> ## Documentation Index > Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt > Use this file to discover all available pages before exploring further. # Local Filesystem V1 > This connector traverses a network file system (NFS), where a shared drive is mounted to the same location on all hosts in the cluster that are running this connector. export const schema = { "category": "Other", "categoryPriority": 1, "description": "Connector for filesystems locally mounted to the Fusion server.", "properties": { "category": { "default": "Filesystem", "hints": ["hidden", "readonly"], "title": "Category", "type": "string" }, "connector": { "description": "Connector Type.", "hints": ["hidden"], "minLength": 1, "title": "Connector Type", "type": "string" }, "description": { "description": "Optional description for this datasource.", "title": "Description", "type": "string" }, "id": { "description": "Unique name for this datasource.", "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$", "title": "Datasource ID", "type": "string" }, "parserId": { "default": "_system", "description": "Parser used when parsing raw content. For some connectors, a configuration to 'retry' parsing if an error occurs is available as an advanced setting", "title": "Parser", "type": "string" }, "pipeline": { "description": "Name of an existing index pipeline for processing documents.", "minLength": 1, "title": "Pipeline ID", "type": "string" }, "properties": { "description": "Datasource configuration properties", "properties": { "aliasExpiration": { "default": 1, "description": "The number of crawls after which an alias will expire. The default is 1 crawl.", "hints": ["advanced"], "title": "Alias expiration", "type": "integer" }, "chunkSize": { "default": 1, "description": "The number of items to batch for each round of fetching. A higher value can make crawling faster, but memory usage is also increased. The default is 1.", "hints": ["advanced"], "title": "Fetch batch size", "type": "integer" }, "collection": { "description": "Collection documents will be indexed to.", "hints": ["hidden"], "pattern": "^[a-zA-Z0-9_-]+$", "title": "Collection", "type": "string" }, "commitAfterItems": { "default": 10000, "description": "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.", "hints": ["advanced"], "title": "Commit After This Many Items", "type": "integer" }, "crawlDBType": { "default": "on-disk", "description": "The type of crawl database to use, in-memory or on-disk.", "enum": ["in-memory", "on-disk"], "hints": ["advanced"], "title": "Crawl database type", "type": "string" }, "db": { "description": "Type and properties for a ConnectorDB implementation to use with this datasource.", "hints": ["hidden"], "properties": { "aliases": { "default": false, "description": "Keep track of original URI-s that resolved to the current URI. This negatively impacts performance and size of DB.", "title": "Process Aliases?", "type": "boolean" }, "inlinks": { "default": false, "description": "Keep track of incoming links. This negatively impacts performance and size of DB.", "title": "Process Inlinks?", "type": "boolean" }, "inv_aliases": { "default": false, "description": "Keep track of target URI-s that the current URI resolves to. This negatively impacts performance and size of DB.", "title": "Process Inverted Aliases?", "type": "boolean" }, "type": { "default": "com.lucidworks.connectors.db.impl.MapDbConnectorDb", "description": "Fully qualified class name of ConnectorDb implementation.", "minLength": 1, "title": "Implementation Class Name", "type": "string" } }, "required": ["type"], "title": "Connector DB", "type": "object" }, "dedupe": { "default": false, "description": "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.", "hints": ["advanced"], "title": "Dedupe documents", "type": "boolean" }, "dedupeField": { "description": "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.", "hints": ["advanced"], "title": "Dedupe field", "type": "string" }, "dedupeSaveSignature": { "default": false, "description": "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.", "hints": ["advanced"], "title": "Save dedupe signature", "type": "boolean" }, "dedupeScript": { "description": "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.", "hints": ["advanced", "code", "code/javascript"], "title": "Dedupe script", "type": "string" }, "delete": { "default": true, "description": "Set to true to remove documents from the index when they can no longer be accessed as unique documents.", "hints": ["advanced"], "title": "Delete dead URIs", "type": "boolean" }, "deleteErrorsAfter": { "default": -1, "description": "Number of fetch failures to tolerate before removing a document from the index. The default of -1 means no fetch failures will be removed.", "hints": ["advanced"], "title": "Fetch failure allowance", "type": "integer" }, "depth": { "default": -1, "description": "Number of levels in a directory or site tree to descend for documents.", "title": "Max crawl depth", "type": "integer" }, "diagnosticMode": { "default": false, "description": "Enable to print more detailed information to the logs about each request.", "hints": ["advanced"], "title": "Diagnostic mode", "type": "boolean" }, "emitThreads": { "default": 5, "description": "The number of threads used to send documents from the connector to the index pipeline. The default is 5.", "title": "Emit threads", "type": "integer" }, "excludeExtensions": { "description": "File extensions that should not to be fetched. This will limit this datasource to all extensions except this list.", "items": { "type": "string" }, "title": "Excluded file extensions", "type": "array" }, "excludeRegexes": { "description": "Regular expressions for URI patterns to exclude. This will limit this datasource to only URIs that do not match the regular expression.", "items": { "type": "string" }, "title": "Exclusive regexes", "type": "array" }, "f.addFileMetadata": { "default": true, "description": "Set to true to add information about documents found in the filesystem to the document, such as document owner, group, or ACL permissions.", "title": "Add file metadata", "type": "boolean" }, "f.index_items_discarded": { "default": false, "description": "Enable to index discarded document metadata", "title": "Index discarded document metadata", "type": "boolean" }, "f.maxSizeBytes": { "default": 4194304, "description": "Maximum size (in bytes) of documents to fetch or -1 for unlimited file size.", "title": "Maximum file size (bytes)", "type": "integer" }, "f.minSizeBytes": { "default": 0, "description": "Minimum size, in bytes, of documents to fetch.", "title": "Minimum file size (bytes)", "type": "integer" }, "failFastOnStartLinkFailure": { "default": true, "description": "If true, when Fusion cannot connect to any of the provided start links, the crawl is stopped and an exception logged.", "hints": ["advanced"], "title": "Fail crawl if start links are invalid", "type": "boolean" }, "fetchDelayMS": { "default": 0, "description": "Number of milliseconds to wait between fetch requests. The default is 0. This property can be used to throttle a crawl if necessary.", "hints": ["advanced"], "title": "Fetch delay", "type": "integer" }, "fetchThreads": { "default": 5, "description": "The number of threads to use during fetching. The default is 5.", "title": "Fetch threads", "type": "integer" }, "forceRefresh": { "default": false, "description": "Set to true to recrawl all items even if they have not changed since the last crawl.", "hints": ["advanced"], "title": "Force recrawl", "type": "boolean" }, "forceRefreshClearSignatures": { "default": true, "description": "If true, signatures will be cleared if force recrawl is enabled.", "hints": ["advanced"], "title": "Clear signatures", "type": "boolean" }, "includeExtensions": { "description": "File extensions to be fetched. This will limit this datasource to only these file extensions.", "items": { "type": "string" }, "title": "Included file extensions", "type": "array" }, "includeRegexes": { "description": "Regular expressions for URI patterns to include. This will limit this datasource to only URIs that match the regular expression.", "items": { "type": "string" }, "title": "Inclusive regexes", "type": "array" }, "initial_mapping": { "category": "Field Transformation", "categoryPriority": 7, "description": "Provides mapping of fields before documents are sent to an index pipeline.", "hints": ["advanced"], "properties": { "condition": { "description": "Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.", "hints": ["code", "code/javascript", "advanced"], "title": "Condition", "type": "string" }, "label": { "description": "A unique label for this stage.", "hints": ["advanced"], "maxLength": 255, "title": "Label", "type": "string" }, "mappings": { "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" }], "description": "List of mapping rules", "hints": ["advanced"], "items": { "properties": { "operation": { "default": "copy", "description": "The type of mapping to perform: move, copy, delete, add, set, or keep.", "enum": ["copy", "move", "delete", "set", "add", "keep"], "hints": ["advanced"], "title": "Operation", "type": "string" }, "source": { "description": "The name of the field to be mapped.", "hints": ["advanced"], "title": "Source Field", "type": "string" }, "target": { "description": "The name of the field to be mapped to.", "hints": ["advanced"], "title": "Target Field", "type": "string" } }, "required": ["source"], "type": "object" }, "title": "Field Mappings", "type": "array" }, "reservedFieldsMappingAllowed": { "default": false, "hints": ["advanced"], "title": "Allow System Fields Mapping?", "type": "boolean" }, "skip": { "default": false, "description": "Set to true to skip this stage.", "hints": ["advanced"], "title": "Skip This Stage", "type": "boolean" }, "unmapped": { "description": "If fields do not match any of the field mapping rules, these rules will apply.", "hints": ["advanced"], "properties": { "operation": { "default": "copy", "description": "The type of mapping to perform: move, copy, delete, add, set, or keep.", "enum": ["copy", "move", "delete", "set", "add", "keep"], "hints": ["advanced"], "title": "Operation", "type": "string" }, "source": { "description": "The name of the field to be mapped.", "hints": ["advanced"], "title": "Source Field", "type": "string" }, "target": { "description": "The name of the field to be mapped to.", "hints": ["advanced"], "title": "Target Field", "type": "string" } }, "required": ["source"], "title": "Unmapped