chunkSize - integer
The number of items to batch for each round of fetching. A higher value can make crawling faster, but memory usage is also increased. The default is 1.
Default: 1
commitAfterItems - integer
Commit the crawlDB to disk after this many items have been received. A smaller number here will result in a slower crawl because of commits to disk being more frequent; conversely, a larger number here will cause a resumed job after a crash to need to recrawl more records.
Default: 10000
crawlDBType - string
The type of crawl database to use, in-memory or on-disk.
Default: on-disk
Allowed values: on-diskin-memory
db - Connector DB
Type and properties for a ConnectorDB implementation to use with this datasource.
aliases - boolean
Keep track of original URI-s that resolved to the current URI. This negatively impacts performance and size of DB.
Default: false
inlinks - boolean
Keep track of incoming links. This negatively impacts performance and size of DB.
Default: false
inv_aliases - boolean
Keep track of target URI-s that the current URI resolves to. This negatively impacts performance and size of DB.
Default: false
type - string
Fully qualified class name of ConnectorDb implementation.
>= 1 characters
Default: com.lucidworks.connectors.db.impl.MapDbConnectorDb
dedupe - boolean
If true, documents will be deduplicated. Deduplication can be done based on an analysis of the content, on the content of a specific field, or by a JavaScript function. If neither a field nor a script are defined, content analysis will be used.
Default: false
dedupeField - string
Field to be used for dedupe. Define either a field or a dedupe script, otherwise the full raw content of each document will be used.
dedupeSaveSignature - boolean
If true,the signature used for dedupe will be stored in a 'dedupeSignature_s' field. Note this may cause errors about 'immense terms' in that field.
Default: false
dedupeScript - string
Custom javascript to dedupe documents. The script must define a 'genSignature(content){}' function, but can use any combination of document fields. The function must return a string.
delete - boolean
Set to true to remove documents from the index when they can no longer be accessed as unique documents.
Default: true
deleteErrorsAfter - integer
Number of fetch failures to tolerate before removing a document from the index. The default of -1 means no fetch failures will be removed.
Default: -1
depth - integer
Number of levels in a directory or site tree to descend for documents.
Default: -1
diagnosticMode - boolean
Enable to print more detailed information to the logs about each request.
Default: false
emitThreads - integer
The number of threads used to send documents from the connector to the index pipeline. The default is 5.
Default: 5
excludeExtensions - array[string]
File extensions that should not to be fetched. This will limit this datasource to all extensions except this list.
excludeRegexes - array[string]
Regular expressions for URI patterns to exclude. This will limit this datasource to only URIs that do not match the regular expression.
f.blobs - boolean
Default: false
f.branches - boolean
Default: false
f.collaborators - boolean
Default: false
f.commit_comments - boolean
Default: false
f.commit_diffs - boolean
Default: false
f.commits - boolean
Default: true
f.github_accept_self_signed_ssl_certificate - boolean
Default: true
f.github_base_url - string
Default: https://github.com
f.github_enterprise - boolean
Default: false
f.github_oauth_token - string
f.issue_comments - boolean
Default: false
f.issues - boolean
Default: true
f.milestones - boolean
Default: false
f.pull_request_comments - boolean
Default: false
f.pull_requests - boolean
Default: true
f.releases - boolean
Default: false
f.tags - boolean
Default: false
failFastOnStartLinkFailure - boolean
If true, when Fusion cannot connect to any of the provided start links, the crawl is stopped and an exception logged.
Default: true
fetchDelayMS - integer
Number of milliseconds to wait between fetch requests. The default is 0. This property can be used to throttle a crawl if necessary.
Default: 0
fetchThreads - integer
The number of threads to use during fetching. The value is 1 when 'enterprise:false', if 'enterprise:true' the threads can be incremented
Default: 1
forceRefresh - boolean
Set to true to recrawl all items even if they have not changed since the last crawl.
Default: false
forceRefreshClearSignatures - boolean
If true, signatures will be cleared if force recrawl is enabled.
Default: true
includeExtensions - array[string]
File extensions to be fetched. This will limit this datasource to only these file extensions.
includeRegexes - array[string]
Regular expressions for URI patterns to include. This will limit this datasource to only URIs that match the regular expression.
indexCrawlDBToSolr - boolean
EXPERIMENTAL: Set to true to index the crawl-database into a 'crawldb_<datasource-ID>' collection in Solr.
Default: false
initial_mapping - Initial field mapping
Provides mapping of fields before documents are sent to an index pipeline.
condition - string
Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.
label - string
A unique label for this stage.
<= 255 characters
mappings - array[object]
List of mapping rules
Default: {"operation":"move","source":"charSet","target":"charSet_s"}{"operation":"move","source":"fetchedDate","target":"fetchedDate_dt"}{"operation":"move","source":"lastModified","target":"lastModified_dt"}{"operation":"move","source":"signature","target":"dedupeSignature_s"}{"operation":"move","source":"length","target":"length_l"}{"operation":"move","source":"mimeType","target":"mimeType_s"}{"operation":"move","source":"parent","target":"parent_s"}{"operation":"move","source":"owner","target":"owner_s"}{"operation":"move","source":"group","target":"group_s"}
object attributes:{operation : {
display name: Operation
type: string
}source required : {
display name: Source Field
type: string
}target : {
display name: Target Field
type: string
}}
reservedFieldsMappingAllowed - boolean
Default: false
skip - boolean
Set to true to skip this stage.
Default: false
unmapped - Unmapped Fields
If fields do not match any of the field mapping rules, these rules will apply.
operation - string
The type of mapping to perform: move, copy, delete, add, set, or keep.
Default: copy
Allowed values: copymovedeletesetaddkeep
source - string
The name of the field to be mapped.
target - string
The name of the field to be mapped to.
maxItems - integer
Maximum number of documents to fetch. The default (-1) means no limit.
Default: -1
refreshAll - boolean
Set to true to always recrawl all items found in the crawldb.
Default: true
refreshErrors - boolean
Set to true to recrawl items that failed during the last crawl.
Default: false
refreshIDPrefixes - array[string]
A prefix to recrawl all items whose IDs begin with this value.
refreshIDRegexes - array[string]
A regular expression to recrawl all items whose IDs match this pattern.
refreshOlderThan - integer
Number of seconds to recrawl items whose last fetched date is longer ago than this value.
Default: -1
refreshScript - string
A JavaScript function ('shouldRefresh()') to customize the items recrawled.
refreshStartLinks - boolean
Set to true to recrawl items specified in the list of start links.
Default: false
retryEmit - boolean
Set to true for emit batch failures to be retried on a document-by-document basis.
Default: true
rewriteLinkScript - string
A Javascript function 'rewriteLink(link) { }' to modify links to documents before they are fetched.
startLinks - array[string]
The link to the GitHub repository to be crawled, e.g., https://github.com/lucidimagination/testing