[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests AllTests.java,1.47,1.48 AssertXmlEqualsTest.jav
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests AllTests.java,1.47,1.48 AssertXmlEqualsTest.java,1.9,1.10 BadTagIdentifier.java,1.9,1.10 FunctionalTests.java,1.40,1.41 InstanceofPerformanceTest.java,1.11,1.12 LineNumberAssignedByNodeReaderTest.java,1.18,1.19 ParserTest.java,1.38,1.39 ParserTestCase.java,1.24,1.25 PerformanceTest.java,1.38,1.39
|
From: <der...@us...> - 2003-09-03 23:36:55
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests
In directory sc8-pr-cvs1:/tmp/cvs-serv31228/tests
Modified Files:
AllTests.java AssertXmlEqualsTest.java BadTagIdentifier.java
FunctionalTests.java InstanceofPerformanceTest.java
LineNumberAssignedByNodeReaderTest.java ParserTest.java
ParserTestCase.java PerformanceTest.java
Log Message:
Change tabs to spaces in all source files.
Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/AllTests.java,v
retrieving revision 1.47
retrieving revision 1.48
diff -C2 -d -r1.47 -r1.48
*** AllTests.java 24 Aug 2003 21:59:43 -0000 1.47
--- AllTests.java 3 Sep 2003 23:36:20 -0000 1.48
***************
*** 34,40 ****
{
! public AllTests(String name) {
! super(name);
! }
/**
--- 34,40 ----
{
! public AllTests(String name) {
! super(name);
! }
/**
***************
*** 49,53 ****
* All other options are passed on to the junit framework.
*/
! public static void main(String[] args)
{
String runner;
--- 49,53 ----
* All other options are passed on to the junit framework.
*/
! public static void main(String[] args)
{
String runner;
***************
*** 99,119 ****
+ ")");
}
! }
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("HTMLParser Tests");
! TestSuite basic = new TestSuite("Basic Tests");
! basic.addTestSuite(ParserTest.class);
suite.addTest(basic);
! suite.addTest(org.htmlparser.tests.scannersTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.utilTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.tagTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.visitorsTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.parserHelperTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.nodeDecoratorTests.AllTests.suite());
! suite.addTest(AssertXmlEqualsTest.suite());
! suite.addTest(LineNumberAssignedByNodeReaderTest.suite());
! return suite;
! }
}
--- 99,119 ----
+ ")");
}
! }
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("HTMLParser Tests");
! TestSuite basic = new TestSuite("Basic Tests");
! basic.addTestSuite(ParserTest.class);
suite.addTest(basic);
! suite.addTest(org.htmlparser.tests.scannersTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.utilTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.tagTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.visitorsTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.parserHelperTests.AllTests.suite());
! suite.addTest(org.htmlparser.tests.nodeDecoratorTests.AllTests.suite());
! suite.addTest(AssertXmlEqualsTest.suite());
! suite.addTest(LineNumberAssignedByNodeReaderTest.suite());
! return suite;
! }
}
Index: AssertXmlEqualsTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/AssertXmlEqualsTest.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** AssertXmlEqualsTest.java 24 Aug 2003 21:59:43 -0000 1.9
--- AssertXmlEqualsTest.java 3 Sep 2003 23:36:20 -0000 1.10
***************
*** 34,81 ****
public class AssertXmlEqualsTest extends ParserTestCase {
! public AssertXmlEqualsTest(String name) {
! super(name);
! }
!
! public void testNestedTagWithText() throws Exception {
! assertXmlEquals("nested with text","<hello> <hi>My name is Nothing</hi></hello>","<hello><hi>My name is Nothing</hi> </hello>");
! }
!
! public void testThreeTagsDifferent() throws Exception {
! assertXmlEquals("two tags different","<someTag></someTag><someOtherTag>","<someTag/><someOtherTag>");
! }
!
! public void testOneTag() throws Exception {
! assertXmlEquals("one tag","<someTag>","<someTag>");
! }
! public void testTwoTags() throws Exception {
! assertXmlEquals("two tags","<someTag></someTag>","<someTag></someTag>");
! }
! public void testTwoTagsDifferent() throws Exception {
! assertXmlEquals("two tags different","<someTag></someTag>","<someTag/>");
! }
!
! public void testTwoTagsDifferent2() throws Exception {
! assertXmlEquals("two tags different","<someTag/>","<someTag></someTag>");
! }
!
! public void testTwoTagsWithSameAttributes() throws Exception {
! assertXmlEquals("attributes","<tag name=\"John\" age=\"22\" sex=\"M\"/>","<tag sex=\"M\" name=\"John\" age=\"22\"/>");
! }
!
! public void testTagWithText() throws Exception {
! assertXmlEquals("text","<hello> My name is Nothing</hello>","<hello>My name is Nothing </hello>");
! }
!
! public void testStringWithLineBreaks() throws Exception {
! assertXmlEquals("string with line breaks","testing & refactoring","testing &\nrefactoring");
! }
!
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("XML Tests");
suite.addTestSuite(AssertXmlEqualsTest.class);
return (suite);
! }
}
--- 34,81 ----
public class AssertXmlEqualsTest extends ParserTestCase {
! public AssertXmlEqualsTest(String name) {
! super(name);
! }
!
! public void testNestedTagWithText() throws Exception {
! assertXmlEquals("nested with text","<hello> <hi>My name is Nothing</hi></hello>","<hello><hi>My name is Nothing</hi> </hello>");
! }
!
! public void testThreeTagsDifferent() throws Exception {
! assertXmlEquals("two tags different","<someTag></someTag><someOtherTag>","<someTag/><someOtherTag>");
! }
!
! public void testOneTag() throws Exception {
! assertXmlEquals("one tag","<someTag>","<someTag>");
! }
! public void testTwoTags() throws Exception {
! assertXmlEquals("two tags","<someTag></someTag>","<someTag></someTag>");
! }
! public void testTwoTagsDifferent() throws Exception {
! assertXmlEquals("two tags different","<someTag></someTag>","<someTag/>");
! }
!
! public void testTwoTagsDifferent2() throws Exception {
! assertXmlEquals("two tags different","<someTag/>","<someTag></someTag>");
! }
!
! public void testTwoTagsWithSameAttributes() throws Exception {
! assertXmlEquals("attributes","<tag name=\"John\" age=\"22\" sex=\"M\"/>","<tag sex=\"M\" name=\"John\" age=\"22\"/>");
! }
!
! public void testTagWithText() throws Exception {
! assertXmlEquals("text","<hello> My name is Nothing</hello>","<hello>My name is Nothing </hello>");
! }
!
