Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
FILE_DOCUMENT_PREFIX |
"file://" |
public static final String |
INLINE_DOCUMENT_PREFIX |
"inline://" |
public static final String |
URL_DOCUMENT_RE |
"^https?://.*" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
DEFAULT_CONFIG_FILE |
"/default-configuration.properties" |
public static final String |
FLAG_PROPERTY_OFF |
"off" |
public static final String |
FLAG_PROPERTY_ON |
"on" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ROOT_EXTRACTION_RESULT_ID |
"root-extraction-result-id" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
EXTRACTION_CONTEXT_URI_PROPERTY |
"any23.extraction.context.uri" |
public static final String |
METADATA_DOMAIN_PER_ENTITY_FLAG |
"any23.extraction.metadata.domain.per.entity" |
public static final String |
METADATA_NESTING_FLAG |
"any23.extraction.metadata.nesting" |
public static final String |
METADATA_TIMESIZE_FLAG |
"any23.extraction.metadata.timesize" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final char |
NULL_CHAR |
32 |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ADDITIONAL_NAME |
"additional-name" |
public static final String |
FAMILY_NAME |
"family-name" |
public static final String |
GIVEN_NAME |
"given-name" |
public static final String |
HONORIFIC_PREFIX |
"honorific-prefix" |
public static final String |
HONORIFIC_SUFFIX |
"honorific-suffix" |
public static final String |
NICKNAME |
"nickname" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-head-meta" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
BEGIN_SCRIPT |
"<script>" |
public static final String |
END_SCRIPT |
"</script>" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ELEMENT_LOCATION |
"Element-Location" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-head-title" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-script-turtle" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ITEMPROP_ATTRIBUTE |
"itemprop" |
public static final String |
ITEMSCOPE_ATTRIBUTE |
"itemscope" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-rdfa11" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ABOUT_ATTRIBUTE |
"about" |
public static final String |
ATTRIBUTE_CSS |
"text/css" |
public static final String |
BODY_TAG |
"BODY" |
public static final String |
CONTENT_ATTRIBUTE |
"content" |
public static final String |
CURIE_SEPARATOR |
":" |
public static final String |
DATATYPE_ATTRIBUTE |
"datatype" |
public static final String |
HEAD_TAG |
"HEAD" |
public static final String |
HREF_ATTRIBUTE |
"href" |
public static final String |
PREFIX_ATTRIBUTE |
"prefix" |
public static final String |
PROFILE_ATTRIBUTE |
"profile" |
public static final String |
PROPERTY_ATTRIBUTE |
"property" |
public static final String |
REL_ATTRIBUTE |
"rel" |
public static final String |
RESOURCE_ATTRIBUTE |
"resource" |
public static final String |
REV_ATTRIBUTE |
"rev" |
public static final String |
SRC_ATTRIBUTE |
"src" |
public static final String |
TYPE_ATTRIBUTE |
"type" |
public static final String |
TYPEOF_ATTRIBUTE |
"typeof" |
public static final String |
URI_PATH_SEPARATOR |
"/" |
public static final char |
URI_PREFIX_SEPARATOR |
58 |
public static final String |
URI_SCHEMA_SEPARATOR |
"://" |
public static final String |
VOCAB_ATTRIBUTE |
"vocab" |
public static final String |
XML_LANG_ATTRIBUTE |
"xml:lang" |
public static final String |
XML_LITERAL_DATATYPE |
"rdf:XMLLiteral" |
public static final String |
XMLNS_ATTRIBUTE |
"xmlns" |
public static final String |
XMLNS_DEFAULT |
"http://www.w3.org/1999/xhtml" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-rdfa" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-xpath" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
CSV_MIMETYPE |
"text/csv" |
public static final String |
RESOURCE_NAME |
"/org/apache/any23/mime/tika-config.xml" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
PLUGIN_DIRS_LIST_SEPARATOR |
":" |
public static final String |
PLUGIN_DIRS_PROPERTY |
"any23.plugin.dirs" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final int |
DEFAULT_NUM_OF_CRAWLERS |
10 |
public static final String |
DEFAULT_PAGE_FILTER_RE |
".*(\\.(css|js|bmp|gif|jpe?g|png|tiff?|mid|mp2|mp3|mp4|wav|wma|avi|mov|mpeg|ram|m4v|wmv|rm|smil|pdf|swf|zip|rar|gz|xml|txt))$" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NAME |
"html-scraper" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
DEFAULT_BASE_URI |
"http://any23.org/tmp/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NODES_WITH_INVALID_ABOUT |
"nodes-with-invalid-about" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
ERRORED_META_NODES |
"errored-meta-nodes" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
OPENGRAPH_PROTOCOL_NS |
