[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/scannersTests ScriptScannerTest.java,1.58,1.59

SourceForge Headquarters 225 Broadway Suite 1600 San Diego, CA 92101 +1 (858) 422-6466

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv25217/tests/scannersTests

Modified Files:
	ScriptScannerTest.java 
Log Message:
Add STRICT flag to ScriptScanner to revert to legacy handling of broken ETAGO (</).
If STRICT is true, scan according to HTML specification, else if false, scan with
quote smart state machine which heuristically yields the correct parse.


Index: ScriptScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ScriptScannerTest.java,v
retrieving revision 1.58
retrieving revision 1.59
diff -C2 -d -r1.58 -r1.59
*** ScriptScannerTest.java	7 Mar 2005 02:18:47 -0000	1.58
--- ScriptScannerTest.java	12 Mar 2005 17:53:11 -0000	1.59
***************
*** 183,195 ****
       * string parser was not moving to the ignore state on encountering double
       * quotes (only single quotes were previously accepted).
-      * 
-      * <pre>
-      * Bug #1104627 Parser Crash reading javascript
-      * Bug #1024045 StringBean crashes on an URL
-      * Bug #1021925 StyleTag with missing linefeed prevents page from parsing
-      * </pre>
-      * Altered test to correctly escape the ETAGO.
-      * See http://www.w3.org/TR/html4/appendix/notes.html#notes-specifying-data
-      *
       * @throws Exception
       */
--- 183,186 ----
***************
*** 212,216 ****
              "document.write(\"}\"); " +
              "// parser thinks this is the end tag.\n" +
!             "document.write(\"<\\/script>\");" +
              "</script>" +
              "<body>" +
--- 203,207 ----
              "document.write(\"}\"); " +
              "// parser thinks this is the end tag.\n" +
!             "document.write(\"</script>\");" +
              "</script>" +
              "<body>" +
***************
*** 235,239 ****
              "document.write(\"}\"); " +
              "// parser thinks this is the end tag.\n" +
!             "document.write(\"<\\/script>\");",
              scriptTag.getScriptCode()
          );
--- 226,230 ----
              "document.write(\"}\"); " +
              "// parser thinks this is the end tag.\n" +
!             "document.write(\"</script>\");",
              scriptTag.getScriptCode()
          );
***************
*** 241,260 ****
      }
  
-     /**
-      * 
-      * <pre>
-      * Bug #1104627 Parser Crash reading javascript
-      * Bug #1024045 StringBean crashes on an URL
-      * Bug #1021925 StyleTag with missing linefeed prevents page from parsing
-      * </pre>
-      * Altered test to correctly escape the ETAGO.
-      * See http://www.w3.org/TR/html4/appendix/notes.html#notes-specifying-data
-      *
-      */
      public void testScriptCodeExtraction() throws ParserException {
          createParser(
              "<SCRIPT language=JavaScript>" +
              "document.write(\"<a href=\"1.htm\"><img src=\"1.jpg\" " +
!             "width=\"80\" height=\"20\" border=\"0\"><\\/a>\");" +
              "</SCRIPT>"
          );
--- 232,240 ----
      }
  
      public void testScriptCodeExtraction() throws ParserException {
          createParser(
              "<SCRIPT language=JavaScript>" +
              "document.write(\"<a href=\"1.htm\"><img src=\"1.jpg\" " +
!             "width=\"80\" height=\"20\" border=\"0\"></a>\");" +
              "</SCRIPT>"
          );
***************
*** 265,289 ****
              "script code",
              "document.write(\"<a href=\"1.htm\"><img src=\"1.jpg\" " +
!             "width=\"80\" height=\"20\" border=\"0\"><\\/a>\");",
              scriptTag.getScriptCode()
          );
      }
  
