskSequence)prevTask).setRate((int)stok.nval,true); // set rate per min
} else if ("sec".equals(unit)) {
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Format.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Format.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Format.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/Format.java Mon Jul 9 15:03:56 2012
@@ -18,6 +18,7 @@ package org.apache.lucene.benchmark.byTa
*/
import java.text.NumberFormat;
+import java.util.Locale;
/**
* Formatting utilities (for reports).
@@ -25,9 +26,9 @@ import java.text.NumberFormat;
public class Format {
private static NumberFormat numFormat [] = {
- NumberFormat.getInstance(),
- NumberFormat.getInstance(),
- NumberFormat.getInstance(),
+ NumberFormat.getInstance(Locale.ROOT),
+ NumberFormat.getInstance(Locale.ROOT),
+ NumberFormat.getInstance(Locale.ROOT),
};
private static final String padd = " ";
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/StreamUtils.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/StreamUtils.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/StreamUtils.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/utils/StreamUtils.java Mon Jul 9 15:03:56 2012
@@ -99,7 +99,7 @@ public class StreamUtils {
String fileName = file.getName();
int idx = fileName.lastIndexOf('.');
if (idx != -1) {
- type = extensionToType.get(fileName.substring(idx).toLowerCase(Locale.ENGLISH));
+ type = extensionToType.get(fileName.substring(idx).toLowerCase(Locale.ROOT));
}
return type==null ? Type.PLAIN : type;
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/QualityStats.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/QualityStats.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/QualityStats.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/QualityStats.java Mon Jul 9 15:03:56 2012
@@ -19,6 +19,7 @@ package org.apache.lucene.benchmark.qual
import java.io.PrintWriter;
import java.text.NumberFormat;
import java.util.ArrayList;
+import java.util.Locale;
/**
* Results of quality benchmark run for a single query or for a set of queries.
@@ -141,7 +142,7 @@ public class QualityStats {
logger.println(title);
}
prefix = prefix==null ? "" : prefix;
- NumberFormat nf = NumberFormat.getInstance();
+ NumberFormat nf = NumberFormat.getInstance(Locale.ROOT);
nf.setMaximumFractionDigits(3);
nf.setMinimumFractionDigits(3);
nf.setGroupingUsed(true);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/trec/QueryDriver.java Mon Jul 9 15:03:56 2012
@@ -24,11 +24,13 @@ import org.apache.lucene.index.Directory
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.store.FSDirectory;
+import org.apache.lucene.util.IOUtils;
import java.io.BufferedReader;
import java.io.File;
-import java.io.FileReader;
+import java.io.OutputStreamWriter;
import java.io.PrintWriter;
+import java.nio.charset.Charset;
import java.util.HashSet;
import java.util.Set;
@@ -51,7 +53,7 @@ public class QueryDriver {
File topicsFile = new File(args[0]);
File qrelsFile = new File(args[1]);
- SubmissionReport submitLog = new SubmissionReport(new PrintWriter(args[2]), "lucene");
+ SubmissionReport submitLog = new SubmissionReport(new PrintWriter(args[2], "UTF-8"), "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);
@@ -60,14 +62,14 @@ public class QueryDriver {
int maxResults = 1000;
String docNameField = "docname";
- PrintWriter logger = new PrintWriter(System.out, true);
+ PrintWriter logger = new PrintWriter(new OutputStreamWriter(System.out, Charset.defaultCharset()), true);
// use trec utilities to read trec topics into quality queries
TrecTopicsReader qReader = new TrecTopicsReader();
- QualityQuery qqs[] = qReader.readQueries(new BufferedReader(new FileReader(topicsFile)));
+ QualityQuery qqs[] = qReader.readQueries(new BufferedReader(IOUtils.getDecodingReader(topicsFile, IOUtils.CHARSET_UTF_8)));
// prepare judge, with trec utilities that read from a QRels file
- Judge judge = new TrecJudge(new BufferedReader(new FileReader(qrelsFile)));
+ Judge judge = new TrecJudge(new BufferedReader(IOUtils.getDecodingReader(qrelsFile, IOUtils.CHARSET_UTF_8)));
// validate topics & judgments match each other
judge.validateData(qqs, logger);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/utils/SubmissionReport.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/utils/SubmissionReport.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/utils/SubmissionReport.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/utils/SubmissionReport.java Mon Jul 9 15:03:56 2012
@@ -19,6 +19,7 @@ package org.apache.lucene.benchmark.qual
import java.io.IOException;
import java.io.PrintWriter;
import java.text.NumberFormat;
+import java.util.Locale;
import org.apache.lucene.benchmark.quality.QualityQuery;
import org.apache.lucene.search.ScoreDoc;
@@ -45,7 +46,7 @@ public class SubmissionReport {
public SubmissionReport (PrintWriter logger, String name) {
this.logger = logger;
this.name = name;
- nf = NumberFormat.getInstance();
+ nf = NumberFormat.getInstance(Locale.ROOT);
nf.setMaximumFractionDigits(4);
nf.setMinimumFractionDigits(4);
}
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractReuters.java Mon Jul 9 15:03:56 2012
@@ -19,12 +19,18 @@ package org.apache.lucene.benchmark.util
import java.io.BufferedReader;
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.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
@@ -73,7 +79,7 @@ public class ExtractReuters {
*/
protected void extractFile(File sgmFile) {
try {
- BufferedReader reader = new BufferedReader(new FileReader(sgmFile));
+ BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(sgmFile), IOUtils.CHARSET_UTF_8));
StringBuilder buffer = new StringBuilder(1024);
StringBuilder outBuffer = new StringBuilder(1024);
@@ -107,7 +113,7 @@ public class ExtractReuters {
File outFile = new File(outputDir, sgmFile.getName() + "-"
+ (docNumber++) + ".txt");
// System.out.println("Writing " + outFile);
- FileWriter writer = new FileWriter(outFile);
+ OutputStreamWriter writer = new OutputStreamWriter(new FileOutputStream(outFile), IOUtils.CHARSET_UTF_8);
writer.write(out);
writer.close();
outBuffer.setLength(0);
Modified: lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/java/org/apache/lucene/benchmark/utils/ExtractWikipedia.java Mon Jul 9 15:03:56 2012
@@ -18,8 +18,10 @@ package org.apache.lucene.benchmark.util
*/
import java.io.File;
-import java.io.FileWriter;
+import java.io.FileOutputStream;
import java.io.IOException;
+import java.io.OutputStreamWriter;
+import java.io.Writer;
import java.util.Properties;
import org.apache.lucene.benchmark.byTask.feeds.ContentSource;
@@ -28,6 +30,7 @@ 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.
