htmlparser-cvs Mailing List for HTML Parser (Page 41)
Brought to you by:
derrickoswald
Menu
▾
▴
htmlparser-cvs — syncmail email notification of CVS commits
You can subscribe to this list here.
| 2003 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(141) |
Jun
(108) |
Jul
(66) |
Aug
(127) |
Sep
(155) |
Oct
(149) |
Nov
(72) |
Dec
(72) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2004 |
Jan
(100) |
Feb
(36) |
Mar
(21) |
Apr
(3) |
May
(87) |
Jun
(28) |
Jul
(84) |
Aug
(5) |
Sep
(14) |
Oct
|
Nov
|
Dec
|
| 2005 |
Jan
(1) |
Feb
(39) |
Mar
(26) |
Apr
(38) |
May
(14) |
Jun
(10) |
Jul
|
Aug
|
Sep
(13) |
Oct
(8) |
Nov
(10) |
Dec
|
| 2006 |
Jan
|
Feb
(1) |
Mar
(17) |
Apr
(20) |
May
(28) |
Jun
(24) |
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2015 |
Jan
|
Feb
|
Mar
(1) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/tests/nodeDecoratorTests
Modified Files:
AllTests.java DecodingNodeTest.java
EscapeCharacterRemovingNodeTest.java
NonBreakingSpaceConvertingNodeTest.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/AllTests.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** AllTests.java 8 Sep 2003 02:26:30 -0000 1.9
--- AllTests.java 10 Sep 2003 03:38:24 -0000 1.10
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 31,35 ****
import junit.framework.TestSuite;
! public class AllTests extends junit.framework.TestCase
{
public AllTests(String name) {
--- 31,35 ----
import junit.framework.TestSuite;
! public class AllTests extends junit.framework.TestCase
{
public AllTests(String name) {
***************
*** 42,46 ****
suite.addTestSuite(EscapeCharacterRemovingNodeTest.class);
suite.addTestSuite(NonBreakingSpaceConvertingNodeTest.class);
! return suite;
}
--- 42,46 ----
suite.addTestSuite(EscapeCharacterRemovingNodeTest.class);
suite.addTestSuite(NonBreakingSpaceConvertingNodeTest.class);
! return suite;
}
Index: DecodingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/DecodingNodeTest.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** DecodingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.10
--- DecodingNodeTest.java 10 Sep 2003 03:38:24 -0000 1.11
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 48,56 ****
stringNodeFactory.setNodeDecoding(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
--- 48,56 ----
stringNodeFactory.setNodeDecoding(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
***************
*** 60,64 ****
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop";
--- 60,64 ----
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop";
***************
*** 73,80 ****
String ENCODED_DIVISION_SIGN =
"÷ is the division sign.";
!
String DECODED_DIVISION_SIGN =
"÷ is the division sign.";
!
assertEquals(
"numeric reference for division sign",
--- 73,80 ----
String ENCODED_DIVISION_SIGN =
"÷ is the division sign.";
!
String DECODED_DIVISION_SIGN =
"÷ is the division sign.";
!
assertEquals(
"numeric reference for division sign",
***************
*** 82,96 ****
parseToObtainDecodedResult(ENCODED_DIVISION_SIGN));
}
!
!
public void testReferencesInString () throws Exception {
String ENCODED_REFERENCE_IN_STRING =
"Thus, the character entity reference ÷ is a more convenient" +
" form than ÷ for obtaining the division sign (÷)";
!
String DECODED_REFERENCE_IN_STRING =
"Thus, the character entity reference ÷ is a more convenient" +
" form than ÷ for obtaining the division sign (÷)";
!
assertEquals (
"character references within a string",
--- 82,96 ----
parseToObtainDecodedResult(ENCODED_DIVISION_SIGN));
}
!
!
public void testReferencesInString () throws Exception {
String ENCODED_REFERENCE_IN_STRING =
"Thus, the character entity reference ÷ is a more convenient" +
" form than ÷ for obtaining the division sign (÷)";
!
String DECODED_REFERENCE_IN_STRING =
"Thus, the character entity reference ÷ is a more convenient" +
" form than ÷ for obtaining the division sign (÷)";
!
assertEquals (
"character references within a string",
***************
*** 100,110 ****
public void testBogusCharacterEntityReference() throws Exception {
!
! String ENCODED_BOGUS_CHARACTER_ENTITY =
"The character entity reference &divode; is bogus";
!
String DECODED_BOGUS_CHARACTER_ENTITY =
"The character entity reference &divode; is bogus";
!
assertEquals (
"bogus character entity reference",
--- 100,110 ----
public void testBogusCharacterEntityReference() throws Exception {
!
! String ENCODED_BOGUS_CHARACTER_ENTITY =
"The character entity reference &divode; is bogus";
!
String DECODED_BOGUS_CHARACTER_ENTITY =
"The character entity reference &divode; is bogus";
!
assertEquals (
"bogus character entity reference",
***************
*** 112,124 ****
parseToObtainDecodedResult(ENCODED_BOGUS_CHARACTER_ENTITY));
}
!
public void testDecodingNonBreakingSpaceDoesNotOccur() throws Exception {
!
! String ENCODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0.";
!
assertEquals (
"bogus character entity reference",
--- 112,124 ----
parseToObtainDecodedResult(ENCODED_BOGUS_CHARACTER_ENTITY));
}
!
public void testDecodingNonBreakingSpaceDoesNotOccur() throws Exception {
!
! String ENCODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0.";
!
assertEquals (
"bogus character entity reference",
***************
*** 126,131 ****
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
!
}
--- 126,131 ----
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
!
}
Index: EscapeCharacterRemovingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/EscapeCharacterRemovingNodeTest.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** EscapeCharacterRemovingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.10
--- EscapeCharacterRemovingNodeTest.java 10 Sep 2003 03:38:24 -0000 1.11
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 48,57 ****
stringNodeFactory.setEscapeCharacterRemoval(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
--- 48,57 ----
stringNodeFactory.setEscapeCharacterRemoval(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
***************
*** 61,65 ****
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\tCreated by Industrial Logic, Inc.";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
--- 61,65 ----
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\tCreated by Industrial Logic, Inc.";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
***************
*** 70,78 ****
parseToObtainDecodedResult(ENCODED_WORKSHOP_TITLE));
}
!
public void testCarriageReturn() throws Exception {
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\nCreated by Industrial Logic, Inc.\n";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
--- 70,78 ----
parseToObtainDecodedResult(ENCODED_WORKSHOP_TITLE));
}
!
public void testCarriageReturn() throws Exception {
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\nCreated by Industrial Logic, Inc.\n";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
***************
*** 82,106 ****
DECODED_WORKSHOP_TITLE,
parseToObtainDecodedResult(ENCODED_WORKSHOP_TITLE));
! }
!
public void testWithDecodingNodeDecorator() throws Exception {
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\nCreated by Industrial Logic, Inc.\n";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
StringBuffer decodedContent = new StringBuffer();
!
StringNodeFactory stringNodeFactory = new StringNodeFactory();
stringNodeFactory.setNodeDecoding(true);
stringNodeFactory.setEscapeCharacterRemoval(true);
!
createParser(ENCODED_WORKSHOP_TITLE);
parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
assertEquals(
--- 82,106 ----
DECODED_WORKSHOP_TITLE,
parseToObtainDecodedResult(ENCODED_WORKSHOP_TITLE));
! }
!
public void testWithDecodingNodeDecorator() throws Exception {
String ENCODED_WORKSHOP_TITLE =
"The Testing & Refactoring Workshop\nCreated by Industrial Logic, Inc.\n";
!
String DECODED_WORKSHOP_TITLE =
"The Testing & Refactoring WorkshopCreated by Industrial Logic, Inc.";
StringBuffer decodedContent = new StringBuffer();
!
StringNodeFactory stringNodeFactory = new StringNodeFactory();
stringNodeFactory.setNodeDecoding(true);
stringNodeFactory.setEscapeCharacterRemoval(true);
!
createParser(ENCODED_WORKSHOP_TITLE);
parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
assertEquals(
***************
*** 108,112 ****
DECODED_WORKSHOP_TITLE,
decodedContent.toString());
!
}
}
--- 108,112 ----
DECODED_WORKSHOP_TITLE,
decodedContent.toString());
!
}
}
Index: NonBreakingSpaceConvertingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/NonBreakingSpaceConvertingNodeTest.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** NonBreakingSpaceConvertingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.9
--- NonBreakingSpaceConvertingNodeTest.java 10 Sep 2003 03:38:24 -0000 1.10
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 44,57 ****
throws ParserException {
StringBuffer decodedContent = new StringBuffer();
!
StringNodeFactory stringNodeFactory = new StringNodeFactory();
stringNodeFactory.setNonBreakSpaceConversion(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
--- 44,57 ----
throws ParserException {
StringBuffer decodedContent = new StringBuffer();
!
StringNodeFactory stringNodeFactory = new StringNodeFactory();
stringNodeFactory.setNonBreakSpaceConversion(true);
createParser(STRING_TO_DECODE);
! parser.setStringNodeFactory(stringNodeFactory);
NodeIterator nodes = parser.elements();
!
! while (nodes.hasMoreNodes())
! decodedContent.append(nodes.nextNode().toPlainTextString());
return decodedContent.toString();
***************
*** 59,68 ****
public void testOneNonBreakingSpace() throws Exception {
! String ENCODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0 inside of it.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
"Here is string with inside of it.";
!
assertEquals (
"\u00a0 was converted to a space correctly",
--- 59,68 ----
public void testOneNonBreakingSpace() throws Exception {
! String ENCODED_WITH_NON_BREAKING_SPACE =
"Here is string with \u00a0 inside of it.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
"Here is string with inside of it.";
!
assertEquals (
"\u00a0 was converted to a space correctly",
***************
*** 70,81 ****
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
public void testMultipleNonBreakingSpace() throws Exception {
! String ENCODED_WITH_NON_BREAKING_SPACE =
"\u00a0Here is string with \u00a0 inside of it\u00a0.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
" Here is string with inside of it .";
!
assertEquals (
"\u00a0 was converted to a space correctly",
--- 70,81 ----
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
public void testMultipleNonBreakingSpace() throws Exception {
! String ENCODED_WITH_NON_BREAKING_SPACE =
"\u00a0Here is string with \u00a0 inside of it\u00a0.";
!
String DECODED_WITH_NON_BREAKING_SPACE =
" Here is string with inside of it .";
!
assertEquals (
"\u00a0 was converted to a space correctly",
***************
*** 83,86 ****
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
}
--- 83,86 ----
parseToObtainDecodedResult(ENCODED_WITH_NON_BREAKING_SPACE));
}
!
}
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/tests/lexerTests
Modified Files:
AllTests.java KitTest.java LexerTests.java PageIndexTests.java
PageTests.java SourceTests.java StreamTests.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/AllTests.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** AllTests.java 8 Sep 2003 02:26:30 -0000 1.9
--- AllTests.java 10 Sep 2003 03:38:24 -0000 1.10
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 32,36 ****
import junit.framework.TestSuite;
! public class AllTests extends TestCase
{
public AllTests (String name)
--- 32,36 ----
import junit.framework.TestSuite;
! public class AllTests extends TestCase
{
public AllTests (String name)
***************
*** 47,51 ****
suite.addTestSuite (PageIndexTests.class);
suite.addTestSuite (LexerTests.class);
! return suite;
}
--- 47,51 ----
suite.addTestSuite (PageIndexTests.class);
suite.addTestSuite (LexerTests.class);
! return suite;
}
***************
*** 92,101 ****
* from http://www.mail-archive.com/commons-user%40jakarta.apache.org/msg02958.html
*
! * The problem is within the UI test runners of JUnit. They bring
! * with them a custom classloader, which causes the
! * LogConfigurationException. Unfortunately Log4j doesn't work
* either.
! *
! * Solution: Disable "Reload classes every run" or start JUnit with
* command line option -noloading before the name of the Testsuite.
*/
--- 92,101 ----
* from http://www.mail-archive.com/commons-user%40jakarta.apache.org/msg02958.html
*
! * The problem is within the UI test runners of JUnit. They bring
! * with them a custom classloader, which causes the
! * LogConfigurationException. Unfortunately Log4j doesn't work
* either.
! *
! * Solution: Disable "Reload classes every run" or start JUnit with
* command line option -noloading before the name of the Testsuite.
*/
Index: KitTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** KitTest.java 27 Aug 2003 02:40:24 -0000 1.3
--- KitTest.java 10 Sep 2003 03:38:24 -0000 1.4
***************
*** 18,22 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 18,22 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 67,71 ****
Vector mNodes;
int mIndex;
!
/**
* Creates a new instance of KitTest
--- 67,71 ----
Vector mNodes;
int mIndex;
!
/**
* Creates a new instance of KitTest
***************
*** 88,92 ****
char ch;
StringBuffer ret;
!
length = s.length ();
ret = new StringBuffer (length);
--- 88,92 ----
char ch;
StringBuffer ret;
!
length = s.length ();
ret = new StringBuffer (length);
***************
*** 97,101 ****
ret.append (ch);
}
!
return (ret.toString ());
}
--- 97,101 ----
ret.append (ch);
}
!
return (ret.toString ());
}
***************
*** 183,187 ****
}
}
!
/**
* Callback for a remark lexeme.
--- 183,187 ----
}
}
!
/**
* Callback for a remark lexeme.
***************
*** 247,251 ****
}
}
!
/**
* Callback for a start tag lexeme.
--- 247,251 ----
}
}
!
/**
* Callback for a start tag lexeme.
***************
*** 313,317 ****
}
}
!
/**
* Callback for an end tag lexeme.
--- 313,317 ----
}
}
!
/**
* Callback for an end tag lexeme.
***************
*** 378,382 ****
}
}
!
/**
* Callback for a non-composite tag.
--- 378,382 ----
}
}
!
/**
* Callback for a non-composite tag.
***************
*** 450,454 ****
}
!
/**
* Callback for an error condition.
--- 450,454 ----
}
!
/**
* Callback for an error condition.
***************
*** 470,474 ****
{
}
!
/**
* This is invoked after the stream has been parsed, but before
--- 470,474 ----
{
}
!
/**
* This is invoked after the stream has been parsed, but before
***************
*** 493,499 ****
// Document doc;
// Element[] ret;
! //
// ret = null;
! //
// // need this because HTMLEditorKit is not thread safe apparently
// synchronized (Boolean.TRUE)
--- 493,499 ----
// Document doc;
// Element[] ret;
! //
// ret = null;
! //
// // need this because HTMLEditorKit is not thread safe apparently
// synchronized (Boolean.TRUE)
***************
*** 503,507 ****
// // the Document class does not yet handle charset's properly
// doc.putProperty ("IgnoreCharsetDirective", Boolean.TRUE);
! //
// try
// {
--- 503,507 ----
// // the Document class does not yet handle charset's properly
// doc.putProperty ("IgnoreCharsetDirective", Boolean.TRUE);
! //
// try
// {
***************
*** 513,520 ****
// throw new IOException ("parse error " + ble.getMessage ());
// }
! //
// ret = doc.getRootElements ();
// }
! //
// return (ret);
// }
--- 513,520 ----
// throw new IOException ("parse error " + ble.getMessage ());
// }
! //
// ret = doc.getRootElements ();
// }
! //
// return (ret);
// }
***************
*** 527,531 ****
// ElementIterator it;
// Element child;
! //
// if (element.isLeaf ())
// {
--- 527,531 ----
// ElementIterator it;
// Element child;
! //
// if (element.isLeaf ())
// {
***************
*** 553,557 ****
}
! public HTMLEditorKit.Parser getParser ()
{
return (super.getParser ());
--- 553,557 ----
}
! public HTMLEditorKit.Parser getParser ()
{
return (super.getParser ());
***************
*** 581,585 ****
MyKit kit;
Parser parser;
!
Element[] elements;
--- 581,585 ----
MyKit kit;
Parser parser;
!
Element[] elements;
***************
*** 608,611 ****
--- 608,631 ----
*
* $Log$
+ * Revision 1.4 2003/09/10 03:38:24 derrickoswald
+ * Add style checking target to ant build script:
+ * ant checkstyle
+ * It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
+ * The rules are in the file htmlparser_checks.xml in the src directory.
+ *
+ * Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
+ * on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
+ *
+ * There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
+ * For example:
+ * It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
+ * It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
+ * that's more than 80 characters long.
+ * It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
+ * It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
+ *
+ * But it points out some really interesting things, even if you don't agree with the style guidelines,
+ * so it's worth a look.
+ *
* Revision 1.3 2003/08/27 02:40:24 derrickoswald
* Testing cvs keyword substitution.
Index: LexerTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/LexerTests.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** LexerTests.java 8 Sep 2003 02:26:30 -0000 1.5
--- LexerTests.java 10 Sep 2003 03:38:24 -0000 1.6
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 57,61 ****
public class LexerTests extends TestCase
{
!
/**
* Test the Lexer class.
--- 57,61 ----
public class LexerTests extends TestCase
{
!
/**
* Test the Lexer class.
***************
*** 149,153 ****
"Hello world\r\n",
"Hello world\r",
!
};
String[] suffixes =
--- 149,153 ----
"Hello world\r\n",
"Hello world\r",
!
};
String[] suffixes =
***************
*** 235,239 ****
node = (RemarkNode)lexer.nextNode ();
assertEquals ("Tag contents wrong", reference, node.toHtml ());
!
suffix = "<head>";
reference = "<!-- This is a comment -->";
--- 235,239 ----
node = (RemarkNode)lexer.nextNode ();
assertEquals ("Tag contents wrong", reference, node.toHtml ());
!
suffix = "<head>";
reference = "<!-- This is a comment -->";
***************
*** 335,339 ****
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
--- 335,339 ----
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
***************
*** 367,371 ****
System.out.println ("lexer is " + ((double)(old_total - new_total)/(double)old_total*100.0) + "% faster");
}
!
/**
* Test the relative speed reading from a string parsing tags too.
--- 367,371 ----
System.out.println ("lexer is " + ((double)(old_total - new_total)/(double)old_total*100.0) + "% faster");
}
!
/**
* Test the relative speed reading from a string parsing tags too.
***************
*** 400,404 ****
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
--- 400,404 ----
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
***************
*** 471,475 ****
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
--- 471,475 ----
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
***************
*** 539,543 ****
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
--- 539,543 ----
buffer.append ((char)i);
source.close ();
! html = buffer.toString ();
old_total = 0;
new_total = 0;
Index: PageIndexTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/PageIndexTests.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** PageIndexTests.java 8 Sep 2003 02:26:30 -0000 1.6
--- PageIndexTests.java 10 Sep 2003 03:38:24 -0000 1.7
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 35,39 ****
public class PageIndexTests extends TestCase
{
!
/**
* Test the end-of-line index class.
--- 35,39 ----
public class PageIndexTests extends TestCase
{
!
/**
* Test the end-of-line index class.
***************
*** 49,55 ****
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
--- 49,55 ----
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
***************
*** 58,62 ****
assertTrue ("wrong position", pos == index.add (i));
}
!
list = index.get ();
for (int i = 0; i < 10000; i++)
--- 58,62 ----
assertTrue ("wrong position", pos == index.add (i));
}
!
list = index.get ();
for (int i = 0; i < 10000; i++)
***************
*** 69,75 ****
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
--- 69,75 ----
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
***************
*** 89,95 ****
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
--- 89,95 ----
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
***************
*** 111,117 ****
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
--- 111,117 ----
int pos;
int[] list;
!
index = new PageIndex (null);
!
for (int i = 0; i < 10000; i++)
{
Index: PageTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/PageTests.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** PageTests.java 8 Sep 2003 02:26:30 -0000 1.8
--- PageTests.java 10 Sep 2003 03:38:24 -0000 1.9
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
Index: SourceTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** SourceTests.java 8 Sep 2003 02:26:30 -0000 1.7
--- SourceTests.java 10 Sep 2003 03:38:24 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 69,73 ****
{
Source source;
!
source = new Source (null);
assertTrue ("erroneous character", -1 == source.read ());
--- 69,73 ----
{
Source source;
!
source = new Source (null);
assertTrue ("erroneous character", -1 == source.read ());
***************
*** 80,84 ****
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[0])), null);
assertTrue ("erroneous character", -1 == source.read ());
--- 80,84 ----
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[0])), null);
assertTrue ("erroneous character", -1 == source.read ());
***************
*** 91,95 ****
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 })), null);
assertTrue ("erroneous character", 'B' == source.read ());
--- 91,95 ----
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 })), null);
assertTrue ("erroneous character", 'B' == source.read ());
***************
*** 127,131 ****
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
--- 127,131 ----
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
***************
*** 151,155 ****
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
--- 151,155 ----
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
***************
*** 175,179 ****
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
--- 175,179 ----
StringBuffer buffer;
int c;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
***************
*** 204,208 ****
StringBuffer buffer;
int c;
!
part1 = "Now is the time ";
part2 = "for all good men ";
--- 204,208 ----
StringBuffer buffer;
int c;
!
part1 = "Now is the time ";
part2 = "for all good men ";
***************
*** 228,232 ****
Source source;
char[] buffer;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
--- 228,232 ----
Source source;
char[] buffer;
!
reference = "Now is the time for all good men to come to the aid of the party";
source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
***************
*** 251,255 ****
int c;
int length;
!
part1 = "Now is the time ";
part2 = "for all good men ";
--- 251,255 ----
int c;
int length;
!
part1 = "Now is the time ";
part2 = "for all good men ";
***************
*** 276,280 ****
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x62 })), null);
assertTrue ("ready?", !source.ready ());
--- 276,280 ----
{
Source source;
!
source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x62 })), null);
assertTrue ("ready?", !source.ready ());
Index: StreamTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/StreamTests.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** StreamTests.java 8 Sep 2003 02:26:30 -0000 1.6
--- StreamTests.java 10 Sep 2003 03:38:24 -0000 1.7
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 59,63 ****
{
Stream stream;
!
stream = new Stream (null);
assertTrue ("erroneous character", -1 == stream.read ());
--- 59,63 ----
{
Stream stream;
!
stream = new Stream (null);
assertTrue ("erroneous character", -1 == stream.read ());
***************
*** 70,74 ****
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[0]));
assertTrue ("erroneous character", -1 == stream.read ());
--- 70,74 ----
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[0]));
assertTrue ("erroneous character", -1 == stream.read ());
***************
*** 81,85 ****
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 }));
assertTrue ("erroneous character", 0x42 == stream.read ());
--- 81,85 ----
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 }));
assertTrue ("erroneous character", 0x42 == stream.read ());
***************
*** 156,160 ****
* though keeps reading while this delay is going on and hence gets a big
* chunk of the file in memory. This advantage translates to a faster
! * spin through the bytes after the delay.
*/
public void testThreaded () throws IOException
--- 156,160 ----
* though keeps reading while this delay is going on and hence gets a big
* chunk of the file in memory. This advantage translates to a faster
! * spin through the bytes after the delay.