"http://opengraphprotocol.org/schema/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
COLUMN_POSITION |
"columnPosition" |
public static final String |
NS |
"http://vocab.sindice.net/csv/" |
public static final String |
NUMBER_OF_COLUMNS |
"numberOfColumns" |
public static final String |
NUMBER_OF_ROWS |
"numberOfRows" |
public static final String |
ROW |
"row" |
public static final String |
ROW_POSITION |
"rowPosition" |
public static final String |
ROW_TYPE |
"Row" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://purl.org/dc/terms/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://ramonantonio.net/doac/0.1/#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
CELL |
"cell" |
public static final String |
CELL_VALUE |
"cellValue" |
public static final String |
CONTAINS_CELL |
"containsCell" |
public static final String |
CONTAINS_ROW |
"containsRow" |
public static final String |
CONTAINS_SHEET |
"containsSheet" |
public static final String |
FIRST_CELL |
"firstCell" |
public static final String |
FIRST_ROW |
"firstRow" |
public static final String |
LAST_CELL |
"lastCell" |
public static final String |
LAST_ROW |
"lastRow" |
public static final String |
NS |
"http://vocab.sindice.net/excel/" |
public static final String |
ROW |
"row" |
public static final String |
SHEET |
"sheet" |
public static final String |
SHEET_NAME |
"sheetName" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://xmlns.com/foaf/0.1/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://www.w3.org/2003/01/geo/wgs84_pos#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://sindice.com/hlisting/0.1/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://vocab.sindice.net/any23#hrecipe/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://www.w3.org/2002/12/cal/icaltzd#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
AUDIO |
"audio" |
public static final String |
AUDIO__SECURE_URL |
"audio:secure_url" |
public static final String |
AUDIO__TYPE |
"audio:type" |
public static final String |
DESCRIPTION |
"description" |
public static final String |
DETERMINER |
"determiner" |
public static final String |
IMAGE |
"image" |
public static final String |
IMAGE__HEIGHT |
"image:height" |
public static final String |
IMAGE__SECURE_URL |
"image:secure_url" |
public static final String |
IMAGE__TYPE |
"image:type" |
public static final String |
IMAGE__URL |
"image:url" |
public static final String |
IMAGE__WIDTH |
"image:width" |
public static final String |
LOCALE |
"locale" |
public static final String |
LOCALE__ALTERNATE |
"locale:alternate" |
public static final String |
NS |
"http://ogp.me/ns#" |
public static final String |
SITE_NAME |
"site_name" |
public static final String |
TITLE |
"title" |
public static final String |
TYPE |
"type" |
public static final String |
URL |
"url" |
public static final String |
VIDEO |
"video" |
public static final String |
VIDEO__HEIGHT |
"video:height" |
public static final String |
VIDEO__SECURE_URL |
"video:secure_url" |
public static final String |
VIDEO__TYPE |
"video:type" |
public static final String |
VIDEO__URL |
"video:url" |
public static final String |
VIDEO__WIDTH |
"video:width" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://purl.org/stuff/rev#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://schema.org/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
DATE |
"date" |
public static final String |
DOMAIN |
"domain" |
public static final String |
NESTING |
"nesting" |
public static final String |
NESTING_ORIGINAL |
"nesting_original" |
public static final String |
NESTING_STRUCTURED |
"nesting_structured" |
public static final String |
NS |
"http://vocab.sindice.net/any23#" |
public static final String |
SIZE |
"size" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://www.w3.org/2006/vcard/ns#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://purl.org/ontology/wo/" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://vocab.sindice.com/xfn#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
NS |
"http://www.w3.org/1999/xhtml/vocab#" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"json" |
public static final String |
MIME_TYPE |
"text/json" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"nquads" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"ntriples" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"rdfxml" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"trix" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"turtle" |
Modifier and Type | Constant Field | Value |
---|---|---|
public static final String |
IDENTIFIER |
"uri" |
public static final String |
MIME_TYPE |
"text/plain" |
Copyright © 2010-2012 The Apache Software Foundation. All Rights Reserved.