! public void testStringWithLineBreaks() throws Exception {
! assertXmlEquals("string with line breaks","testing & refactoring","testing &\nrefactoring");
! }
!
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("XML Tests");
suite.addTestSuite(AssertXmlEqualsTest.class);
return (suite);
! }
}
Index: BadTagIdentifier.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/BadTagIdentifier.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** BadTagIdentifier.java 24 Aug 2003 21:59:43 -0000 1.9
--- BadTagIdentifier.java 3 Sep 2003 23:36:20 -0000 1.10
***************
*** 34,67 ****
public class BadTagIdentifier {
! public BadTagIdentifier() {
! super();
! }
! public static void main(String[] args)
! throws Exception {
! BadTagIdentifier badTags =
! new BadTagIdentifier();
! badTags.identify("http://www.amazon.com");
! }
!
! private void identify(String url)
! throws Exception{
! String [] tagsBeingChecked =
! {"TABLE","DIV","SPAN"};
!
! Parser parser =
! new Parser(url);
! TagFindingVisitor tagFinder =
! new TagFindingVisitor(tagsBeingChecked, true);
! parser.visitAllNodesWith(tagFinder);
! for (int i=0;i<tagsBeingChecked.length;i++) {
! System.out.println(
! "Number of "+tagsBeingChecked[i]+" begin tags = "+
! tagFinder.getTagCount(i));
! System.out.println(
! "Number of "+tagsBeingChecked[i]+" end tags = "+
! tagFinder.getEndTagCount(i));
! }
!
! }
}
--- 34,67 ----
public class BadTagIdentifier {
! public BadTagIdentifier() {
! super();
! }
! public static void main(String[] args)
! throws Exception {
! BadTagIdentifier badTags =
! new BadTagIdentifier();
! badTags.identify("http://www.amazon.com");
! }
!
! private void identify(String url)
! throws Exception{
! String [] tagsBeingChecked =
! {"TABLE","DIV","SPAN"};
!
! Parser parser =
! new Parser(url);
! TagFindingVisitor tagFinder =
! new TagFindingVisitor(tagsBeingChecked, true);
! parser.visitAllNodesWith(tagFinder);
! for (int i=0;i<tagsBeingChecked.length;i++) {
! System.out.println(
! "Number of "+tagsBeingChecked[i]+" begin tags = "+
! tagFinder.getTagCount(i));
! System.out.println(
! "Number of "+tagsBeingChecked[i]+" end tags = "+
! tagFinder.getEndTagCount(i));
! }
!
! }
}
Index: FunctionalTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/FunctionalTests.java,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** FunctionalTests.java 24 Aug 2003 21:59:43 -0000 1.40
--- FunctionalTests.java 3 Sep 2003 23:36:20 -0000 1.41
***************
*** 50,133 ****
public class FunctionalTests extends TestCase {
! public FunctionalTests(String arg0) {
! super(arg0);
! }
! /**
! * Based on a suspected bug report by Annette Doyle,
! * to check if the no of image tags are correctly
! * identified by the parser
! */
! public void testNumImageTagsInYahooWithoutRegisteringScanners() throws ParserException {
! // First count the image tags as is
! int imgTagCount;
! imgTagCount = findImageTagCount();
! try {
! int parserImgTagCount = countImageTagsWithHTMLParser();
! assertEquals("Image Tag Count",imgTagCount,parserImgTagCount);
! }
! catch (ParserException e) {
! throw new ParserException("Error thrown in call to countImageTagsWithHTMLParser()",e);
! }
!
! }
! public int findImageTagCount() {
! int imgTagCount = 0;
! try {
! URL url = new URL("http://www.yahoo.com");
! InputStream is = url.openStream();
! BufferedReader reader;
! reader = new BufferedReader(new InputStreamReader(is));
! imgTagCount = countImageTagsWithoutHTMLParser(reader);
! is.close();
! }
! catch (MalformedURLException e) {
! System.err.println("URL was malformed!");
! }
! catch (IOException e) {
! System.err.println("IO Exception occurred while trying to open stream");
! }
! return imgTagCount;
! }
! public int countImageTagsWithHTMLParser() throws ParserException {
! Parser parser = new Parser("http://www.yahoo.com",new DefaultParserFeedback());
! parser.addScanner(new ImageScanner("-i",new LinkProcessor()));
! int parserImgTagCount = 0;
! Node node;
! for (NodeIterator e= parser.elements();e.hasMoreNodes();) {
! node = (Node)e.nextNode();
! if (node instanceof ImageTag) {
! parserImgTagCount++;
! }
! }
! return parserImgTagCount;
! }
! public int countImageTagsWithoutHTMLParser(BufferedReader reader) throws IOException {
! String line;
! int imgTagCount = 0;
! do {
! line = reader.readLine();
! if (line!=null) {
! // Check the line for image tags
! String newline = line.toUpperCase();
! int fromIndex = -1;
! do {
! fromIndex = newline.indexOf("<IMG",fromIndex+1);
! if (fromIndex!=-1) {
! imgTagCount++;
! }
! }
! while (fromIndex!=-1);
! }
! }
! while (line!=null);
! return imgTagCount;
! }
! public static TestSuite suite() {
! return new TestSuite(FunctionalTests.class);
! }
}
--- 50,133 ----
public class FunctionalTests extends TestCase {
! public FunctionalTests(String arg0) {
! super(arg0);
! }
! /**
! * Based on a suspected bug report by Annette Doyle,
! * to check if the no of image tags are correctly
! * identified by the parser
! */
! public void testNumImageTagsInYahooWithoutRegisteringScanners() throws ParserException {
! // First count the image tags as is
! int imgTagCount;
! imgTagCount = findImageTagCount();
! try {
! int parserImgTagCount = countImageTagsWithHTMLParser();
! assertEquals("Image Tag Count",imgTagCount,parserImgTagCount);
! }
! catch (ParserException e) {
! throw new ParserException("Error thrown in call to countImageTagsWithHTMLParser()",e);
! }
!