*/
public void testThreaded () throws IOException
***************
*** 307,311 ****
bytes2.add (new Byte ((byte)b));
}
!
index = 0;
while (index < bytes1.size ())
--- 307,311 ----
bytes2.add (new Byte ((byte)b));
}
!
index = 0;
while (index < bytes1.size ())
***************
*** 314,318 ****
index++;
}
!
bytes1.clear ();
bytes2.clear ();
--- 314,318 ----
index++;
}
!
bytes1.clear ();
bytes2.clear ();
***************
*** 383,387 ****
bytes2.add (new Byte ((byte)b));
}
!
index = 0;
while (index < bytes1.size ())
--- 383,387 ----
bytes2.add (new Byte ((byte)b));
}
!
index = 0;
while (index < bytes1.size ())
***************
*** 390,394 ****
index++;
}
!
bytes1.clear ();
bytes2.clear ();
--- 390,394 ----
index++;
}
!
bytes1.clear ();
bytes2.clear ();
***************
*** 427,431 ****
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x78 }));
assertTrue ("erroneous character", 0x42 == stream.read ());
--- 427,431 ----
{
Stream stream;
!
stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x78 }));
assertTrue ("erroneous character", 0x42 == stream.read ());
|
|
From: <der...@us...> - 2003-09-10 03:39:06
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/codeMetrics
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/tests/codeMetrics
Modified Files:
LineCounter.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: LineCounter.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/codeMetrics/LineCounter.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** LineCounter.java 8 Sep 2003 02:26:30 -0000 1.6
--- LineCounter.java 10 Sep 2003 03:38:23 -0000 1.7
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 36,40 ****
public class LineCounter {
!
public int count(File file) {
System.out.println("Handling "+file.getName());
--- 36,40 ----
public class LineCounter {
!
public int count(File file) {
System.out.println("Handling "+file.getName());
***************
*** 51,55 ****
}
! /**
* Counts code excluding comments and blank lines in the given file
* @param file
--- 51,55 ----
}
! /**
* Counts code excluding comments and blank lines in the given file
* @param file
***************
*** 64,72 ****
do {
line = reader.readLine();
! if (line!=null &&
! line.indexOf("*")==-1 &&
! line.indexOf("//")==-1 &&
line.length()>0
! ) count++;
}
while (line!=null);
--- 64,72 ----
do {
line = reader.readLine();
! if (line!=null &&
! line.indexOf("*")==-1 &&
! line.indexOf("//")==-1 &&
line.length()>0
! ) count++;
}
while (line!=null);
***************
*** 82,86 ****
public boolean accept(File file) {
if (file.getName().indexOf(".java")!=-1 || file.isDirectory()) {
! return true;
} else {
return false;
--- 82,86 ----
public boolean accept(File file) {
if (file.getName().indexOf(".java")!=-1 || file.isDirectory()) {
! return true;
} else {
return false;
***************
*** 93,97 ****
return count;
}
!
public static void main(String [] args) {
LineCounter lc = new LineCounter();
--- 93,97 ----
return count;
}
!
public static void main(String [] args) {
LineCounter lc = new LineCounter();
|
|
From: <der...@us...> - 2003-09-10 03:39:06
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/data
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/tags/data
Modified Files:
CompositeTagData.java FormData.java LinkData.java TagData.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: CompositeTagData.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/data/CompositeTagData.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** CompositeTagData.java 8 Sep 2003 02:26:30 -0000 1.31
--- CompositeTagData.java 10 Sep 2003 03:38:23 -0000 1.32
***************
*** 1,27 ****
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 1,27 ----
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 37,41 ****
private Tag endTag;
private NodeList children;
!
public CompositeTagData(
Tag startTag, Tag endTag, NodeList children) {
--- 37,41 ----
private Tag endTag;
private NodeList children;
!
public CompositeTagData(
Tag startTag, Tag endTag, NodeList children) {
***************
*** 46,50 ****
for (SimpleNodeIterator i = children.elements();i.hasMoreNodes();) {
this.children.add(i.nextNode());
! }
}
--- 46,50 ----
for (SimpleNodeIterator i = children.elements();i.hasMoreNodes();) {
this.children.add(i.nextNode());
! }
}
***************
*** 60,64 ****
return startTag;
}
!
public String toString() {
StringBuffer childrenString = new StringBuffer();
--- 60,64 ----
return startTag;
}
!
public String toString() {
StringBuffer childrenString = new StringBuffer();
Index: FormData.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/data/FormData.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** FormData.java 8 Sep 2003 02:26:30 -0000 1.26
--- FormData.java 10 Sep 2003 03:38:23 -0000 1.27
***************
*** 1,27 ****
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 1,27 ----
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 37,41 ****
private Vector formInputVector;
private Vector textAreaVector;
!
public FormData(String formURL, String formName, String formMethod,
Vector formInputVector, Vector textAreaVector) {
--- 37,41 ----
private Vector formInputVector;
private Vector textAreaVector;
!
public FormData(String formURL, String formName, String formMethod,
Vector formInputVector, Vector textAreaVector) {
Index: LinkData.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/data/LinkData.java,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** LinkData.java 8 Sep 2003 02:26:30 -0000 1.28
--- LinkData.java 10 Sep 2003 03:38:23 -0000 1.29
***************
*** 1,27 ****
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 1,27 ----
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 35,39 ****
private boolean mailLink;
private boolean javascriptLink;
!
public LinkData(String link,String linkText,String accessKey,boolean mailLink,
boolean javascriptLink) {
--- 35,39 ----
private boolean mailLink;
private boolean javascriptLink;
!
public LinkData(String link,String linkText,String accessKey,boolean mailLink,
boolean javascriptLink) {
Index: TagData.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/data/TagData.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** TagData.java 8 Sep 2003 02:26:30 -0000 1.29
--- TagData.java 10 Sep 2003 03:38:23 -0000 1.30
***************
*** 1,27 ****
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 1,27 ----
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 38,50 ****
private String urlBeingParsed;
private boolean isXmlEndTag;
!
public TagData(int tagBegin, int tagEnd, String tagContents,String tagLine) {
this(tagBegin, tagEnd, 0, 0, tagContents, tagLine, "", false);
}
!
public TagData(int tagBegin, int tagEnd, String tagContents,String tagLine, String urlBeingParsed) {
this(tagBegin, tagEnd, 0, 0, tagContents, tagLine, urlBeingParsed, false);
}
!
public TagData(int tagBegin, int tagEnd, int startLine, int endLine, String tagContents,String tagLine, String urlBeingParsed, boolean isXmlEndTag) {
this.tagBegin = tagBegin;
--- 38,50 ----
private String urlBeingParsed;
private boolean isXmlEndTag;
!
public TagData(int tagBegin, int tagEnd, String tagContents,String tagLine) {
this(tagBegin, tagEnd, 0, 0, tagContents, tagLine, "", false);
}
!
public TagData(int tagBegin, int tagEnd, String tagContents,String tagLine, String urlBeingParsed) {
this(tagBegin, tagEnd, 0, 0, tagContents, tagLine, urlBeingParsed, false);
}
!
public TagData(int tagBegin, int tagEnd, int startLine, int endLine, String tagContents,String tagLine, String urlBeingParsed, boolean isXmlEndTag) {
this.tagBegin = tagBegin;
***************
*** 53,61 ****
this.endLine = endLine;
this.tagContents = tagContents;
! this.tagLine = tagLine;
this.urlBeingParsed = urlBeingParsed;
this.isXmlEndTag = isXmlEndTag;
}
!
public int getTagBegin() {
return tagBegin;
--- 53,61 ----
this.endLine = endLine;
this.tagContents = tagContents;
! this.tagLine = tagLine;
this.urlBeingParsed = urlBeingParsed;
this.isXmlEndTag = isXmlEndTag;
}
!
public int getTagBegin() {
return tagBegin;
***************
*** 85,89 ****
this.urlBeingParsed = baseUrl;
}
!
public boolean isEmptyXmlTag() {
return isXmlEndTag;
--- 85,89 ----
this.urlBeingParsed = baseUrl;
}
!
public boolean isEmptyXmlTag() {
return isXmlEndTag;
***************
*** 94,98 ****
* will only be valid for tags created with the
* <code>CompositeTagScanner</code> or a subclass of it.
! */
public int getStartLine() {
return startLine;
--- 94,98 ----
* will only be valid for tags created with the
* <code>CompositeTagScanner</code> or a subclass of it.
! */
public int getStartLine() {
return startLine;
***************
*** 103,110 ****
* will only be valid for tags created with the
* <code>CompositeTagScanner</code> or a subclass of it.
! */
public int getEndLine() {
return endLine;
}
!
}
--- 103,110 ----
* will only be valid for tags created with the
* <code>CompositeTagScanner</code> or a subclass of it.
! */
public int getEndLine() {
return endLine;
}
!
}
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/parserapplications
Modified Files:
LinkExtractor.java MailRipper.java Robot.java
StringExtractor.java package.html
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: LinkExtractor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/LinkExtractor.java,v
retrieving revision 1.43
retrieving revision 1.44
diff -C2 -d -r1.43 -r1.44
*** LinkExtractor.java 8 Sep 2003 02:26:29 -0000 1.43
--- LinkExtractor.java 10 Sep 2003 03:38:18 -0000 1.44
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 50,54 ****
e.printStackTrace();
}
!
}
public void extractLinks() throws ParserException {
--- 50,54 ----
e.printStackTrace();
}
!
}
public void extractLinks() throws ParserException {
Index: MailRipper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/MailRipper.java,v
retrieving revision 1.44
retrieving revision 1.45
diff -C2 -d -r1.44 -r1.45
*** MailRipper.java 8 Sep 2003 02:26:29 -0000 1.44
--- MailRipper.java 10 Sep 2003 03:38:18 -0000 1.45
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 77,85 ****
System.out.println("If you have any doubts, please join the HTMLParser mailing list (user/developer) from the HTML Parser home page instead of mailing any of the contributors directly. You will be surprised with the quality of open source support. ");
System.exit(-1);
! }
String resourceLocation = "http://htmlparser.sourceforge.net";
if (args.length!=0) resourceLocation = args[0];
!
! MailRipper ripper = new MailRipper(resourceLocation);
System.out.println("Ripping Site "+resourceLocation);
try {
--- 77,85 ----
System.out.println("If you have any doubts, please join the HTMLParser mailing list (user/developer) from the HTML Parser home page instead of mailing any of the contributors directly. You will be surprised with the quality of open source support. ");
System.exit(-1);
! }
String resourceLocation = "http://htmlparser.sourceforge.net";
if (args.length!=0) resourceLocation = args[0];
!
! MailRipper ripper = new MailRipper(resourceLocation);
System.out.println("Ripping Site "+resourceLocation);
try {
***************
*** 109,113 ****
}
}
! return mailAddresses.elements();
}
}
--- 109,113 ----
}
}
! return mailAddresses.elements();
}
}
Index: Robot.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/Robot.java,v
retrieving revision 1.46
retrieving revision 1.47
diff -C2 -d -r1.46 -r1.47
*** Robot.java 8 Sep 2003 02:26:29 -0000 1.46
--- Robot.java 10 Sep 2003 03:38:18 -0000 1.47
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 41,45 ****
private org.htmlparser.Parser parser;
/**
! * Robot crawler - Provide the starting url
*/
public Robot(String resourceLocation) {
--- 41,45 ----
private org.htmlparser.Parser parser;
/**
! * Robot crawler - Provide the starting url
*/
public Robot(String resourceLocation) {
***************
*** 82,86 ****
if (!linkTag.isMailLink())
{
! if (linkTag.getLink().toUpperCase().indexOf("HTM")!=-1 ||
linkTag.getLink().toUpperCase().indexOf("COM")!=-1 ||
linkTag.getLink().toUpperCase().indexOf("ORG")!=-1)
--- 82,86 ----
if (!linkTag.isMailLink())
{
! if (linkTag.getLink().toUpperCase().indexOf("HTM")!=-1 ||
linkTag.getLink().toUpperCase().indexOf("COM")!=-1 ||
linkTag.getLink().toUpperCase().indexOf("ORG")!=-1)
***************
*** 101,105 ****
}
! public static void main(String[] args)
{
System.out.println("Robot Crawler v" + Parser.getVersion ());
--- 101,105 ----
}
! public static void main(String[] args)
{
System.out.println("Robot Crawler v" + Parser.getVersion ());
***************
*** 120,131 ****
System.out.println("If you have any doubts, please join the HTMLParser mailing list (user/developer) from the HTML Parser home page instead of mailing any of the contributors directly. You will be surprised with the quality of open source support. ");
System.exit(-1);
! }
String resourceLocation="";
int crawlDepth = 1;
if (args.length!=0) resourceLocation = args[0];
if (args.length==2) crawlDepth=Integer.valueOf(args[1]).intValue();
!
!
! Robot robot = new Robot(resourceLocation);
System.out.println("Crawling Site "+resourceLocation);
try {
--- 120,131 ----
System.out.println("If you have any doubts, please join the HTMLParser mailing list (user/developer) from the HTML Parser home page instead of mailing any of the contributors directly. You will be surprised with the quality of open source support. ");
System.exit(-1);
! }
String resourceLocation="";
int crawlDepth = 1;
if (args.length!=0) resourceLocation = args[0];
if (args.length==2) crawlDepth=Integer.valueOf(args[1]).intValue();
!
!
! Robot robot = new Robot(resourceLocation);
System.out.println("Crawling Site "+resourceLocation);
try {
Index: StringExtractor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/StringExtractor.java,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** StringExtractor.java 8 Sep 2003 02:26:29 -0000 1.40
--- StringExtractor.java 10 Sep 2003 03:38:19 -0000 1.41
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 39,48 ****
* Construct a StringExtractor to read from the given resource.
* @param resource Either a URL or a file name.
! */
public StringExtractor (String resource)
{
this.resource = resource;
}
!
/**
* Extract the text from a page.
--- 39,48 ----
* Construct a StringExtractor to read from the given resource.
* @param resource Either a URL or a file name.
! */
public StringExtractor (String resource)
{
this.resource = resource;
}
!
/**
* Extract the text from a page.
***************
*** 55,59 ****
{
StringBean sb;
!
sb = new StringBean ();
sb.setLinks (links);
--- 55,59 ----
{
StringBean sb;
!
sb = new StringBean ();
sb.setLinks (links);
***************
*** 72,76 ****
String url;
StringExtractor se;
!
links = false;
url = null;
--- 72,76 ----
String url;
StringExtractor se;
!
links = false;
url = null;
Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/package.html,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** package.html 8 Sep 2003 02:26:29 -0000 1.13
--- package.html 10 Sep 2003 03:38:19 -0000 1.14
***************
*** 17,21 ****
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
--- 17,21 ----
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
***************
*** 24,33 ****
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
--- 24,33 ----
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
***************
*** 36,40 ****
<body bgcolor="white">
Developers and users alike should try out the applications in this package. The code of these applications will give
! a good idea about the capabilities of the HTML Parser, and its intended usage. The binary releases of html parser would
typically contain these applications in runnable form.
--- 36,40 ----
<body bgcolor="white">
Developers and users alike should try out the applications in this package. The code of these applications will give
! a good idea about the capabilities of the HTML Parser, and its intended usage. The binary releases of html parser would
typically contain these applications in runnable form.
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/parserHelper
Modified Files:
AttributeParser.java CompositeTagScannerHelper.java
ParserHelper.java ScriptScannerHelper.java StringParser.java
TagParser.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AttributeParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/AttributeParser.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** AttributeParser.java 8 Sep 2003 02:26:29 -0000 1.38
--- AttributeParser.java 10 Sep 2003 03:38:18 -0000 1.39
***************
*** 233,237 ****
return delim.indexOf(tokenAccumulator)>=0;
}
!
private boolean isCurrentTokenSingleQuote() {
return currentToken.charAt(0)==SINGLE_QUOTE;
--- 233,237 ----
return delim.indexOf(tokenAccumulator)>=0;
}
!
private boolean isCurrentTokenSingleQuote() {
return currentToken.charAt(0)==SINGLE_QUOTE;
Index: CompositeTagScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/CompositeTagScannerHelper.java,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** CompositeTagScannerHelper.java 8 Sep 2003 02:26:29 -0000 1.45
--- CompositeTagScannerHelper.java 10 Sep 2003 03:38:18 -0000 1.46
***************
*** 1,27 ****
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 1,27 ----
// HTMLParser Library v1_4_20030907 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
! //
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
! //
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
! //
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 52,69 ****
private int endingLineNumber;
private boolean balance_quotes;
!
public CompositeTagScannerHelper(
CompositeTagScanner scanner,
! Tag tag,
! String url,
NodeReader reader,
String currLine,
boolean balance_quotes) {
!
this.scanner = scanner;
this.tag = tag;
this.url = url;
this.reader = reader;
! this.currLine = currLine;
this.endTag = null;
this.nodeList = new NodeList();
--- 52,69 ----
private int endingLineNumber;
private boolean balance_quotes;
!
public CompositeTagScannerHelper(
CompositeTagScanner scanner,
! Tag tag,
! String url,
NodeReader reader,
String currLine,
boolean balance_quotes) {
!
this.scanner = scanner;
this.tag = tag;
this.url = url;
this.reader = reader;
! this.currLine = currLine;
this.endTag = null;
this.nodeList = new NodeList();
***************
*** 79,95 ****
scanner.beforeScanningStarts();
Node currentNode = tag;
!
doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound) {
do {
currentNode = reader.readElement(balance_quotes);
! if (currentNode==null) continue;
currLine = reader.getCurrentLine();
! if (currentNode instanceof Tag)
doForceCorrectionCheckOn((Tag)currentNode);
!
doEmptyXmlTagCheckOn(currentNode);
if (!endTagFound)
! doChildAndEndTagCheckOn(currentNode);
}
while (currentNode!=null && !endTagFound);
--- 79,95 ----
scanner.beforeScanningStarts();
Node currentNode = tag;
!
doEmptyXmlTagCheckOn(currentNode);
! if (!endTagFound) {
do {
currentNode = reader.readElement(balance_quotes);
! if (currentNode==null) continue;
currLine = reader.getCurrentLine();
! if (currentNode instanceof Tag)
doForceCorrectionCheckOn((Tag)currentNode);
!
doEmptyXmlTagCheckOn(currentNode);
if (!endTagFound)
! doChildAndEndTagCheckOn(currentNode);
}
while (currentNode!=null && !endTagFound);
***************
*** 98,102 ****
createCorrectionEndTagBefore(reader.getLastReadPosition()+1);
}
!
this.endingLineNumber = reader.getLastLineNumber();
return createTag();
--- 98,102 ----
createCorrectionEndTagBefore(reader.getLastReadPosition()+1);
}
!
this.endingLineNumber = reader.getLastLineNumber();
return createTag();
***************
*** 117,121 ****
String endTagName = tag.getTagName();
int endTagBegin = pos ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
endTag = new EndTag(
new TagData(
--- 117,121 ----
String endTagName = tag.getTagName();
int endTagBegin = pos ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
endTag = new EndTag(
new TagData(
***************
*** 127,135 ****
);
}
!
private void createCorrectionEndTagBefore(Tag possibleEndTagCauser) {
String endTagName = tag.getTagName();
int endTagBegin = possibleEndTagCauser.elementBegin();
! int endTagEnd = endTagBegin + endTagName.length() + 2;
possibleEndTagCauser.setTagBegin(endTagEnd+1);
reader.addNextParsedNode(possibleEndTagCauser);
--- 127,135 ----
);
}
!
private void createCorrectionEndTagBefore(Tag possibleEndTagCauser) {
String endTagName = tag.getTagName();
int endTagBegin = possibleEndTagCauser.elementBegin();
! int endTagEnd = endTagBegin + endTagName.length() + 2;
possibleEndTagCauser.setTagBegin(endTagEnd+1);
reader.addNextParsedNode(possibleEndTagCauser);
***************
*** 145,149 ****
private Tag createTag() throws ParserException {
! CompositeTag newTag =
(CompositeTag)
scanner.createTag(
--- 145,149 ----
private Tag createTag() throws ParserException {
! CompositeTag newTag =
(CompositeTag)
scanner.createTag(
***************
*** 191,196 ****
if (isXmlEndTag(tag)) {
endTag = possibleEndTag;
! endTagFound = true;
! }
}
}
--- 191,196 ----
if (isXmlEndTag(tag)) {
endTag = possibleEndTag;
! endTagFound = true;
! }
}
}
***************
*** 200,210 ****
createCorrectionEndTagBefore(possibleEndTagCauser);
! endTagFound = true;
}
}
private boolean isEndTagMissing(Tag possibleEndTag) {
! return
! scanner.isTagToBeEndedFor(possibleEndTag) ||
isSelfChildTagRecievedIncorrectly(possibleEndTag);
}
--- 200,210 ----
createCorrectionEndTagBefore(possibleEndTagCauser);
! endTagFound = true;
}
}
private boolean isEndTagMissing(Tag possibleEndTag) {
! return
! scanner.isTagToBeEndedFor(possibleEndTag) ||
isSelfChildTagRecievedIncorrectly(possibleEndTag);
}
***************
*** 213,221 ****
return (
!(possibleEndTag instanceof EndTag) &&
! !scanner.isAllowSelfChildren() &&
possibleEndTag.getTagName().equals(tag.getTagName())
);
}
!
public boolean isXmlEndTag(Tag tag) {
String tagText = tag.getText();
--- 213,221 ----
return (
!(possibleEndTag instanceof EndTag) &&
! !scanner.isAllowSelfChildren() &&
possibleEndTag.getTagName().equals(tag.getTagName())
);
}
!
public boolean isXmlEndTag(Tag tag) {
String tagText = tag.getText();
Index: ParserHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ParserHelper.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** ParserHelper.java 8 Sep 2003 02:26:29 -0000 1.15
--- ParserHelper.java 10 Sep 2003 03:38:18 -0000 1.16
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 57,61 ****
{
URLConnection ret;
!
try
{
--- 57,61 ----
{
URLConnection ret;
!
try
{
***************
*** 70,74 ****
throw ex;
}
!
return (ret);
}
--- 70,74 ----
throw ex;
}
!
return (ret);
}
***************
*** 93,97 ****
StringBuffer buffer;
URLConnection ret;
!
try
{
--- 93,97 ----
StringBuffer buffer;
URLConnection ret;
!
try
{
***************
*** 132,136 ****
}
}
!
return (ret);
}
--- 132,136 ----
}
}
!
return (ret);
}
***************
*** 147,151 ****
{
String ret;
!
try
{
--- 147,151 ----
{
String ret;
!
try
{
***************
*** 153,157 ****
java.lang.reflect.Method method;
Object object;
!
cls = Class.forName ("java.nio.charset.Charset");
method = cls.getMethod ("forName", new Class[] { String.class });
--- 153,157 ----
java.lang.reflect.Method method;
Object object;
!
cls = Class.forName ("java.nio.charset.Charset");
method = cls.getMethod ("forName", new Class[] { String.class });
***************
*** 183,187 ****
ret = _default;
}
!
return (ret);
}
--- 183,187 ----
ret = _default;
}
!
return (ret);
}
Index: ScriptScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ScriptScannerHelper.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** ScriptScannerHelper.java 8 Sep 2003 02:26:29 -0000 1.10
--- ScriptScannerHelper.java 10 Sep 2003 03:38:18 -0000 1.11
***************
*** 11,15 ****
//MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
//Lesser General Public License for more details.
! //
//You should have received a copy of the GNU Lesser General Public
//License along with this library; if not, write to the Free Software
--- 11,15 ----
//MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
//Lesser General Public License for more details.
! //
//You should have received a copy of the GNU Lesser General Public
//License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
//For any questions or suggestions, you can write to me at :
//Email :so...@in...
! //
! //Postal Address :
//Somik Raha
//Extreme Programmer & Coach
//Industrial Logic, Inc.
! //2583 Cedar Street, Berkeley,
//CA 94708, USA
//Website : http://www.industriallogic.com
--- 18,27 ----
//For any questions or suggestions, you can write to me at :
//Email :so...@in...
! //
! //Postal Address :
//Somik Raha
//Extreme Programmer & Coach
//Industrial Logic, Inc.
