> ## 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. # Dropbox V1 > The Dropbox connector retrieves data from a Dropbox cloud-based data repository. export const schema = { "type": "object", "title": "Dropbox", "description": "Connector for Dropbox file storage. To use this connector, you must first register an application with access to the Dropbox API via http://www.dropbox.com/developers.", "required": ["id", "connector", "type", "pipeline", "properties"], "properties": { "category": { "type": "string", "title": "Category", "default": "Filesystem", "hints": ["hidden", "readonly"] }, "id": { "type": "string", "title": "Datasource ID", "description": "Unique name for this datasource.", "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$" }, "connector": { "type": "string", "title": "Connector Type", "description": "Connector Type.", "hints": ["hidden"], "minLength": 1 }, "type": { "type": "string", "title": "Datasource Type", "description": "Datasource type supported by the selected connector type.", "hints": ["hidden"], "minLength": 1 }, "pipeline": { "type": "string", "title": "Pipeline ID", "description": "Name of an existing index pipeline for processing documents.", "minLength": 1 }, "description": { "type": "string", "title": "Description", "description": "Optional description for this datasource." }, "type_description": { "type": "string", "title": "Type Description", "default": "Connector for Dropbox file storage. To use this connector, you must first register an application with access to the Dropbox API via http://www.dropbox.com/developers.", "hints": ["hidden", "readonly"] }, "parserId": { "type": "string", "title": "Parser", "description": "Parser used when parsing raw content. For some connectors, a configuration to 'retry' parsing if an error occurs is available as an advanced setting" }, "properties": { "type": "object", "title": "Properties", "description": "Datasource configuration properties", "required": ["startLinks", "f.fs.oAuthAccessToken"], "properties": { "startLinks": { "type": "array", "title": "Start Links", "description": "To crawl all of the files owned by the account, simply add ‘/’ as the start link; otherwise, use a path to the specific files or directories that you want to crawl, e.g., https://www.dropbox.com/home/Test_files/test_basic_crawl", "items": { "type": "string", "minLength": 1 } }, "collection": { "type": "string", "title": "Collection", "description": "Collection documents will be indexed to.", "hints": ["hidden"], "pattern": "^[a-zA-Z0-9_-]+$" }, "db": { "type": "object", "title": "Connector DB", "description": "Type and properties for a ConnectorDB implementation to use with this datasource.", "required": ["type"], "properties": { "type": { "type": "string", "title": "Implementation Class Name", "description": "Fully qualified class name of ConnectorDb implementation.", "default": "com.lucidworks.connectors.db.impl.MapDbConnectorDb", "minLength": 1 }, "inlinks": { "type": "boolean", "title": "Process Inlinks?", "description": "Keep track of incoming links. This negatively impacts performance and size of DB.", "default": false }, "aliases": { "type": "boolean", "title": "Process Aliases?", "description": "Keep track of original URI-s that resolved to the current URI. This negatively impacts performance and size of DB.", "default": false }, "inv_aliases": { "type": "boolean", "title": "Process Inverted Aliases?", "description": "Keep track of target URI-s that the current URI resolves to. This negatively impacts performance and size of DB.", "default": false } }, "hints": ["hidden"] }, "dedupe": { "type": "boolean", "title": "Dedupe documents", "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.", "default": false, "hints": ["advanced"] }, "dedupeField": { "type": "string", "title": "Dedupe field", "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"] }, "dedupeScript": { "type": "string", "title": "Dedupe script", "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"] }, "dedupeSaveSignature": { "type": "boolean", "title": "Save dedupe signature", "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.", "default": false, "hints": ["advanced"] }, "delete": { "type": "boolean", "title": "Delete dead URIs", "description": "Set to true to remove documents from the index when they can no longer be accessed as unique documents.", "default": true }, "deleteErrorsAfter": { "type": "integer", "title": "Fetch failure allowance", "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.", "default": -1 }, "fetchThreads": { "type": "integer", "title": "Fetch threads", "description": "The number of threads to use during fetching. The default is 5.", "default": 5 }, "emitThreads": { "type": "integer", "title": "Emit threads", "description": "The number of threads used to send documents from the connector to the index pipeline. The default is 5.", "default": 5 }, "chunkSize": { "type": "integer", "title": "Fetch batch