public class ZemantaExtractor.ZemantaParser
extends java.lang.Object
implements org.xml.sax.ContentHandler, org.xml.sax.ErrorHandler
| Modifier and Type | Field and Description |
|---|---|
int |
articleCount |
int |
categoryCount |
private java.lang.String |
data_article_confidence |
private java.lang.String |
data_article_published_datetime |
private java.lang.String |
data_article_title |
private java.lang.String |
data_article_url |
private java.lang.String |
data_article_zemified |
private java.lang.String |
data_category_categorization |
private java.lang.String |
data_category_confidence |
private java.lang.String |
data_category_name |
private java.lang.String |
data_image_attribution |
private java.lang.String |
data_image_confidence |
private java.lang.String |
data_image_description |
private java.lang.String |
data_image_license |
private java.lang.String |
data_image_source_url |
private java.lang.String |
data_image_url_l |
private java.lang.String |
data_image_url_l_h |
private java.lang.String |
data_image_url_l_w |
private java.lang.String |
data_image_url_m |
private java.lang.String |
data_image_url_m_h |
private java.lang.String |
data_image_url_m_w |
private java.lang.String |
data_image_url_s |
private java.lang.String |
data_image_url_s_h |
private java.lang.String |
data_image_url_s_w |
private java.lang.String |
data_keyword_confidence |
private java.lang.String |
data_keyword_name |
private java.lang.String |
data_keyword_schema |
private java.lang.String |
data_link_anchor |
private java.lang.String |
data_link_confidence |
private java.lang.String |
data_link_relevance |
private java.lang.String |
data_link_target_title |
private java.lang.String |
data_link_target_type |
private java.lang.String |
data_link_target_url |
private java.lang.String |
data_rid |
private java.lang.String |
data_signature |
private java.lang.String |
data_status |
int |
imageCount |
int |
keywordCount |
(package private) Topic |
masterTopic |
private AbstractZemantaExtractor |
parent |
private int |
state |
private static int |
STATE_RSP |
private static int |
STATE_RSP_ARTICLES |
private static int |
STATE_RSP_ARTICLES_ARTICLE |
private static int |
STATE_RSP_ARTICLES_ARTICLE_CONFIDENCE |
private static int |
STATE_RSP_ARTICLES_ARTICLE_PUBLISHED_DATETIME |
private static int |
STATE_RSP_ARTICLES_ARTICLE_TITLE |
private static int |
STATE_RSP_ARTICLES_ARTICLE_URL |
private static int |
STATE_RSP_ARTICLES_ARTICLE_ZEMIFIED |
private static int |
STATE_RSP_CATEGORIES |
private static int |
STATE_RSP_CATEGORIES_CATEGORY |
private static int |
STATE_RSP_CATEGORIES_CATEGORY_CATEGORIZATION |
private static int |
STATE_RSP_CATEGORIES_CATEGORY_CONFIDENCE |
private static int |
STATE_RSP_CATEGORIES_CATEGORY_NAME |
private static int |
STATE_RSP_IMAGES |
private static int |
STATE_RSP_IMAGES_IMAGE |
private static int |
STATE_RSP_IMAGES_IMAGE_ATTRIBUTION |
private static int |
STATE_RSP_IMAGES_IMAGE_CONFIDENCE |
private static int |
STATE_RSP_IMAGES_IMAGE_DESCRIPTION |
private static int |
STATE_RSP_IMAGES_IMAGE_LICENSE |
private static int |
STATE_RSP_IMAGES_IMAGE_SOURCE_URL |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_L |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_L_H |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_L_W |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_M |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_M_H |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_M_W |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_S |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_S_H |
private static int |
STATE_RSP_IMAGES_IMAGE_URL_S_W |
private static int |
STATE_RSP_KEYWORDS |
private static int |
STATE_RSP_KEYWORDS_KEYWORD |
private static int |
STATE_RSP_KEYWORDS_KEYWORD_CONFIDENCE |
private static int |
STATE_RSP_KEYWORDS_KEYWORD_NAME |
private static int |
STATE_RSP_KEYWORDS_KEYWORD_SCHEMA |
private static int |
STATE_RSP_MARKUP |
private static int |
STATE_RSP_MARKUP_LINKS |
private static int |