! //2583 Cedar Street, Berkeley,
//CA 94708, USA
//Website : http://www.industriallogic.com
***************
*** 50,54 ****
private String url;
private String currLine;
!
public ScriptScannerHelper(Tag tag, String url, NodeReader nodeReader, String currLine, ScriptScanner scriptScanner) {
this.reader = nodeReader;
--- 50,54 ----
private String url;
private String currLine;
!
public ScriptScannerHelper(Tag tag, String url, NodeReader nodeReader, String currLine, ScriptScanner scriptScanner) {
this.reader = nodeReader;
***************
*** 68,72 ****
return createScriptTagUsing(url, currLine, startLine);
}
!
private Tag createScriptTagUsing(String url, String currLine, int startLine) {
return scriptScanner.createTag(
--- 68,72 ----
return createScriptTagUsing(url, currLine, startLine);
}
!
private Tag createScriptTagUsing(String url, String currLine, int startLine) {
return scriptScanner.createTag(
***************
*** 102,106 ****
String endTagName = tag.getTagName();
int endTagBegin = reader.getLastReadPosition()+1 ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
endTag = new EndTag(
new TagData(
--- 102,106 ----
String endTagName = tag.getTagName();
int endTagBegin = reader.getLastReadPosition()+1 ;
! int endTagEnd = endTagBegin + endTagName.length() + 2;
endTag = new EndTag(
new TagData(
***************
*** 121,125 ****
scriptContents = new StringBuffer();
endTagFound = false;
!
endTag = null;
line = currLine;
--- 121,125 ----
scriptContents = new StringBuffer();
endTagFound = false;
!
endTag = null;
line = currLine;
***************
*** 132,136 ****
startingPos = 0;
}
! if (sameLine)
sameLine = false;
}
--- 132,136 ----
startingPos = 0;
}
! if (sameLine)
sameLine = false;
}
***************
*** 141,145 ****
endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(),startingPos);
findStartingAndEndingLocations(line);
!
if (endTagLoc!=-1) {
extractEndTagFrom(line);
--- 141,145 ----
endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(),startingPos);
findStartingAndEndingLocations(line);
!
if (endTagLoc!=-1) {
extractEndTagFrom(line);
***************
*** 150,154 ****
private void continueParsing(String line) {
! if (sameLine)
scriptContents.append(
line.substring(
--- 150,154 ----
private void continueParsing(String line) {
! if (sameLine)
scriptContents.append(
line.substring(
***************
*** 165,169 ****
endTagFound = true;
endTag = (EndTag)EndTag.find(line,endTagLoc);
! if (sameLine)
scriptContents.append(
getCodeBetweenStartAndEndTags(
--- 165,169 ----
endTagFound = true;
endTag = (EndTag)EndTag.find(line,endTagLoc);
! if (sameLine)
scriptContents.append(
getCodeBetweenStartAndEndTags(
***************
*** 176,180 ****
scriptContents.append(line.substring(0,endTagLoc));
}
!
reader.setPosInLine(endTag.elementEnd());
}
--- 176,180 ----
scriptContents.append(line.substring(0,endTagLoc));
}
!
reader.setPosInLine(endTag.elementEnd());
}
***************
*** 183,187 ****
while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
startingPos = endTagLoc+scriptScanner.getEndTag().length();
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(), startingPos);
}
}
--- 183,187 ----
while (endTagLoc>0 && isThisEndTagLocationFalseMatch(line, endTagLoc)) {
startingPos = endTagLoc+scriptScanner.getEndTag().length();
! endTagLoc = line.toUpperCase().indexOf(scriptScanner.getEndTag(), startingPos);
}
}
***************
*** 192,196 ****
int endTagLoc) throws ParserException {
try {
!
return line.substring(
startTag.elementEnd()+1,
--- 192,196 ----
int endTagLoc) throws ParserException {
try {
!
return line.substring(
startTag.elementEnd()+1,
***************
*** 208,213 ****
private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
if (endTagLoc+scriptScanner.getEndTag().length() > line.length()-1) return false;
! char charAfterSuspectedEndTag =
! line.charAt(endTagLoc+scriptScanner.getEndTag().length());
return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
}
--- 208,213 ----
private boolean isThisEndTagLocationFalseMatch(String line, int endTagLoc) {
if (endTagLoc+scriptScanner.getEndTag().length() > line.length()-1) return false;
! char charAfterSuspectedEndTag =
! line.charAt(endTagLoc+scriptScanner.getEndTag().length());
return charAfterSuspectedEndTag=='"' || charAfterSuspectedEndTag=='\'';
}
Index: StringParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/StringParser.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** StringParser.java 8 Sep 2003 02:26:29 -0000 1.38
--- StringParser.java 10 Sep 2003 03:38:18 -0000 1.39
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 34,40 ****
public class StringParser {
! private final static int BEFORE_PARSE_BEGINS_STATE=0;
private final static int PARSE_HAS_BEGUN_STATE=1;
! private final static int PARSE_COMPLETED_STATE=2;
private final static int PARSE_IGNORE_STATE=3;
--- 34,40 ----
public class StringParser {
! private final static int BEFORE_PARSE_BEGINS_STATE=0;
private final static int PARSE_HAS_BEGUN_STATE=1;
! private final static int PARSE_COMPLETED_STATE=2;
private final static int PARSE_IGNORE_STATE=3;
***************
*** 50,56 ****
char ch;
boolean ret;
!
ret = false;
!
if (pos + 2 <= line.length ())
if ('<' == line.charAt (pos))
--- 50,56 ----
char ch;
boolean ret;
!
ret = false;
!
if (pos + 2 <= line.length ())
if ('<' == line.charAt (pos))
***************
*** 72,76 ****
* @param balance_quotes If <code>true</code> enter ignoring state on
* encountering quotes.
! */
public Node find(NodeReader reader,String input,int position, boolean balance_quotes)
{
--- 72,76 ----
* @param balance_quotes If <code>true</code> enter ignoring state on
* encountering quotes.
! */
public Node find(NodeReader reader,String input,int position, boolean balance_quotes)
{
***************
*** 105,109 ****
state = PARSE_IGNORE_STATE;
}
! }
if (state==BEFORE_PARSE_BEGINS_STATE)
{
--- 105,109 ----
state = PARSE_IGNORE_STATE;
}
! }
if (state==BEFORE_PARSE_BEGINS_STATE)
{
***************
*** 113,117 ****
{
textBuffer.append(input.charAt(i));
! }
// Patch by Cedric Rosa
if (state==BEFORE_PARSE_BEGINS_STATE && i==inputLen-1)
--- 113,117 ----
{
textBuffer.append(input.charAt(i));
! }
// Patch by Cedric Rosa
if (state==BEFORE_PARSE_BEGINS_STATE && i==inputLen-1)
***************
*** 125,133 ****
}
while (input!=null && input.length()==0);
!
if (input==null) {
textEnd=i;
state =PARSE_COMPLETED_STATE;
!
} else {
textBuffer.append(Parser.getLineSeparator());
--- 125,133 ----
}
while (input!=null && input.length()==0);
!
if (input==null) {
textEnd=i;
state =PARSE_COMPLETED_STATE;
!
} else {
textBuffer.append(Parser.getLineSeparator());
Index: TagParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/TagParser.java,v
retrieving revision 1.41
retrieving revision 1.42
diff -C2 -d -r1.41 -r1.42
*** TagParser.java 8 Sep 2003 02:26:29 -0000 1.41
--- TagParser.java 10 Sep 2003 03:38:18 -0000 1.42
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 42,51 ****
public final static int TAG_FINISHED_PARSING_STATE=1<<3;
public final static int TAG_ILLEGAL_STATE=1<<4;
! public final static int TAG_IGNORE_DATA_STATE=1<<5;
public final static int TAG_IGNORE_BEGIN_TAG_STATE=1<<6;
public final static int TAG_IGNORE_CHAR_SINGLE_QUOTE=1<<7;
!
public final static String ENCOUNTERED_QUERY_MESSAGE = "TagParser : Encountered > after a query. Accepting without correction and continuing parsing";
!
private ParserFeedback feedback;
--- 42,51 ----
public final static int TAG_FINISHED_PARSING_STATE=1<<3;
public final static int TAG_ILLEGAL_STATE=1<<4;
! public final static int TAG_IGNORE_DATA_STATE=1<<5;
public final static int TAG_IGNORE_BEGIN_TAG_STATE=1<<6;
public final static int TAG_IGNORE_CHAR_SINGLE_QUOTE=1<<7;
!
public final static String ENCOUNTERED_QUERY_MESSAGE = "TagParser : Encountered > after a query. Accepting without correction and continuing parsing";
!
private ParserFeedback feedback;
***************
*** 62,67 ****
Bool encounteredQuery = new Bool(false);
! while (i<tag.getTagLine().length() &&
! state!=TAG_FINISHED_PARSING_STATE &&
state!=TAG_ILLEGAL_STATE
)
--- 62,67 ----
Bool encounteredQuery = new Bool(false);
! while (i<tag.getTagLine().length() &&
! state!=TAG_FINISHED_PARSING_STATE &&
state!=TAG_ILLEGAL_STATE
)
***************
*** 106,111 ****
private int checkBeginParsingState(int i, int state, char ch, Tag tag) {
! if (ch=='<' &&
! (state==TAG_BEFORE_PARSING_STATE ||
state==TAG_ILLEGAL_STATE))
{
--- 106,111 ----
private int checkBeginParsingState(int i, int state, char ch, Tag tag) {
! if (ch=='<' &&
! (state==TAG_BEFORE_PARSING_STATE ||
state==TAG_ILLEGAL_STATE))
{
***************
*** 123,127 ****
return openTagPos > closeTagPos || (openTagPos ==-1 && closeTagPos!=-1);
}
!
private int checkFinishedState(Bool encounteredQuery, int i, int state, char ch, Tag tag, int pos) {
if (ch=='>')
--- 123,127 ----
return openTagPos > closeTagPos || (openTagPos ==-1 && closeTagPos!=-1);
}
!
private int checkFinishedState(Bool encounteredQuery, int i, int state, char ch, Tag tag, int pos) {
if (ch=='>')
***************
*** 142,146 ****
// or it is a mistake in the html, in which case we need to correct it *sigh*
if (isWellFormedTag(tag,pos)) return state;
!
state = TAG_FINISHED_PARSING_STATE;
tag.setTagEnd(i);
--- 142,146 ----
// or it is a mistake in the html, in which case we need to correct it *sigh*
if (isWellFormedTag(tag,pos)) return state;
!
state = TAG_FINISHED_PARSING_STATE;
tag.setTagEnd(i);
***************
*** 149,153 ****
// Remove all inverted commas.
correctTag(tag);
!
StringBuffer msg = new StringBuffer();
msg.append("HTMLTagParser : Encountered > inside inverted commas in line \n");
--- 149,153 ----
// Remove all inverted commas.
correctTag(tag);
!
StringBuffer msg = new StringBuffer();
msg.append("HTMLTagParser : Encountered > inside inverted commas in line \n");
***************
*** 162,167 ****
}
} else
! if (ch=='<' &&
! state==TAG_BEGIN_PARSING_STATE &&
tag.getText().charAt(0)!='%'
) {
--- 162,167 ----
}
} else
! if (ch=='<' &&
! state==TAG_BEGIN_PARSING_STATE &&
tag.getText().charAt(0)!='%'
) {
***************
*** 173,180 ****
private void checkIfAppendable(Bool encounteredQuery,int state, char ch, Tag tag) {
! if (state==TAG_IGNORE_DATA_STATE ||
! state==TAG_BEGIN_PARSING_STATE ||
state==TAG_IGNORE_BEGIN_TAG_STATE) {
! if (ch=='?')
encounteredQuery.setBoolean(true);
tag.append(ch);
--- 173,180 ----
private void checkIfAppendable(Bool encounteredQuery,int state, char ch, Tag tag) {
! if (state==TAG_IGNORE_DATA_STATE ||
! state==TAG_BEGIN_PARSING_STATE ||
state==TAG_IGNORE_BEGIN_TAG_STATE) {
! if (ch=='?')
encounteredQuery.setBoolean(true);
tag.append(ch);
***************
*** 183,188 ****
private int checkIllegalState(int i, int state, char ch, Tag tag) {
! if (ch=='/' && i>0 && tag.getTagLine().charAt(i-1)=='<' &&
! state!=TAG_IGNORE_DATA_STATE &&
state!=TAG_IGNORE_BEGIN_TAG_STATE)
{
--- 183,188 ----
private int checkIllegalState(int i, int state, char ch, Tag tag) {
! if (ch=='/' && i>0 && tag.getTagLine().charAt(i-1)=='<' &&
! state!=TAG_IGNORE_DATA_STATE &&
state!=TAG_IGNORE_BEGIN_TAG_STATE)
{
***************
*** 192,196 ****
return state;
}
!
public void correctTag(Tag tag) {
String tempText = tag.getText();
--- 192,196 ----
return state;
}
!
public void correctTag(Tag tag) {
String tempText = tag.getText();
***************
*** 205,209 ****
StringBuffer result = insertInvertedCommasCorrectly(absorbedText);
tag.setText(result.toString());
! }
public StringBuffer insertInvertedCommasCorrectly(StringBuffer absorbedText) {
StringBuffer result = new StringBuffer();
--- 205,209 ----
StringBuffer result = insertInvertedCommasCorrectly(absorbedText);
tag.setText(result.toString());
! }
public StringBuffer insertInvertedCommasCorrectly(StringBuffer absorbedText) {
StringBuffer result = new StringBuffer();
***************
*** 225,229 ****
}
return result;
! }
public static String pruneSpaces(String token) {
int firstSpace;
--- 225,229 ----
}
return result;
! }
public static String pruneSpaces(String token) {
int firstSpace;
***************
*** 238,244 ****
token = token.substring(0,token.length()-1);
lastSpace = token.lastIndexOf(' ');
! }
return token;
! }
/**
--- 238,244 ----
token = token.substring(0,token.length()-1);
lastSpace = token.lastIndexOf(' ');
! }
return token;
! }
/**
***************
*** 264,276 ****
return (state);
! }
!
public int incrementCounter(int i, NodeReader reader, int state, Tag tag) {
String nextLine = null;
if (
! (state==TAG_BEGIN_PARSING_STATE ||
state==TAG_IGNORE_DATA_STATE ||
state==TAG_IGNORE_BEGIN_TAG_STATE
! ) &&
i==tag.getTagLine().length()-1)
{
--- 264,276 ----
return (state);
! }
!
public int incrementCounter(int i, NodeReader reader, int state, Tag tag) {
String nextLine = null;
if (
! (state==TAG_BEGIN_PARSING_STATE ||
state==TAG_IGNORE_DATA_STATE ||
state==TAG_IGNORE_BEGIN_TAG_STATE
! ) &&
i==tag.getTagLine().length()-1)
{
***************
*** 291,295 ****
tag.append(Parser.getLineSeparator());
}
!
// Ensure blank lines are included in tag's 'tagLines'
while (--numLinesAdvanced > 0)
--- 291,295 ----
tag.append(Parser.getLineSeparator());
}
!
// Ensure blank lines are included in tag's 'tagLines'
while (--numLinesAdvanced > 0)
***************
*** 299,317 ****
tag.setTagLine(nextLine);
i=-1;
! }
return ++i;
! }
// Class provided for thread safety in TagParser
class Bool {
private boolean boolValue;
!
Bool(boolean boolValue) {
! this.boolValue = boolValue;
}
!
public void setBoolean(boolean boolValue) {
this.boolValue = boolValue;
}
!
public boolean getBoolean() {
return boolValue;
--- 299,317 ----
tag.setTagLine(nextLine);
i=-1;
! }
return ++i;
! }
// Class provided for thread safety in TagParser
class Bool {
private boolean boolValue;
!
Bool(boolean boolValue) {
! this.boolValue = boolValue;
}
!
public void setBoolean(boolean boolValue) {
this.boolValue = boolValue;
}
!
public boolean getBoolean() {
return boolValue;
|
|
From: <der...@us...> - 2003-09-10 03:38:59
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser
Modified Files:
AbstractNode.java Node.java NodeReader.java Parser.java
RemarkNode.java RemarkNodeParser.java StringNode.java
StringNodeFactory.java package.html
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AbstractNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/AbstractNode.java,v
retrieving revision 1.12
retrieving revision 1.13
diff -C2 -d -r1.12 -r1.13
*** AbstractNode.java 8 Sep 2003 02:26:28 -0000 1.12
--- AbstractNode.java 10 Sep 2003 03:38:17 -0000 1.13
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 37,41 ****
*/
public abstract class AbstractNode implements Node, Serializable {
! /**
* The beginning position of the tag in the line
*/
--- 37,41 ----
*/
public abstract class AbstractNode implements Node, Serializable {
! /**
* The beginning position of the tag in the line
*/
***************
*** 55,59 ****
* The children of this node.
*/
! protected NodeList children;
/**
--- 55,59 ----
* The children of this node.
*/
! protected NodeList children;
/**
***************
*** 85,89 ****
/**
* This method will make it easier when using html parser to reproduce html pages (with or without modifications)
! * Applications reproducing html can use this method on nodes which are to be used or transferred as they were
* recieved, with the original html
*/
--- 85,89 ----
/**
* This method will make it easier when using html parser to reproduce html pages (with or without modifications)
! * Applications reproducing html can use this method on nodes which are to be used or transferred as they were
* recieved, with the original html
*/
***************
*** 101,105 ****
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
--- 101,105 ----
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
***************
*** 107,120 ****
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
! * String filter = LinkTag.LINK_TAG_FILTER;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
! * node.collectInto (collectionVector, filter);
* }
* </pre>
--- 107,120 ----
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
! * String filter = LinkTag.LINK_TAG_FILTER;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
! * node.collectInto (collectionVector, filter);
* }
* </pre>
***************
*** 122,132 ****
* deep the links are embedded. This of course implies that tags must
* fulfill their responsibilities toward honouring certain filters.
! *
! * <B>Important:</B> In order to keep performance optimal, <B>do not create</B> you own filter strings, as
* the internal matching occurs with the pre-existing filter string object (in the relevant class). i.e. do not
! * make calls like :
* <I>collectInto(collectionList,"-l")</I>, instead, make calls only like :
* <I>collectInto(collectionList,LinkTag.LINK_TAG_FILTER)</I>.<P/>
! *
* To find out if your desired tag has filtering support, check the API of the tag.
*/
--- 122,132 ----
* deep the links are embedded. This of course implies that tags must
* fulfill their responsibilities toward honouring certain filters.
! *
! * <B>Important:</B> In order to keep performance optimal, <B>do not create</B> you own filter strings, as
* the internal matching occurs with the pre-existing filter string object (in the relevant class). i.e. do not
! * make calls like :
* <I>collectInto(collectionList,"-l")</I>, instead, make calls only like :
* <I>collectInto(collectionList,LinkTag.LINK_TAG_FILTER)</I>.<P/>
! *
* To find out if your desired tag has filtering support, check the API of the tag.
*/
***************
*** 136,140 ****
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
--- 136,140 ----
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
***************
*** 142,151 ****
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
--- 142,151 ----
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
***************
*** 154,158 ****
* </pre>
* Thus, collectionList will hold all the link nodes, irrespective of how
! * deep the links are embedded.
*/
public void collectInto(NodeList collectionList, Class nodeType) {
--- 154,158 ----
* </pre>
* Thus, collectionList will hold all the link nodes, irrespective of how
! * deep the links are embedded.
*/
public void collectInto(NodeList collectionList, Class nodeType) {
***************
*** 184,188 ****
return toHtml();
}
!
/**
* Get the parent of this node.
--- 184,188 ----
return toHtml();
}
!
/**
* Get the parent of this node.
***************
*** 205,209 ****
parent = node;
}
!
/**
* Get the children of this node.
--- 205,209 ----
parent = node;
}
!
/**
* Get the children of this node.
***************
*** 230,234 ****
return null;
}
!
/**
* Sets the string contents of the node.
--- 230,234 ----
return null;
}
!
/**
* Sets the string contents of the node.
Index: Node.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Node.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** Node.java 8 Sep 2003 02:26:28 -0000 1.38
--- Node.java 10 Sep 2003 03:38:17 -0000 1.39
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 49,53 ****
/**
* This method will make it easier when using html parser to reproduce html pages (with or without modifications)
! * Applications reproducing html can use this method on nodes which are to be used or transferred as they were
* recieved, with the original html
*/
--- 49,53 ----
/**
* This method will make it easier when using html parser to reproduce html pages (with or without modifications)
! * Applications reproducing html can use this method on nodes which are to be used or transferred as they were
* recieved, with the original html
*/
***************
*** 63,67 ****
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
--- 63,67 ----
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
***************
*** 69,82 ****
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
! * String filter = LinkTag.LINK_TAG_FILTER;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
! * node.collectInto (collectionVector, filter);
* }
* </pre>
--- 69,82 ----
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
! * String filter = LinkTag.LINK_TAG_FILTER;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
! * node.collectInto (collectionVector, filter);
* }
* </pre>
***************
*** 84,94 ****
* deep the links are embedded. This of course implies that tags must
* fulfill their responsibilities toward honouring certain filters.
! *
! * <B>Important:</B> In order to keep performance optimal, <B>do not create</B> you own filter strings, as
* the internal matching occurs with the pre-existing filter string object (in the relevant class). i.e. do not
! * make calls like :
* <I>collectInto(collectionList,"-l")</I>, instead, make calls only like :
* <I>collectInto(collectionList,LinkTag.LINK_TAG_FILTER)</I>.<P/>
! *
* To find out if your desired tag has filtering support, check the API of the tag.
*/
--- 84,94 ----
* deep the links are embedded. This of course implies that tags must
* fulfill their responsibilities toward honouring certain filters.
! *
! * <B>Important:</B> In order to keep performance optimal, <B>do not create</B> you own filter strings, as
* the internal matching occurs with the pre-existing filter string object (in the relevant class). i.e. do not
! * make calls like :
* <I>collectInto(collectionList,"-l")</I>, instead, make calls only like :
* <I>collectInto(collectionList,LinkTag.LINK_TAG_FILTER)</I>.<P/>
! *
* To find out if your desired tag has filtering support, check the API of the tag.
*/
***************
*** 97,101 ****
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
--- 97,101 ----
* Collect this node and its child nodes (if-applicable) into the collection parameter, provided the node
* satisfies the filtering criteria. <P/>
! *
* This mechanism allows powerful filtering code to be written very easily, without bothering about collection
* of embedded tags separately. e.g. when we try to get all the links on a page, it is not possible to get it
***************
*** 103,112 ****
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
--- 103,112 ----
* out by checking if the current node is a form tag, and going through its contents. However, this ties us down
* to specific tags, and is not a very clean approach. <P/>
! *
! * Using collectInto(), programs get a lot shorter. Now, the code to extract all links from a page would look
* like :
* <pre>
! * NodeList collectionList = new NodeList();
! * Node node;
* for (NodeIterator e = parser.elements(); e.hasMoreNodes();) {
* node = e.nextNode();
***************
*** 115,119 ****
* </pre>
* Thus, collectionList will hold all the link nodes, irrespective of how
! * deep the links are embedded.
*/
public abstract void collectInto(NodeList collectionList, Class nodeType);
--- 115,119 ----
* </pre>
* Thus, collectionList will hold all the link nodes, irrespective of how
! * deep the links are embedded.
*/
public abstract void collectInto(NodeList collectionList, Class nodeType);
***************
*** 126,130 ****
*/
public abstract int elementEnd();
!
public abstract void accept(Object visitor);
--- 126,130 ----
*/
public abstract int elementEnd();
!
public abstract void accept(Object visitor);
***************
*** 159,168 ****
* Returns the text of the string line
*/
! public String getText();
!
/**
* Sets the string contents of the node.
* @param text The new text for the node.
*/
! public void setText(String text);
}
--- 159,168 ----
* Returns the text of the string line
*/
! public String getText();
!
/**
* Sets the string contents of the node.
