|
|||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object org.apache.avalon.framework.logger.AbstractLogEnabled org.apache.cocoon.xml.AbstractXMLProducer org.apache.cocoon.generation.AbstractGenerator org.apache.cocoon.generation.ServiceableGenerator org.apache.lenya.cms.cocoon.generation.LinkStatusGenerator
public class LinkStatusGenerator
Generates a list of links that are reachable from the src and their status.
<map:generator name="linkStatus" src="org.apache.lenya.cms.cocoon.generation.LinkStatusGenerator"/> <map:generate type="linkStatus" src="/{pubid}/{area}/{doc-id}.html"> <map:parameter name="depth" value="1"/> </map:generate>
Field Summary | |
---|---|
static java.lang.String |
ACCEPT_CONFIG
Config element name specifying http header value for accept. |
static java.lang.String |
ACCEPT_DEFAULT
Default value of accept configuration value. |
protected org.xml.sax.helpers.AttributesImpl |
attributes
|
protected static java.lang.String |
CONTENT_ATTR_NAME
|
protected int |
depth
The depth parameter determines how deep the EnhancedLinkStatusGenerator should delve. |
static java.lang.String |
EXCLUDE_CONFIG
Config element name specifying excluding regular expression pattern. |
protected static java.lang.String |
HREF_ATTR_NAME
|
static java.lang.String |
INCLUDE_CONFIG
Config element name specifying including regular expression pattern. |
protected org.apache.excalibur.source.Source |
inputSource
|
static java.lang.String |
LINK_CONTENT_TYPE_CONFIG
Config element name specifying expected link content-typ. |
java.lang.String |
LINK_CONTENT_TYPE_DEFAULT
Default value of link-content-type configuration value. |
protected static java.lang.String |
LINK_NODE_NAME
|
static java.lang.String |
LINK_VIEW_QUERY_CONFIG
Config element name specifying query-string appendend for requesting links of an URL. |
static java.lang.String |
LINK_VIEW_QUERY_DEFAULT
Default value of link-view-query configuration value. |
protected static java.lang.String |
MESSAGE_ATTR_NAME
|
protected static java.lang.String |
PREFIX
The namespace prefix for this namespace. |
protected static java.lang.String |
REFERRER_ATTR_NAME
|
protected static java.lang.String |
STATUS_ATTR_NAME
|
protected static java.lang.String |
TOP_NODE_NAME
|
protected static java.lang.String |
URI
The URI of the namespace of this generator. |
static java.lang.String |
USER_AGENT_CONFIG
Config element name specifying http header value for user-Agent. |
static java.lang.String |
USER_AGENT_DEFAULT
Default value of user-agent configuration value. |
Fields inherited from class org.apache.cocoon.generation.ServiceableGenerator |
---|
manager |
Fields inherited from class org.apache.cocoon.generation.AbstractGenerator |
---|
objectModel, parameters, resolver, source |
Fields inherited from class org.apache.cocoon.xml.AbstractXMLProducer |
---|
contentHandler, EMPTY_CONTENT_HANDLER, lexicalHandler, xmlConsumer |
Fields inherited from interface org.apache.cocoon.generation.Generator |
---|
ROLE |
Constructor Summary | |
---|---|
LinkStatusGenerator()
|
Method Summary | |
---|---|
void |
configure(org.apache.avalon.framework.configuration.Configuration configuration)
Configure the crawler component. |
void |
generate()
Generate XML data. |
protected java.util.List |
getLinksFromConnection(java.lang.String url_link_string,
java.lang.String url_of_referrer,
int referrerDepth)
Retrieve a list of links of a url |
protected java.lang.String |
processURL(java.lang.String uri,
java.lang.String referrer,
int referrerDepth)
Generate xml attributes of a url, calculate url for retrieving links |
void |
recycle()
|
void |
setup(org.apache.cocoon.environment.SourceResolver resolver,
java.util.Map objectModel,
java.lang.String src,
org.apache.avalon.framework.parameters.Parameters par)
|
Methods inherited from class org.apache.cocoon.generation.ServiceableGenerator |
---|
dispose, service |
Methods inherited from class org.apache.cocoon.xml.AbstractXMLProducer |
---|
setConsumer, setContentHandler, setLexicalHandler |
Methods inherited from class org.apache.avalon.framework.logger.AbstractLogEnabled |
---|
enableLogging, getLogger, setupLogger, setupLogger, setupLogger |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Methods inherited from interface org.apache.cocoon.xml.XMLProducer |
---|
setConsumer |
Field Detail |
---|
protected static final java.lang.String URI
protected static final java.lang.String PREFIX
protected static final java.lang.String TOP_NODE_NAME
protected static final java.lang.String LINK_NODE_NAME
protected static final java.lang.String HREF_ATTR_NAME
protected static final java.lang.String REFERRER_ATTR_NAME
protected static final java.lang.String CONTENT_ATTR_NAME
protected static final java.lang.String STATUS_ATTR_NAME
protected static final java.lang.String MESSAGE_ATTR_NAME
protected org.xml.sax.helpers.AttributesImpl attributes
public static final java.lang.String LINK_CONTENT_TYPE_CONFIG
Its value is link-content-type
.