STATE_RSP_MARKUP_LINKS_LINK |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_ANCHOR |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_CONFIDENCE |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_RELEVANCE |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_TARGET |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_TARGET_TITLE |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_TARGET_TYPE |
private static int |
STATE_RSP_MARKUP_LINKS_LINK_TARGET_URL |
private static int |
STATE_RSP_MARKUP_TEXT |
private static int |
STATE_RSP_RID |
private static int |
STATE_RSP_SIGNATURE |
private static int |
STATE_RSP_STATUS |
private static int |
STATE_START |
static java.lang.String |
TAG_ANCHOR |
static java.lang.String |
TAG_ARTICLE |
static java.lang.String |
TAG_ARTICLES |
static java.lang.String |
TAG_ATTRIBUTION |
static java.lang.String |
TAG_CATEGORIES |
static java.lang.String |
TAG_CATEGORIZATION |
static java.lang.String |
TAG_CATEGORY |
static java.lang.String |
TAG_CONFIDENCE |
static java.lang.String |
TAG_DESCRIPTION |
static java.lang.String |
TAG_IMAGE |
static java.lang.String |
TAG_IMAGES |
static java.lang.String |
TAG_KEYWORD |
static java.lang.String |
TAG_KEYWORDS |
static java.lang.String |
TAG_LICENSE |
static java.lang.String |
TAG_LINK |
static java.lang.String |
TAG_LINKS |
static java.lang.String |
TAG_MARKUP |
static java.lang.String |
TAG_NAME |
static java.lang.String |
TAG_PUBLISHED_DATETIME |
static java.lang.String |
TAG_RELEVANCE |
static java.lang.String |
TAG_RESULTS |
static java.lang.String |
TAG_RID |
static java.lang.String |
TAG_RSP |
static java.lang.String |
TAG_SCHEMA |
static java.lang.String |
TAG_SIGNATURE |
static java.lang.String |
TAG_SOURCE_URL |
static java.lang.String |
TAG_STATUS |
static java.lang.String |
TAG_TARGET |
static java.lang.String |
TAG_TEXT |
static java.lang.String |
TAG_TITLE |
static java.lang.String |
TAG_TYPE |
static java.lang.String |
TAG_URL |
static java.lang.String |
TAG_URL_L |
static java.lang.String |
TAG_URL_L_H |
static java.lang.String |
TAG_URL_L_W |
static java.lang.String |
TAG_URL_M |
static java.lang.String |
TAG_URL_M_H |
static java.lang.String |
TAG_URL_M_W |
static java.lang.String |
TAG_URL_S |
static java.lang.String |
TAG_URL_S_H |
static java.lang.String |
TAG_URL_S_W |
static java.lang.String |
TAG_ZEMIFIED |
private TopicMap |
tm |
| Constructor and Description |
|---|
ZemantaParser(java.lang.String term,
java.lang.String data,
TopicMap tm,
AbstractZemantaExtractor parent) |
| Modifier and Type | Method and Description |
|---|---|
void |
characters(char[] ch,
int start,
int length) |
void |
endDocument() |
void |
endElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName) |
void |
endPrefixMapping(java.lang.String prefix) |
boolean |
equalTags(java.lang.String t1,
java.lang.String t2) |
void |
error(org.xml.sax.SAXParseException exception) |
void |
fatalError(org.xml.sax.SAXParseException exception) |
void |
ignorableWhitespace(char[] ch,
int start,
int length) |
boolean |
isValid(java.lang.String str) |
void |
processingInstruction(java.lang.String target,
java.lang.String data) |
void |
setDocumentLocator(org.xml.sax.Locator locator) |
void |
skippedEntity(java.lang.String name) |
void |
startDocument() |
void |
startElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName,
org.xml.sax.Attributes atts) |
void |
startPrefixMapping(java.lang.String prefix,
java.lang.String uri) |
void |
warning(org.xml.sax.SAXParseException exception) |
Topic masterTopic
public int keywordCount
public int categoryCount
public int imageCount
public int articleCount
private TopicMap tm
private AbstractZemantaExtractor parent
public static final java.lang.String TAG_RSP
public static final java.lang.String TAG_RESULTS
public static final java.lang.String TAG_STATUS
public static final java.lang.String TAG_RID
public static final java.lang.String TAG_ARTICLES
public static final java.lang.String TAG_KEYWORDS
public static final java.lang.String TAG_IMAGES
public static final java.lang.String TAG_MARKUP
public static final java.lang.String TAG_CATEGORIES
public static final java.lang.String TAG_SIGNATURE