* @param text The new text for the node.
*/
! public void setText(String text);
}
Index: NodeReader.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/NodeReader.java,v
retrieving revision 1.42
retrieving revision 1.43
diff -C2 -d -r1.42 -r1.43
*** NodeReader.java 8 Sep 2003 02:26:28 -0000 1.42
--- NodeReader.java 10 Sep 2003 03:38:17 -0000 1.43
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 72,76 ****
super(in, len);
this.url = url;
! this.parser = null;
this.lineCount = 1;
}
--- 72,76 ----
super(in, len);
this.url = url;
! this.parser = null;
this.lineCount = 1;
}
***************
*** 95,99 ****
this(in, 8192, url);
}
!
/**
* Get the url for this reader.
--- 95,99 ----
this(in, 8192, url);
}
!
/**
* Get the url for this reader.
***************
*** 106,110 ****
/**
! * This method is intended to be called only by scanners, when a situation of dirty html has arisen,
* and action has been taken to correct the parsed tags. For e.g. if we have html of the form :
* <pre>
--- 106,110 ----
/**
! * This method is intended to be called only by scanners, when a situation of dirty html has arisen,
* and action has been taken to correct the parsed tags. For e.g. if we have html of the form :
* <pre>
***************
*** 113,117 ****
* Now to salvage the first link, we'd probably like to insert an end tag somewhere (typically before the
* second begin link tag). So that the parsing continues uninterrupted, we will need to change the existing
! * line being parsed, to contain the end tag in it.
*/
public void changeLine(String line) {
--- 113,117 ----
* Now to salvage the first link, we'd probably like to insert an end tag somewhere (typically before the
* second begin link tag). So that the parsing continues uninterrupted, we will need to change the existing
! * line being parsed, to contain the end tag in it.
*/
public void changeLine(String line) {
***************
*** 124,128 ****
* Get the last line number that the reader has read
* @return int last line number read by the reader
! */
public int getLastLineNumber() {
return lineCount-1;
--- 124,128 ----
* Get the last line number that the reader has read
* @return int last line number read by the reader
! */
public int getLastLineNumber() {
return lineCount-1;
***************
*** 186,192 ****
char ch;
boolean ret;
!
ret = false;
!
if (pos + 2 <= line.length ())
if ('<' == line.charAt (pos))
--- 186,192 ----
char ch;
boolean ret;
!
ret = false;
!
if (pos + 2 <= line.length ())
if ('<' == line.charAt (pos))
***************
*** 223,227 ****
node = nextParsedNode.elementAt(0);
nextParsedNode.remove(0);
! return node;
}
if (readNextLine()) {
--- 223,227 ----
node = nextParsedNode.elementAt(0);
nextParsedNode.remove(0);
! return node;
}
if (readNextLine()) {
***************
*** 231,235 ****
}
while (line!=null && line.length()==0);
!
}
else if (dontReadNextLine) {
--- 231,235 ----
}
while (line!=null && line.length()==0);
!
}
else if (dontReadNextLine) {
***************
*** 239,243 ****
if (line==null)
return null;
!
if (beginTag (line, posInLine))
{
--- 239,243 ----
if (line==null)
return null;
!
if (beginTag (line, posInLine))
{
***************
*** 255,264 ****
}
catch (Exception e)
! {
StringBuffer msgBuffer = new StringBuffer();
msgBuffer.append(DECIPHER_ERROR+"\n" +
" Tag being processed : "+tag.getTagName()+"\n" +
" Current Tag Line : "+tag.getTagLine()
! );
appendLineDetails(msgBuffer);
ParserException ex = new ParserException(msgBuffer.toString(),e);
--- 255,264 ----
}
catch (Exception e)
! {
StringBuffer msgBuffer = new StringBuffer();
msgBuffer.append(DECIPHER_ERROR+"\n" +
" Tag being processed : "+tag.getTagName()+"\n" +
" Current Tag Line : "+tag.getTagLine()
! );
appendLineDetails(msgBuffer);
ParserException ex = new ParserException(msgBuffer.toString(),e);
***************
*** 277,281 ****
if (node!=null) return node;
}
!
return null;
}
--- 277,281 ----
if (node!=null) return node;
}
!
return null;
}
***************
*** 292,296 ****
ParserException ex = new ParserException(msgBuffer.toString(),e);
parser.getFeedback().error(msgBuffer.toString(),ex);
! throw ex;
}
}
--- 292,296 ----
ParserException ex = new ParserException(msgBuffer.toString(),e);
parser.getFeedback().error(msgBuffer.toString(),ex);
! throw ex;
}
}
***************
*** 330,334 ****
this.previousOpenScanner = previousOpenScanner;
}
!
/**
* @param lineSeparator New Line separator to be used
--- 330,334 ----
this.previousOpenScanner = previousOpenScanner;
}
!
/**
* @param lineSeparator New Line separator to be used
***************
*** 336,346 ****
public static void setLineSeparator(String lineSeparator)
{
! Parser.setLineSeparator(lineSeparator);
}
!
/**
* Gets the line seperator that is being used
* @return String
! */
public static String getLineSeparator()
{
--- 336,346 ----
public static void setLineSeparator(String lineSeparator)
{
! Parser.setLineSeparator(lineSeparator);
}
!
/**
* Gets the line seperator that is being used
* @return String
! */
public static String getLineSeparator()
{
***************
*** 405,411 ****
*/
public void addNextParsedNode(Node nextParsedNode) {
! this.nextParsedNode.prepend(nextParsedNode);
}
!
public boolean isDontReadNextLine() {
return dontReadNextLine;
--- 405,411 ----
*/
public void addNextParsedNode(Node nextParsedNode) {
! this.nextParsedNode.prepend(nextParsedNode);
}
!
public boolean isDontReadNextLine() {
return dontReadNextLine;
Index: Parser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Parser.java,v
retrieving revision 1.59
retrieving revision 1.60
diff -C2 -d -r1.59 -r1.60
*** Parser.java 8 Sep 2003 02:26:28 -0000 1.59
--- Parser.java 10 Sep 2003 03:38:17 -0000 1.60
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 78,82 ****
/**
! * This is the class that the user will use, either to get an iterator into
* the html page or to directly parse the page and print the results
* <BR>
--- 78,82 ----
/**
! * This is the class that the user will use, either to get an iterator into
* the html page or to directly parse the page and print the results
* <BR>
***************
*** 84,93 ****
* [1] Create a parser object - passing the URL and a feedback object to the parser<BR>
* [2] Register the common scanners. See {@link #registerScanners()} <BR>
! * You wouldnt do this if you want to configure a custom lightweight parser. In that case,
* you would add the scanners of your choice using {@link #addScanner(TagScanner)}<BR>
* [3] Enumerate through the elements from the parser object <BR>
! * It is important to note that the parsing occurs when you enumerate, ON DEMAND. This is a thread-safe way,
* and you only get the control back after a particular element is parsed and returned.
! *
* <BR>
* Below is some sample code to parse Yahoo.com and print all the tags.
--- 84,93 ----
* [1] Create a parser object - passing the URL and a feedback object to the parser<BR>
* [2] Register the common scanners. See {@link #registerScanners()} <BR>
! * You wouldnt do this if you want to configure a custom lightweight parser. In that case,
* you would add the scanners of your choice using {@link #addScanner(TagScanner)}<BR>
* [3] Enumerate through the elements from the parser object <BR>
! * It is important to note that the parsing occurs when you enumerate, ON DEMAND. This is a thread-safe way,
* and you only get the control back after a particular element is parsed and returned.
! *
* <BR>
* Below is some sample code to parse Yahoo.com and print all the tags.
***************
*** 95,99 ****
* Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback());
* // In this example, we are registering all the common scanners
! * parser.registerScanners();
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
* Node node = i.nextNode();
--- 95,99 ----
* Parser parser = new Parser("http://www.yahoo.com",new DefaultHTMLParserFeedback());
* // In this example, we are registering all the common scanners
! * parser.registerScanners();
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
* Node node = i.nextNode();
***************
*** 109,121 ****
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
* Node node = i.nextNode();
! * if (node instanceof StringNode) {
* StringNode stringNode =
! * (StringNode)node;
! * System.out.println(stringNode.getText());
! * }
* }
* </pre>
* The above snippet will print out only the text contents in the html document.<br>
! * Here's another snippet that will only print out the link urls in a document.
* This is an example of adding a link scanner.
* <pre>
--- 109,121 ----
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
* Node node = i.nextNode();
! * if (node instanceof StringNode) {
* StringNode stringNode =
! * (StringNode)node;
! * System.out.println(stringNode.getText());
! * }
* }
* </pre>
* The above snippet will print out only the text contents in the html document.<br>
! * Here's another snippet that will only print out the link urls in a document.
* This is an example of adding a link scanner.
* <pre>
***************
*** 123,134 ****
* parser.addScanner(new LinkScanner("-l"));
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
! * Node node = i.nextNode();
* if (node instanceof LinkTag) {
! * LinkTag linkTag = (LinkTag)node;
! * System.out.println(linkTag.getLink());
! * }
* }
* </pre>
! * @see Parser#elements()
*/
public class Parser
--- 123,134 ----
* parser.addScanner(new LinkScanner("-l"));
* for (NodeIterator i = parser.elements();i.hasMoreNodes();) {
! * Node node = i.nextNode();
* if (node instanceof LinkTag) {
! * LinkTag linkTag = (LinkTag)node;
! * System.out.println(linkTag.getLink());
! * }
* }
* </pre>
! * @see Parser#elements()
*/
public class Parser
***************
*** 163,167 ****
* The display version.
*/
! public final static String
VERSION_STRING = "" + VERSION_NUMBER + " (" + VERSION_TYPE + " " + VERSION_DATE + ")"
;
--- 163,167 ----
* The display version.
*/
! public final static String
VERSION_STRING = "" + VERSION_NUMBER + " (" + VERSION_TYPE + " " + VERSION_DATE + ")"
;
***************
*** 184,188 ****
/**
! * This object is used by the StringParser to create new StringNodes at runtime, based on
* use configurations of the factory
*/
--- 184,188 ----
/**
! * This object is used by the StringParser to create new StringNodes at runtime, based on
* use configurations of the factory
*/
***************
*** 193,203 ****
*/
protected ParserFeedback feedback;
!
/**
* The URL or filename to be parsed.
*/
protected String resourceLocn;
!
! /**
* The html reader associated with this parser.
*/
--- 193,203 ----
*/
protected ParserFeedback feedback;
!
/**
* The URL or filename to be parsed.
*/
protected String resourceLocn;
!
! /**
* The html reader associated with this parser.
*/
***************
*** 237,241 ****
*/
public static ParserFeedback noFeedback = new DefaultParserFeedback (DefaultParserFeedback.QUIET);
!
/**
* A verbose message sink.
--- 237,241 ----
*/
public static ParserFeedback noFeedback = new DefaultParserFeedback (DefaultParserFeedback.QUIET);
!
/**
* A verbose message sink.
***************
*** 253,259 ****
public static void setLineSeparator(String lineSeparatorString)
{
! lineSeparator = lineSeparatorString;
}
!
/**
* Return the version string of this parser.
--- 253,259 ----
public static void setLineSeparator(String lineSeparatorString)
{
! lineSeparator = lineSeparatorString;
}
!
/**
* Return the version string of this parser.
***************
*** 320,324 ****
* is provided.
*/
! public Parser(NodeReader rd, ParserFeedback fb)
{
setFeedback (fb);
--- 320,324 ----
* is provided.
*/
! public Parser(NodeReader rd, ParserFeedback fb)
{
setFeedback (fb);
***************
*** 332,336 ****
Tag.setTagParser(new TagParser(feedback));
}
!
/**
* Constructor for custom HTTP access.
--- 332,336 ----
Tag.setTagParser(new TagParser(feedback));
}
!
/**
* Constructor for custom HTTP access.
***************
*** 378,384 ****
this (resourceLocn, stdout);
}
!
/**
! * This constructor is present to enable users to plugin their own readers.
* A DefaultHTMLParserFeedback object is used for feedback. It can also be used with readers of the user's choice
* streaming data into the parser.<p/>
--- 378,384 ----
this (resourceLocn, stdout);
}
!
/**
! * This constructor is present to enable users to plugin their own readers.
* A DefaultHTMLParserFeedback object is used for feedback. It can also be used with readers of the user's choice
* streaming data into the parser.<p/>
***************
*** 394,401 ****
* @param reader The source for HTML to be parsed.
*/
! public Parser(NodeReader reader)
{
! this (reader, stdout);
! }
/**
--- 394,401 ----
* @param reader The source for HTML to be parsed.
*/
! public Parser(NodeReader reader)
{
! this (reader, stdout);
! }
/**
***************
*** 602,606 ****
* and <code>reader</code>. It does not adjust the <code>scanners</code> list
* or <code>feedback</code> object. The <code>url_conn</code> is set to
! * null since this cannot be determined from the reader. The
* <code>character_set</code> is set to the default character set since
* this cannot be determined from the reader.
--- 602,606 ----
* and <code>reader</code>. It does not adjust the <code>scanners</code> list
* or <code>feedback</code> object. The <code>url_conn</code> is set to
! * null since this cannot be determined from the reader. The
* <code>character_set</code> is set to the default character set since
* this cannot be determined from the reader.
***************
*** 634,640 ****
*/
public int getNumScanners() {
! return scanners.size();
}
!
/**
* This method is to be used to change the set of scanners in the current parser.
--- 634,640 ----
*/
public int getNumScanners() {
! return scanners.size();
}
!
/**
* This method is to be used to change the set of scanners in the current parser.
***************
*** 645,649 ****
scanners = (null == newScanners) ? new HashMap() : newScanners;
}
!
/**
* Get an enumeration of scanners registered currently in the parser
--- 645,649 ----
scanners = (null == newScanners) ? new HashMap() : newScanners;
}
!
/**
* Get an enumeration of scanners registered currently in the parser
***************
*** 696,700 ****
StringBuffer msg;
String message;
!
msg = new StringBuffer (1024);
msg.append (url_conn.getURL ().toExternalForm ());
--- 696,700 ----
StringBuffer msg;
String message;
!
msg = new StringBuffer (1024);
msg.append (url_conn.getURL ().toExternalForm ());
***************
*** 708,715 ****
ret = new InputStreamReader (input, character_set);
}
!
return (ret);
}
!
/**
* Create a new reader for the URLConnection object.
--- 708,715 ----
ret = new InputStreamReader (input, character_set);
}
!
return (ret);
}
!
/**
* Create a new reader for the URLConnection object.
***************
*** 762,766 ****
}
}
!
/**
* Try and extract the character set from the HTTP header.
--- 762,766 ----
}
}
!
/**
* Try and extract the character set from the HTTP header.
***************
*** 774,778 ****
String string;
String ret;
!
ret = DEFAULT_CHARSET;
string = connection.getHeaderField (field);
--- 774,778 ----
String string;
String ret;
!
ret = DEFAULT_CHARSET;
string = connection.getHeaderField (field);
***************
*** 816,820 ****
{
index = content.indexOf(CHARSET_STRING);
!
if (index != -1)
{
--- 816,820 ----
{
index = content.indexOf(CHARSET_STRING);
!
if (index != -1)
{
***************
*** 862,866 ****
* In typical situations where you require a no-frills parser, use the registerScanners() method to add the most
* common parsers. But when you wish to either compose a parser with only certain scanners registered, use this method.
! * It is advantageous to register only the scanners you want, in order to achieve faster parsing speed. This method
* would also be of use when you have developed custom scanners, and need to register them into the parser.
* @param scanner TagScanner object (or derivative) to be added to the list of registered scanners
--- 862,866 ----
* In typical situations where you require a no-frills parser, use the registerScanners() method to add the most
* common parsers. But when you wish to either compose a parser with only certain scanners registered, use this method.
! * It is advantageous to register only the scanners you want, in order to achieve faster parsing speed. This method
* would also be of use when you have developed custom scanners, and need to register them into the parser.
* @param scanner TagScanner object (or derivative) to be added to the list of registered scanners
***************
*** 873,877 ****
scanner.setFeedback(feedback);
}
!
/**
* Returns an iterator (enumeration) to the html nodes. Each node can be a tag/endtag/
--- 873,877 ----
scanner.setFeedback(feedback);
}
!
/**
* Returns an iterator (enumeration) to the html nodes. Each node can be a tag/endtag/
***************
*** 925,929 ****
remove_scanner = true;
}
!
/* pre-read up to </HEAD> looking for charset directive */
while (null != (node = ret.peek ()))
--- 925,929 ----
remove_scanner = true;
}
!
/* pre-read up to </HEAD> looking for charset directive */
while (null != (node = ret.peek ()))
***************
*** 976,987 ****
return ret;
}
!
/**
* Flush the current scanners registered. The registered scanners list becomes empty with this call.
*/
public void flushScanners() {
! scanners = new Hashtable();
}
!
/**
* Return the scanner registered in the parser having the
--- 976,987 ----
return ret;
}
!
/**
* Flush the current scanners registered. The registered scanners list becomes empty with this call.
*/
public void flushScanners() {
! scanners = new Hashtable();
}
!
/**
* Return the scanner registered in the parser having the
***************
*** 1006,1010 ****
{
if (filter==null)
! System.out.println(node.toString());
else
{
--- 1006,1010 ----
{
if (filter==null)
! System.out.println(node.toString());
else
{
***************
*** 1014,1025 ****
Tag tag=(Tag)node;
TagScanner scanner = tag.getThisScanner();
! if (scanner==null)
continue;
!
String tagFilter = scanner.getFilter();
if (tagFilter==null) continue;
if (tagFilter.equals(filter))
! System.out.println(node.toString());
! }
}
else System.out.println("Node is null");
--- 1014,1025 ----
Tag tag=(Tag)node;
TagScanner scanner = tag.getThisScanner();
! if (scanner==null)
continue;
!
String tagFilter = scanner.getFilter();
if (tagFilter==null) continue;
if (tagFilter.equals(filter))
! System.out.println(node.toString());
! }
}
else System.out.println("Node is null");
***************
*** 1027,1031 ****
}
!
/**
* This method should be invoked in order to register some common scanners. The scanners that get added are : <br>
--- 1027,1031 ----
}
!
/**
* This method should be invoked in order to register some common scanners. The scanners that get added are : <br>
***************
*** 1048,1052 ****
* parser.registerScanners();
* </pre>
! */
public void registerScanners() {
if (scanners.size()>0) {
--- 1048,1052 ----
* parser.registerScanners();
* </pre>
! */
public void registerScanners() {
if (scanners.size()>0) {
***************
*** 1069,1073 ****
addScanner(new DoctypeScanner("-d"));
addScanner(new FormScanner("-f",this));
! addScanner(new FrameSetScanner("-r"));
addScanner(linkScanner.createBaseHREFScanner("-b"));
addScanner(new BulletListScanner("-bulletList",this));
--- 1069,1073 ----
addScanner(new DoctypeScanner("-d"));
addScanner(new FormScanner("-f",this));
! addScanner(new FrameSetScanner("-r"));
addScanner(linkScanner.createBaseHREFScanner("-b"));
addScanner(new BulletListScanner("-bulletList",this));
***************
*** 1076,1086 ****
addScanner(new TableScanner(this));
}
!
/**
* Make a call to registerDomScanners(), instead of registerScanners(),
* when you are interested in retrieving a Dom representation of the html
* page. Upon parsing, you will receive an Html object - which will contain
! * children, one of which would be the body. This is still evolving, and in
! * future releases, you might see consolidation of Html - to provide you
* with methods to access the body and the head.
*/
--- 1076,1086 ----
addScanner(new TableScanner(this));
}
!
/**
* Make a call to registerDomScanners(), instead of registerScanners(),
* when you are interested in retrieving a Dom representation of the html
* page. Upon parsing, you will receive an Html object - which will contain
! * children, one of which would be the body. This is still evolving, and in
! * future releases, you might see consolidation of Html - to provide you
* with methods to access the body and the head.
*/
***************
*** 1091,1099 ****
addScanner(new HeadScanner());
}
!
/**
* Removes a specified scanner object. You can create
* an anonymous object as a parameter. This method
! * will use the scanner's key and remove it from the
* registry of scanners.
* e.g.
--- 1091,1099 ----
addScanner(new HeadScanner());
}
!
/**
* Removes a specified scanner object. You can create
* an anonymous object as a parameter. This method
! * will use the scanner's key and remove it from the
* registry of scanners.
* e.g.
***************
*** 1123,1128 ****
System.out.println(" -t Show only the Style code extracted from the document");
System.out.println(" -a Show only the Applet tag extracted from the document");
! System.out.println(" -j Parse JSP tags");
! System.out.println(" -m Parse Meta tags");
System.out.println(" -T Extract the Title");
System.out.println(" -f Extract forms");
--- 1123,1128 ----
System.out.println(" -t Show only the Style code extracted from the document");
System.out.println(" -a Show only the Applet tag extracted from the document");
! System.out.println(" -j Parse JSP tags");
! System.out.println(" -m Parse Meta tags");
System.out.println(" -T Extract the Title");
System.out.println(" -f Extract forms");
***************
*** 1156,1160 ****
}
}
!
public void visitAllNodesWith(NodeVisitor visitor) throws ParserException {
Node node;
--- 1156,1160 ----
}
}
!
public void visitAllNodesWith(NodeVisitor visitor) throws ParserException {
Node node;
***************
*** 1165,1169 ****
visitor.finishedParsing();
}
!
/**
* Initializes the parser with the given input HTML String.
--- 1165,1169 ----
visitor.finishedParsing();
}
!
/**
* Initializes the parser with the given input HTML String.
***************
*** 1173,1179 ****
{
if (!"".equals (inputHTML))
! reader = new NodeReader (new StringReader (inputHTML), "");
! }
!
public Node [] extractAllNodesThatAre(Class nodeType) throws ParserException {
NodeList nodeList = new NodeList();
--- 1173,1179 ----
{
if (!"".equals (inputHTML))
! reader = new NodeReader (new StringReader (inputHTML), "");
! }
!
public Node [] extractAllNodesThatAre(Class nodeType) throws ParserException {
NodeList nodeList = new NodeList();
***************
*** 1183,1187 ****
return nodeList.toNodeArray();
}
!
/**
* Creates the parser on an input string.
--- 1183,1187 ----
return nodeList.toNodeArray();
}
!
/**
* Creates the parser on an input string.
***************
*** 1190,1198 ****
*/
public static Parser createParser(String inputHTML) {
! NodeReader reader =
new NodeReader(new StringReader(inputHTML),"");
return new Parser(reader);
}
!
public static Parser createLinkRecognizingParser(String inputHTML) {
Parser parser = createParser(inputHTML);
--- 1190,1198 ----
*/
public static Parser createParser(String inputHTML) {
! NodeReader reader =
new NodeReader(new StringReader(inputHTML),"");
return new Parser(reader);
}
!
public static Parser createLinkRecognizingParser(String inputHTML) {
Parser parser = createParser(inputHTML);
***************
*** 1213,1219 ****
return stringNodeFactory;
}
!
public void setStringNodeFactory(StringNodeFactory stringNodeFactory) {
! this.stringNodeFactory = stringNodeFactory;
! }
}
--- 1213,1219 ----
return stringNodeFactory;
}
!
public void setStringNodeFactory(StringNodeFactory stringNodeFactory) {
! this.stringNodeFactory = stringNodeFactory;
! }
}
Index: RemarkNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/RemarkNode.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** RemarkNode.java 8 Sep 2003 02:26:28 -0000 1.29
--- RemarkNode.java 10 Sep 2003 03:38:17 -0000 1.30
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 39,43 ****
{
public final static String REMARK_NODE_FILTER="-r";
!
/**
* Tag contents will have the contents of the comment tag.