@@ -83,7 +86,7 @@ public class ExtractWikipedia {
contents.append("\n");
try {
- FileWriter writer = new FileWriter(f);
+ Writer writer = new OutputStreamWriter(new FileOutputStream(f), IOUtils.CHARSET_UTF_8);
writer.write(contents.toString());
writer.close();
} catch (IOException ioe) {
Modified: lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/DocMakerTest.java Mon Jul 9 15:03:56 2012
@@ -166,7 +166,7 @@ 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);
+ PrintStream ps = new PrintStream(f, "UTF-8");
ps.println("one title\t" + System.currentTimeMillis() + "\tsome content");
ps.close();
Modified: lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTaskTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTaskTest.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTaskTest.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/CreateIndexTaskTest.java Mon Jul 9 15:03:56 2012
@@ -20,6 +20,7 @@ package org.apache.lucene.benchmark.byTa
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.PrintStream;
+import java.nio.charset.Charset;
import java.util.Properties;
import org.apache.lucene.benchmark.BenchmarkTestCase;
@@ -50,7 +51,7 @@ public class CreateIndexTaskTest extends
PrintStream curOut = System.out;
ByteArrayOutputStream baos = new ByteArrayOutputStream();
- System.setOut(new PrintStream(baos));
+ System.setOut(new PrintStream(baos, false, Charset.defaultCharset().name()));
try {
PerfRunData runData = createPerfRunData("SystemOut");
CreateIndexTask cit = new CreateIndexTask(runData);
@@ -63,7 +64,7 @@ public class CreateIndexTaskTest extends
PrintStream curErr = System.err;
baos.reset();
- System.setErr(new PrintStream(baos));
+ System.setErr(new PrintStream(baos, false, Charset.defaultCharset().name()));
try {
PerfRunData runData = createPerfRunData("SystemErr");
CreateIndexTask cit = new CreateIndexTask(runData);
Modified: lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/utils/StreamUtilsTest.java Mon Jul 9 15:03:56 2012
@@ -31,6 +31,7 @@ import java.io.OutputStreamWriter;
import org.apache.commons.compress.compressors.CompressorStreamFactory;
import org.apache.lucene.benchmark.BenchmarkTestCase;
import org.apache.lucene.benchmark.byTask.utils.StreamUtils;
+import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util._TestUtil;
import org.junit.After;
import org.junit.Before;
@@ -88,7 +89,7 @@ public class StreamUtilsTest extends Ben
private File rawTextFile(String ext) throws Exception {
File f = new File(testDir,"testfile." + ext);
- BufferedWriter w = new BufferedWriter(new FileWriter(f));
+ BufferedWriter w = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(f), IOUtils.CHARSET_UTF_8));
w.write(TEXT);
w.newLine();
w.close();
@@ -117,7 +118,7 @@ public class StreamUtilsTest extends Ben
}
private void writeText(OutputStream os) throws IOException {
- BufferedWriter w = new BufferedWriter(new OutputStreamWriter(os));
+ BufferedWriter w = new BufferedWriter(new OutputStreamWriter(os, IOUtils.CHARSET_UTF_8));
w.write(TEXT);
w.newLine();
w.close();
@@ -125,7 +126,7 @@ public class StreamUtilsTest extends Ben
private void assertReadText(File f) throws Exception {
InputStream ir = StreamUtils.inputStream(f);
- InputStreamReader in = new InputStreamReader(ir);
+ InputStreamReader in = new InputStreamReader(ir, IOUtils.CHARSET_UTF_8);
BufferedReader r = new BufferedReader(in);
String line = r.readLine();
assertEquals("Wrong text found in "+f.getName(), TEXT, line);
Modified: lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java (original)
+++ lucene/dev/trunk/lucene/benchmark/src/test/org/apache/lucene/benchmark/quality/TestQualityRun.java Mon Jul 9 15:03:56 2012
@@ -31,7 +31,9 @@ import java.io.BufferedReader;
import java.io.File;
import java.io.InputStream;
import java.io.InputStreamReader;
+import java.io.OutputStreamWriter;
import java.io.PrintWriter;
+import java.nio.charset.Charset;
/**
* Test that quality run does its job.
