Main Page | Namespace List | Class Hierarchy | Class List | File List | Namespace Members | Class Members | File Members | Related Pages

indri::parse::AnchorTextHarvester Class Reference

#include <AnchorTextHarvester.hpp>

Inheritance diagram for indri::parse::AnchorTextHarvester:

indri::parse::ObjectHandler< _Type > List of all members.

Public Member Functions

 AnchorTextHarvester (const std::string &linkFilePath, const std::string &docOrderPath, lemur::file::Keyfile *docNoKeyfile, lemur::file::Keyfile *redirectKeyfile=NULL)
 ~AnchorTextHarvester ()
void handle (indri::api::ParsedDocument *document)

Private Attributes

std::ofstream _linkFile
std::ofstream _docOrder
char linkFileOutBuffer [5 *1024 *1024]
char docOrderOutBuffer [3 *1024 *1024]
lemur::file::Keyfile_docNoKeyfile
lemur::file::Keyfile_redirectKeyfile
lemur::utility::SHA1 SHA1Hasher

Detailed Description

Writes anchor text from a parsed document out to a file.


Constructor & Destructor Documentation

AnchorTextHarvester::AnchorTextHarvester const std::string &  linkFilePath,
const std::string &  docOrderPath,
lemur::file::Keyfile docNoKeyfile,
lemur::file::Keyfile redirectKeyfile = NULL
 

AnchorTextHarvester::~AnchorTextHarvester  ) 
 


Member Function Documentation

void AnchorTextHarvester::handle indri::api::ParsedDocument document  ) 
 


Member Data Documentation

lemur::file::Keyfile* indri::parse::AnchorTextHarvester::_docNoKeyfile [private]
 

std::ofstream indri::parse::AnchorTextHarvester::_docOrder [private]
 

std::ofstream indri::parse::AnchorTextHarvester::_linkFile [private]
 

lemur::file::Keyfile* indri::parse::AnchorTextHarvester::_redirectKeyfile [private]
 

char indri::parse::AnchorTextHarvester::docOrderOutBuffer[3*1024*1024] [private]
 

char indri::parse::AnchorTextHarvester::linkFileOutBuffer[5*1024*1024] [private]
 

lemur::utility::SHA1 indri::parse::AnchorTextHarvester::SHA1Hasher [private]
 


The documentation for this class was generated from the following files:
Generated on Tue Jun 15 11:03:03 2010 for Lemur by doxygen 1.3.4