--- 39,43 ----
{
public final static String REMARK_NODE_FILTER="-r";
!
/**
* Tag contents will have the contents of the comment tag.
***************
*** 57,61 ****
}
! /**
* Returns the text contents of the comment tag.
*/
--- 57,61 ----
}
! /**
* Returns the text contents of the comment tag.
*/
Index: RemarkNodeParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/RemarkNodeParser.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** RemarkNodeParser.java 8 Sep 2003 02:26:28 -0000 1.29
--- RemarkNodeParser.java 10 Sep 2003 03:38:17 -0000 1.30
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 34,44 ****
public final static int REMARK_NODE_EXCLAMATION_RECEIVED_STATE=2;
public final static int REMARK_NODE_FIRST_DASH_RECEIVED_STATE=3;
! public final static int REMARK_NODE_ACCEPTING_STATE=4;
! public final static int REMARK_NODE_CLOSING_FIRST_DASH_RECEIVED_STATE=5;
! public final static int REMARK_NODE_CLOSING_SECOND_DASH_RECEIVED_STATE=6;
! public final static int REMARK_NODE_ACCEPTED_STATE=7;
public final static int REMARK_NODE_ILLEGAL_STATE=8;
! public final static int REMARK_NODE_FINISHED_PARSING_STATE=2;
!
/**
* Locate the remark tag withing the input string, by parsing from the given position
--- 34,44 ----
public final static int REMARK_NODE_EXCLAMATION_RECEIVED_STATE=2;
public final static int REMARK_NODE_FIRST_DASH_RECEIVED_STATE=3;
! public final static int REMARK_NODE_ACCEPTING_STATE=4;
! public final static int REMARK_NODE_CLOSING_FIRST_DASH_RECEIVED_STATE=5;
! public final static int REMARK_NODE_CLOSING_SECOND_DASH_RECEIVED_STATE=6;
! public final static int REMARK_NODE_ACCEPTED_STATE=7;
public final static int REMARK_NODE_ILLEGAL_STATE=8;
! public final static int REMARK_NODE_FINISHED_PARSING_STATE=2;
!
/**
* Locate the remark tag withing the input string, by parsing from the given position
***************
*** 46,50 ****
* @param input Input String
* @param position Position to start parsing from
! */
public RemarkNode find(NodeReader reader,String input,int position)
{
--- 46,50 ----
* @param input Input String
* @param position Position to start parsing from
! */
public RemarkNode find(NodeReader reader,String input,int position)
{
***************
*** 91,95 ****
tagContents.append(prevChar);
}
! }
if (state==REMARK_NODE_ACCEPTING_STATE) {
if (ch == '-') {
--- 91,95 ----
tagContents.append(prevChar);
}
! }
if (state==REMARK_NODE_ACCEPTING_STATE) {
if (ch == '-') {
***************
*** 103,111 ****
if (state==REMARK_NODE_ACCEPTING_STATE)
{
! // We can append contents now
tagContents.append(ch);
! }
-
if (state==REMARK_NODE_FIRST_DASH_RECEIVED_STATE)
{
--- 103,111 ----
if (state==REMARK_NODE_ACCEPTING_STATE)
{
! // We can append contents now
tagContents.append(ch);
! }
!
if (state==REMARK_NODE_FIRST_DASH_RECEIVED_STATE)
{
***************
*** 118,122 ****
}
else state=REMARK_NODE_ILLEGAL_STATE;
! }
if (state==REMARK_NODE_EXCLAMATION_RECEIVED_STATE)
{
--- 118,122 ----
}
else state=REMARK_NODE_ILLEGAL_STATE;
! }
if (state==REMARK_NODE_EXCLAMATION_RECEIVED_STATE)
{
***************
*** 129,133 ****
}
else state=REMARK_NODE_ILLEGAL_STATE;
! }
if (state==REMARK_NODE_OPENING_ANGLE_BRACKET_STATE)
{
--- 129,133 ----
}
else state=REMARK_NODE_ILLEGAL_STATE;
! }
if (state==REMARK_NODE_OPENING_ANGLE_BRACKET_STATE)
{
***************
*** 135,139 ****
state=REMARK_NODE_EXCLAMATION_RECEIVED_STATE;
else state = REMARK_NODE_ILLEGAL_STATE; // This is not a remark tag
! }
if (state == REMARK_NODE_BEFORE_PARSING_STATE)
{
--- 135,139 ----
state=REMARK_NODE_EXCLAMATION_RECEIVED_STATE;
else state = REMARK_NODE_ILLEGAL_STATE; // This is not a remark tag
! }
if (state == REMARK_NODE_BEFORE_PARSING_STATE)
{
***************
*** 147,153 ****
state = REMARK_NODE_ILLEGAL_STATE;
}
! }
// if...
[truncated message content] |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/nodeDecorators
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/nodeDecorators
Modified Files:
AbstractNodeDecorator.java DecodingNode.java
EscapeCharacterRemovingNode.java
NonBreakingSpaceConvertingNode.java
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AbstractNodeDecorator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/nodeDecorators/AbstractNodeDecorator.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** AbstractNodeDecorator.java 8 Sep 2003 02:26:28 -0000 1.9
--- AbstractNodeDecorator.java 10 Sep 2003 03:38:18 -0000 1.10
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 36,40 ****
public abstract class AbstractNodeDecorator implements Node {
protected Node delegate;
!
protected AbstractNodeDecorator(Node delegate) {
this.delegate = delegate;
--- 36,40 ----
public abstract class AbstractNodeDecorator implements Node {
protected Node delegate;
!
protected AbstractNodeDecorator(Node delegate) {
this.delegate = delegate;
Index: DecodingNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/nodeDecorators/DecodingNode.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** DecodingNode.java 8 Sep 2003 02:26:28 -0000 1.9
--- DecodingNode.java 10 Sep 2003 03:38:18 -0000 1.10
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
Index: EscapeCharacterRemovingNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/nodeDecorators/EscapeCharacterRemovingNode.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** EscapeCharacterRemovingNode.java 8 Sep 2003 02:26:28 -0000 1.7
--- EscapeCharacterRemovingNode.java 10 Sep 2003 03:38:18 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
Index: NonBreakingSpaceConvertingNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/nodeDecorators/NonBreakingSpaceConvertingNode.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** NonBreakingSpaceConvertingNode.java 8 Sep 2003 02:26:28 -0000 1.7
--- NonBreakingSpaceConvertingNode.java 10 Sep 2003 03:38:18 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/lexer/nodes
Modified Files:
AbstractNode.java Attribute.java RemarkNode.java
StringNode.java TagNode.java package.html
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: AbstractNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/AbstractNode.java,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** AbstractNode.java 8 Sep 2003 02:26:28 -0000 1.4
--- AbstractNode.java 10 Sep 2003 03:38:18 -0000 1.5
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 45,49 ****
*/
protected Page mPage;
!
/**
* Create a lexeme.
--- 45,49 ----
*/
protected Page mPage;
!
/**
* Create a lexeme.
Index: Attribute.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/Attribute.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** Attribute.java 8 Sep 2003 02:26:28 -0000 1.6
--- Attribute.java 10 Sep 2003 03:38:18 -0000 1.7
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 58,62 ****
*/
protected Page mPage;
!
/**
* The starting offset of the name within the page.
--- 58,62 ----
*/
protected Page mPage;
!
/**
* The starting offset of the name within the page.
***************
*** 88,92 ****
*/
protected String mName;
!
/**
* The value of the attribute.
--- 88,92 ----
*/
protected String mName;
!
/**
* The value of the attribute.
***************
*** 96,100 ****
*/
protected String mValue;
!
/**
* The quote, if any, surrounding the value of the attribute, if any.
--- 96,100 ----
*/
protected String mValue;
!
/**
* The quote, if any, surrounding the value of the attribute, if any.
***************
*** 179,183 ****
StringBuffer buffer;
String ret;
!
ret = getValue ();
if (null != ret && (0 != (quote = getQuote ())))
--- 179,183 ----
StringBuffer buffer;
String ret;
!
ret = getValue ();
if (null != ret && (0 != (quote = getQuote ())))
***************
*** 252,256 ****
{
String name;
!
name = getName ();
if (null == name)
--- 252,256 ----
{
String name;
!
name = getName ();
if (null == name)
***************
*** 301,305 ****
ret = new StringBuffer (length);
toString (ret);
!
return (ret.toString ());
}
--- 301,305 ----
ret = new StringBuffer (length);
toString (ret);
!
return (ret.toString ());
}
Index: RemarkNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/RemarkNode.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** RemarkNode.java 8 Sep 2003 02:26:28 -0000 1.5
--- RemarkNode.java 10 Sep 2003 03:38:18 -0000 1.6
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 40,45 ****
{
public final static String REMARK_NODE_FILTER="-r";
!
! /**
* Constructor takes in the text string, beginning and ending posns.
* @param page The page this string is on.
--- 40,45 ----
{
public final static String REMARK_NODE_FILTER="-r";
!
! /**
* Constructor takes in the text string, beginning and ending posns.
* @param page The page this string is on.
***************
*** 52,56 ****
}
! /**
* Returns the text contents of the comment tag.
* todo: this only works for the usual case.
--- 52,56 ----
}
! /**
* Returns the text contents of the comment tag.
* todo: this only works for the usual case.
***************
*** 75,79 ****
Cursor start;
Cursor end;
!
start = new Cursor (getPage (), elementBegin ());
end = new Cursor (getPage (), elementEnd ());
--- 75,79 ----
Cursor start;
Cursor end;
!
start = new Cursor (getPage (), elementBegin ());
end = new Cursor (getPage (), elementEnd ());
Index: StringNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/StringNode.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** StringNode.java 8 Sep 2003 02:26:28 -0000 1.5
--- StringNode.java 10 Sep 2003 03:38:18 -0000 1.6
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 41,46 ****
{
public static final String STRING_FILTER = "-string";
!
! /**
* Constructor takes in the text string, beginning and ending posns.
* @param page The page this string is on.
--- 41,46 ----
{
public static final String STRING_FILTER = "-string";
!
! /**
* Constructor takes in the text string, beginning and ending posns.
* @param page The page this string is on.
***************
*** 77,96 ****
}
}
!
public String toPlainTextString ()
{
return (toHtml ());
}
!
public String toHtml ()
{
return (mPage.getText (elementBegin (), elementEnd ()));
}
!
public String toString ()
{
Cursor start;
Cursor end;
!
start = new Cursor (getPage (), elementBegin ());
end = new Cursor (getPage (), elementEnd ());
--- 77,96 ----
}
}
!
public String toPlainTextString ()
{
return (toHtml ());
}
!
public String toHtml ()
{
return (mPage.getText (elementBegin (), elementEnd ()));
}
!
public String toString ()
{
Cursor start;
Cursor end;
!
start = new Cursor (getPage (), elementBegin ());
end = new Cursor (getPage (), elementEnd ());
***************
*** 98,102 ****
}
!
public void collectInto (NodeList collectionList, String filter)
{
--- 98,102 ----
}
!
public void collectInto (NodeList collectionList, String filter)
{
***************
*** 104,108 ****
collectionList.add (this);
}
!
public void accept (Object visitor)
{
--- 104,108 ----
collectionList.add (this);
}
!
public void accept (Object visitor)
{
Index: TagNode.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/TagNode.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** TagNode.java 8 Sep 2003 02:26:28 -0000 1.8
--- TagNode.java 10 Sep 2003 03:38:18 -0000 1.9
***************
*** 59,63 ****
public final static String NOTHING = "$<NOTHING>$";
private final static String EMPTY_STRING="";
!
private boolean emptyXmlTag = false;
--- 59,63 ----
public final static String NOTHING = "$<NOTHING>$";
private final static String EMPTY_STRING="";
!
private boolean emptyXmlTag = false;
***************
*** 139,143 ****
* @param name Name of attribute, case insensitive.
* @return The value associated with the attribute or null if it does
! * not exist, or is a stand-alone or
*/
public String getAttribute (String name)
--- 139,143 ----
* @param name Name of attribute, case insensitive.
* @return The value associated with the attribute or null if it does
! * not exist, or is a stand-alone or
*/
public String getAttribute (String name)
***************
*** 148,152 ****
String string;
String ret;
!
ret = null;
--- 148,152 ----
String string;
String ret;
!
ret = null;
***************
*** 168,172 ****
}
}
!
return (ret);
}
--- 168,172 ----
}
}
!
return (ret);
}
***************
*** 203,207 ****
doubleq = false;
}
!
// now apply quoting
if (needed)
--- 203,207 ----
doubleq = false;
}
!
// now apply quoting
if (needed)
***************
*** 291,299 ****
return (getAttribute (name));
}
!
/**
* Gets the attributes in the tag.
* NOTE: Values of the extended hashtable are two element arrays of String,
! * with the first element being the original name (not uppercased),
* and the second element being the value.
* @return Returns a special hashtable of attributes in two element String arrays.
--- 291,299 ----
return (getAttribute (name));
}
!
/**
* Gets the attributes in the tag.
* NOTE: Values of the extended hashtable are two element arrays of String,
! * with the first element being the original name (not uppercased),
* and the second element being the value.
* @return Returns a special hashtable of attributes in two element String arrays.
***************
*** 315,319 ****
StringBuffer _value;
Hashtable ret;
!
ret = new SpecialHashtable ();
attributes = getAttributesEx ();
--- 315,319 ----
StringBuffer _value;
Hashtable ret;
!
ret = new SpecialHashtable ();
attributes = getAttributesEx ();
***************
*** 414,418 ****
char quote;
Attribute attribute;
!
att = new Vector ();
for (Enumeration e = attributes.keys (); e.hasMoreElements (); )
--- 414,418 ----
char quote;
Attribute attribute;
!
att = new Vector ();
for (Enumeration e = attributes.keys (); e.hasMoreElements (); )
***************
*** 441,445 ****
* Sets the attributes.
* NOTE: Values of the extended hashtable are two element arrays of String,
! * with the first element being the original name (not uppercased),
* and the second element being the value.
* @param attribs The attribute collection to set.
--- 441,445 ----
* Sets the attributes.
* NOTE: Values of the extended hashtable are two element arrays of String,
! * with the first element being the original name (not uppercased),
* and the second element being the value.
* @param attribs The attribute collection to set.
***************
*** 467,471 ****
return (nodeBegin);
}
!
/**
* Sets the nodeEnd.
--- 467,471 ----
return (nodeBegin);
}
!
/**
* Sets the nodeEnd.
***************
*** 476,480 ****
nodeEnd = tagEnd;
}
!
/**
* Gets the nodeEnd.
--- 476,480 ----
nodeEnd = tagEnd;
}
!
/**
* Gets the nodeEnd.
***************
*** 613,617 ****
/**
* Is this an empty xml tag of the form<br>
! * <tag/>
* @return boolean
*/
--- 613,617 ----
/**
* Is this an empty xml tag of the form<br>
! * <tag/>
* @return boolean
*/
Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/nodes/package.html,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** package.html 8 Sep 2003 02:26:28 -0000 1.3
--- package.html 10 Sep 2003 03:38:18 -0000 1.4
***************
*** 19,23 ****
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
--- 19,23 ----
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
***************
*** 26,38 ****
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
<TITLE>Nodes Package</TITLE>
--- 26,38 ----
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
<TITLE>Nodes Package</TITLE>
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/lexer
Modified Files:
Cursor.java Lexer.java Page.java PageIndex.java Source.java
Stream.java package.html
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: Cursor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Cursor.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** Cursor.java 8 Sep 2003 02:26:28 -0000 1.6
--- Cursor.java 10 Sep 2003 03:38:18 -0000 1.7
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 45,49 ****
*/
protected int mPosition;
!
/**
* This cursor's page.
--- 45,49 ----
*/
protected int mPosition;
!
/**
* This cursor's page.
***************
*** 114,118 ****
}
}
!
public String toString ()
{
--- 114,118 ----
}
}
!
public String toString ()
{
***************
*** 120,124 ****
int column;
StringBuffer ret;
!
ret = new StringBuffer (9 * 3 + 3); // three ints and delimiters
ret.append (getPosition ());
--- 120,124 ----
int column;
StringBuffer ret;
!
ret = new StringBuffer (9 * 3 + 3); // three ints and delimiters
ret.append (getPosition ());
***************
*** 130,134 ****
ret.append (column);
ret.append ("]");
!
return (ret.toString ());
}
--- 130,134 ----
ret.append (column);
ret.append ("]");
!
return (ret.toString ());
}
***************
*** 147,150 ****
return (getPosition () - r.getPosition ());
}
! }
--- 147,150 ----
return (getPosition () - r.getPosition ());
}
! }
Index: Lexer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Lexer.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** Lexer.java 8 Sep 2003 02:26:28 -0000 1.7
--- Lexer.java 10 Sep 2003 03:38:18 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 164,168 ****
int end;
StringNode ret;
!
cursor = mCursor.dup ();
done = false;
--- 164,168 ----
int end;
StringNode ret;
!
cursor = mCursor.dup ();
done = false;
***************
*** 312,316 ****
int length;
TagNode ret;
!
cursor = mCursor.dup ();
// sanity check
--- 312,316 ----
int length;
TagNode ret;
!
cursor = mCursor.dup ();
// sanity check
***************
*** 447,451 ****
* which occupies more than one line --><p>
* </code>
! * White space is not permitted between the markup declaration
* open delimiter("<!") and the comment open delimiter ("--"),
* but is permitted between the comment close delimiter ("--") and
--- 447,451 ----
* which occupies more than one line --><p>
* </code>
! * White space is not permitted between the markup declaration
* open delimiter("<!") and the comment open delimiter ("--"),
* but is permitted between the comment close delimiter ("--") and
***************
*** 481,485 ****
int length;
RemarkNode ret;
!
cursor = mCursor.dup ();
// sanity check
--- 481,485 ----
int length;
RemarkNode ret;
!
cursor = mCursor.dup ();
// sanity check
Index: Page.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Page.java,v
retrieving revision 1.12
retrieving revision 1.13
diff -C2 -d -r1.12 -r1.13
*** Page.java 8 Sep 2003 02:26:28 -0000 1.12
--- Page.java 10 Sep 2003 03:38:18 -0000 1.13
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 225,229 ****
i = mSource.read ();
if (-1 == i)
! {
// do nothing
}
--- 225,229 ----
i = mSource.read ();
if (-1 == i)
! {
// do nothing
}
***************
*** 269,273 ****
String string;
String ret;
!
ret = DEFAULT_CHARSET;
string = connection.getHeaderField (CONTENT_TYPE_STRING);
--- 269,273 ----
String string;
String ret;
!
ret = DEFAULT_CHARSET;
string = connection.getHeaderField (CONTENT_TYPE_STRING);
***************
*** 312,316 ****
{
index = content.indexOf (CHARSET_STRING);
!
if (index != -1)
{
--- 312,316 ----
{
index = content.indexOf (CHARSET_STRING);
!
if (index != -1)
{
***************
*** 362,366 ****
{
String ret;
!
try
{
--- 362,366 ----
{
String ret;
!
try
{
***************
*** 403,407 ****
+ _default);
}
!
return (ret);
}
--- 403,407 ----
+ _default);
}
!
return (ret);
}
***************
*** 439,446 ****
{
StringBuffer ret;
!
ret = new StringBuffer (Math.abs (end - start));
getText (ret, start, end);
!
return (ret.toString ());
}
--- 439,446 ----
{
StringBuffer ret;
!
ret = new StringBuffer (Math.abs (end - start));
getText (ret, start, end);
!
return (ret.toString ());
}
***************
*** 478,485 ****
{
StringBuffer ret;
!
ret = new StringBuffer (mSource.mOffset);
getText (ret);
!
return (ret.toString ());
}
--- 478,485 ----
{
StringBuffer ret;
!
ret = new StringBuffer (mSource.mOffset);
getText (ret);
!
return (ret.toString ());
}
Index: PageIndex.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/PageIndex.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** PageIndex.java 8 Sep 2003 02:26:28 -0000 1.7
--- PageIndex.java 10 Sep 2003 03:38:18 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,31 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
--- 18,31 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
! //
! // This class was contributed by
// Derrick Oswald
//
***************
*** 46,50 ****
* does not incur the overhead of an <code>Integer</code> object per element.
*/
! public class PageIndex implements Sortable
{
/**
--- 46,50 ----
* does not incur the overhead of an <code>Integer</code> object per element.
*/
! public class PageIndex implements Sortable
{
/**
***************
*** 52,61 ****
*/
protected static final int mIncrement = 100;
!
/**
* The number of valid elements.
*/
protected int mCount;
!
/**
* The elements.
--- 52,61 ----
*/
protected static final int mIncrement = 100;
!
/**
* The number of valid elements.
*/
protected int mCount;
!
/**
* The elements.
***************
*** 77,81 ****
mIndices = new int[mIncrement];
mCount = 0;
! }
/**
--- 77,81 ----
mIndices = new int[mIncrement];
mCount = 0;
! }
/**
***************
*** 89,93 ****
mIndices[0] = cursor;
mCount = 1;
! }
/**
--- 89,93 ----
mIndices[0] = cursor;
mCount = 1;
! }
/**
***************
*** 102,106 ****
mIndices = cursors;
mCount = cursors.length;
! }
/**
--- 102,106 ----
mIndices = cursors;
mCount = cursors.length;
! }
/**
***************
*** 130,134 ****
return (mIndices.length);
}
!
/**
* Add an element to the list
--- 130,134 ----
return (mIndices.length);
}
!
/**
* Add an element to the list
***************
*** 149,155 ****
if (!((ret < size ()) && (position == mIndices[ret])))
insertElementAt (position, ret);
!
return (ret);
! }
/**
--- 149,155 ----
if (!((ret < size ()) && (position == mIndices[ret])))
insertElementAt (position, ret);
!
return (ret);
! }
/**
***************
*** 162,166 ****
{
return (add (new Cursor (getPage (), cursor)));
! }
/**
--- 162,166 ----
{
return (add (new Cursor (getPage (), cursor)));
! }
/**
***************
*** 178,182 ****
if ((i < size ()) && (cursor.getPosition () == mIndices[i]))
removeElementAt (i);
! }
/**
--- 178,182 ----
if ((i < size ()) && (cursor.getPosition () == mIndices[i]))
removeElementAt (i);
! }
/**
***************
*** 187,191 ****
{
remove (new Cursor (getPage (), cursor));
! }
/**
--- 187,191 ----
{
remove (new Cursor (getPage (), cursor));
! }
/**
***************
*** 197,201 ****
{
return (mIndices[index]);
! }
/**
--- 197,201 ----
{
return (mIndices[index]);
! }
/**
***************
*** 207,211 ****
{
int ret;
!
ret = Sort.bsearch (this, cursor);
// handle line transition, the search returns the index if it matches
--- 207,211 ----
{
int ret;
!
ret = Sort.bsearch (this, cursor);
// handle line transition, the search returns the index if it matches
***************
*** 215,219 ****
if ((ret < mCount) && (cursor.getPosition () == mIndices[ret]))
ret++;
!
return (ret);
}
--- 215,219 ----
if ((ret < mCount) && (cursor.getPosition () == mIndices[ret]))
ret++;
!
return (ret);
}
***************
*** 244,248 ****
else
previous = 0;
!
return (cursor.getPosition () - previous);
}
--- 244,248 ----
else
previous = 0;
!
return (cursor.getPosition () - previous);
}
***************
*** 267,273 ****
int[] ret = new int[size ()];
System.arraycopy (mIndices, 0, ret, 0, size ());
!
return (ret);
! }
/**
--- 267,273 ----
int[] ret = new int[size ()];
System.arraycopy (mIndices, 0, ret, 0, size ());
!
return (ret);
! }
/**
***************
*** 279,283 ****
{
return (Sort.bsearch (this, new Cursor (getPage (), cursor)));
! }
/**
--- 279,283 ----
{
return (Sort.bsearch (this, new Cursor (getPage (), cursor)));
! }
/**
***************
*** 291,295 ****
{
return (Sort.bsearch (this, new Cursor (getPage (), cursor), first, last));
! }
/**
--- 291,295 ----
{
return (Sort.bsearch (this, new Cursor (getPage (), cursor), first, last));
! }
/**
***************
*** 320,324 ****
mIndices[index] = cursor;
mCount++;
! }
/**
--- 320,324 ----
mIndices[index] = cursor;
mCount++;
! }
/**
***************
*** 333,337 ****
mCount--;
}
!
//
// Sortable interface
--- 333,337 ----
mCount--;
}
!
//
// Sortable interface
***************
*** 345,349 ****
{
return (0);
! }
/**
--- 345,349 ----
{
return (0);
! }
/**
***************
*** 355,359 ****
{
return (mCount - 1);
! }
/**
--- 355,359 ----
{
return (mCount - 1);
! }
/**
***************
*** 362,366 ****
* @param reuse If this argument is not null, it is an object
* acquired from a previous fetch that is no longer needed and
! * may be returned as the result if it makes mores sense to alter
* and return it than to fetch or create a new element. That is, the
* reuse object is garbage and may be used to avoid allocating a new
--- 362,366 ----
* @param reuse If this argument is not null, it is an object
* acquired from a previous fetch that is no longer needed and
! * may be returned as the result if it makes mores sense to alter
* and return it than to fetch or create a new element. That is, the
* reuse object is garbage and may be used to avoid allocating a new
***************
*** 382,386 ****
return (ret);
! }
/**
--- 382,386 ----
return (ret);
! }
/**
Index: Source.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Source.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** Source.java 8 Sep 2003 02:26:28 -0000 1.7
--- Source.java 10 Sep 2003 03:38:18 -0000 1.8
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 44,48 ****
* <li>the fetching of bytes from the connection's input stream may be asynchronous</li>
* <li>the character set may be changed, which resets the input stream</li>
! *
*/
public class Source extends Reader
--- 44,48 ----
* <li>the fetching of bytes from the connection's input stream may be asynchronous</li>
* <li>the character set may be changed, which resets the input stream</li>
! *
*/
public class Source extends Reader
***************
*** 52,56 ****
*/
public static int BUFFER_SIZE = 16384;
!
/**
* Return value when no more characters are left.
--- 52,56 ----
*/
public static int BUFFER_SIZE = 16384;
!
/**
* Return value when no more characters are left.
***************
*** 211,215 ****
{
int ret;
!
if (mLevel - mOffset < 1)
{
--- 211,215 ----
{
int ret;
!
if (mLevel - mOffset < 1)
{
***************
*** 224,231 ****
else
ret = mBuffer[mOffset++];
!
return (ret);
}
!
/**
* Read characters into a portion of an array. This method will block
--- 224,231 ----
else
ret = mBuffer[mOffset++];
!
return (ret);
}
!
/**
* Read characters into a portion of an array. This method will block
***************
*** 259,263 ****
mOffset += ret;
}
!
return (ret);
}
--- 259,263 ----
mOffset += ret;
}
!
return (ret);
}
***************
*** 272,276 ****
* @exception IOException If an I/O error occurs.
*/
!
public int read (char[] cbuf) throws IOException
{
--- 272,276 ----
* @exception IOException If an I/O error occurs.
*/
!
public int read (char[] cbuf) throws IOException
{
***************
*** 299,305 ****
mOffset = 0;
}
!
/**
! * Tell whether this stream supports the mark() operation.
* @return <code>true</code> if and only if this stream supports the mark operation.
*/
--- 299,305 ----
mOffset = 0;
}
!
/**
! * Tell whether this stream supports the mark() operation.
* @return <code>true</code> if and only if this stream supports the mark operation.
*/
***************
*** 308,312 ****
return (true);
}
!
/**
* Mark the present position in the stream. Subsequent calls to reset()
--- 308,312 ----
return (true);
}
!
/**
* Mark the present position in the stream. Subsequent calls to reset()
***************
*** 323,327 ****
mMark = mOffset;
}
!
/**
* Tell whether this stream is ready to be read.
--- 323,327 ----
mMark = mOffset;
}
!
/**
* Tell whether this stream is ready to be read.
***************
*** 337,341 ****
return (mOffset < mLevel);
}
!
/**
* Skip characters.
--- 337,341 ----
return (mOffset < mLevel);
}
!
/**
* Skip characters.
***************
*** 363,370 ****
mOffset += ret;
}
!
return (ret);
}
!
//
// Methods not in your Daddy's Reader
--- 363,370 ----
mOffset += ret;
}
!
return (ret);
}
!
//
// Methods not in your Daddy's Reader
Index: Stream.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Stream.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** Stream.java 8 Sep 2003 02:26:28 -0000 1.5
--- Stream.java 10 Sep 2003 03:38:18 -0000 1.6
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 35,39 ****
/**
* Provides for asynchronous fetching from a stream.
! *
*/
public class Stream extends InputStream implements Runnable
--- 35,39 ----
/**
* Provides for asynchronous fetching from a stream.
! *
*/
public class Stream extends InputStream implements Runnable
***************
*** 148,152 ****
}
else
! {
if (mBuffer.length - mLevel < BUFFER_SIZE / 2)
buffer = new byte[Math.max (mBuffer.length * 2, mBuffer.length + mIn.available ())];
--- 148,152 ----
}
else
! {
if (mBuffer.length - mLevel < BUFFER_SIZE / 2)
buffer = new byte[Math.max (mBuffer.length * 2, mBuffer.length + mIn.available ())];
***************
*** 259,266 ****
else
ret = EOF;
!
return (ret);
}
!
/**
* Returns the number of bytes that can be read (or skipped over) from
--- 259,266 ----
else
ret = EOF;
!
return (ret);
}
!
/**
* Returns the number of bytes that can be read (or skipped over) from
***************
*** 276,280 ****
return (mLevel - mOffset);
}
!
/**
* Closes this input stream and releases any system resources associated
--- 276,280 ----
return (mLevel - mOffset);
}
!
/**
* Closes this input stream and releases any system resources associated
***************
*** 295,299 ****
mMark = -1;
}
!
/**
* Repositions this stream to the position at the time the
--- 295,299 ----
mMark = -1;
}
!
/**
* Repositions this stream to the position at the time the
***************
*** 345,349 ****
mOffset = 0;
}
!
/**
* Tests if this input stream supports the <code>mark</code> and
--- 345,349 ----
mOffset = 0;
}
!
/**
* Tests if this input stream supports the <code>mark</code> and
***************
*** 362,366 ****
return (true);
}
!
/**
* Marks the current position in this input stream. A subsequent call to
--- 362,366 ----
return (true);
}
!
/**
* Marks the current position in this input stream. A subsequent call to
Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/package.html,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** package.html 8 Sep 2003 02:26:28 -0000 1.5
--- package.html 10 Sep 2003 03:38:18 -0000 1.6
***************
*** 19,23 ****
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
--- 19,23 ----
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
***************
*** 26,38 ****
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
<TITLE>Lexer Package</TITLE>
--- 26,38 ----
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
<TITLE>Lexer Package</TITLE>
***************
*** 105,109 ****
but instead simply contain offsets into a single large buffer that contains the
text read from the HTML source. Even within tags, the attributes list can
! contain whitespace, thus there is no lost whitespace or text formatting
either outside or within tags. Upper and lower case text is preserved.
<DT>Line Endings
--- 105,109 ----
but instead simply contain offsets into a single large buffer that contains the
text read from the HTML source. Even within tags, the attributes list can
! contain whitespace, thus there is no lost whitespace or text formatting
either outside or within tags. Upper and lower case text is preserved.
<DT>Line Endings
***************
*** 127,131 ****
all that's needed for a low level parse of the HTML source. In previous
implementations, the attributes were parsed on a second scan after the initial
! tag was extracted.
<DT>Two Jars
<DD>For elementary operations at the node level, a minimalist jar file containing
--- 127,131 ----
all that's needed for a low level parse of the HTML source. In previous
implementations, the attributes were parsed on a second scan after the initial
! tag was extracted.
<DT>Two Jars
<DD>For elementary operations at the node level, a minimalist jar file containing
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans
In directory sc8-pr-cvs1:/tmp/cvs-serv24483/src/org/htmlparser/beans
Modified Files:
BeanyBaby.java HTMLLinkBean.java HTMLTextBean.java
LinkBean.java StringBean.java package.html
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
Index: BeanyBaby.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/BeanyBaby.java,v
retrieving revision 1.14
retrieving revision 1.15
diff -C2 -d -r1.14 -r1.15
*** BeanyBaby.java 8 Sep 2003 02:26:28 -0000 1.14
--- BeanyBaby.java 10 Sep 2003 03:38:18 -0000 1.15
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 49,58 ****
*/
java.util.Vector mTrail;
!
/**
* Current position on the bread crumb trail.
*/
int mCrumb;
!
/** Creates new form BeanyBaby */
public BeanyBaby ()
--- 49,58 ----
*/
java.util.Vector mTrail;
!
/**
* Current position on the bread crumb trail.
*/
int mCrumb;
!
/** Creates new form BeanyBaby */
public BeanyBaby ()
***************
*** 95,99 ****
Object source;
String name;
!
source = event.getSource ();
if (source == mLinkBean)
--- 95,99 ----
Object source;
String name;
!
source = event.getSource ();
if (source == mLinkBean)
***************
*** 170,176 ****
}
}
!
}
!
//
// MouseListener interface
--- 170,176 ----
}
}
!
}
!
//
// MouseListener interface
***************
*** 232,241 ****
mTrail.setElementAt (url, mCrumb);
mLinkBean.setURL (url);
!
// update navigation menu
mBack.setEnabled (mCrumb > 0);
mForward.setEnabled (mCrumb + 1 < mTrail.size ());
}
!
/** This method is called from within the constructor to
* initialize the form.
--- 232,241 ----
mTrail.setElementAt (url, mCrumb);
mLinkBean.setURL (url);
!
// update navigation menu
mBack.setEnabled (mCrumb > 0);
mForward.setEnabled (mCrumb + 1 < mTrail.size ());
}
!
/** This method is called from within the constructor to
* initialize the form.
***************
*** 345,349 ****
setLocation((screenSize.width-640)/2,(screenSize.height-480)/2);
}//GEN-END:initComponents
!
/** Exit the Application */
private void exitForm (java.awt.event.WindowEvent evt)
--- 345,349 ----
setLocation((screenSize.width-640)/2,(screenSize.height-480)/2);
}//GEN-END:initComponents
!
/** Exit the Application */
private void exitForm (java.awt.event.WindowEvent evt)
***************
*** 351,355 ****
System.exit (0);
}//GEN-LAST:event_exitForm
!
// Variables declaration - do not modify//GEN-BEGIN:variables
private org.htmlparser.beans.HTMLLinkBean mLinkBean;
--- 351,355 ----
System.exit (0);
}//GEN-LAST:event_exitForm
!
// Variables declaration - do not modify//GEN-BEGIN:variables
private org.htmlparser.beans.HTMLLinkBean mLinkBean;
Index: HTMLLinkBean.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/HTMLLinkBean.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** HTMLLinkBean.java 8 Sep 2003 02:26:28 -0000 1.15
--- HTMLLinkBean.java 10 Sep 2003 03:38:18 -0000 1.16
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 100,104 ****
getBean ().addPropertyChangeListener (listener);
}
!
/**
* Remove a PropertyChangeListener from the listener list.
--- 100,104 ----
getBean ().addPropertyChangeListener (listener);
}
!
/**
* Remove a PropertyChangeListener from the listener list.
***************
*** 112,116 ****
getBean ().removePropertyChangeListener (listener);
}
!
//
// Properties
--- 112,116 ----
getBean ().removePropertyChangeListener (listener);
}
!
//
// Properties
***************
*** 126,130 ****
return (getBean ().getLinks ());
}
!
/**
* Getter for property URL.
--- 126,130 ----
return (getBean ().getLinks ());
}
!
/**
* Getter for property URL.
***************
*** 136,140 ****
return (getBean ().getURL ());
}
!
/**
* Setter for property URL.
--- 136,140 ----
return (getBean ().getURL ());
}
!
/**
* Setter for property URL.
***************
*** 155,159 ****
return (getBean ().getConnection ());
}
!
/**
* Setter for property Connection.
--- 155,159 ----
return (getBean ().getConnection ());
}
!
/**
* Setter for property Connection.
***************
*** 180,184 ****
}
}
!
// /**
// * Unit test.
--- 180,184 ----
}
}
!
// /**
// * Unit test.
Index: HTMLTextBean.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/HTMLTextBean.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** HTMLTextBean.java 8 Sep 2003 02:26:28 -0000 1.16
--- HTMLTextBean.java 10 Sep 2003 03:38:18 -0000 1.17
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 67,71 ****
int width;
int height;
!
metrics = getFontMetrics (getFont ());
width = metrics.stringWidth ("Hello World");
--- 67,71 ----
int width;
int height;
!
metrics = getFontMetrics (getFont ());
width = metrics.stringWidth ("Hello World");
***************
*** 86,90 ****
getBean ().addPropertyChangeListener (listener);
}
!
/**
* Remove a PropertyChangeListener from the listener list.
--- 86,90 ----
getBean ().addPropertyChangeListener (listener);
}
!
/**
* Remove a PropertyChangeListener from the listener list.
***************
*** 98,102 ****
getBean ().removePropertyChangeListener (listener);
}
!
//
// Properties
--- 98,102 ----
getBean ().removePropertyChangeListener (listener);
}
!
//
// Properties
***************
*** 135,139 ****
return (getBean ().getLinks ());
}
!
/**
* Setter for property links.
--- 135,139 ----
return (getBean ().getLinks ());
}
!
/**
* Setter for property links.
***************
*** 145,149 ****
getBean ().setLinks (links);
}
!
/**
* Getter for property URL.
--- 145,149 ----
getBean ().setLinks (links);
}
!
/**
* Getter for property URL.
***************
*** 155,159 ****
return (getBean ().getURL ());
}
!
/**
* Setter for property URL.
--- 155,159 ----
return (getBean ().getURL ());
}
!
/**
* Setter for property URL.
***************
*** 176,180 ****
return (getBean ().getReplaceNonBreakingSpaces ());
}
!
/**
* Set the 'replace non breaking spaces' state.
--- 176,180 ----
return (getBean ().getReplaceNonBreakingSpaces ());
}
!
/**
* Set the 'replace non breaking spaces' state.
***************
*** 204,208 ****
return (getBean ().getCollapse ());
}
!
/**
* Set the current 'collapse whitespace' state.
--- 204,208 ----
return (getBean ().getCollapse ());
}
!
/**
* Set the current 'collapse whitespace' state.
***************
*** 223,227 ****
return (getBean ().getConnection ());
}
!
/**
* Setter for property Connection.
--- 223,227 ----
return (getBean ().getConnection ());
}
!
/**
* Setter for property Connection.
***************
*** 249,253 ****
}
}
!
// /**
// * Unit test.
--- 249,253 ----
}
}
!
// /**
// * Unit test.
Index: LinkBean.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/LinkBean.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** LinkBean.java 8 Sep 2003 02:26:28 -0000 1.19
--- LinkBean.java 10 Sep 2003 03:38:18 -0000 1.20
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 69,73 ****
*/
protected URL[] mLinks;
!
/**
* The parser used to extract strings.
--- 69,73 ----
*/
protected URL[] mLinks;
!
/**
* The parser used to extract strings.
***************
*** 93,97 ****
LinkTag link;
URL[] ret;
!
parser = new Parser (url);
parser.registerScanners ();
--- 93,97 ----
LinkTag link;
URL[] ret;
!
parser = new Parser (url);
parser.registerScanners ();
***************
*** 127,131 ****
{
boolean ret;
!
ret = false;
if ((null == array1) && (null == array2))
--- 127,131 ----
{
boolean ret;
!
ret = false;
if ((null == array1) && (null == array2))
***************
*** 139,143 ****
ret = false;
}
!
return (ret);
}
--- 139,143 ----
ret = false;
}
!
return (ret);
}
***************
*** 166,170 ****
mPropertySupport.removePropertyChangeListener (listener);
}
!
//
// Properties
--- 166,170 ----
mPropertySupport.removePropertyChangeListener (listener);
}
!
//
// Properties
***************
*** 218,222 ****
}
!
/**
* Getter for property URL.
--- 218,222 ----
}
!
/**
* Getter for property URL.
***************
*** 227,231 ****
return (mParser.getURL ());
}
!
/**
* Setter for property URL.
--- 227,231 ----
return (mParser.getURL ());
}
!
/**
* Setter for property URL.
***************
*** 235,239 ****
{
String old;
!
old = getURL ();
if (((null == old) && (null != url)) || ((null != old) && !old.equals (url)))
--- 235,239 ----
{
String old;
!
old = getURL ();
if (((null == old) && (null != url)) || ((null != old) && !old.equals (url)))
***************
*** 260,264 ****
return (mParser.getConnection ());
}
!
/**
* Setter for property Connection.
--- 260,264 ----
return (mParser.getConnection ());
}
!
/**
* Setter for property Connection.
Index: StringBean.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/StringBean.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** StringBean.java 8 Sep 2003 02:26:28 -0000 1.25
--- StringBean.java 10 Sep 2003 03:38:18 -0000 1.26
***************
*** 11,15 ****
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
--- 11,15 ----
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
! //
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
***************
*** 18,27 ****
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
--- 18,27 ----
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
! //
! // Postal Address :
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
! // 2583 Cedar Street, Berkeley,
// CA 94708, USA
// Website : http://www.industriallogic.com
***************
*** 116,120 ****
*/
protected String mStrings;
!
/**
* If <code>true</code> the link URLs are embedded in the text output.
--- 116,120 ----
*/
protected String mStrings;
!
/**
* If <code>true</code> the link URLs are embedded in the text output.
***************
*** 148,153 ****
*/
protected boolean mIsPre;
!
! /**
* Create a StringBean object.
* Default property values are set to 'do the right thing':
--- 148,153 ----
*/
protected boolean mIsPre;
!
! /**
* Create a StringBean object.
* Default property values are set to 'do the right thing':
***************
*** 183,187 ****
{
int length;
!
length = mBuffer.length ();
if ( (0 != length) // why bother appending newlines to the beginning of a buffer
--- 183,187 ----
{
int length;
!
length = mBuffer.length ();
if ( (0 != length) // why bother appending newlines to the beginning of a buffer
***************
*** 190,194 ****
mBuffer.append (newline);
}
!
/**
* Add the given text collapsing whitespace.
--- 190,194 ----
mBuffer.append (newline);
}
!
/**
* Add the given text collapsing whitespace.
***************
*** 217,221 ****
int state;
char character;
!
chars = string.length ();
if (0 != chars)
--- 217,221 ----
int state;
char character;
!
chars = string.length ();
if (0 != chars)
***************
*** 269,273 ****
ret = mBuffer.toString ();
mBuffer = null;
!
return (ret);
}
--- 269,273 ----
ret = mBuffer.toString ();
mBuffer = null;
!
return (ret);
}
***************
*** 361,365 ****
mPropertySupport.removePropertyChangeListener (listener);
}
!
//
// Properties
--- 361,365 ----
mPropertySupport.removePropertyChangeListener (listener);
}
!
//
// Properties
***************
*** 388,392 ****
return (mLinks);
}
!
/**
* Set the 'include links' state.
--- 388,392 ----
return (mLinks);
}
!
/**
* Set the 'include links' state.
***************
*** 406,410 ****
}
}
!
/**
* Get the current URL.
--- 406,410 ----
}
}
!
/**
* Get the current URL.
***************
*** 416,420 ****
return ((null != mParser) ? mParser.getURL () : null);
}
!
/**
* Set the URL to extract strings from.
--- 416,420 ----
return ((null != mParser) ? mParser.getURL () : null);
}
!
/**
* Set the URL to extract strings from.
***************
*** 427,431 ****
String old;
URLConnection conn;
!
old = getURL ();
conn = getConnection ();
--- 427,431 ----
String old;
URLConnection conn;
!
old = getURL ();
conn = getConnection ();
***************
*** 459,463 ****
return (mReplaceSpace);
}
!
/**
* Set the 'replace non breaking spaces' state.
--- 459,463 ----
return (mReplaceSpace);
}
!
/**
* Set the 'replace non breaking spaces' state.
***************
*** 496,500 ****
return (mCollapse);
}
!
/**
* Set the current 'collapse whitespace' state.
--- 496,500 ----
return (mCollapse);
}
!
/**
* Set the current 'collapse whitespace' state.
***************
*** 524,528 ****
return ((null != mParser) ? mParser.getConnection () : null);
}
!
/**
* Set the parser's connection.
--- 524,528 ----
return ((null != mParser) ? mParser.getConnection () : null);
}
!
/**
* Set the parser's connection.
***************
*** 535,539 ****
String url;
URLConnection conn;
!
url = getURL ();
conn = getConnection ();
--- 535,539 ----
String url;
URLConnection conn;
!
url = getURL ();
conn = getConnection ();
***************
*** 560,564 ****
// NodeVisitor overrides
//
!
/**
* Appends the link as text between angle brackets to the output.
--- 560,564 ----
// NodeVisitor overrides
//
!
/**
* Appends the link as text between angle brackets to the output.
***************
*** 613,617 ****
mIsScript = false;
}
!
/**
* Appends a newline to the output if the tag breaks flow, and
--- 613,617 ----
mIsScript = false;
}
!
/**
* Appends a newline to the output if the tag breaks flow, and
***************
*** 630,634 ****
carriage_return ();
}
!
/**
* Unit test.
--- 630,634 ----
carriage_return ();
}
!
/**
* Unit test.
Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/beans/package.html,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** package.html 8 Sep 2003 02:26:28 -0000 1.13
--- package.html 10 Sep 2003 03:38:18 -0000 1.14
***************
*** 18,22 ****
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
--- 18,22 ----
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
!
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
***************
*** 25,41 ****
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
</head>
<body bgcolor="white">
! The beans package contains Java Beans that can integrate within IDEs.
There are visual and non-visual beans, the former follow the naming
pattern HTMLxxx.
--- 25,41 ----
For any questions or suggestions, you can write to me at :
Email :so...@in...
!
! Postal Address :
Somik Raha
Extreme Programmer & Coach
Industrial Logic Corporation
! 2583 Cedar Street, Berkeley,
CA 94708, USA
Website : http://www.industriallogic.com
!
-->
</head>
<body bgcolor="white">
! The beans package contains Java Beans that can integrate within IDEs.
There are visual and non-visual beans, the former follow the naming
pattern HTMLxxx.
|
|
From: <der...@us...> - 2003-09-10 03:38:52
|
Update of /cvsroot/htmlparser/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv24483
Modified Files:
build.xml
Added Files:
htmlparser_checks.xml
Log Message:
Add style checking target to ant build script:
ant checkstyle
It uses a jar from http://checkstyle.sourceforge.net which is dropped in the lib directory.
The rules are in the file htmlparser_checks.xml in the src directory.
Added lexerapplications package with Tabby as the first app. It performs whitespace manipulation
on source files to follow the style rules. This reduced the number of style violations to roughly 14,000.
There are a few issues with the style checker that need to be resolved before it should be taken too seriously.
For example:
It thinks all method arguments should be final, even if they are modified by the code (which the compiler frowns on).
It complains about long lines, even when there is no possibility of wrapping the line, i.e. a URL in a comment
that's more than 80 characters long.
