Package rocks.imsofa.ai.puppychatter.rag

Class PuppyChatterHtmlContentExtractor

java.lang.Object

rocks.imsofa.ai.puppychatter.rag.PuppyChatterTextContentExtractor

rocks.imsofa.ai.puppychatter.rag.PuppyChatterHtmlContentExtractor

All Implemented Interfaces:

TextContentExtractor

public class PuppyChatterHtmlContentExtractor
extends PuppyChatterTextContentExtractor

this implementation expect the given url to be a html page

Field Summary

Fields inherited from class rocks.imsofa.ai.puppychatter.rag.PuppyChatterTextContentExtractor

puppyChatter

Constructor Summary

Constructors

Constructor	Description
PuppyChatterHtmlContentExtractor(PuppyChatter puppyChatter)

Method Summary

Modifier and Type	Method	Description
String	extractTextContent(List<Conversation> messages, URL url)	extract text content from a url using a default charset
String	extractTextContent(List<Conversation> messages, URL url, String charset)	extract text content from a url

Methods inherited from class rocks.imsofa.ai.puppychatter.rag.PuppyChatterTextContentExtractor

extractTextContent

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

PuppyChatterHtmlContentExtractor

public PuppyChatterHtmlContentExtractor(PuppyChatter puppyChatter)

Method Details

extractTextContent

public String extractTextContent(List<Conversation> messages,
 URL url,
 String charset)
                          throws Exception

Description copied from interface: TextContentExtractor

extract text content from a url

Specified by:

extractTextContent in interface TextContentExtractor

Overrides:

extractTextContent in class PuppyChatterTextContentExtractor

Parameters:

messages -

url -

charset -

Returns:

Throws:

Exception

extractTextContent

public String extractTextContent(List<Conversation> messages,
 URL url)
                          throws Exception

Description copied from interface: TextContentExtractor

extract text content from a url using a default charset

Specified by:

extractTextContent in interface TextContentExtractor

Overrides:

extractTextContent in class PuppyChatterTextContentExtractor

Parameters:

messages -

url -

Returns:

Throws:

Exception