! }
! public int findImageTagCount() {
! int imgTagCount = 0;
! try {
! URL url = new URL("http://www.yahoo.com");
! InputStream is = url.openStream();
! BufferedReader reader;
! reader = new BufferedReader(new InputStreamReader(is));
! imgTagCount = countImageTagsWithoutHTMLParser(reader);
! is.close();
! }
! catch (MalformedURLException e) {
! System.err.println("URL was malformed!");
! }
! catch (IOException e) {
! System.err.println("IO Exception occurred while trying to open stream");
! }
! return imgTagCount;
! }
! public int countImageTagsWithHTMLParser() throws ParserException {
! Parser parser = new Parser("http://www.yahoo.com",new DefaultParserFeedback());
! parser.addScanner(new ImageScanner("-i",new LinkProcessor()));
! int parserImgTagCount = 0;
! Node node;
! for (NodeIterator e= parser.elements();e.hasMoreNodes();) {
! node = (Node)e.nextNode();
! if (node instanceof ImageTag) {
! parserImgTagCount++;
! }
! }
! return parserImgTagCount;
! }
! public int countImageTagsWithoutHTMLParser(BufferedReader reader) throws IOException {
! String line;
! int imgTagCount = 0;
! do {
! line = reader.readLine();
! if (line!=null) {
! // Check the line for image tags
! String newline = line.toUpperCase();
! int fromIndex = -1;
! do {
! fromIndex = newline.indexOf("<IMG",fromIndex+1);
! if (fromIndex!=-1) {
! imgTagCount++;
! }
! }
! while (fromIndex!=-1);
! }
! }
! while (line!=null);
! return imgTagCount;
! }
! public static TestSuite suite() {
! return new TestSuite(FunctionalTests.class);
! }
}
Index: InstanceofPerformanceTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/InstanceofPerformanceTest.java,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** InstanceofPerformanceTest.java 24 Aug 2003 21:59:43 -0000 1.11
--- InstanceofPerformanceTest.java 3 Sep 2003 23:36:20 -0000 1.12
***************
*** 40,108 ****
public class InstanceofPerformanceTest {
! FormTag formTag;
! Vector formChildren;
! public void setUp() throws Exception {
! Parser parser =
! Parser.createParser(
! FormScannerTest.FORM_HTML
! );
! parser.registerScanners();
! NodeIterator e = parser.elements();
! Node node = e.nextNode();
! formTag = (FormTag)node;
! formChildren = new Vector();
! for (SimpleNodeIterator se = formTag.children();se.hasMoreNodes();) {
! formChildren.addElement(se.nextNode());
! }
! }
!
! public void doInstanceofTest(long [] time,int index, long numTimes) {
! System.out.println("doInstanceofTest("+index+")");
! long start = System.currentTimeMillis();
! for (long i=0;i<numTimes;i++) {
! for (Enumeration e = formChildren.elements();e.hasMoreElements();) {
! Node node = (Node)e.nextElement();
! }
! }
! long end = System.currentTimeMillis();
! time[index] = end-start;
! }
!
! public void doGetTypeTest(long [] time,int index, long numTimes) {
! System.out.println("doGetTypeTest("+index+")");
! long start = System.currentTimeMillis();
! for (long i=0;i<numTimes;i++) {
! for (SimpleNodeIterator e = formTag.children();e.hasMoreNodes();) {
! Node node = e.nextNode();
! }
! }
! long end = System.currentTimeMillis();
! time[index] = end-start;
! }
! public void perform() {
! int numTimes = 30;
! long time1[] = new long[numTimes],
! time2[] = new long[numTimes];
!
! for (int i=0;i<numTimes;i++)
! doInstanceofTest(time1,i,i*10000);
!
! for (int i=0;i<numTimes;i++)
! doGetTypeTest(time2,i,i*10000);
!
! print(time1,time2);
! }
! public void print(long [] time1, long [] time2) {
! for (int i=0;i<time1.length;i++) {
! System.out.println(i*1000000+":"+","+time1[i]+" "+time2[i]);
! }
! }
! public static void main(String [] args) throws Exception {
! InstanceofPerformanceTest test =
! new InstanceofPerformanceTest();
! test.setUp();
! test.perform();
! }
}
--- 40,108 ----
public class InstanceofPerformanceTest {
! FormTag formTag;
! Vector formChildren;
! public void setUp() throws Exception {
! Parser parser =
! Parser.createParser(
! FormScannerTest.FORM_HTML
! );
! parser.registerScanners();
! NodeIterator e = parser.elements();
! Node node = e.nextNode();
! formTag = (FormTag)node;
! formChildren = new Vector();
! for (SimpleNodeIterator se = formTag.children();se.hasMoreNodes();) {
! formChildren.addElement(se.nextNode());
! }
! }
!
! public void doInstanceofTest(long [] time,int index, long numTimes) {
! System.out.println("doInstanceofTest("+index+")");
! long start = System.currentTimeMillis();
! for (long i=0;i<numTimes;i++) {
! for (Enumeration e = formChildren.elements();e.hasMoreElements();) {
! Node node = (Node)e.nextElement();
! }
! }
! long end = System.currentTimeMillis();
! time[index] = end-start;
! }
!
! public void doGetTypeTest(long [] time,int index, long numTimes) {
! System.out.println("doGetTypeTest("+index+")");
! long start = System.currentTimeMillis();
! for (long i=0;i<numTimes;i++) {
! for (SimpleNodeIterator e = formTag.children();e.hasMoreNodes();) {
! Node node = e.nextNode();
! }
! }
! long end = System.currentTimeMillis();
! time[index] = end-start;
! }
! public void perform() {
! int numTimes = 30;
! long time1[] = new long[numTimes],
! time2[] = new long[numTimes];
!
! for (int i=0;i<numTimes;i++)
! doInstanceofTest(time1,i,i*10000);
!
! for (int i=0;i<numTimes;i++)
! doGetTypeTest(time2,i,i*10000);
!
! print(time1,time2);
! }
! public void print(long [] time1, long [] time2) {
! for (int i=0;i<time1.length;i++) {
! System.out.println(i*1000000+":"+","+time1[i]+" "+time2[i]);
! }
! }
! public static void main(String [] args) throws Exception {
! InstanceofPerformanceTest test =
! new InstanceofPerformanceTest();
! test.setUp();
! test.perform();
! }
}
Index: LineNumberAssignedByNodeReaderTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/LineNumberAssignedByNodeReaderTest.java,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** LineNumberAssignedByNodeReaderTest.java 24 Aug 2003 21:59:43 -0000 1.18
--- LineNumberAssignedByNodeReaderTest.java 3 Sep 2003 23:36:20 -0000 1.19
***************
*** 46,123 ****
public class LineNumberAssignedByNodeReaderTest extends ParserTestCase {
! public LineNumberAssignedByNodeReaderTest(String name) {
! super(name);
! }
!
! /**
! * Test to ensure that the <code>Tag</code> being created by the
! * <code>CompositeTagScanner</code> has the correct startLine and endLine
! * information in the <code>TagData</code> it is constructed with.