Fields", "type": "object" } }, "title": "Initial field mapping", "type": "object", "unsafe": false }, "maxItems": { "default": -1, "description": "Maximum number of documents to fetch. The default (-1) means no limit.", "title": "Max items", "type": "integer" }, "refreshAll": { "default": true, "description": "Set to true to always recrawl all items found in the crawldb.", "hints": ["advanced"], "title": "Recrawl all items", "type": "boolean" }, "refreshErrors": { "default": false, "description": "Set to true to recrawl items that failed during the last crawl.", "hints": ["advanced"], "title": "Recrawl errors", "type": "boolean" }, "refreshIDPrefixes": { "description": "A prefix to recrawl all items whose IDs begin with this value.", "hints": ["advanced"], "items": { "type": "string" }, "title": "Recrawl ID prefixes", "type": "array" }, "refreshIDRegexes": { "description": "A regular expression to recrawl all items whose IDs match this pattern.", "hints": ["advanced"], "items": { "type": "string" }, "title": "Recrawl ID regexes", "type": "array" }, "refreshOlderThan": { "default": -1, "description": "Number of seconds to recrawl items whose last fetched date is longer ago than this value.", "hints": ["advanced"], "title": "Recrawl age", "type": "integer" }, "refreshScript": { "description": "A JavaScript function ('shouldRefresh()') to customize the items recrawled. ", "hints": ["advanced", "code", "code/javascript"], "title": "Recrawl script", "type": "string" }, "refreshStartLinks": { "default": false, "description": "Set to true to recrawl items specified in the list of start links.", "hints": ["advanced"], "title": "Recrawl start links", "type": "boolean" }, "restrictToTree": { "default": true, "description": "If true, only documents found in a tree below the start links will be fetched. By default, this means limiting the crawl to the domain of the start links. For example, if the start link is 'http://host.com/US' then only links to the 'host.com' domain will be followed. Further options are available for modifying this behavior.", "title": "Restrict crawl to start-link tree", "type": "boolean" }, "retainOutlinks": { "default": false, "description": "Set to true for links found during fetching to be stored in the crawldb. This increases precision in certain recrawl scenarios, but requires more memory and disk space.", "hints": ["advanced"], "title": "Retain links in the crawldb", "type": "boolean" }, "retryEmit": { "default": true, "description": "Set to true for emit batch failures to be retried on a document-by-document basis.", "hints": ["advanced"], "title": "Retry emits", "type": "boolean" }, "rewriteLinkScript": { "description": "A Javascript function 'rewriteLink(link) { }' to modify links to documents before they are fetched.", "hints": ["advanced", "code", "code/javascript"], "title": "URI rewrite script", "type": "string" }, "startLinks": { "description": "One or more paths to files or directories to index, e.g. /path/to/folder, or /path/to/file.txt", "items": { "minLength": 1, "type": "string" }, "title": "Start Links", "type": "array" }, "trackEmbeddedIDs": { "default": true, "description": "Track IDs produced by splitters to enable dedupe and deletion of embedded content?", "hints": ["advanced"], "title": "Track embedded IDs?", "type": "boolean" } }, "propertyGroups": [{ "label": "Limit Documents", "properties": ["f.maxSizeBytes", "f.minSizeBytes", "f.addFileMetadata", "f.index_items_discarded", "restrictToTree", "depth", "maxItems", "includeExtensions", "includeRegexes", "excludeExtensions", "excludeRegexes"] }, { "label": "Crawl Performance", "properties": ["chunkSize", "fetchThreads", "fetchDelayMS", "emitThreads", "retryEmit", "failFastOnStartLinkFailure"] }, { "label": "Dedupe", "properties": ["dedupe", "dedupeSaveSignature", "dedupeField", "dedupeScript"] }, { "label": "Recrawl Rules", "properties": ["delete", "deleteErrorsAfter", "refreshAll", "refreshStartLinks", "refreshErrors", "refreshOlderThan", "refreshIDPrefixes", "refreshIDRegexes", "refreshScript", "forceRefresh", "forceRefreshClearSignatures"] }, { "label": "Crawl History", "properties": ["retainOutlinks", "aliasExpiration", "commitAfterItems", "crawlDBType"] }, { "label": "Field Mapping", "properties": ["initial_mapping"] }], "required": ["startLinks"], "title": "Properties", "type": "object" }, "type": { "description": "Datasource type supported by the selected connector type.", "hints": ["hidden"], "minLength": 1, "title": "Datasource Type", "type": "string" }, "type_description": { "default": "Connector for filesystems locally mounted to the Fusion server.", "hints": ["hidden", "readonly"], "title": "Type Description", "type": "string" } }, "required": ["id", "connector", "type", "pipeline", "properties"], "title": "Local Filesystem", "type": "object", "unsafe": false }; export const SchemaParamFields = ({schema}) => { const sanitize = str => { if (typeof str !== "string") return str; return str.replace(/^"(.*)"$/s, "$1").replace(/\\/g, "").replace(/"/g, "'"); }; const formatDescription = str => { const s = sanitize(str); return (/[.!?]\)*$/).test(s) ? s : `${s}.`; }; const {description, properties = {}, required: requiredProps = []} = schema; const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]); return
{description &&