@@ -55,7 +57,7 @@ public class TestQualityRun extends Benc
int maxResults = 1000;
String docNameField = "doctitle"; // orig docID is in the linedoc format title
- PrintWriter logger = VERBOSE ? new PrintWriter(System.out,true) : null;
+ PrintWriter logger = VERBOSE ? new PrintWriter(new OutputStreamWriter(System.out, Charset.defaultCharset()),true) : null;
// prepare topics
InputStream topics = getClass().getResourceAsStream("trecTopics.txt");
Modified: lucene/dev/trunk/lucene/build.xml
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/build.xml?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/build.xml (original)
+++ lucene/dev/trunk/lucene/build.xml Mon Jul 9 15:03:56 2012
@@ -169,11 +169,19 @@
</clover-report>
</target>
- <!-- Validate once from top-level. -->
- <target name="validate" depends="compile-tools,resolve" description="Validate legal stuff.">
+ <!-- Validation (license/notice/api checks). -->
+ <target name="validate" depends="check-licenses,check-forbidden-apis" description="Validate stuff." />
+
+ <target name="check-licenses" depends="compile-tools,resolve,load-custom-tasks" description="Validate license stuff.">
<license-check-macro dir="${basedir}" />
</target>
+ <target name="check-forbidden-apis" depends="compile-tools,compile-test,load-custom-tasks" description="Check forbidden API calls in compiled class files.">
+ <forbidden-apis apiFile="${custom-tasks.dir}/forbiddenApis/jdk.txt">
+ <fileset dir="${basedir}/build" includes="**/*.class" />
+ </forbidden-apis>
+ </target>
+
<target name="resolve">
<sequential>
<ant dir="test-framework" target="resolve" inheritall="false">
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/codecs/BlockTreeTermsReader.java Mon Jul 9 15:03:56 2012
@@ -20,8 +20,10 @@ package org.apache.lucene.codecs;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.PrintStream;
+import java.io.UnsupportedEncodingException;
import java.util.Comparator;
import java.util.Iterator;
+import java.util.Locale;
import java.util.TreeMap;
import org.apache.lucene.index.DocsAndPositionsEnum;
@@ -345,7 +347,12 @@ public class BlockTreeTermsReader extend
@Override
public String toString() {
final ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
- final PrintStream out = new PrintStream(bos);
+ PrintStream out;
+ try {
+ out = new PrintStream(bos, false, "UTF-8");
+ } catch (UnsupportedEncodingException bogus) {
+ throw new RuntimeException(bogus);
+ }
out.println(" index FST:");
out.println(" " + indexNodeCount + " nodes");
@@ -353,7 +360,7 @@ public class BlockTreeTermsReader extend
out.println(" " + indexNumBytes + " bytes");
out.println(" terms:");
out.println(" " + totalTermCount + " terms");
- out.println(" " + totalTermBytes + " bytes" + (totalTermCount != 0 ? " (" + String.format("%.1f", ((double) totalTermBytes)/totalTermCount) + " bytes/term)" : ""));
+ out.println(" " + totalTermBytes + " bytes" + (totalTermCount != 0 ? " (" + String.format(Locale.ROOT, "%.1f", ((double) totalTermBytes)/totalTermCount) + " bytes/term)" : ""));
out.println(" blocks:");
out.println(" " + totalBlockCount + " blocks");
out.println(" " + termsOnlyBlockCount + " terms-only blocks");
@@ -362,9 +369,9 @@ public class BlockTreeTermsReader extend
out.println(" " + floorBlockCount + " floor blocks");
out.println(" " + (totalBlockCount-floorSubBlockCount) + " non-floor blocks");
out.println(" " + floorSubBlockCount + " floor sub-blocks");
- out.println(" " + totalBlockSuffixBytes + " term suffix bytes" + (totalBlockCount != 0 ? " (" + String.format("%.1f", ((double) totalBlockSuffixBytes)/totalBlockCount) + " suffix-bytes/block)" : ""));
- out.println(" " + totalBlockStatsBytes + " term stats bytes" + (totalBlockCount != 0 ? " (" + String.format("%.1f", ((double) totalBlockStatsBytes)/totalBlockCount) + " stats-bytes/block)" : ""));
- out.println(" " + totalBlockOtherBytes + " other bytes" + (totalBlockCount != 0 ? " (" + String.format("%.1f", ((double) totalBlockOtherBytes)/totalBlockCount) + " other-bytes/block)" : ""));
+ out.println(" " + totalBlockSuffixBytes + " term suffix bytes" + (totalBlockCount != 0 ? " (" + String.format(Locale.ROOT, "%.1f", ((double) totalBlockSuffixBytes)/totalBlockCount) + " suffix-bytes/block)" : ""));
+ out.println(" " + totalBlockStatsBytes + " term stats bytes" + (totalBlockCount != 0 ? " (" + String.format(Locale.ROOT, "%.1f", ((double) totalBlockStatsBytes)/totalBlockCount) + " stats-bytes/block)" : ""));
+ out.println(" " + totalBlockOtherBytes + " other bytes" + (totalBlockCount != 0 ? " (" + String.format(Locale.ROOT, "%.1f", ((double) totalBlockOtherBytes)/totalBlockCount) + " other-bytes/block)" : ""));
if (totalBlockCount != 0) {
out.println(" by prefix length:");
int total = 0;
@@ -372,13 +379,17 @@ public class BlockTreeTermsReader extend
final int blockCount = blockCountByPrefixLen[prefix];
total += blockCount;
if (blockCount != 0) {
- out.println(" " + String.format("%2d", prefix) + ": " + blockCount);
+ out.println(" " + String.format(Locale.ROOT, "%2d", prefix) + ": " + blockCount);
}
}
assert totalBlockCount == total;
}
- return bos.toString();
+ try {
+ return bos.toString("UTF-8");
+ } catch (UnsupportedEncodingException bogus) {
+ throw new RuntimeException(bogus);
+ }
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/DateTools.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/DateTools.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/DateTools.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/document/DateTools.java Mon Jul 9 15:03:56 2012
@@ -53,7 +53,7 @@ public class DateTools {
private static final ThreadLocal<Calendar> TL_CAL = new ThreadLocal<Calendar>() {
@Override
protected Calendar initialValue() {
- return Calendar.getInstance(GMT, Locale.US);
+ return Calendar.getInstance(GMT, Locale.ROOT);
}
};
@@ -194,7 +194,7 @@ public class DateTools {
this.formatLen = formatLen;
// formatLen 10's place: 11111111
// formatLen 1's place: 12345678901234567
- this.format = new SimpleDateFormat("yyyyMMddHHmmssSSS".substring(0,formatLen),Locale.US);
+ this.format = new SimpleDateFormat("yyyyMMddHHmmssSSS".substring(0,formatLen),Locale.ROOT);
this.format.setTimeZone(GMT);
}
@@ -202,7 +202,7 @@ public class DateTools {
* in lowercase (for backwards compatibility) */
@Override
public String toString() {
- return super.toString().toLowerCase(Locale.ENGLISH);
+ return super.toString().toLowerCase(Locale.ROOT);
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/CheckIndex.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/CheckIndex.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/CheckIndex.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/CheckIndex.java Mon Jul 9 15:03:56 2012
@@ -25,6 +25,7 @@ import java.util.ArrayList;
import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import org.apache.lucene.codecs.BlockTreeTermsReader;
@@ -340,7 +341,7 @@ public class CheckIndex {
* you only call this when the index is not opened by any
* writer. */
public Status checkIndex(List<String> onlySegments) throws IOException {
- NumberFormat nf = NumberFormat.getInstance();
+ NumberFormat nf = NumberFormat.getInstance(Locale.ROOT);
SegmentInfos sis = new SegmentInfos();
Status result = new Status();
result.dir = dir;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DocumentsWriterPerThread.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DocumentsWriterPerThread.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DocumentsWriterPerThread.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/DocumentsWriterPerThread.java Mon Jul 9 15:03:56 2012
@@ -20,6 +20,7 @@ package org.apache.lucene.index;
import java.io.IOException;
import java.text.NumberFormat;
import java.util.HashSet;
+import java.util.Locale;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.codecs.Codec;
@@ -181,7 +182,7 @@ class DocumentsWriterPerThread {
private int flushedDocCount;
DocumentsWriterDeleteQueue deleteQueue;
DeleteSlice deleteSlice;
- private final NumberFormat nf = NumberFormat.getInstance();
+ private final NumberFormat nf = NumberFormat.getInstance(Locale.ROOT);
final Allocator byteBlockAllocator;
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/IndexWriter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/IndexWriter.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/IndexWriter.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/IndexWriter.java Mon Jul 9 15:03:56 2012
@@ -27,6 +27,7 @@ import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger;
@@ -3610,7 +3611,7 @@ public class IndexWriter implements Clos
// lost...
if (infoStream.isEnabled("IW")) {
- infoStream.message("IW", String.format("merged segment size=%.3f MB vs estimate=%.3f MB", merge.info.info.sizeInBytes()/1024./1024., merge.estimatedMergeBytes/1024/1024.));
+ infoStream.message("IW", String.format(Locale.ROOT, "merged segment size=%.3f MB vs estimate=%.3f MB", merge.info.info.sizeInBytes()/1024./1024., merge.estimatedMergeBytes/1024/1024.));
}
final IndexReaderWarmer mergedSegmentWarmer = config.getMergedSegmentWarmer();
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/LogMergePolicy.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/LogMergePolicy.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/LogMergePolicy.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/LogMergePolicy.java Mon Jul 9 15:03:56 2012
@@ -21,6 +21,7 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.Collection;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
@@ -535,7 +536,7 @@ public abstract class LogMergePolicy ext
if (size >= maxMergeSize) {
extra += " [skip: too large]";
}
- message("seg=" + writer.get().segString(info) + " level=" + infoLevel.level + " size=" + String.format("%.3f MB", segBytes/1024/1024.) + extra);
+ message("seg=" + writer.get().segString(info) + " level=" + infoLevel.level + " size=" + String.format(Locale.ROOT, "%.3f MB", segBytes/1024/1024.) + extra);
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java Mon Jul 9 15:03:56 2012
@@ -18,6 +18,7 @@ package org.apache.lucene.index;
*/
import java.io.IOException;
+import java.util.Locale;
import java.util.Map;
import java.util.Collection;
import java.util.Collections;
@@ -289,7 +290,7 @@ public class TieredMergePolicy extends M
} else if (segBytes < floorSegmentBytes) {
extra += " [floored]";
}
- message(" seg=" + writer.get().segString(info) + " size=" + String.format("%.3f", segBytes/1024/1024.) + " MB" + extra);
+ message(" seg=" + writer.get().segString(info) + " size=" + String.format(Locale.ROOT, "%.3f", segBytes/1024/1024.) + " MB" + extra);
}
minSegmentBytes = Math.min(segBytes, minSegmentBytes);
@@ -388,7 +389,7 @@ public class TieredMergePolicy extends M
final MergeScore score = score(candidate, hitTooLarge, mergingBytes);
if (verbose()) {
- message(" maybe=" + writer.get().segString(candidate) + " score=" + score.getScore() + " " + score.getExplanation() + " tooLarge=" + hitTooLarge + " size=" + String.format("%.3f MB", totAfterMergeBytes/1024./1024.));
+ message(" maybe=" + writer.get().segString(candidate) + " score=" + score.getScore() + " " + score.getExplanation() + " tooLarge=" + hitTooLarge + " size=" + String.format(Locale.ROOT, "%.3f MB", totAfterMergeBytes/1024./1024.));
}
// If we are already running a max sized merge
@@ -413,7 +414,7 @@ public class TieredMergePolicy extends M
}
if (verbose()) {
- message(" add merge=" + writer.get().segString(merge.segments) + " size=" + String.format("%.3f MB", bestMergeBytes/1024./1024.) + " score=" + String.format("%.3f", bestScore.getScore()) + " " + bestScore.getExplanation() + (bestTooLarge ? " [max merge]" : ""));
+ message(" add merge=" + writer.get().segString(merge.segments) + " size=" + String.format(Locale.ROOT, "%.3f MB", bestMergeBytes/1024./1024.) + " score=" + String.format(Locale.ROOT, "%.3f", bestScore.getScore()) + " " + bestScore.getExplanation() + (bestTooLarge ? " [max merge]" : ""));
}
} else {
return spec;
@@ -475,7 +476,7 @@ public class TieredMergePolicy extends M
@Override
public String getExplanation() {
- return "skew=" + String.format("%.3f", skew) + " nonDelRatio=" + String.format("%.3f", nonDelRatio);
+ return "skew=" + String.format(Locale.ROOT, "%.3f", skew) + " nonDelRatio=" + String.format(Locale.ROOT, "%.3f", nonDelRatio);
}
};
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMDirichletSimilarity.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMDirichletSimilarity.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMDirichletSimilarity.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMDirichletSimilarity.java Mon Jul 9 15:03:56 2012
@@ -17,6 +17,8 @@ package org.apache.lucene.search.similar
* limitations under the License.
*/
+import java.util.Locale;
+
import org.apache.lucene.search.Explanation;
/**
@@ -92,6 +94,6 @@ public class LMDirichletSimilarity exten
@Override
public String getName() {
- return String.format("Dirichlet(%f)", getMu());
+ return String.format(Locale.ROOT, "Dirichlet(%f)", getMu());
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMJelinekMercerSimilarity.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMJelinekMercerSimilarity.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMJelinekMercerSimilarity.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMJelinekMercerSimilarity.java Mon Jul 9 15:03:56 2012
@@ -17,6 +17,8 @@ package org.apache.lucene.search.similar
* limitations under the License.
*/
+import java.util.Locale;
+
import org.apache.lucene.search.Explanation;
/**
@@ -72,6 +74,6 @@ public class LMJelinekMercerSimilarity e
@Override
public String getName() {
- return String.format("Jelinek-Mercer(%f)", getLambda());
+ return String.format(Locale.ROOT, "Jelinek-Mercer(%f)", getLambda());
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMSimilarity.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMSimilarity.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMSimilarity.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/search/similarities/LMSimilarity.java Mon Jul 9 15:03:56 2012
@@ -17,6 +17,8 @@ package org.apache.lucene.search.similar
* limitations under the License.
*/
+import java.util.Locale;
+
import org.apache.lucene.search.CollectionStatistics;
import org.apache.lucene.search.Explanation;
import org.apache.lucene.search.TermStatistics;
@@ -91,9 +93,9 @@ public abstract class LMSimilarity exten
public String toString() {
String coll = collectionModel.getName();
if (coll != null) {
- return String.format("LM %s - %s", getName(), coll);
+ return String.format(Locale.ROOT, "LM %s - %s", getName(), coll);
} else {
- return String.format("LM %s", getName());
+ return String.format(Locale.ROOT, "LM %s", getName());
}
}
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/NamedThreadFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/NamedThreadFactory.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/NamedThreadFactory.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/NamedThreadFactory.java Mon Jul 9 15:03:56 2012
@@ -17,6 +17,7 @@ package org.apache.lucene.util;
* limitations under the License.
