goller 2003/11/23 07:37:26
Modified: src/demo/org/apache/lucene/demo/html HTMLParser.java
HTMLParser.jj
Log:
Fix for deadlock between indexing thread and parsing
thread that occurs with long titles. Parsing thread waits
for indexing thread to read from pipeIn, indexing thread
waits for summary. This fixes bug #24301
Revision Changes Path
1.2 +34 -15
jakarta-lucene/src/demo/org/apache/lucene/demo/html/HTMLParser.java
Index: HTMLParser.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/html/HTMLParser.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- HTMLParser.java 11 Sep 2003 01:51:33 -0000 1.1
+++ HTMLParser.java 23 Nov 2003 15:37:26 -0000 1.2
@@ -20,8 +20,25 @@
boolean afterTag = false;
boolean afterSpace = false;
String eol = System.getProperty("line.separator");
- PipedReader pipeIn = null;
- PipedWriter pipeOut;
+ Reader pipeIn = null;
+ Writer pipeOut;
+ private MyPipedInputStream pipeInStream = null;
+ private PipedOutputStream pipeOutStream = null;
+
+ private class MyPipedInputStream extends PipedInputStream{
+
+ public MyPipedInputStream(){
+ super();
+ }
+
+ public MyPipedInputStream(PipedOutputStream src) throws IOException{
+ super(src);
+ }
+
+ public boolean full() throws IOException{
+ return this.available() >= PipedInputStream.PIPE_SIZE;
+ }
+ }
public HTMLParser(File file) throws FileNotFoundException {
this(new FileInputStream(file));
@@ -32,7 +49,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (titleComplete || (length > SUMMARY_LENGTH))
+ if (titleComplete || pipeInStream.full())
break;
wait(10);
}
@@ -46,7 +63,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (titleComplete || (length > SUMMARY_LENGTH))
+ if (titleComplete || pipeInStream.full())
break;
wait(10);
}
@@ -60,7 +77,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (summary.length() >= SUMMARY_LENGTH)
+ if (summary.length() >= SUMMARY_LENGTH || pipeInStream.full())
break;
wait(10);
}
@@ -70,16 +87,18 @@
String sum = summary.toString().trim();
String tit = getTitle();
- if (sum.startsWith(tit))
- return sum.substring(tit.length());
+ if (sum.startsWith(tit) || sum.equals(""))
+ return tit;
else
return sum;
}
public Reader getReader() throws IOException {
if (pipeIn == null) {
- pipeIn = new PipedReader();
- pipeOut = new PipedWriter(pipeIn);
+ pipeInStream = new MyPipedInputStream();
+ pipeOutStream = new PipedOutputStream(pipeInStream);
+ pipeIn = new InputStreamReader(pipeInStream);
+ pipeOut = new OutputStreamWriter(pipeOutStream);
Thread thread = new ParserThread(this);
thread.start(); // start parsing
@@ -405,15 +424,15 @@
finally { jj_save(1, xla); }
}
- final private boolean jj_3_1() {
- if (jj_scan_token(ArgQuote1)) return true;
- if (jj_scan_token(CloseQuote1)) return true;
- return false;
- }
-
final private boolean jj_3_2() {
if (jj_scan_token(ArgQuote2)) return true;
if (jj_scan_token(CloseQuote2)) return true;
+ return false;
+ }
+
+ final private boolean jj_3_1() {
+ if (jj_scan_token(ArgQuote1)) return true;
+ if (jj_scan_token(CloseQuote1)) return true;
return false;
}
1.3 +28 -9
jakarta-lucene/src/demo/org/apache/lucene/demo/html/HTMLParser.jj
Index: HTMLParser.jj
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/html/HTMLParser.jj,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- HTMLParser.jj 29 Jun 2002 22:08:26 -0000 1.2
+++ HTMLParser.jj 23 Nov 2003 15:37:26 -0000 1.3
@@ -84,8 +84,25 @@
boolean afterTag = false;
boolean afterSpace = false;
String eol = System.getProperty("line.separator");
- PipedReader pipeIn = null;
- PipedWriter pipeOut;
+ Reader pipeIn = null;
+ Writer pipeOut;
+ private MyPipedInputStream pipeInStream = null;
+ private PipedOutputStream pipeOutStream = null;
+
+ private class MyPipedInputStream extends PipedInputStream{
+
+ public MyPipedInputStream(){
+ super();
+ }
+
+ public MyPipedInputStream(PipedOutputStream src) throws IOException{
+ super(src);
+ }
+
+ public boolean full() throws IOException{
+ return this.available() >= PipedInputStream.PIPE_SIZE;
+ }
+ }
public HTMLParser(File file) throws FileNotFoundException {
this(new FileInputStream(file));
@@ -96,7 +113,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (titleComplete || (length > SUMMARY_LENGTH))
+ if (titleComplete || pipeInStream.full())
break;
wait(10);
}
@@ -110,7 +127,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (titleComplete || (length > SUMMARY_LENGTH))
+ if (titleComplete || pipeInStream.full())
break;
wait(10);
}
@@ -124,7 +141,7 @@
getReader(); // spawn parsing thread
while (true) {
synchronized(this) {
- if (summary.length() >= SUMMARY_LENGTH)
+ if (summary.length() >= SUMMARY_LENGTH || pipeInStream.full())
break;
wait(10);
}
@@ -134,16 +151,18 @@
String sum = summary.toString().trim();
String tit = getTitle();
- if (sum.startsWith(tit))
- return sum.substring(tit.length());
+ if (sum.startsWith(tit) || sum.equals(""))
+ return tit;
else
return sum;
}
public Reader getReader() throws IOException {
if (pipeIn == null) {
- pipeIn = new PipedReader();
- pipeOut = new PipedWriter(pipeIn);
+ pipeInStream = new MyPipedInputStream();
+ pipeOutStream = new PipedOutputStream(pipeInStream);
+ pipeIn = new InputStreamReader(pipeInStream);
+ pipeOut = new OutputStreamWriter(pipeOutStream);
Thread thread = new ParserThread(this);
thread.start(); // start parsing
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