public static final java.lang.String TAG_ARTICLE
public static final java.lang.String TAG_KEYWORD
public static final java.lang.String TAG_IMAGE
public static final java.lang.String TAG_CATEGORY
public static final java.lang.String TAG_URL
public static final java.lang.String TAG_TITLE
public static final java.lang.String TAG_PUBLISHED_DATETIME
public static final java.lang.String TAG_CONFIDENCE
public static final java.lang.String TAG_ZEMIFIED
public static final java.lang.String TAG_NAME
public static final java.lang.String TAG_SCHEMA
public static final java.lang.String TAG_URL_L
public static final java.lang.String TAG_URL_M
public static final java.lang.String TAG_URL_S
public static final java.lang.String TAG_URL_L_W
public static final java.lang.String TAG_URL_M_W
public static final java.lang.String TAG_URL_S_W
public static final java.lang.String TAG_URL_L_H
public static final java.lang.String TAG_URL_M_H
public static final java.lang.String TAG_URL_S_H
public static final java.lang.String TAG_SOURCE_URL
public static final java.lang.String TAG_LICENSE
public static final java.lang.String TAG_DESCRIPTION
public static final java.lang.String TAG_ATTRIBUTION
public static final java.lang.String TAG_TEXT
public static final java.lang.String TAG_LINKS
public static final java.lang.String TAG_LINK
public static final java.lang.String TAG_RELEVANCE
public static final java.lang.String TAG_ANCHOR
public static final java.lang.String TAG_TARGET
public static final java.lang.String TAG_TYPE
public static final java.lang.String TAG_CATEGORIZATION
private static final int STATE_START
private static final int STATE_RSP
private static final int STATE_RSP_STATUS
private static final int STATE_RSP_ARTICLES
private static final int STATE_RSP_ARTICLES_ARTICLE
private static final int STATE_RSP_ARTICLES_ARTICLE_URL
private static final int STATE_RSP_ARTICLES_ARTICLE_CONFIDENCE
private static final int STATE_RSP_ARTICLES_ARTICLE_PUBLISHED_DATETIME
private static final int STATE_RSP_ARTICLES_ARTICLE_TITLE
private static final int STATE_RSP_ARTICLES_ARTICLE_ZEMIFIED
private static final int STATE_RSP_MARKUP
private static final int STATE_RSP_MARKUP_TEXT
private static final int STATE_RSP_MARKUP_LINKS
private static final int STATE_RSP_MARKUP_LINKS_LINK
private static final int STATE_RSP_MARKUP_LINKS_LINK_CONFIDENCE
private static final int STATE_RSP_MARKUP_LINKS_LINK_ANCHOR
private static final int STATE_RSP_MARKUP_LINKS_LINK_TARGET
private static final int STATE_RSP_MARKUP_LINKS_LINK_TARGET_URL
private static final int STATE_RSP_MARKUP_LINKS_LINK_TARGET_TYPE
private static final int STATE_RSP_MARKUP_LINKS_LINK_TARGET_TITLE
private static final int STATE_RSP_MARKUP_LINKS_LINK_RELEVANCE
private static final int STATE_RSP_IMAGES
private static final int STATE_RSP_IMAGES_IMAGE
private static final int STATE_RSP_IMAGES_IMAGE_DESCRIPTION
private static final int STATE_RSP_IMAGES_IMAGE_ATTRIBUTION
private static final int STATE_RSP_IMAGES_IMAGE_LICENSE
private static final int STATE_RSP_IMAGES_IMAGE_SOURCE_URL
private static final int STATE_RSP_IMAGES_IMAGE_CONFIDENCE
private static final int STATE_RSP_IMAGES_IMAGE_URL_S
private static final int STATE_RSP_IMAGES_IMAGE_URL_S_W
private static final int STATE_RSP_IMAGES_IMAGE_URL_S_H
private static final int STATE_RSP_IMAGES_IMAGE_URL_M
private static final int STATE_RSP_IMAGES_IMAGE_URL_M_W
private static final int STATE_RSP_IMAGES_IMAGE_URL_M_H
private static final int STATE_RSP_IMAGES_IMAGE_URL_L
private static final int STATE_RSP_IMAGES_IMAGE_URL_L_W
private static final int STATE_RSP_IMAGES_IMAGE_URL_L_H
private static final int STATE_RSP_KEYWORDS
private static final int STATE_RSP_KEYWORDS_KEYWORD
private static final int STATE_RSP_KEYWORDS_KEYWORD_NAME
private static final int STATE_RSP_KEYWORDS_KEYWORD_CONFIDENCE
private static final int STATE_RSP_KEYWORDS_KEYWORD_SCHEMA
private static final int STATE_RSP_CATEGORIES
private static final int STATE_RSP_CATEGORIES_CATEGORY
private static final int STATE_RSP_CATEGORIES_CATEGORY_NAME
private static final int STATE_RSP_CATEGORIES_CATEGORY_CONFIDENCE