It considers all naked integers as 'magic numbers', even when they are obvious, i.e. the 4 corners of a box.
It complains about whitespace following braces, even in array initializers, i.e. X[][] = { {a, b} { } }
But it points out some really interesting things, even if you don't agree with the style guidelines,
so it's worth a look.
--- NEW FILE: htmlparser_checks.xml ---
<?xml version="1.0"?>
<!DOCTYPE module PUBLIC
"-//Puppy Crawl//DTD Check Configuration 1.1//EN"
"http://www.puppycrawl.com/dtds/configuration_1_1.dtd">
<!--
Checkstyle configuration that checks the sun coding conventions from:
- the Java Language Specification at
http://java.sun.com/docs/books/jls/second_edition/html/index.html
- the Sun Code Conventions at http://java.sun.com/docs/codeconv/
- the Javadoc guidelines at
http://java.sun.com/j2se/javadoc/writingdoccomments/index.html
- the JDK Api documentation http://java.sun.com/j2se/docs/api/index.html
- some best practices
Checkstyle is very configurable. Be sure to read the documentation at
http://checkstyle.sf.net (or in your downloaded distribution).
Most Checks are configurable, be sure to consult the documentation.
To completely disable a check, just comment it out or delete it from the file.
Finally, it is worth reading the documentation.
-->
<module name="Checker">
<!-- Checks that a package.html file exists for each package. -->
<!-- See http://checkstyle.sf.net/config_javadoc.html#PackageHtml -->
<module name="PackageHtml"/>
<!-- Checks whether files end with a new line. -->
<!-- See http://checkstyle.sf.net/config_misc.html#NewlineAtEndOfFile -->
<module name="NewlineAtEndOfFile"/>
<!-- Checks that property files contain the same keys. -->
<!-- See http://checkstyle.sf.net/config_misc.html#Translation -->
<module name="Translation"/>
<module name="TreeWalker">
<!-- Checks for Javadoc comments. -->
<!-- See http://checkstyle.sf.net/config_javadoc.html -->
<module name="JavadocMethod">
<property name="allowUndeclaredRTE" value="true"/>
</module>
<module name="JavadocType"/>
<module name="JavadocVariable"/>
<!-- Checks for Naming Conventions. -->
<!-- See http://checkstyle.sf.net/config_naming.html -->
<module name="ConstantName"/>
<module name="LocalFinalVariableName"/>
<module name="LocalVariableName"/>
<module name="MemberName"/>
<module name="MethodName"/>
<module name="PackageName"/>
<module name="ParameterName"/>
<module name="StaticVariableName"/>
<module name="TypeName"/>
<!-- Checks for Headers -->
<!-- See http://checkstyle.sf.net/config_header.html -->
<module name="RegexpHeader">
<!-- The follow property value demonstrates the ability -->
<!-- to have access to ANT properties. In this case it uses -->
<!-- the ${basedir} property to allow Checkstyle to be run -->
<!-- from any directory within a project. -->
<property name="headerFile" value="${basedir}/java.header"/>
</module>
<!-- Following interprets the header file as regular expressions. -->
<!-- <module name="RegexpHeader"/> -->
<!-- Checks for imports -->
<!-- See http://checkstyle.sf.net/config_import.html -->
<module name="AvoidStarImport"/>
<module name="IllegalImport"/> <!-- defaults to sun.* packages -->
<module name="RedundantImport"/>
<module name="UnusedImports"/>
<!-- Checks for Size Violations. -->
<!-- See http://checkstyle.sf.net/config_sizes.html -->
<module name="FileLength"/>
<module name="LineLength"/>
<module name="MethodLength"/>
<module name="ParameterNumber"/>
<!-- Checks for whitespace -->
<!-- See http://checkstyle.sf.net/config_whitespace.html -->
<module name="EmptyForIteratorPad"/>
<module name="NoWhitespaceAfter"/>
<module name="NoWhitespaceBefore"/>
<module name="OperatorWrap"/>
<module name="ParenPad"/>
<module name="TabCharacter"/>
<module name="WhitespaceAfter">
<property name="tokens" value="COMMA, SEMI"/>
</module>
<module name="WhitespaceAround"/>
<!-- Modifier Checks -->
<!-- See http://checkstyle.sf.net/config_modifiers.html -->
<module name="ModifierOrder"/>
<module name="RedundantModifier"/>
<!-- Checks for blocks. You know, those {}'s -->
<!-- See http://checkstyle.sf.net/config_blocks.html -->
<module name="AvoidNestedBlocks"/>
<module name="EmptyBlock"/>
<module name="LeftCurly">
<property name="option" value="nl"/>
</module>
<!-- module name="NeedBraces"/-->
<module name="RightCurly">
<property name="option" value="alone"/>
</module>
<!-- Checks for common coding problems -->
<!-- See http://checkstyle.sf.net/config_coding.html -->
<module name="AvoidInlineConditionals"/>
<module name="DoubleCheckedLocking"/> <!-- MY FAVOURITE -->
<module name="EmptyStatement"/>
<module name="EqualsHashCode"/>
<module name="HiddenField"/>
<module name="IllegalInstantiation"/>
<module name="InnerAssignment"/>
<module name="MagicNumber"/>
<module name="MissingSwitchDefault"/>
<!--module name="RedundantThrows"/-->
<module name="SimplifyBooleanExpression"/>
<module name="SimplifyBooleanReturn"/>
<!-- Checks for class design -->
<!-- See http://checkstyle.sf.net/config_design.html -->
<!--module name="DesignForExtension"/-->
<module name="FinalClass"/>
<module name="HideUtilityClassConstructor"/>
<module name="InterfaceIsType"/>
<module name="VisibilityModifier">
<property name="protectedAllowed" value="true"/>
</module>
<!-- Miscellaneous other checks. -->
<!-- See http://checkstyle.sf.net/config_misc.html -->
<module name="ArrayTypeStyle"/>
<module name="FinalParameters"/>
<module name="GenericIllegalRegexp">
<property name="format" value="\s+$"/>
<property name="message" value="Line has trailing spaces."/>
</module>
<module name="TodoComment"/>
<module name="UpperEll"/>
</module>
</module>
Index: build.xml
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/build.xml,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** build.xml 24 Aug 2003 21:59:40 -0000 1.45
--- build.xml 10 Sep 2003 03:38:17 -0000 1.46
***************
*** 91,94 ****
--- 91,104 ----
<property name="commons-logging.jar" value="lib/commons-logging.jar"/>
+ <taskdef resource="checkstyletask.properties"
+ classpath="lib/checkstyle-all-3.1.jar"/>
+
+ <target name="checkstyle" description="check source code adheres to coding standards">
+ <checkstyle config="./htmlparser_checks.xml">
+ <fileset dir="src" includes="**/*.java"/>
+ </checkstyle>
+ </target>
+
+
<target name="init" description="initialize version properties">
<echo message="**********************************"/>
|
|
From: <der...@us...> - 2003-09-10 03:08:28
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexerapplications/tabby In directory sc8-pr-cvs1:/tmp/cvs-serv20163/tabby Log Message: Directory /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexerapplications/tabby added to the repository |
|
From: <der...@us...> - 2003-09-10 03:08:14
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexerapplications In directory sc8-pr-cvs1:/tmp/cvs-serv20111/lexerapplications Log Message: Directory /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexerapplications added to the repository |
|
From: <der...@us...> - 2003-09-08 02:38:10
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/temporaryFailures Modified Files: AttributeParserTest.java TagParserTest.java Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AttributeParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures/AttributeParserTest.java,v retrieving revision 1.11 retrieving revision 1.12 diff -C2 -d -r1.11 -r1.12 *** AttributeParserTest.java 3 Sep 2003 23:36:22 -0000 1.11 --- AttributeParserTest.java 8 Sep 2003 02:26:31 -0000 1.12 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TagParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures/TagParserTest.java,v retrieving revision 1.9 retrieving revision 1.10 diff -C2 -d -r1.9 -r1.10 *** TagParserTest.java 3 Sep 2003 23:36:22 -0000 1.9 --- TagParserTest.java 8 Sep 2003 02:26:31 -0000 1.10 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/scannersTests Modified Files: AllTests.java AppletScannerTest.java BaseHREFScannerTest.java BodyScannerTest.java BulletListScannerTest.java BulletScannerTest.java CompositeTagScannerTest.java DivScannerTest.java FormScannerTest.java FrameScannerTest.java FrameSetScannerTest.java HeadScannerTest.java HtmlTest.java ImageScannerTest.java InputTagScannerTest.java JspScannerTest.java LabelScannerTest.java LinkScannerTest.java MetaTagScannerTest.java OptionTagScannerTest.java ScriptScannerTest.java SelectTagScannerTest.java SpanScannerTest.java StyleScannerTest.java TableScannerTest.java TagScannerTest.java TextareaTagScannerTest.java TitleScannerTest.java XmlEndTagScanningTest.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/AllTests.java,v retrieving revision 1.46 retrieving revision 1.47 diff -C2 -d -r1.46 -r1.47 *** AllTests.java 3 Sep 2003 23:36:21 -0000 1.46 --- AllTests.java 8 Sep 2003 02:26:31 -0000 1.47 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // *************** *** 19,23 **** // Email :so...@ki... // ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 19,23 ---- // Email :so...@ki... // ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: AppletScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/AppletScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** AppletScannerTest.java 1 Sep 2003 22:02:48 -0000 1.24 --- AppletScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BaseHREFScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/BaseHREFScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** BaseHREFScannerTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- BaseHREFScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BodyScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/BodyScannerTest.java,v retrieving revision 1.10 retrieving revision 1.11 diff -C2 -d -r1.10 -r1.11 *** BodyScannerTest.java 3 Sep 2003 23:36:21 -0000 1.10 --- BodyScannerTest.java 8 Sep 2003 02:26:31 -0000 1.11 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BulletListScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/BulletListScannerTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** BulletListScannerTest.java 3 Sep 2003 23:36:21 -0000 1.6 --- BulletListScannerTest.java 8 Sep 2003 02:26:31 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BulletScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/BulletScannerTest.java,v retrieving revision 1.7 retrieving revision 1.8 diff -C2 -d -r1.7 -r1.8 *** BulletScannerTest.java 3 Sep 2003 23:36:21 -0000 1.7 --- BulletScannerTest.java 8 Sep 2003 02:26:31 -0000 1.8 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CompositeTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/CompositeTagScannerTest.java,v retrieving revision 1.36 retrieving revision 1.37 diff -C2 -d -r1.36 -r1.37 *** CompositeTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.36 --- CompositeTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.37 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DivScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/DivScannerTest.java,v retrieving revision 1.30 retrieving revision 1.31 diff -C2 -d -r1.30 -r1.31 *** DivScannerTest.java 3 Sep 2003 23:36:21 -0000 1.30 --- DivScannerTest.java 8 Sep 2003 02:26:31 -0000 1.31 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FormScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FormScannerTest.java,v retrieving revision 1.30 retrieving revision 1.31 diff -C2 -d -r1.30 -r1.31 *** FormScannerTest.java 3 Sep 2003 23:36:21 -0000 1.30 --- FormScannerTest.java 8 Sep 2003 02:26:31 -0000 1.31 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FrameScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** FrameScannerTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- FrameScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameSetScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FrameSetScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** FrameSetScannerTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- FrameSetScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HeadScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/HeadScannerTest.java,v retrieving revision 1.14 retrieving revision 1.15 diff -C2 -d -r1.14 -r1.15 *** HeadScannerTest.java 3 Sep 2003 23:36:21 -0000 1.14 --- HeadScannerTest.java 8 Sep 2003 02:26:31 -0000 1.15 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HtmlTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/HtmlTest.java,v retrieving revision 1.8 retrieving revision 1.9 diff -C2 -d -r1.8 -r1.9 *** HtmlTest.java 3 Sep 2003 23:36:21 -0000 1.8 --- HtmlTest.java 8 Sep 2003 02:26:31 -0000 1.9 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ImageScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ImageScannerTest.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** ImageScannerTest.java 3 Sep 2003 23:36:21 -0000 1.28 --- ImageScannerTest.java 8 Sep 2003 02:26:31 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: InputTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/InputTagScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** InputTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- InputTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: JspScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/JspScannerTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** JspScannerTest.java 3 Sep 2003 23:36:21 -0000 1.25 --- JspScannerTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LabelScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/LabelScannerTest.java,v retrieving revision 1.33 retrieving revision 1.34 diff -C2 -d -r1.33 -r1.34 *** LabelScannerTest.java 3 Sep 2003 23:36:21 -0000 1.33 --- LabelScannerTest.java 8 Sep 2003 02:26:31 -0000 1.34 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LinkScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/LinkScannerTest.java,v retrieving revision 1.34 retrieving revision 1.35 diff -C2 -d -r1.34 -r1.35 *** LinkScannerTest.java 3 Sep 2003 23:36:21 -0000 1.34 --- LinkScannerTest.java 8 Sep 2003 02:26:31 -0000 1.35 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: MetaTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/MetaTagScannerTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** MetaTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.25 --- MetaTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: OptionTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/OptionTagScannerTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** OptionTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.26 --- OptionTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ScriptScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ScriptScannerTest.java,v retrieving revision 1.37 retrieving revision 1.38 diff -C2 -d -r1.37 -r1.38 *** ScriptScannerTest.java 3 Sep 2003 23:36:21 -0000 1.37 --- ScriptScannerTest.java 8 Sep 2003 02:26:31 -0000 1.38 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SelectTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/SelectTagScannerTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** SelectTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.26 --- SelectTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SpanScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/SpanScannerTest.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** SpanScannerTest.java 3 Sep 2003 23:36:21 -0000 1.27 --- SpanScannerTest.java 8 Sep 2003 02:26:31 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: StyleScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/StyleScannerTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** StyleScannerTest.java 3 Sep 2003 23:36:21 -0000 1.25 --- StyleScannerTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TableScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TableScannerTest.java,v retrieving revision 1.32 retrieving revision 1.33 diff -C2 -d -r1.32 -r1.33 *** TableScannerTest.java 3 Sep 2003 23:36:21 -0000 1.32 --- TableScannerTest.java 8 Sep 2003 02:26:31 -0000 1.33 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TagScannerTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** TagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.26 --- TagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TextareaTagScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TextareaTagScannerTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** TextareaTagScannerTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- TextareaTagScannerTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TitleScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TitleScannerTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** TitleScannerTest.java 3 Sep 2003 23:36:21 -0000 1.25 --- TitleScannerTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: XmlEndTagScanningTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/XmlEndTagScanningTest.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** XmlEndTagScanningTest.java 3 Sep 2003 23:36:21 -0000 1.27 --- XmlEndTagScanningTest.java 8 Sep 2003 02:26:31 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:44 -0000 1.12 --- package.html 8 Sep 2003 02:26:31 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/tagTests Modified Files: AllTests.java AppletTagTest.java BaseHrefTagTest.java BodyTagTest.java CompositeTagTest.java DoctypeTagTest.java EndTagTest.java FormTagTest.java FrameSetTagTest.java FrameTagTest.java ImageTagTest.java InputTagTest.java JspTagTest.java LinkTagTest.java MetaTagTest.java ObjectCollectionTest.java OptionTagTest.java ScriptTagTest.java SelectTagTest.java StyleTagTest.java TagTest.java TextareaTagTest.java TitleTagTest.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/AllTests.java,v retrieving revision 1.41 retrieving revision 1.42 diff -C2 -d -r1.41 -r1.42 *** AllTests.java 3 Sep 2003 23:36:21 -0000 1.41 --- AllTests.java 8 Sep 2003 02:26:31 -0000 1.42 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: AppletTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** AppletTagTest.java 1 Sep 2003 19:11:57 -0000 1.25 --- AppletTagTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BaseHrefTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/BaseHrefTagTest.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** BaseHrefTagTest.java 3 Sep 2003 23:36:21 -0000 1.24 --- BaseHrefTagTest.java 8 Sep 2003 02:26:31 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BodyTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/BodyTagTest.java,v retrieving revision 1.10 retrieving revision 1.11 diff -C2 -d -r1.10 -r1.11 *** BodyTagTest.java 3 Sep 2003 23:36:21 -0000 1.10 --- BodyTagTest.java 8 Sep 2003 02:26:31 -0000 1.11 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CompositeTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/CompositeTagTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** CompositeTagTest.java 3 Sep 2003 23:36:21 -0000 1.6 --- CompositeTagTest.java 8 Sep 2003 02:26:31 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DoctypeTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/DoctypeTagTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** DoctypeTagTest.java 3 Sep 2003 23:36:21 -0000 1.25 --- DoctypeTagTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: EndTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/EndTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** EndTagTest.java 3 Sep 2003 23:36:21 -0000 1.26 --- EndTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FormTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FormTagTest.java,v retrieving revision 1.29 retrieving revision 1.30 diff -C2 -d -r1.29 -r1.30 *** FormTagTest.java 3 Sep 2003 23:36:21 -0000 1.29 --- FormTagTest.java 8 Sep 2003 02:26:31 -0000 1.30 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameSetTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FrameSetTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** FrameSetTagTest.java 3 Sep 2003 23:36:21 -0000 1.26 --- FrameSetTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FrameTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** FrameTagTest.java 3 Sep 2003 23:36:22 -0000 1.26 --- FrameTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ImageTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/ImageTagTest.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** ImageTagTest.java 1 Sep 2003 21:41:28 -0000 1.28 --- ImageTagTest.java 8 Sep 2003 02:26:31 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: InputTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/InputTagTest.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** InputTagTest.java 3 Sep 2003 23:36:22 -0000 1.28 --- InputTagTest.java 8 Sep 2003 02:26:31 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: JspTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/JspTagTest.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** JspTagTest.java 1 Sep 2003 21:53:33 -0000 1.28 --- JspTagTest.java 8 Sep 2003 02:26:31 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LinkTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/LinkTagTest.java,v retrieving revision 1.31 retrieving revision 1.32 diff -C2 -d -r1.31 -r1.32 *** LinkTagTest.java 1 Sep 2003 21:28:33 -0000 1.31 --- LinkTagTest.java 8 Sep 2003 02:26:31 -0000 1.32 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: MetaTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/MetaTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** MetaTagTest.java 3 Sep 2003 23:36:22 -0000 1.26 --- MetaTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ObjectCollectionTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/ObjectCollectionTest.java,v retrieving revision 1.10 retrieving revision 1.11 diff -C2 -d -r1.10 -r1.11 *** ObjectCollectionTest.java 3 Sep 2003 23:36:22 -0000 1.10 --- ObjectCollectionTest.java 8 Sep 2003 02:26:31 -0000 1.11 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: OptionTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/OptionTagTest.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** OptionTagTest.java 3 Sep 2003 23:36:22 -0000 1.27 --- OptionTagTest.java 8 Sep 2003 02:26:31 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ScriptTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/ScriptTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** ScriptTagTest.java 3 Sep 2003 23:36:22 -0000 1.26 --- ScriptTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SelectTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/SelectTagTest.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** SelectTagTest.java 3 Sep 2003 23:36:22 -0000 1.28 --- SelectTagTest.java 8 Sep 2003 02:26:31 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: StyleTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/StyleTagTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** StyleTagTest.java 3 Sep 2003 23:36:22 -0000 1.25 --- StyleTagTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java,v retrieving revision 1.40 retrieving revision 1.41 diff -C2 -d -r1.40 -r1.41 *** TagTest.java 3 Sep 2003 23:36:22 -0000 1.40 --- TagTest.java 8 Sep 2003 02:26:31 -0000 1.41 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TextareaTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TextareaTagTest.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** TextareaTagTest.java 3 Sep 2003 23:36:22 -0000 1.26 --- TextareaTagTest.java 8 Sep 2003 02:26:31 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TitleTagTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TitleTagTest.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** TitleTagTest.java 3 Sep 2003 23:36:22 -0000 1.25 --- TitleTagTest.java 8 Sep 2003 02:26:31 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:44 -0000 1.12 --- package.html 8 Sep 2003 02:26:31 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
|
From: <der...@us...> - 2003-09-08 02:38:09
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/utilTests Modified Files: AllTests.java BeanTest.java CharacterTranslationTest.java HTMLLinkProcessorTest.java HTMLParserUtilsTest.java HTMLTagParserTest.java NodeListTest.java SortTest.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/AllTests.java,v retrieving revision 1.45 retrieving revision 1.46 diff -C2 -d -r1.45 -r1.46 *** AllTests.java 3 Sep 2003 23:36:22 -0000 1.45 --- AllTests.java 8 Sep 2003 02:26:31 -0000 1.46 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BeanTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v retrieving revision 1.39 retrieving revision 1.40 diff -C2 -d -r1.39 -r1.40 *** BeanTest.java 3 Sep 2003 23:36:22 -0000 1.39 --- BeanTest.java 8 Sep 2003 02:26:32 -0000 1.40 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CharacterTranslationTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java,v retrieving revision 1.29 retrieving revision 1.30 diff -C2 -d -r1.29 -r1.30 *** CharacterTranslationTest.java 3 Sep 2003 23:36:22 -0000 1.29 --- CharacterTranslationTest.java 8 Sep 2003 02:26:32 -0000 1.30 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HTMLLinkProcessorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/HTMLLinkProcessorTest.java,v retrieving revision 1.43 retrieving revision 1.44 diff -C2 -d -r1.43 -r1.44 *** HTMLLinkProcessorTest.java 3 Sep 2003 23:36:22 -0000 1.43 --- HTMLLinkProcessorTest.java 8 Sep 2003 02:26:32 -0000 1.44 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HTMLParserUtilsTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/HTMLParserUtilsTest.java,v retrieving revision 1.7 retrieving revision 1.8 diff -C2 -d -r1.7 -r1.8 *** HTMLParserUtilsTest.java 3 Sep 2003 23:36:22 -0000 1.7 --- HTMLParserUtilsTest.java 8 Sep 2003 02:26:32 -0000 1.8 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HTMLTagParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/HTMLTagParserTest.java,v retrieving revision 1.42 retrieving revision 1.43 diff -C2 -d -r1.42 -r1.43 *** HTMLTagParserTest.java 3 Sep 2003 23:36:22 -0000 1.42 --- HTMLTagParserTest.java 8 Sep 2003 02:26:32 -0000 1.43 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: NodeListTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/NodeListTest.java,v retrieving revision 1.15 retrieving revision 1.16 diff -C2 -d -r1.15 -r1.16 *** NodeListTest.java 3 Sep 2003 23:36:22 -0000 1.15 --- NodeListTest.java 8 Sep 2003 02:26:32 -0000 1.16 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SortTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/SortTest.java,v retrieving revision 1.3 retrieving revision 1.4 diff -C2 -d -r1.3 -r1.4 *** SortTest.java 24 Aug 2003 21:59:44 -0000 1.3 --- SortTest.java 8 Sep 2003 02:26:32 -0000 1.4 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:44 -0000 1.12 --- package.html 8 Sep 2003 02:26:32 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
|
From: <der...@us...> - 2003-09-08 02:38:07