size", "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.", "default": 1, "hints": ["advanced"] }, "fetchDelayMS": { "type": "integer", "title": "Fetch delay", "description": "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, "hints": ["advanced"] }, "refreshAll": { "type": "boolean", "title": "Recrawl all items", "description": "Set to true to always recrawl all items found in the crawldb.", "default": true, "hints": ["advanced"] }, "refreshStartLinks": { "type": "boolean", "title": "Recrawl start links", "description": "Set to true to recrawl items specified in the list of start links.", "default": false, "hints": ["advanced"] }, "refreshErrors": { "type": "boolean", "title": "Recrawl errors", "description": "Set to true to recrawl items that failed during the last crawl.", "default": false, "hints": ["advanced"] }, "refreshOlderThan": { "type": "integer", "title": "Recrawl age", "description": "Number of seconds to recrawl items whose last fetched date is longer ago than this value.", "default": -1, "hints": ["advanced"] }, "refreshIDPrefixes": { "type": "array", "title": "Recrawl ID prefixes", "description": "A prefix to recrawl all items whose IDs begin with this value.", "hints": ["advanced"], "items": { "type": "string" } }, "refreshIDRegexes": { "type": "array", "title": "Recrawl ID regexes", "description": "A regular expression to recrawl all items whose IDs match this pattern.", "hints": ["advanced"], "items": { "type": "string" } }, "refreshScript": { "type": "string", "title": "Recrawl script", "description": "A JavaScript function ('shouldRefresh()') to customize the items recrawled. ", "hints": ["advanced", "code", "code/javascript"] }, "forceRefresh": { "type": "boolean", "title": "Force recrawl", "description": "Set to true to recrawl all items even if they have not changed since the last crawl.", "default": false, "hints": ["advanced"] }, "forceRefreshClearSignatures": { "type": "boolean", "title": "Clear signatures", "description": "If true, signatures will be cleared if force recrawl is enabled.", "default": true, "hints": ["advanced"] }, "retryEmit": { "type": "boolean", "title": "Retry emits", "description": "Set to true for emit batch failures to be retried on a document-by-document basis.", "default": true, "hints": ["advanced"] }, "depth": { "type": "integer", "title": "Max crawl depth", "description": "Number of levels in a directory or site tree to descend for documents.", "default": -1 }, "maxItems": { "type": "integer", "title": "Max items", "description": "Maximum number of documents to fetch. The default (-1) means no limit.", "default": -1 }, "failFastOnStartLinkFailure": { "type": "boolean", "title": "Fail crawl if start links are invalid", "description": "If true, when Fusion cannot connect to any of the provided start links, the crawl is stopped and an exception logged.", "default": true, "hints": ["advanced"] }, "crawlDBType": { "type": "string", "title": "Crawl database type", "description": "The type of crawl database to use, in-memory or on-disk.", "enum": ["in-memory", "on-disk"], "default": "on-disk", "hints": ["advanced"] }, "commitAfterItems": { "type": "integer", "title": "Commit After This Many Items", "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.", "default": 10000, "hints": ["advanced"] }, "initial_mapping": { "type": "object", "title": "Initial field mapping", "description": "Provides mapping of fields before documents are sent to an index pipeline.", "properties": { "skip": { "type": "boolean", "title": "Skip This Stage", "description": "Set to true to skip this stage.", "default": false, "hints": ["advanced"] }, "label": { "type": "string", "title": "Label", "description": "A unique label for this stage.", "hints": ["advanced"], "maxLength": 255 }, "condition": { "type": "string", "title": "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"] }, "reservedFieldsMappingAllowed": { "type": "boolean", "title": "Allow System Fields Mapping?", "default": false, "hints": ["advanced"] }, "retentionMappings": { "type": "array", "title": "Field Retention", "description": "Fields that should be kept or deleted", "default": [], "hints": ["advanced"], "items": { "type": "object", "required": ["field"], "properties": { "field": { "type": "string", "title": "Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: keep (default) or delete", "enum": ["keep", "delete"], "default": "keep", "hints": ["advanced"] } } } }, "updateMappings": { "type": "array", "title": "Field Value Updates", "description": "Values that should be added to or set on a field. When a value is added, any values previously on the field will be retained. When a value is set, any values previously on the field will be overwritten.", "default": [], "hints": ["advanced"], "items": { "type": "object", "required": ["field", "value"], "properties": { "field": { "type": "string", "title": "Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "value": { "type": "string", "title": "Value", "description": "The value to add to or set on the field.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: add (default) or set.", "enum": ["add", "set"], "default": "add", "hints": ["advanced"] } } } }, "translationMappings": { "type": "array", "title": "Field Translations", "description": "Fields that should be moved or copied to another field. When a field is moved, the values from the source field are moved over to the target field and the source field is removed. When a field is copied, the values from the source field are copied over to the target field and the source field is retained.", "default": [{ "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", "operation": "move" }], "hints": ["advanced"], "items": { "type": "object", "required": ["source", "target"], "properties": { "source": { "type": "string", "title": "Source Field", "description": "The name of the field to operate on.", "hints": ["advanced"] }, "target": { "type": "string", "title": "Target Field", "description": "The name of the target field.", "hints": ["advanced"] }, "operation": { "type": "string", "title": "Operation", "description": "The type of operation to perform: copy (default) or move.", "enum": ["copy", "move"], "default": "copy", "hints": ["advanced"] } } } }, "unmappedRule": { "type": "object", "title": "Unmapped Fields", "description": "Fields not mapped by the above rules. By default, any remaining fields will be kept on the document.", "properties": { "keep": { "type": "boolean", "title": "Keep", "description": "Keep all unmapped fields", "default": true, "hints": ["advanced"] }, "delete": { "type": "boolean", "title": "Delete", "description": "Delete all unmapped fields", "default": false, "hints": ["advanced"] }, "fieldToMoveValuesTo": { "type": "string", "title": "Move", "description": "Move all unmapped field values to this field", "hints": ["advanced"] }, "fieldToCopyValuesTo": { "type": "string", "title": "Copy", "description": "Copy all unmapped field values to this field", "hints": ["advanced"] }, "valueToAddToUnmappedFields": { "type": "string", "title": "Add", "description": "Add this value to all unmapped fields", "hints": ["advanced"] }, "valueToSetOnUnmappedFields": { "type": "string", "title": "Set", "description": "Set this value on all unmapped fields", "hints": ["advanced"] } }, "default": { "keep": true, "delete": false, "fieldToMoveValuesTo": "", "fieldToCopyValuesTo": "", "valueToAddToUnmappedFields": "", "valueToSetOnUnmappedFields": "" } } }, "category": "Field Transformation", "categoryPriority": 7, "hints": ["advanced"], "unsafe": false }, "f.maxSizeBytes": { "type": "integer", "title": "Maximum file size (bytes)", "description": "Maximum size (in bytes) of documents to fetch or -1 for unlimited file size.", "default": 20000000 }, "f.minSizeBytes": { "type": "integer", "title": "Minimum file size (bytes)", "description": "Minimum size, in bytes, of documents to fetch.", "default": 0 }, "f.addFileMetadata": { "type": "boolean", "title": "Add file metadata", "description": "Set to true to add information about documents found in the filesystem to the document, such as document owner, group, or ACL permissions.", "default": true }, "f.index_items_discarded": { "type": "boolean", "title": "Index discarded document metadata", "description": "Enable to index discarded document metadata", "default": false }, "aliasExpiration": { "type": "integer", "title": "Alias expiration", "description": "The number of crawls after which an alias will expire. The default is 1 crawl.", "default": 1, "hints": ["advanced"] }, "excludeExtensions": { "type": "array", "title": "Excluded file extensions", "description": "File extensions that should not to be fetched. This will limit this datasource to all extensions except this list.", "items": { "type": "string" } }, "excludeRegexes": { "type": "array", "title": "Exclusive regexes", "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" } }, "includeExtensions": { "type": "array", "title": "Included file extensions", "description": "File extensions to be fetched. This will limit this datasource to only these file extensions.", "items": { "type": "string" } }, "includeRegexes": { "type": "array", "title": "Inclusive regexes", "description": "Regular expressions for URI patterns to include. This will limit this datasource to only URIs that match the regular expression.", "items": { "type": "string" } }, "reevaluateCrawlDBOnStart": { "type": "boolean", "title": "Reevaluate crawldb on start?", "description": "Reevaluate exisiting crawldb entries for legality on startup?", "default": false, "hints": ["advanced"] }, "restrictToTree": { "type": "boolean", "title": "Restrict crawl to start-link tree", "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.", "default": true }, "retainOutlinks": { "type": "boolean", "title": "Retain links in the