public abstract class AbstractCommonCrawlFormat extends java.lang.Object implements CommonCrawlFormat
| Modifier and Type | Field and Description |
|---|---|
protected Configuration |
conf |
protected Content |
content |
protected java.util.List<java.lang.String> |
inLinks |
protected boolean |
jsonArray |
protected java.lang.String |
keyPrefix |
protected static org.slf4j.Logger |
LOG |
protected Metadata |
metadata |
protected boolean |
reverseKey |
protected java.lang.String |
reverseKeyValue |
protected boolean |
simpleDateFormat |
protected java.lang.String |
url |
| Constructor and Description |
|---|
AbstractCommonCrawlFormat(java.lang.String url,
Content content,
Metadata metadata,
Configuration nutchConf,
CommonCrawlConfig config) |
| Modifier and Type | Method and Description |
|---|---|
void |
close()
Optional method that could be implemented if the actual format needs some
close procedure.
|
protected abstract void |
closeArray(java.lang.String key,
boolean nested,
boolean newline) |
protected abstract void |
closeObject(java.lang.String key) |
protected abstract java.lang.String |
generateJson() |
protected java.lang.String |
getImported() |
java.util.List<java.lang.String> |
getInLinks()
gets set of inlinks
|
java.lang.String |
getJsonData() |
java.lang.String |
getJsonData(java.lang.String url,
Content content,
Metadata metadata)
Returns a string representation of the JSON structure of the URL content
|
java.lang.String |
getJsonData(java.lang.String url,
Content content,
Metadata metadata,
ParseData parseData)
Returns a string representation of the JSON structure of the URL content
takes into account the parsed metadata about the URL
|
protected java.lang.String |
getKey() |
protected java.lang.String |
getMethod() |
protected java.lang.String |
getRequestAccept() |
protected java.lang.String |
getRequestAcceptEncoding() |
protected java.lang.String |
getRequestAcceptLanguage() |
protected java.lang.String |
getRequestContactEmail() |
protected java.lang.String |
getRequestContactName() |
protected java.lang.String |
getRequestHostAddress() |
protected java.lang.String |
getRequestHostName() |
protected java.lang.String |
getRequestRobots() |
protected java.lang.String |
getRequestSoftware() |
protected java.lang.String |
getRequestUserAgent() |
protected java.lang.String |
getResponseAddress() |
protected java.lang.String |
getResponseContent() |
protected java.lang.String |
getResponseContentEncoding() |
protected java.lang.String |
getResponseContentType() |
protected java.lang.String |
getResponseDate() |
protected java.lang.String |
getResponseHostName() |
protected java.lang.String |
getResponseServer() |
protected java.lang.String |
getResponseStatus() |
protected java.lang.String |
getTimestamp() |
protected java.lang.String |
getUrl() |
void |
setInLinks(java.util.List<java.lang.String> inLinks)
sets inlinks of this document
|
protected abstract void |
startArray(java.lang.String key,
boolean nested,
boolean newline) |
protected abstract void |
startObject(java.lang.String key) |
protected abstract void |
writeArrayValue(java.lang.String value) |
protected abstract void |
writeKeyNull(java.lang.String key) |
protected abstract void |
writeKeyValue(java.lang.String key,
java.lang.String value) |
protected static final org.slf4j.Logger LOG
protected java.lang.String url
protected Content content
protected Metadata metadata
protected Configuration conf
protected java.lang.String keyPrefix
protected boolean simpleDateFormat
protected boolean jsonArray
protected boolean reverseKey
protected java.lang.String reverseKeyValue
protected java.util.List<java.lang.String> inLinks
public AbstractCommonCrawlFormat(java.lang.String url,
Content content,
Metadata metadata,
Configuration nutchConf,
CommonCrawlConfig config)
throws java.io.IOException
java.io.IOExceptionpublic java.lang.String getJsonData(java.lang.String url,
Content content,
Metadata metadata)
throws java.io.IOException
CommonCrawlFormatgetJsonData in interface CommonCrawlFormatjava.io.IOExceptionpublic java.lang.String getJsonData(java.lang.String url,
Content content,
Metadata metadata,
ParseData parseData)
throws java.io.IOException
CommonCrawlFormatgetJsonData in interface CommonCrawlFormatjava.io.IOExceptionpublic java.lang.String getJsonData()
throws java.io.IOException
getJsonData in interface CommonCrawlFormatjava.io.IOExceptionprotected abstract void writeKeyValue(java.lang.String key,
java.lang.String value)
throws java.io.IOException
java.io.IOExceptionprotected abstract void writeKeyNull(java.lang.String key)
throws java.io.IOException
java.io.IOExceptionprotected abstract void startArray(java.lang.String key,
boolean nested,
boolean newline)
throws java.io.IOException
java.io.IOExceptionprotected abstract void closeArray(java.lang.String key,
boolean nested,
boolean newline)
throws java.io.IOException
java.io.IOExceptionprotected abstract void writeArrayValue(java.lang.String value)
throws java.io.IOException
java.io.IOExceptionprotected abstract void startObject(java.lang.String key)
throws java.io.IOException
java.io.IOExceptionprotected abstract void closeObject(java.lang.String key)
throws java.io.IOException
java.io.IOExceptionprotected abstract java.lang.String generateJson()
throws java.io.IOException
java.io.IOExceptionprotected java.lang.String getUrl()
protected java.lang.String getTimestamp()
protected java.lang.String getMethod()
protected java.lang.String getRequestHostName()
protected java.lang.String getRequestHostAddress()
protected java.lang.String getRequestSoftware()
protected java.lang.String getRequestRobots()
protected java.lang.String getRequestContactName()
protected java.lang.String getRequestContactEmail()
protected java.lang.String getRequestAccept()
protected java.lang.String getRequestAcceptEncoding()
protected java.lang.String getRequestAcceptLanguage()
protected java.lang.String getRequestUserAgent()
protected java.lang.String getResponseStatus()
protected java.lang.String getResponseHostName()
protected java.lang.String getResponseAddress()
protected java.lang.String getResponseContentEncoding()
protected java.lang.String getResponseContentType()
public java.util.List<java.lang.String> getInLinks()
CommonCrawlFormatgetInLinks in interface CommonCrawlFormatpublic void setInLinks(java.util.List<java.lang.String> inLinks)
CommonCrawlFormatsetInLinks in interface CommonCrawlFormatinLinks - list of inlinksprotected java.lang.String getResponseDate()
protected java.lang.String getResponseServer()
protected java.lang.String getResponseContent()
protected java.lang.String getKey()
protected java.lang.String getImported()
public void close()
CommonCrawlFormatclose in interface java.io.Closeableclose in interface java.lang.AutoCloseableclose in interface CommonCrawlFormatCopyright © 2019 The Apache Software Foundation