XMLContentHandler Class Reference

Inheritance diagram for XMLContentHandler:

Public Member Functions
	XMLContentHandler (const QString &path)
	~XMLContentHandler ()
Public Member Functions inherited from QXmlDefaultHandler
	QXmlDefaultHandler ()
virtual	~QXmlDefaultHandler ()
void	setDocumentLocator (QXmlLocator *locator)
bool	startDocument ()
bool	endDocument ()
bool	startPrefixMapping (const QString &prefix, const QString &uri)
bool	endPrefixMapping (const QString &prefix)
bool	startElement (const QString &namespaceURI, const QString &localName, const QString &qName, const QXmlAttributes &atts)
bool	endElement (const QString &namespaceURI, const QString &localName, const QString &qName)
bool	characters (const QString &ch)
bool	ignorableWhitespace (const QString &ch)
bool	processingInstruction (const QString &target, const QString &data)
bool	skippedEntity (const QString &name)
bool	warning (const QXmlParseException &exception)
bool	error (const QXmlParseException &exception)
bool	fatalError (const QXmlParseException &exception)
bool	notationDecl (const QString &name, const QString &publicId, const QString &systemId)
bool	unparsedEntityDecl (const QString &name, const QString &publicId, const QString &systemId, const QString &notationName)
bool	resolveEntity (const QString &publicId, const QString &systemId, QXmlInputSource *&ret)
bool	startDTD (const QString &name, const QString &publicId, const QString &systemId)
bool	endDTD ()
bool	startCDATA ()
bool	endCDATA ()
bool	comment (const QString &ch)
bool	attributeDecl (const QString &eName, const QString &aName, const QString &type, const QString &valueDefault, const QString &value)
bool	internalEntityDecl (const QString &name, const QString &value)
bool	externalEntityDecl (const QString &name, const QString &publicId, const QString &systemId)
QString	errorString ()
Public Member Functions inherited from QXmlContentHandler
virtual	~QXmlContentHandler ()
Public Member Functions inherited from QXmlErrorHandler
virtual	~QXmlErrorHandler ()
Public Member Functions inherited from QXmlDTDHandler
virtual	~QXmlDTDHandler ()
Public Member Functions inherited from QXmlEntityResolver
virtual	~QXmlEntityResolver ()
Public Member Functions inherited from QXmlLexicalHandler
virtual	~QXmlLexicalHandler ()
Public Member Functions inherited from QXmlDeclHandler
virtual	~QXmlDeclHandler ()

Private Types
enum	FieldNames {   UnknownField = 0, TypeField = 1, NameField = 2, ArgsField = 3,   TagField = 4, UrlField = 5, KeywordField = 6, TextField = 7 }

Private Member Functions
bool	startElement (const QString &, const QString &, const QString &name, const QXmlAttributes &attrib)
bool	endElement (const QString &, const QString &, const QString &name)
bool	characters (const QString &ch)

Private Attributes
Xapian::WritableDatabase	m_db
Xapian::Document	m_doc
Xapian::TermGenerator	m_indexer
Xapian::Stem	m_stemmer
std::string	m_data
FieldNames	m_curFieldName

Detailed Description

This class is a wrapper around SAX style XML parser, which parses the file without first building a DOM tree in memory.

Definition at line 143 of file doxyindexer.cpp.

Member Enumeration Documentation

enum XMLContentHandler::FieldNames

private

Enumerator
UnknownField
TypeField
NameField
ArgsField
TagField
UrlField
KeywordField
TextField

Definition at line 163 of file doxyindexer.cpp.

    {
      UnknownField = 0,
      TypeField    = 1,
      NameField    = 2,
      ArgsField    = 3,
      TagField     = 4,
      UrlField     = 5,
      KeywordField = 6,
      TextField    = 7
    };

Constructor & Destructor Documentation

XMLContentHandler::XMLContentHandler ( const QString &  path )

inline

Handler for parsing XML data

Definition at line 147 of file doxyindexer.cpp.

      : m_db((path+"doxysearch.db").utf8().data(),Xapian::DB_CREATE_OR_OVERWRITE), 
        m_stemmer("english")
    {
      m_curFieldName = UnknownField;
      m_indexer.set_stemmer(m_stemmer);
      m_indexer.set_document(m_doc);
    }

XMLContentHandler::~XMLContentHandler ( )

inline

Free data handler

Definition at line 157 of file doxyindexer.cpp.