! * @throws ParserException if there is a problem parsing the test data
! */
! public void testLineNumbers() throws ParserException {
! testLineNumber("<Custom/>", 1, 0, 1, 1);
! testLineNumber("<Custom />", 1, 0, 1, 1);
! testLineNumber("<Custom></Custom>", 1, 0, 1, 1);
! testLineNumber("<Custom>Content</Custom>", 1, 0, 1, 1);
! testLineNumber("<Custom>Content<Custom></Custom>", 1, 0, 1, 1);
! testLineNumber(
! "<Custom>\n" +
! " Content\n" +
! "</Custom>",
! 1, 0, 1, 3
! );
! testLineNumber(
! "Foo\n" +
! "<Custom>\n" +
! " Content\n" +
! "</Custom>",
! 2, 1, 2, 4
! );
! testLineNumber(
! "Foo\n" +
! "<Custom>\n" +
! " <Custom>SubContent</Custom>\n" +
! "</Custom>",
! 2, 1, 2, 4
! );
! char[] oneHundredNewLines = new char[100];
! Arrays.fill(oneHundredNewLines, '\n');
! testLineNumber(
! "Foo\n" +
! new String(oneHundredNewLines) +
! "<Custom>\n" +
! " <Custom>SubContent</Custom>\n" +
! "</Custom>",
! 2, 1, 102, 104
! );
! }
!
! /**
! * Helper method to ensure that the <code>Tag</code> being created by the
! * <code>CompositeTagScanner</code> has the correct startLine and endLine
! * information in the <code>TagData</code> it is constructed with.
! * @param xml String containing HTML or XML to parse, containing a Custom tag
! * @param numNodes int number of expected nodes returned by parser
! * @param useNode int index of the node to test (should be of type CustomTag)
! * @param startLine int the expected start line number of the tag
! * @param endLine int the expected end line number of the tag
! * @throws ParserException if there is an exception during parsing
! */
! private void testLineNumber(String xml, int numNodes, int useNode, int expectedStartLine, int expectedEndLine) throws ParserException {
! createParser(xml);
! parser.addScanner(new CustomScanner());
! parseAndAssertNodeCount(numNodes);
! assertType("custom node",CustomTag.class,node[useNode]);
! CustomTag tag = (CustomTag)node[useNode];
! assertEquals("start line", expectedStartLine, tag.tagData.getStartLine());
! assertEquals("end line", expectedEndLine, tag.tagData.getEndLine());
!
! }
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("Line Number Tests");
suite.addTestSuite(LineNumberAssignedByNodeReaderTest.class);
return (suite);
! }
}
--- 46,123 ----
public class LineNumberAssignedByNodeReaderTest extends ParserTestCase {
! public LineNumberAssignedByNodeReaderTest(String name) {
! super(name);
! }
!
! /**
! * Test to ensure that the <code>Tag</code> being created by the
! * <code>CompositeTagScanner</code> has the correct startLine and endLine
! * information in the <code>TagData</code> it is constructed with.
! * @throws ParserException if there is a problem parsing the test data
! */
! public void testLineNumbers() throws ParserException {
! testLineNumber("<Custom/>", 1, 0, 1, 1);
! testLineNumber("<Custom />", 1, 0, 1, 1);
! testLineNumber("<Custom></Custom>", 1, 0, 1, 1);
! testLineNumber("<Custom>Content</Custom>", 1, 0, 1, 1);
! testLineNumber("<Custom>Content<Custom></Custom>", 1, 0, 1, 1);
! testLineNumber(
! "<Custom>\n" +
! " Content\n" +
! "</Custom>",
! 1, 0, 1, 3
! );
! testLineNumber(
! "Foo\n" +
! "<Custom>\n" +
! " Content\n" +
! "</Custom>",
! 2, 1, 2, 4
! );
! testLineNumber(
! "Foo\n" +
! "<Custom>\n" +
! " <Custom>SubContent</Custom>\n" +
! "</Custom>",
! 2, 1, 2, 4
! );
! char[] oneHundredNewLines = new char[100];
! Arrays.fill(oneHundredNewLines, '\n');
! testLineNumber(
! "Foo\n" +
! new String(oneHundredNewLines) +
! "<Custom>\n" +
! " <Custom>SubContent</Custom>\n" +
! "</Custom>",
! 2, 1, 102, 104
! );
! }
!
! /**
! * Helper method to ensure that the <code>Tag</code> being created by the
! * <code>CompositeTagScanner</code> has the correct startLine and endLine
! * information in the <code>TagData</code> it is constructed with.
! * @param xml String containing HTML or XML to parse, containing a Custom tag
! * @param numNodes int number of expected nodes returned by parser
! * @param useNode int index of the node to test (should be of type CustomTag)
! * @param startLine int the expected start line number of the tag
! * @param endLine int the expected end line number of the tag
! * @throws ParserException if there is an exception during parsing
! */
! private void testLineNumber(String xml, int numNodes, int useNode, int expectedStartLine, int expectedEndLine) throws ParserException {
! createParser(xml);
! parser.addScanner(new CustomScanner());
! parseAndAssertNodeCount(numNodes);
! assertType("custom node",CustomTag.class,node[useNode]);
! CustomTag tag = (CustomTag)node[useNode];
! assertEquals("start line", expectedStartLine, tag.tagData.getStartLine());
! assertEquals("end line", expectedEndLine, tag.tagData.getEndLine());
!
! }
! public static TestSuite suite() {
! TestSuite suite = new TestSuite("Line Number Tests");
suite.addTestSuite(LineNumberAssignedByNodeReaderTest.class);
return (suite);
! }
}
Index: ParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTest.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** ParserTest.java 24 Aug 2003 21:59:43 -0000 1.38
--- ParserTest.java 3 Sep 2003 23:36:20 -0000 1.39
***************
*** 53,111 ****
public class ParserTest extends ParserTestCase {
! public ParserTest(String name) {
! super(name);
! }
! public void testElements() throws Exception {
! StringBuffer hugeData = new StringBuffer();
! for (int i=0;i<5001;i++) hugeData.append('a');
! createParser(hugeData.toString());
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! assertEquals("There should be 1 node identified",1,i);
! // Now try getting the elements again
! // i = 0;
! // reader.reset();
! // reader.setLineCount(1);
! // reader.setPosInLine(-1);
! // for (HTMLEnumeration e = parser.elements();e.hasMoreNodes();)
! // {
! // node[i++] = e.nextHTMLNode();
! // }
! // assertEquals("There should be 1 node identified (second call to parser.elements())",1,i);
! }
! /**
! * This testcase needs you to be online.
