You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@lucene.apache.org by dn...@apache.org on 2004/08/06 21:26:17 UTC
cvs commit: jakarta-lucene/src/demo/org/apache/lucene/demo HTMLDocument.java
dnaber 2004/08/06 12:26:16
Modified: src/demo/org/apache/lucene/demo/html HTMLParser.java
HTMLParser.jj Test.java
src/demo/org/apache/lucene/demo HTMLDocument.java
Log:
Use the HTMLParser constructor that takes a FileInputStream and make sure it gets closed. This was not the case with the constructor that takes a File.
Thus I deprecated that one. I guess the demo isn't part of the "official" API but there are surely people who use it for more than just testing.
PR: 28187
Revision Changes Path
1.7 +9 -6 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 1.6
retrieving revision 1.7
diff -u -r1.6 -r1.7
--- HTMLParser.java 3 Aug 2004 21:32:49 -0000 1.6
+++ HTMLParser.java 6 Aug 2004 19:26:16 -0000 1.7
@@ -40,6 +40,9 @@
}
}
+ /**
+ * @deprecated Use HTMLParser(FileInputStream) instead
+ */
public HTMLParser(File file) throws FileNotFoundException {
this(new FileInputStream(file));
}
@@ -450,15 +453,15 @@
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;
}
1.8 +3 -0 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 1.7
retrieving revision 1.8
diff -u -r1.7 -r1.8
--- HTMLParser.jj 3 Aug 2004 21:32:50 -0000 1.7
+++ HTMLParser.jj 6 Aug 2004 19:26:16 -0000 1.8
@@ -104,6 +104,9 @@
}
}
+ /**
+ * @deprecated Use HTMLParser(FileInputStream) instead
+ */
public HTMLParser(File file) throws FileNotFoundException {
this(new FileInputStream(file));
}
1.3 +15 -8 jakarta-lucene/src/demo/org/apache/lucene/demo/html/Test.java
Index: Test.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/html/Test.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- Test.java 29 Mar 2004 22:48:00 -0000 1.2
+++ Test.java 6 Aug 2004 19:26:16 -0000 1.3
@@ -19,7 +19,7 @@
import java.io.*;
class Test {
- public static void main(String[] argv) throws Exception {
+ public static void main(String[] argv) throws IOException, InterruptedException {
if ("-dir".equals(argv[0])) {
String[] files = new File(argv[1]).list();
java.util.Arrays.sort(files);
@@ -32,12 +32,19 @@
parse(new File(argv[0]));
}
- public static void parse(File file) throws Exception {
- HTMLParser parser = new HTMLParser(file);
- System.out.println("Title: " + Entities.encode(parser.getTitle()));
- System.out.println("Summary: " + Entities.encode(parser.getSummary()));
- LineNumberReader reader = new LineNumberReader(parser.getReader());
- for (String l = reader.readLine(); l != null; l = reader.readLine())
- System.out.println(l);
+ public static void parse(File file) throws IOException, InterruptedException {
+ FileInputStream fis = null;
+ try {
+ fis = new FileInputStream(file);
+ HTMLParser parser = new HTMLParser(fis);
+ System.out.println("Title: " + Entities.encode(parser.getTitle()));
+ System.out.println("Summary: " + Entities.encode(parser.getSummary()));
+ System.out.println("Content:");
+ LineNumberReader reader = new LineNumberReader(parser.getReader());
+ for (String l = reader.readLine(); l != null; l = reader.readLine())
+ System.out.println(l);
+ } finally {
+ if (fis != null) fis.close();
+ }
}
}
1.4 +18 -11 jakarta-lucene/src/demo/org/apache/lucene/demo/HTMLDocument.java
Index: HTMLDocument.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/demo/org/apache/lucene/demo/HTMLDocument.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- HTMLDocument.java 3 Aug 2004 21:49:24 -0000 1.3
+++ HTMLDocument.java 6 Aug 2004 19:26:16 -0000 1.4
@@ -61,19 +61,26 @@
// tokenized prior to indexing.
doc.add(new Field("uid", uid(f), false, true, false));
- HTMLParser parser = new HTMLParser(f);
+ FileInputStream fis = null;
+ try {
+ fis = new FileInputStream(f);
+ HTMLParser parser = new HTMLParser(fis);
+
+ // Add the tag-stripped contents as a Reader-valued Text field so it will
+ // get tokenized and indexed.
+ doc.add(Field.Text("contents", parser.getReader()));
- // Add the tag-stripped contents as a Reader-valued Text field so it will
- // get tokenized and indexed.
- doc.add(Field.Text("contents", parser.getReader()));
+ // Add the summary as an UnIndexed field, so that it is stored and returned
+ // with hit documents for display.
+ doc.add(Field.UnIndexed("summary", parser.getSummary()));
- // Add the summary as an UnIndexed field, so that it is stored and returned
- // with hit documents for display.
- doc.add(Field.UnIndexed("summary", parser.getSummary()));
-
- // Add the title as a separate Text field, so that it can be searched
- // separately.
- doc.add(Field.Text("title", parser.getTitle()));
+ // Add the title as a separate Text field, so that it can be searched
+ // separately.
+ doc.add(Field.Text("title", parser.getTitle()));
+ } finally {
+ if (fis != null)
+ fis.close();
+ }
// return the document
return doc;
---------------------------------------------------------------------
To unsubscribe, e-mail: lucene-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: lucene-dev-help@jakarta.apache.org