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/visitorsTests Modified Files: AllTests.java CompositeTagFindingVisitorTest.java HtmlPageTest.java LinkFindingVisitorTest.java NodeVisitorTest.java StringFindingVisitorTest.java TagFindingVisitorTest.java TextExtractingVisitorTest.java UrlModifyingVisitorTest.java Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/AllTests.java,v retrieving revision 1.33 retrieving revision 1.34 diff -C2 -d -r1.33 -r1.34 *** AllTests.java 3 Sep 2003 23:36:22 -0000 1.33 --- AllTests.java 8 Sep 2003 02:26:32 -0000 1.34 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CompositeTagFindingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/CompositeTagFindingVisitorTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** CompositeTagFindingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.6 --- CompositeTagFindingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HtmlPageTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/HtmlPageTest.java,v retrieving revision 1.9 retrieving revision 1.10 diff -C2 -d -r1.9 -r1.10 *** HtmlPageTest.java 3 Sep 2003 23:36:22 -0000 1.9 --- HtmlPageTest.java 8 Sep 2003 02:26:32 -0000 1.10 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LinkFindingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/LinkFindingVisitorTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** LinkFindingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.6 --- LinkFindingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: NodeVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/NodeVisitorTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** NodeVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.6 --- NodeVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: StringFindingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/StringFindingVisitorTest.java,v retrieving revision 1.8 retrieving revision 1.9 diff -C2 -d -r1.8 -r1.9 *** StringFindingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.8 --- StringFindingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.9 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TagFindingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/TagFindingVisitorTest.java,v retrieving revision 1.9 retrieving revision 1.10 diff -C2 -d -r1.9 -r1.10 *** TagFindingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.9 --- TagFindingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.10 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TextExtractingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/TextExtractingVisitorTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** TextExtractingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.6 --- TextExtractingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: UrlModifyingVisitorTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/UrlModifyingVisitorTest.java,v retrieving revision 1.6 retrieving revision 1.7 diff -C2 -d -r1.6 -r1.7 *** UrlModifyingVisitorTest.java 3 Sep 2003 23:36:22 -0000 1.6 --- UrlModifyingVisitorTest.java 8 Sep 2003 02:26:32 -0000 1.7 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/util Modified Files: ChainedException.java CommandLine.java DefaultParserFeedback.java FeedbackManager.java Generate.java IteratorImpl.java LinkProcessor.java NodeIterator.java NodeList.java ParserException.java ParserFeedback.java ParserUtils.java PeekingIterator.java SimpleNodeIterator.java Translate.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: ChainedException.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ChainedException.java,v retrieving revision 1.37 retrieving revision 1.38 diff -C2 -d -r1.37 -r1.38 *** ChainedException.java 24 Aug 2003 21:59:44 -0000 1.37 --- ChainedException.java 8 Sep 2003 02:26:32 -0000 1.38 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CommandLine.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/CommandLine.java,v retrieving revision 1.35 retrieving revision 1.36 diff -C2 -d -r1.35 -r1.36 *** CommandLine.java 24 Aug 2003 21:59:44 -0000 1.35 --- CommandLine.java 8 Sep 2003 02:26:33 -0000 1.36 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DefaultParserFeedback.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/DefaultParserFeedback.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** DefaultParserFeedback.java 3 Sep 2003 23:36:22 -0000 1.24 --- DefaultParserFeedback.java 8 Sep 2003 02:26:33 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FeedbackManager.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/FeedbackManager.java,v retrieving revision 1.37 retrieving revision 1.38 diff -C2 -d -r1.37 -r1.38 *** FeedbackManager.java 24 Aug 2003 21:59:44 -0000 1.37 --- FeedbackManager.java 8 Sep 2003 02:26:33 -0000 1.38 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: Generate.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Generate.java,v retrieving revision 1.39 retrieving revision 1.40 diff -C2 -d -r1.39 -r1.40 *** Generate.java 24 Aug 2003 21:59:44 -0000 1.39 --- Generate.java 8 Sep 2003 02:26:33 -0000 1.40 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: IteratorImpl.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/IteratorImpl.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** IteratorImpl.java 24 Aug 2003 21:59:45 -0000 1.25 --- IteratorImpl.java 8 Sep 2003 02:26:33 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LinkProcessor.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/LinkProcessor.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** LinkProcessor.java 3 Sep 2003 23:36:22 -0000 1.24 --- LinkProcessor.java 8 Sep 2003 02:26:33 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: NodeIterator.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeIterator.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** NodeIterator.java 3 Sep 2003 23:36:22 -0000 1.25 --- NodeIterator.java 8 Sep 2003 02:26:33 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: NodeList.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeList.java,v retrieving revision 1.41 retrieving revision 1.42 diff -C2 -d -r1.41 -r1.42 *** NodeList.java 3 Sep 2003 23:36:22 -0000 1.41 --- NodeList.java 8 Sep 2003 02:26:33 -0000 1.42 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ParserException.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserException.java,v retrieving revision 1.22 retrieving revision 1.23 diff -C2 -d -r1.22 -r1.23 *** ParserException.java 24 Aug 2003 21:59:45 -0000 1.22 --- ParserException.java 8 Sep 2003 02:26:33 -0000 1.23 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ParserFeedback.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserFeedback.java,v retrieving revision 1.23 retrieving revision 1.24 diff -C2 -d -r1.23 -r1.24 *** ParserFeedback.java 24 Aug 2003 21:59:45 -0000 1.23 --- ParserFeedback.java 8 Sep 2003 02:26:33 -0000 1.24 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ParserUtils.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserUtils.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** ParserUtils.java 3 Sep 2003 23:36:22 -0000 1.27 --- ParserUtils.java 8 Sep 2003 02:26:33 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: PeekingIterator.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/PeekingIterator.java,v retrieving revision 1.13 retrieving revision 1.14 diff -C2 -d -r1.13 -r1.14 *** PeekingIterator.java 3 Sep 2003 23:36:22 -0000 1.13 --- PeekingIterator.java 8 Sep 2003 02:26:33 -0000 1.14 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SimpleNodeIterator.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/SimpleNodeIterator.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** SimpleNodeIterator.java 3 Sep 2003 23:36:22 -0000 1.27 --- SimpleNodeIterator.java 8 Sep 2003 02:26:33 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: Translate.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Translate.java,v retrieving revision 1.33 retrieving revision 1.34 diff -C2 -d -r1.33 -r1.34 *** Translate.java 3 Sep 2003 23:36:22 -0000 1.33 --- Translate.java 8 Sep 2003 02:26:33 -0000 1.34 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:45 -0000 1.12 --- package.html 8 Sep 2003 02:26:33 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/parserHelperTests Modified Files: AllTests.java CompositeTagScannerHelperTest.java RemarkNodeParserTest.java StringParserTest.java Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/AllTests.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** AllTests.java 3 Sep 2003 23:36:21 -0000 1.25 --- AllTests.java 8 Sep 2003 02:26:30 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CompositeTagScannerHelperTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/CompositeTagScannerHelperTest.java,v retrieving revision 1.18 retrieving revision 1.19 diff -C2 -d -r1.18 -r1.19 *** CompositeTagScannerHelperTest.java 3 Sep 2003 23:36:21 -0000 1.18 --- CompositeTagScannerHelperTest.java 8 Sep 2003 02:26:31 -0000 1.19 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: RemarkNodeParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/RemarkNodeParserTest.java,v retrieving revision 1.33 retrieving revision 1.34 diff -C2 -d -r1.33 -r1.34 *** RemarkNodeParserTest.java 1 Sep 2003 19:55:59 -0000 1.33 --- RemarkNodeParserTest.java 8 Sep 2003 02:26:31 -0000 1.34 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: StringParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/StringParserTest.java,v retrieving revision 1.35 retrieving revision 1.36 diff -C2 -d -r1.35 -r1.36 *** StringParserTest.java 3 Sep 2003 23:36:21 -0000 1.35 --- StringParserTest.java 8 Sep 2003 02:26:31 -0000 1.36 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // |
|
From: <der...@us...> - 2003-09-08 02:38:05
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/sort In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/util/sort Modified Files: Ordered.java Sort.java Sortable.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: Ordered.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/sort/Ordered.java,v retrieving revision 1.4 retrieving revision 1.5 diff -C2 -d -r1.4 -r1.5 *** Ordered.java 3 Sep 2003 23:36:22 -0000 1.4 --- Ordered.java 8 Sep 2003 02:26:33 -0000 1.5 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: Sort.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/sort/Sort.java,v retrieving revision 1.4 retrieving revision 1.5 diff -C2 -d -r1.4 -r1.5 *** Sort.java 3 Sep 2003 23:36:22 -0000 1.4 --- Sort.java 8 Sep 2003 02:26:33 -0000 1.5 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: Sortable.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/sort/Sortable.java,v retrieving revision 1.4 retrieving revision 1.5 diff -C2 -d -r1.4 -r1.5 *** Sortable.java 3 Sep 2003 23:36:22 -0000 1.4 --- Sortable.java 8 Sep 2003 02:26:33 -0000 1.5 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/sort/package.html,v retrieving revision 1.3 retrieving revision 1.4 diff -C2 -d -r1.3 -r1.4 *** package.html 24 Aug 2003 21:59:45 -0000 1.3 --- package.html 8 Sep 2003 02:26:33 -0000 1.4 *************** *** 5,11 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 5,11 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests/nodeDecoratorTests Modified Files: AllTests.java DecodingNodeTest.java EscapeCharacterRemovingNodeTest.java NonBreakingSpaceConvertingNodeTest.java Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/AllTests.java,v retrieving revision 1.8 retrieving revision 1.9 diff -C2 -d -r1.8 -r1.9 *** AllTests.java 3 Sep 2003 23:36:21 -0000 1.8 --- AllTests.java 8 Sep 2003 02:26:30 -0000 1.9 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DecodingNodeTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/DecodingNodeTest.java,v retrieving revision 1.9 retrieving revision 1.10 diff -C2 -d -r1.9 -r1.10 *** DecodingNodeTest.java 3 Sep 2003 23:36:21 -0000 1.9 --- DecodingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.10 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: EscapeCharacterRemovingNodeTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/EscapeCharacterRemovingNodeTest.java,v retrieving revision 1.9 retrieving revision 1.10 diff -C2 -d -r1.9 -r1.10 *** EscapeCharacterRemovingNodeTest.java 3 Sep 2003 23:36:21 -0000 1.9 --- EscapeCharacterRemovingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.10 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: NonBreakingSpaceConvertingNodeTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/NonBreakingSpaceConvertingNodeTest.java,v retrieving revision 1.8 retrieving revision 1.9 diff -C2 -d -r1.8 -r1.9 *** NonBreakingSpaceConvertingNodeTest.java 3 Sep 2003 23:36:21 -0000 1.8 --- NonBreakingSpaceConvertingNodeTest.java 8 Sep 2003 02:26:30 -0000 1.9 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // |
|
From: <der...@us...> - 2003-09-08 02:27:34
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/tests Modified Files: AllTests.java AssertXmlEqualsTest.java BadTagIdentifier.java FunctionalTests.java InstanceofPerformanceTest.java LineNumberAssignedByNodeReaderTest.java ParserTest.java ParserTestCase.java PerformanceTest.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AllTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/AllTests.java,v retrieving revision 1.48 retrieving revision 1.49 diff -C2 -d -r1.48 -r1.49 *** AllTests.java 3 Sep 2003 23:36:20 -0000 1.48 --- AllTests.java 8 Sep 2003 02:26:30 -0000 1.49 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: AssertXmlEqualsTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/AssertXmlEqualsTest.java,v retrieving revision 1.10 retrieving revision 1.11 diff -C2 -d -r1.10 -r1.11 *** AssertXmlEqualsTest.java 3 Sep 2003 23:36:20 -0000 1.10 --- AssertXmlEqualsTest.java 8 Sep 2003 02:26:30 -0000 1.11 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BadTagIdentifier.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/BadTagIdentifier.java,v retrieving revision 1.10 retrieving revision 1.11 diff -C2 -d -r1.10 -r1.11 *** BadTagIdentifier.java 3 Sep 2003 23:36:20 -0000 1.10 --- BadTagIdentifier.java 8 Sep 2003 02:26:30 -0000 1.11 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FunctionalTests.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/FunctionalTests.java,v retrieving revision 1.41 retrieving revision 1.42 diff -C2 -d -r1.41 -r1.42 *** FunctionalTests.java 3 Sep 2003 23:36:20 -0000 1.41 --- FunctionalTests.java 8 Sep 2003 02:26:30 -0000 1.42 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: InstanceofPerformanceTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/InstanceofPerformanceTest.java,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** InstanceofPerformanceTest.java 3 Sep 2003 23:36:20 -0000 1.12 --- InstanceofPerformanceTest.java 8 Sep 2003 02:26:30 -0000 1.13 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LineNumberAssignedByNodeReaderTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/LineNumberAssignedByNodeReaderTest.java,v retrieving revision 1.19 retrieving revision 1.20 diff -C2 -d -r1.19 -r1.20 *** LineNumberAssignedByNodeReaderTest.java 3 Sep 2003 23:36:20 -0000 1.19 --- LineNumberAssignedByNodeReaderTest.java 8 Sep 2003 02:26:30 -0000 1.20 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ParserTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTest.java,v retrieving revision 1.39 retrieving revision 1.40 diff -C2 -d -r1.39 -r1.40 *** ParserTest.java 3 Sep 2003 23:36:20 -0000 1.39 --- ParserTest.java 8 Sep 2003 02:26:30 -0000 1.40 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ParserTestCase.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTestCase.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** ParserTestCase.java 3 Sep 2003 23:36:20 -0000 1.25 --- ParserTestCase.java 8 Sep 2003 02:26:30 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: PerformanceTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/PerformanceTest.java,v retrieving revision 1.39 retrieving revision 1.40 diff -C2 -d -r1.39 -r1.40 *** PerformanceTest.java 3 Sep 2003 23:36:20 -0000 1.39 --- PerformanceTest.java 8 Sep 2003 02:26:30 -0000 1.40 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:43 -0000 1.12 --- package.html 8 Sep 2003 02:26:30 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners In directory sc8-pr-cvs1:/tmp/cvs-serv7654/src/org/htmlparser/scanners Modified Files: AppletScanner.java BaseHrefScanner.java BodyScanner.java BulletListScanner.java BulletScanner.java CompositeTagScanner.java DivScanner.java DoctypeScanner.java FormScanner.java FrameScanner.java FrameSetScanner.java HeadScanner.java HtmlScanner.java ImageScanner.java InputTagScanner.java JspScanner.java LabelScanner.java LinkScanner.java MetaTagScanner.java OptionTagScanner.java ScriptScanner.java SelectTagScanner.java SpanScanner.java StyleScanner.java TableColumnScanner.java TableRowScanner.java TableScanner.java TagScanner.java TextareaTagScanner.java TitleScanner.java package.html Log Message: Update version headers to 1.4-20030907 and update changelog. Index: AppletScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/AppletScanner.java,v retrieving revision 1.29 retrieving revision 1.30 diff -C2 -d -r1.29 -r1.30 *** AppletScanner.java 3 Sep 2003 23:36:19 -0000 1.29 --- AppletScanner.java 8 Sep 2003 02:26:29 -0000 1.30 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BaseHrefScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/BaseHrefScanner.java,v retrieving revision 1.23 retrieving revision 1.24 diff -C2 -d -r1.23 -r1.24 *** BaseHrefScanner.java 3 Sep 2003 23:36:19 -0000 1.23 --- BaseHrefScanner.java 8 Sep 2003 02:26:29 -0000 1.24 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BodyScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/BodyScanner.java,v retrieving revision 1.15 retrieving revision 1.16 diff -C2 -d -r1.15 -r1.16 *** BodyScanner.java 3 Sep 2003 23:36:19 -0000 1.15 --- BodyScanner.java 8 Sep 2003 02:26:29 -0000 1.16 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BulletListScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/BulletListScanner.java,v retrieving revision 1.14 retrieving revision 1.15 diff -C2 -d -r1.14 -r1.15 *** BulletListScanner.java 3 Sep 2003 23:36:19 -0000 1.14 --- BulletListScanner.java 8 Sep 2003 02:26:29 -0000 1.15 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: BulletScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/BulletScanner.java,v retrieving revision 1.19 retrieving revision 1.20 diff -C2 -d -r1.19 -r1.20 *** BulletScanner.java 3 Sep 2003 23:36:19 -0000 1.19 --- BulletScanner.java 8 Sep 2003 02:26:29 -0000 1.20 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: CompositeTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/CompositeTagScanner.java,v retrieving revision 1.64 retrieving revision 1.65 diff -C2 -d -r1.64 -r1.65 *** CompositeTagScanner.java 3 Sep 2003 23:36:19 -0000 1.64 --- CompositeTagScanner.java 8 Sep 2003 02:26:29 -0000 1.65 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DivScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/DivScanner.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** DivScanner.java 3 Sep 2003 23:36:19 -0000 1.27 --- DivScanner.java 8 Sep 2003 02:26:29 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: DoctypeScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/DoctypeScanner.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** DoctypeScanner.java 3 Sep 2003 23:36:19 -0000 1.24 --- DoctypeScanner.java 8 Sep 2003 02:26:29 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FormScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/FormScanner.java,v retrieving revision 1.42 retrieving revision 1.43 diff -C2 -d -r1.42 -r1.43 *** FormScanner.java 3 Sep 2003 23:36:19 -0000 1.42 --- FormScanner.java 8 Sep 2003 02:26:29 -0000 1.43 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/FrameScanner.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** FrameScanner.java 3 Sep 2003 23:36:19 -0000 1.26 --- FrameScanner.java 8 Sep 2003 02:26:29 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: FrameSetScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/FrameSetScanner.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** FrameSetScanner.java 3 Sep 2003 23:36:19 -0000 1.25 --- FrameSetScanner.java 8 Sep 2003 02:26:29 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HeadScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/HeadScanner.java,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** HeadScanner.java 3 Sep 2003 23:36:19 -0000 1.12 --- HeadScanner.java 8 Sep 2003 02:26:29 -0000 1.13 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: HtmlScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/HtmlScanner.java,v retrieving revision 1.27 retrieving revision 1.28 diff -C2 -d -r1.27 -r1.28 *** HtmlScanner.java 3 Sep 2003 23:36:19 -0000 1.27 --- HtmlScanner.java 8 Sep 2003 02:26:29 -0000 1.28 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ImageScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ImageScanner.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** ImageScanner.java 3 Sep 2003 23:36:20 -0000 1.25 --- ImageScanner.java 8 Sep 2003 02:26:29 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: InputTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/InputTagScanner.java,v retrieving revision 1.23 retrieving revision 1.24 diff -C2 -d -r1.23 -r1.24 *** InputTagScanner.java 3 Sep 2003 23:36:20 -0000 1.23 --- InputTagScanner.java 8 Sep 2003 02:26:29 -0000 1.24 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: JspScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/JspScanner.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** JspScanner.java 3 Sep 2003 23:36:20 -0000 1.24 --- JspScanner.java 8 Sep 2003 02:26:29 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LabelScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/LabelScanner.java,v retrieving revision 1.30 retrieving revision 1.31 diff -C2 -d -r1.30 -r1.31 *** LabelScanner.java 3 Sep 2003 23:36:20 -0000 1.30 --- LabelScanner.java 8 Sep 2003 02:26:29 -0000 1.31 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: LinkScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/LinkScanner.java,v retrieving revision 1.50 retrieving revision 1.51 diff -C2 -d -r1.50 -r1.51 *** LinkScanner.java 3 Sep 2003 23:36:20 -0000 1.50 --- LinkScanner.java 8 Sep 2003 02:26:29 -0000 1.51 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: MetaTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/MetaTagScanner.java,v retrieving revision 1.23 retrieving revision 1.24 diff -C2 -d -r1.23 -r1.24 *** MetaTagScanner.java 3 Sep 2003 23:36:20 -0000 1.23 --- MetaTagScanner.java 8 Sep 2003 02:26:29 -0000 1.24 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: OptionTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/OptionTagScanner.java,v retrieving revision 1.30 retrieving revision 1.31 diff -C2 -d -r1.30 -r1.31 *** OptionTagScanner.java 3 Sep 2003 23:36:20 -0000 1.30 --- OptionTagScanner.java 8 Sep 2003 02:26:29 -0000 1.31 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: ScriptScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/ScriptScanner.java,v retrieving revision 1.36 retrieving revision 1.37 diff -C2 -d -r1.36 -r1.37 *** ScriptScanner.java 3 Sep 2003 23:36:20 -0000 1.36 --- ScriptScanner.java 8 Sep 2003 02:26:29 -0000 1.37 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SelectTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/SelectTagScanner.java,v retrieving revision 1.28 retrieving revision 1.29 diff -C2 -d -r1.28 -r1.29 *** SelectTagScanner.java 3 Sep 2003 23:36:20 -0000 1.28 --- SelectTagScanner.java 8 Sep 2003 02:26:29 -0000 1.29 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: SpanScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/SpanScanner.java,v retrieving revision 1.29 retrieving revision 1.30 diff -C2 -d -r1.29 -r1.30 *** SpanScanner.java 3 Sep 2003 23:36:20 -0000 1.29 --- SpanScanner.java 8 Sep 2003 02:26:29 -0000 1.30 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: StyleScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/StyleScanner.java,v retrieving revision 1.24 retrieving revision 1.25 diff -C2 -d -r1.24 -r1.25 *** StyleScanner.java 3 Sep 2003 23:36:20 -0000 1.24 --- StyleScanner.java 8 Sep 2003 02:26:29 -0000 1.25 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TableColumnScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TableColumnScanner.java,v retrieving revision 1.32 retrieving revision 1.33 diff -C2 -d -r1.32 -r1.33 *** TableColumnScanner.java 3 Sep 2003 23:36:20 -0000 1.32 --- TableColumnScanner.java 8 Sep 2003 02:26:29 -0000 1.33 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TableRowScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TableRowScanner.java,v retrieving revision 1.35 retrieving revision 1.36 diff -C2 -d -r1.35 -r1.36 *** TableRowScanner.java 3 Sep 2003 23:36:20 -0000 1.35 --- TableRowScanner.java 8 Sep 2003 02:26:29 -0000 1.36 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TableScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TableScanner.java,v retrieving revision 1.34 retrieving revision 1.35 diff -C2 -d -r1.34 -r1.35 *** TableScanner.java 3 Sep 2003 23:36:20 -0000 1.34 --- TableScanner.java 8 Sep 2003 02:26:29 -0000 1.35 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TagScanner.java,v retrieving revision 1.37 retrieving revision 1.38 diff -C2 -d -r1.37 -r1.38 *** TagScanner.java 3 Sep 2003 23:36:20 -0000 1.37 --- TagScanner.java 8 Sep 2003 02:26:29 -0000 1.38 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TextareaTagScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TextareaTagScanner.java,v retrieving revision 1.25 retrieving revision 1.26 diff -C2 -d -r1.25 -r1.26 *** TextareaTagScanner.java 3 Sep 2003 23:36:20 -0000 1.25 --- TextareaTagScanner.java 8 Sep 2003 02:26:29 -0000 1.26 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: TitleScanner.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/TitleScanner.java,v retrieving revision 1.26 retrieving revision 1.27 diff -C2 -d -r1.26 -r1.27 *** TitleScanner.java 3 Sep 2003 23:36:20 -0000 1.26 --- TitleScanner.java 8 Sep 2003 02:26:29 -0000 1.27 *************** *** 1,3 **** ! // HTMLParser Library v1_4_20030824 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // --- 1,3 ---- ! // HTMLParser Library v1_4_20030907 - A java-based parser for HTML // Copyright (C) Dec 31, 2000 Somik Raha // Index: package.html =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/scanners/package.html,v retrieving revision 1.12 retrieving revision 1.13 diff -C2 -d -r1.12 -r1.13 *** package.html 24 Aug 2003 21:59:42 -0000 1.12 --- package.html 8 Sep 2003 02:26:29 -0000 1.13 *************** *** 4,10 **** <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030824 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha --- 4,10 ---- <!-- ! @(#)package.html 1.60 98/01/27 ! HTMLParser Library v1_4_20030907 - A java-based parser for HTML Copyright (C) Dec 31, 2000 Somik Raha |
1 message has been excluded from this view by a project administrator.