-     /**
-      * 
-      * <pre>
-      * Bug #1104627 Parser Crash reading javascript
-      * Bug #1024045 StringBean crashes on an URL
-      * Bug #1021925 StyleTag with missing linefeed prevents page from parsing
-      * </pre>
-      * Altered test to correctly escape the ETAGO.
-      * See http://www.w3.org/TR/html4/appendix/notes.html#notes-specifying-data
-      *
-      */
      public void testScriptCodeExtractionWithMultipleQuotes() throws ParserException {
          createParser(
              "<SCRIPT language=JavaScript>" +
              "document.write(\"<a href=\\\"1.htm\\\"><img src=\\\"1.jpg\\\" " +
!             "width=\\\"80\\\" height=\\\"20\\\" border=\\\"0\\\"><\\/a>\");" +
              "</SCRIPT>"
          );
--- 245,258 ----
              "script code",
              "document.write(\"<a href=\"1.htm\"><img src=\"1.jpg\" " +
!             "width=\"80\" height=\"20\" border=\"0\"></a>\");",
              scriptTag.getScriptCode()
          );
      }
  
      public void testScriptCodeExtractionWithMultipleQuotes() throws ParserException {
          createParser(
              "<SCRIPT language=JavaScript>" +
              "document.write(\"<a href=\\\"1.htm\\\"><img src=\\\"1.jpg\\\" " +
!             "width=\\\"80\\\" height=\\\"20\\\" border=\\\"0\\\"></a>\");" +
              "</SCRIPT>"
          );
***************
*** 294,313 ****
              "script code",
              "document.write(\"<a href=\\\"1.htm\\\"><img src=\\\"1.jpg\\\" " +
!             "width=\\\"80\\\" height=\\\"20\\\" border=\\\"0\\\"><\\/a>\");",
              scriptTag.getScriptCode()
          );
      }
  
-     /**
-      * 
-      * <pre>
-      * Bug #1104627 Parser Crash reading javascript
-      * Bug #1024045 StringBean crashes on an URL
-      * Bug #1021925 StyleTag with missing linefeed prevents page from parsing
-      * </pre>
-      * Altered test to correctly escape the ETAGO.
-      * See http://www.w3.org/TR/html4/appendix/notes.html#notes-specifying-data
-      *
-      */
      public void testScriptWithinComments() throws Exception {
          createParser(
--- 263,271 ----
              "script code",
              "document.write(\"<a href=\\\"1.htm\\\"><img src=\\\"1.jpg\\\" " +
!             "width=\\\"80\\\" height=\\\"20\\\" border=\\\"0\\\"></a>\");",
              scriptTag.getScriptCode()
          );
      }
  
      public void testScriptWithinComments() throws Exception {
          createParser(
***************
*** 350,354 ****
              "else{" +
              "\n" +
!             "menuobj.document.write('<layer name=gui bgColor=#E6E6E6 width=165 onmouseover=\"clearhidemenu()\" onmouseout=\"hidemenu()\">'+which+'<\\/layer>')" +
              "\n" +
              "menuobj.document.close()" +
--- 308,312 ----
              "else{" +
              "\n" +
!             "menuobj.document.write('<layer name=gui bgColor=#E6E6E6 width=165 onmouseover=\"clearhidemenu()\" onmouseout=\"hidemenu()\">'+which+'</layer>')" +
              "\n" +
              "menuobj.document.close()" +
***************
*** 558,574 ****
      /**
       * See bug #741769 ScriptScanner doesn't handle quoted </script> tags
-      * 
-      * <pre>
-      * Bug #1104627 Parser Crash reading javascript
-      * Bug #1024045 StringBean crashes on an URL
-      * Bug #1021925 StyleTag with missing linefeed prevents page from parsing
-      * </pre>
-      * Altered test to correctly escape the ETAGO.
-      * See http://www.w3.org/TR/html4/appendix/notes.html#notes-specifying-data
-      *
       */
      public void testScanQuotedEndTag() throws ParserException
      {
!         String html = "<SCRIPT language=\"JavaScript\">document.write('<\\/SCRIPT>');</SCRIPT>";
          createParser(html);
          parseAndAssertNodeCount(1);
--- 516,523 ----
      /**
       * See bug #741769 ScriptScanner doesn't handle quoted </script> tags
       */
      public void testScanQuotedEndTag() throws ParserException
      {
!         String html = "<SCRIPT language=\"JavaScript\">document.write('</SCRIPT>');</SCRIPT>";
          createParser(html);
          parseAndAssertNodeCount(1);