public final java.lang.String LINK_CONTENT_TYPE_DEFAULT
link-content-type
configuration value.
Its value is application/x-cocoon-links
.
public static final java.lang.String LINK_VIEW_QUERY_CONFIG
Its value is link-view-query
.
public static final java.lang.String LINK_VIEW_QUERY_DEFAULT
link-view-query
configuration value.
Its value is ?cocoon-view=links
.
public static final java.lang.String EXCLUDE_CONFIG
Its value is exclude
.
public static final java.lang.String INCLUDE_CONFIG
Its value is include
.
public static final java.lang.String USER_AGENT_CONFIG
Its value is user-agent
.
public static final java.lang.String USER_AGENT_DEFAULT
user-agent
configuration value.
Constants.COMPLETE_NAME
public static final java.lang.String ACCEPT_CONFIG
Its value is accept
.
public static final java.lang.String ACCEPT_DEFAULT
accept
configuration value.
Its value is * / *
protected int depth
protected org.apache.excalibur.source.Source inputSource
Constructor Detail |
---|
public LinkStatusGenerator()
Method Detail |
---|
public void configure(org.apache.avalon.framework.configuration.Configuration configuration) throws org.apache.avalon.framework.configuration.ConfigurationException
Configure can specify which URI to include, and which URI to exclude from crawling. You specify the patterns as regular expressions.
Morover you can configure the required content-type of crawling request, and the query-string appended to each crawling request.
<include>.*\.html?</include> or <include>.*\.html?, .*\.xsp</include> <exclude>.*\.gif</exclude> or <exclude>.*\.gif, .*\.jpe?g</exclude> <link-content-type> application/x-cocoon-links </link-content-type> <link-view-query> ?cocoon-view=links </link-view-query> <user-agent> Cocoon </user-agent> <accept> text/xml </accept>
configure
in interface org.apache.avalon.framework.configuration.Configurable
configuration
- XML configuration of this avalon component.
org.apache.avalon.framework.configuration.ConfigurationException
- is throwing if configuration is invalid.public void setup(org.apache.cocoon.environment.SourceResolver resolver, java.util.Map objectModel, java.lang.String src, org.apache.avalon.framework.parameters.Parameters par) throws org.apache.cocoon.ProcessingException, org.xml.sax.SAXException, java.io.IOException
setup
in interface org.apache.cocoon.sitemap.SitemapModelComponent
setup
in class org.apache.cocoon.generation.AbstractGenerator
org.apache.cocoon.ProcessingException
org.xml.sax.SAXException
java.io.IOException
public void generate() throws org.xml.sax.SAXException, org.apache.cocoon.ProcessingException
generate
in interface org.apache.cocoon.generation.Generator
org.xml.sax.SAXException
- if an error occurs while outputting the document
org.apache.cocoon.ProcessingException
- if the requsted URI wasn't foundprotected java.util.List getLinksFromConnection(java.lang.String url_link_string, java.lang.String url_of_referrer, int referrerDepth)
url_link_string
- url for requesting links, it is assumed that
url_link_string queries the cocoon view links, ie of the form
http://host/foo/bar?cocoon-view=links
url_of_referrer
- base url of which links are requested, ie of the form
http://host/foo/bar
protected java.lang.String processURL(java.lang.String uri, java.lang.String referrer, int referrerDepth) throws org.xml.sax.SAXException
url
- to processreferrer
- of the url
org.xml.sax.SAXException
public void recycle()
recycle
in interface org.apache.avalon.excalibur.pool.Recyclable
recycle
in class org.apache.cocoon.generation.AbstractGenerator
|
|||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |