Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv30508/src/org/htmlparser/lexer
Modified Files:
Lexer.java InputStreamSource.java
Log Message:
Apply patch #1247128 Bug Fix: #1227213 Particular SCRIPT tags close too late
from Keiron McCammon.
Index: InputStreamSource.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/InputStreamSource.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** InputStreamSource.java 15 May 2005 11:49:04 -0000 1.7
--- InputStreamSource.java 19 Sep 2005 02:35:05 -0000 1.8
***************
*** 47,51 ****
/**
* An initial buffer size.
! * Has a default value of {@value}.
*/
public static int BUFFER_SIZE = 16384;
--- 47,51 ----
/**
* An initial buffer size.
! * Has a default value of {16384}.
*/
public static int BUFFER_SIZE = 16384;
Index: Lexer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Lexer.java,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** Lexer.java 20 Jun 2005 01:56:32 -0000 1.40
--- Lexer.java 19 Sep 2005 02:35:05 -0000 1.41
***************
*** 1182,1185 ****
--- 1182,1186 ----
char ch;
int end;
+ boolean comment;
start = mCursor.getPosition ();
***************
*** 1187,1190 ****
--- 1188,1193 ----
done = false;
quote = 0;
+ comment = false;
+
while (!done)
{
***************
*** 1199,1203 ****
break;
case '\'':
! if (quotesmart)
if (0 == quote)
quote = '\''; // enter quoted state
--- 1202,1206 ----
break;
case '\'':
! if (quotesmart && !comment)
if (0 == quote)
quote = '\''; // enter quoted state
***************
*** 1206,1210 ****
break;
case '"':
! if (quotesmart)
if (0 == quote)
quote = '"'; // enter quoted state
--- 1209,1213 ----
break;
case '"':
! if (quotesmart && !comment)
if (0 == quote)
quote = '"'; // enter quoted state
***************
*** 1232,1240 ****
done = true;
else if ('/' == ch)
! {
! do
! ch = mPage.getCharacter (mCursor);
! while ((Page.EOF != ch) && ('\n' != ch));
! }
else if ('*' == ch)
{
--- 1235,1239 ----
done = true;
else if ('/' == ch)
! comment = true;
else if ('*' == ch)
{
***************
*** 1254,1257 ****
--- 1253,1259 ----
}
break;
+ case '\n':
+ comment = false;
+ break;
case '<':
if (quotesmart)
***************
*** 1276,1279 ****
--- 1278,1298 ----
state = 2;
break;
+ case '!':
+ ch = mPage.getCharacter (mCursor);
+ if (Page.EOF == ch)
+ done = true;
+ else if ('-' == ch)
+ {
+ ch = mPage.getCharacter (mCursor);
+ if (Page.EOF == ch)
+ done = true;
+ else if ('-' == ch)
+ state = 3;
+ else
+ state = 0;
+ }
+ else
+ state = 0;
+ break;
default:
state = 0;
***************
*** 1282,1285 ****
--- 1301,1305 ----
break;
case 2: // </
+ comment = false;
if (Page.EOF == ch)
done = true;
***************
*** 1295,1298 ****
--- 1315,1337 ----
state = 0;
break;
+ case 3: // <!
+ comment = false;
+ if (Page.EOF == ch)
+ done = true;
+ else if ('-' == ch)
+ {
+ ch = mPage.getCharacter (mCursor);
+ if (Page.EOF == ch)
+ done = true;
+ else if ('-' == ch)
+ {
+ ch = mPage.getCharacter (mCursor);
+ if (Page.EOF == ch)
+ done = true;
+ else if ('>' == ch)
+ state = 0;
+ }
+ }
+ break;
default:
throw new IllegalStateException ("how the fuck did we get in state " + state);
|