! */
! public void testElementsFromWeb() throws Exception {
! Parser parser;
! try {
! parser = new Parser("http://www.google.com");
! }
! catch (Exception e ){
! throw new ParserException("You must be offline! This test needs you to be connected to the internet.",e);
! }
! parser.getReader().mark(5000);
! Node [] node = new AbstractNode[500];
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! int cnt = i;
! parser.getReader().reset();
! // Now try getting the elements again
! i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! assertEquals("There should be "+cnt+" nodes identified (second call to parser.elements())",cnt,i);
! }
!
/**
* Test the Parser(URLConnection) constructor.
--- 53,111 ----
public class ParserTest extends ParserTestCase {
! public ParserTest(String name) {
! super(name);
! }
! public void testElements() throws Exception {
! StringBuffer hugeData = new StringBuffer();
! for (int i=0;i<5001;i++) hugeData.append('a');
! createParser(hugeData.toString());
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! assertEquals("There should be 1 node identified",1,i);
! // Now try getting the elements again
! // i = 0;
! // reader.reset();
! // reader.setLineCount(1);
! // reader.setPosInLine(-1);
! // for (HTMLEnumeration e = parser.elements();e.hasMoreNodes();)
! // {
! // node[i++] = e.nextHTMLNode();
! // }
! // assertEquals("There should be 1 node identified (second call to parser.elements())",1,i);
! }
! /**
! * This testcase needs you to be online.
! */
! public void testElementsFromWeb() throws Exception {
! Parser parser;
! try {
! parser = new Parser("http://www.google.com");
! }
! catch (Exception e ){
! throw new ParserException("You must be offline! This test needs you to be connected to the internet.",e);
! }
! parser.getReader().mark(5000);
! Node [] node = new AbstractNode[500];
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! int cnt = i;
! parser.getReader().reset();
! // Now try getting the elements again
! i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! {
! node[i++] = e.nextNode();
! }
! assertEquals("There should be "+cnt+" nodes identified (second call to parser.elements())",cnt,i);
! }
!
/**
* Test the Parser(URLConnection) constructor.
***************
*** 114,118 ****
* <pre>
* <form NAME="SearchQuick" method="POST" action="cp_search_response-e.asp"
! * onSubmit="return runSubmit();">
*
* <!-- begin test hidden field code -->
--- 114,118 ----
* <pre>
* <form NAME="SearchQuick" method="POST" action="cp_search_response-e.asp"
! * onSubmit="return runSubmit();">
*
* <!-- begin test hidden field code -->
***************
*** 190,196 ****
* <tr>
* <td colspan="2" align="right" nowrap>
! * <input type="image" src="images/bb_submit-e.gif" name="Search" border="0" WIDTH="88" HEIGHT="23">
* &nbsp; <a href="#" onclick="javascript:fClearAllFields();"><img src="images/bb_clear_form-e.gif" name="Clear" border="0" WIDTH="88" HEIGHT="23"></a>
! * </td>
* </tr>
* </table>
--- 190,196 ----
* <tr>
* <td colspan="2" align="right" nowrap>
! * <input type="image" src="images/bb_submit-e.gif" name="Search" border="0" WIDTH="88" HEIGHT="23">
* &nbsp; <a href="#" onclick="javascript:fClearAllFields();"><img src="images/bb_clear_form-e.gif" name="Clear" border="0" WIDTH="88" HEIGHT="23"></a>
! * </td>
* </tr>
* </table>
***************
*** 210,214 ****
final String postal_code = "K2B 7V4";
! Parser parser;
URL url;
HttpURLConnection connection;
--- 210,214 ----
final String postal_code = "K2B 7V4";
! Parser parser;
URL url;
HttpURLConnection connection;
***************
*** 289,302 ****
out.print (buffer);
out.close ();
! parser = new Parser (connection);
! }
! catch (Exception e)
{
! throw new ParserException ("You must be offline! This test needs you to be connected to the internet.", e);
! }
pass = false;
! for (enumeration = parser.elements (); enumeration.hasMoreNodes ();)
! {
node = enumeration.nextNode ();
if (node instanceof StringNode)
--- 289,302 ----
out.print (buffer);
out.close ();
! parser = new Parser (connection);
! }
! catch (Exception e)
{
! throw new ParserException ("You must be offline! This test needs you to be connected to the internet.", e);
! }
pass = false;
! for (enumeration = parser.elements (); enumeration.hasMoreNodes ();)
! {
node = enumeration.nextNode ();
if (node instanceof StringNode)
***************
*** 306,312 ****
pass = true;
}
! }
! assertTrue("POST operation failed.", pass);
! }
/**
--- 306,312 ----
pass = true;
}
! }
! assertTrue("POST operation failed.", pass);
! }
/**
***************
*** 368,381 ****
public void testHTTPCharset ()
{
! Parser parser;
! try
{
! parser = new Parser("http://www.ibm.com/jp/", Parser.noFeedback);
! assertTrue("Character set should be Shift_JIS", parser.getEncoding ().equalsIgnoreCase ("Shift_JIS"));
! }
! catch (ParserException e)
{
fail ("could not open http://www.ibm.com/jp/");
! }
}
--- 368,381 ----
public void testHTTPCharset ()
{
! Parser parser;
! try
{
! parser = new Parser("http://www.ibm.com/jp/", Parser.noFeedback);
! assertTrue("Character set should be Shift_JIS", parser.getEncoding ().equalsIgnoreCase ("Shift_JIS"));
! }
! catch (ParserException e)
{
fail ("could not open http://www.ibm.com/jp/");
! }
}
***************
*** 388,405 ****
public void testHTMLCharset ()
{
! Parser parser;
NodeIterator enumeration;
! try
{
! parser = new Parser("http://www.sony.co.jp", Parser.noFeedback);
! assertEquals("Character set by default is ISO-8859-1", "ISO-8859-1", parser.getEncoding ());
enumeration = parser.elements();
! assertTrue("Character set should be Shift_JIS", parser.getEncoding ().equalsIgnoreCase ("Shift_JIS"));
! }
! catch (ParserException e)
{
fail ("could not open http://www.sony.co.jp");
! }
}
--- 388,405 ----
public void testHTMLCharset ()
{
! Parser parser;
NodeIterator enumeration;
! try
{
! parser = new Parser("http://www.sony.co.jp", Parser.noFeedback);
! assertEquals("Character set by default is ISO-8859-1", "ISO-8859-1", parser.getEncoding ());
enumeration = parser.elements();
! assertTrue("Character set should be Shift_JIS", parser.getEncoding ().equalsIgnoreCase ("Shift_JIS"));
! }
! catch (ParserException e)
{
fail ("could not open http://www.sony.co.jp");
! }
}
***************
*** 409,424 ****
* and bug #699886 can't parse website other than iso-8859-1
*/
! public void testSwitchCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/gb2312Charset.html";
int i;
Node[] nodes;
!