*/
+import java.util.Locale;
import java.util.concurrent.Executors;
import java.util.concurrent.ThreadFactory;
import java.util.concurrent.atomic.AtomicInteger;
@@ -43,7 +44,7 @@ public class NamedThreadFactory implemen
final SecurityManager s = System.getSecurityManager();
group = (s != null) ? s.getThreadGroup() : Thread.currentThread()
.getThreadGroup();
- this.threadNamePrefix = String.format(NAME_PATTERN,
+ this.threadNamePrefix = String.format(Locale.ROOT, NAME_PATTERN,
checkPrefix(threadNamePrefix), threadPoolNumber.getAndIncrement());
}
@@ -57,7 +58,7 @@ public class NamedThreadFactory implemen
* @see java.util.concurrent.ThreadFactory#newThread(java.lang.Runnable)
*/
public Thread newThread(Runnable r) {
- final Thread t = new Thread(group, r, String.format("%s-%d",
+ final Thread t = new Thread(group, r, String.format(Locale.ROOT, "%s-%d",
this.threadNamePrefix, threadNumber.getAndIncrement()), 0);
t.setDaemon(false);
t.setPriority(Thread.NORM_PRIORITY);
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/RamUsageEstimator.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/RamUsageEstimator.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/RamUsageEstimator.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/RamUsageEstimator.java Mon Jul 9 15:03:56 2012
@@ -559,7 +559,7 @@ public final class RamUsageEstimator {
*/
public static String humanReadableUnits(long bytes) {
return humanReadableUnits(bytes,
- new DecimalFormat("0.#", DecimalFormatSymbols.getInstance(Locale.ENGLISH)));
+ new DecimalFormat("0.#", DecimalFormatSymbols.getInstance(Locale.ROOT)));
}
/**
Modified: lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/Version.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/Version.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/Version.java (original)
+++ lucene/dev/trunk/lucene/core/src/java/org/apache/lucene/util/Version.java Mon Jul 9 15:03:56 2012
@@ -73,7 +73,7 @@ public enum Version {
}
public static Version parseLeniently(String version) {
- String parsedMatchVersion = version.toUpperCase(Locale.ENGLISH);
+ String parsedMatchVersion = version.toUpperCase(Locale.ROOT);
return Version.valueOf(parsedMatchVersion.replaceFirst("^(\\d)\\.(\\d)$", "LUCENE_$1$2"));
}
}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/analysis/tokenattributes/TestCharTermAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/analysis/tokenattributes/TestCharTermAttributeImpl.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/analysis/tokenattributes/TestCharTermAttributeImpl.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/analysis/tokenattributes/TestCharTermAttributeImpl.java Mon Jul 9 15:03:56 2012
@@ -159,7 +159,7 @@ public class TestCharTermAttributeImpl e
public void testAppendableInterface() {
CharTermAttributeImpl t = new CharTermAttributeImpl();
- Formatter formatter = new Formatter(t, Locale.US);
+ Formatter formatter = new Formatter(t, Locale.ROOT);
formatter.format("%d", 1234);
assertEquals("1234", t.toString());
formatter.format("%d", 5678);
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/codecs/pulsing/Test10KPulsings.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/codecs/pulsing/Test10KPulsings.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/codecs/pulsing/Test10KPulsings.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/codecs/pulsing/Test10KPulsings.java Mon Jul 9 15:03:56 2012
@@ -71,7 +71,7 @@ public class Test10KPulsings extends Luc
Field field = newField("field", "", ft);
document.add(field);
- NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ENGLISH));
+ NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ROOT));
for (int i = 0; i < 10050; i++) {
field.setStringValue(df.format(i));
@@ -122,7 +122,7 @@ public class Test10KPulsings extends Luc
Field field = newField("field", "", ft);
document.add(field);
- NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ENGLISH));
+ NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ROOT));
final int freq = freqCutoff + 1;
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestBinaryDocument.java Mon Jul 9 15:03:56 2012
@@ -37,7 +37,7 @@ public class TestBinaryDocument extends
{
FieldType ft = new FieldType();
ft.setStored(true);
- IndexableField binaryFldStored = new StoredField("binaryStored", binaryValStored.getBytes());
+ IndexableField binaryFldStored = new StoredField("binaryStored", binaryValStored.getBytes("UTF-8"));
IndexableField stringFldStored = new Field("stringStored", binaryValStored, ft);
Document doc = new Document();
@@ -62,7 +62,7 @@ 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);
+ String binaryFldStoredTest = new String(bytes.bytes, bytes.offset, bytes.length, "UTF-8");
assertTrue(binaryFldStoredTest.equals(binaryValStored));
/** fetch the string field and compare it's content with the original one */
@@ -75,7 +75,7 @@ public class TestBinaryDocument extends
}
public void testCompressionTools() throws Exception {
- IndexableField binaryFldCompressed = new StoredField("binaryCompressed", CompressionTools.compress(binaryValCompressed.getBytes()));
+ IndexableField binaryFldCompressed = new StoredField("binaryCompressed", CompressionTools.compress(binaryValCompressed.getBytes("UTF-8")));
IndexableField stringFldCompressed = new StoredField("stringCompressed", CompressionTools.compressString(binaryValCompressed));
Document doc = new Document();
@@ -94,7 +94,7 @@ 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")));
+ String binaryFldCompressedTest = new String(CompressionTools.decompress(docFromReader.getBinaryValue("binaryCompressed")), "UTF-8");
assertTrue(binaryFldCompressedTest.equals(binaryValCompressed));
assertTrue(CompressionTools.decompressString(docFromReader.getBinaryValue("stringCompressed")).equals(binaryValCompressed));
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestDateTools.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestDateTools.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestDateTools.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/document/TestDateTools.java Mon Jul 9 15:03:56 2012
