modified local reader to take in a parsed url pointer to fix test case

constraintSolver/ISRWord.h

@@ -40,6 +40,7 @@ class ISRWord : public ISR
 		Location Seek ( Location target );
 
 
+
 		// ISR *GetDocumentISR( );
 
 		Location GetEndDocument ( );

crawler/Readers/LocalReader.cpp

@@ -31,8 +31,7 @@ string LocalReader::PageToString ( )
 
 ParsedUrl * LocalReader::getUrl ( )
 	{
-	ParsedUrl url(test_url);
-	return &url;
+	return test_url;
 	}
 
 bool LocalReader::checkStatus ( )
@@ -45,7 +44,7 @@ void LocalReader::closeReader ( )
 	close(fd);
 	}
 
-void LocalReader::setUrl(ParsedUrl url_in)
+void LocalReader::setUrl(ParsedUrl* url_in)
 	{
 		test_url = url_in;
 	}
\ No newline at end of file

crawler/Readers/LocalReader.h

@@ -25,11 +25,11 @@ public:
 
 	void closeReader ( );
 
-	void setUrl(ParsedUrl url);
+	void setUrl(ParsedUrl * url);
 
 private:
 	string fileName;
-	ParsedUrl test_url;
+	ParsedUrl * test_url;
 	int fd;
 
 	};

indexer/Indexer.cpp

@@ -16,7 +16,7 @@ void Indexer::run ( )
 
 	bool cond = true;
 
-    while(alive) {
+    while(alive && pointerToDictionaries->Size() != 0 ) {
 
         DocIndex * dictionary = pointerToDictionaries->Pop();
 		 cout << "INDEX GOT A NEW Dictionary" << endl;
@@ -43,7 +43,7 @@ void Indexer::run ( )
         docEnd.docNumWords = indexedCount;
         docEndings.push_back(docEnd);
 
-        if(currentBlockNumberWords >= 100000 || alive == false) {
+        if(currentBlockNumberWords >= 100000 ) {
             save();
             reset();
         }

main.cpp

@@ -164,16 +164,11 @@ int main ( int argc, char *argv[] )
 
 
 
-
-
-
-
 	Indexer indexer( IndexerQueue );
 	indexer.StartThread( );
 
 	Crawler *crawler = new Crawler( mode, urlFrontier, IndexerQueue );
-	atomic_bool *alive = new atomic_bool(true); // At the beginning of the program
-
+	atomic_bool *alive = new atomic_bool(true);
 	crawler->SpawnSpiders( numberOfSpiders , alive);
 
 	HouseKeeper logger( crawler );
@@ -191,6 +186,7 @@ int main ( int argc, char *argv[] )
 			cout << "Shutting down the indexer  " << endl ;
 			crawler->KillAllSpiders();
 			crawler->WaitOnAllSpiders( );
+
 			indexer.Kill();
 			indexer.WaitForFinish( );
 
@@ -206,16 +202,4 @@ int main ( int argc, char *argv[] )
 
 		}
 
-
-	//main threads is just reading command
-	//if it wants work, has to spawn thread to do it
-	//thread we spawn, periodically pulls should
-
-
-
-
-
-
-
-
 	}
\ No newline at end of file

parser/tests/parserTest.cpp

@@ -57,7 +57,7 @@ void testSimple ( )
 	cout << "Testing Simple: " << endl;
 	UrlFrontier urlFrontierTest;
 	Parser parser( &urlFrontierTest );
-	ParsedUrl fake_url = ParsedUrl( "http://www.cats.com" );
+	ParsedUrl * fake_url = new ParsedUrl( "http://www.cats.com" );
 	string filepath = util::GetCurrentWorkingDir( ) + "/tests/plaintext.txt";
 
 	LocalReader reader( filepath );
@@ -144,7 +144,7 @@ void testURL ( )
 	string filepath = util::GetCurrentWorkingDir( ) + "/tests/urlTest.html";
 
 	LocalReader reader( filepath );
-	reader.setUrl( fake_url );
+	reader.setUrl( &fake_url );
 	auto success = reader.request( );
 	if ( !success )
 		{
@@ -178,7 +178,7 @@ void testBody ( )
 	string filepath = util::GetCurrentWorkingDir( ) + "/tests/testParserBody.html";
 
 	LocalReader reader( filepath );
-	reader.setUrl( fake_url );
+	reader.setUrl( &fake_url );
 	auto success = reader.request( );
 	if ( !success )
 		{
@@ -224,7 +224,7 @@ void testExtractBody ( )
 	cout << "Testing ExtractBody: " << endl;
 	UrlFrontier urlFrontierTest;
 	Parser parser( &urlFrontierTest );
-	ParsedUrl fake_url = ParsedUrl( "https://developer.mozilla.org/en-US/docs/Learn" );
+	ParsedUrl *fake_url = new ParsedUrl( "https://developer.mozilla.org/en-US/docs/Learn" );
 	string filepath = util::GetCurrentWorkingDir( ) + "/tests/testExtractBodyTest.html";
 
 	LocalReader reader( filepath );
@@ -275,7 +275,7 @@ void testAnchorText ( )
 	string filepath = util::GetCurrentWorkingDir( ) + "/tests/testParserBody.html";
 
 	LocalReader reader( filepath );
-	reader.setUrl( fake_url );
+	reader.setUrl( &fake_url );
 	auto success = reader.request( );
 	if ( !success )
 		{