! parser = new Parser(url);
i = 0;
nodes = new AbstractNode[30];
! for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
! nodes[i++] = e.nextNode();
assertEquals ("Expected nodes", 14, i);
}
--- 409,424 ----
* and bug #699886 can't parse website other than iso-8859-1
*/
! public void testSwitchCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/gb2312Charset.html";
int i;
Node[] nodes;
!
! parser = new Parser(url);
i = 0;
nodes = new AbstractNode[30];
! for (NodeIterator e = parser.elements(); e.hasMoreNodes();)
! nodes[i++] = e.nextNode();
assertEquals ("Expected nodes", 14, i);
}
***************
*** 433,444 ****
* Nonetheless, it would be nice to handle this case.
*/
! public void testDoubleQuotedCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/DoublequotedCharset.html";
!
! parser = new Parser(url);
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! e.nextNode();
assertTrue ("Wrong encoding", parser.getEncoding ().equals ("UTF-8"));
}
--- 433,444 ----
* Nonetheless, it would be nice to handle this case.
*/
! public void testDoubleQuotedCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/DoublequotedCharset.html";
!
! parser = new Parser(url);
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! e.nextNode();
assertTrue ("Wrong encoding", parser.getEncoding ().equals ("UTF-8"));
}
***************
*** 453,464 ****
* Nonetheless, it would be nice to handle this case.
*/
! public void testSingleQuotedCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/SinglequotedCharset.html";
!
! parser = new Parser(url);
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! e.nextNode();
assertTrue ("Wrong encoding", parser.getEncoding ().equals ("UTF-8"));
}
--- 453,464 ----
* Nonetheless, it would be nice to handle this case.
*/
! public void testSingleQuotedCharset () throws ParserException
{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/SinglequotedCharset.html";
!
! parser = new Parser(url);
! for (NodeIterator e = parser.elements();e.hasMoreNodes();)
! e.nextNode();
assertTrue ("Wrong encoding", parser.getEncoding ().equals ("UTF-8"));
}
***************
*** 472,481 ****
* AOL it would be nice to handle this case.
*/
! public void testCommaListCharset () throws ParserException
{
URL url;
URLConnection connection;
! Parser parser;
! String idiots = "http://users.aol.com/geinster/rej.htm";
try
--- 472,481 ----
* AOL it would be nice to handle this case.
*/
! public void testCommaListCharset () throws ParserException
{
URL url;
URLConnection connection;
! Parser parser;
! String idiots = "http://users.aol.com/geinster/rej.htm";
try
***************
*** 537,696 ****
public void testNullUrl() {
! Parser parser;
! try {
! parser = new Parser("http://someoneexisting.com", Parser.noFeedback);
! assertTrue("Should have thrown an exception!",false);
! }
! catch (ParserException e) {
!
! }
! }
!
! public void testURLWithSpaces() throws ParserException{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/This is a Test Page.html";
!
! parser = new Parser(url);
! Node node [] = new AbstractNode[30];
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! node[i] = e.nextNode();
! i++;
!
! }
! assertEquals("Expected nodes",12,i);
! }
! public void testLinkCollection() throws ParserException {
! createParser(
! "<html><head><meta http-equiv=\"content-type\" content=\"text/html; charset=UTF-8\"><title>Google</title><style><!--\n"+
! "body,td,a,p,.h{font-family:arial,sans-serif;} .h{font-size: 20px;} .h{color:} .q{text-decoration:none; color:#0000cc;}\n"+
! "//--></style>\n"+
! "<script>\n"+
! "<!--\n"+
! "function sf(){document.f.q.focus();}\n"+
! "function c(p){var f=document.f;if (f.action) {f.action = 'http://'+p;f.submit();return false;}return true;}\n"+
! "// -->\n"+
! "</script>\n"+
! "</head><body bgcolor=#ffffff text=#000000 link=#0000cc vlink=#551a8b alink=#ff0000 onLoad=sf()><center><table border=0 cellspacing=0 cellpadding=0><tr><td><img src=\"images/logo.gif\" width=276 height=110 alt=\"Google\"></td></tr></table><br>\n"+
! "<table border=0 cellspacing=0 cellpadding=0>" +
! "<tr>" +
! "<td width=15> </td>" +
! "<td id=0 bgcolor=#3366cc align=center width=95 nowrap>" +
! "<font color=#ffffff size=-1><b>Web</b></font>" +
! "</td>" +
! "<td width=15> </td>" +
! "<td id=1 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/imghp');\" style=cursor:pointer;cursor:hand;><a id=1a class=q href=\"/imghp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/imghp');\"><font size=-1>Images</font></a></td><td width=15> </td><td id=2 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/grphp');\" style=cursor:pointer;cursor:hand;><a id=2a class=q href=\"/grphp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/grphp');\"><font size=-1>Groups</font></a></td><td width=15> </td><td id=3 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/dirhp');\" style=cursor:pointer;cursor:hand;><a id=3a class=q href=\"/dirhp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/dirhp');\"><font size=-1>Directory</font></a></td><td width=15> </td><td id=4 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/nwshp');\" style=cursor:pointer;cursor:hand;><a id=4a class=q href=\"/nwshp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/nwshp');\"><font size=-1><nobr>News-<font color=red>New!</font></nobr></font></a></td><td width=15> </td></tr><tr><td colspan=12 bgcolor=#3366cc><img width=1 height=1 alt=\"\">" +
! "</td>" +
! "</tr>" +
! "</table>" +
! "<br>" +
! "<form action=\"/search\" name=f>" +
! "<table cellspacing=0 cellpadding=0>" +
! "<tr>" +
! "<td width=75> </td>" +
! "<td align=center>" +
! "<input type=hidden name=hl value=en>" +
! "<input type=hidden name=ie value=\"UTF-8\">" +
! "<input type=hidden name=oe value=\"UTF-8\">" +
! "<input maxLength=256 size=55 name=q value=\"\"><br>" +
! "<input type=submit value=\"Google Search\" name=btnG>" +
! "<input type=submit value=\"I'm Feeling Lucky\" name=btnI>" +
