mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
311 lines
7.2 KiB
Plaintext
311 lines
7.2 KiB
Plaintext
## this is a list of all solr keys
|
|
## solr can be used as alternative index target, solr is NOT the primary indexing system of YaCy
|
|
## this complete list of keys can be reduced:
|
|
## reduced list of keys can be placed in DATA/SETTINGS/solr.keys.<profile>.list
|
|
## where they can be used as profiles for solr index transport
|
|
|
|
## the syntax of this file:
|
|
## - all lines beginning with '##' are comments
|
|
## - all non-empty lines not beginning with '#' are keyword lines
|
|
## - all lines beginning with '#' and where the second character is not '#' are commented-out keyword lines
|
|
|
|
##url of document, string
|
|
sku
|
|
|
|
## primary key of document, the URL hash, string
|
|
id
|
|
|
|
## longitude of location as declared in WSG84, tdouble
|
|
lon_coordinate
|
|
|
|
## longitude of location as declared in WSG84, tdouble
|
|
lat_coordinate
|
|
|
|
## last-modified from http header, date
|
|
last_modified
|
|
|
|
## ip of host of url (after DNS lookup), string
|
|
ip_s
|
|
|
|
## mime-type of document, string
|
|
content_type
|
|
|
|
## content of title tag, text
|
|
title
|
|
|
|
## content of author-tag, texgen
|
|
author
|
|
|
|
## content of description-tag, text
|
|
description
|
|
|
|
## content of keywords tag; words are separated by space, textgen
|
|
keywords
|
|
|
|
## character encoding, string
|
|
charset_s
|
|
|
|
## tags of css entries, normalized with absolute URL, textgen
|
|
css_tag_txt
|
|
|
|
## urls of css entries, normalized with absolute URL, textgen
|
|
css_url_txt
|
|
|
|
## number of css entries, int
|
|
csscount_i
|
|
|
|
## urls of script entries, normalized with absolute URL, textgen
|
|
scripts_txt
|
|
|
|
## number of script entries, int
|
|
scriptscount_i
|
|
|
|
## encoded as binary value into an integer:
|
|
## bit 0: "all" contained in html header meta
|
|
## bit 1: "index" contained in html header meta
|
|
## bit 2: "noindex" contained in html header meta
|
|
## bit 3: "nofollow" contained in html header meta
|
|
## bit 8: "noarchive" contained in http header properties
|
|
## bit 9: "nosnippet" contained in http header properties
|
|
## bit 10: "noindex" contained in http header properties
|
|
## bit 11: "nofollow" contained in http header properties
|
|
## bit 12: "unavailable_after" contained in http header properties
|
|
## content of <meta name="robots" content=#content#> tag and the "X-Robots-Tag" HTTP property
|
|
robots_i
|
|
|
|
## html status return code (i.e. "200" for ok), -1 if not loaded (see content of failreason_t for this case), int
|
|
httpstatus_i
|
|
|
|
## content of <meta name="generator" content=#content#> tag, text
|
|
metagenerator_t
|
|
|
|
## all visible text, text
|
|
text_t
|
|
|
|
## number of words in visible area, int
|
|
wordcount_i
|
|
|
|
## internal links, normalized (absolute URLs), as <a> - tag with anchor text and nofollow, textgen
|
|
inboundlinks_tag_txt
|
|
|
|
## internal links, only the protocol
|
|
#inboundlinks_protocol_txt
|
|
|
|
## internal links, the url only without the protocol
|
|
#inboundlinks_urlstub_txt
|
|
|
|
## internal links, the name property of the a-tag
|
|
#inboundlinks_name_txt
|
|
|
|
## internal links, the rel property of the a-tag
|
|
#inboundlinks_rel_txt
|
|
|
|
## internal links, the rel property of the a-tag, coded binary
|
|
#inboundlinks_relflags_txt
|
|
|
|
## internal links, the text content of the a-tag
|
|
#inboundlinks_text_txt
|
|
|
|
## total number of inbound links, int
|
|
inboundlinkscount_i
|
|
|
|
## number of inbound links with nofollow tag, int
|
|
inboundlinksnofollowcount_i
|
|
|
|
## external links, normalized (absolute URLs), as <a> - tag with anchor text and nofollow, textgen
|
|
outboundlinks_tag_txt
|
|
|
|
## external links, only the protocol
|
|
#outboundlinks_protocol_txt
|
|
|
|
## external links, the url only without the protocol
|
|
#outboundlinks_urlstub_txt
|
|
|
|
## external links, the name property of the a-tag
|
|
#outboundlinks_name_txt
|
|
|
|
## external links, the rel property of the a-tag
|
|
#outboundlinks_rel_txt
|
|
|
|
## external links, the rel property of the a-tag, coded binary
|
|
#outboundlinks_relflags_txt
|
|
|
|
## external links, the text content of the a-tag
|