@@ -61,12 +61,12 @@ public class TestDateTools extends Lucen
public void testStringtoTime() throws ParseException {
long time = DateTools.stringToTime("197001010000");
- Calendar cal = new GregorianCalendar();
+ // we use default locale since LuceneTestCase randomizes it
+ Calendar cal = new GregorianCalendar(TimeZone.getTimeZone("GMT"), Locale.getDefault());
cal.clear();
cal.set(1970, 0, 1, // year=1970, month=january, day=1
0, 0, 0); // hour, minute, second
cal.set(Calendar.MILLISECOND, 0);
- cal.setTimeZone(TimeZone.getTimeZone("GMT"));
assertEquals(cal.getTime().getTime(), time);
cal.set(1980, 1, 2, // year=1980, month=february, day=2
11, 5, 0); // hour, minute, second
@@ -76,9 +76,9 @@ public class TestDateTools extends Lucen
}
public void testDateAndTimetoString() throws ParseException {
- Calendar cal = new GregorianCalendar();
+ // we use default locale since LuceneTestCase randomizes it
+ Calendar cal = new GregorianCalendar(TimeZone.getTimeZone("GMT"), Locale.getDefault());
cal.clear();
- cal.setTimeZone(TimeZone.getTimeZone("GMT"));
cal.set(2004, 1, 3, // year=2004, month=february(!), day=3
22, 8, 56); // hour, minute, second
cal.set(Calendar.MILLISECOND, 333);
@@ -141,9 +141,9 @@ public class TestDateTools extends Lucen
}
public void testRound() {
- Calendar cal = new GregorianCalendar();
+ // we use default locale since LuceneTestCase randomizes it
+ Calendar cal = new GregorianCalendar(TimeZone.getTimeZone("GMT"), Locale.getDefault());
cal.clear();
- cal.setTimeZone(TimeZone.getTimeZone("GMT"));
cal.set(2004, 1, 3, // year=2004, month=february(!), day=3
22, 8, 56); // hour, minute, second
cal.set(Calendar.MILLISECOND, 333);
@@ -180,7 +180,7 @@ public class TestDateTools extends Lucen
}
private String isoFormat(Date date) {
- SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss:SSS", Locale.US);
+ SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss:SSS", Locale.ROOT);
sdf.setTimeZone(TimeZone.getTimeZone("GMT"));
return sdf.format(date);
}
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java Mon Jul 9 15:03:56 2012
@@ -219,10 +219,10 @@ public class TestBackwardsCompatibility
ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
CheckIndex checker = new CheckIndex(dir);
- checker.setInfoStream(new PrintStream(bos));
+ checker.setInfoStream(new PrintStream(bos, false, "UTF-8"));
CheckIndex.Status indexStatus = checker.checkIndex();
assertFalse(indexStatus.clean);
- assertTrue(bos.toString().contains(IndexFormatTooOldException.class.getName()));
+ assertTrue(bos.toString("UTF-8").contains(IndexFormatTooOldException.class.getName()));
dir.close();
_TestUtil.rmDir(oldIndxeDir);
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestCheckIndex.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestCheckIndex.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestCheckIndex.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestCheckIndex.java Mon Jul 9 15:03:56 2012
@@ -52,12 +52,12 @@ public class TestCheckIndex extends Luce
ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
CheckIndex checker = new CheckIndex(dir);
- checker.setInfoStream(new PrintStream(bos));
+ checker.setInfoStream(new PrintStream(bos, false, "UTF-8"));
if (VERBOSE) checker.setInfoStream(System.out);
CheckIndex.Status indexStatus = checker.checkIndex();
if (indexStatus.clean == false) {
System.out.println("CheckIndex failed");
- System.out.println(bos.toString());
+ System.out.println(bos.toString("UTF-8"));
fail();
}
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestDoc.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestDoc.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestDoc.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestDoc.java Mon Jul 9 15:03:56 2012
@@ -17,11 +17,14 @@ package org.apache.lucene.index;
* limitations under the License.
*/
import java.io.File;
-import java.io.FileReader;
-import java.io.FileWriter;
+import java.io.FileInputStream;
+import java.io.FileOutputStream;
import java.io.IOException;
+import java.io.InputStreamReader;
+import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.io.StringWriter;
+import java.io.Writer;
import java.util.Collection;
import java.util.HashSet;
import java.util.LinkedList;
@@ -78,14 +81,14 @@ public class TestDoc extends LuceneTestC
}
private File createOutput(String name, String text) throws IOException {
- FileWriter fw = null;
+ Writer fw = null;
PrintWriter pw = null;
try {
File f = new File(workDir, name);
if (f.exists()) f.delete();
- fw = new FileWriter(f);
+ fw = new OutputStreamWriter(new FileOutputStream(f), "UTF-8");
pw = new PrintWriter(fw);
pw.println(text);
return f;
@@ -182,9 +185,11 @@ public class TestDoc extends LuceneTestC
{
File file = new File(workDir, fileName);
Document doc = new Document();
- doc.add(new TextField("contents", new FileReader(file), Field.Store.NO));
+ InputStreamReader is = new InputStreamReader(new FileInputStream(file), "UTF-8");
+ doc.add(new TextField("contents", is, Field.Store.NO));
writer.addDocument(doc);
writer.commit();
+ is.close();
return writer.newestSegment();
}
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestPayloads.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestPayloads.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestPayloads.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/index/TestPayloads.java Mon Jul 9 15:03:56 2012
@@ -43,9 +43,8 @@ public class TestPayloads extends Lucene
// Simple tests to test the Payload class
public void testPayload() throws Exception {
- byte[] testData = "This is a test!".getBytes();
- BytesRef payload = new BytesRef(testData);
- assertEquals("Wrong payload length.", testData.length, payload.length);
+ BytesRef payload = new BytesRef("This is a test!");
+ assertEquals("Wrong payload length.", "This is a test!".length(), payload.length);
BytesRef clone = payload.clone();