crawldb", "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.", "default": false, "hints": ["advanced"] }, "f.fs.oAuthAccessToken": { "type": "string", "title": "Dropbox OAuth Access Token", "description": "Dropbox OAuth Token for the registered application.", "hints": ["secret"] }, "f.fs.connect_timeout": { "type": "integer", "title": "Connect timeout", "description": "The connection timeout is the timeout in making the initial connection; i.e. completing the TCP connection handshake.", "default": 60000 }, "f.fs.read_timeout": { "type": "integer", "title": "Read timeout", "description": "The read timeout is the timeout on waiting to read data. Specifically, if the server fails to send a byte seconds after the last byte, a read timeout error will be raised.", "default": 60000 }, "rewriteLinkScript": { "type": "string", "title": "URI rewrite script", "description": "A Javascript function 'rewriteLink(link) { }' to modify links to documents before they are fetched.", "hints": ["advanced", "code", "code/javascript"] }, "diagnosticMode": { "type": "boolean", "title": "Diagnostic mode", "description": "Enable to print more detailed information to the logs about each request.", "default": false, "hints": ["advanced"] } }, "propertyGroups": [{ "label": "Limit Documents", "properties": ["restrictToTree", "depth", "maxItems", "includeExtensions", "includeRegexes", "excludeExtensions", "excludeRegexes", "delete", "deleteErrorsAfter", "f.maxSizeBytes", "f.minSizeBytes", "f.addFileMetadata", "f.index_items_discarded"] }, { "label": "Dedupe", "properties": ["dedupe", "dedupeSaveSignature", "dedupeField", "dedupeScript"] }, { "label": "Crawl History", "properties": ["retainOutlinks", "aliasExpiration", "crawlDBType", "commitAfterItems", "reevaluateCrawlDBOnStart"] }, { "label": "Recrawl Rules", "properties": ["refreshAll", "refreshStartLinks", "refreshErrors", "refreshOlderThan", "refreshIDPrefixes", "refreshIDRegexes", "refreshScript", "forceRefresh", "forceRefreshClearSignatures"] }, { "label": "Crawl Performance", "properties": ["chunkSize", "fetchThreads", "fetchDelayMS", "emitThreads", "retryEmit", "failFastOnStartLinkFailure"] }, { "label": "Field Mapping", "properties": ["initial_mapping"] }] } }, "category": "Other", "categoryPriority": 1, "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/dropbox [mintlify link]: https://doc.lucidworks.com/docs/fusion-connectors/connectors/v1/dropbox [old doc.lw link]: https://doc.lucidworks.com/fusion-connectors/37 **Compatible with Fusion version:** 4.0.0 through 5.12.0 V1 deprecation and removal notice All V1 connectors are deprecated in Fusion 5.18.0 and later. This means they are no longer being actively developed and will be removed in Fusion 6. V1 connectors were also previously deprecated in Fusion 5.12.0 but remained available in all versions between 5.12.0 and 5.18.0, including the Fusion 5.9.x long-term support release line, to support customers on those versions. The replacement for this connector is in active development at this time and will be released at a future date. If you are using this connector, you must migrate to the replacement connector or a supported alternative before upgrading to Fusion 6. Migrate to the replacement connector as soon as possible to avoid any disruption to your workflows. This connector is not available in Fusion 4.1.x. To fetch content from Dropbox, you must have an OAuth token accessible to the crawler so it can properly authenticate. If you want to crawl all of the files owned by the account, you can simply use `/` as the `startLink`. The `startLink` for a folder is its share link: * In the Dropbox Web UI, navigate to the folder and then to **Share Folder** > **Share with Dropbox** > **Create Link** (or **Copy Link** if the link has already been created). * In the Dropbox integration for the Finder in OS X , select the folder, right-click, and select **Copy Dropbox Link**. ## Learn more The Dropbox connector retrieves data from a Dropbox cloud-based data repository. In order to authenticate to Dropbox, you must have an access token. This is obtained by first creating an app in the Dropbox platform as follows: 1. Go to [https://www.dropbox.com/developers/apps](https://www.dropbox.com/developers/apps) and sign in with your Dropbox credentials. The **My Apps** page appears. 2. Click **Create app**. Dropbox prompts you to enter the following information: 1. Choose an API: Select **Dropbox API**. 2. Choose the type of access you need: Select **Full Dropbox**. 3. Name your app: Enter an arbitrary string to identify your Dropbox app. 3. Click **Create app**. Dropbox displays the complete settings for your new app. 4. Under **OAuth 2** > **Generated access token**, click **Generate**. 5. Copy the new access token. 6. In Fusion UI, paste the access token into the **DROPBOX OAUTH ACCESS TOKEN** field of the Dropbox connector configuration panel. If you are using the REST API, this is the value of the property `f.fs.oAuthAccessToken`. ## 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.