|
#outboundlinks_text_txt
|
|
|
|
## external number of inbound links, int
|
|
outboundlinkscount_i
|
|
|
|
## number of external links with nofollow tag, int
|
|
outboundlinksnofollowcount_i
|
|
|
|
## all image tags, encoded as <img> tag inclusive alt- and title property, textgen
|
|
images_tag_txt
|
|
|
|
## all image links without the protocol and '://'
|
|
#images_urlstub_txt
|
|
|
|
## all image link protocols
|
|
#images_protocol_txt
|
|
|
|
## all image link alt tag
|
|
#images_alt_txt
|
|
|
|
## number of images, int
|
|
imagescount_i
|
|
|
|
## h1 header, textgen
|
|
h1_txt
|
|
|
|
## h2 header, textgen
|
|
h2_txt
|
|
|
|
## h3 header, textgen
|
|
h3_txt
|
|
|
|
## h4 header, textgen
|
|
h4_txt
|
|
|
|
## h5 header, textgen
|
|
h5_txt
|
|
|
|
## h6 header, textgen
|
|
h6_txt
|
|
|
|
## binary pattern for the existance of h1..h6 headlines, int
|
|
htags_i
|
|
|
|
## all path elements in the url, textgen
|
|
paths_txt
|
|
|
|
## host of the url, string
|
|
host_s
|
|
|
|
## url inside the canonical link element, string
|
|
canonical_s
|
|
|
|
## link from the url property inside the refresh link element, string
|
|
refresh_s
|
|
|
|
## all texts in <li> tags, textgen
|
|
li_txt
|
|
|
|
## number of <li> tags, int
|
|
licount_i
|
|
|
|
## all texts inside of <b> or <strong> tags. no doubles. listed in the order of number of occurrences in decreasing order, textgen
|
|
bold_txt
|
|
|
|
## number of occurrences of texts in bold_txt, textgen
|
|
#bold_val
|
|
|
|
## total number of occurrences of <b> or <strong>, int
|
|
boldcount_i
|
|
|
|
## all texts inside of <i> tags. no doubles. listed in the order of number of occurrences in decreasing order, textgen
|
|
italic_txt
|
|
|
|
## number of occurrences of texts in italic_txt, textgen
|
|
#italic_val
|
|
|
|
## total number of occurrences of <i>, int
|
|
italiccount_i
|
|
|
|
## flag that shows if a swf file is linked, boolean
|
|
flash_b
|
|
|
|
## list of all links to frames, textgen
|
|
frames_txt
|
|
|
|
## number of attr_frames, int
|
|
framesscount_i
|
|
|
|
## list of all links to iframes, textgen
|
|
iframes_txt
|
|
|
|
## number of attr_iframes, int
|
|
iframesscount_i
|
|
|
|
## names of cms attributes; if several are recognized then they are listen in decreasing order of number of matching criterias, textgen
|
|
#ext_cms_txt
|
|
|
|
##number of attributes that count for a specific cms in attr_cms, textgen
|
|
#ext_cms_val
|
|
|
|
## names of ad-servers/ad-services, textgen
|
|
#ext_ads_txt
|
|
|
|
## number of attributes counts in attr_ads, textgen
|
|
#ext_ads_val
|
|
|
|
## names of recognized community functions, textgen
|
|
#ext_community_txt
|
|
|
|
## number of attribute counts in attr_community, textgen
|
|
#ext_community_val
|
|
|
|
## names of map services, textgen
|
|
#ext_maps_txt
|
|
|
|
## number of attribute counts in attr_maps, textgen
|
|
#ext_maps_val
|
|
|
|
## names of tracker server, textgen
|
|
#ext_tracker_txt
|
|
|
|
## number of attribute counts in attr_tracker, textgen
|
|
#ext_tracker_val
|
|
|
|
## names matching title expressions, textgen
|
|
#ext_title_txt
|
|
|
|
## number of matching title expressions, textgen
|
|
#ext_title_val
|
|
|
|
## fail reason if a page was not loaded. if the page was loaded then this field is empty, text
|
|
failreason_t
|
|
|
|
## response time of target server in milliseconds, int
|
|
responsetime_i
|
|
|
|
|
|
### values used additionally by URIMetadataRow, part of the index transfer process
|
|
|
|
## time when resource was loaded
|
|
load_date_dt
|
|
|
|
## date until resource shall be considered as fresh
|
|
fresh_date_dt
|
|
|
|
## id of the host, a 6-byte hash that is part of the document id
|
|
host_id_s
|
|
|
|
## ids of referrer to this document
|
|
referrer_id_txt
|
|
|
|
## the md5 of the raw source
|
|
md5_s
|
|
|
|
## the name of the publisher of the document
|
|
publisher_t
|
|
|
|
## the language used in the document; starts with primary language
|
|
language_txt
|
|
|
|
## an external ranking value
|
|
ranking_i
|
|
|
|
## the size of the raw source
|
|
size_i
|
|
|
|
## number of links to audio resources
|
|
audiolinkscount_i
|
|
|
|
## number of links to video resources
|
|
videolinkscount_i
|
|
|
|
## number of links to application resources
|
|
applinkscount_i
|
|
|
|
## index creation comment
|
|
process_s |