assertEquals(payload.length, clone.length);
@@ -73,7 +72,7 @@ public class TestPayloads extends Lucene
// 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(), 0, 1);
+ analyzer.setPayloadData("f2", "somedata".getBytes("UTF-8"), 0, 1);
writer.addDocument(d);
// flush
writer.close();
@@ -96,8 +95,8 @@ public class TestPayloads extends Lucene
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(), 0, 1);
- analyzer.setPayloadData("f3", "somedata".getBytes(), 0, 3);
+ analyzer.setPayloadData("f2", "somedata".getBytes("UTF-8"), 0, 1);
+ analyzer.setPayloadData("f3", "somedata".getBytes("UTF-8"), 0, 3);
writer.addDocument(d);
// force merge
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestCustomSearcherSort.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestCustomSearcherSort.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestCustomSearcherSort.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestCustomSearcherSort.java Mon Jul 9 15:03:56 2012
@@ -19,8 +19,10 @@ package org.apache.lucene.search;
import java.io.IOException;
import java.util.Calendar;
import java.util.GregorianCalendar;
+import java.util.Locale;
import java.util.Map;
import java.util.Random;
+import java.util.TimeZone;
import java.util.TreeMap;
import org.apache.lucene.document.DateTools;
@@ -230,10 +232,12 @@ public class TestCustomSearcherSort exte
private class RandomGen {
RandomGen(Random random) {
this.random = random;
+ base.set(1980, 1, 1);
}
private Random random;
- private Calendar base = new GregorianCalendar(1980, 1, 1);
+ // we use the default Locale/TZ since LuceneTestCase randomizes it
+ private Calendar base = new GregorianCalendar(TimeZone.getDefault(), Locale.getDefault());
// Just to generate some different Lucene Date strings
private String getLuceneDate() {
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestFieldCache.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestFieldCache.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestFieldCache.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestFieldCache.java Mon Jul 9 15:03:56 2012
@@ -23,6 +23,7 @@ import java.util.ArrayList;
import java.util.Arrays;
import java.util.LinkedHashSet;
import java.util.List;
+import java.util.Locale;
import java.util.concurrent.CyclicBarrier;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
@@ -117,10 +118,10 @@ public class TestFieldCache extends Luce
try {
FieldCache cache = FieldCache.DEFAULT;
ByteArrayOutputStream bos = new ByteArrayOutputStream(1024);
- cache.setInfoStream(new PrintStream(bos));
+ cache.setInfoStream(new PrintStream(bos, false, "UTF-8"));
cache.getDoubles(reader, "theDouble", false);
cache.getFloats(reader, "theDouble", false);
- assertTrue(bos.toString().indexOf("WARNING") != -1);
+ assertTrue(bos.toString("UTF-8").indexOf("WARNING") != -1);
} finally {
FieldCache.DEFAULT.purgeAllCaches();
}
@@ -261,7 +262,7 @@ public class TestFieldCache extends Luce
if (chunk == 0) {
for (int ord = 0; ord < values.size(); ord++) {
BytesRef term = values.get(ord);
- assertNull(String.format("Document[%d] misses field must be null. Has value %s for ord %d", i, term, ord), term);
+ assertNull(String.format(Locale.ROOT, "Document[%d] misses field must be null. Has value %s for ord %d", i, term, ord), term);
}
break;
}
@@ -275,7 +276,7 @@ public class TestFieldCache extends Luce
reuse = termOrds.lookup(i, reuse);
reuse.read(buffer);
}
- assertTrue(String.format("Expected value %s for doc %d and ord %d, but was %s", expected, i, idx, actual), expected.equals(actual));
+ assertTrue(String.format(Locale.ROOT, "Expected value %s for doc %d and ord %d, but was %s", expected, i, idx, actual), expected.equals(actual));
}
if (chunk <= buffer.length) {
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestMultiValuedNumericRangeQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestMultiValuedNumericRangeQuery.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestMultiValuedNumericRangeQuery.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestMultiValuedNumericRangeQuery.java Mon Jul 9 15:03:56 2012
@@ -44,7 +44,7 @@ public class TestMultiValuedNumericRange
newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random()))
.setMaxBufferedDocs(_TestUtil.nextInt(random(), 50, 1000)));
- DecimalFormat format = new DecimalFormat("00000000000", new DecimalFormatSymbols(Locale.US));
+ DecimalFormat format = new DecimalFormat("00000000000", new DecimalFormatSymbols(Locale.ROOT));
int num = atLeast(500);
for (int l = 0; l < num; l++) {
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestRegexpRandom.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestRegexpRandom.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestRegexpRandom.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestRegexpRandom.java Mon Jul 9 15:03:56 2012
@@ -58,7 +58,7 @@ public class TestRegexpRandom extends Lu
Field field = newField("field", "", customType);
doc.add(field);
- NumberFormat df = new DecimalFormat("000", new DecimalFormatSymbols(Locale.ENGLISH));
+ NumberFormat df = new DecimalFormat("000", new DecimalFormatSymbols(Locale.ROOT));
for (int i = 0; i < 1000; i++) {
field.setStringValue(df.format(i));
writer.addDocument(doc);
Modified: lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestWildcardRandom.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestWildcardRandom.java?rev=1359202&r1=1359201&r2=1359202&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestWildcardRandom.java (original)
+++ lucene/dev/trunk/lucene/core/src/test/org/apache/lucene/search/TestWildcardRandom.java Mon Jul 9 15:03:56 2012
@@ -54,7 +54,7 @@ public class TestWildcardRandom extends
Field field = newStringField("field", "", Field.Store.NO);
doc.add(field);
- NumberFormat df = new DecimalFormat("000", new DecimalFormatSymbols(Locale.ENGLISH));
+ NumberFormat df = new DecimalFormat("000", new DecimalFormatSymbols(Locale.ROOT));
for (int i = 0; i < 1000; i++) {
field.setStringValue(df.format(i));
writer.addDocument(doc);