    {
      m_db.commit();
    }

Member Function Documentation

bool XMLContentHandler::characters ( const QString &  ch )

inlineprivatevirtual

Handler for inline text

Implements QXmlContentHandler.

Definition at line 265 of file doxyindexer.cpp.

    {
      m_data += ch.utf8();
      return TRUE;
    }

bool XMLContentHandler::endElement ( const QString &  , const QString &  , const QString &  name  )

inlineprivatevirtual

Handler for an end tag. Called for </doc> and </field> tags

Implements QXmlContentHandler.

Definition at line 196 of file doxyindexer.cpp.

    {
      if (name=="doc") // </doc>
      {
        std::string term = m_doc.get_value(NameField);
        std::string partTerm;
        size_t pos = term.rfind("::");
        if (pos!=std::string::npos)
        {
          partTerm = term.substr(pos+2);
        }
        if (m_doc.get_value(TypeField)=="class" || 
            m_doc.get_value(TypeField)=="file" || 
            m_doc.get_value(TypeField)=="namespace") // containers get highest prio
        {
          safeAddTerm(term,m_doc,1000);
          if (!partTerm.empty())
          {
            safeAddTerm(partTerm,m_doc,500);
          }
        }
        else // members and others get lower prio
        {
          safeAddTerm(m_doc.get_value(NameField),m_doc,100);
          if (!partTerm.empty())
          {
            safeAddTerm(partTerm,m_doc,50);
          }
        }
        m_db.add_document(m_doc);
        m_doc.clear_values();
        m_doc.clear_terms();
      }
      else if (name=="field" && m_curFieldName!=UnknownField) // </field>
      {
        // strip whitespace from m_data
        m_data = reduce(m_data);
        // replace XML entities
        m_data = unescapeXmlEntities(m_data);
        // add data to the document
        m_doc.add_value(m_curFieldName,m_data); 
        switch (m_curFieldName)
        {
          case TypeField:    
          case NameField:    
          case TagField:     
          case UrlField:     
            // meta data that is not searchable
            break;
          case KeywordField: 
            addWords(m_data,m_doc,50);
            break;
          case ArgsField:    
            addIdentifiers(m_data,m_doc,10);
            break;
          case TextField:    
            addWords(m_data,m_doc,2);
            break;
          default:
            break;
        }
        m_data="";
        m_curFieldName=UnknownField;
      }
      // reset m_data
      return TRUE;
    }

bool XMLContentHandler::startElement ( const QString &  , const QString &  , const QString &  name, const QXmlAttributes &  attrib  )

inlineprivatevirtual

Handler for a start tag. Called for <doc> and <field> tags

Implements QXmlContentHandler.

Definition at line 176 of file doxyindexer.cpp.

    {
      m_data="";
      if (name=="field")
      {
        QString fieldName = attrib.value("name");
        if      (fieldName=="type")     m_curFieldName=TypeField;
        else if (fieldName=="name")     m_curFieldName=NameField;
        else if (fieldName=="args")     m_curFieldName=ArgsField;
        else if (fieldName=="tag")      m_curFieldName=TagField;
        else if (fieldName=="url")      m_curFieldName=UrlField;
        else if (fieldName=="keywords") m_curFieldName=KeywordField;
        else if (fieldName=="text")     m_curFieldName=TextField;
        else m_curFieldName=UnknownField;
      }
      return TRUE;
    }

Member Data Documentation

FieldNames XMLContentHandler::m_curFieldName

private

Definition at line 277 of file doxyindexer.cpp.

std::string XMLContentHandler::m_data

private

Definition at line 276 of file doxyindexer.cpp.

Xapian::WritableDatabase XMLContentHandler::m_db

private

Definition at line 272 of file doxyindexer.cpp.

Xapian::Document XMLContentHandler::m_doc

private

Definition at line 273 of file doxyindexer.cpp.

Xapian::TermGenerator XMLContentHandler::m_indexer

private

Definition at line 274 of file doxyindexer.cpp.

Xapian::Stem XMLContentHandler::m_stemmer

private

Definition at line 275 of file doxyindexer.cpp.

---

The documentation for this class was generated from the following file:

• doxygen-1.8.11/addon/doxysearch/doxyindexer.cpp