private static final int STATE_RSP_CATEGORIES_CATEGORY_CATEGORIZATION
private static final int STATE_RSP_SIGNATURE
private static final int STATE_RSP_RID
private int state
private java.lang.String data_status
private java.lang.String data_signature
private java.lang.String data_rid
private java.lang.String data_keyword_name
private java.lang.String data_keyword_confidence
private java.lang.String data_keyword_schema
private java.lang.String data_category_name
private java.lang.String data_category_confidence
private java.lang.String data_category_categorization
private java.lang.String data_link_anchor
private java.lang.String data_link_confidence
private java.lang.String data_link_target_url
private java.lang.String data_link_target_type
private java.lang.String data_link_target_title
private java.lang.String data_link_relevance
private java.lang.String data_article_url
private java.lang.String data_article_title
private java.lang.String data_article_published_datetime
private java.lang.String data_article_confidence
private java.lang.String data_article_zemified
private java.lang.String data_image_url_l
private java.lang.String data_image_url_m
private java.lang.String data_image_url_s
private java.lang.String data_image_url_l_w
private java.lang.String data_image_url_m_w
private java.lang.String data_image_url_s_w
private java.lang.String data_image_url_l_h
private java.lang.String data_image_url_m_h
private java.lang.String data_image_url_s_h
private java.lang.String data_image_source_url
private java.lang.String data_image_license
private java.lang.String data_image_description
private java.lang.String data_image_attribution
private java.lang.String data_image_confidence
public ZemantaParser(java.lang.String term,
java.lang.String data,
TopicMap tm,
AbstractZemantaExtractor parent)
public void startDocument()
throws org.xml.sax.SAXException
startDocument in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endDocument()
throws org.xml.sax.SAXException
endDocument in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void startElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName,
org.xml.sax.Attributes atts)
throws org.xml.sax.SAXException
startElement in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endElement(java.lang.String uri,
java.lang.String localName,
java.lang.String qName)
throws org.xml.sax.SAXException
endElement in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void characters(char[] ch,
int start,
int length)
throws org.xml.sax.SAXException
characters in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void warning(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
warning in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void error(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
error in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void fatalError(org.xml.sax.SAXParseException exception)
throws org.xml.sax.SAXException
fatalError in interface org.xml.sax.ErrorHandlerorg.xml.sax.SAXExceptionpublic void ignorableWhitespace(char[] ch,
int start,
int length)
throws org.xml.sax.SAXException
ignorableWhitespace in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void processingInstruction(java.lang.String target,
java.lang.String data)
throws org.xml.sax.SAXException
processingInstruction in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void startPrefixMapping(java.lang.String prefix,
java.lang.String uri)
throws org.xml.sax.SAXException
startPrefixMapping in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void endPrefixMapping(java.lang.String prefix)
throws org.xml.sax.SAXException
endPrefixMapping in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic void setDocumentLocator(org.xml.sax.Locator locator)
setDocumentLocator in interface org.xml.sax.ContentHandlerpublic void skippedEntity(java.lang.String name)
throws org.xml.sax.SAXException
skippedEntity in interface org.xml.sax.ContentHandlerorg.xml.sax.SAXExceptionpublic boolean equalTags(java.lang.String t1,
java.lang.String t2)
public boolean isValid(java.lang.String str)
Copyright 2004-2015 Wandora Team