! "</td>" +
! "<td valign=top nowrap>" +
! "<font size=-2> • <a href=/advanced_search?hl=en>Advanced Search</a>" +
! "<br> • <a href=/preferences?hl=en>Preferences</a>" +
! "<br> • <a href=/language_tools?hl=en>Language Tools</a>" +
! "</font>" +
! "</td>" +
! "</tr>" +
! "</table>" +
! "</form><br>\n"+
! "<br><font size=-1><a href=\"/ads/\">Advertise with Us</a> - <a href=\"/services/\">Search Solutions</a> - <a href=\"/options/\">Services & Tools</a> - <a href=/about.html>Jobs, Press, & Help</a><span id=hp style=\"behavior:url(#default#homepage)\"></span>\n"+
! "<script>\n"+
! "if (!hp.isHomePage('http://www.google.com/')) {document.write(\"<p><a href=\"/mgyhp.html\" onClick=\"style.behavior='url(#default#homepage)';setHomePage('http://www.google.com/');\">Make Google Your Homepage!</a>\");}\n"+
! "</script></font>\n"+
! "<p><font size=-2>©2002 Google</font><font size=-2> - Searching 3,083,324,652 web pages</font></center></body></html>\n"
! );
! parser.registerScanners();
! NodeList collectionList = new NodeList();
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! node.collectInto(collectionList,LinkTag.class);
! }
! assertEquals("Size of collection vector should be 11",11,collectionList.size());
! // All items in collection vector should be links
! for (SimpleNodeIterator e = collectionList.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! assertTrue("Only links should have been parsed",node instanceof LinkTag);
! }
! }
! public void testImageCollection() throws ParserException {
! createParser(
! "<html>\n"+
! "<head>\n"+
! "<meta name=\"generator\" content=\"Created Using Yahoo! PageBuilder 2.60.24\">\n"+
! "</head>\n"+
! "<body bgcolor=\"#FFFFFF\" link=\"#0000FF\" vlink=\"#FF0000\" text=\"#000000\"\n"+
! " onLoad=\"window.onresize=new Function('if (navigator.appVersion==\'Netscape\') history.go(0);');\">\n"+
! "<div id=\"layer0\" style=\"position:absolute;left:218;top:40;width:240;height:26;\">\n"+
! "<table width=240 height=26 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><b><font size=\"+2\"><span style=\"font-size:24\">NISHI-HONGWAN-JI</span></font></b></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer1\" style=\"position:absolute;left:75;top:88;width:542;height:83;\">\n"+
! "<table width=542 height=83 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><span style=\"font-size:14\">The Nihi Hongwanj-ji temple is very traditional, very old, and very beautiful. This is the place that we stayed on our first night in Kyoto. We then attended the morning prayer ceremony, at 6:30 am. Staying here costed us 7,500 yen, which was inclusive of dinner and breakfast, and usage of the o-furo (public bath). Felt more like a luxury hotel than a temple.</span></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer2\" style=\"position:absolute;left:144;top:287;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji1.html\"><img height=96 width=128 src=\"nishi-hongwanji1-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer3\" style=\"position:absolute;left:415;top:285;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji3.html\"><img height=96 width=128 src=\"nishi-hongwanji2-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer4\" style=\"position:absolute;left:414;top:182;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"higashi-hongwanji.html\"><img height=96 width=128 src=\"higashi-hongwanji-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer5\" style=\"position:absolute;left:78;top:396;width:530;height:49;\">\n"+
! "<table width=530 height=49 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><span style=\"font-size:14\">Click on the pictures to see the full-sized versions. The picture at the top right corner is taken in Higashi-Hongwanji. Nishi means west, and Higashi means east. These two temples are adjacent to each other and represent two different Buddhist sects.</span></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer6\" style=\"position:absolute;left:143;top:180;width:128;height:102;\">\n"+
! "<table width=128 height=102 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji4.html\"><img height=102 width=128 src=\"nishi-hongwanji4-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer7\" style=\"position:absolute;left:280;top:235;width:124;height:99;\">\n"+
! "<table width=124 height=99 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji-lodging.html\"><img height=99 width=124 src=\"nishi-hongwanji-lodging-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "</body>\n"+
! "</html>");
! parser.registerScanners();
! NodeList collectionList = new NodeList();
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! node.collectInto(collectionList,ImageTag.IMAGE_TAG_FILTER);
! }
! assertEquals("Size of collection vector should be 5",5,collectionList.size());
! // All items in collection vector should be links
! for (SimpleNodeIterator e = collectionList.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! assertTrue("Only images should have been parsed",node instanceof ImageTag);
! }
! }
! public void testRemoveScanner() throws Exception {
! createParser(
! ""
! );
! parser.registerScanners();
! parser.removeScanner(new FormScanner("",parser));
! Map scanners = parser.getScanners();
! TagScanner scanner = (TagScanner)scanners.get("FORM");
! assertNull("shouldnt have found scanner",scanner);
! }
/**
--- 537,696 ----
public void testNullUrl() {
! Parser parser;
! try {
! parser = new Parser("http://someoneexisting.com", Parser.noFeedback);
! assertTrue("Should have thrown an exception!",false);
! }
! catch (ParserException e) {
!
! }
! }
!
! public void testURLWithSpaces() throws ParserException{
! Parser parser;
! String url = "http://htmlparser.sourceforge.net/test/This is a Test Page.html";
!
! parser = new Parser(url);
! Node node [] = new AbstractNode[30];
! int i = 0;
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! node[i] = e.nextNode();
! i++;
!
