2013-02-21 13:23:55 +01:00
## this is a list of all solr keys for the webgraph index 'webgraph', an index of all links
## this complete list of keys can be changed; the actual schema is stored in:
## DATA/SETTINGS/solr.webgraph.schema
## 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
##
## document organization
##
## primary key of document, a combination of <source-url-hash><target-url-hash><four-digit-hex-counter> (28 characters)
id
2013-02-22 15:45:15 +01:00
## last-modified from http header, date (mandatory field)
last_modified
## time when resource was loaded
2013-03-14 01:35:38 +01:00
#load_date_dt
2013-02-22 15:45:15 +01:00
2013-02-21 13:23:55 +01:00
## tags that are attached to crawls/index generation to separate the search result into user-defined subsets
collection_sxt
2014-04-16 22:16:20 +02:00
## needed (post-)processing steps on this metadata set
2013-03-14 01:35:38 +01:00
#process_sxt
2013-09-25 14:38:24 +02:00
## key from a harvest process (i.e. the crawl profile hash key) which is needed for near-realtime postprocessing. This shall be deleted as soon as postprocessing has been terminated.
harvestkey_s
2013-03-14 01:35:38 +01:00
2013-02-21 13:23:55 +01:00
##
## url construction information about the source
##
## primary key of document, the URL hash (source)
source_id_s
2013-02-22 15:45:15 +01:00
## the protocol of the url (source)
#source_protocol_s
## the url without the protocol (source)
#source_urlstub_s
2013-02-21 13:23:55 +01:00
2013-06-25 16:27:20 +02:00
## the file name without the extension (source)
#source_file_name_s
2013-02-21 13:23:55 +01:00
## the file name extension (source)
#source_file_ext_s
## number of all characters in the url (source)
#source_chars_i
## path of the url (source)
#source_path_s
## count of all path elements in the url (source)
#source_path_folders_count_i
2013-06-25 16:27:20 +02:00
## all path elements in the url without the file name (source)
2013-02-21 13:23:55 +01:00
#source_path_folders_sxt
## number of key-value pairs in search part of the url (source)
#source_parameter_count_i
## the keys from key-value pairs in the search part of the url (source)
#source_parameter_key_sxt
## the values from key-value pairs in the search part of the url (source)
#source_parameter_value_sxt
## depth of web page according to number of clicks from the 'main' page, which is the page that appears if only the host is entered as url (source)
2014-04-16 22:16:20 +02:00
#source_crawldepth_i
2013-02-21 13:23:55 +01:00
2013-09-27 16:57:05 +02:00
## copy of the citation rank norm value from the source link
2013-12-04 17:48:12 +01:00
#source_cr_host_norm_i
2013-09-27 16:57:05 +02:00
2013-02-22 15:45:15 +01:00
## host of the url (source)
2013-02-21 13:23:55 +01:00
#source_host_s
2013-02-22 15:45:15 +01:00
## id of the host (source)
source_host_id_s
2013-02-21 13:23:55 +01:00
## the Domain Class Name, either the TLD or a combination of ccSLD+TLD if a ccSLD is used (source)
#source_host_dnc_s
## either the second level domain or, if a ccSLD is used, the third level domain
#source_host_organization_s
## the organization and dnc concatenated with '.' (source)
#source_host_organizationdnc_s
## the remaining part of the host without organizationdnc (source)
#source_host_subdomain_s
##
## Information in the source about the target
##
## the text content of the a-tag (in source, but pointing to a target)
2014-08-01 13:20:25 +02:00
target_linktext_s
2013-02-21 13:23:55 +01:00
## the length of the a-tag content text as number of characters (in source, but pointing to a target)
#target_linktext_charcount_i
## the length of the a-tag content text as number of words (in source, but pointing to a target)
#target_linktext_wordcount_i
## if the link is an image link, this contains the alt tag if the image is also liked as img link (in source, but pointing to a target)
2014-08-01 13:20:25 +02:00
target_alt_s
2013-02-21 13:23:55 +01:00
## the length of the a-tag content text as number of characters (in source, but pointing to a target)
#target_alt_charcount_i
## the length of the a-tag content text as number of words (in source, but pointing to a target)
#target_alt_wordcount_i
## the name property of the a-tag (in source, but pointing to a target)
target_name_t
## the rel property of the a-tag (in source, but pointing to a target)
#target_rel_s
## the rel property of the a-tag, coded binary (in source, but pointing to a target)
#target_relflags_i
##
## url construction information about the target
##
## primary key of document, the URL hash (target)
target_id_s
2013-09-15 23:27:04 +02:00
## order number of target url, a count from first to last URL on the source page (target)
target_order_i
2013-02-22 15:45:15 +01:00
## the protocol of the url (target)
target_protocol_s
## the url without the protocol (target)
target_urlstub_s
2013-02-21 13:23:55 +01:00
2013-06-25 16:27:20 +02:00
## the file name without the extension (target)
target_file_name_s
2013-02-21 13:23:55 +01:00
## the file name extension (target)
target_file_ext_s
## number of all characters in the url (target)
#target_chars_i
## path of the url (target)
#target_path_s
## count of all path elements in the url (target)
#target_path_folders_count_i
2013-06-25 16:27:20 +02:00
## all path elements in the url without the file name (target)
2013-02-21 13:23:55 +01:00
target_path_folders_sxt
## number of key-value pairs in search part of the url (target)
#target_parameter_count_i
## the keys from key-value pairs in the search part of the url (target)
#target_parameter_key_sxt
## the values from key-value pairs in the search part of the url (target)
#target_parameter_value_sxt
2013-03-17 22:13:56 +01:00
## depth of web page according to number of clicks from the 'main' page, which is the page that appears if only the host is entered as url (target)
2014-04-16 22:16:20 +02:00
#target_crawldepth_i
2013-02-21 13:23:55 +01:00
2013-09-27 16:57:05 +02:00
## copy of the citation rank norm value from the target link; this is only filled if the target host is identical to the source host
2013-12-04 17:48:12 +01:00
#target_cr_host_norm_i
2013-09-27 16:57:05 +02:00
2013-02-21 13:23:55 +01:00
## host of the url (target)
#target_host_s
2013-02-22 15:45:15 +01:00
## id of the host (target)
target_host_id_s
2013-02-21 13:23:55 +01:00
## the Domain Class Name, either the TLD or a combination of ccSLD+TLD if a ccSLD is used (target)
#target_host_dnc_s
## either the second level domain or, if a ccSLD is used, the third level domain (target)
#target_host_organization_s
## the organization and dnc concatenated with '.' (target)
#target_host_organizationdnc_s
## the remaining part of the host without organizationdnc (target)
#target_host_subdomain_s
2013-02-22 15:45:15 +01:00
## flag shows if the target host is equal to the source host
target_inbound_b