{formatDescription(description)}

} {visibleProps.map(([name, prop]) => { const isRequired = requiredProps.includes(name); const hasDefault = prop.default !== undefined; const rawDefault = prop.default; const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"'))); const fieldProps = { key: name, body: prop.title || name, type: prop.type, ...prop.title && ({ post: [<>API property: {name}] }), ...isRequired && ({ required: true }), ...!isComplexDefault && hasDefault ? { default: sanitize(String(rawDefault)) } : {} }; const isObject = prop.type === "object" && prop.properties; const isArrayOfObjects = prop.type === "array" && prop.items?.type === "object" && prop.items.properties; return {prop.description &&

{formatDescription(prop.description)}

} {isComplexDefault &&

Default: 

                  
                    {JSON.stringify(rawDefault, null, 2)}
} {isArrayOfObjects &&

Object attributes: 

                
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) &&  required}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    )}
                  {'}'}
} {isObject && } ; })}
; }; export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => { const [isLoaded, setIsLoaded] = useState(false); useEffect(() => { const timer = setTimeout(() => { setIsLoaded(true); }, 500); return () => clearTimeout(timer); }, []); return
{isLoaded && ` }} />} Powered by Lucidworks Agent Studio
; }; [localhost link]: http://localhost:3000/docs/fusion-connectors/connectors/v1/local-filesystem-v1 [mintlify link]: https://doc.lucidworks.com/docs/fusion-connectors/connectors/v1/local-filesystem-v1 [old doc.lw link]: https://doc.lucidworks.com/fusion-connectors/42 **Compatible with Fusion version:** 4.0.0 through 5.1.5 This connector traverses a network file system (NFS), where a shared drive is mounted to the same location on all hosts in the cluster that are running this connector. The crawler captures information about the node, such as filename, permissions, date of creation, last modification, and last access, as well as the contents of the nodes. The extent of the network of nodes to be traversed is discovered during the crawl, when each node (such as a Unix file directory) provides information about its child nodes (such as the files in that directory) or references other nodes (such as links in an HTML document). The connector provides rules to limit the crawl and recrawling. These rules use datasource configuration properties to limit the extent of the network (depth of nodes to explore) as well as limiting processing to a subset of files based on file names and file size. An overall limit can be set on number of files retrieved during a crawl. **Important** As of Fusion 4.1.1, Fusion comes bundled with the V2 Local Filesystem Connector. The V1 Local Filesystem Connector for Fusion 4.x can be downloaded from [Fusion 4.x V1 Connector Downloads](/docs/fusion-connectors/downloads/fusion-4-x-connector-downloads). ## Configuration When entering configuration values in the UI, use *unescaped* characters, such as `\t` for the tab character. When entering configuration values in the API, use *escaped* characters, such as `\\t` for the tab character.