! }
! assertEquals("Expected nodes",12,i);
! }
! public void testLinkCollection() throws ParserException {
! createParser(
! "<html><head><meta http-equiv=\"content-type\" content=\"text/html; charset=UTF-8\"><title>Google</title><style><!--\n"+
! "body,td,a,p,.h{font-family:arial,sans-serif;} .h{font-size: 20px;} .h{color:} .q{text-decoration:none; color:#0000cc;}\n"+
! "//--></style>\n"+
! "<script>\n"+
! "<!--\n"+
! "function sf(){document.f.q.focus();}\n"+
! "function c(p){var f=document.f;if (f.action) {f.action = 'http://'+p;f.submit();return false;}return true;}\n"+
! "// -->\n"+
! "</script>\n"+
! "</head><body bgcolor=#ffffff text=#000000 link=#0000cc vlink=#551a8b alink=#ff0000 onLoad=sf()><center><table border=0 cellspacing=0 cellpadding=0><tr><td><img src=\"images/logo.gif\" width=276 height=110 alt=\"Google\"></td></tr></table><br>\n"+
! "<table border=0 cellspacing=0 cellpadding=0>" +
! "<tr>" +
! "<td width=15> </td>" +
! "<td id=0 bgcolor=#3366cc align=center width=95 nowrap>" +
! "<font color=#ffffff size=-1><b>Web</b></font>" +
! "</td>" +
! "<td width=15> </td>" +
! "<td id=1 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/imghp');\" style=cursor:pointer;cursor:hand;><a id=1a class=q href=\"/imghp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/imghp');\"><font size=-1>Images</font></a></td><td width=15> </td><td id=2 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/grphp');\" style=cursor:pointer;cursor:hand;><a id=2a class=q href=\"/grphp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/grphp');\"><font size=-1>Groups</font></a></td><td width=15> </td><td id=3 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/dirhp');\" style=cursor:pointer;cursor:hand;><a id=3a class=q href=\"/dirhp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/dirhp');\"><font size=-1>Directory</font></a></td><td width=15> </td><td id=4 bgcolor=#efefef align=center width=95 nowrap onClick=\"return c('www.google.com/nwshp');\" style=cursor:pointer;cursor:hand;><a id=4a class=q href=\"/nwshp?hl=en&ie=UTF-8&oe=UTF-8\" onClick=\"return c('www.google.com/nwshp');\"><font size=-1><nobr>News-<font color=red>New!</font></nobr></font></a></td><td width=15> </td></tr><tr><td colspan=12 bgcolor=#3366cc><img width=1 height=1 alt=\"\">" +
! "</td>" +
! "</tr>" +
! "</table>" +
! "<br>" +
! "<form action=\"/search\" name=f>" +
! "<table cellspacing=0 cellpadding=0>" +
! "<tr>" +
! "<td width=75> </td>" +
! "<td align=center>" +
! "<input type=hidden name=hl value=en>" +
! "<input type=hidden name=ie value=\"UTF-8\">" +
! "<input type=hidden name=oe value=\"UTF-8\">" +
! "<input maxLength=256 size=55 name=q value=\"\"><br>" +
! "<input type=submit value=\"Google Search\" name=btnG>" +
! "<input type=submit value=\"I'm Feeling Lucky\" name=btnI>" +
! "</td>" +
! "<td valign=top nowrap>" +
! "<font size=-2> • <a href=/advanced_search?hl=en>Advanced Search</a>" +
! "<br> • <a href=/preferences?hl=en>Preferences</a>" +
! "<br> • <a href=/language_tools?hl=en>Language Tools</a>" +
! "</font>" +
! "</td>" +
! "</tr>" +
! "</table>" +
! "</form><br>\n"+
! "<br><font size=-1><a href=\"/ads/\">Advertise with Us</a> - <a href=\"/services/\">Search Solutions</a> - <a href=\"/options/\">Services & Tools</a> - <a href=/about.html>Jobs, Press, & Help</a><span id=hp style=\"behavior:url(#default#homepage)\"></span>\n"+
! "<script>\n"+
! "if (!hp.isHomePage('http://www.google.com/')) {document.write(\"<p><a href=\"/mgyhp.html\" onClick=\"style.behavior='url(#default#homepage)';setHomePage('http://www.google.com/');\">Make Google Your Homepage!</a>\");}\n"+
! "</script></font>\n"+
! "<p><font size=-2>©2002 Google</font><font size=-2> - Searching 3,083,324,652 web pages</font></center></body></html>\n"
! );
! parser.registerScanners();
! NodeList collectionList = new NodeList();
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! node.collectInto(collectionList,LinkTag.class);
! }
! assertEquals("Size of collection vector should be 11",11,collectionList.size());
! // All items in collection vector should be links
! for (SimpleNodeIterator e = collectionList.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! assertTrue("Only links should have been parsed",node instanceof LinkTag);
! }
! }
! public void testImageCollection() throws ParserException {
! createParser(
! "<html>\n"+
! "<head>\n"+
! "<meta name=\"generator\" content=\"Created Using Yahoo! PageBuilder 2.60.24\">\n"+
! "</head>\n"+
! "<body bgcolor=\"#FFFFFF\" link=\"#0000FF\" vlink=\"#FF0000\" text=\"#000000\"\n"+
! " onLoad=\"window.onresize=new Function('if (navigator.appVersion==\'Netscape\') history.go(0);');\">\n"+
! "<div id=\"layer0\" style=\"position:absolute;left:218;top:40;width:240;height:26;\">\n"+
! "<table width=240 height=26 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><b><font size=\"+2\"><span style=\"font-size:24\">NISHI-HONGWAN-JI</span></font></b></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer1\" style=\"position:absolute;left:75;top:88;width:542;height:83;\">\n"+
! "<table width=542 height=83 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><span style=\"font-size:14\">The Nihi Hongwanj-ji temple is very traditional, very old, and very beautiful. This is the place that we stayed on our first night in Kyoto. We then attended the morning prayer ceremony, at 6:30 am. Staying here costed us 7,500 yen, which was inclusive of dinner and breakfast, and usage of the o-furo (public bath). Felt more like a luxury hotel than a temple.</span></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer2\" style=\"position:absolute;left:144;top:287;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji1.html\"><img height=96 width=128 src=\"nishi-hongwanji1-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer3\" style=\"position:absolute;left:415;top:285;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji3.html\"><img height=96 width=128 src=\"nishi-hongwanji2-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer4\" style=\"position:absolute;left:414;top:182;width:128;height:96;\">\n"+
! "<table width=128 height=96 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"higashi-hongwanji.html\"><img height=96 width=128 src=\"higashi-hongwanji-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer5\" style=\"position:absolute;left:78;top:396;width:530;height:49;\">\n"+
! "<table width=530 height=49 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><span style=\"font-size:14\">Click on the pictures to see the full-sized versions. The picture at the top right corner is taken in Higashi-Hongwanji. Nishi means west, and Higashi means east. These two temples are adjacent to each other and represent two different Buddhist sects.</span></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer6\" style=\"position:absolute;left:143;top:180;width:128;height:102;\">\n"+
! "<table width=128 height=102 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji4.html\"><img height=102 width=128 src=\"nishi-hongwanji4-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "<div id=\"layer7\" style=\"position:absolute;left:280;top:235;width:124;height:99;\">\n"+
! "<table width=124 height=99 border=0 cellpadding=0 cellspacing=0><tr valign=\"top\">\n"+
! "<td><a href=\"nishi-hongwanji-lodging.html\"><img height=99 width=124 src=\"nishi-hongwanji-lodging-thumb.jpg\" border=0 ></a></td>\n"+
! "</tr></table></div>\n"+
! "</body>\n"+
! "</html>");
! parser.registerScanners();
! NodeList collectionList = new NodeList();
! for (NodeIterator e = parser.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! node.collectInto(collectionList,ImageTag.IMAGE_TAG_FILTER);
! }
! assertEquals("Size of collection vector should be 5",5,collectionList.size());
! // All items in collection vector should be links
! for (SimpleNodeIterator e = collectionList.elements();e.hasMoreNodes();) {
! Node node = e.nextNode();
! assertTrue("Only images sh...
[truncated message content] |
